% Year: 2020 % Encoding: utf-8 @Article{Zhao2020, author = {Zhiming Zhao and Ian Taylor and Radu Prodan}, journal = {Future Generation Computer Systems}, title = {{Editorial for FGCS Special issue on "Time-critical Applications on Software-defined Infrastructures"}}, year = {2020}, issn = {0167-739X}, month = {nov}, pages = {1170--1171}, volume = {112}, doi = {10.1016/j.future.2020.07.056}, publisher = {Elsevier BV}, url = {https://www.sciencedirect.com/science/article/abs/pii/S0167739X20324146} } @InProceedings{Zabrovskiy2020, author = {Anatoliy Zabrovskiy and Prateek Agrawal and Roland Matha and Christian Timmerer and Radu Prodan}, booktitle = {2020 IEEE Sixth International Conference on Multimedia Big Data (BigMM)}, title = {{ComplexCTTP: Complexity Class Based Transcoding Time Prediction for Video Sequences Using Artificial Neural Network}}, year = {2020}, month = sep, pages = {316--325}, publisher = {{IEEE}}, abstract = {HTTP Adaptive Streaming of video content is becoming an integral part of the Internet and accounts for the majority of today’s traffic. Although Internet bandwidth is constantly increasing, video compression technology plays an important role and the major challenge is to select and set up multiple video codecs, each with hundreds of transcoding parameters. Additionally, the transcoding speed depends directly on the selected transcoding parameters and the infrastructure used. Predicting transcoding time for multiple transcoding parameters with different codecs and processing units is a challenging task, as it depends on many factors. This paper provides a novel and considerably fast method for transcoding time prediction using video content classification and neural network prediction. Our artificial neural network (ANN) model predicts the transcoding times of video segments for state of the art video codecs based on transcoding parameters and content complexity. We evaluated our method for two video codecs/implementations (AVC/x264 and HEVC/x265) as part of large-scale HTTP Adaptive Streaming services. The ANN model of our method is able to predict the transcoding time by minimizing the mean absolute error (MAE) to 1.37 and 2.67 for x264 and x265 codecs, respectively. For x264, this is an improvement of 22\% compared to the state of the art.}, doi = {10.1109/bigmm50055.2020.00056}, keywords = {Transcoding time prediction, adaptive streaming, video transcoding, neural networks, video encoding, video complexity class, HTTP adaptive streaming, MPEG-DASH}, url = {https://ieeexplore.ieee.org/document/9232616} } @Misc{Vladislav2020, author = {Prodan, Radu and Kashanskii, Vladislav and Kimovski, Dragi and Agrawal, Prateek}, howpublished = {Online Publication (Abstract)}, month = feb, title = {{ASPIDE Project: Perspectives on the Scalable Monitoring and Auto-tuning}}, year = {2020}, abstract = {Extreme Data is an incarnation of Big Data concept distinguished by the massive amounts of data that must be queried, communicated and analyzed in (near) real-time by using a very large number of memory/storage elements of both, the converging Cloud and Pre-Exascale computing systems. Notable examples are the raw high energy physics data produced at a rate of hundreds of gigabits-per-second that must be filtered, stored and analyzed in a fault-tolerant fasion, multi-scale brain imaging data analysis and simulations, complex networks data analyses, driven by the social media systems. To handle such amounts of data multi-tierung architectures are introduced, including scheduling systems and distributed storage systems, ranging from in-memory databases to tape libraries. The ASPIDE project is contributing with the definition of a new programming paradigm, APIs, runtime tools and methodologies for expressing data intensive tasks on the converging large-scale systems , which can pave the way for the exploitation of parallelism policies over the various models of the system architectures, promoting high performance and efficiency, and offering powerful operations and mechanisms for processing extreme data sources at high speed and / or real-time.}, url = {https://research-explorer.app.ist.ac.at/record/7474} } @Article{Versluis2020, author = {Laurens Versluis and Roland Matha and Sacheendra Talluri and Tim Hegeman and Radu Prodan and Ewa Deelman and Alexandru Iosup}, journal = {IEEE Transactions on Parallel and Distributed Systems}, title = {{The Workflow Trace Archive: Open-Access Data From Public and Private Computing Infrastructures}}, year = {2020}, issn = {1045-9219}, month = {sep}, number = {9}, pages = {2170--2184}, volume = {31}, abstract = {Realistic, relevant, and reproducible experiments often need input traces collected from real-world environments. In this work, we focus on traces of workflows—common in datacenters, clouds, and HPC infrastructures. We show that the state-of-the-art in using workflow-traces raises important issues: (1) the use of realistic traces is infrequent and (2) the use of realistic, open-access traces even more so. Alleviating these issues, we introduce the Workflow Trace Archive (WTA), an open-access archive of workflow traces from diverse computing infrastructures and tooling to parse, validate, and analyze traces. The WTA includes >48 million workflows captured from >10 computing infrastructures, representing a broad diversity of trace domains and characteristics. To emphasize the importance of trace diversity, we characterize the WTA contents and analyze in simulation the impact of trace diversity on experiment results. Our results indicate significant differences in characteristics, properties, and workflow structures between workload sources, domains, and fields.}, doi = {10.1109/tpds.2020.2984821}, keywords = {Workflow, open-source, open-access, traces, characterization, archive, survey, simulation}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, url = {https://ieeexplore.ieee.org/document/9066946} } @InCollection{Verma2020, author = {Pawan Kumar Verma and Prateek Agrawal}, booktitle = {Data Management, Analytics and Innovation}, publisher = {Springer Singapore}, title = {{Study and Detection of Fake News: P2C2-Based Machine Learning Approach}}, year = {2020}, month = {sep}, pages = {261--278}, abstract = {News is the most important and sensitive piece of information which affects the society nowadays. In the current scenario, there are two ways to propagate news all over the world; first one is the traditional way, i.e., newspaper and second is electronic media like social media websites. Electronic media is the most popular medium these days because it helps to propagate news to huge audience in few seconds. Besides these benefits of electronic media, it has one disadvantage also, i.e., “spreading the Fake News”. Fake news is the most common problem these days. Even big companies like Twitter, Facebook, etc. are facing fake news problems. Several researchers are working in these big companies to solve this problem. Fake news can be defined as the news story that is not true. In some specific words, we can say that news is fake if any news agency declares a piece of news deliberately written as false and it is also verifiably as false. This paper focuses on some key characteristics of fake news and how it is affecting the society nowadays. It also includes various key viewpoints which are useful to categorize whether the news is fake or not. At last, this paper discussed some key challenges and future directions that help in increasing accuracy in detection of fake news on the basis of P2C2 (Propagation, Pattern, Comprehension & Credibility) approach having two phases: Detection and Verification. This paper helps readers in two ways (i) Newcomer can easily get the basic knowledge and impact of fake news; (ii) They can get knowledge of different perspectives of fake news which are helpful in the detection process.}, doi = {10.1007/978-981-15-5619-7_18}, keywords = {Credibility-based content classification, Comprehension content study on social media}, url = {https://link.springer.com/chapter/10.1007/978-981-15-5619-7_18} } @InProceedings{VenkataPhaniKumar2020, author = {Venkata Phani Kumar Malladi and Christian Timmerer and Hellwagner, Hermann}, booktitle = {2020 IEEE International Conference on Multimedia and Expo (ICME)}, title = {{Mipso: Multi-Period Per-Scene Optimization For HTTP Adaptive Streaming}}, year = {2020}, month = {jul}, pages = {1--6}, publisher = {IEEE}, abstract = {Video delivery over the Internet has become more and more established in recent years due to the widespread use of Dynamic Adaptive Streaming over HTTP (DASH). The current DASH specification defines a hierarchical data model for Media Presentation Descriptions (MPDs) in terms of periods, adaptation sets, representations and segments. Although multi-period MPDs are widely used in live streaming scenarios, they are not fully utilized in Video-on-Demand (VoD) HTTP adaptive streaming (HAS) scenarios. In this paper, we introduce MiPSO, a framework for Multi–Period per-Scene Optimization, to examine multiple periods in VoD HAS scenarios. MiPSO provides different encoded representations of a video at either (i) maximum possible quality or (ii) minimum possible bitrate, beneficial to both service providers and subscribers. In each period, the proposed framework adjusts the video representations (resolution-bitrate pairs) by taking into account the complexities of the video content, with the aim of achieving streams at either higher qualities or lower bitrates. The experimental evaluation with a test video data set shows that the MiPSO reduces the average bitrate of streams with the same visual quality by approximately 10% or increases the visual quality of streams by at least 1 dB in terms of Peak Signal-to-Noise (PSNR) at the same bitrate compared to conventional approaches to video content delivery.}, doi = {10.1109/icme46284.2020.9102775}, keywords = {Adaptive Streaming, Video-on-Demand, Per-Scene Encoding, Media Presentation Description}, url = {https://ieeexplore.ieee.org/document/9102775} } @Article{Torre2020, author = {Ennio Torre and Juan J. Durillo and Vincenzo de Maio and Prateek Agrawal and Shajulin Benedict and Nishant Saurabh and Radu Prodan}, journal = {Information and Software Technology}, title = {{A dynamic evolutionary multi-objective virtual machine placement heuristic for cloud data centers}}, year = {2020}, issn = {0950-5849}, month = {dec}, pages = {106390}, volume = {128}, abstract = {Minimizing the resource wastage reduces the energy cost of operating a data center, but may also lead to a considerably high resource overcommitment affecting the Quality of Service (QoS) of the running applications. The effective tradeoff between resource wastage and overcommitment is a challenging task in virtualized Clouds and depends on the allocation of virtual machines (VMs) to physical resources. We propose in this paper a multi-objective method for dynamic VM placement, which exploits live migration mechanisms to simultaneously optimize the resource wastage, overcommitment ratio and migration energy. Our optimization algorithm uses a novel evolutionary meta-heuristic based on an island population model to approximate the Pareto optimal set of VM placements with good accuracy and diversity. Simulation results using traces collected from a real Google cluster demonstrate that our method outperforms related approaches by reducing the migration energy by up to 57% with a QoS increase below 6%.}, doi = {10.1016/j.infsof.2020.106390}, keywords = {VM placement, Multi-objective optimisation, Resource overcommitment, Resource wastage, Live migration, Energy consumption, Pareto optimal set, Genetic algorithm, Data center simulation}, publisher = {Elsevier BV}, url = {https://www.sciencedirect.com/science/article/pii/S0950584919302101} } @InProceedings{Timmerer2020, author = {Christian Timmerer and Hellwagner, Hermann}, booktitle = {Proceedings of the Brazilian Symposium on Multimedia and the Web}, title = {{HTTP Adaptive Streaming: Where Is It Heading?}}, year = {2020}, month = {nov}, pages = {349--350}, publisher = {ACM}, abstract = {In this contribution, we present selected novel approaches and results of our research work in the ATHENA Christian Doppler Laboratory (Adaptive Streaming over HTTP and Emerging Networked Multimedia Services), a major research project at our department jointly funded by public sources and industry. By putting this work also into the context of related ongoing research activities, we aim at working out where HTTP Adaptive Streaming is currently heading.}, doi = {10.1145/3428658.3434574}, keywords = {HTTP adaptive streaming, video coding, machine learning, edge computing, immersive media, quality of experience}, url = {https://dl.acm.org/doi/10.1145/3428658.3434574} } @InProceedings{Taraghi2020, author = {Babak Taraghi and Anatoliy Zabrovskiy and Christian Timmerer and Hellwagner, Hermann}, booktitle = {Proceedings of the 11th ACM Multimedia Systems Conference}, title = {{Cloud-based Adaptive Video Streaming Evaluation Framework for the Automated Testing of Media Players CAdViSE}}, year = {2020}, month = {may}, pages = {349--352}, publisher = {ACM}, abstract = {Attempting to cope with fluctuations of network conditions in terms of available bandwidth, latency and packet loss, and to deliver the highest quality of video (and audio) content to users, research on adaptive video streaming has attracted intense efforts from the research community and huge investments from technology giants. How successful these efforts and investments are, is a question that needs precise measurements of the results of those technological advancements. HTTP-based Adaptive Streaming (HAS) algorithms, which seek to improve video streaming over the Internet, introduce video bitrate adaptivity in a way that is scalable and efficient. However, how each HAS implementation takes into account the wide spectrum of variables and configuration options, brings a high complexity to the task of measuring the results and visualizing the statistics of the performance and quality of experience. In this paper, we introduce CAdViSE, our Cloud-based Adaptive Video Streaming Evaluation framework for the automated testing of adaptive media players. The paper aims to demonstrate a test environment which can be instantiated in a cloud infrastructure, examines multiple media players with different network attributes at defined points of the experiment time, and finally concludes the evaluation with visualized statistics and insights into the results.}, doi = {10.1145/3339825.3393581}, keywords = {HTTP Adaptive Streaming, Media Players, MPEG-DASH, Network Emulation, Automated Testing, Quality of Experience}, url = {https://dl.acm.org/doi/10.1145/3339825.3393581} } @InProceedings{Sokolova2020, author = {Natalia Sokolova and Mario Taschwer and Stephanie Sarny and Doris Putzgruber-Adamitsch and Klaus Schoeffmann}, booktitle = {2020 IEEE 17th International Symposium on Biomedical Imaging Workshops (ISBI Workshops)}, title = {{Pixel-Based Iris and Pupil Segmentation in Cataract Surgery Videos Using Mask R-CNN}}, year = {2020}, month = {apr}, publisher = {IEEE}, abstract = {Automatically detecting clinically relevant events in surgery video recordings is becoming increasingly important for documentary, educational, and scientific purposes in the medical domain. From a medical image analysis perspective, such events need to be treated individually and associated with specific visible objects or regions. In the field of cataract surgery (lens replacement in the human eye), pupil reaction (dilation or restriction) during surgery may lead to complications and hence represents a clinically relevant event. Its detection requires automatic segmentation and measurement of pupil and iris in recorded video frames. In this work, we contribute to research on pupil and iris segmentation methods by (1) providing a dataset of 82 annotated images for training and evaluating suitable machine learning algorithms, and (2) applying the Mask R-CNN algorithm to this problem, which – in contrast to existing techniques for pupil segmentation – predicts free-form pixel-accurate segmentation masks for iris and pupil. The proposed approach achieves consistent high segmentation accuracies on several metrics while delivering an acceptable prediction efficiency, establishing a promising basis for further segmentation and event detection approaches on eye surgery videos.}, doi = {10.1109/isbiworkshops50223.2020.9153367}, keywords = {object segmentation, cataract surgery videos, mask RCNN, deep learning}, url = {https://ieeexplore.ieee.org/document/9153367} } @Article{Saurabh2020, author = {Nishant Saurabh and Shajulin Benedict and Jorge G. Barbosa and Radu Prodan}, journal = {Journal of Parallel and Distributed Computing}, title = {{Expelliarmus: Semantic-centric virtual machine image management in IaaS Clouds}}, year = {2020}, issn = {0743-7315}, month = {dec}, pages = {107--121}, volume = {146}, abstract = {Infrastructure-as-a-service (IaaS) Clouds concurrently accommodate diverse sets of user requests, requiring an efficient strategy for storing and retrieving virtual machine images (VMIs) at a large scale. The VMI storage management requires dealing with multiple VMIs, typically in the magnitude of gigabytes, which entails VMI sprawl issues hindering the elastic resource management and provisioning. Unfortunately, existing techniques to facilitate VMI management overlook VMI semantics (i.e at the level of base image and software packages), with either restricted possibility to identify and extract reusable functionalities or with higher VMI publishing and retrieval overheads. In this paper, we propose Expelliarmus, a novel VMI management system that helps to minimize VMI storage, publishing and retrieval overheads. To achieve this goal, Expelliarmus incorporates three complementary features. First, it models VMIs as semantic graphs to facilitate their similarity computation. Second, it provides a semantically-aware VMI decomposition and base image selection to extract and store non-redundant base image and software packages. Third, it assembles VMIs based on the required software packages upon user request. We evaluate Expelliarmus through a representative set of synthetic Cloud VMIs on a real test-bed. Experimental results show that our semantic-centric approach is able to optimize the repository size by 2.3 - 22 times compared to state-of-the-art systems (e.g. IBM’s Mirage and Hemera) with significant VMI publishing and slight retrieval performance improvement.}, doi = {10.1016/j.jpdc.2020.08.001}, keywords = {Theoretical Computer Science, Computer Networks and Communications, Hardware and Architecture, Software, Artificial Intelligence}, publisher = {Elsevier BV}, url = {https://www.sciencedirect.com/science/article/pii/S0743731520303415} } @InCollection{Prodan2020, author = {Radu Prodan and Nishant Saurabh and Zhiming Zhao and Kate Orton-Johnson and Antorweep Chakravorty and Aleksandar Karadimce and Alexandre Ulisses}, booktitle = {Euro-Par 2019: Parallel Processing Workshops}, publisher = {Springer International Publishing}, title = {{ARTICONF: Towards a Smart Social Media Ecosystem in a Blockchain Federated Environment}}, year = {2020}, month = may, number = {1997}, pages = {417--428}, abstract = {The ARTICONF project funded by the European Horizon 2020 program addresses issues of trust, time-criticality and democratisation for a new generation of federated infrastructure, to full the privacy, robustness, and autonomy related promises critical in proprietary social media platforms. It aims to: (1) simplify the creation of open and agile social media ecosystem with trusted participation using a two stage permissioned blockchain; (2) automatically detect interest groups and communities using graph anonymization techniques for decentralised and tokenized decision-making and reasoning; (3) elastically autoscale time-critical social media applications through an adaptive orchestrated Cloud edge-based infrastructure meeting application runtime requirements; and (4) enhance monetary inclusion in collaborative models through cognition and knowledge supply chains. We summarize the initial envisaged architecture of the ARTICONF ecosystem, the industrial pilot use cases for validating it, and the planned innovations compared to related other European research projects.}, doi = {10.1007/978-3-030-48340-1_32}, keywords = {Decentralized social media, privacy, trust, blockchain, semantic network, autoscaling, Cloud and edge computing}, url = {https://link.springer.com/chapter/10.1007/978-3-030-48340-1_32} } @Article{Perkis2020, author = {Andrew Perkis and Christian Timmerer and Sabina Baraković and Jasmina Baraković Husić and Søren Bech and Sebastian Bosse and Jean Botev and Kjell Brunnström and Luis Cruz and Katrien De Moor and Andrea de Polo Saibanti and Wouter Durnez and Sebastian Egger-Lampl and Ulrich Engelke and Tiago H. Falk and Jesús Gutiérrez and Asim Hameed and Andrew Hines and Tanja Kojic and Dragan Kukolj and Eirini Liotou and Dragorad Milovanovic and Sebastian Möller and Niall Murray and Babak Naderi and Manuela Pereira and Stuart Perry and Antonio Pinheiro and Andres Pinilla and Alexander Raake and Sarvesh Rajesh Agrawal and Ulrich Reiter and Rafael Rodrigues and Raimund Schatz and Peter Schelkens and Steven Schmidt and Saeed Shafiee Sabet and Ashutosh Singla and Lea Skorin-Kapov and Mirko Suznjevic and Stefan Uhrig and Sara Vlahović and Jan-Niklas Voigt-Antons and Saman Zadtootaghaj}, title = {{QUALINET White Paper on Definitions of Immersive Media Experience (IMEx)}}, year = {2020}, month = jun, abstract = {With the coming of age of virtual/augmented reality and interactive media, numerous definitions, frameworks, and models of immersion have emerged across different fields ranging from computer graphics to literary works. Immersion is oftentimes used interchangeably with presence as both concepts are closely related. However, there are noticeable interdisciplinary differences regarding definitions, scope, and constituents that are required to be addressed so that a coherent understanding of the concepts can be achieved. Such consensus is vital for paving the directionality of the future of immersive media experiences (IMEx) and all related matters. The aim of this white paper is to provide a survey of definitions of immersion and presence which leads to a definition of immersive media experience (IMEx). The Quality of Experience (QoE) for immersive media is described by establishing a relationship between the concepts of QoE and IMEx followed by application areas of immersive media experience. Influencing factors on immersive media experience are elaborated as well as the assessment of immersive media experience. Finally, standardization activities related to IMEx are highlighted and the white paper is concluded with an outlook related to future developments.}, keywords = {cs.MM} } @InProceedings{Palanisamy2020, author = {Anandhakumar Palanisamy and Mirsat Sefidanoski and Spiros Koulouzis and Carlos Rubia and Nishant Saurabh and Radu Prodan}, booktitle = {2020 IEEE Symposium on Computers and Communications (ISCC)}, title = {{Decentralized Social Media Applications as a Service: a Car-Sharing Perspective}}, year = {2020}, month = {jul}, pages = {1--7}, publisher = {IEEE}, abstract = {Social media applications are essential for next generation connectivity. Today, social media are centralized platforms with a single proprietary organization controlling the network and posing critical trust and governance issues over the created and propagated content. The ARTICONF project funded by the European Union’s Horizon 2020 program researches a decentralized social media platform based on a novel set of trustworthy, resilient and globally sustainable tools to fulfil the privacy, robustness and autonomy-related promises that proprietary social media platforms have failed to deliver so far. This paper presents the ARTICONF approach to a car-sharing use case application, as a new collaborative peer-to-peer model providing an alternative solution to private car ownership. We describe a prototype implementation of the car-sharing social media application and illustrate through real snapshots how the different ARTICONF tools support it in a simulated scenario.}, doi = {10.1109/iscc50000.2020.9219617}, keywords = {Social media, car-sharing, decentralization, blockchain}, url = {https://ieeexplore.ieee.org/document/9219617} } @InProceedings{Nguyen2020a, author = {Minh Nguyen and Christian Timmerer and Hellwagner, Hermann}, booktitle = {Proceedings of the 25th ACM Workshop on Packet Video}, title = {{H2BR: An HTTP/2-based Retransmission Technique to Improve the QoE of Adaptive Video Streaming}}, year = {2020}, month = {jun}, pages = {1--7}, publisher = {ACM}, abstract = {HTTP-based Adaptive Streaming (HAS) plays a key role in over-the-top video streaming. It contributes towards reducing the rebuffering duration of video playout by adapting the video quality to the current network conditions. However, it incurs variations of video quality in a streaming session because of the throughput fluctuation, which impacts the user’s Quality of Experience (QoE). Besides, many adaptive bitrate (ABR) algorithms choose the lowest-quality segments at the beginning of the streaming session to ramp up the playout buffer as soon as possible. Although this strategy decreases the startup time, the users can be annoyed as they have to watch a low-quality video initially. In this paper, we propose an efficient retransmission technique, namely H2BR, to replace low-quality segments being stored in the playout buffer with higher-quality versions by using features of HTTP/2 including (i) stream priority, (ii) server push, and (iii) stream termination. The experimental results show that H2BR helps users avoid watching low video quality during video playback and improves the user’s QoE. H2BR can decrease by up to more than 70% the time when the users suffer the lowest-quality video as well as benefits the QoE by up to 13%.}, doi = {10.1145/3386292.3397117}, keywords = {HTTP adaptive streaming, DASH, ABR algorithms, QoE, HTTP/2}, url = {https://dl.acm.org/doi/abs/10.1145/3386292.3397117} } @InProceedings{Nguyen2020, author = {Minh Nguyen and Hadi Amirpour and Christian Timmerer and Hellwagner, Hermann}, booktitle = {Proceedings of the Workshop on the Evolution, Performance, and Interoperability of QUIC}, title = {{Scalable High Efficiency Video Coding based HTTP Adaptive Streaming over QUIC}}, year = {2020}, month = {aug}, pages = {28--34}, publisher = {ACM}, abstract = {HTTP/2 has been explored widely for adaptive video streaming, but still suffers from Head-of-Line blocking, and three-way handshake delay due to TCP. Meanwhile, QUIC running on top of UDP can tackle these issues. In addition, although many adaptive bitrate (ABR) algorithms have been proposed for scalable and non-scalable video streaming, the literature lacks an algorithm designed for both types of video streaming approaches. In this paper, we investigate the impact of QUIC and HTTP/2 on the performance of ABR algorithms. Moreover, we propose an efficient approach for utilizing scalable video coding formats for adaptive video streaming that combines a traditional video streaming approach (based on non-scalable video coding formats) and a retransmission technique. The experimental results show that QUIC benefits significantly from our proposed method in the context of packet loss and retransmission. Compared to HTTP/2, it improves the average video quality and provides a smoother adaptation behavior. Finally, we demonstrate that our proposed method originally designed for non-scalable video codecs also works efficiently for scalable videos such as Scalable High Efficiency Video Coding (SHVC).}, doi = {10.1145/3405796.3405829}, keywords = {QUIC, H2BR, HTTP adaptive streaming, Retransmission, SHVC}, url = {https://dl.acm.org/doi/10.1145/3405796.3405829} } @InCollection{Najafabadi2020, author = {Zahra Najafabadi Samani and Alexander Lercher and Nishant Saurabh and Radu Prodan}, booktitle = {Euro-Par 2019: Parallel Processing Workshops}, publisher = {Springer International Publishing}, title = {{A Semantic Model with Self-adaptive and Autonomous Relevant Technology for Social Media Applications}}, year = {2020}, month = may, number = {11997}, pages = {442--451}, abstract = {With the rapidly increasing popularity of social media applications, decentralized control and ownership is taking more attention topreserve user's privacy. However, the lack of central control in the decentralized social network poses new issues of collaborative decision makingand trust to this permission-less environment. To tackle these problemsand ful ll the requirements of social media services, there is a need forintelligent mechanisms integrated to the decentralized social media thatconsider trust in various aspects according to the requirement of services. In this paper, we describe an adaptive microservice-based designcapable of nding relevant communities and accurate decision makingby extracting semantic information and applying role-stage model whilepreserving anonymity. We apply this information along with exploitingPareto solutions to estimate the trust in accordance with the quality ofservice and various con icting parameters, such as accuracy, timeliness,and latency.}, doi = {10.1007/978-3-030-48340-1_34}, keywords = {Semantic information, Community detection, Pareto-trust, Decentralized social media, Role-stage model}, url = {https://link.springer.com/chapter/10.1007/978-3-030-48340-1_34} } @InProceedings{Moll2020, author = {Philipp Moll and Veit Frick and Natascha Rauscher and Mathias Lux}, booktitle = {Proceedings of the 12th ACM International Workshop on Immersive Mixed and Virtual Environment Systems}, title = {{How players play games}}, year = {2020}, month = {jun}, publisher = {ACM}, abstract = {The popularity of computer games is remarkably high and is still growingevery year. Despite this popularity and the economical importance of gaming,research in game design, or to be more precise, of game mechanics that can beused to improve the enjoyment of a game, is still scarce. In this paper, weanalyze Fortnite, one of the currently most successful games, and observe howplayers play the game. We investigate what makes playing the game enjoyable byanalyzing video streams of experienced players from game streaming platformsand by conducting a user study with players who are new to the game. Weformulate four hypotheses about how game mechanics influence the way playersinteract with the game and how it influences player enjoyment. We presentdifferences in player behavior between experienced players and beginners anddiscuss how game mechanics could be used to improve the enjoyment forbeginners. In addition, we describe our approach to analyze games withoutaccess to game-internal data by using a toolchain which automatically extractsgame information from video streams.}, doi = {10.1145/3386293.3397113}, keywords = {Online Games, Game Mechanics, Game Design, Video Analysis}, url = {https://dl.acm.org/doi/10.1145/3386293.3397113} } @InProceedings{Messous2020, author = {Mohamed Ayoub Messous and Hellwagner, Hermann and Sidi-Mohammed Senouci and Driton Emini and Dominik Schnieders}, booktitle = {ICC 2020 - 2020 IEEE International Conference on Communications (ICC)}, title = {{Edge Computing for Visual Navigation and Mapping in a UAV Network}}, year = {2020}, month = {jun}, pages = {1--6}, publisher = {IEEE}, abstract = {This research work presents conceptual considerations and quantitative evaluations into how integrating computation offloading to edge computing servers would offer a paradigm shift for an effective deployment of autonomous drones. The specific mission that has been considered is collaborative autonomous navigation and mapping in a 3D environment of a small drone network. Specifically, in order to achieve this mission, each drone is required to compute a low latency, highly compute intensive task in a timely manner. The proposed model decides for each task, while considering the impact on performance and mission requirements, whether to (i) compute locally, (ii) offload to the edge server, or (iii) to the ground station. Extensive simulation work was performed to assess the effectiveness of the proposed scheme compared to other models.}, doi = {10.1109/icc40277.2020.9149087}, keywords = {UAV Network, Edge Computing, Computation Offloading, Visual Navigation and Mapping}, url = {https://ieeexplore.ieee.org/document/9149087} } @InProceedings{Mazdin2020, author = {Petra Mazdin and Michal Barcis and Hellwagner, Hermann and Bernhard Rinner}, booktitle = {2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)}, title = {{Distributed Task Assignment in Multi-Robot Systems based on Information Utility}}, year = {2020}, month = {aug}, pages = {734--740}, publisher = {IEEE}, abstract = {Most multi-robot systems (MRS) require to coordinate the assignment of tasks to individual robots for efficient missions. Due to the dynamics, incomplete knowledge and changing requirements, the robots need to distribute their local state information within the MRS continuously during the mission. Since communication resources are limited and message transfers may be erroneous, the global state estimated by each robot may become inconsistent. This inconsistency may lead to degraded task assignment and mission performance. In this paper, we explore the effect and cost of communication and exploit information utility for online distributed task assignment. In particular, we model the usefulness of the transferred state information by its information utility and use it for controlling the distribution of local state information and for updating the global state. We compare our distributed, utility-based online task assignment with well-known centralized and auction-based methods and show how substantial reduction of communication effort still leads to successful mission completion. We demonstrate our approach in a wireless communication testbed using ROS2.}, doi = {10.1109/case48305.2020.9216982}, keywords = {Task analysis, Robot kinematics, Mathematical model, Multi-robot systems, Optimization, Heuristic algorithms}, url = {https://doi.org/10.1109/CASE48305.2020.9216982} } @Article{Matha2020, author = {Roland Matha and Sasko Ristov and Thomas Fahringer and Radu Prodan}, journal = {IEEE Transactions on Parallel and Distributed Systems}, title = {{Simplified Workflow Simulation on Clouds based on Computation and Communication Noisiness}}, year = {2020}, issn = {1045-9219}, month = {jul}, number = {7}, pages = {1559--1574}, volume = {31}, abstract = {Many researchers rely on simulations to analyze and validate their researched methods on Cloud infrastructures. However, determining relevant simulation parameters and correctly instantiating them to match the real Cloud performance is a difficult and costly operation, as minor configuration changes can easily generate an unreliable inaccurate simulation result. Using legacy values experimentally determined by other researchers can reduce the configuration costs, but is still inaccurate as the underlying public Clouds and the number of active tenants are highly different and dynamic in time. To overcome these deficiencies, we propose a novel model that simulates the dynamic Cloud performance by introducing noise in the computation and communication tasks, determined by a small set of runtime execution data. Although the estimating method is apparently costly, a comprehensive sensitivity analysis shows that the configuration parameters determined for a certain simulation setup can be used for other simulations too, thereby reducing the tuning cost by up to 82.46%, while declining the simulation accuracy by only 1.98% in average. Extensive evaluation also shows that our novel model outperforms other state-of-the-art dynamic Cloud simulation models, leading up to 22% lower makespan inaccuracy.}, doi = {10.1109/tpds.2020.2967662}, keywords = {Cloud computing, simulation, workflow applications, burstable instances, performance instability and noisiness}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, url = {https://ieeexplore.ieee.org/document/8964294/} } @Article{Maio2020, author = {Vincenzo De Maio and Dragi Kimovski}, journal = {Future Generation Computer Systems}, title = {{Multi-objective scheduling of extreme data scientific workflows in Fog}}, year = {2020}, issn = {0167-739X}, month = {may}, pages = {171--184}, volume = {106}, abstract = {The concept of “extreme data” is a recent re-incarnation of the “big data” problem, which is distinguished by the massive amounts of information that must be analyzed with strict time requirements. In the past decade, the Cloud data centers have been envisioned as the essential computing architectures for enabling extreme data workflows. However, the Cloud data centers are often geographically distributed. Such geographical distribution increases offloading latency, making it unsuitable for processing of workflows with strict latency requirements, as the data transfer times could be very high. Fog computing emerged as a promising solution to this issue, as it allows partial workflow processing in lower-network layers. Performing data processing on the Fog significantly reduces data transfer latency, allowing to meet the workflows’ strict latency requirements. However, the Fog layer is highly heterogeneous and loosely connected, which affects reliability and response time of task offloading. In this work, we investigate the potential of Fog for scheduling of extreme data workflows with strict response time requirements. Moreover, we propose a novel Pareto-based approach for task offloading in Fog, called Multi-objective Workflow Offloading (MOWO). MOWO considers three optimization objectives, namely response time, reliability, and financial cost. We evaluate MOWO workflow scheduler on a set of real-world biomedical, meteorological and astronomy workflows representing examples of extreme data application with strict latency requirements.}, doi = {10.1016/j.future.2019.12.054}, keywords = {Scheduling, Scientific workflows, Fog computing, Task offloading, Monte-Carlo simulation, Multi-objective optimization}, publisher = {Elsevier BV}, url = {https://www.sciencedirect.com/science/article/pii/S0167739X19309197?via=ihub} } @InCollection{Limbasiya2020, author = {Nivid Limbasiya and Prateek Agrawal}, booktitle = {Algorithms for Intelligent Systems}, publisher = {Springer Singapore}, title = {{Bidirectional Long Short-Term Memory-Based Spatio-Temporal in Community Question Answering}}, year = {2020}, month = jan, pages = {291--310}, abstract = {Community-based question answering (CQA) is an online-based crowdsourcing service that enables users to share and exchange information in the field of natural language processing. A major challenge of CQA service is to determine the high-quality answer with respect to the given question. The existing methods perform semantic matches between a single pair of a question and its relevant answer. In this paper, a Spatio-Temporal bidirectional Long Short-Term Memory (ST-BiLSTM) method is proposed to predict the semantic representation between the question–answer and answer–answer. ST-BiLSTM has two LSTM network instead of one LSTM network (i.e., forward and backward LSTM). The forward LSTM controls the spatial relationship and backward LSTM for examining the temporal interactions for accurate answer prediction. Hence, it captures both the past and future context by using two networks for accurate answer prediction based on the user query. Initially, preprocessing is carried out by name-entity recognition (NER), dependency parsing, tokenization, part of speech (POS) tagging, lemmatization, stemming, syntactic parsing, and stop word removal techniques to filter out the useless information. Then, a par2vec is applied to transform the distributed representation of question and answer into a fixed vector representation. Next, ST-BiLSTM cell learns the semantic relationship between question–answer and answer–answer to determine the relevant answer set for the given user question. The experiment performed on SemEval 2016 and Baidu Zhidao datasets shows that our proposed method outperforms than other state-of-the-art approaches.}, doi = {10.1007/978-981-15-1216-2_11}, keywords = {Answer quality prediction, BiLSTM, Community question answering, Deep learning, Par2vec, Spatio-Temporal}, url = {https://link.springer.com/chapter/10.1007/978-981-15-1216-2_11} } @InProceedings{Leibetseder2020a, author = {Andreas Leibetseder and Klaus Schoeffmann}, booktitle = {Proceedings of the 2020 International Conference on Multimedia Retrieval}, title = {{surgXplore: Interactive Video Exploration for Endoscopy}}, year = {2020}, month = {jun}, pages = {397--401}, publisher = {ACM}, abstract = {Accumulating recordings of daily conducted surgical interventions such as endoscopic procedures for the long term generates very large video archives that are both difficult to search and explore. Since physicians utilize this kind of media routinely for documentation, treatment planning or education and training, it can be considered a crucial task to make said archives manageable in regards to discovering or retrieving relevant content. We present an interactive tool including a multitude of modalities for browsing, searching and filtering medical content, demonstrating its usefulness on over 140 hours of pre-processed laparoscopic surgery videos.}, doi = {10.1145/3372278.3391930}, keywords = {medical video exploration, endoscopy, interactive video retrieval}, url = {https://dl.acm.org/doi/10.1145/3372278.3391930} } @InProceedings{Leibetseder2020, author = {Andreas Leibetseder and Klaus Schoeffmann}, booktitle = {Proceedings of the Third Annual Workshop on Lifelog Search Challenge}, title = {{lifeXplore at the Lifelog Search Challenge 2020}}, year = {2020}, month = {jun}, pages = {37--42}, publisher = {ACM}, abstract = {Since its first iteration in 2018, the Lifelog Search Challenge (LSC) -- an interactive competition for retrieving lifelogging moments -- is co-located at the annual ACM International Conference on Multimedia Retrieval (ICMR) and has drawn international attention. With the goal of making an ever growing public lifelogging dataset searchable, several teams develop systems for quickly solving time-limited queries during the challenge. Having participated in both previous LSC iterations, i.e. LSC2018 and LSC2019, we present our lifeXplore system -- a video exploration and retrieval tool combining feature map browsing, concept search and filtering as well as hand-drawn sketching. The system is improved by including additional deep concept YOLO9000, optical character recognition (OCR) as well as adding uniform sampling as an alternative to the system's traditional underlying shot segmentation.}, doi = {10.1145/3379172.3391721}, keywords = {lifelogging, evaluation campaign, interactive image retrieval, video browsing}, url = {https://dl.acm.org/doi/10.1145/3379172.3391721} } @InProceedings{Kimovski_2020, author = {Dragi Kimovski and Dijana C. Bogatinoska and Narges Mehran and Aleksandar Karadimce and Natasa Paunkoska and Radu Prodan and Ninoslav Marina}, booktitle = {2020 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (BDCloud)}, title = {{Cloud-Edge Offloading Model for Vehicular Traffic Analysis}}, year = {2020}, month = {dec}, pages = {746--753}, publisher = {IEEE}, abstract = {The proliferation of smart sensing and computing devices, capable of collecting a vast amount of data, has made the gathering of the necessary vehicular traffic data relatively easy. However, the analysis of these big data sets requires computational resources, which are currently provided by the Cloud Data Centers. Nevertheless, the Cloud Data Centers can have unacceptably high latency for vehicular analysis applications with strict time requirements. The recent introduction of the Edge computing paradigm, as an extension of the Cloud services, has partially moved the processing of big data closer to the data sources, thus addressing this issue. Unfortunately, this unlocked multiple challenges related to resources management. Therefore, we present a model for scheduling of vehicular traffic analysis applications with partial task offloading across the Cloud - Edge continuum. The approach represents the traffic applications as a set of interconnected tasks composed into a workflow that can be partially offloaded to the Edge. We evaluated the approach through a simulated Cloud - Edge environment that considers two representative vehicular traffic applications with a focus on video stream analysis. Our results show that the presented approach reduces the application response time up to eight times while improving energy efficiency by a factor of four.}, doi = {10.1109/ispa-bdcloud-socialcom-sustaincom51426.2020.00119}, keywords = {Edge offloading, Cloud-Edge continuum, Application Scheduling, Particle Swarm Optimization}, url = {https://ieeexplore.ieee.org/document/9443969} } @InProceedings{Kashansky2020, author = {Vladislav Kashansky and Dragi Kimovski and Radu Prodan and Prateek Agrawal and Fabrizio Marozzo and Gabriel Iuhasz and Marek Marozzo and Javier Garcia-Blas}, booktitle = {2020 28th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)}, title = {{M3AT: Monitoring Agents Assignment Model for Data-Intensive Applications}}, year = {2020}, month = {mar}, pages = {72--79}, publisher = {IEEE}, abstract = {Nowadays, massive amounts of data are acquired, transferred, and analyzed nearly in real-time by utilizing a large number of computing and storage elements interconnected through high-speed communication networks. However, one issue that still requires research effort is to enable efficient monitoring of applications and infrastructures of such complex systems. In this paper, we introduce a Integer Linear Programming (ILP) model called M3AT for optimised assignment of monitoring agents and aggregators on large-scale computing systems. We identified a set of requirements from three representative data-intensive applications and exploited them to define the model’s input parameters. We evaluated the scalability of M3AT using the Constraint Integer Programing (SCIP) solver with default configuration based on synthetic data sets. Preliminary results show that the model provides optimal assignments for systems composed of up to 200 monitoring agents while keeping the number of aggregators constant and demonstrates variable sensitivity with respect to the scale of monitoring data aggregators and limitation policies imposed.}, doi = {10.1109/pdp50117.2020.00018}, keywords = {Monitoring systems, high performance computing, aggregation, systems control, data-intensive systems, generalized assignment problem, SCIP optimization suite}, url = {https://ieeexplore.ieee.org/document/9092397} } @Article{Hooft2020a, author = {Jeroen van der Hooft and Maria Torres Vega and Tim Wauters and Christian Timmerer and Ali C. Begen and Filip De Turck and Raimund Schatz}, journal = {IEEE Communications Magazine}, title = {{From Capturing to Rendering: Volumetric Media Delivery with Six Degrees of Freedom}}, year = {2020}, issn = {0163-6804}, month = {oct}, number = {10}, pages = {49--55}, volume = {58}, abstract = {Technological improvements are rapidly advancing holographic-type content distribution. Significant research efforts have been made to meet the low-latency and high-bandwidth requirements set forward by interactive applications such as remote surgery and virtual reality. Recent research made six degrees of freedom (6DoF) for immersive media possible, where users may both move their heads and change their position within a scene. In this article, we present the status and challenges of 6DoF applications based on volumetric media, focusing on the key aspects required to deliver such services. Furthermore, we present results from a subjective study to highlight relevant directions for future research.}, doi = {10.1109/mcom.001.2000242}, keywords = {Streaming media, Media, Cameras, Three-dimensional displays, Encoding, Bit rate, Real-time systems}, publisher = {Institute of Electrical and Electronics Engineers ({IEEE})}, url = {https://ieeexplore.ieee.org/document/9247522} } @InProceedings{Hooft2020, author = {Jeroen van der Hooft and Maria Torres Vega and Christian Timmerer and Ali C. Begen and Filip De Turck and Raimund Schatz}, booktitle = {2020 Twelfth International Conference on Quality of Multimedia Experience (QoMEX)}, title = {{Objective and Subjective QoE Evaluation for Adaptive Point Cloud Streaming}}, year = {2020}, month = {may}, publisher = {IEEE}, abstract = {Volumetric media has the potential to provide the six degrees of freedom (6DoF) required by truly immersive media. However, achieving 6DoF requires ultra-high bandwidth transmissions, which real-world wide area networks cannot provide economically. Therefore, recent efforts have started to target efficient delivery of volumetric media, using a combination of compression and adaptive streaming techniques. It remains, however, unclear how the effects of such techniques on the user perceived quality can be accurately evaluated. In this paper, we present the results of an extensive objective and subjective quality of experience (QoE) evaluation of volumetric 6DoF streaming. We use PCC-DASH, a standards-compliant means for HTTP adaptive streaming of scenes comprising multiple dynamic point cloud objects. By means of a thorough analysis we investigate the perceived quality impact of the available bandwidth, rate adaptation algorithm, viewport prediction strategy and user’s motion within the scene. We determine which of these aspects has more impact on the user’s QoE, and to what extent subjective and objective assessments are aligned.}, doi = {10.1109/qomex48832.2020.9123081}, keywords = {Volumetric Media, HTTP Adaptive Streaming, 6DoF, MPEG V-PCC, QoE Assessment, Objective Metrics}, url = {https://ieeexplore.ieee.org/document/9123081} } @Article{Hayat2020, author = {Samira Hayat and Evsen Yanmaz and Christian Bettstetter and Timothy X. Brown}, journal = {Autonomous Robots}, title = {{Multi-objective drone path planning for search and rescue with quality-of-service requirements}}, year = {2020}, month = {jul}, number = {7}, pages = {1183--1198}, volume = {44}, abstract = {We incorporate communication into the multi-UAV path planning problem for search and rescue missions to enable dynamic task allocation via information dissemination. Communication is not treated as a constraint but a mission goal. While achieving this goal, our aim is to avoid compromising the area coverage goal and the overall mission time. We define the mission tasks as: search, inform, and monitor at the best possible link quality. Building on our centralized simultaneous inform and connect (SIC) path planning strategy, we propose two adaptive strategies: (1) SIC with QoS (SICQ): optimizes search, inform, and monitor tasks simultaneously and (2) SIC following QoS (SIC+): first optimizes search and inform tasks together and then finds the optimum positions for monitoring. Both strategies utilize information as soon as it becomes available to determine UAV tasks. The strategies can be tuned to prioritize certain tasks in relation to others. We illustrate that more tasks can be performed in the given mission time by efficient incorporation of communication in the path design. We also observe that the quality of the resultant paths improves in terms of connectivity.}, doi = {10.1007/s10514-020-09926-9}, keywords = {multi-uav, dynamic task allocation, information dissemination, communication, path planning, search and rescue, area coverage, SIC, SICQ, connectivity}, publisher = {Springer Science and Business Media LLC}, url = {https://link.springer.com/article/10.1007/s10514-020-09926-9} } @InProceedings{Gurrin2020, author = {Cathal Gurrin and Tu-Khiem Le and Van-Tu Ninh and Duc-Tien Dang-Nguyen and Björn Thor Jonsson and Jakub Loko and Wolfgang Hürst and Minh-Triet Tran and Klaus Schöffmann}, booktitle = {Proceedings of the 2020 International Conference on Multimedia Retrieval}, title = {{Introduction to the Third Annual Lifelog Search Challenge (LSC' 20)}}, year = {2020}, month = {jun}, pages = {584--585}, publisher = {{ACM}}, abstract = {The Lifelog Search Challenge (LSC) is an annual comparative benchmarking activity for comparing approaches to interactive retrieval from multi-modal lifelogs. LSC'20, the third such challenge, attracts fourteen participants with their interactive lifelog retrieval systems. These systems are comparatively evaluated in front of a live-audience at the LSC workshop at ACM ICMR'20 in Dublin, Ireland. This overview motivates the challenge, presents the dataset and system configuration used in the challenge, and briefly presents the participating teams.}, doi = {10.1145/3372278.3388043}, keywords = {Lifelog, interactive retrieval systems, benchmarking}, url = {https://dl.acm.org/doi/abs/10.1145/3372278.3388043} } @Article{Ghamsarian2020c, author = {Negin Ghamsarian and Klaus Schoeffmann and Morteza Khademi}, journal = {Multimedia Tools and Applications}, title = {{Blind MV-based video steganalysis based on joint inter-frame and intra-frame statistics}}, year = {2020}, issn = {1573-7721}, month = {nov}, number = {6}, pages = {1--23}, volume = {80}, abstract = {Despite all its irrefutable benefits, the development of steganography methods has sparked ever-increasing concerns over steganography abuse in recent decades. To prevent the inimical usage of steganography, steganalysis approaches have been introduced. Since motion vector manipulation leads to random and indirect changes in the statistics of videos, MV-based video steganography has been the center of attention in recent years. In this paper, we propose a 54-dimentional feature set exploiting spatio-temporal features of motion vectors to blindly detect MV-based stego videos. The idea behind the proposed features originates from two facts. First, there are strong dependencies among neighboring MVs due to utilizing rate-distortion optimization techniques and belonging to the same rigid object or static background. Accordingly, MV manipulation can leave important clues on the differences between each MV and the MVs belonging to the neighboring blocks. Second, a majority of MVs in original videos are locally optimal after decoding concerning the Lagrangian multiplier, notwithstanding the information loss during compression. Motion vector alteration during information embedding can affect these statistics that can be utilized for steganalysis. Experimental results have shown that our features’ performance far exceeds that of state-of-the-art steganalysis methods. This outstanding performance lies in the utilization of complementary spatio-temporal statistics affected by MV manipulation as well as feature dimensionality reduction applied to prevent overfitting. Moreover, unlike other existing MV-based steganalysis methods, our proposed features can be adjusted to various settings of the state-of-the-art video codec standards such as sub-pixel motion estimation and variable-block-size motion estimation.}, doi = {10.1007/s11042-020-10001-9}, keywords = {Blind steganalysis, Video steganography, Information security, Motion vector, Video compression, H264/AVC}, publisher = {Springer Science and Business Media LLC}, url = {https://link.springer.com/article/10.1007/s11042-020-10001-9} } @InProceedings{Ghamsarian2020b, author = {Negin Ghamsarian and Mario Taschwer and Klaus Schoeffmann}, booktitle = {2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI)}, title = {{Deblurring Cataract Surgery Videos Using a Multi-Scale Deconvolutional Neural Network}}, year = {2020}, month = {apr}, pages = {872--876}, publisher = {IEEE}, abstract = {A common quality impairment observed in surgery videos is blur, caused by object motion or a defocused camera. Degraded image quality hampers the progress of machine-learning-based approaches in learning and recognizing semantic information in surgical video frames like instruments, phases, and surgical actions. This problem can be mitigated by automatically deblurring video frames as a preprocessing method for any subsequent video analysis task. In this paper, we propose and evaluate a multi-scale deconvolutional neural network to deblur cataract surgery videos. Experimental results confirm the effectiveness of the proposed approach in terms of the visual quality of frames as well as PSNR improvement.}, doi = {10.1109/isbi45749.2020.9098318}, keywords = {Video Deblurring, Deconvolutional Neural Networks, Cataract Surgery Videos}, url = {https://ieeexplore.ieee.org/document/9098318} } @InProceedings{Ghamsarian2020a, author = {Negin Ghamsarian}, booktitle = {Proceedings of the 2020 International Conference on Multimedia Retrieval}, title = {{Enabling Relevance-Based Exploration of Cataract Videos}}, year = {2020}, month = {jun}, pages = {378--382}, publisher = {ACM}, abstract = {Training new surgeons as one of the major duties of experienced expert surgeons demands a considerable supervisory investment of them. To expedite the training process and subsequently reduce the extra workload on their tight schedule, surgeons are seeking a surgical video retrieval system. Automatic workflow analysis approaches can optimize the training procedure by indexing the surgical video segments to be used for online video exploration. The aim of the doctoral project described in this paper is to provide the basis for a cataract video exploration system, that is able to (i) automatically analyze and extract the relevant segments of videos from cataract surgery, and (ii) provide interactive exploration means for browsing archives of cataract surgery videos. In particular, we apply deep-learning-based classification and segmentation approaches to cataract surgery videos to enable automatic phase and action recognition and similarity detection.}, doi = {10.1145/3372278.3391937}, keywords = {Action recognition, Phase recognition, Deep learning, Cataract surgery}, url = {https://dl.acm.org/doi/10.1145/3372278.3391937} } @InProceedings{Ghamsarian2020, author = {Negin Ghamsarian and Hadi Amirpourazarian and Christian Timmerer and Mario Taschwer and Klaus Schöffmann}, booktitle = {Proceedings of the 28th ACM International Conference on Multimedia}, title = {{Relevance-Based Compression of Cataract Surgery Videos Using Convolutional Neural Networks}}, year = {2020}, month = {oct}, pages = {3577--3585}, publisher = {ACM}, abstract = {Recorded cataract surgery videos play a prominent role in training and investigating the surgery, and enhancing the surgical outcomes. Due to storage limitations in hospitals, however, the recorded cataract surgeries are deleted after a short time and this precious source of information cannot be fully utilized. Lowering the quality to reduce the required storage space is not advisable since the degraded visual quality results in the loss of relevant information that limits the usage of these videos. To address this problem, we propose a relevance-based compression technique consisting of two modules: (i) relevance detection, which uses neural networks for semantic segmentation and classification of the videos to detect relevant spatio-temporal information, and (ii) content-adaptive compression, which restricts the amount of distortion applied to the relevant content while allocating less bitrate to irrelevant content. The proposed relevance-based compression framework is implemented considering five scenarios based on the definition of relevant information from the target audience's perspective. Experimental results demonstrate the capability of the proposed approach in relevance detection. We further show that the proposed approach can achieve high compression efficiency by abstracting substantial redundant information while retaining the high quality of the relevant content.}, doi = {10.1145/3394171.3413658}, keywords = {Convolutional Neural Networks, ROI Detection, Video Coding, HEVC, Medical Multimedia}, url = {https://dl.acm.org/doi/10.1145/3394171.3413658} } @InProceedings{Fox2020, author = {Markus Fox and Mario Taschwer and Klaus Schoeffmann}, booktitle = {2020 IEEE 33rd International Symposium on Computer-Based Medical Systems (CBMS)}, title = {{Pixel-Based Tool Segmentation in Cataract Surgery Videos with Mask R-CNN}}, year = {2020}, month = {jul}, pages = {565--568}, publisher = {IEEE}, abstract = {Automatically detecting surgical tools in recorded surgery videos is an important building block of further content-based video analysis. In ophthalmology, the results of such methods can support training and teaching of operation techniques and enable investigation of medical research questions on a dataset of recorded surgery videos. While previous methods used frame-based classification techniques to predict the presence of surgical tools — but did not localize them, we apply a recent deep-learning segmentation method (Mask R-CNN) to localize and segment surgical tools used in ophthalmic cataract surgery. We add ground-truth annotations for multi-class instance segmentation to two existing datasets of cataract surgery videos and make resulting datasets publicly available for research purposes. In the absence of comparable results from literature, we tune and evaluate the Mask R-CNN approach on these datasets for instrument segmentation/localization and achieve promising results (61\% mean average precision on 50\% intersection over union for instance segmentation, working even better for bounding box detection or binary segmentation), establishing a reasonable baseline for further research. Moreover, we experiment with common data augmentation techniques and analyze the achieved segmentation performance with respect to each class (instrument), providing evidence for future improvements of this approach.}, doi = {10.1109/cbms49503.2020.00112}, keywords = {cataract surgeries, instrument segmentation, tool annotation, deep neural networks, ophthalmology}, url = {https://ieeexplore.ieee.org/document/9183116} } @InProceedings{Fard2020a, author = {Hamid Mohammadi Fard and Radu Prodan and Felix Wolf}, booktitle = {2020 IEEE/ACM 13th International Conference on Utility and Cloud Computing (UCC)}, title = {{Dynamic Multi-objective Scheduling of Microservices in the Cloud}}, year = {2020}, month = {dec}, pages = {386--393}, publisher = {IEEE}, abstract = {For many applications, a microservices architecture promises better performance and flexibility compared to a conventional monolithic architecture. In spite of the advantages of a microservices architecture, deploying microservices poses various challenges for service developers and providers alike. One of these challenges is the efficient placement of microservices on the cluster nodes. Improper allocation of microservices can quickly waste resource capacities and cause low system throughput. In the last few years, new technologies in orchestration frameworks, such as the possibility of multiple schedulers for pods in Kubernetes, have improved scheduling solutions of microservices but using these technologies needs to involve both the service developer and the service provider in the behavior analysis of workloads. Using memory and CPU requests specified in the service manifest, we propose a general microservices scheduling mechanism that can operate efficiently in private clusters or enterprise clouds. We model the scheduling problem as a complex variant of the knapsack problem and solve it using a multi-objective optimization approach. Our experiments show that the proposed mechanism is highly scalable and simultaneously increases utilization of both memory and CPU, which in turn leads to better throughput when compared to the state-of-the-art.}, doi = {10.1109/ucc48980.2020.00061}, keywords = {scheduling microservices, cloud computing, multi-objective optimization, knapsack problem, resource management}, url = {https://ieeexplore.ieee.org/document/9302823} } @InCollection{Fard2020, author = {Hamid Mohammadi Fard and Radu Prodan and Felix Wolf}, booktitle = {Algorithmic Aspects of Cloud Computing}, publisher = {Springer International Publishing}, title = {{A Container-Driven Approach for Resource Provisioning in Edge-Fog Cloud}}, year = {2020}, month = aug, number = {12041}, pages = {59--76}, abstract = {With the emerging Internet of Things (IoT), distributed systems enter a new era. While pervasive and ubiquitous computing already became reality with the use of the cloud, IoT networks present new challenges because the ever growing number of IoT devices increases the latency of transferring data to central cloud data centers. Edge and fog computing represent practical solutions to counter the huge communication needs between IoT devices and the cloud. Considering the complexity and heterogeneity of edge and fog computing, however, resource provisioning remains the Achilles heel of efficiency for IoT applications. According to the importance of operating-system virtualization (so-called containerization), we propose an application-aware container scheduler that helps to orchestrate dynamic heterogeneous resources of edge and fog architectures. By considering available computational capacity, the proximity of computational resources to data producers and consumers, and the dynamic system status, our proposed scheduling mechanism selects the most adequate host to achieve the minimum response time for a given IoT service. We show how a hybrid use of containers and serverless microservices improves the performance of running IoT applications in fog-edge clouds and lowers usage fees. Moreover, our approach outperforms the scheduling mechanisms of Docker Swarm.}, doi = {10.1007/978-3-030-58628-7_5}, keywords = {Edge computing, Fog computing, Cloud computing, Resource provisioning, Containerization, Microservice, Orchestration, Scheduling}, url = {https://link.springer.com/chapter/10.1007/978-3-030-58628-7_5} } @InProceedings{Erfanian2020, author = {Alireza Erfanian and Farzad Tashtarian and Reza Farahani and Christian Timmerer and Hellwagner, Hermann}, booktitle = {2020 6th IEEE Conference on Network Softwarization (NetSoft)}, title = {{On Optimizing Resource Utilization in AVC-based Real-time Video Streaming}}, year = {2020}, month = {jun}, pages = {301--309}, publisher = {IEEE}, abstract = {Real-time video streaming traffic and related applications have witnessed significant growth in recent years. However, this has been accompanied by some challenging issues, predominantly resource utilization. IP multicasting, as a solution to this problem, suffers from many problems. Using scalable video coding could not gain wide adoption in the industry, due to reduced compression efficiency and additional computational complexity. The emerging software-defined networking (SDN)and network function virtualization (NFV) paradigms enable re-searchers to cope with IP multicasting issues in novel ways. In this paper, by leveraging the SDN and NFV concepts, we introduce a cost-aware approach to provide advanced video coding (AVC)-based real-time video streaming services in the network. In this study, we use two types of virtualized network functions (VNFs): virtual reverse proxy (VRP) and virtual transcoder (VTF)functions. At the edge of the network, VRPs are responsible for collecting clients’ requests and sending them to an SDN controller. Then, executing a mixed-integer linear program (MILP) determines an optimal multicast tree from an appropriate set of video source servers to the optimal group of transcoders. The desired video is sent over the multicast tree. The VTFs transcode the received video segments and stream to the requested VRPs over unicast paths. To mitigate the time complexity of the proposed MILPmodel, we propose a heuristic algorithm that determines a near-optimal solution in a reasonable amount of time. Using theMiniNet emulator, we evaluate the proposed approach and show it achieves better performance in terms of cost and resource utilization in comparison with traditional multicast and unicast approaches.}, doi = {10.1109/netsoft48620.2020.9165450}, keywords = {Dynamic Adaptive Streaming over HTTP (DASH), Real-time Video Streaming, Software Defined Networking (SDN), Video Transcoding, Network Function Virtualization (NFV)}, url = {https://ieeexplore.ieee.org/document/9165450} } @Article{Cetinkaya2020a, author = {Cetinkaya, Ekrem and KIRAÇ, M. Furkan}, journal = {TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES}, title = {{Image denoising using deep convolutional autoencoder with feature pyramids}}, year = {2020}, issn = {1303-6203}, month = {7}, number = {4}, pages = {2096--2109}, volume = {28}, abstract = {Image denoising is 1 of the fundamental problems in the image processing field since it is the preliminary stepfor many computer vision applications. Various approaches have been used for image denoising throughout the yearsfrom spatial filtering to model-based approaches. Having outperformed all traditional methods, neural-network-baseddiscriminative methods have gained popularity in recent years. However, most of these methods still struggle to achieveflexibility against various noise levels and types. In this paper, a deep convolutional autoencoder combined with a variantof feature pyramid network is proposed for image denoising. Simulated data generated by Blender software along withcorrupted natural images are used during training to improve robustness against various noise levels. Experimental resultsshow that the proposed method can achieve competitive performance in blind Gaussian denoising with significantly lesstraining time required compared to state of the art methods. Extensive experiments showed the proposed method givespromising performance in a wide range of noise levels with a single network.}, doi = {10.3906/elk-1911-138}, keywords = {Image denoising, convolutional autoencoder, feature pyramid, image processing}, url = {https://journals.tubitak.gov.tr/elektrik/issues/elk-20-28-4/elk-28-4-20-1911-138.pdf} } @InProceedings{Cetinkaya2020, author = {Ekrem Cetinkaya and Hadi Amirpour and Christian Timmerer and Mohammad Ghanbari}, booktitle = {2020 IEEE International Conference on Visual Communications and Image Processing (VCIP)}, title = {{FaME-ML: Fast Multirate Encoding for HTTP Adaptive Streaming Using Machine Learning}}, year = {2020}, month = {dec}, pages = {87--90}, publisher = {{IEEE}}, abstract = {HTTP Adaptive Streaming(HAS) is the most common approach for delivering video content over the Internet. The requirement to encode the same content at different quality levels (i.e., representations) in HAS is a challenging problem for content providers. Fast multirate encoding approaches try to accelerate this process by reusing information from previously encoded representations. In this paper, we propose to use convolutional neural networks (CNNs) to speed up the encoding of multiple representations with a specific focus on parallel encoding. In parallel encoding, the overall time-complexity is limited to the maximum time-complexity of one of the representations that are encoded in parallel. Therefore, instead of reducing the time-complexity for all representations, the highest time-complexities are reduced. Experimental results show that FaME-ML achieves significant time-complexity savings in parallel encoding scenarios(41%in average) with a slight increase in bitrate and quality degradation compared to the HEVC reference software.}, doi = {10.1109/vcip49819.2020.9301850}, keywords = {HEVC, Multirate Encoding, Machine Learning, DASH, HTTP Adaptive Streaming, HAS}, url = {https://ieeexplore.ieee.org/abstract/document/9301850} } @Article{Borgli2020, author = {Hanna Borgli and Vajira Thambawita and Pia H. Smedsrud and Steven Hicks and Debesh Jha and Sigrun L. Eskeland and Kristin Ranheim Randel and Konstantin Pogorelov and Mathias Lux and Duc Tien Dang Nguyen and Dag Johansen and Carsten Griwodz and H{\aa}kon K. Stensland and Enrique Garcia-Ceja and Peter T. Schmidt and Hugo L. Hammer and Michael A. Riegler and Paal Halvorsen and Thomas de Lange}, journal = {Scientific Data}, title = {{HyperKvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy}}, year = {2020}, issn = {2052-4463}, month = {aug}, number = {1}, volume = {7}, abstract = {Artificial intelligence is currently a hot topic in medicine. However, medical data is often sparse and hard to obtain due to legal restrictions and lack of medical personnel for the cumbersome and tedious process to manually label training data. These constraints make it difficult to develop systems for automatic analysis, like detecting disease or other lesions. In this respect, this article presents HyperKvasir, the largest image and video dataset of the gastrointestinal tract available today. The data is collected during real gastro- and colonoscopy examinations at Bærum Hospital in Norway and partly labeled by experienced gastrointestinal endoscopists. The dataset contains 110,079 images and 374 videos, and represents anatomical landmarks as well as pathological and normal findings. The total number of images and video frames together is around 1 million. Initial experiments demonstrate the potential benefits of artificial intelligence-based computer-assisted diagnosis systems. The HyperKvasir dataset can play a valuable role in developing better algorithms and computer-assisted examination systems not only for gastro- and colonoscopy, but also for other fields in medicine.}, doi = {10.1038/s41597-020-00622-y}, keywords = {Statistics, Probability and Uncertainty, Statistics and Probability, Education, Library and Information Sciences, Information Systems, Computer Science Applications}, publisher = {Springer Science and Business Media LLC}, url = {https://www.nature.com/articles/s41597-020-00622-y} } @Article{Bhadwal2020, author = {Neha Bhadwal and Prateek Agrawal and Vishu Madaan}, journal = {Scalable Computing: Practice and Experience}, title = {{A Machine Translation System from Hindi to Sanskrit Language using Rule based Approach}}, year = {2020}, issn = {1895-1767}, month = {aug}, number = {3}, pages = {543--554}, volume = {21}, abstract = {Machine Translation is an area of Natural Language Processing which can replace the laborious task of manual translation. Sanskrit language is among the ancient Indo-Aryan languages. There are numerous works of art and literature in Sanskrit. It has also been a medium for creating treatise of philosophical work as well as works on logic, astronomy and mathematics. On the other hand, Hindi is the most prominent language of India. Moreover,it is among the most widely spoken languages across the world. This paper is an effort to bridge the language barrier between Hindi and Sanskrit language such that any text in Hindi can be translated to Sanskrit. The technique used for achieving the aforesaid objective is rule-based machine translation. The salient linguistic features of the two languages are used to perform the translation. The results are produced in the form of two confusion matrices wherein a total of 50 random sentences and 100 tokens (Hindi words or phrases) were taken for system evaluation. The semantic evaluation of 100 tokens produce an accuracy of 94% while the pragmatic analysis of 50 sentences produce an accuracy of around 86%. Hence, the proposed system can be used to understand the whole translation process and can further be employed as a tool for learning as well as teaching. Further, this application can be embedded in local communication based assisting Internet of Things (IoT) devices like Alexa or Google Assistant.}, doi = {10.12694/scpe.v21i3.1783}, keywords = {Rule based approach, Natural Language Translation, Parts of speech tagging, Sanskrit Translation, Hindi Translation}, publisher = {Scalable Computing: Practice and Experience}, url = {https://www.scpe.org/index.php/scpe/article/view/1783} } @Article{Bentaleb2020, author = {Abdelhak Bentaleb and Christian Timmerer and Ali C. Begen and Roger Zimmermann}, journal = {ACM Transactions on Multimedia Computing, Communications, and Applications}, title = {{Performance Analysis of ACTE: a Bandwidth Prediction Method for Low-Latency Chunked Streaming}}, year = {2020}, issn = {1551-6857}, month = {jul}, number = {2s}, pages = {1--24}, volume = {16}, abstract = {HTTP adaptive streaming with chunked transfer encoding can offer low-latency streaming without sacrificing the coding efficiency.This allows media segments to be delivered while still being packaged. However, conventional schemes often make widely inaccurate bandwidth measurements due to the presence of idle periods between the chunks and hence this is causing sub-optimal adaptation decisions. To address this issue, we earlier proposed ACTE (ABR for Chunked Transfer Encoding), a bandwidth prediction scheme for low-latency chunked streaming. While ACTE was a significant step forward, in this study we focus on two still remaining open areas, namely (i) quantifying the impact of encoding parameters, including chunk and segment durations, bitrate levels, minimum interval between IDR-frames and frame rate onACTE, and (ii) exploring the impact of video content complexity on ACTE. We thoroughly investigate these questions and report on our findings. We also discuss some additional issues that arise in the context of pursuing very low latency HTTP video streaming.}, doi = {10.1145/3387921}, keywords = {HAS, ABR, DASH, CMAF, low-latency, HTTP chunked transfer encoding, bandwidth measurement and prediction, RLS, encoding parameters, FFmpeg}, publisher = {Association for Computing Machinery (ACM)}, url = {https://dl.acm.org/doi/abs/10.1145/3387921} } @Article{Barcis2020, author = {Michal Barcis and Agata Barcis and Hellwagner, Hermann}, journal = {Sensors}, title = {{Information Distribution in Multi-Robot Systems: Utility-Based Evaluation Model}}, year = {2020}, issn = {1424-8220}, month = {jan}, number = {3}, volume = {20}, abstract = {This work addresses the problem of information distribution in multi-robot systems, with an emphasis on multi-UAV (unmanned aerial vehicle) applications. We present an analytical model that helps evaluate and compare different information distribution schemes in a robotic mission. It serves as a unified framework to represent the usefulness (utility) of each message exchanged by the robots. It can be used either on its own in order to assess the information distribution efficacy or as a building block of solutions aimed at optimizing information distribution. Moreover, we present multiple examples of instantiating the model for specific missions. They illustrate various approaches to defining the utility of different information types. Finally, we introduce a proof of concept showing the applicability of the model in a robotic system by implementing it in Robot Operating System 2 (ROS 2) and performing a simple simulated mission using a network emulator. We believe the introduced model can serve as a basis for further research on generic solutions for assessing or optimizing information distribution.}, doi = {10.3390/s20030710}, keywords = {autonomous systems, multi-robot systems, information distribution, utility theory}, publisher = {MDPI AG}, url = {https://www.mdpi.com/1424-8220/20/3/710/htm} } @InProceedings{Amirpour_2020, author = {Hadi Amirpour and Ekrem Cetinkaya and Christian Timmerer and Mohammad Ghanbari}, booktitle = {2020 Data Compression Conference (DCC)}, title = {{Fast Multi-rate Encoding for Adaptive HTTP Streaming}}, year = {2020}, month = {mar}, publisher = {IEEE}, abstract = {Adaptive HTTP streaming is the preferred method to deliver multimedia content in the internet. It provides multiple representations of the same content in different qualities (i.e. bit-rates and resolutions) and allows the client to request segments from the available representations in a dynamic, adaptive way depending on its context. The growing number of representations in adaptive HTTP streaming makes encoding of one video segment at different representations a challenging task in terms of encoding time-complexity. In this paper, information of both highest and lowest quality representations are used to limit Rate Distortion Optimization (RDO) for each Coding Unit Tree (CTU) in High Efficiency Video Coding. Our proposed method first encodes the highest quality representation and consequently uses it to encode the lowest quality representation. In particular, the block structure and the selected reference frame of both highest and lowest quality representations are then used to predict and shorten the RDO process of each CTU for intermediate quality representations. Our proposed method introduces a delay of two CTUs thanks to employing parallel processing techniques. Experimental results show significant reduction in time-complexity over the reference software 38% and the state-of-the-art 10% while quality degradation is negligible.}, doi = {10.1109/dcc47342.2020.00080}, keywords = {HTTP adaptive streaming, Multi-rate encoding, HEVC, Fast block partitioning}, url = {https://ieeexplore.ieee.org/document/9105709} } @InProceedings{Amirpour2020, author = {Hadi Amirpour and Christian Timmerer and Mohammad Ghanbari}, booktitle = {2020 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)}, title = {{Towards View-Aware Adaptive Streaming of Holographic Content}}, year = {2020}, month = {jul}, publisher = {IEEE}, abstract = {Holography is able to reconstruct a three-dimensional structure of an object by recording full wave fields of light emitted from the object. This requires a huge amount of data to be encoded, stored, transmitted, and decoded for holographic content, making its practical usage challenging especially for bandwidth-constrained networks and memory-limited devices. In the delivery of holographic content via the internet, bandwidth wastage should be avoided to tackle high bandwidth demands of holography streaming. For real-time applications, encoding time-complexity is also a major problem. In this paper, the concept of dynamic adaptive streaming over HTTP (DASH) is extended to holography image streaming and view-aware adaptation techniques are studied. As each area of a hologram contains information of a specific view, instead of encoding and decoding the entire hologram, just the part required to render the selected view is encoded and transmitted via the network based on the users’ interactivity. Four different strategies, namely, monolithic, single view, adaptive view, and non-real time streaming strategies are explained and compared in terms of bandwidth requirements, encoding time-complexity, and bitrate overhead. Experimental results show that the view-aware methods reduce the required bandwidth for holography streaming at the cost of a bitrate increase.}, doi = {10.1109/icmew46912.2020.9106055}, keywords = {Holography, compression, bitrate adaption, dynamic adaptive streaming over HTTP, DASH}, url = {https://ieeexplore.ieee.org/document/9106055} } @InProceedings{AguilarArmijo2020, author = {Jesus Aguilar-Armijo and Babak Taraghi and Christian Timmerer and Hellwagner, Hermann}, booktitle = {2020 IEEE International Symposium on Multimedia (ISM)}, title = {{Dynamic Segment Repackaging at the Edge for {HTTP} Adaptive Streaming}}, year = {2020}, month = {dec}, pages = {17--24}, publisher = {IEEE}, abstract = {Adaptive video streaming systems typically support different media delivery formats, e.g., MPEG-DASH and HLS, replicating the same content multiple times into the network. Such a diversified system results in inefficient use of storage, caching, and bandwidth resources. The Common Media Application Format (CMAF) emerges to simplify HTTP Adaptive Streaming (HAS), providing a single encoding and packaging format of segmented media content and offering the opportunities of bandwidth savings, more cache hits and less storage needed. However, CMAF is not yet supported by most devices. To solve this issue, we present a solution where we maintain the main advantages of CMAF while supporting heterogeneous devices using different media delivery formats. For that purpose, we propose to dynamically convert the content from CMAF to the desired media delivery format at an edge node. We study the bandwidth savings with our proposed approach using an analytical model and simulation, resulting in bandwidth savings of up to 20% with different media delivery format distributions. We analyze the runtime impact of the required operations on the segmented content performed in two scenarios: the classic one, with four different media delivery formats, and the proposed scenario, using CMAF-only delivery through the network. We compare both scenarios with different edge compute power assumptions. Finally, we perform experiments in a real video streaming testbed delivering MPEG-DASH using CMAF content to serve a DASH and an HLS client, performing the media conversion for the latter one.}, doi = {10.1109/ism.2020.00009}, keywords = {CMAF, Edge Computing, HTTP Adaptive Streaming (HAS)} } @Article{Agrawal2020a, author = {Prateek Agrawal and Deepak Chaudhary and Vishu Madaan and Anatoliy Zabrovskiy and Radu Prodan and Dragi Kimovski and Christian Timmerer}, journal = {Multimedia Tools and Applications}, title = {{Automated bank cheque verification using image processing and deep learning methods}}, year = {2020}, issn = {1573-7721}, month = {oct}, number = {4}, pages = {5319--5350}, volume = {80}, abstract = {Automated bank cheque verification using image processing is an attempt to complement the present cheque truncation system, as well as to provide an alternate methodology for the processing of bank cheques with minimal human intervention. When it comes to the clearance of the bank cheques and monetary transactions, this should not only be reliable and robust but also save time which is one of the major factor for the countries having large population. In order to perform the task of cheque verification, we developed a tool which acquires the cheque leaflet key components, essential for the task of cheque clearance using image processing and deep learning methods. These components include the bank branch code, cheque number, legal as well as courtesy amount, account number, and signature patterns. our innovation aims at benefiting the banking system by re-innovating the other competent cheque-based monetary transaction system which requires automated system intervention. For this research, we used institute of development and research in banking technology (IDRBT) cheque dataset and deep learning based convolutional neural networks (CNN) which gave us an accuracy of 99.14% for handwritten numeric character recognition. It resulted in improved accuracy and precise assessment of the handwritten components of bank cheque. For machine printed script, we used MATLAB in-built OCR method and the accuracy achieved is satisfactory (97.7%) also for verification of Signature we have used Scale Invariant Feature Transform (SIFT) for extraction of features and Support Vector Machine (SVM) as classifier, the accuracy achieved for signature verification is 98.10%.}, doi = {10.1007/s11042-020-09818-1}, keywords = {Cheque truncation system, Image segmentation, Bank cheque clearance, Image feature extraction, Convolution neural network, Support vector machine, Scale invariant feature transform}, publisher = {Springer Science and Business Media LLC}, url = {https://link.springer.com/article/10.1007/s11042-020-09818-1} } @Article{Agrawal2020, author = {Prateek Agrawal and Anatoliy Zabrovskiy and Adithyan Ilangovan and Christian Timmerer and Radu Prodan}, journal = {Cluster Computing}, title = {{FastTTPS: fast approach for video transcoding time prediction and scheduling for HTTP adaptive streaming videos}}, year = {2020}, issn = {1573-7543}, month = {nov}, pages = {1--17}, abstract = {HTTP adaptive streaming of video content becomes an integrated part of the Internet and dominates other streaming protocols and solutions. The duration of creating video content for adaptive streaming ranges from seconds or up to several hours or days, due to the plethora of video transcoding parameters and video source types. Although, the computing resources of different transcoding platforms and services constantly increase, accurate and fast transcoding time prediction and scheduling is still crucial. We propose in this paper a novel method called fast video transcoding time prediction and scheduling (FastTTPS) of x264 encoded videos based on three phases: (i) transcoding data engineering, (ii) transcoding time prediction, and (iii) transcoding scheduling. The first phase is responsible for video sequence selection, segmentation and feature data collection required for predicting the transcoding time. The second phase develops an artificial neural network (ANN) model for segment transcoding time prediction based on transcoding parameters and derived video complexity features. The third phase compares a number of parallel schedulers to map the predicted transcoding segments on the underlying high-performance computing resources. Experimental results show that our predictive ANN model minimizes the transcoding mean absolute error (MAE) and mean square error (MSE) by up to 1.7 and 26.8, respectively. In terms of scheduling, our method reduces the transcoding time by up to 38% using a Max–Min algorithm compared to the actual transcoding time without prediction information.}, doi = {10.1007/s10586-020-03207-x}, keywords = {Transcoding time prediction, Video transcoding, Scheduling, Artificial neural networks, MPEG-DASH, Adaptive streaming}, publisher = {Springer Science and Business Media LLC}, url = {https://link.springer.com/article/10.1007/s10586-020-03207-x} }