Endre søk
Begrens søket
6789 401 - 435 of 435
RefereraExporteraLink til resultatlisten
Permanent link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Treff pr side
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sortering
  • Standard (Relevans)
  • Forfatter A-Ø
  • Forfatter Ø-A
  • Tittel A-Ø
  • Tittel Ø-A
  • Type publikasjon A-Ø
  • Type publikasjon Ø-A
  • Eldste først
  • Nyeste først
  • Skapad (Eldste først)
  • Skapad (Nyeste først)
  • Senast uppdaterad (Eldste først)
  • Senast uppdaterad (Nyeste først)
  • Disputationsdatum (tidligste først)
  • Disputationsdatum (siste først)
  • Standard (Relevans)
  • Forfatter A-Ø
  • Forfatter Ø-A
  • Tittel A-Ø
  • Tittel Ø-A
  • Type publikasjon A-Ø
  • Type publikasjon Ø-A
  • Eldste først
  • Nyeste først
  • Skapad (Eldste først)
  • Skapad (Nyeste først)
  • Senast uppdaterad (Eldste først)
  • Senast uppdaterad (Nyeste først)
  • Disputationsdatum (tidligste først)
  • Disputationsdatum (siste først)
Merk
Maxantalet träffar du kan exportera från sökgränssnittet är 250. Vid större uttag använd dig av utsökningar.
  • 401.
    Törnquist Krasemann, Johanna
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Computational decision-support for railway traffic management and associated configuration challenges: An experimental study2015Inngår i: Journal of Rail Transport Planning & Management, ISSN 2210-9706, Vol. 5, nr 3, s. 95-109, artikkel-id 10.1016/j.jrtpm.2015.09.002Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    This paper investigates potential configuration challenges in the development of optimization-based computational re-scheduling support for railway traffic networks. The paper presents results from an experimental study on how the characteristics of different situations influence the problem formulation and the resulting re-scheduling solutions. Two alternative objective functions are applied: Minimization of the delays at the end stations which exceed three minutes and minimization of delays larger than three minutes at intermediary commercial stops and at end stations. The study focuses on the congested, single-tracked Iron Ore line located in Northern Sweden. A combinatorial optimization model adapted to the special restrictions of this line is applied on 20 different disturbance scenarios and solved using commercial optimization software. The resulting re-scheduling solutions are analyzed numerically and visually in order to better understand the practical impact of using the suggested problem formulations in this context. The results show that the two alternative, objective functions result in structurally, quite different re-scheduling solutions. All scenarios were solved to optimality within 1 minute or less, which indicates that commercial solvers can handle practical problems of a relevant size for this type of setting, but the type of scenario has also a significant impact on the computation time.

  • 402.
    Törnquist Krasemann, Johanna
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Configuration of an optimization-based decision support for railway traffic management in different contexts2015Inngår i: 6th International Conference on Railway Operations Modelling and Analysis, Tokyo, March 23-26, 2015, 2015Konferansepaper (Fagfellevurdert)
    Abstract [en]

    This paper investigates potential configuration challenges in the development of optimization-based computational re-scheduling support for railway traffic networks. The paper presents results from an experimental study on how the characteristics of different situations and the network influence the problem formulation and the resulting re-scheduling solutions. Two alternative objective functions are applied: a) Minimization of the delays at the end stations which exceed three minutes and b) minimization of delays larger than three minutes at intermediary commercial stops and at end stations. The study focuses on the congested, single-tracked Iron Ore line located in Northern Sweden and partially Norway. A combinatorial optimization model adapted to the special restrictions of this line is applied and solved using commercial optimization software. 20 different disturbance scenarios are solved and the resulting re-scheduling solutions are analyzed numerically and visually in order to better understand their practical impact. The results show that the two alternative, but similar, objective functions result in structurally, quite different re-scheduling solutions. The results also show that the selected objective functions have some flaws when it comes to scheduling trains that are ahead of their schedule by early departure, or by having a lot of margin time due to waiting time in meeting/passing locations. These early trains are not always “pushed” forward unless the objective function promotes that in some way. All scenarios were solved to optimality within 1 minute or less, which indicates that commercial solvers can handle practical problems of a relevant size for this type of setting.

  • 403.
    Unterkalmsteiner, Michael
    et al.
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för programvaruteknik.
    Feldt, Robert
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för programvaruteknik.
    Gorschek, Tony
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för programvaruteknik.
    Lavesson, Niklas
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Large-scale Information Retrieval in Software Engineering - An Experience Report from Industrial Application2016Inngår i: Journal of Empirical Software Engineering, ISSN 1382-3256, E-ISSN 1573-7616, Vol. 21, nr 6, s. 2324-2365Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    Background: Software Engineering activities are information intensive. Research proposes Information Retrieval (IR) techniques to support engineers in their daily tasks, such as establishing and maintaining traceability links, fault identification, and software maintenance. Objective: We describe an engineering task, test case selection, and illustrate our problem analysis and solution discovery process. The objective of the study is to gain an understanding of to what extent IR techniques (one potential solution) can be applied to test case selection and provide decision support in a large-scale, industrial setting. Method: We analyze, in the context of the studied company, how test case selection is performed and design a series of experiments evaluating the performance of different IR techniques. Each experiment provides lessons learned from implementation, execution, and results, feeding to its successor. Results: The three experiments led to the following observations: 1) there is a lack of research on scalable parameter optimization of IR techniques for software engineering problems; 2) scaling IR techniques to industry data is challenging, in particular for latent semantic analysis; 3) the IR context poses constraints on the empirical evaluation of IR techniques, requiring more research on developing valid statistical approaches. Conclusions: We believe that our experiences in conducting a series of IR experiments with industry grade data are valuable for peer researchers so that they can avoid the pitfalls that we have encountered. Furthermore, we identified challenges that need to be addressed in order to bridge the gap between laboratory IR experiments and real applications of IR in the industry.

  • 404.
    Upadhya, Bhanu
    et al.
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Altoumaimi, Rasha
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Altoumaimi, Thelal
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Characteristics and Control of the Motor System in E-bikes2014Independent thesis Basic level (degree of Bachelor)Oppgave
    Abstract [en]

    This study is based on e-bikes, mainly the ‘Pedelecs’ (under Swedish standards). Pedelecs* is the category of e-bikes which indicates electric bicycles only, that has specific standard in terms of motor power and speed limitations. We are concerned with respect to Sweden, in the analysis, especially because though it is already defined by EU for Europeans, it still varies in some countries, within Europe itself. In this research and experiment, we have brought useful revelations about its features in terms of power, comfort and cost. Likewise, our efforts have been to test its reliability on technical grounds, geographical conditions, people’s awareness and interests. Similarly, on effective grounds, ratio of bike users, import conditions, its growth and declines trends, and other influencing factors have been analyzed to understand e-bike’s possibilities in Sweden. To highlights e-bike’s features and importance, we have done a thorough investigation, taking comparative analysis with ordinary bicycles and normal vehicles, by using common elements like cost effectiveness, power efficiency, leisure service, easy accessibility, environment effects and so on. The findings have proven e-bikes to be the most effective solution on various grounds than any other transport alternatives especially in short distance and inner city traveling. In theoretical details on e-bikes, we have introduced details about the components applicable in e-bike, how they operate, their importance in terms of effectiveness with respect to power consumption and energy dispatching (motor capacity), quality of performance (types of components and features) and other comparative technical aspects. To understand the ground reality better, a short survey have been conducted to give some understanding about the awareness people are having regarding e-bike, their remarks towards this product, and based on their conclusions, our predictions report on its development and popularity chances in Sweden. While analyzing facts in general, we discovered that pedelecs for US may not be pedelecs for Sweden, because of standard varies from country to country. According to European classification standard, a pedelec must have the motor capacity up to 250 W, and must stop the motor when the speed is above 25 km/h. Speaking about the popularity of e-bike, In China the number of e-bikes sold reached up to 200 million, Germany is leading the way in Europe, therefore by the favorable situations available in Sweden, we can predict high potential in Sweden. The statistics data proved that Sweden is a bicycle country, where the amount of bicycles sold in 2012 was around 525,000, among which 6,500 were e-bikes imported the same year, suggesting its potential of growth being real. While analyzing mathematically e-bike’s functions, the four different calculations have been analyzed, keeping the weight of the person constant, but varying other common parameters that in use, in order to personify the drag in equation. By doing so taking the average power we have observed that it requires around 157 watts going up the hill when gradient is 4%, at the speed around 10 Km/h. This result have been again tried to be verified in the experimental works as well. Based on these relevant information, in the experiment we have tested to find how much energy is dissipated in 2 minutes, taking six samples to authenticate our result. After not being successful taking angle measurements by riding outside or inside lab, it is achieved to some degree after applying it on running machine in gym with some complications. The result that have been achieved signifying that the voltage of the battery dropped to 37.8V, which in the beginning of the experiment have been recorded 40.8V when current applied have been around 4.8A. Angle measurement here precisely indicating the behavior of e-bike on various degrees of hillsides, because there comes the angle, which is formed in relation to the plane surface. When e-bike goes uphill it creates a positive angle, that is where we have our main concern, because then the difference in power consumption suddenly increases. The angle is also form when e-bike moves downhill but that is a negative angle, and cost no difference on power consumption, therefore we are giving emphasis on angle measurements to positive ones only. The battery that has been used in the experiment rated 36V/9Ah (i.e., 0.324 kWh). Using this battery we have got the reading that it can hold (when completely charged) up to 32 Km distance (or 10 Wh/km), which is inversely proportional** to rider’s weight and drag. To sum up the experiment, the results have revealed that battery performance directly depends upon whether condition, weight of the rider and area where the cycle is ridden. These are among the discovered facts found in the experiment. When e-bike is used in hilly areas the speed slows down considerably to 13km/hour, because of the disequilibrium force, and that is when excessive power is consumed. This part has been difficult to test correctly in the lab because to simulate the disequilibrium drag or pull could not be realized accurately, besides when it has been tried outdoor, we could not get stable running motor because of the pedal dependent motor system, it has also not been so fruitful for precise readings. Afterwards when it has been tried in the gym, the outcome is that at every angle the power consumed by the battery or the energy dissipated is around 3.7watt. Even then it is still not possible to calculate measurements that must be available in real like situations, because the other affected parameters like wind, friction, tire size, weather, rider’s weight is not possible to take into considerations. ___________ *Pedelec is the abbreviation form of "Pedal Electric Bicycle". The characteristics of Pedelec is to assist human input power rather than replacing it completely. **It is obvious that when the weight of the rider is heavy then it takes more power to draw him ahead, which directly indicates that the consumption of power rises, which again means that e-bike’s total covering distance is simultaneously reduced. This is also true when there is a drag, which stops e-bike’s natural flow on normal conditions. That again means it needs additional power to run, therefore when these factors rise, the efficiency of power subsequently declines, accordingly the total coverage distance of an e-bike.

  • 405.
    Usman, Muhammad
    et al.
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för programvaruteknik.
    Britto, Ricardo
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för programvaruteknik.
    Börstler, Jürgen
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för programvaruteknik.
    Mendes, Emilia
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik. Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för programvaruteknik.
    Taxonomies in software engineering: A Systematic mapping study and a revised taxonomy development method2017Inngår i: Information and Software Technology, ISSN 0950-5849, E-ISSN 1873-6025, Vol. 85, s. 43-59Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    Context: Software Engineering (SE) is an evolving discipline with new subareas being continuously developed and added. To structure and better understand the SE body of knowledge, taxonomies have been proposed in all SE knowledge areas. Objective: The objective of this paper is to characterize the state-of-the-art research on SE taxonomies. Method: A systematic mapping study was conducted, based on 270 primary studies. Results: An increasing number of SE taxonomies have been published since 2000 in a broad range of venues, including the top SE journals and conferences. The majority of taxonomies can be grouped into the following SWEBOI(knowledge areas: construction (19.55%), design (19.55%), requirements (15.50%) and maintenance (11.81%). Illustration (45.76%) is the most frequently used approach for taxonomy validation. Hierarchy (53.14%) and faceted analysis (39.48%) are the most frequently used classification structures. Most taxonomies rely on qualitative procedures to classify subject matter instances, but in most cases (86.53%) these procedures are not described in sufficient detail. The majority of the taxonomies (97%) target unique subject matters and many taxonomy-papers are cited frequently. Most SE taxonomies are designed in an ad-hoc way. To address this issue, we have revised an existing method for developing taxonomies in a more systematic way. Conclusion: There is a strong interest in taxonomies in SE, but few taxonomies are extended or revised. Taxonomy design decisions regarding the used classification structures, procedures and descriptive bases are usually not well described and motivated. (C) 2017 The Authors. Published by Elsevier B.V.

  • 406.
    Usman, Muhammad
    et al.
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för programvaruteknik.
    Börstler, Jürgen
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för programvaruteknik.
    Mendes, Emilia
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Effort estimation in agile software development: a survey on the state of the practice2015Inngår i: Proceedings of the 19th International Conference on Evaluation and Assessment in Software Engineering (EASE 2015), ACM Digital Library, 2015Konferansepaper (Fagfellevurdert)
  • 407.
    Usman, Muhammad
    et al.
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för programvaruteknik.
    Mendes, Emilia
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Weidt, Francila
    Britto, Ricardo
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för programvaruteknik.
    Effort estimation in agile software development: a systematic literature review2014Inngår i: Proceedings of the 10th International Conference on Predictive Models in Software Engineering, 2014, s. 82-91Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Context: Ever since the emergence of agile methodologies in 2001, many software companies have shifted to Agile Software Development (ASD), and since then many studies have been conducted to investigate effort estimation within such context; however to date there is no single study that presents a detailed overview of the state of the art in effort estimation for ASD. Objectives: The aim of this study is to provide a detailed overview of the state of the art in the area of effort estimation in ASD. Method: To report the state of the art, we conducted a systematic literature review in accordance with the guidelines proposed in the evidence-based software engineering literature.Results: A total of 25 primary studies were selected; the main findings are: i) Subjective estimation techniques (e.g. expert judgment, planning poker, use case points estimation method) are the most frequently applied in an agile context; ii) Use case points and story points are the most frequently used size metrics respectively; iii) MMRE (Mean Magnitude of Relative Error) and MRE (Magnitude of Relative Error) are the most frequently used accuracy metrics; iv) team skills, prior experience and task size are cited as the three important cost drivers for effort estimation in ASD; and v) Extreme Programming (XP) and SCRUM are the only two agile methods that are identified in the primary studies. Conclusion: Subjective estimation techniques, e.g. expert judgment-based techniques, planning poker or the use case points method, are the one used the most in agile effort estimation studies. As for the size metrics, the ones that were used the most in the primary studies were story points and use case points. Several research gaps were identified, relating to the agile methods, size metrics and cost drivers, thus suggesting numerous possible avenues for future work.

  • 408.
    vadlamudi, jithin chand
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    How a Discrete event simulation model can relieve congestion at a RORO terminal gate system: Case study: RORO port terminal in the Port of Karlshamn.2016Independent thesis Advanced level (degree of Master (Two Years)), 20 poäng / 30 hpOppgave
    Abstract [en]

    Context. Due to increase in demand for RORO shipping services,the RORO terminal gate system need to handle more number of vehicles for every RORO vessel departure. Therefore, various congestion problems can occur; so, to address all possible congestion related problemsat RORO terminal, terminal gate systems are implemented with advanced technologies and updated to full or partial functioning automated gate systems.

    Objectives. In this research study considering the future increase in demand for wheeled cargo shipping, we attempt to propose a solution for reducing congestion and investigating optimal positions for each automated gate system service at RORO port terminal.

    Methods. In this Master thesis, as part of qualitative study we conduct a literature review and case study to know about the existing related work on this research problem and know about the real world system operation and behaviour of a RORO terminal gate system.Later, applying the adequate knowledge acquired from above mentioned qualitative studies, we perform a discrete event simulation experiment using Anylogic® professional 7.02 simulation software to address defined research objectives.

    Results. Considering the peak and low periods of present and future estimated demand volumes as different scenarios,various simulation experiment results are generated for different key performance indicators. The result values of these key performance indicators address various research objectives.

    Conclusions. This research study finally concludes that, the average queue length values at each automated gate system service implicates optimal position for each service and directly address the congestion problem. We also conclude that in every estimated increase in vehicles attending the RORO terminal, assigning optimal arrival time windows for respective vehicle types minimizes the congestion problem at automated gate system.

  • 409.
    van der Mei, Rob
    et al.
    Centrum Wiskunde and Informatica (CWI), NLD.
    van den Berg, Hans
    TNO, NLD.
    Ganchev, Ivan
    University of Limerick, IRE.
    Tutschku, Kurt Tutschku
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Leitner, Philipp
    University of Zurich, CHE.
    Lassila, Pasi
    Aalto University, FIN.
    Burakowski, Wojciech
    Warsaw University of Technology, POL.
    Liberal, Fidel
    University of the Basque Country (UPV/EHU), ESP.
    Arvidsson, Åke
    Kristianstad University, SWE.
    Hoßfeld, Tobias
    lInstitute of Computer Science and Business Information Systems (ICB), DEU.
    Wac, Katarzyna
    University of Geneva, CHE.
    Melvin, Hugh
    National University of Ireland, IRE.
    Galinac Grbac, Tihana
    University of Rijeka, HRV.
    Haddad, Yoram
    JCT-Lev Academic Center, ISR.
    Key, Peter
    Microsoft Research Ltd., GBR.
    State of the Art and Research Challenges in the Area of Autonomous Control for a Reliable Internet of Services2018Inngår i: Autonomous Control for a Reliable Internet of Services: Methods, Models, Approaches, Techniques, Algorithms, and Tools / [ed] Ganchev, Ivan, van der Mei, Robert D., van den Berg, J.L., Springer Publishing Company, 2018Kapittel i bok, del av antologi (Fagfellevurdert)
    Abstract [en]

    The explosive growth of the Internet has fundamentally changed the global society. The emergence of concepts like service-oriented architecture (SOA), Software as a Service (SaaS), Platform as a Service (PaaS), Infrastructure as a Service (IaaS), Network as a Service (NaaS) and Cloud Computing in general has catalyzed the migration from the information-oriented Internet into an Internet of Services (IoS). This has opened up virtually unbounded possibilities for the creation of new and innovative services that facilitate business processes and improve the quality of life. However, this also calls for new approaches to ensuring quality and reliability of these services. The goal of this book chapter is to first analyze the state-of-the-art in the area of autonomous control for a reliable IoS and then to identify the main research challenges within it. A general background and high-level description of the current state of knowledge is presented. Then, for each of the three subareas, namely the autonomous management and real-time control, methods and tools for monitoring and service prediction, and smart pricing and competition in multi-domain systems, a brief general introduction and background are presented, and a list of key research challenges is formulated.

  • 410.
    VANGALA, SHIVAKANTHREDDY
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Pattern Recognition applied to Continuous integration system.2018Independent thesis Advanced level (degree of Master (Two Years)), 20 poäng / 30 hpOppgave
    Abstract [en]

    Context: Thisthesis focuses on regression testing in the continuous integration environment which is integration testing that ensures that changes made in the new development code to thesoftware product do not introduce new faults to the software product. Continuous integration is software development practice which integrates all development, testing, and deployment activities. In continuous integration,regression testing is done by manually selecting and prioritizingtestcases from a larger set of testcases. The main challenge faced using manual testcases selection and prioritization is insome caseswhereneeded testcases are ignored in subset of selected testcasesbecause testers didn’t includethem manually while designing hourly cycle regression test suite for particular feature development in product. So, Ericsson, the company in which environment this thesis is conducted,aims at improvingtheirtestcase selection and prioritization in regression testing using pattern recognition.

    Objectives:This thesis study suggests prediction models using pattern recognition algorithms for predicting future testcases failures using historical data. This helpsto improve the present quality of continuous integration environment by selecting appropriate subset of testcases from larger set of testcases for regression testing. There exist several candidate pattern recognition algorithms that are promising for predicting testcase failures. Based on the characteristics of the data collected at Ericsson, suitable pattern recognition algorithms are selected and predictive models are built. Finally, two predictive models are evaluated and the best performing model is integrated into the continuous integration system.

    Methods:Experiment research method is chosen for this research because discovery of cause and effect relationships between dependent and independent variables can be used for the evaluation of the predictive model.The experiment is conducted in RStudio, which facilitates to train the predictive models using continuous integration historical data. The predictive ability of the algorithms is evaluated using prediction accuracy evaluation metrics.

    Results: After implementing two predictive models (neural networks & k-nearest means) using continuous integration data, neural networks achieved aprediction accuracy of 75.3%, k-nearest neighbor gave result 67.75%.

    Conclusions: This research investigated the feasibility of an adaptive and self-learning test machinery by pattern recognition in continuous integration environment to improve testcase selection and prioritization in regression testing. Neural networks have proved effective capability of predicting failure testcase by 75.3% over the k-nearest neighbors.Predictive model can only make continuous integration efficient only if it has 100% prediction capability, the prediction capability of the 75.3% will not make continuous integration system more efficient than present static testcase selection and prioritization as it has deficiency of lacking prediction 25%. So, this research can only conclude that neural networks at present has 75.3% prediction capability but in future when data availability is more,this may reach to 100% predictive capability. The present Ericsson continuous integration system needs to improve its data storage for historical data at present it can only store 30 days of historical data. The predictive models require large data to give good prediction. To support continuous integration at present Ericsson is using jenkins automation server, there are other automation servers like Team city, Travis CI, Go CD, Circle CI which can store data more than 30 days using them will mitigate the problem of data storage.

  • 411.
    Vellanki, Mohit
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Performance Evaluation of Cassandra in a Virtualized Environment2017Independent thesis Advanced level (degree of Master (Two Years)), 20 poäng / 30 hpOppgave
    Abstract [en]

    Context. Apache Cassandra is an open-source, scalable, NoSQL database that distributes the data over many commodity servers. It provides no single point of failure by copying and storing the data in different locations. Cassandra uses a ring design rather than the traditional master-slave design.

    Virtualization is the technique using which physical resources of a machine are divided and utilized by various virtual machines. It is the fundamental technology, which allows cloud computing to provide resource sharing among the users.

     Objectives. Through this research, the effects of virtualization on Cassandra are observed by comparing the virtual machine arrangement to physical machine arrangement along with the overhead caused by virtualization.

     Methods. An experiment is conducted in this study to identify the aforementioned effects of virtualization on Cassandra compared to the physical machines. Cassandra runs on physical machines with Ubuntu 14.04 LTS arranged in a multi node cluster. Results are obtained by executing the mixed, read only and write only operations in the Cassandra stress tool on the data populated in this cluster. This procedure is repeated for 100% and 66% workload. The same procedure is repeated in virtual machines cluster and the results are compared.

     Results. Virtualization overhead has been identified in terms of CPU utilization and the effects of virtualization on Cassandra are found out in terms of Disk utilization, throughput and latency.

     Conclusions. The overhead caused due to virtualization is observed and the effect of this overhead on the performance of Cassandra has been identified. The consequence of the virtualization overhead has been related to the change in performance of Cassandra.

  • 412.
    Vesterlund, Martin
    et al.
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Wiklund, Viktor
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Is this your smart phone?: On connecting MAC-addresses to a specific individual using access point data2015Independent thesis Advanced level (professional degree), 20 poäng / 30 hpOppgave
    Abstract [en]

    Context. The potential to track individuals become greater and greater in the society today. We want to develop a method that is easy to understand so more people can participate in the discussion about the collection, and storing, of seemingly non-invasive device data and personal integrity.

    Objectives. In this work we investigate the potential to connect a WiFi enabled device to a known individual by analysing log files. Since we want to keep the method as simple as possible we choose to not use machine learning because this might add unnecessary layers of complexity.

    Methods. The conducted experiments were performed against a test group consisting of six persons. The dataset used consisted of authentication logs from a university WiFi-network collected during a month and data acquired by capturing WiFi-traffic.

    Results. We were able to connect 67% of the targeted test persons to their smart phones and 60% to their laptops.

    Conclusions. In this work we conclude that a device identifier in combination with data that can tie it to a location at a given time is to be seen as sensitive information with regard to personal integrity. We also conclude that it is possible to create and use an easy method to connect a device to a given person.

  • 413.
    Vishnubhotla, Sai Datta
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Supplementary Material of: "An insight into the capabilities of professionals and teams in agile software development - A systematic literature review"2017Annet (Annet (populærvitenskap, debatt, mm))
    Abstract [en]

    This document contains the supplementary material regarding the systematic literature review titled: "An insight into the capabilities of professionals and teams in agile software development" 

  • 414.
    Vishnubhotla, Sai Datta
    et al.
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Mendes, Emilia
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik. Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för programvaruteknik.
    Lundberg, Lars
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    An insight into the capabilities of professionals and teams in agile software development: A systematic literature review2018Inngår i: PROCEEDINGS OF 2018 7TH INTERNATIONAL CONFERENCE ON SOFTWARE AND COMPUTER APPLICATIONS (ICSCA 2018), Association for Computing Machinery , 2018, s. 10-19Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Background: Previous studies investigated key characteristics of software engineers and factors influencing the performance of individuals, productivity of teams and project success within agile software development (ASD). They aided in the active investigation of human aspects in ASD. However, capability measurement and prediction with respect to agile workforce, owing to its importance, is an area that needs spotlight. Objective: The objective of this paper is to present the state of the art relating to capability measurement of software engineers and teams working in ASD projects. Method: We carried out a systematic literature review (SLR) focused on identifying attributes used for measuring and predicting the capabilities of individual software engineers and teams. Results: Evidence from 16 studies showed attributes that can measure capabilities of engineers and teams, and also attributes that can be used as capability predictors. Further, different instruments used to measure those attributes were presented. Conclusions: The SLR presented a wide list of attributes that were grouped into various categories. This information can be used by project managers as, for example, a checklist to consider when allocating software engineers to teams and in turn teams to a project. Further, this study indicated the necessity for an investigation into capability prediction models. © 2018 Association for Computing Machinery.

  • 415.
    Vishnubhotla, Sai Datta
    et al.
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Mendes, Emilia
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik. Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för programvaruteknik.
    Lundberg, Lars
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Designing a capability-centric web tool to support agile team composition and task allocation: A work in progress2018Inngår i: 2018 IEEE/ACM 11TH INTERNATIONAL WORKSHOP ON COOPERATIVE AND HUMAN ASPECTS OF SOFTWARE ENGINEERING (CHASE), IEEE Computer Society , 2018, Vol. F137813, s. 41-44Konferansepaper (Fagfellevurdert)
    Abstract [en]

    A significant number of studies reported models for competence profiling, measuring capabilities of professionals and recommendation systems for roles within agile software development (ASD). These models coordinated in human resource management within ASD. However, in the light of swift, incremental and iterative nature of ASD practices, designing solutions that easily integrate capability measurements with ongoing project management routines, is an important area for investigation. With the support of interviews, grounded theory procedure and workshops, we identified the aspects valued by our industrial collaborator while allocating professionals to tasks. This information was further utilized towards devising a framework for capability-centric Web tool. This tool provides a one-stop solution for project managers to create projects, keep track of capabilities and execute allocation routines. © 2018 ACM.

  • 416.
    Vishnumolakala, Bandhavi
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Performance Evaluation of Gaming Anywhere Server in a Virtual Environment2018Independent thesis Advanced level (degree of Master (One Year)), 20 poäng / 30 hpOppgave
    Abstract [en]

    In the recent years, cloud services are dominating the internet world. Streaming video content is drastically increased. This trend created a way for the cloud gaming industry. Gaming Anywhere is one such an open source cloud gaming system designed specifically for gaming users to experience high-quality gaming while eliminating the burden of upgrading hardware or software whenever the gaming system becomes outdated. Gaming Anywhere client can stream the desired game from a remote server with high-quality resolution and fps. Gaming Anywhere launches almost all type of games as per the request of the client.

    In this paper, the performance of a Gaming Anywhere server is evaluated in a virtual windows environment. Performance is categorically divided into two types. One is server metrics and the other is power consumption. Server metrics deals with CPU utilization, GPU utilization and multi-player capability. Power consumption deals with the CPU power usage of a virtual machine. The main aim of this paper is to conduct measurement studies on Gaming Anywhere server in two virtual implementation kits, VMware and VirtualBox, using monitoring tools. The analysis of the outcome is evaluated against the Gaming Anywhere physical server.

  • 417.
    Wang, Teng
    et al.
    University of California - Davis, USA.
    Erlandsson, Fredrik
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Wu, Shyhtsun Felix
    University of California - Davis, USA.
    Mining User Deliberation and Bias in Online Newsgroups: A Dynamic View2015Inngår i: Proceedings of the 2015 ACM on Conference on Online Social Networks, ACM , 2015, s. 209-219Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Social media is changing many different aspects of our lives. By participating in online discussions, people exchange opinions on various topics, shape their stances, and gradually form their own characteristics. In this paper, we propose a framework for identifying online user characteristics and understanding the formation of user deliberation and bias in online newsgroups. In the first section of the paper, we propose a dynamic user-like graph model for recognizing user deliberation and bias automatically in online newsgroups. In addition, we evaluate our identification results with linguistic features and implement this model in our SINCERE system as a real-time service. In the second section, after applying this model to two large online newsgroups, we analyze the influence of early discussion context on the formation of user characteristics. Our conclusion is that user deliberation and bias are a product of situations, not simply dispositions: confronting disagreement in unfamiliar circumstances promotes more consideration of different opinions, while recurring conflict in familiar circumstances evokes close-minded behavior and bias. Based on this observation, we also build a supervised learning model to predict user deliberation and bias at an early online life-stage. Our results show that having only the first three months of users' interaction data generates an F1 accuracy level of around 70% in predicting user deliberation and bias in online newsgroups. This work has practical significance for people who design and maintain online newsgroups. It yields new insights into opinion diffusion and has wide potential applications in politics, education, and online social media.

  • 418. Wang, Teng
    et al.
    Wang, K. C.
    Erlandsson, Fredrik
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Wu, S. Felix
    Faris, Robert W.
    The influence of feedback with different opinions on continued user participation in online newsgroups2013Inngår i: Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2013, IEEE Computer Society, 2013, s. 388-395Konferansepaper (Fagfellevurdert)
    Abstract [en]

    With the popularity of social media in recent years, it has been a critical topic for social network designer to understand the factors that influence continued user participation in online newsgroups. Our study examines how feedback with different opinions is associated with participants' lifetime in online newsgroups. Firstly, we propose a new method of classifying different opinions among user interaction contents. Generally, we leverage user behavior information in online newsgroups to estimate their opinions and evaluate our classification results based on linguistic features. In addition, we also implement this opinion classification method into our SINCERE system as a real-time service. Based on this opinion classification tool, we use survival analysis to examine how others' feedback with different opinions influence continued participation. In our experiment, we analyze more than 88,770 interactions on the official Occupy LA Facebook page. Our final result shows that not only the feedback with the same opinions as the user, but also the feedback with different opinions can motivate continued user participation in online newsgroup. Furthermore, an interaction of feedback with both the same and different opinions can boost user continued participation to the greatest extent. This finding forms the basis of understanding how to improve online service in social media. Copyright 2013 ACM.

  • 419.
    Westphal, Florian
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Efficient Document Image Binarization using Heterogeneous Computing and Interactive Machine Learning2018Licentiatavhandling, med artikler (Annet vitenskapelig)
    Abstract [en]

    Large collections of historical document images have been collected by companies and government institutions for decades. More recently, these collections have been made available to a larger public via the Internet. However, to make accessing them truly useful, the contained images need to be made readable and searchable. One step in that direction is document image binarization, the separation of text foreground from page background. This separation makes the text shown in the document images easier to process by humans and other image processing algorithms alike. While reasonably well working binarization algorithms exist, it is not sufficient to just being able to perform the separation of foreground and background well. This separation also has to be achieved in an efficient manner, in terms of execution time, but also in terms of training data used by machine learning based methods. This is necessary to make binarization not only theoretically possible, but also practically viable.

    In this thesis, we explore different ways to achieve efficient binarization in terms of execution time by improving the implementation and the algorithm of a state-of-the-art binarization method. We find that parameter prediction, as well as mapping the algorithm onto the graphics processing unit (GPU) help to improve its execution performance. Furthermore, we propose a binarization algorithm based on recurrent neural networks and evaluate the choice of its design parameters with respect to their impact on execution time and binarization quality. Here, we identify a trade-off between binarization quality and execution performance based on the algorithm’s footprint size and show that dynamically weighted training loss tends to improve the binarization quality. Lastly, we address the problem of training data efficiency by evaluating the use of interactive machine learning for reducing the required amount of training data for our recurrent neural network based method. We show that user feedback can help to achieve better binarization quality with less training data and that visualized uncertainty helps to guide users to give more relevant feedback.

  • 420.
    Westphal, Florian
    et al.
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Axelsson, Stefan
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Neuhaus, Christian
    Polze, Andreas
    VMI-PL: A monitoring language for virtual platforms using virtual machine introspection2014Inngår i: Digital Investigation. The International Journal of Digital Forensics and Incident Response, ISSN 1742-2876, E-ISSN 1873-202X, Vol. 11, s. S85-S94 Supplement: 2Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    With the growth of virtualization and cloud computing, more and more forensic investigations rely on being able to perform live forensics on a virtual machine using virtual machine introspection (VMI). Inspecting a virtual machine through its hypervisor enables investigation without risking contamination of the evidence, crashing the computer, etc. To further access to these techniques for the investigator/researcher we have developed a new VMI monitoring language. This language is based on a review of the most commonly used VMI-techniques to date, and it enables the user to monitor the virtual machine's memory, events and data streams. A prototype implementation of our monitoring system was implemented in KVM, though implementation on any hypervisor that uses the common x86 virtualization hardware assistance support should be straightforward. Our prototype outperforms the proprietary VMWare VProbes in many cases, with a maximum performance loss of 18% for a realistic test case, which we consider acceptable. Our implementation is freely available under a liberal software distribution license.

  • 421.
    Westphal, Florian
    et al.
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Grahn, Håkan
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Lavesson, Niklas
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Efficient document image binarization using heterogeneous computing and parameter tuning2018Inngår i: International Journal on Document Analysis and Recognition, ISSN 1433-2833, E-ISSN 1433-2825, Vol. 21, nr 1-2, s. 41-58Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    In the context of historical document analysis, image binarization is a first important step, which separates foreground from background, despite common image degradations, such as faded ink, stains, or bleed-through. Fast binarization has great significance when analyzing vast archives of document images, since even small inefficiencies can quickly accumulate to years of wasted execution time. Therefore, efficient binarization is especially relevant to companies and government institutions, who want to analyze their large collections of document images. The main challenge with this is to speed up the execution performance without affecting the binarization performance. We modify a state-of-the-art binarization algorithm and achieve on average a 3.5 times faster execution performance by correctly mapping this algorithm to a heterogeneous platform, consisting of a CPU and a GPU. Our proposed parameter tuning algorithm additionally improves the execution time for parameter tuning by a factor of 1.7, compared to previous parameter tuning algorithms. We see that for the chosen algorithm, machine learning-based parameter tuning improves the execution performance more than heterogeneous computing, when comparing absolute execution times. © 2018 The Author(s)

  • 422.
    Westphal, Florian
    et al.
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Grahn, Håkan
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Lavesson, Niklas
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    User Feedback and Uncertainty in Interactive BinarizationManuskript (preprint) (Annet vitenskapelig)
    Abstract [en]

    A major challenge in document image binarization is the large variety in appearance of images from different document collections. This is especially challenging for parameterless, machine learning based binarization algorithms, which require additional ground truth training data to generalize or fine-tune to a new image collection. Reducing this costly labeling effort is relevant to companies and government institutions, which possess many different document image collections. One approach to address this problem is interactive machine learning, which enables a user to guide the fine-tuning process by providing feedback on the produced binarization result.

    In this paper, we evaluate the claim that user guided training requires less labeled samples to fine-tune a basic model for binarization to a new image collection. Further, we propose a way to guide user feedback by visualizing the model’s labeling uncertainty and analyze the relationship between model uncertainty and binarization quality. Our experiments show that user feedback biases the model towards favoring foreground labels, which results in less erased text and thus better readability than when training samples are chosen randomly. Additionally, we find that model uncertainty serves as a useful guide for users and explain how the Dunning-Kruger effect prevents model uncertainty from being useful for automated sample selection.

  • 423.
    Westphal, Florian
    et al.
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Grahn, Håkan
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Lavesson, Niklas
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    User Feedback and Uncertainty in User Guided Binarization2018Inngår i: International Conference on Data Mining Workshops / [ed] Tong, H; Li, Z; Zhu, F; Yu, J, IEEE Computer Society, 2018, s. 403-410, artikkel-id 8637367Konferansepaper (Fagfellevurdert)
    Abstract [en]

    In a child’s development, the child’s inherent ability to construct knowledge from new information is as important as explicit instructional guidance. Similarly, mechanisms to produce suitable learning representations, which can be trans- ferred and allow integration of new information are important for artificial learning systems. However, equally important are modes of instructional guidance, which allow the system to learn efficiently. Thus, the challenge for efficient learning is to identify suitable guidance strategies together with suitable learning mechanisms.

    In this paper, we propose guided machine learning as source for suitable guidance strategies, we distinguish be- tween sample selection based and privileged information based strategies and evaluate three sample selection based strategies on a simple transfer learning task. The evaluated strategies are random sample selection, i.e., supervised learning, user based sample selection based on readability, and user based sample selection based on readability and uncertainty. We show that sampling based on readability and uncertainty tends to produce better learning results than the other two strategies. Furthermore, we evaluate the use of the learner’s uncertainty for self directed learning and find that effects similar to the Dunning-Kruger effect prevent this use case. The learning task in this study is document image binarization, i.e., the separation of text foreground from page background and the source domain of the transfer are texts written on paper in Latin characters, while the target domain are texts written on palm leaves in Balinese script.

  • 424.
    Westphal, Florian
    et al.
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Lavesson, Niklas
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Grahn, Håkan
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Document Image Binarization Using Recurrent Neural Networks2018Inngår i: Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018, IEEE, 2018, s. 263-268Konferansepaper (Fagfellevurdert)
    Abstract [en]

    In the context of document image analysis, image binarization is an important preprocessing step for other document analysis algorithms, but also relevant on its own by improving the readability of images of historical documents. While historical document image binarization is challenging due to common image degradations, such as bleedthrough, faded ink or stains, achieving good binarization performance in a timely manner is a worthwhile goal to facilitate efficient information extraction from historical documents. In this paper, we propose a recurrent neural network based algorithm using Grid Long Short-Term Memory cells for image binarization, as well as a pseudo F-Measure based weighted loss function. We evaluate the binarization and execution performance of our algorithm for different choices of footprint size, scale factor and loss function. Our experiments show a significant trade-off between binarization time and quality for different footprint sizes. However, we see no statistically significant difference when using different scale factors and only limited differences for different loss functions. Lastly, we compare the binarization performance of our approach with the best performing algorithm in the 2016 handwritten document image binarization contest and show that both algorithms perform equally well.

  • 425.
    Wnuk, Krzysztof
    et al.
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för programvaruteknik.
    Mendes, Emilia
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    The Project management perspective on Software Value: A Literature Review2015Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Context: To remain competitive, innovative and to grow, companies must change from cost-based decision-making to value-based decision-making where the decisions taken maximize software value and support company’s overall value creation. Objective: The objective of this paper is to complement and expand an existing classification of value aspects within the context of product management and development with additional aspects relating to value within the context of project management and development. Method: In this study, we present the results from a snowballing literature review that focuses on software value in software project management. In the research for relevance literature we focus on software value aspects different than cost. Results: We have identified nine primary studies in two snowball iterations. From these studies, we derived three categories of value aspects: financial, risk analysis and process improvement based on value identification.

  • 426.
    WoldeMichael, Helina Getachew
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Deployment of AI Model inside Docker on ARM-Cortex-based Single-Board Computer: Technologies, Capabilities, and Performance2018Independent thesis Advanced level (degree of Master (Two Years)), 20 poäng / 30 hpOppgave
    Abstract [en]

    IoT has become tremendously popular. It provides information access, processing and connectivity for a huge number of devices or sensors. IoT systems, however, often do not process the information locally, rather send the information to remote locations in the Cloud. As a result, it adds huge amount of data traffic to the network and additional delay to data processing. The later feature might have significant impact on applications that require fast response times, such as sophisticated artificial intelligence (AI) applications including Augmented reality, face recognition, and object detection. Consequently, edge computing paradigm that enables computation of data near the source has gained a significant importance in achieving a fast response time in the recent years. IoT devices can be employed to provide computational resources at the edge of the network near the sensors and actuators. The aim of this thesis work is to design and implement a kind of edge computing concept that brings AI models to a small embedded IoT device by the use of virtualization concepts. The use of virtualization technology enables the easy packing and shipping of applications to different hardware platforms. Additionally, this enable the mobility of AI models between edge devices and the Cloud. We will implement an AI model inside a Docker container, which will be deployed on a FireflyRK3399 single-board computer (SBC). Furthermore, we will conduct CPU and memory performance evaluations of Docker on Firefly-RK3399. The methodology adopted to reach to our goal is experimental research. First, different literatures have been studied to demonstrate by implementation the feasibility of our concept. Then we setup an experiment that covers measurement of performance metrics by applying synthetic load in multiple scenarios. Results are validated by repeating the experiment and statistical analysis. Results of this study shows that, an AI model can successfully be deployed and executed inside a Docker container on Arm-Cortex-based single-board computer. A Docker image of OpenFace face recognition model is built for ARM architecture of the Firefly SBC. On the other hand, the performance evaluation reveals that the performance overhead of Docker in terms of CPU and Memory is negligible. The research work comprises the mechanisms how AI application can be containerized in ARM architecture. We conclude that the methods can be applied to containerize software application in ARM based IoT devices. Furthermore, the insignificant overhead brought by Docker facilitates for deployment of applications inside a container with less performance overhead. The functionality of IoT device i.e. Firefly-RK3399 is exploited in this thesis. It is shown that the device is capable and powerful and gives an insight for further studies. 

  • 427.
    Wozny, Dawid
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Time-Varying Motion Pattern Detection with Application in Coaching and Rehabilitation2014Independent thesis Advanced level (degree of Master (Two Years))Oppgave
    Abstract [en]

    MS Kinect premiere has introduced new possibilities in the field of motion capture and has inspired many researchers to use it in coaching or rehabilitation support systems. Nonetheless, the majority of researches have been focused on game development and do not emphasize on motion analysis. In this thesis a set of tools are provided to detect certain motion pattern for rehabilitation, coaching or other similar area. A novel set of tracking signals, originated from joints data of body movement, along with their selection algorithm is proposed. The signals are utilized by a novel time-varying motion pattern detection algorithm which operates in the time domain and only needs one sample of a training pattern. The performance of the algorithm is evaluated on a group of five people performing seven types of exercises 10 times each, giving 350 samples. The performance evaluation shows significant success of the proposed algorithm. Also in spite of low recall factors, the results promise the high potential of future use of the algorithm. Finally, an interactive software application was created to record movement, create the reference pattern and perform coaching of individual movements.

  • 428.
    Yao, Yong
    et al.
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Popescu, Adrian
    Blekinge Tekniska Högskola.
    On Energy Consumption in Mobile Multimedia Networks with OpwnFlow Switch2016Inngår i: International Conference on Communications (COMM), 2016, IEEE, 2016Konferansepaper (Fagfellevurdert)
    Abstract [en]

    With the advance of new wireless technologies and ubiquitous radio access, mobile multimedia is becoming a very important application for both service providers and end users. This also leads to different business models such as mobile television, mobile conferencing, and remote gaming. A Mobile Multimedia Network (MMN) generally refers to several parts, which are known as the video contribution, the network distribution and the mobile terminals. The video contribution is connected to the functions of generating and processing the video content, which is eventually transferred onto the network for further distribution to mobile terminals.

  • 429.
    Yao, Yong
    et al.
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Popescu, Adrian
    Blekinge Tekniska Högskola.
    Fiedler, Markus
    Blekinge Tekniska Högskola.
    Ljung, Rickard
    Sony Mobile Communications, SWE.
    On the Performance of Video Streaming in Energy-Aware Wireless Mesh Networks2017Inngår i: European Conference on Networks and Communications (EuCNC) 2017, IEEE, 2017Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Mobile multimedia has today become a promising application for end users and service providers. With reference to the existing systems for mobile communications, this application further demands for solving several technical problems, especially regarding video streaming over wireless networks. An interesting approach is in form ofWireless Mesh Network (WMN) based networks, where the individual video flows operate in an end-to-end (e2e) manner along a particular networking scenario including several mesh routers. That means, a particular mesh router may be traversed by multiple video flows. This situation may become even more complicated in the case of a large amount of packet retransmissions, which may deteriorate the performance of video flows. To investigate this problem, a two-level Modulated Markov Poisson Process (MMPP) based queueing model is built up and the transport performance of e2e video streaming in WMN based mobile multimedia system is analysed. Four metrics are used to study the system performance, namely e2e throughput, e2e delay, e2e error-rate and traffic-related energy consumption. Numerical analysis and evaluation studies are done. Based on the reported results, two different solutions are suggested and discussed with regard to the trade-off among these metrics.

  • 430.
    Yasar, Fatma Gunseli
    et al.
    Izmir Katip Celebi Universitesi, TUR.
    Kusetogullari, Hüseyin
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Underwater human body detection using computer vision algorithms2018Inngår i: 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018, Institute of Electrical and Electronics Engineers Inc. , 2018, s. 1-4Konferansepaper (Fagfellevurdert)
    Abstract [en]

    The number of studies to ensure the security when life-threatening unexpected events are encountered increases. Increasing of time spent under the water can cause the death of people. Thus, people who are in a risk of suffocation in the water must be found for early intervention and this process must be quick. The main contribution of this study is to detect and to track the people under the water quickly. Thresholding, Background Subtraction, Interframe Difference and Foreground Detection methods have been applied to create the silhouette of the people under the water. These methods have been demonstrated on videos which are found from internet. © 2018 IEEE.

  • 431.
    Yavariabdi, Amir
    et al.
    Karatay Üniversitesi, TUR.
    Kusetogullari, Hüseyin
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Mendi, Engin
    Karatay Üniversitesi, TUR.
    Karabatak, Begum
    Turkcell, Nicosia, CYP.
    Unsupervised Change Detection using Thin Cloud-Contaminated Landsat Images2018Inngår i: 9th International Conference on Intelligent Systems 2018: Theory, Research and Innovation in Applications, IS 2018 - Proceedings / [ed] JardimGoncalves, R; Mendonca, JP; Jotsov, V; Marques, M; Martins, J; Bierwolf, R, Institute of Electrical and Electronics Engineers Inc. , 2018, s. 21-25Konferansepaper (Fagfellevurdert)
    Abstract [en]

    In this paper, a novel unsupervised change detection method is proposed to automatically detect changes between two cloud-contaminated Landsat images. To achieve this, firstly, a photometric invariants technique with Stationary Wavelet Transform (SWT) are applied to input images to decrease the influence of cloud and noise artifacts in the change detection process. Then, mean shift image filtering is employed on the sub-band difference images, generated via image differencing technique, to smooth the images. Next, multiple binary change detection masks are obtained by partitioning the pixels in each of the smoothed sub-band difference images into two clusters using Fuzzy c-means (FCM). Finally, the binary masks are fused using Markov Random Field (MRF) to generate the final solution. Experiments on both semi-simulated and real data sets show the effectiveness and robustness of the proposed change detection method in noisy and cloud-contaminated Landsat images. © 2018 IEEE.

  • 432.
    Yilmaz, Gulay
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Sound Source Localization by Using Two Microphones2014Oppgave
    Abstract [en]

    This thesis work presents the way of locating the sound source by using two microphone. The idea to approach the goal is based on the Time di fference of Arrival Estimation (TDOA). There are several ways to the TDOA such as the generalized cross-correlation (GCC) and Steered Response Power (SRP).The most common technique used in TDOA estimation is the generalized cross-correlation (GCC). But Steered Response Power PHAT (SRP-PHAT) together with the Windowed Discrete Fourier Transform(WDFT) are mainly focused on this thesis work.

  • 433.
    Zeid Baker, Mousa
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Generation of Synthetic Images with Generative Adversarial Networks2018Independent thesis Advanced level (degree of Master (Two Years)), 20 poäng / 30 hpOppgave
    Abstract [en]

    Machine Learning is a fast growing area that revolutionizes computer programs by providing systems with the ability to automatically learn and improve from experience. In most cases, the training process begins with extracting patterns from data. The data is a key factor for machine learning algorithms, without data the algorithms will not work. Thus, having sufficient and relevant data is crucial for the performance.

    In this thesis, the researcher tackles the problem of not having a sufficient dataset, in terms of the number of training examples, for an image classification task. The idea is to use Generative Adversarial Networks to generate synthetic images similar to the ground truth, and in this way expand a dataset. Two types of experiments were conducted: the first was used to fine-tune a Deep Convolutional Generative Adversarial Network for a specific dataset, while the second experiment was used to analyze how synthetic data examples affect the accuracy of a Convolutional Neural Network in a classification task. Three well known datasets were used in the first experiment, namely MNIST, Fashion-MNIST and Flower photos, while two datasets were used in the second experiment: MNIST and Fashion-MNIST.

    The results of the generated images of MNIST and Fashion-MNIST had good overall quality. Some classes had clear visual errors while others were indistinguishable from ground truth examples. When it comes to the Flower photos, the generated images suffered from poor visual quality. One can easily tell the synthetic images from the real ones. One reason for the bad performance is due to the large quantity of noise in the Flower photos dataset. This made it difficult for the model to spot the important features of the flowers.

    The results from the second experiment show that the accuracy does not increase when the two datasets, MNIST and Fashion-MNIST, are expanded with synthetic images. This is not because the generated images had bad visual quality, but because the accuracy turned out to not be highly dependent on the number of training examples.

    It can be concluded that Deep Convolutional Generative Adversarial Networks are capable of generating synthetic images similar to the ground truth and thus can be used to expand a dataset. However, this approach does not completely solve the initial problem of not having adequate datasets because Deep Convolutional Generative Adversarial Networks may themselves require, depending on the dataset, a large quantity of training examples.

  • 434.
    Zhang, Yiran
    et al.
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Liu, Xiaohui
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Design of Eco-Smart Homes For Elderly Independent Living2015Independent thesis Advanced level (degree of Master (One Year))Oppgave
    Abstract [en]

    The aging of the world population has increased dramatically during the past century. The rapid increase of elderly population is putting a heavy strain on healthcare and social welfare. Living conditions and service provision for elderly people have thus become an increasingly hot topic worldwide. In this paper, we address this problem by presenting a conceptual model of an integrated and personalized system for an eco-smart home for elderly independent living. This approach was inspired by an on-going European project, INNOVAGE, which researchers at Blekinge Institute of Technology are currently participating in, and which focuses on regional knowledge clusters for promoting eco-smart homes for elderly independent living. Contrasting the social situation of elderly in China and Europe, we have chosen to focus on a solution for a Swedish context, which takes technical, environmental, social and human-computer interaction aspects into consideration in the design of eco-smart homes for elderly people in Sweden. Three studies have been carried out in order to clarify and explore the main issues at stake. A literature review gave an overview of on-going research and the current state-of-the-art concerning smart homes. The literature review, along with an interview of an expert on solar energy, also gave insights into additional design challenges which are introduced when focusing specifically on eco-smart building solutions. In order to explore and gain a better understanding of the perceived needs and requests of the target group, i.e. the elderly population, we carried out interviews with three experts in healthcare and homecare for the elderly, and also carried out interviews among the elderly in Karlskrona and interviews and a web survey among the elderly in China. As a way of addressing the design challenges of integrating a multitude of diverse, complicated technical systems in a home environment while at the same time high-lighting the need for comprehensive personalized service provision for elderly people, we designed a conceptual model – an exemplar – of an eco-smart home for elderly independent living. The eco-smart home exemplar aims to inspire interdisciplinary and multi-stakeholder discussions around innovative design and development of environmentally friendly, comfortable, safe and supportive living for the elderly in the future. Finally, we did an evaluation of the model in two workshops with elderly people in two different towns in Blekinge.

  • 435.
    Zou, Ming
    Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för datalogi och datorsystemteknik.
    Industrial Decision Support System with Assistance of 3D Game Engine2015Independent thesis Advanced level (degree of Master (Two Years))Oppgave
    Abstract [en]

    Context. Industrial Decision Support System(DSS) traditionally relies on 2D approach to visualize the scenarios. For some abstract information, like chronological sequence of tasks or data trend, it provides a good visualization. For concrete information, such as location and spatial relationships, 2D visualizations are too abstract. Techniques from Game design, 3D modeling, virtual reality(VR) and animation provides many inspiration to develop a DSS tools for industrial applications. Objectives. The work in our research was to develop a unique prototype for data visualization in wind power systems, and compare it with traditional ones. The product combined 3D VR, 2D graphics, user navigation, and Human Machine Interaction(HMI). It was developed with a game engine, Unity3D. The study explored how much usability can be improved when using applied gamificaion 3D approaches in industrial monitoring and control systems. Methods. The research methods included Literature Review, Commercial Example Analysis, Development, and Evaluation. In the evaluation phase, Systematic Usability Scale(SUS) tests were performed with two independent groups, the testing results were analyzed with statistical method, t-test. Results. The evaluation results showed that an interface developed with 3D virtual reality can provide better usability(include learnability) than traditional 2D industrial interface in wind power system. The difference between them is significant. Conclusions. The study indicates that, compared with the traditional 2D interfaces, the gamification 3D approach in industrial DSS can provide user more comprehensive information visualization, better usability and learnability . It also gives more effective interactions to enhance the user experience.

6789 401 - 435 of 435
RefereraExporteraLink til resultatlisten
Permanent link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf