Veröffentlichungen

2022   🔗

• Performance Evaluation of Open-Source Serverless Platforms for Kubernetes (Jonathan Decker, Piotr Kasprzak, Julian Kunkel), In Algorithms, MDPI, ISSN: 1999-4893, 2022-06-02 URL DOI PDF BIBTEX

  @article{PEOOSPFKDK22
  	abstract = {| Serverless computing has grown massively in popularity over the last few years, and has provided developers with a way to deploy function-sized code units  without having to take care of the actual servers or deal with logging,  monitoring, and scaling of their code. High-performance computing (HPC)  clusters can profit from improved serverless resource sharing capabilities  compared to reservation-based systems such as Slurm. However, before running  self-hosted serverless platforms in HPC becomes a viable option, serverless  platforms must be able to deliver a decent level of performance. Other  researchers have already pointed out that there is a distinct lack of studies  in the area of comparative benchmarks on serverless platforms, especially for  open-source self-hosted platforms. This study takes a step towards filling  this gap by systematically benchmarking two promising self-hosted Kubernetes- based serverless platforms in comparison. While the resulting benchmarks signal
   potential, they demonstrate that many opportunities for performance 
   improvements in serverless computing are being left on the table.}
  	author = {Jonathan Decker and Piotr Kasprzak and Julian Kunkel}
  	doi = {https://doi.org/10.3390/a15070234}
  	issn = {1999-4893}
  	journal = {Algorithms}
  	publisher = {MDPI}
  	title = {Performance Evaluation of Open-Source Serverless Platforms for Kubernetes}
  	url = {https://www.mdpi.com/1999-4893/15/7/234}
  	year = {2022}
  	month = {06}
  }

• Road Intersection Coordination Scheme for Mixed Traffic (Human-Driven and Driverless Vehicles): A Systematic Review (Ekene F. Ozioko, Julian Kunkel, Frederic Stahl), In Journal of Advanced Transportation, Hindawi, 2022-05-30 DOI PDF BIBTEX

  @article{RICSFMTADV22
  	abstract = {| Autonomous vehicles (AVs) are emerging with enormous potentials to solve many  challenging road traffic problems. The AV emergence leads to a paradigm shift  in the road traffic system, making the penetration of autonomous vehicles fast  and its coexistence with human-driven cars inevitable. The migration from the  traditional driving to the intelligent driving system with AV’s gradual  deployment needs supporting technology to address mixed traffic systems problems,  mixed driving behaviour in a car-following model, variation in-vehicle type  control means, the impact of a proportion of AV in traffic mixed traffic,  and many more. The migration to fully AV will solve many traffic problems:  desire to reclaim travel and commuting time, driving comfort, and accident  reduction. Motivated by the above facts, this paper presents an extensive  review of road intersection mixed traffic management techniques with a  classification matrix of different traffic management strategies and  technologies that could effectively describe a mix of human and autonomous  vehicles. It explores the existing traffic control strategies and analyses  their compatibility in a mixed traffic environment. Then review their drawback  and build on it for the proposed robust mix of traffic management schemes.  Though many traffic control strategies have been in existence, the analysis  presented in this paper gives new insights to the readers on the applications  of the cell reservation strategy in a mixed traffic environment. Though many  traffic control strategies have been in existence, the Gipp’s car-following  model has shown to be very effective for optimal traffic flow performance.}
  	author = {Ekene F. Ozioko and Julian Kunkel and Frederic Stahl}
  	doi = {https://doi.org/10.1155/2022/2951999}
  	journal = {Journal of Advanced Transportation}
  	publisher = {Hindawi}
  	title = {Road Intersection Coordination Scheme for Mixed Traffic (Human-Driven and Driverless Vehicles): A Systematic Review}
  	year = {2022}
  	month = {05}
  }

• Improve the Deep Learning Models in Forestry Based on Explanations and Expertise (Ximeng Cheng, Ali Doosthosseini, Julian Kunkel), In Frontiers in Plant Science, Schloss Dagstuhl -- Leibniz-Zentrum für Informatik, ISSN: 1664-462X, 2022-05-01 DOI PDF BIBTEX

  @article{ITDLMIFBOE22
  	abstract = {"In forestry studies, deep learning models have achieved excellent performance in many application scenarios (e.g., detecting forest damage). However, the unclear model decisions (i.e., black-box) undermine the credibility of the results and hinder their practicality. This study intends to obtain explanations of such models through the use of explainable artificial intelligence methods, and then use feature unlearning methods to improve their performance, which is the first such attempt in the field of forestry. Results of three experiments show that the model training can be guided by expertise to gain specific knowledge, which is reflected by explanations. For all three experiments based on synthetic and real leaf images, the improvement of models is quantified in the classification accuracy (up to 4.6%) and three indicators of explanation assessment (i.e., root-mean-square error, cosine similarity, and the proportion of important pixels). Besides, the introduced expertise in annotation matrix form was automatically created in all experiments. This study emphasizes that studies of deep learning in forestry should not only pursue model performance (e.g., higher classification accuracy) but also focus on the explanations and try to improve models according to the expertise."}
  	author = {Ximeng Cheng and Ali Doosthosseini and Julian Kunkel}
  	doi = {https://doi.org/10.3389/fpls.2022.902105}
  	issn = {1664-462X}
  	journal = {Frontiers in Plant Science}
  	publisher = {Schloss Dagstuhl -- Leibniz-Zentrum für Informatik}
  	title = {Improve the Deep Learning Models in Forestry Based on Explanations and Expertise}
  	year = {2022}
  	month = {05}
  }

• Predicting Stock Price Changes Based on the Limit Order Book: A Survey (Ilia Zaznov, Julian Kunkel, Alfonso Dufour, Atta Badii), In Mathematics, Series: 1234, MDPI, ISSN: 2227-7390, 2022-04-01 URL DOI PDF BIBTEX

  @article{PSPCBOTLOB22
  	abstract = {"This survey starts with a general overview of the strategies for stock price change predictions based on market data and in particular Limit Order Book (LOB) data. The main discussion is devoted to the systematic analysis, comparison, and critical evaluation of the state-of-the-art studies in the research area of stock price movement predictions based on LOB data. LOB and Order Flow data are two of the most valuable information sources available to traders on the stock markets. Academic researchers are actively exploring the application of different quantitative methods and algorithms for this type of data to predict stock price movements. With the advancements in machine learning and subsequently in deep learning, the complexity and computational intensity of these models was growing, as well as the claimed predictive power. Some researchers claim accuracy of stock price movement prediction well in excess of 80%. These models are now commonly employed by automated market-making programs to set bids and ask quotes. If these results were also applicable to arbitrage trading strategies, then those algorithms could make a fortune for their developers. Thus, the open question is whether these results could be used to generate buy and sell signals that could be exploited with active trading. Therefore, this survey paper is intended to answer this question by reviewing these results and scrutinising their reliability. The ultimate conclusion from this analysis is that although considerable progress was achieved in this direction, even the state-of-art models can not guarantee a consistent profit in active trading. Taking this into account several suggestions for future research in this area were formulated along the three dimensions: input data, model’s architecture, and experimental setup. In particular, from the input data perspective, it is critical that the dataset is properly processed, up-to-date, and its size is sufficient for the particular model training. From the model architecture perspective, even though deep learning models are demonstrating a stronger performance than classical models, they are also more prone to over-fitting. To avoid over-fitting it is suggested to optimize the feature space, as well as a number of layers and neurons, and apply dropout functionality. The over-fitting problem can be also addressed by optimising the experimental setup in several ways: Introducing the early stopping mechanism; Saving the best weights of the model achieved during the training; Testing the model on the out-of-sample data, which should be separated from the validation and training samples. Finally, it is suggested to always conduct the trading simulation under realistic market conditions considering transactions costs, bid–ask spreads, and market impact. View Full-Text"}
  	author = {Ilia Zaznov and Julian Kunkel and Alfonso Dufour and Atta Badii}
  	doi = {https://doi.org/10.3390/math10081234}
  	editor = {}
  	issn = {2227-7390}
  	journal = {Mathematics}
  	publisher = {MDPI}
  	series = {1234}
  	title = {Predicting Stock Price Changes Based on the Limit Order Book: A Survey}
  	url = {https://www.mdpi.com/2227-7390/10/8/1234}
  	year = {2022}
  	month = {04}
  }

• Performance Evaluation of Open-Source Serverless Platforms for Kubernetes (Jonathan Decker, Piotr Kasprzak, Julian Martin Kunkel), 2022-01-01 DOI PDF BIBTEX

  @article{PEOOSPFKDK22
  	abstract = {"Serverless computing has grown massively in popularity over the last few years, and has provided developers with a way to deploy function-sized code units without having to take care of the actual servers or deal with logging, monitoring, and scaling of their code. High-performance computing (HPC) clusters can profit from improved serverless resource sharing capabilities compared to reservation-based systems such as Slurm. However, before running self-hosted serverless platforms in HPC becomes a viable option, serverless platforms must be able to deliver a decent level of performance. Other researchers have already pointed out that there is a distinct lack of studies in the area of comparative benchmarks on serverless platforms, especially for open-source self-hosted platforms. This study takes a step towards filling this gap by systematically benchmarking two promising self-hosted Kubernetes-based serverless platforms in comparison. While the resulting benchmarks signal potential, they demonstrate that many opportunities for performance improvements in serverless computing are being left on the table."}
  	author = {Jonathan Decker and Piotr Kasprzak and Julian Martin Kunkel}
  	doi = {10.3390/a15070234}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/112598}
  	title = {Performance Evaluation of Open-Source Serverless Platforms for Kubernetes}
  	year = {2022}
  	month = {01}
  }

• Canonical Workflow for Experimental Research (Dirk Betz, Claudia Biniossek, Christophe Blanchi, Felix Henninger, Thomas Lauer, Philipp Wieder, Peter Wittenburg, Martin Zünkeler), 2022-01-01 DOI BIBTEX

  @article{2_121152
  	author = {Dirk Betz and Claudia Biniossek and Christophe Blanchi and Felix Henninger and Thomas Lauer and Philipp Wieder and Peter Wittenburg and Martin Zünkeler}
  	doi = {10.1162/dint_a_00123}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/121152}
  	title = {Canonical Workflow for Experimental Research}
  	year = {2022}
  	month = {01}
  }

• Predicting Stock Price Changes Based on the Limit Order Book: A Survey (Ilia Zaznov, Julian Kunkel, Alfonso Dufour, Atta Badii), 2022-01-01 DOI PDF BIBTEX

  @article{PSPCBOTLOB22
  	abstract = {"This survey starts with a general overview of the strategies for stock price change predictions based on market data and in particular Limit Order Book (LOB) data. The main discussion is devoted to the systematic analysis, comparison, and critical evaluation of the state-of-the-art studies in the research area of stock price movement predictions based on LOB data. LOB and Order Flow data are two of the most valuable information sources available to traders on the stock markets. Academic researchers are actively exploring the application of different quantitative methods and algorithms for this type of data to predict stock price movements. With the advancements in machine learning and subsequently in deep learning, the complexity and computational intensity of these models was growing, as well as the claimed predictive power. Some researchers claim accuracy of stock price movement prediction well in excess of 80%. These models are now commonly employed by automated market-making programs to set bids and ask quotes. If these results were also applicable to arbitrage trading strategies, then those algorithms could make a fortune for their developers. Thus, the open question is whether these results could be used to generate buy and sell signals that could be exploited with active trading. Therefore, this survey paper is intended to answer this question by reviewing these results and scrutinising their reliability. The ultimate conclusion from this analysis is that although considerable progress was achieved in this direction, even the state-of-art models can not guarantee a consistent profit in active trading. Taking this into account several suggestions for future research in this area were formulated along the three dimensions: input data, model’s architecture, and experimental setup. In particular, from the input data perspective, it is critical that the dataset is properly processed, up-to-date, and its size is sufficient for the particular model training. From the model architecture perspective, even though deep learning models are demonstrating a stronger performance than classical models, they are also more prone to over-fitting. To avoid over-fitting it is suggested to optimize the feature space, as well as a number of layers and neurons, and apply dropout functionality. The over-fitting problem can be also addressed by optimising the experimental setup in several ways: Introducing the early stopping mechanism; Saving the best weights of the model achieved during the training; Testing the model on the out-of-sample data, which should be separated from the validation and training samples. Finally, it is suggested to always conduct the trading simulation under realistic market conditions considering transactions costs, bid–ask spreads, and market impact."}
  	author = {Ilia Zaznov and Julian Kunkel and Alfonso Dufour and Atta Badii}
  	doi = {10.3390/math10081234}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/107425}
  	title = {Predicting Stock Price Changes Based on the Limit Order Book: A Survey}
  	year = {2022}
  	month = {01}
  }

• Realising Data-Centric Scientific Workflows with Provenance-Capturing on Data Lakes (Hendrik Nolte, Philipp Wieder), 2022-01-01 DOI BIBTEX

  @article{2_121151
  	author = {Hendrik Nolte and Philipp Wieder}
  	doi = {10.1162/dint_a_00141}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/121151}
  	title = {Realising Data-Centric Scientific Workflows with Provenance-Capturing on Data Lakes}
  	year = {2022}
  	month = {01}
  }

• Toward data lakes as central building blocks for data management and analysis (Philipp Wieder, Hendrik Nolte), 2022-01-01 DOI BIBTEX

  @article{2_114449
  	abstract = {"Data lakes are a fundamental building block for many industrial data analysis solutions and becoming increasingly popular in research. Often associated with big data use cases, data lakes are, for example, used as central data management systems of research institutions or as the core entity of machine learning pipelines. The basic underlying idea of retaining data in its native format within a data lake facilitates a large range of use cases and improves data reusability, especially when compared to the schema-on-write approach applied in data warehouses, where data is transformed prior to the actual storage to fit a predefined schema. Storing such massive amounts of raw data, however, has its very own challenges, spanning from the general data modeling, and indexing for concise querying to the integration of suitable and scalable compute capabilities. In this contribution, influential papers of the last decade have been selected to provide a comprehensive overview of developments and obtained results. The papers are analyzed with regard to the applicability of their input to data lakes that serve as central data management systems of research institutions. To achieve this, contributions to data lake architectures, metadata models, data provenance, workflow support, and FAIR principles are investigated. Last, but not least, these capabilities are mapped onto the requirements of two common research personae to identify open challenges. With that, potential research topics are determined, which have to be tackled toward the applicability of data lakes as central building blocks for research data management."}
  	author = {Philipp Wieder and Hendrik Nolte}
  	doi = {10.3389/fdata.2022.945720}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/114449}
  	title = {Toward data lakes as central building blocks for data management and analysis}
  	year = {2022}
  	month = {01}
  }

• Road Intersection Coordination Scheme for Mixed Traffic (Human-Driven and Driverless Vehicles): A Systematic Review (Ekene F. Ozioko, Julian Kunkel, Fredric Stahl), 2022-01-01 DOI PDF BIBTEX

  @article{RICSFMTADV22
  	abstract = {"Autonomous vehicles (AVs) are emerging with enormous potentials to solve many challenging road traffic problems. The AV emergence leads to a paradigm shift in the road traffic system, making the penetration of autonomous vehicles fast and its coexistence with human-driven cars inevitable. The migration from the traditional driving to the intelligent driving system with AV’s gradual deployment needs supporting technology to address mixed traffic systems problems, mixed driving behaviour in a car-following model, variation in-vehicle type control means, the impact of a proportion of AV in traffic mixed traffic, and many more. The migration to fully AV will solve many traffic problems: desire to reclaim travel and commuting time, driving comfort, and accident reduction. Motivated by the above facts, this paper presents an extensive review of road intersection mixed traffic management techniques with a classification matrix of different traffic management strategies and technologies that could effectively describe a mix of human and autonomous vehicles. It explores the existing traffic control strategies and analyses their compatibility in a mixed traffic environment. Then review their drawback and build on it for the proposed robust mix of traffic management schemes. Though many traffic control strategies have been in existence, the analysis presented in this paper gives new insights to the readers on the applications of the cell reservation strategy in a mixed traffic environment. Though many traffic control strategies have been in existence, the Gipp’s car-following model has shown to be very effective for optimal traffic flow performance."}
  	author = {Ekene F. Ozioko and Julian Kunkel and Fredric Stahl}
  	doi = {10.1155/2022/2951999}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/113814}
  	title = {Road Intersection Coordination Scheme for Mixed Traffic (Human-Driven and Driverless Vehicles): A Systematic Review}
  	year = {2022}
  	month = {01}
  }

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

2018   🔗

• NEPHELE: An End-to-End Scalable and Dynamically Reconfigurable Optical Architecture for Application-Aware SDN Cloud Data Centers (Paraskevas Bakopoulos, Konstantinos Christodoulopoulos, Giada Landi, Muzzamil Aziz, Eitan Zahavi, Domenico Gallico, Richard Pitwon, Konstantinos Tokas, Ioannis Patronas, Marco Capitani, Christos Spatharakis, Konstantinos Yiannopoulos, Kai Wang, Konstantinos Kontodimas, Ioannis Lazarou, Philipp Wieder, Dionysios I. Reisis, Emmanouel Manos Varvarigos, Matteo Biancani, Hercules Avramopoulos), 2018-01-01 DOI BIBTEX

  @article{2_90984
  	author = {Paraskevas Bakopoulos and Konstantinos Christodoulopoulos and Giada Landi and Muzzamil Aziz and Eitan Zahavi and Domenico Gallico and Richard Pitwon and Konstantinos Tokas and Ioannis Patronas and Marco Capitani and Christos Spatharakis and Konstantinos Yiannopoulos and Kai Wang and Konstantinos Kontodimas and Ioannis Lazarou and Philipp Wieder and Dionysios I. Reisis and Emmanouel Manos Varvarigos and Matteo Biancani and Hercules Avramopoulos}
  	doi = {10.1109/MCOM.2018.1600804}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/90984}
  	title = {NEPHELE: An End-to-End Scalable and Dynamically Reconfigurable Optical Architecture for Application-Aware SDN Cloud Data Centers}
  	year = {2018}
  	month = {01}
  }

• Latency-Sensitive Data Allocation and Workload Consolidation for Cloud Storage (Song Yang, Philipp Wieder, Muzzamil Aziz, Ramin Yahyapour, Xiaoming Fu, Xu Chen), 2018-01-01 DOI BIBTEX

  @article{2_93400
  	abstract = {"Customers often suffer from the variability of data access time in (edge) cloud storage service, caused by network congestion, load dynamics, and so on. One ef cient solution to guarantee a reliable latency-sensitive service (e.g., for industrial Internet of Things application) is to issue requests with multiple download/upload sessions which access the required data (replicas) stored in one or more servers, and use the earliest response from those sessions. In order to minimize the total storage costs, how to optimally allocate data in a minimum number of servers without violating latency guarantees remains to be a crucial issue for the cloud provider to deal with. In this paper, we study the latency-sensitive data allocation problem, the latency-sensitive data reallocation problem and the latency-sensitive workload consolidation problem for cloud storage. We model the data access time as a given distribution whose cumulative density function is known, and prove that these three problems are NP-hard. To solve them, we propose an exact integer nonlinear program (INLP) and a Tabu Search-based heuristic. The simulation results reveal that the INLP can always achieve the best performance in terms of lower number of used nodes and higher storage and throughput utilization, but this comes at the expense of much higher running time. The Tabu Searchbased heuristic, on the other hand, can obtain close-to-optimal performance, but in a much lower running time."}
  	author = {Song Yang and Philipp Wieder and Muzzamil Aziz and Ramin Yahyapour and Xiaoming Fu and Xu Chen}
  	doi = {10.1109/ACCESS.2018.2883674}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/93400}
  	title = {Latency-Sensitive Data Allocation and Workload Consolidation for Cloud Storage}
  	year = {2018}
  	month = {01}
  }

2017   🔗

• Latency-Sensitive Data Allocation for cloud storage (Song Yang, Philipp Wieder, Muzzamil Aziz, Ramin Yahyapour, Xiaoming Fu), In 2017 IFIP/IEEE Symposium on Integrated Network and Service Management (IM), 2017-01-01 DOI BIBTEX

  @inproceedings{2_13221
  	abstract = {"Customers often suffer from the variability of data access time in cloud storage service, caused by network congestion, load dynamics, etc. One solution to guarantee a reliable latency-sensitive service is to issue requests with multiple download/upload sessions, accessing the required data (replicas) stored in one or more servers. In order to minimize storage costs, how to optimally allocate data in a minimum number of servers without violating latency guarantees remains to be a crucial issue for the cloud provider to tackle. In this paper, we study the latency-sensitive data allocation problem for cloud storage. We model the data access time as a given distribution whose Cumulative Density Function (CDF) is known, and prove that this problem is NP-hard. To solve it, we propose both exact Integer Nonlinear Program (INLP) and Tabu Search-based heuristic. The proposed algorithms are evaluated in terms of the number of used servers, storage utilization and throughput utilization."}
  	author = {Song Yang and Philipp Wieder and Muzzamil Aziz and Ramin Yahyapour and Xiaoming Fu}
  	doi = {10.23919/INM.2017.7987258}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/13221}
  	journal = {2017 IFIP/IEEE Symposium on Integrated Network and Service Management (IM)}
  	title = {Latency-Sensitive Data Allocation for cloud storage}
  	year = {2017}
  	month = {01}
  }

2016   🔗

• SDN-enabled application-aware networking for data center networks (Muzzamil Aziz, H. Amirreza Fazely, Giada Landi, Domenico Gallico, Kostas Christodoulopoulos, Philipp Wieder), 2016-01-01 DOI BIBTEX

  @inproceedings{2_90983
  	author = {Muzzamil Aziz and H. Amirreza Fazely and Giada Landi and Domenico Gallico and Kostas Christodoulopoulos and Philipp Wieder}
  	doi = {10.1109/ICECS.2016.7841210}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/90983}
  	title = {SDN-enabled application-aware networking for data center networks}
  	year = {2016}
  	month = {01}
  }

Veröffentlichungen

2021   🔗

• An Optimized Single Sign-On Schema for Reliable Multi -Level Security Management in Clouds (Aytaj Badirova, Shirin Dabbaghi, Faraz Fatemi-Moghaddam, Philipp Wieder, Ramin Yahyapour), In Proceedings of FiCloud 2021 – 8th International Conference on Future Internet of Things and Cloud, 2021-01-01 DOI BIBTEX

  @inproceedings{2_121153
  	author = {Aytaj Badirova and Shirin Dabbaghi and Faraz Fatemi-Moghaddam and Philipp Wieder and Ramin Yahyapour}
  	doi = {10.1109/FiCloud49777.2021.00014}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/121153}
  	journal = {Proceedings of FiCloud 2021 – 8th International Conference on Future Internet of Things and Cloud}
  	title = {An Optimized Single Sign-On Schema for Reliable Multi -Level Security Management in Clouds}
  	year = {2021}
  	month = {01}
  }

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

2019   🔗

• A Graph Database for Persistent Identifiers (Triet Doan, Sven Bingert, Lena Wiese, Ramin Yahyapour), In Proceedings of the Conference on "Lernen, Wissen, Daten, Analysen", 2019-01-01 DOI BIBTEX

  @inproceedings{2_91394
  	author = {Triet Doan and Sven Bingert and Lena Wiese and Ramin Yahyapour}
  	doi = {10.15488/9817}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/91394}
  	journal = {Proceedings of the Conference on "Lernen, Wissen, Daten, Analysen"}
  	title = {A Graph Database for Persistent Identifiers}
  	year = {2019}
  	month = {01}
  }

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

2020   🔗

• OCR-D kompakt: Ergebnisse und Stand der Forschung in der Förderinitiative (Konstantin Baierer, Matthias Boenig, Elisabeth Engl, Clemens Neudecker, Reinhard Altenhöner, Alexander Geyken, Johannes Mangei, Rainer Stotzka, Andreas Dengel, Martin Jenckel, Alexander Gehrke, Frank Puppe, Stefan Weil, Robert Sachunsky, Lena K. Schiffer, Maciej Janicki, Gerhard Heyer, Florian Fink, Klaus U. Schulz, Nikolaus Weichselbaumer, Saskia Limbach, Mathias Seuret, Rui Dong, Manuel Burghardt, Vincent Christlein, Triet Ho Anh Doan, Zeki Mustafa Dogan, Jörg-Holger Panzer, Kristine Schima-Voigt, Philipp Wieder), 2020-01-01 URL DOI BIBTEX

  @misc{2_121682
  	abstract = {"Bereits seit einigen Jahren werden große Anstrengungen unternommen, um die im deutschen Sprachraum erschienenen Drucke des 16.-18. Jahrhunderts zu erfassen und zu digitalisieren. Deren Volltexttransformation konzeptionell und technisch vorzubereiten, ist das übergeordnete Ziel des DFG-Projekts OCR-D, das sich mit der Weiterentwicklung von Verfahren der Optical Character Recognition befasst. Der Beitrag beschreibt den aktuellen Entwicklungsstand der OCR-D-Software und analysiert deren erste Teststellung in ausgewählten Bibliotheken."}
  	author = {Konstantin Baierer and Matthias Boenig and Elisabeth Engl and Clemens Neudecker and Reinhard Altenhöner and Alexander Geyken and Johannes Mangei and Rainer Stotzka and Andreas Dengel and Martin Jenckel and Alexander Gehrke and Frank Puppe and Stefan Weil and Robert Sachunsky and Lena K. Schiffer and Maciej Janicki and Gerhard Heyer and Florian Fink and Klaus U. Schulz and Nikolaus Weichselbaumer and Saskia Limbach and Mathias Seuret and Rui Dong and Manuel Burghardt and Vincent Christlein and Triet Ho Anh Doan and Zeki Mustafa Dogan and Jörg-Holger Panzer and Kristine Schima-Voigt and Philipp Wieder}
  	doi = {10.18452/21548}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/121682}
  	title = {OCR-D kompakt: Ergebnisse und Stand der Forschung in der Förderinitiative}
  	url = {https://publications.goettingen-research-online.de/handle/2/116509}
  	year = {2020}
  	month = {01}
  }

• OLA-HD – Ein OCR-D-Langzeitarchiv für historische Drucke (Triet Ho Anh Doan, Zeki Mustafa Doğan, Jörg-Holger Panzer, Kristine Schima-Voigt, Philipp Wieder), 2020-01-01 DOI BIBTEX

  @article{2_116509
  	author = {Triet Ho Anh Doan and Zeki Mustafa Doğan and Jörg-Holger Panzer and Kristine Schima-Voigt and Philipp Wieder}
  	doi = {10.18452/21548}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/116509}
  	title = {OLA-HD – Ein OCR-D-Langzeitarchiv für historische Drucke}
  	year = {2020}
  	month = {01}
  }

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

2016   🔗

• Butterfly-like Algorithms for GASPI Split Phase Allreduce (Vanessa End, Ramin Yahyapour, Thomas Alrutz, Christian Simmendinger), 2016-01-01 BIBTEX

  @article{2_57535
  	abstract = {"Collective communication routines pose a significant bottleneck of highly parallel programs. Research on different algorithms for disseminating information among all participat- ing processes in a collective communication has brought forth many different algorithms, some of which have a butterfly- like communication scheme. While these algorithms have been abandoned from usage in collective communication routines with larger messages, due to the congestion that arises from their use, these algorithms have ideal properties for split-phase allreduce routines: all processes are involved in the computation of the result in each communication round and they have few communication rounds. This article will present several different algorithms with a butterfly-like communication scheme and examine their usability for a GASPI allreduce library routine. The library routines will be compared to state-of-the-art MPI implementations and also to a tree-based allreduce algorithm."}
  	author = {Vanessa End and Ramin Yahyapour and Thomas Alrutz and Christian Simmendinger}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/57535}
  	title = {Butterfly-like Algorithms for GASPI Split Phase Allreduce}
  	year = {2016}
  	month = {01}
  }

2015   🔗

• Adaption of the n-way Dissemination Algorithm for GASPI Split-Phase Allreduce (Vanessa End, Ramin Yahyapour, Christian Simmendinger, Thomas Alrutz), In The Fifth International Conference on Advanced Communications and Computation (INFOCOMP 2015), 2015-01-01 BIBTEX

  @inproceedings{2_57541
  	abstract = {"This paper presents an adaption of the n-way dissemination algorithm, such that it can be used for an allreduce operation, which is - together with the barrier operation - one of the most time consuming collective communication routines available in most parallel communication interfaces and libraries. Thus, a fast underlying algorithm with few communication rounds is needed. The dissemination algorithm is such an algorithm and already used for a variety of barrier implementations due to its speed. Yet, this algorithm is also interesting for the split-phase allreduce operations, as defined in the Global Address Space Programming Interface (GASPI) specification, due to its small number of communication rounds. Even though it is a butterflylike algorithm, significant improvements in runtime are seen when comparing this implementation on top of ibverbs to different message-passing interface (MPI) implementations, which are the de facto standard for distributed memory computing."}
  	address = {Red Hook, USA}
  	author = {Vanessa End and Ramin Yahyapour and Christian Simmendinger and Thomas Alrutz}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/57541}
  	journal = {The Fifth International Conference on Advanced Communications and Computation (INFOCOMP 2015)}
  	title = {Adaption of the n-way Dissemination Algorithm for GASPI Split-Phase Allreduce}
  	year = {2015}
  	month = {01}
  }

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

2020   🔗

• menoci: Lightweight Extensible Web Portal enabling FAIR Data Management for Biomedical Research Projects (Markus Suhr, Christoph Lehmann, Christian Robert Bauer, Theresa Bender, Cornelius Knopp, Luca Freckmann, Björn Öst Hansen, Christian Henke, Georg Aschenbrandt, Lea Katharina Kühlborn, Sophia Rheinländer, Linus Weber, Bartlomiej Marzec, Marcel Hellkamp, Philipp Wieder, Harald Kusch, Ulrich Sax, Sara Yasemin Nussbeck), 2020-01-01 URL BIBTEX

  @misc{2_63412
  	abstract = {"Background: Biomedical research projects deal with data management requirements from multiple sources like funding agencies' guidelines, publisher policies, discipline best practices, and their own users' needs. We describe functional and quality requirements based on many years of experience implementing data management for the CRC 1002 and CRC 1190. A fully equipped data management software should improve documentation of experiments and materials, enable data storage and sharing according to the FAIR Guiding Principles while maximizing usability, information security, as well as software sustainability and reusability. Results: We introduce the modular web portal software menoci for data collection, experiment documentation, data publication, sharing, and preservation in biomedical research projects. Menoci modules are based on the Drupal content management system which enables lightweight deployment and setup, and creates the possibility to combine research data management with a customisable project home page or collaboration platform. Conclusions: Management of research data and digital research artefacts is transforming from individual researcher or groups best practices towards project- or organisation-wide service infrastructures. To enable and support this structural transformation process, a vital ecosystem of open source software tools is needed. Menoci is a contribution to this ecosystem of research data management tools that is specifically designed to support biomedical research projects."}
  	author = {Markus Suhr and Christoph Lehmann and Christian Robert Bauer and Theresa Bender and Cornelius Knopp and Luca Freckmann and Björn Öst Hansen and Christian Henke and Georg Aschenbrandt and Lea Katharina Kühlborn and Sophia Rheinländer and Linus Weber and Bartlomiej Marzec and Marcel Hellkamp and Philipp Wieder and Harald Kusch and Ulrich Sax and Sara Yasemin Nussbeck}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/63412}
  	title = {menoci: Lightweight Extensible Web Portal enabling FAIR Data Management for Biomedical Research Projects}
  	url = {https://sfb1190.med.uni-goettingen.de/production/literature/publications/106}
  	year = {2020}
  	month = {01}
  }

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

2022   🔗

• Performance Evaluation of Open-Source Serverless Platforms for Kubernetes (Jonathan Decker, Piotr Kasprzak, Julian Kunkel), In Algorithms, MDPI, ISSN: 1999-4893, 2022-06-02 URL DOI PDF BIBTEX

  @article{PEOOSPFKDK22
  	abstract = {| Serverless computing has grown massively in popularity over the last few years, and has provided developers with a way to deploy function-sized code units  without having to take care of the actual servers or deal with logging,  monitoring, and scaling of their code. High-performance computing (HPC)  clusters can profit from improved serverless resource sharing capabilities  compared to reservation-based systems such as Slurm. However, before running  self-hosted serverless platforms in HPC becomes a viable option, serverless  platforms must be able to deliver a decent level of performance. Other  researchers have already pointed out that there is a distinct lack of studies  in the area of comparative benchmarks on serverless platforms, especially for  open-source self-hosted platforms. This study takes a step towards filling  this gap by systematically benchmarking two promising self-hosted Kubernetes- based serverless platforms in comparison. While the resulting benchmarks signal
   potential, they demonstrate that many opportunities for performance 
   improvements in serverless computing are being left on the table.}
  	author = {Jonathan Decker and Piotr Kasprzak and Julian Kunkel}
  	doi = {https://doi.org/10.3390/a15070234}
  	issn = {1999-4893}
  	journal = {Algorithms}
  	publisher = {MDPI}
  	title = {Performance Evaluation of Open-Source Serverless Platforms for Kubernetes}
  	url = {https://www.mdpi.com/1999-4893/15/7/234}
  	year = {2022}
  	month = {06}
  }

• Road Intersection Coordination Scheme for Mixed Traffic (Human-Driven and Driverless Vehicles): A Systematic Review (Ekene F. Ozioko, Julian Kunkel, Frederic Stahl), In Journal of Advanced Transportation, Hindawi, 2022-05-30 DOI PDF BIBTEX

  @article{RICSFMTADV22
  	abstract = {| Autonomous vehicles (AVs) are emerging with enormous potentials to solve many  challenging road traffic problems. The AV emergence leads to a paradigm shift  in the road traffic system, making the penetration of autonomous vehicles fast  and its coexistence with human-driven cars inevitable. The migration from the  traditional driving to the intelligent driving system with AV’s gradual  deployment needs supporting technology to address mixed traffic systems problems,  mixed driving behaviour in a car-following model, variation in-vehicle type  control means, the impact of a proportion of AV in traffic mixed traffic,  and many more. The migration to fully AV will solve many traffic problems:  desire to reclaim travel and commuting time, driving comfort, and accident  reduction. Motivated by the above facts, this paper presents an extensive  review of road intersection mixed traffic management techniques with a  classification matrix of different traffic management strategies and  technologies that could effectively describe a mix of human and autonomous  vehicles. It explores the existing traffic control strategies and analyses  their compatibility in a mixed traffic environment. Then review their drawback  and build on it for the proposed robust mix of traffic management schemes.  Though many traffic control strategies have been in existence, the analysis  presented in this paper gives new insights to the readers on the applications  of the cell reservation strategy in a mixed traffic environment. Though many  traffic control strategies have been in existence, the Gipp’s car-following  model has shown to be very effective for optimal traffic flow performance.}
  	author = {Ekene F. Ozioko and Julian Kunkel and Frederic Stahl}
  	doi = {https://doi.org/10.1155/2022/2951999}
  	journal = {Journal of Advanced Transportation}
  	publisher = {Hindawi}
  	title = {Road Intersection Coordination Scheme for Mixed Traffic (Human-Driven and Driverless Vehicles): A Systematic Review}
  	year = {2022}
  	month = {05}
  }

• Improve the Deep Learning Models in Forestry Based on Explanations and Expertise (Ximeng Cheng, Ali Doosthosseini, Julian Kunkel), In Frontiers in Plant Science, Schloss Dagstuhl -- Leibniz-Zentrum für Informatik, ISSN: 1664-462X, 2022-05-01 DOI PDF BIBTEX

  @article{ITDLMIFBOE22
  	abstract = {"In forestry studies, deep learning models have achieved excellent performance in many application scenarios (e.g., detecting forest damage). However, the unclear model decisions (i.e., black-box) undermine the credibility of the results and hinder their practicality. This study intends to obtain explanations of such models through the use of explainable artificial intelligence methods, and then use feature unlearning methods to improve their performance, which is the first such attempt in the field of forestry. Results of three experiments show that the model training can be guided by expertise to gain specific knowledge, which is reflected by explanations. For all three experiments based on synthetic and real leaf images, the improvement of models is quantified in the classification accuracy (up to 4.6%) and three indicators of explanation assessment (i.e., root-mean-square error, cosine similarity, and the proportion of important pixels). Besides, the introduced expertise in annotation matrix form was automatically created in all experiments. This study emphasizes that studies of deep learning in forestry should not only pursue model performance (e.g., higher classification accuracy) but also focus on the explanations and try to improve models according to the expertise."}
  	author = {Ximeng Cheng and Ali Doosthosseini and Julian Kunkel}
  	doi = {https://doi.org/10.3389/fpls.2022.902105}
  	issn = {1664-462X}
  	journal = {Frontiers in Plant Science}
  	publisher = {Schloss Dagstuhl -- Leibniz-Zentrum für Informatik}
  	title = {Improve the Deep Learning Models in Forestry Based on Explanations and Expertise}
  	year = {2022}
  	month = {05}
  }

• Predicting Stock Price Changes Based on the Limit Order Book: A Survey (Ilia Zaznov, Julian Kunkel, Alfonso Dufour, Atta Badii), In Mathematics, Series: 1234, MDPI, ISSN: 2227-7390, 2022-04-01 URL DOI PDF BIBTEX

  @article{PSPCBOTLOB22
  	abstract = {"This survey starts with a general overview of the strategies for stock price change predictions based on market data and in particular Limit Order Book (LOB) data. The main discussion is devoted to the systematic analysis, comparison, and critical evaluation of the state-of-the-art studies in the research area of stock price movement predictions based on LOB data. LOB and Order Flow data are two of the most valuable information sources available to traders on the stock markets. Academic researchers are actively exploring the application of different quantitative methods and algorithms for this type of data to predict stock price movements. With the advancements in machine learning and subsequently in deep learning, the complexity and computational intensity of these models was growing, as well as the claimed predictive power. Some researchers claim accuracy of stock price movement prediction well in excess of 80%. These models are now commonly employed by automated market-making programs to set bids and ask quotes. If these results were also applicable to arbitrage trading strategies, then those algorithms could make a fortune for their developers. Thus, the open question is whether these results could be used to generate buy and sell signals that could be exploited with active trading. Therefore, this survey paper is intended to answer this question by reviewing these results and scrutinising their reliability. The ultimate conclusion from this analysis is that although considerable progress was achieved in this direction, even the state-of-art models can not guarantee a consistent profit in active trading. Taking this into account several suggestions for future research in this area were formulated along the three dimensions: input data, model’s architecture, and experimental setup. In particular, from the input data perspective, it is critical that the dataset is properly processed, up-to-date, and its size is sufficient for the particular model training. From the model architecture perspective, even though deep learning models are demonstrating a stronger performance than classical models, they are also more prone to over-fitting. To avoid over-fitting it is suggested to optimize the feature space, as well as a number of layers and neurons, and apply dropout functionality. The over-fitting problem can be also addressed by optimising the experimental setup in several ways: Introducing the early stopping mechanism; Saving the best weights of the model achieved during the training; Testing the model on the out-of-sample data, which should be separated from the validation and training samples. Finally, it is suggested to always conduct the trading simulation under realistic market conditions considering transactions costs, bid–ask spreads, and market impact. View Full-Text"}
  	author = {Ilia Zaznov and Julian Kunkel and Alfonso Dufour and Atta Badii}
  	doi = {https://doi.org/10.3390/math10081234}
  	editor = {}
  	issn = {2227-7390}
  	journal = {Mathematics}
  	publisher = {MDPI}
  	series = {1234}
  	title = {Predicting Stock Price Changes Based on the Limit Order Book: A Survey}
  	url = {https://www.mdpi.com/2227-7390/10/8/1234}
  	year = {2022}
  	month = {04}
  }

• Predicting Stock Price Changes Based on the Limit Order Book: A Survey (Ilia Zaznov, Julian Kunkel, Alfonso Dufour, Atta Badii), 2022-01-01 DOI PDF BIBTEX

  @article{PSPCBOTLOB22
  	abstract = {"This survey starts with a general overview of the strategies for stock price change predictions based on market data and in particular Limit Order Book (LOB) data. The main discussion is devoted to the systematic analysis, comparison, and critical evaluation of the state-of-the-art studies in the research area of stock price movement predictions based on LOB data. LOB and Order Flow data are two of the most valuable information sources available to traders on the stock markets. Academic researchers are actively exploring the application of different quantitative methods and algorithms for this type of data to predict stock price movements. With the advancements in machine learning and subsequently in deep learning, the complexity and computational intensity of these models was growing, as well as the claimed predictive power. Some researchers claim accuracy of stock price movement prediction well in excess of 80%. These models are now commonly employed by automated market-making programs to set bids and ask quotes. If these results were also applicable to arbitrage trading strategies, then those algorithms could make a fortune for their developers. Thus, the open question is whether these results could be used to generate buy and sell signals that could be exploited with active trading. Therefore, this survey paper is intended to answer this question by reviewing these results and scrutinising their reliability. The ultimate conclusion from this analysis is that although considerable progress was achieved in this direction, even the state-of-art models can not guarantee a consistent profit in active trading. Taking this into account several suggestions for future research in this area were formulated along the three dimensions: input data, model’s architecture, and experimental setup. In particular, from the input data perspective, it is critical that the dataset is properly processed, up-to-date, and its size is sufficient for the particular model training. From the model architecture perspective, even though deep learning models are demonstrating a stronger performance than classical models, they are also more prone to over-fitting. To avoid over-fitting it is suggested to optimize the feature space, as well as a number of layers and neurons, and apply dropout functionality. The over-fitting problem can be also addressed by optimising the experimental setup in several ways: Introducing the early stopping mechanism; Saving the best weights of the model achieved during the training; Testing the model on the out-of-sample data, which should be separated from the validation and training samples. Finally, it is suggested to always conduct the trading simulation under realistic market conditions considering transactions costs, bid–ask spreads, and market impact."}
  	author = {Ilia Zaznov and Julian Kunkel and Alfonso Dufour and Atta Badii}
  	doi = {10.3390/math10081234}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/107425}
  	title = {Predicting Stock Price Changes Based on the Limit Order Book: A Survey}
  	year = {2022}
  	month = {01}
  }

• Road Intersection Coordination Scheme for Mixed Traffic (Human-Driven and Driverless Vehicles): A Systematic Review (Ekene F. Ozioko, Julian Kunkel, Fredric Stahl), 2022-01-01 DOI PDF BIBTEX

  @article{RICSFMTADV22
  	abstract = {"Autonomous vehicles (AVs) are emerging with enormous potentials to solve many challenging road traffic problems. The AV emergence leads to a paradigm shift in the road traffic system, making the penetration of autonomous vehicles fast and its coexistence with human-driven cars inevitable. The migration from the traditional driving to the intelligent driving system with AV’s gradual deployment needs supporting technology to address mixed traffic systems problems, mixed driving behaviour in a car-following model, variation in-vehicle type control means, the impact of a proportion of AV in traffic mixed traffic, and many more. The migration to fully AV will solve many traffic problems: desire to reclaim travel and commuting time, driving comfort, and accident reduction. Motivated by the above facts, this paper presents an extensive review of road intersection mixed traffic management techniques with a classification matrix of different traffic management strategies and technologies that could effectively describe a mix of human and autonomous vehicles. It explores the existing traffic control strategies and analyses their compatibility in a mixed traffic environment. Then review their drawback and build on it for the proposed robust mix of traffic management schemes. Though many traffic control strategies have been in existence, the analysis presented in this paper gives new insights to the readers on the applications of the cell reservation strategy in a mixed traffic environment. Though many traffic control strategies have been in existence, the Gipp’s car-following model has shown to be very effective for optimal traffic flow performance."}
  	author = {Ekene F. Ozioko and Julian Kunkel and Fredric Stahl}
  	doi = {10.1155/2022/2951999}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/113814}
  	title = {Road Intersection Coordination Scheme for Mixed Traffic (Human-Driven and Driverless Vehicles): A Systematic Review}
  	year = {2022}
  	month = {01}
  }

2021   🔗

• User-Centric System Fault Identification Using IO500 Benchmark (Radita Liem, Dmytro Povaliaiev, Jay Lofstead, Julian Kunkel, Christian Terboven), pp. 35-40, IEEE, 2021-12-01 DOI PDF BIBTEX

  @inproceedings{USFIUIBLPL21
  	abstract = {"I/O performance in a multi-user environment is difficult to predict. Users do not know what I/O performance to expect when running and tuning applications. We propose to use the IO500 benchmark as a way to guide user expectations on their application’s performance and to aid identifying root causes of their I/O problems that might come from the system. Our experiments describe how we manage user expectation with IO500 and provide a mechanism for system fault identification. This work also provides us with information of the tail latency problem that needs to be addressed and granular information about the impact of I/O technique choices (POSIX and MPI-IO)."}
  	author = {Radita Liem and Dmytro Povaliaiev and Jay Lofstead and Julian Kunkel and Christian Terboven}
  	booktitle = {In 2021 IEEE/ACM Sixth International Parallel Data Systems Workshop (PDSW)}
  	conference = {International Parallel Data Systems Workshop (PDSW)}
  	doi = {https://doi.org/10.1109/PDSW54622.2021.00011}
  	editor = {}
  	location = {St. Louis}
  	pages = {35-40}
  	publisher = {IEEE}
  	title = {User-Centric System Fault Identification Using IO500 Benchmark}
  	year = {2021}
  	month = {12}
  }

• Toward a Workflow for Identifying Jobs with Similar I/O Behavior Utilizing Time Series Analysis (Julian Kunkel, Eugen Betke), Series: Lecture Notes in Computer Science, pp. 161–173, Springer, 2021-11-01 DOI PDF BIBTEX

  @inproceedings{TAWFIJWSIB21
  	abstract = {"One goal of support staff at a data center is to identify inefficient jobs and to improve their efficiency. Therefore, a data center deploys monitoring systems that capture the behavior of the executed jobs. While it is easy to utilize statistics to rank jobs based on the utilization of computing, storage, and network, it is tricky to find patterns in 100,000 jobs, i.e., is there a class of jobs that aren't performing well. Similarly, when support staff investigates a specific job in detail, e.g., because it is inefficient or highly efficient, it is relevant to identify related jobs to such a blueprint. This allows staff to understand the usage of the exhibited behavior better and to assess the optimization potential. In this article, our goal is to identify jobs similar to an arbitrary reference job. In particular, we sketch a methodology that utilizes temporal I/O similarity to identify jobs related to the reference job. Practically, we apply several previously developed time series algorithms. A study is conducted to explore the effectiveness of the approach by investigating related jobs for a  reference job. The data stem from DKRZ's supercomputer Mistral and include more than 500,000 jobs that have been executed for more than 6 months of operation. Our analysis shows that the strategy and algorithms bear the potential to identify similar jobs, but more testing is necessary."}
  	author = {Julian Kunkel and Eugen Betke}
  	booktitle = {High Performance Computing: ISC High Performance 2021 International Workshops, Revised Selected Papers}
  	conference = {ISC HPC}
  	doi = {https://doi.org/10.1007/978-3-030-90539-2_10}
  	editor = {}
  	isbn = {978-3-030-90539-2}
  	location = {Frankfurt, Germany}
  	number = {12761}
  	pages = {161–173}
  	publisher = {Springer}
  	series = {Lecture Notes in Computer Science}
  	title = {Toward a Workflow for Identifying Jobs with Similar I/O Behavior Utilizing Time Series Analysis}
  	year = {2021}
  	month = {11}
  }

• Analyzing the Performance of the S3 Object Storage API for HPC Workloads (Frank Gadban, Julian Kunkel), In Applied Sciences, Series: 11, MDPI, 2021-09-14 URL DOI PDF BIBTEX

  @article{ATPOTSOSAF21
  	abstract = {| The line between HPC and Cloud is getting blurry: Performance is still the  main driver in HPC, while cloud storage systems are assumed to offer low  latency, high throughput, high availability, and scalability. The Simple  Storage Service S3 has emerged as the de facto storage API for object  storage in the Cloud. This paper seeks to check if the S3 API is already a  viable alternative for HPC access patterns in terms of performance or if  further performance advancements are necessary. For this purpose: (a) We  extend two common HPC I/O benchmarks—the IO500 and MD-Workbench—to quantify  the performance of the S3 API. We perform the analysis on the Mistral  supercomputer by launching the enhanced benchmarks against different S3  implementations: on-premises (Swift, MinIO) and in the Cloud (Google,  IBM. . . ). We find that these implementations do not yet meet the demanding  performance and scalability expectations of HPC workloads. (b) We aim to  identify the cause for the performance loss by systematically replacing  parts of a popular S3 client library with lightweight replacements of lower  stack components. The created S3Embedded library is highly scalable and  leverages the shared cluster file systems of HPC infrastructure to  accommodate arbitrary S3 client applications. Another introduced library,  S3remote, uses TCP/IP for communication instead of HTTP; it provides a  single local S3 gateway on each node. By broadening the scope of the IO500,  this research enables the community to track the performance growth of S3  and encourage sharing best practices for performance optimization. The  analysis also proves that there can be a performance convergence—at the  storage level—between Cloud and HPC over time by using a high-performance  S3 library like S3Embedded.}
  	author = {Frank Gadban and Julian Kunkel}
  	doi = {https://doi.org/10.3390/app11188540}
  	journal = {Applied Sciences}
  	publisher = {MDPI}
  	series = {11}
  	title = {Analyzing the Performance of the S3 Object Storage API for HPC Workloads}
  	url = {https://www.mdpi.com/2076-3417/11/18/8540}
  	year = {2021}
  	month = {09}
  }

• Understanding I/O Behavior in Scientific and Data-Intensive Computing (Dagstuhl Seminar 21332) (Philip Carns, Julian Kunkel, Kathryn Mohror, Martin Schulz), In Dagstuhl Reports, pp. 16-75, Schloss Dagstuhl -- Leibniz-Zentrum für Informatik, ISSN: 2192-5283, 2021-09-14 URL DOI PDF BIBTEX

  @article{UIBISADCSC21
  	abstract = {| Two key changes are driving an immediate need for deeper understanding of I/O  workloads in high-performance computing (HPC): applications are evolving beyond  the traditional bulk-synchronous models to include integrated multistep workflows,  in situ analysis, artificial intelligence, and data analytics methods; and storage  systems designs are evolving beyond a two-tiered file system and archive model to  complex hierarchies containing temporary, fast tiers of storage close to compute  resources with markedly different performance properties. Both of these changes  represent a significant departure from the decades-long status quo and require  investigation from storage researchers and practitioners to understand their  impacts on overall I/O performance. Without an in-depth understanding of I/O  workload behavior, storage system designers, I/O middleware developers, facility  operators, and application developers will not know how best to design or utilize  the additional tiers for optimal performance of a given I/O workload. The goal  of this Dagstuhl Seminar was to bring together experts in I/O performance analysis  and storage system architecture to collectively evaluate how our community is  capturing and analyzing I/O workloads on HPC systems, identify any gaps in our  methodologies, and determine how to develop a better in-depth understanding of  their impact on HPC systems. Our discussions were lively and resulted in identifying  critical needs for research in the area of understanding I/O behavior. We  document those discussions in this report.}
  	author = {Philip Carns and Julian Kunkel and Kathryn Mohror and Martin Schulz}
  	doi = {https://doi.org/10.4230/DagRep.11.7.16}
  	issn = {2192-5283}
  	journal = {Dagstuhl Reports}
  	pages = {16-75}
  	publisher = {Schloss Dagstuhl -- Leibniz-Zentrum für Informatik}
  	title = {Understanding I/O Behavior in Scientific and Data-Intensive Computing (Dagstuhl Seminar 21332)}
  	url = {https://drops.dagstuhl.de/opus/volltexte/2021/15589}
  	year = {2021}
  	month = {09}
  }

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

2022   🔗

• Realising Data-Centric Scientific Workflows with Provenance-Capturing on Data Lakes (Hendrik Nolte, Philipp Wieder), 2022-01-01 DOI BIBTEX

  @article{2_121151
  	author = {Hendrik Nolte and Philipp Wieder}
  	doi = {10.1162/dint_a_00141}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/121151}
  	title = {Realising Data-Centric Scientific Workflows with Provenance-Capturing on Data Lakes}
  	year = {2022}
  	month = {01}
  }

• Toward data lakes as central building blocks for data management and analysis (Philipp Wieder, Hendrik Nolte), 2022-01-01 DOI BIBTEX

  @article{2_114449
  	abstract = {"Data lakes are a fundamental building block for many industrial data analysis solutions and becoming increasingly popular in research. Often associated with big data use cases, data lakes are, for example, used as central data management systems of research institutions or as the core entity of machine learning pipelines. The basic underlying idea of retaining data in its native format within a data lake facilitates a large range of use cases and improves data reusability, especially when compared to the schema-on-write approach applied in data warehouses, where data is transformed prior to the actual storage to fit a predefined schema. Storing such massive amounts of raw data, however, has its very own challenges, spanning from the general data modeling, and indexing for concise querying to the integration of suitable and scalable compute capabilities. In this contribution, influential papers of the last decade have been selected to provide a comprehensive overview of developments and obtained results. The papers are analyzed with regard to the applicability of their input to data lakes that serve as central data management systems of research institutions. To achieve this, contributions to data lake architectures, metadata models, data provenance, workflow support, and FAIR principles are investigated. Last, but not least, these capabilities are mapped onto the requirements of two common research personae to identify open challenges. With that, potential research topics are determined, which have to be tackled toward the applicability of data lakes as central building blocks for research data management."}
  	author = {Philipp Wieder and Hendrik Nolte}
  	doi = {10.3389/fdata.2022.945720}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/114449}
  	title = {Toward data lakes as central building blocks for data management and analysis}
  	year = {2022}
  	month = {01}
  }

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

2015   🔗

• Enhanced Research for the Göttingen Campus (Jens Dierkes, Timo Gnadt, Fabian Cremer, Péter Király, Christopher Menke, Oliver Wannenwetsch, Lena Steilen, Ulrike Wuttke, Wolfram Horstmann, Ramin Yahyapour), 2015-01-01 BIBTEX

  @inproceedings{2_57543
  	author = {Jens Dierkes and Timo Gnadt and Fabian Cremer and Péter Király and Christopher Menke and Oliver Wannenwetsch and Lena Steilen and Ulrike Wuttke and Wolfram Horstmann and Ramin Yahyapour}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/57543}
  	title = {Enhanced Research for the Göttingen Campus}
  	year = {2015}
  	month = {01}
  }

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

Veröffentlichungen

2022   🔗

• Canonical Workflow for Experimental Research (Dirk Betz, Claudia Biniossek, Christophe Blanchi, Felix Henninger, Thomas Lauer, Philipp Wieder, Peter Wittenburg, Martin Zünkeler), 2022-01-01 DOI BIBTEX

  @article{2_121152
  	author = {Dirk Betz and Claudia Biniossek and Christophe Blanchi and Felix Henninger and Thomas Lauer and Philipp Wieder and Peter Wittenburg and Martin Zünkeler}
  	doi = {10.1162/dint_a_00123}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/121152}
  	title = {Canonical Workflow for Experimental Research}
  	year = {2022}
  	month = {01}
  }

• Realising Data-Centric Scientific Workflows with Provenance-Capturing on Data Lakes (Hendrik Nolte, Philipp Wieder), 2022-01-01 DOI BIBTEX

  @article{2_121151
  	author = {Hendrik Nolte and Philipp Wieder}
  	doi = {10.1162/dint_a_00141}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/121151}
  	title = {Realising Data-Centric Scientific Workflows with Provenance-Capturing on Data Lakes}
  	year = {2022}
  	month = {01}
  }

• Toward data lakes as central building blocks for data management and analysis (Philipp Wieder, Hendrik Nolte), 2022-01-01 DOI BIBTEX

  @article{2_114449
  	abstract = {"Data lakes are a fundamental building block for many industrial data analysis solutions and becoming increasingly popular in research. Often associated with big data use cases, data lakes are, for example, used as central data management systems of research institutions or as the core entity of machine learning pipelines. The basic underlying idea of retaining data in its native format within a data lake facilitates a large range of use cases and improves data reusability, especially when compared to the schema-on-write approach applied in data warehouses, where data is transformed prior to the actual storage to fit a predefined schema. Storing such massive amounts of raw data, however, has its very own challenges, spanning from the general data modeling, and indexing for concise querying to the integration of suitable and scalable compute capabilities. In this contribution, influential papers of the last decade have been selected to provide a comprehensive overview of developments and obtained results. The papers are analyzed with regard to the applicability of their input to data lakes that serve as central data management systems of research institutions. To achieve this, contributions to data lake architectures, metadata models, data provenance, workflow support, and FAIR principles are investigated. Last, but not least, these capabilities are mapped onto the requirements of two common research personae to identify open challenges. With that, potential research topics are determined, which have to be tackled toward the applicability of data lakes as central building blocks for research data management."}
  	author = {Philipp Wieder and Hendrik Nolte}
  	doi = {10.3389/fdata.2022.945720}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/114449}
  	title = {Toward data lakes as central building blocks for data management and analysis}
  	year = {2022}
  	month = {01}
  }

2021   🔗

• Sekundäre Nutzung von hausärztlichen Routinedaten ist machbar – Bericht vom RADAR Projekt (Johannes Hauswaldt, Thomas Bahls, Arne Blumentritt, Iris Demmer, Johannes Drepper, Roland Groh, Stephanie Heinemann, Wolfgang Hoffmann, Valérie Kempter, Johannes Pung, Otto Rienhoff, Falk Schlegelmilch, Philipp Wieder, Ramin Yahyapour, Eva Hummers), 2021-01-01 DOI BIBTEX

  @article{2_97749
  	abstract = {"Zusammenfassung Ziel der Studie „Real world“-Daten aus der ambulanten Gesundheitsversorgung sind in Deutschland nur schwer systematisch und longitudinal zu erlangen. Unsere Vision ist eine permanente Datenablage mit repräsentativen, de-identifizierten Patienten- und Versorgungsdaten, längsschnittlich, fortwährend aktualisiert und von verschiedenen Versorgern, mit der Möglichkeit zur Verknüpfung mit weiteren Daten, etwa aus Patientenbefragungen oder biologischer Forschung, zugänglich für andere Forscher. Wir berichten methodische Vorgehensweisen und Ergebnisse aus dem RADAR Projekt.Methodik Untersuchung des Rechtsrahmens, Entwicklung prototypischer technischer Abläufe und Lösungen, mit Machbarkeitsstudie zur Evaluation von technischer und inhaltlicher Funktionalität sowie Eignung für Fragestellungen der Versorgungsforschung.Ergebnisse Ab 2016 entwickelte ein interdisziplinäres Wissenschaftlerteam ein Datenschutzkonzept für Exporte von Versorgungsdaten aus elektronischen Praxisverwaltungssystemen. Eine technische und organisatorische Forschungsinfrastruktur im ambulanten Sektor wurden entwickelt und im Anwendungsfall „Orale Antikoagulation“ (OAK) umgesetzt. In 7 niedersächsischen Hausarztpraxen wurden 100 Patienten gewonnen und nach informierter Einwilligung ihre ausgewählten Behandlungsdaten, reduziert auf 40 relevante Datenfelder, über die Behandlungsdatentransfer-Schnittstelle extrahiert, unmittelbar vor Ort in identifizierende bzw. medizinische Daten getrennt und verschlüsselt zur Treuhandstelle (THS) bzw. an den Datenhalter übertragen. 75 Patienten, die die Einschlusskriterien erfüllten (mind. 1 Jahr Behandlung mit OAK), erhielten einen Lebensqualitäts-Fragebogen über die THS per Post. Von 66 Rücksendungen wurden 63 Fragebogenergebnisse mit den Behandlungsdaten in der Datenablage verknüpft.Schlussfolgerung Die rechtskonforme Machbarkeit der Gewinnung von pseudonymisierten hausärztlichen Routinedaten mit expliziter informierter Patienteneinwilligung und deren wissenschaftliche Nutzung einschließlich Re-Kontaktierung und Einbindung von Fragebogendaten konnte nachgewiesen werden. Die Schutzkonzepte Privacy by design und Datenminimierung (Artikel 25 mit Erwägungsgrund 78 DSGVO) wurden systematisch in das RADAR Projekt integriert und begründen wesentlich, dass der Machbarkeitsnachweis rechtskonformer Primärdatengewinnung und sekundärer Nutzung für Forschungszwecke gelang. Eine Nutzung hinreichend anonymisierter, aber noch sinnvoller hausärztlicher Gesundheitsdaten ohne individuelle Einwilligung ist im bestehenden Rechtsrahmen in Deutschland schwerlich umsetzbar."}
  	author = {Johannes Hauswaldt and Thomas Bahls and Arne Blumentritt and Iris Demmer and Johannes Drepper and Roland Groh and Stephanie Heinemann and Wolfgang Hoffmann and Valérie Kempter and Johannes Pung and Otto Rienhoff and Falk Schlegelmilch and Philipp Wieder and Ramin Yahyapour and Eva Hummers}
  	doi = {10.1055/a-1676-4020}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/97749}
  	title = {Sekundäre Nutzung von hausärztlichen Routinedaten ist machbar – Bericht vom RADAR Projekt}
  	year = {2021}
  	month = {01}
  }

• Certification Schemes for Research Infrastructures (Felix Helfer, Stefan Buddenbohm, Thomas Eckart, Philipp Wieder), 2021-01-01 BIBTEX

  @misc{2_108259
  	abstract = {"This working paper discusses the use and importance of various certification systems for the field of modern research infrastructures. For infrastructures such as CLARIAH-DE, reliable storage, management and dissemination of research data is an essential task. The certification of various areas, such as the technical architecture used, the work processes used or the qualification level of the staff, is an established procedure to ensure compliance with a variety of standards and quality criteria and to demonstrate the quality and reliability of an infrastructure to researchers, funders and comparable consortia. The working paper conducts this discussion based on an overview of selected certification systems that are of particular importance for CLARIAH-DE, but also for other research infrastructures. In addition to formalised certifications, the paper also addresses the areas of software-specific and self-assessment-based procedures and the different roles of the actors involved."}
  	address = {Göttingen}
  	author = {Felix Helfer and Stefan Buddenbohm and Thomas Eckart and Philipp Wieder}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/108259}
  	title = {Certification Schemes for Research Infrastructures}
  	year = {2021}
  	month = {01}
  }

• An Optimized Single Sign-On Schema for Reliable Multi -Level Security Management in Clouds (Aytaj Badirova, Shirin Dabbaghi, Faraz Fatemi-Moghaddam, Philipp Wieder, Ramin Yahyapour), In Proceedings of FiCloud 2021 – 8th International Conference on Future Internet of Things and Cloud, 2021-01-01 DOI BIBTEX

  @inproceedings{2_121153
  	author = {Aytaj Badirova and Shirin Dabbaghi and Faraz Fatemi-Moghaddam and Philipp Wieder and Ramin Yahyapour}
  	doi = {10.1109/FiCloud49777.2021.00014}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/121153}
  	journal = {Proceedings of FiCloud 2021 – 8th International Conference on Future Internet of Things and Cloud}
  	title = {An Optimized Single Sign-On Schema for Reliable Multi -Level Security Management in Clouds}
  	year = {2021}
  	month = {01}
  }

2020   🔗

• OCR-D kompakt: Ergebnisse und Stand der Forschung in der Förderinitiative (Konstantin Baierer, Matthias Boenig, Elisabeth Engl, Clemens Neudecker, Reinhard Altenhöner, Alexander Geyken, Johannes Mangei, Rainer Stotzka, Andreas Dengel, Martin Jenckel, Alexander Gehrke, Frank Puppe, Stefan Weil, Robert Sachunsky, Lena K. Schiffer, Maciej Janicki, Gerhard Heyer, Florian Fink, Klaus U. Schulz, Nikolaus Weichselbaumer, Saskia Limbach, Mathias Seuret, Rui Dong, Manuel Burghardt, Vincent Christlein, Triet Ho Anh Doan, Zeki Mustafa Dogan, Jörg-Holger Panzer, Kristine Schima-Voigt, Philipp Wieder), 2020-01-01 URL DOI BIBTEX

  @misc{2_121682
  	abstract = {"Bereits seit einigen Jahren werden große Anstrengungen unternommen, um die im deutschen Sprachraum erschienenen Drucke des 16.-18. Jahrhunderts zu erfassen und zu digitalisieren. Deren Volltexttransformation konzeptionell und technisch vorzubereiten, ist das übergeordnete Ziel des DFG-Projekts OCR-D, das sich mit der Weiterentwicklung von Verfahren der Optical Character Recognition befasst. Der Beitrag beschreibt den aktuellen Entwicklungsstand der OCR-D-Software und analysiert deren erste Teststellung in ausgewählten Bibliotheken."}
  	author = {Konstantin Baierer and Matthias Boenig and Elisabeth Engl and Clemens Neudecker and Reinhard Altenhöner and Alexander Geyken and Johannes Mangei and Rainer Stotzka and Andreas Dengel and Martin Jenckel and Alexander Gehrke and Frank Puppe and Stefan Weil and Robert Sachunsky and Lena K. Schiffer and Maciej Janicki and Gerhard Heyer and Florian Fink and Klaus U. Schulz and Nikolaus Weichselbaumer and Saskia Limbach and Mathias Seuret and Rui Dong and Manuel Burghardt and Vincent Christlein and Triet Ho Anh Doan and Zeki Mustafa Dogan and Jörg-Holger Panzer and Kristine Schima-Voigt and Philipp Wieder}
  	doi = {10.18452/21548}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/121682}
  	title = {OCR-D kompakt: Ergebnisse und Stand der Forschung in der Förderinitiative}
  	url = {https://publications.goettingen-research-online.de/handle/2/116509}
  	year = {2020}
  	month = {01}
  }

• OLA-HD – Ein OCR-D-Langzeitarchiv für historische Drucke (Triet Ho Anh Doan, Zeki Mustafa Doğan, Jörg-Holger Panzer, Kristine Schima-Voigt, Philipp Wieder), 2020-01-01 DOI BIBTEX

  @article{2_116509
  	author = {Triet Ho Anh Doan and Zeki Mustafa Doğan and Jörg-Holger Panzer and Kristine Schima-Voigt and Philipp Wieder}
  	doi = {10.18452/21548}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/116509}
  	title = {OLA-HD – Ein OCR-D-Langzeitarchiv für historische Drucke}
  	year = {2020}
  	month = {01}
  }

• menoci: Lightweight Extensible Web Portal enabling FAIR Data Management for Biomedical Research Projects (Markus Suhr, Christoph Lehmann, Christian Robert Bauer, Theresa Bender, Cornelius Knopp, Luca Freckmann, Björn Öst Hansen, Christian Henke, Georg Aschenbrandt, Lea Katharina Kühlborn, Sophia Rheinländer, Linus Weber, Bartlomiej Marzec, Marcel Hellkamp, Philipp Wieder, Harald Kusch, Ulrich Sax, Sara Yasemin Nussbeck), 2020-01-01 URL BIBTEX

  @misc{2_63412
  	abstract = {"Background: Biomedical research projects deal with data management requirements from multiple sources like funding agencies' guidelines, publisher policies, discipline best practices, and their own users' needs. We describe functional and quality requirements based on many years of experience implementing data management for the CRC 1002 and CRC 1190. A fully equipped data management software should improve documentation of experiments and materials, enable data storage and sharing according to the FAIR Guiding Principles while maximizing usability, information security, as well as software sustainability and reusability. Results: We introduce the modular web portal software menoci for data collection, experiment documentation, data publication, sharing, and preservation in biomedical research projects. Menoci modules are based on the Drupal content management system which enables lightweight deployment and setup, and creates the possibility to combine research data management with a customisable project home page or collaboration platform. Conclusions: Management of research data and digital research artefacts is transforming from individual researcher or groups best practices towards project- or organisation-wide service infrastructures. To enable and support this structural transformation process, a vital ecosystem of open source software tools is needed. Menoci is a contribution to this ecosystem of research data management tools that is specifically designed to support biomedical research projects."}
  	author = {Markus Suhr and Christoph Lehmann and Christian Robert Bauer and Theresa Bender and Cornelius Knopp and Luca Freckmann and Björn Öst Hansen and Christian Henke and Georg Aschenbrandt and Lea Katharina Kühlborn and Sophia Rheinländer and Linus Weber and Bartlomiej Marzec and Marcel Hellkamp and Philipp Wieder and Harald Kusch and Ulrich Sax and Sara Yasemin Nussbeck}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/63412}
  	title = {menoci: Lightweight Extensible Web Portal enabling FAIR Data Management for Biomedical Research Projects}
  	url = {https://sfb1190.med.uni-goettingen.de/production/literature/publications/106}
  	year = {2020}
  	month = {01}
  }

• Designing and piloting a generic research architecture and workflows to unlock German primary care data for secondary use (Thomas Bahls, Johannes Pung, Stephanie Heinemann, Johannes Hauswaldt, Iris Demmer, Arne Blumentritt, Henriette Rau, Johannes Drepper, Philipp Wieder, Roland Groh, Eva Hummers, Falk Schlegelmilch), 2020-01-01 DOI BIBTEX

  @article{2_68099
  	abstract = {"Medical data from family doctors are of great importance to health care researchers but seem to be locked in German practices and, thus, are underused in research. The RADAR project (Routine Anonymized Data for Advanced Health Services Research) aims at designing, implementing and piloting a generic research architecture, technical software solutions as well as procedures and workflows to unlock data from family doctor's practices. A long-term medical data repository for research taking legal requirements into account is established. Thereby, RADAR helps closing the gap between the European countries and to contribute data from primary care in Germany."}
  	author = {Thomas Bahls and Johannes Pung and Stephanie Heinemann and Johannes Hauswaldt and Iris Demmer and Arne Blumentritt and Henriette Rau and Johannes Drepper and Philipp Wieder and Roland Groh and Eva Hummers and Falk Schlegelmilch}
  	doi = {10.1186/s12967-020-02547-x}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/68099}
  	title = {Designing and piloting a generic research architecture and workflows to unlock German primary care data for secondary use}
  	year = {2020}
  	month = {01}
  }

Veröffentlichungen

Veröffentlichungen

2021   🔗

• Recent Advances of Resource Allocation in Network Function Virtualization (Song Yang, Fan Li, Stojan Trajanovski, Ramin Yahyapour, Xiaoming Fu), 2021-01-01 DOI BIBTEX

  @article{2_68120
  	abstract = {"Network Function Virtualization (NFV) has been emerging as an appealing solution that transforms complex network functions from dedicated hardware implementations to software instances running in a virtualized environment. Due to the numerous advantages such as flexibility, efficiency, scalability, short deployment cycles, and service upgrade, NFV has been widely recognized as the next-generation network service provisioning paradigm. In NFV, the requested service is implemented by a sequence of Virtual Network Functions (VNF) that can run on generic servers by leveraging the virtualization technology. These VNFs are pitched with a predefined order through which data flows traverse, and it is also known as the Service Function Chaining (SFC). In this article, we provide an overview of recent advances of resource allocation in NFV. We generalize and analyze four representative resource allocation problems, namely, (1) the VNF Placement and Traffic Routing problem, (2) VNF Placement problem, (3) Traffic Routing problem in NFV, and (4) the VNF Redeployment and Consolidation problem. After that, we study the delay calculation models and VNF protection (availability) models in NFV resource allocation, which are two important Quality of Service (QoS) parameters. Subsequently, we classify and summarize the representative work for solving the generalized problems by considering various QoS parameters (e.g., cost, delay, reliability, and energy) and different scenarios (e.g., edge cloud, online provisioning, and distributed provisioning). Finally, we conclude our article with a short discussion on the state-of-the-art and emerging topics in the related fields, and highlight areas where we expect high potential for future research."}
  	author = {Song Yang and Fan Li and Stojan Trajanovski and Ramin Yahyapour and Xiaoming Fu}
  	doi = {10.1109/TPDS.2020.3017001}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/68120}
  	title = {Recent Advances of Resource Allocation in Network Function Virtualization}
  	year = {2021}
  	month = {01}
  }

• Sekundäre Nutzung von hausärztlichen Routinedaten ist machbar – Bericht vom RADAR Projekt (Johannes Hauswaldt, Thomas Bahls, Arne Blumentritt, Iris Demmer, Johannes Drepper, Roland Groh, Stephanie Heinemann, Wolfgang Hoffmann, Valérie Kempter, Johannes Pung, Otto Rienhoff, Falk Schlegelmilch, Philipp Wieder, Ramin Yahyapour, Eva Hummers), 2021-01-01 DOI BIBTEX

  @article{2_97749
  	abstract = {"Zusammenfassung Ziel der Studie „Real world“-Daten aus der ambulanten Gesundheitsversorgung sind in Deutschland nur schwer systematisch und longitudinal zu erlangen. Unsere Vision ist eine permanente Datenablage mit repräsentativen, de-identifizierten Patienten- und Versorgungsdaten, längsschnittlich, fortwährend aktualisiert und von verschiedenen Versorgern, mit der Möglichkeit zur Verknüpfung mit weiteren Daten, etwa aus Patientenbefragungen oder biologischer Forschung, zugänglich für andere Forscher. Wir berichten methodische Vorgehensweisen und Ergebnisse aus dem RADAR Projekt.Methodik Untersuchung des Rechtsrahmens, Entwicklung prototypischer technischer Abläufe und Lösungen, mit Machbarkeitsstudie zur Evaluation von technischer und inhaltlicher Funktionalität sowie Eignung für Fragestellungen der Versorgungsforschung.Ergebnisse Ab 2016 entwickelte ein interdisziplinäres Wissenschaftlerteam ein Datenschutzkonzept für Exporte von Versorgungsdaten aus elektronischen Praxisverwaltungssystemen. Eine technische und organisatorische Forschungsinfrastruktur im ambulanten Sektor wurden entwickelt und im Anwendungsfall „Orale Antikoagulation“ (OAK) umgesetzt. In 7 niedersächsischen Hausarztpraxen wurden 100 Patienten gewonnen und nach informierter Einwilligung ihre ausgewählten Behandlungsdaten, reduziert auf 40 relevante Datenfelder, über die Behandlungsdatentransfer-Schnittstelle extrahiert, unmittelbar vor Ort in identifizierende bzw. medizinische Daten getrennt und verschlüsselt zur Treuhandstelle (THS) bzw. an den Datenhalter übertragen. 75 Patienten, die die Einschlusskriterien erfüllten (mind. 1 Jahr Behandlung mit OAK), erhielten einen Lebensqualitäts-Fragebogen über die THS per Post. Von 66 Rücksendungen wurden 63 Fragebogenergebnisse mit den Behandlungsdaten in der Datenablage verknüpft.Schlussfolgerung Die rechtskonforme Machbarkeit der Gewinnung von pseudonymisierten hausärztlichen Routinedaten mit expliziter informierter Patienteneinwilligung und deren wissenschaftliche Nutzung einschließlich Re-Kontaktierung und Einbindung von Fragebogendaten konnte nachgewiesen werden. Die Schutzkonzepte Privacy by design und Datenminimierung (Artikel 25 mit Erwägungsgrund 78 DSGVO) wurden systematisch in das RADAR Projekt integriert und begründen wesentlich, dass der Machbarkeitsnachweis rechtskonformer Primärdatengewinnung und sekundärer Nutzung für Forschungszwecke gelang. Eine Nutzung hinreichend anonymisierter, aber noch sinnvoller hausärztlicher Gesundheitsdaten ohne individuelle Einwilligung ist im bestehenden Rechtsrahmen in Deutschland schwerlich umsetzbar."}
  	author = {Johannes Hauswaldt and Thomas Bahls and Arne Blumentritt and Iris Demmer and Johannes Drepper and Roland Groh and Stephanie Heinemann and Wolfgang Hoffmann and Valérie Kempter and Johannes Pung and Otto Rienhoff and Falk Schlegelmilch and Philipp Wieder and Ramin Yahyapour and Eva Hummers}
  	doi = {10.1055/a-1676-4020}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/97749}
  	title = {Sekundäre Nutzung von hausärztlichen Routinedaten ist machbar – Bericht vom RADAR Projekt}
  	year = {2021}
  	month = {01}
  }

• An Optimized Single Sign-On Schema for Reliable Multi -Level Security Management in Clouds (Aytaj Badirova, Shirin Dabbaghi, Faraz Fatemi-Moghaddam, Philipp Wieder, Ramin Yahyapour), In Proceedings of FiCloud 2021 – 8th International Conference on Future Internet of Things and Cloud, 2021-01-01 DOI BIBTEX

  @inproceedings{2_121153
  	author = {Aytaj Badirova and Shirin Dabbaghi and Faraz Fatemi-Moghaddam and Philipp Wieder and Ramin Yahyapour}
  	doi = {10.1109/FiCloud49777.2021.00014}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/121153}
  	journal = {Proceedings of FiCloud 2021 – 8th International Conference on Future Internet of Things and Cloud}
  	title = {An Optimized Single Sign-On Schema for Reliable Multi -Level Security Management in Clouds}
  	year = {2021}
  	month = {01}
  }

• A two-phase virtual machine placement policy for data-intensive applications in cloud (Samaneh Sadegh, Kamran Zamanifar, Piotr Kasprzak, Ramin Yahyapour), 2021-01-01 DOI BIBTEX

  @article{2_84902
  	author = {Samaneh Sadegh and Kamran Zamanifar and Piotr Kasprzak and Ramin Yahyapour}
  	doi = {10.1016/j.jnca.2021.103025}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/84902}
  	title = {A two-phase virtual machine placement policy for data-intensive applications in cloud}
  	year = {2021}
  	month = {01}
  }

2019   🔗

• A multi-layered policy generation and management engine for semantic policy mapping in clouds (Faraz Fatemi Moghaddam, Philipp Wieder, Ramin Yahyapour), 2019-01-01 DOI BIBTEX

  @article{2_62713
  	abstract = {"The long awaited cloud computing concept is a reality now due to the transformation of computer generations. However, security challenges have become the biggest obstacles for the advancement of this emerging technology. A well-established policy framework is defined in this paper to generate security policies which are compliant to requirements and capabilities. Moreover, a federated policy management schema is introduced based on the policy definition framework and a multi-level policy application to create and manage virtual clusters with identical or common security levels. The proposed model consists in the design of a well-established ontology according to security mechanisms, a procedure which classifies nodes with common policies into virtual clusters, a policy engine to enhance the process of mapping requests to a specific node as well as an associated cluster and matchmaker engine to eliminate inessential mapping processes. The suggested model has been evaluated according to performance and security parameters to prove the efficiency and reliability of this multi-layered engine in cloud computing environments during policy definition, application and mapping procedures."}
  	author = {Faraz Fatemi Moghaddam and Philipp Wieder and Ramin Yahyapour}
  	doi = {10.1016/j.dcan.2019.02.001}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/62713}
  	title = {A multi-layered policy generation and management engine for semantic policy mapping in clouds}
  	year = {2019}
  	month = {01}
  }

• An Updateable Token-Based Schema for Authentication and Access Management in Clouds (Tayyebe Emadinia, Faraz Fatemi Moghaddam, Philipp Wieder, Shirin Dabbaghi Varnosfaderani, Ramin Yahyapour), In Proceedings of the 7th International Conference on Future Internet of Things and Cloud (FiCloud), 2019-01-01 DOI BIBTEX

  @inproceedings{2_63926
  	author = {Tayyebe Emadinia and Faraz Fatemi Moghaddam and Philipp Wieder and Shirin Dabbaghi Varnosfaderani and Ramin Yahyapour}
  	doi = {10.1109/FiCloud.2019.00015}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/63926}
  	journal = {Proceedings of the 7th International Conference on Future Internet of Things and Cloud (FiCloud)}
  	title = {An Updateable Token-Based Schema for Authentication and Access Management in Clouds}
  	year = {2019}
  	month = {01}
  }

• Loyal Consumers or One-Time Deal Hunters: Repeat Buyer Prediction for E-Commerce (Bo Zhao, Atsuhiro Takasu, Ramin Yahyapour, Xiaoming Fu), In 2019 International Conference on Data Mining Workshops (ICDMW), 2019-01-01 DOI BIBTEX

  @inproceedings{2_63192
  	abstract = {"Merchants sometimes run big promotions (e.g., discounts or cash coupons) on particular dates (e.g., Boxing-day Sales, \"Black Friday\" or \"Double 11 (Nov 11th)\", in order to attract a large number of new buyers. Unfortunately, many of the attracted buyers are one-time deal hunters, and these promotions may have little long lasting impact on sales. To alleviate this problem, it is important for merchants to identify who can be converted into repeated buyers. By targeting on these potential loyal customers, merchants can greatly reduce the promotion cost and enhance the return on investment (ROI). It is well known that in the field of online advertising, customer targeting is extremely challenging, especially for fresh buyers. With the long-term user behavior log accumulated by Tmall.com, we get a set of merchants and their corresponding new buyers acquired during the promotion on the \"Double 11\" day. Our goal is to predict which new buyers for given merchants will become loyal customers in the future. In other words, we need to predict the probability that these new buyers would purchase items from the same merchants again within 6 months. A data set containing around 200k users is given for training, while the other of similar size for testing. We extracted as many features as possible and find the key features to train our models. We proposed merged model of different classification models and merged lightGBM model with different parameter sets. The experimental results show that our merged models can bring about great performance improvements comparing with the original models."}
  	author = {Bo Zhao and Atsuhiro Takasu and Ramin Yahyapour and Xiaoming Fu}
  	doi = {10.1109/ICDMW.2019.00158}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/63192}
  	journal = {2019 International Conference on Data Mining Workshops (ICDMW)}
  	title = {Loyal Consumers or One-Time Deal Hunters: Repeat Buyer Prediction for E-Commerce}
  	year = {2019}
  	month = {01}
  }

• A Flexible and Compatible Model for Supporting Assurance Level through a Central Proxy (Shirin Dabbaghi Varnosfaderani, Piotr Kasprzak, Christof Pohl, Ramin Yahyapour), In 2019 6th IEEE International Conference on Cyber Security and Cloud Computing (CSCloud)/ 2019 5th IEEE International Conference on Edge Computing and Scalable Cloud (EdgeCom), 2019-01-01 DOI BIBTEX

  @inproceedings{2_62711
  	abstract = {"Generally, methods of authentication and identification utilized in asserting users' credentials directly affect security of offered services. In a federated environment, service owners must trust external credentials and make access control decisions based on Assurance Information received from remote Identity Providers (IdPs). Communities (e.g. NIST, IETF and etc.) have tried to provide a coherent and justifiable architecture in order to evaluate Assurance Information and define Assurance Levels (AL). Expensive deployment, limited service owners' authority to define their own requirements and lack of compatibility between heterogeneous existing standards can be considered as some of the unsolved concerns that hinder developers to openly accept published works. By assessing the advantages and disadvantages of well-known models, a comprehensive, flexible and compatible solution is proposed to value and deploy assurance levels through a central entity called Proxy."}
  	author = {Shirin Dabbaghi Varnosfaderani and Piotr Kasprzak and Christof Pohl and Ramin Yahyapour}
  	doi = {10.1109/CSCloud/EdgeCom.2019.00018}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/62711}
  	journal = {2019 6th IEEE International Conference on Cyber Security and Cloud Computing (CSCloud)/ 2019 5th IEEE International Conference on Edge Computing and Scalable Cloud (EdgeCom)}
  	title = {A Flexible and Compatible Model for Supporting Assurance Level through a Central Proxy}
  	year = {2019}
  	month = {01}
  }

• Delay-Sensitive and Availability-Aware Virtual Network Function Scheduling for NFV (Song Yang, Fan Li, Ramin Yahyapour, Xiaoming Fu), 2019-01-01 DOI BIBTEX

  @article{2_62710
  	abstract = {"Network Function Virtualization (NFV) has been emerging as an appealing solution that transforms from dedicated hardware implementations to software instances running in a virtualized environment. In NFV, the requested service is implemented by a sequence of Virtual Network Functions (VNF) that can run on generic servers by leveraging the virtualization technology. These VNFs are pitched with a predefined order, and it is also known as the Service Function Chaining (SFC). Considering that the delay and resiliency are two important Service Level Agreements (SLA) in a NFV service, in this paper, we first investigate how to quantitatively model the traversing delay of a flow in both totally ordered and partially ordered SFCs. Subsequently, we study how to calculate the VNF placement availability mathematically for both unprotected and protected SFCs. After that, we study the delay-sensitive Virtual Network Function (VNF) placement and routing problem with and without resiliency concerns. We prove that this problem is NP-hard under two cases. We subsequently propose an exact Integer Nonlinear Programming formulation and an efficient heuristic for this problem in each case. Finally, we evaluate the proposed algorithms in terms of acceptance ratio, average number of used nodes and total running time via extensive simulations."}
  	author = {Song Yang and Fan Li and Ramin Yahyapour and Xiaoming Fu}
  	doi = {10.1109/TSC.2019.2927339}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/62710}
  	title = {Delay-Sensitive and Availability-Aware Virtual Network Function Scheduling for NFV}
  	year = {2019}
  	month = {01}
  }

• Cloud Security Distributary Set (CSDS): A Policy-Based Framework to Define Multi-Level Security Structure in Clouds (Faraz Fatemi Moghaddam, Philipp Wieder, Süleyman Berk Çemberci, Ramin Yahyapour), In COINS '19 Proceedings of the International Conference on Omni-Layer Intelligent Systems, 2019-01-01 DOI BIBTEX

  @inproceedings{2_62712
  	abstract = {"Security challenges are the most important obstacles for the advancement of IT-based on-demand services and cloud computing as an emerging technology. In this paper, a structural policy management engine has been introduced to enhance the reliability of managing different policies in clouds and to provide standard as well as dedicated security levels (rings) based on the capabilities of the cloud provider and the requirements of cloud customers. Cloud security ontology (CSON) is an object-oriented framework defined to manage and enable appropriate communication between the potential security terms of cloud service providers. CSON uses two super classes to establish appropriate mapping between the requirements of cloud customers and the capabilities of the service provider."}
  	author = {Faraz Fatemi Moghaddam and Philipp Wieder and Süleyman Berk Çemberci and Ramin Yahyapour}
  	doi = {10.1145/3312614.3312633}
  	grolink = {https://resolver.sub.uni-goettingen.de/purl?gro-2/62712}
  	journal = {COINS '19 Proceedings of the International Conference on Omni-Layer Intelligent Systems}
  	title = {Cloud Security Distributary Set (CSDS): A Policy-Based Framework to Define Multi-Level Security Structure in Clouds}
  	year = {2019}
  	month = {01}
  }