lnu.sePublications
Change search
Refine search result
1234567 151 - 200 of 512
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 151.
    Grzonka, Daniel
    et al.
    Cracow University of Technology, Poland.
    Jakobik, Agnieszka
    Cracow University of Technology, Poland.
    Kołodziej, Joanna
    Research and Academic Computer Network (NASK), Poland.
    Pllana, Sabri
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Using a Multi-Agent System and Artificial Intelligence for Monitoring and Improving the Cloud Performance and Security2018In: Future generations computer systems, ISSN 0167-739X, E-ISSN 1872-7115, Vol. 86, p. 1106-1117Article in journal (Refereed)
    Abstract [en]

    Cloud Computing is one of the most intensively developed solutions  for large-scale distributed processing. Effective use of such environments, management of their high complexity and ensuring appropriate levels of Quality of Service (QoS) require advanced monitoring systems. Such monitoring systems have to support the scalability, adaptability and reliability of Cloud. Most of existing monitoring systems  do not incorporate any Artificial  Intelligence (AI) algorithms for supporting the change inside the task stream or environment itself. They  focus  only on monitoring or enabling the control of the system as a part of a separated service. An effective monitoring system for the Cloud environment should gather information about all stages of tasks processing and should actively control the monitored environment. In this paper, we present a novel Multi-Agent System based Cloud Monitoring (MAS-CM) model that supports the performance and security of tasks gathering, scheduling and execution processes in large-scale service-oriented environments. Such models are explicitly designed to control the performance and security objectives of the environment. In our work, we focus on prevention of unauthorized task injection and modification, optimization of scheduling process and maximization of resource usage.We evaluate the effectiveness of MAS-CM empirically using an evolutionary driven implementation of Independent Batch Scheduler and FastFlow framework. The obtained results demonstrate the effectiveness of the proposed approach and the performance improvement.

  • 152.
    Gudmundsson, Johan
    et al.
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Menkes, Francis
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Swedish Natural Language Processing with Long Short-term Memory Neural Networks: A Machine Learning-powered Grammar and Spell-checker for the Swedish Language2018Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Natural Language Processing (NLP) is a field studying computer processing of human language. Recently, neural network language models, a subset of machine learning, have been used to great effect in this field. However, research remains focused on the English language, with few implementations in other languages of the world. This work focuses on how NLP techniques can be used for the task of grammar and spelling correction in the Swedish language, in order to investigate how language models can be applied to non-English languages. We use a controlled experiment to find the hyperparameters most suitable for grammar and spelling correction on the Göteborgs-Posten corpus, using a Long Short-term Memory Recurrent Neural Network. We present promising results for Swedish-specific grammar correction tasks using this kind of neural network; specifically, our network has a high accuracy in completing these tasks, though the accuracy achieved for language-independent typos remains low.

    Download full text (pdf)
    fulltext
  • 153.
    Gunnarsson, Adam
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Real time object detection on a Raspberry Pi2019Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    With the recent advancement of deep learning, the performance of object detection techniques has greatly increased in both speed and accuracy. This has made it possible to run highly accurate object detection with real time speed on modern desktop computer systems. Recently, there has been a growing interest in developing smaller and faster deep neural network architectures suited for embedded devices. This thesis explores the suitability of running object detection on the Raspberry Pi 3, a popular embedded computer board. Two controlled experiments are conducted where two state of the art object detection models SSD and YOLO are tested in how they perform in accuracy and speed. The results show that the SSD model slightly outperforms YOLO in both speed and accuracy, but with the low processing power that the current generation of Raspberry Pi has to offer, none of the two performs well enough to be viable in applications where high speed is necessary.

    Download full text (pdf)
    fulltext
  • 154.
    Gusinja, Bjeshka
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM), Department of Media Technology.
    Analyzing and controlling food waste inside supermarkets.Evaluation of implemented prototype to connect supermarkets with charities. Case study: Kosovo’s supermarkets2018Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    Food waste is considered to be a big problem worldwide. Different research projects have been done within this area in order to find ways that can help reduce this problem. This thesis addresses the problem of food waste in the supermarkets of Kosovo, by identifying the amounts of food waste in 3 supermarkets of this region. In addition, it explores the possibility of connection between supermarkets and charity organizations by using a developed prototype that corresponds to the field of web technologies. The prototype is implemented based on the feedback of supermarket workers. Interviews with open-ended questions were realized with supermarket workers and charity organization workers in order to identify the best medium that can be used to connect them. The prototype is realized using Wordpress, and evaluated first using the SUS questionnaire. Furthermore, it is also evaluated by performing usability test with supermarket and charity organization workers. The participants were asked to perform different tasks during the evaluation. The study shows that the use of the developed prototype reduces the amount of food waste in supermarkets. Furthermore, it successfully connects charity organizations with supermarkets. In addition, it provides a new way of controlling expiry dates of items resulting in reduction of waste inside supermarkets.

    Download full text (pdf)
    Gusinja master thesis
  • 155.
    Gustafsson, Marcus
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Sentiment Analysis for Tweets in Swedish: Using a sentiment lexicon with syntactic rules2020Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Sentiment Analysis refers to the extraction of opinion and emotion from data. In its simplest form, an application estimates a sentence and labels it with a positive or negative sentiment score. One way of doing this is through a lexicon of sentiment-laden words, each annotated with its respective polarity. Tweets are a specific kind of data that has spurred interest in researchers, since they tend to carry opinions on various topics, such as political parties, stocks or commercial brands. Tools and libraries have been developed for analyzing the sentiment of tweets and other kinds of data, but mainly for the English language. This report investigates ways of efficiently analyzing the sentiment of tweets written in Swedish. A sentiment lexicon translated from English to Swedish, together with different combinations of syntax rules, is tested on a labeled set of tweets. Machine-translating a lexicon did not provide a fully satisfying result for sentiment analysis in Swedish. However, the resulting model could be used as a base for constructing a more successful tool.

    Download full text (pdf)
    Sentiment Analysis for Tweets in Swedish
  • 156.
    Hafizovic, Nedzad
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM), Department of Computer Science. Linneuniversitetet.
    Candidate - job recommendation system: Building a prototype of a machine learning – based recommendation system for an online recruitment company2019Independent thesis Advanced level (degree of Master (One Year)), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Recommendation systems are gaining more popularity because of the complexity of problems that they provide a solution to. There are many applications of recommendation systems everywhere around us. Implementation of these systems differs and there are two approaches that are most distinguished. First approach is a system without Machine Learning, while the other one includes Machine Learning. The second approach, used in this project, is based on Machine Learning collaborative filtering techniques. These techniques include numerous algorithms and data processing methods. This document describes a process that focuses on building a job recommendation system for a recruitment industry, starting from data acquisition to the final result. Data used in the project is collected from the Pitchler AB company, which provides an online recruitment platform. Result of this project is a machine learning based recommendation system used as an engine for the Pitchler AB IT recruitment platform.

    Download full text (pdf)
    Candidate - job recommendation system
  • 157.
    Hagelbäck, Johan
    et al.
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Liapota, Pavlo
    Softwerk, Sweden.
    Lincke, Alisa
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Löwe, Welf
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    The performance of some machine learning approaches in human movement assessment2019In: 13th Multi Conference on Computer Science and Information Systems (MCCSIS) / [ed] Mário Macedo, L. Rodrigues, Porto, Portugal: IADIS Press, 2019, p. 35-42Conference paper (Refereed)
    Abstract [en]

    The advent of commodity 3D sensor technology enabled, amongst other things, the efficient and effective assessment of human movements. Statistical and machine learning approaches map recorded movement instances to expert scores to train models for the automated assessment of new movements. However, there are many variations in selecting the approaches and setting the parameters for achieving high performance, i.e., high accuracy and low response time. The present paper researches the design space and the impact of approaches of statistical and machine learning on accuracy and response time in human movement assessment. Results show that a random forest regression approach outperforms linear regression, support vector regression and neuronal network approaches. Since the results do not rely on the movement specifics, they can help improving the performance of automated human movement assessment, in general.

  • 158.
    Hagelbäck, Johan
    et al.
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Liapota, Pavlo
    Softwerk, Sweden.
    Lincke, Alisa
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Löwe, Welf
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Variants of Dynamic Time Warping and their Performance in Human Movement Assessment2019In: 21st International Conference on Artificial Intelligence (ICAI'19: July 29 - August 1, 2019, Las Vegas, USA), CSREA Press, 2019, p. 9-15Conference paper (Refereed)
    Abstract [en]

    The advent of commodity 3D sensor technology enabled, amongst other things, the efficient and effective assessment of human movements. Statistical and machine learning approaches map recorded movement instances to expert scores to train models for the automated assessment of new movements. However, there are many variations in selecting the approaches and setting the parameters for achieving good performance, i.e., high scoring accuracy and low response time. The present paper researches the design space and the impact of sequence alignment on accuracy and response time. More specifically, we introduce variants of Dynamic Time Warping (DTW) for aligning the phases of slow and fast movement instances and assess their effect on the scoring accuracy and response time. Results show that an automated stripping of leading and trailing frames not belonging to the movement (using one DTW variant) followed by an alignment of selected frames in the movements (based on another DTW variant) outperforms the original DTW and other suggested variants thereof. Since these results are independent of the selected learning approach and do not rely on the movement specifics, the results can help improving the performance of automated human movement assessment, in general.

  • 159.
    Hagelbäck, Johan
    et al.
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Lincke, Alisa
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Löwe, Welf
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Rall, Eduard
    AIMO, Sweden.
    On the Agreement of Commodity 3D Cameras2019In: Proceedings of the 2019 International Conference on Image Processing, Computer Vision, & Pattern Recognition / [ed] Hamid R. Arabnia, Leonidas Deligiannidis, Fernando G. Tinetti, CSREA Press, 2019, p. 36-42Conference paper (Refereed)
    Abstract [en]

    The advent of commodity 3D sensor technol- ogy has, amongst other things, enabled the efficient and effective assessment of human movements. Machine learning approaches do not rely manual definitions of gold standards for each new movement. However, to train models for the automated assessments of a new movement they still need a lot of data that map recorded movements to expert judg- ments. As camera technology changes, this training needs to be repeated if a new camera does not agree with the old one. The present paper presents an inexpensive method to check the agreement of cameras, which, in turn, would allow for a safe reuse of trained models regardless of the cameras. We apply the method to the Kinect, Astra Mini, and Real Sense cameras. The results show that these cameras do not agree and that the models cannot be reused without an unacceptable decay in accuracy. However, the suggested method works independent of movements and cameras and could potentially save effort when integrating new cameras in an existing assessment environment.

  • 160.
    Hallink, Robert Willem
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    The Application of Design Principles on Fast-Action Puzzle Games: A study on how the use of design principles affect how players perform in Fast-Action Puzzle Games2019Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    This thesis studies a few established design principles which were implemented in a developed fast-action puzzle game prototype. The aim was to study how several design principles affected the performance of players.

    The prototype was described as a Time-Based Memory Mashup with six different ”presets” based on the established design principles in which small changes occur.

    All participants in the study played through all six presets. Gameplay data was gathered from the participating users and were automatically recorded into a database in order to determine which preset was the most successful.

    Participants also filled in a survey to answer questions regarding on how they would judge their own performance, engagement and enjoyment of each played preset.

    Collected gameplay data from the participants were compared and ranked to determine which presets and design principles were the most effective. Surveys, observations and interviews have been studied to see if it matched the statistical data.

    Participants had higher performances with a fixed or more forgiving timer, which participants preferred the most. Downgraded graphics and sound were enjoyed the least, however did not led to much worse performances. An increased difficulty had the most effect in lowering performances.

    Design principles such as Pacing, Difficulty, Feedback, Interface Design and Foreground had the most potential to lower performances among participants.

    Download full text (pdf)
    The Application of Design Principles on Fast-Action Puzzle Games
  • 161.
    Hamidi, Ali
    et al.
    Linnaeus University, Faculty of Technology, Department of Informatics.
    Milrad, Marcelo
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Increasing STEM engagement through the mediation of textile materials combined with physical computing2019In: Transforming lLearning with meaningful technologies: 14th European Conference on Technology Enhanced Learning, EC-TEL 2019, Delft, The Netherlands, September 16–19, 2019, Proceedings / [ed] Maren Scheffel, Julien Broisin, Viktoria Pammer-Schindler, Andri Ioannou & Jan Schneider, Springer, 2019, Vol. 11722, p. 617-621Conference paper (Refereed)
    Abstract [en]

    Recent trends indicate an increasing global demand for skilled IT and Engineering professionals. At the same, it has been acknowledged that there is a decline in the number of graduates in the disciplines of Science, Technology, Engineering and Mathematics (STEM). The lack of interest in these subjects, which has been addressed by many scholars, has triggered recent efforts in order to investigate novel ways to attract and engage more young students in STEM related subjects. In this paper, we describe an exploratory qualitative research study that has been carried out by combining the subjects of technology and programming in a series of workshops hosting sixty pupils 12–13 years old. Children have used the Makey-Makey kit and the Scratch programming language together with textiles to explore how the combination of these different forms of expression can influence their engagement and interest with STEM related topics. The theoretical ideas used for the design and implementation of this study were guided by flow theory. Data was collected through observations, video recordings, and semi-structured interviews. The initial results of this study indicate that the attributes of attention, motivation, and empowerment shape the levels of engagement to retain and reinforce the flow state by using all these materials.

  • 162.
    Hasangjekaj, Rilind
    et al.
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Karlsson, Sandra
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    A reusable framework to accelerate the development of visual analytics applications based on dimensionality reduction2019Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    To be able to visualize and analyze multidimensional data sets, the dimensions have to be reduced to two or three, by using dimensionality reducing (DR) methods. The problem is that there is no established foundation for building applications to handle data sets, DR and visualization and therefore the process of doing so is not as efficient as it could be. This thesis suggests a framework as a solution to the problem, and covers the implementation of such a framework. The framework is used to create a prototype application to ensure that it is useful in such a scenario. For further evaluation, a domain expert tested the framework by following the associated instructions, and answered a questionnaire. The answers were positive and contained comments that were used to improve the instructions, and suggestions on how to improve the framework in the future.

    Download full text (pdf)
    fulltext
  • 163.
    Heberle, Andreas
    et al.
    Karlsruhe University of Applied Sciences, Germany.
    Löwe, Welf
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM). Softwerk AB, Växjö.
    Gustafsson, Anders
    Södra Skog, Växjö.
    Vorrei, Orjan
    Södra Skog, Växjö.
    Digitalization Canvas - Towards Identifying Digitalization Use Cases and Projects2017In: Journal of universal computer science (Online), ISSN 0948-695X, E-ISSN 0948-6968, Vol. 23, no 11, p. 1070-1097Article in journal (Refereed)
    Abstract [en]

    Nowadays, many companies are running digitalization initiatives or are planning to do so. There exist various models to evaluate the digitalization potential of a company and to define the maturity level of a company in exploiting digitalization technologies summarized under buzzwords such as Big Data, Artificial Intelligence (AI), Deep Learning, and the Industrial Internet of Things (IIoT). While platforms, protocols, patterns, technical implementations, and standards are in place to adopt these technologies, small-to mediumsized enterprises (SME) still struggle with digitalization. This is because it is hard to identify the most beneficial projects with manageable cost, limited resources and restricted know-how. In the present paper, we describe a real-life project where digitalization use cases have been identified, evaluated, and prioritized with respect to benefits and costs. This effort led to a portfolio of projects, some with quick and easy wins and some others with mid-to long-term benefits. From our experiences, we extracted a general approach that could be useful for other SMEs to identify concrete digitalization activities and to define projects implementing their digital transformation. The results are summarized in a Digitalization Canvas.

  • 164.
    Hedenborg, Mathias
    et al.
    Linnaeus University, Faculty of Technology, Department of Computer Science.
    Lundberg, Jonas
    Linnaeus University, Faculty of Technology, Department of Computer Science.
    Löwe, Welf
    Linnaeus University, Faculty of Technology, Department of Computer Science.
    Trapp, Martin
    Senacor Technologies AG, Germany.
    Approximating Context-Sensitive Program Information2015In: Proceedings Kolloquium Programmiersprachen (KPS 2015) / [ed] Jens Knoop, 2015Conference paper (Other academic)
    Abstract [en]

    Static program analysis is in general more precise if it is sensitive to execution contexts (execution paths). In this paper we propose χ-terms as a mean to capture and manipulate context-sensitive program information in a data-flow analysis. We introduce finite k-approximation and loop approximation that limit the size of the context-sensitive information. These approximated χ-terms form a lattice with a finite depth, thus guaranteeing every data-flow analysis to reach a fixed point. 

    Download full text (pdf)
    fulltext
  • 165.
    Hedin, Andreas
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    CRAMO: Continuously Rendered Aerial Maps with Open Data2019Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    One issue with a lot of the free aerial satellite maps that exists is the actuality of the acquired images in terms of the acquisition date. A lot of times the images are a few years old and will not represent the current reality. This project will try and mitigate this by using free open data from the Copernicus directive supplied by the European Space Agency ESA and use that to create maps. By doing this the ability to have daily updated aerial satellite maps occurs and that could be really interesting for scientific and commercial purposes. To make this work an automated process was created that downloaded the images from Copernicus and processed them with GDAL to create the maps. The process deals with the issues of mosaicing, reprojection and unattended downloads amongst other things. In the results, there is a comparison between three different maps to give a comparison and an idea of how big of a map the process can handle in a reasonable time. 

    Download full text (pdf)
    fulltext
  • 166.
    Hedin, Björn
    et al.
    KTH Royal Institute of Technology.
    Zapico, Jorge Luis
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM), Department of Media Technology.
    Kilowh.at – Increasing Energy Awareness Using an Interactive Energy Comparison Tool2017In: Persuasive Technology: Development and Implementation of Personalized Technologies to Change Attitudes and Behaviors / [ed] de Vries, P.W., Oinas-Kukkonen, H., Siemons, L., Beerlage-de Jong, N., van Gemert-Pijnen, L, Springer, 2017, p. 175-185Conference paper (Refereed)
    Abstract [en]

    Reducing the use of energy is important for several reasons, such as saving money and reducing impact on the climate. However, the awareness among non-experts of how much energy is required by different activities is generally low, which can lead to wrong prioritizations. In this study, we have developed an interactive tool to increase “energy awareness”. A group of 58 students first did a test to benchmark their current energy awareness, then tried the tool for 10 min, and then did the same test immediately after trying the prototype and one week after trying the prototype. In addition, they answered questions regarding which, if any, of the energy requirement of different activities surprised them, any thoughts about their own energy use aroused after using the prototype and what they thought about using the tool compared to more conventional methods of learning. The results showed a significant learning effect in energy awareness with a very strong effect size of 1.689, that they were most surprised by the energy required to produce a hamburger, 39 of 58 explicitly said they intended to change one or more aspects in order to improve their energy use, where 24 actions involved changing habits and 18 actions was of a one-time investment character. The attitude towards using such a tool instead of more conventional learning was very good and the words most frequently used to describe the tool was good, simple and easy to use, fun, and interesting, but five users also said they were bored after a while. In total the results indicate that using an interactive tool like this even for a limited time is a good way to in an efficient and fun way increase energy awareness.

  • 167.
    Hedin, Björn
    et al.
    KTH Royal Institute of Technology.
    Zapico, Jorge Luis
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    What Can You Do with 100 kWh?: A Longitudinal Study of Using an Interactive Energy Comparison Tool to Increase Energy Awareness2018In: Sustainability, ISSN 2071-1050, E-ISSN 2071-1050, Vol. 10, no 7, article id 2269Article in journal (Refereed)
    Abstract [en]

    Reducing the use of energy is important for several reasons, such as saving money and reducing impact on the climate. However, the awareness among non-experts of how much energy is required by different activities and appliances is generally low, which can lead to wrong prioritizations. In this study, we have developed an interactive tool to increase “energy awareness”, and performed a longitudinal study to evaluate its effect. A group of 58 students first did a test to benchmark their current energy awareness, where their current knowledge of energy used for 14 different activities, such as driving vehicles and using home appliances, was measured. They then tried the interactive learning tool for 10 min. Next, they did the same test immediately after trying the tool, then again one week after trying the tool, and finally again six months after trying the tool. The results showed a significant learning effect in energy awareness with a “huge” effect size of 2.25 immediately after the intervention, a “very large” effect size of 1.70 after one week, and a “large” effect size of 0.93 after six months. The results further showed that the respondents consistently underestimated what 100 kWh could be used for, and especially so for appliances and activities requiring little energy. Before the intervention, on average they underestimated how much 100 kWh could be used for by 95.2%, and six months after the intervention the underestimation was 86.8%.

  • 168.
    Herault, Romain Christian
    et al.
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Lincke, Alisa
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Milrad, Marcelo
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Forsgärde, Elin-Sofie
    Linnaeus University, Faculty of Health and Life Sciences, Department of Health and Caring Sciences.
    Elmqvist, Carina
    Linnaeus University, Faculty of Health and Life Sciences, Department of Health and Caring Sciences.
    Using 360-degrees interactive videos inpatient trauma treatment education: design, development and evaluationaspects2018In: Smart Learning Environments, E-ISSN 2196-7091, Vol. 5, article id 26Article in journal (Refereed)
    Abstract [en]

    Extremely catastrophic situations are rare in Sweden, which makes training opportunities important to ensure competence among emergency personnel who should be actively involved during such situations. There is a requirement to conceptualize, design, and implement an interactive learning environment that allows the education, training and assessment of these catastrophic situations more often, and in different environments, conditions and places. Therefore, to address these challenges, a prototype system has been designed and developed, containing immersive, interactive 360-degrees videos that are available via a web browser. The content of these videos includes situations such as simulated learning scenes of a trauma team working at the hospital emergency department. Various forms of interactive mechanisms are integrated within the videos, to which learners should respond and act upon. The prototype was tested during the fall term of 2017 with 17 students (working in groups), from a specialist nursing program, and four experts. The video recordings of these study sessions were analyzed and the outcomes are presented in this paper. Different group interaction patterns with the proposed tool were identified. Furthermore, new requirements for refining the 360-degrees interactive video, and the technical challenges associated with the production of this content, have been found during the study. The results of our evaluation indicate that the system can provide the students with novel interaction mechanisms, to improve their skills, and it can be used as a complementary tool for the teaching and learning methods currently used in their education process.

  • 169.
    Herault, Romain Christian
    et al.
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Lincke, Alisa
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Milrad, Marcelo
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Forsgärde, Elin-Sofie
    Linnaeus University, Faculty of Health and Life Sciences, Department of Health and Caring Sciences.
    Elmqvist, Carina
    Linnaeus University, Faculty of Health and Life Sciences, Department of Health and Caring Sciences.
    Svensson, Anders
    Linnaeus University, Faculty of Health and Life Sciences, Department of Health and Caring Sciences.
    Design and Evaluation of a 360 Degrees Interactive Video System to Support Collaborative Training for Nursing Students in Patient Trauma Treatment2018In: 26TH INTERNATIONAL CONFERENCE ON COMPUTERS IN EDUCATION (ICCE 2018) / [ed] Yang, JC Chang, M Wong, LH Rodrigo, MMT, Asia-Pacific Society for Computers in Education, 2018, p. 298-303Conference paper (Refereed)
    Abstract [en]

    Extreme catastrophe situations are rare in Sweden, which makes training opportunities important to secure the competence among emergency personnel that should be actively involved during those situations. There is a need to conceptualize, design and implement interactive learning environments that allow to educate, train and assess these catastrophe situations more often and in different settings, conditions and places. In order to address these challenges, a prototype system has been designed and developed containing immersive interactive 360 degrees educational videos that are available via a web browser. The content of these videos includes simulated learning scenes of a trauma team working at the hospital emergency department. Different types of interaction mechanisms are integrated within the videos in which learners should act upon and respond. The prototype was tested during the fall term 2017 with 17 students from the specialist nursing program, and four medical experts. These activities were assessed in order to get new insights into issues related to the proposed approach and feedback connected to the usefulness, usability and learnability of the suggested prototype. The initial outcomes of the evaluation indicate that the system can provide students with novel interaction mechanisms to improve their skills and it can be applied as a complementary tool to the methods used currently in their education.

  • 170.
    Herault, Romain Christian
    et al.
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Lundman, Madeleine
    Golub, Koraljka
    Linnaeus University, Faculty of Arts and Humanities, Department of Cultural Sciences.
    Milrad, Marcelo
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Developing Attractive Information Landscapes for the Mapping of Cultural Events Using Web and Mobile Technologies: Uppföljningsseminarium av fakultetsöverskridande project, 22 mars 20182018Other (Other academic)
    Download full text (pdf)
    fulltext
  • 171.
    Heyder, Jakob
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Hierarchical Temporal Memory Software Agent: In the light of general artificial intelligence criteria2018Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Artificial general intelligence is not well defined, but attempts such as the recent listof “Ingredients for building machines that think and learn like humans” are a startingpoint for building a system considered as such [1]. Numenta is attempting to lead thenew era of machine intelligence with their research to re-engineer principles of theneocortex. It is to be explored how the ingredients are in line with the design princi-ples of their algorithms. Inspired by Deep Minds commentary about an autonomy-ingredient, this project created a combination of Numentas Hierarchical TemporalMemory theory and Temporal Difference learning to solve simple tasks defined in abrowser environment. An open source software, based on Numentas intelligent com-puting platform NUPIC and Open AIs framework Universe, was developed to allowfurther research of HTM based agents on customized browser tasks. The analysisand evaluation of the results show that the agent is capable of learning simple tasksand there is potential for generalization inherent to sparse representations. However,they also reveal the infancy of the algorithms, not capable of learning dynamic com-plex problems, and that much future research is needed to explore if they can createscalable solutions towards a more general intelligent system.

    Download full text (pdf)
    Bachelor_Thesis_Jakob_Heyder_Final_Version
  • 172.
    Hmidi, Mehdi
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Formation Control and UAV Path Finding Under Uncertainty: A contingent and cooperative swarm intelligence approach2020Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Several of our technological breakthroughs are influenced by types of behavior and structures developed in the natural world, including the emulation of swarm in- telligence and the engineering of artificial synapses that function like the human mind. Much like these breakthroughs, this report examines emerging behaviors across swarms of non-communicating, adaptive units that evade obstacles while find- ing a path, to present a swarming algorithm premised on a class of local rule sets re- sulting in a Unmanned Aerial Vehicle (UAV) group navigating together as a unified swarm. Primarily, this method’s important quality is that its rules are local in nature. Thus, the exponential calculations which can be supposed with growing number of drones, their states, and potential tasks are remedied. To this extent, the study tests the algorithmic rules in experiments to replicate the desired behavior in a bounded virtual space filled with simulated units. Simultaneously, in the adaptation of natural flocking rules the study also introduces the rule sets for goal seeking and uncertainty evasion. In effect, the study succeeds in reaching and displaying the desired goals even as the units avoid unknown before flight obstacles and inter-unit collisions with- out the need for a global centralized command nor a leader based hierarchical system.

    Download full text (pdf)
    fulltext
  • 173.
    Hult, Adam
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM), Department of Computer Science.
    Automatiserad IO-adressering: Ett konfigureringssystem som hanterar maskinunik hårdvaruadressering2018Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [sv]

    Genom Norden Machinerys förmåga att innovera och skapa har de bland annat lyckats producera maskiner med otroliga kapaciteter. Med det och den höga verkningsgraden maskinerna verkar på har gjort att företaget idag är världsledande inom tubfyllningsindustrin.

     

    Varje maskin som levereras utav Norden har ofta unika kundspecifikationer, detta gör att Nordens elkonstruktionsavdelning behöver tilldela en maskinunik eldokumentation till varje maskin. Detta innebär att IO-konfigurationen är unik och måste då anpassas i maskinens PLC-program. Vid uppstart av maskiner idag måste alla IO-adresser matas in för hand via en operatörspanel. Detta utgör att uppstartsfatsen är både tidskrävande samt att det finns en risk att felaktiga adresser anges.

     

    Denna rapport kommer avhandla och beskriva hur man kan hantera IO-adressering och IO-konfigurering när antalet portar hos en PLC är otillräckliga samt att undersöka möjligheterna till att automatisera den manuella hanteringen utav adresser och IO-konfigurationen.

    Download full text (pdf)
    fulltext
  • 174.
    Humeniuk, Vladyslav
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Android Architecture Comparison: MVP vs. VIPER2019Independent thesis Advanced level (degree of Master (One Year)), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Android application development has been of interest since the first Android smartphone was released. Applications are constantly getting more complex as well as smartphone hardware is getting better. New ways of developing Android applications are developed with time. There is Model View Presenter architecture that is the most used for android applications now and new View InteractorPresenter Entity Router architecture that is becoming more popular. But there is no empirical data to compare these architectures to understand what architecture will fit better for developing new applications. This thesis aims to compare the MVP and the VIPER android architectures using a few important metrics like maintainability, modifiability, testability, and performance. Results will answer what architecture is better for developing different types of projects. VIPERarchitecture showed better performance results and maintenance metrics comparison shows that both architectures have advantages and disadvantages.

    Download full text (pdf)
    fulltext
  • 175.
    Hönel, Sebastian
    et al.
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Ericsson, Morgan
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Löwe, Welf
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Wingkvist, Anna
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    A changeset-based approach to assess source code density and developer efficacy2018In: ICSE '18 Proceedings of the 40th International Conference on Software Engineering: Companion Proceeedings, IEEE , 2018, p. 220-221Conference paper (Refereed)
    Abstract [en]

    The productivity of a (team of) developer(s) can be expressed as a ratio between effort and delivered functionality. Several different estimation models have been proposed. These are based on statistical analysis of real development projects; their accuracy depends on the number and the precision of data points. We propose a data-driven method to automate the generation of precise data points. Functionality is proportional to the code size and Lines of Code (LoC) is a fundamental metric of code size. However, code size and LoC are not well defined as they could include or exclude lines that do not affect the delivered functionality. We present a new approach to measure the density of code in software repositories. We demonstrate how the accuracy of development time spent in relation to delivered code can be improved when basing it on net-instead of the gross-size measurements. We validated our tool by studying ca. 1,650 open-source software projects.

  • 176.
    Hönel, Sebastian
    et al.
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Ericsson, Morgan
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Löwe, Welf
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Wingkvist, Anna
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Bayesian Regression on segmented data using Kernel Density Estimation2019In: 5th annual Big Data Conference: Linnaeus University, Växjö, Sweden, 5-6 December 2019, Zenodo , 2019Conference paper (Other academic)
    Abstract [en]

    The challenge of having to deal with dependent variables in classification and regression using techniques based on Bayes' theorem is often avoided by assuming a strong independence between them, hence such techniques are said to be naive. While analytical solutions supporting classification on arbitrary amounts of discrete and continuous random variables exist, practical solutions are scarce. We are evaluating a few Bayesian models empirically and consider their computational complexity. To overcome the often assumed independence, those models attempt to resolve the dependencies using empirical joint conditional probabilities and joint conditional probability densities. These are obtained by posterior probabilities of the dependent variable after segmenting the dataset for each random variable's value. We demonstrate the advantages of these models, such as their nature being deterministic (no randomization or weights required), that no training is required, that each random variable may have any kind of probability distribution, how robustness is upheld without having to impute missing data, and that online learning is effortlessly possible. We compare such Bayesian models against well-established classifiers and regression models, using some well-known datasets. We conclude that our evaluated models can outperform other models in certain settings, using classification. The regression models deliver respectable performance, without leading the field.

  • 177.
    Hönel, Sebastian
    et al.
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Ericsson, Morgan
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Löwe, Welf
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Wingkvist, Anna
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Importance and Aptitude of Source code Density for Commit Classification into Maintenance Activities2019In: 2019 IEEE 19th International Conference on Software Quality, Reliability and Security (QRS) / [ed] Dr. David Shepherd, IEEE, 2019, p. 109-120Conference paper (Refereed)
    Abstract [en]

    Commit classification, the automatic classification of the purpose of changes to software, can support the understanding and quality improvement of software and its development process. We introduce code density of a commit, a measure of the net size of a commit, as a novel feature and study how well it is suited to determine the purpose of a change. We also compare the accuracy of code-density-based classifications with existing size-based classifications. By applying standard classification models, we demonstrate the significance of code density for the accuracy of commit classification. We achieve up to 89% accuracy and a Kappa of 0.82 for the cross-project commit classification where the model is trained on one project and applied to other projects. Such highly accurate classification of the purpose of software changes helps to improve the confidence in software (process) quality analyses exploiting this classification information.

  • 178.
    Idrizi, Florim
    et al.
    Tetovo State University, Macedonia.
    Rustemi, Avni
    Tetovo State University, Macedonia.
    Dalipi, Fisnik
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM), Department of Computer Science. Tetovo State University, Macedonia.
    A new modified sorting algorithm: A comparison with state of the art2017In: 2017 6th Mediterranean Conference on Embedded Computing (MECO), IEEE, 2017, p. 419-424Conference paper (Refereed)
    Abstract [en]

    Choosing the right method to sort numbers has a huge effect on how quickly a computer can process a task. The most used sorting algorithms today have been discovered years ago, and to this day, they have been the best for the job as there was no other competitive algorithm. Through this paper, we make an analysis and comparison between the state of the art algorithms in sorting and based on their analogy of functionality, we propose a new modified sorting algorithm. We then present a brief description of the new modified algorithm, conduct comparisons with the state of the art, and finally we give conclusions about the performance of the proposed algorithm versus the most popular sorting algorithms. Moreover, we highlight the benefits of using this algorithm in different fields by various business companies or software developers, in cases when they need faster and easier sorting for their data management.

  • 179.
    Iftikhar, Muhammad Usman
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM), Department of Computer Science. Faculty of Engineering Science, Department of Computer Science, KU Leuven, Belgium.
    A Model-Based Approach to Engineer Self-Adaptive Systems with Guarantees2017Doctoral thesis, monograph (Other academic)
    Abstract [en]

    Modern software systems are increasingly characterized by uncertainties in the operating context and user requirements. These uncertainties are difficult to predict at design time. Achieving the quality goals of such systems depends on the ability of the software to deal with these uncertainties at runtime. A self-adaptive system employs a feedback loop to continuously monitor and adapt itself to achieve particular quality goals (i.e., adaptation goals) regardless of uncertainties. Current research applies formal techniques to provide guarantees for adaptation goals, typically using exhaustive verification techniques. Although these techniques offer strong guarantees for the goals, they suffer from well-known state explosion problem. In this thesis, we take a broader perspective and focus on two types of guarantees: (1) functional correctness of the feedback loop, and (2) guaranteeing the adaptation goals in an efficient manner. To that end, we present ActivFORMS (Active FORmal Models for Self-adaptation), a formally founded model-driven approach for engineering self-adaptive systems with guarantees. ActivFORMS achieves functional correctness by direct execution of formally verified models of the feedback loop using a reusable virtual machine. To efficiently provide guarantees for the adaptation goals with a required level of confidence, ActivFORMS applies statistical model checking at runtime. ActivFORMS supports on the fly changes of adaptation goals and updates of the verified feedback loop models that meet the changed goals. To demonstrate the applicability and effectiveness of the approach, we applied ActivFORMS in several domains: warehouse transportation, oceanic surveillance, tele assistance, and IoT building security monitoring.

    Download full text (pdf)
    fulltext
  • 180.
    Iftikhar, Muhammad Usman
    et al.
    Linnaeus University, Faculty of Technology, Department of Computer Science.
    Lundberg, Jonas
    Linnaeus University, Faculty of Technology, Department of Computer Science.
    Weyns, Danny
    Linnaeus University, Faculty of Technology, Department of Computer Science. Katholieke Univ Leuven, Leuven, Belgium.
    A Model Interpreter for Timed Automata2016In: Leveraging Applications of Formal Methods, Verification and Validation: Foundational Techniques, PT I, Springer, 2016, p. 243-258Conference paper (Refereed)
    Abstract [en]

    In the model-centric approach to model-driven development, the models used are sufficiently detailed to be executed. Being able to execute the model directly, without any intermediate model-to-code translation, has a number of advantages. The model is always up-to-date and runtime updates of the model are possible. This paper presents a model interpreter for timed automata, a formalism often used for modeling and verification of real-time systems. The model interpreter supports real-time system features like simultaneous execution, system wide signals, a ticking clock, and time constraints. Many existing formal representations can be verified, and many existing DSMLs can be executed. It is the combination of being both verifiable and executable that makes our approach rather unique.

  • 181.
    Iftikhar, Muhammad Usman
    et al.
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Ramachandran, Gowri Sankar
    KU Leuven, Belgium.
    Bollansée, Pablo
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM). KU Leuven, Belgium.
    Weyns, Danny
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM). KU Leuven, Belgium.
    Hughes, Danny
    KU Leuven, Belgium.
    DeltaIoT: A Self-Adaptive Internet of Things Exemplar2017In: Proceedings - 2017 IEEE/ACM 12th International Symposium on Software Engineering for Adaptive and Self-Managing Systems, SEAMS 2017, IEEE, 2017, p. 76-82Conference paper (Refereed)
    Abstract [en]

    Internet of Things (IoT) consists of networked tiny embedded computers (motes) that are capable of monitoring and controlling the physical world. Examples range from building security monitoring to smart factories. A central problem of IoT is minimising the energy consumption of the motes, while guaranteeing high packet delivery performance, regardless of uncertainties such as sudden changes in traffic load and communication interference. Traditionally, to deal with uncertainties the network settings are either hand-tuned or over-provisioned, resulting in continuous network maintenance or inefficiencies. Enhancing the IoT network with self-adaptation can automate these tasks. This paper presents DeltaIoT, an exemplar that enables researchers to evaluate and compare new methods, techniques and tools for self-adaptation in IoT. DeltaIoT is the first exemplar for research on self-adaptation that provides both a simulator for offline experimentation and a physical setup that can be accessed remotely for real-world experimentation. © 2017 IEEE.

  • 182.
    Iftikhar, Muhammad Usman
    et al.
    Linnaeus University, Faculty of Technology, Department of Computer Science.
    Weyns, Danny
    Linnaeus University, Faculty of Technology, Department of Computer Science. Katholieke University Leuven, Belgium.
    ActivFORMS: A Runtime Environment for Architecture-Based Adaptation with Guarantees2017In: 2017 IEEE INTERNATIONAL CONFERENCE ON SOFTWARE ARCHITECTURE WORKSHOPS (ICSAW), IEEE, 2017, p. 278-281Conference paper (Refereed)
    Abstract [en]

    Modern software systems are exposed to various types of uncertainties, such as dynamics in the available resources that are difficult to predict and goals that may change during operation. Self-adaptation equips a software system with a feedback loop that collects additional knowledge at runtime, monitors the system and adapts it when necessary to maintain its quality goals, regardless of uncertainties. One challenging problem of self-adaptation is to provide guarantees for the goals that are subject of adaptation. In this paper, we present the ActivFORMS runtime environment to realise self- adaptation with guarantees. With ActivFORMS designers model and verify a feedback loop. The verified models can directly be deployed on top of a virtual machine that executes the models to realise adaption. The approach avoids coding of the models, which is an error-prone task. The runtime environment visualises the executing models, the state of the goals, and it supports on the fly updates of the models and goals. We illustrate the approach with an adaptation scenario of an IoT building security example.

  • 183.
    Iftikhar, Muhammad Usman
    et al.
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM), Department of Computer Science. Linnaeus University.
    Weyns, Danny
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM), Department of Computer Science.
    Assuring System Goals Under Uncertainty with Active Formal Models of Self-adaptation2014In: Companion Proceedings of the 36th International Conference on Software Engineering, ACM Publications, 2014, p. 604-605Conference paper (Refereed)
    Abstract [en]

    Designing software systems with uncertainties, such as incomplete knowledge about changing system goals, is challenging. One approach to handle uncertainties is self-adaptation, where a system consists of a managed system and a managing system that realizes a feedback loop. The promise of self-adaptation is to enable a system to adapt itself realizing the system goals, regarding uncertainties. To realize this promise it is critical to provide assurances for the self-adaptive behaviours. Several approaches have been proposed that exploit formal methods to provide these assurances. However, an integrated approach that combines: (1) seamless integration of offline and online verification (to deal with inherent limitations of verification), with (2) support for runtime evolution of the system (to deal with new or changing goals) is lacking. In this paper, we outline a new approach named Active FORmal Models of Self-adaptation (ActivFORMS) that aims to deal with these challenges. In ActivFORMS, the formal models of the managing system are directly deployed and executed to realize self-adaptation, guaranteeing the verified properties. Having the formal models readily available at runtime paves the way for: (1) incremental verification during system execution, and (2) runtime evolution of the self-adaptive system. Experiences with a robotic system show promising results.

    Download full text (pdf)
    fulltext
  • 184.
    Imran, Ali Shariq
    et al.
    Norwegian University of Science and Technology (NTNU), Norway.
    Dalipi, Fisnik
    University of South-Eastern Norway, Norway.
    Kastrati, Zenun
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Predicting Student Dropout in a MOOC: An Evaluation of a Deep Neural Network Model2019In: Proceedings of the 2019 5th International Conference on Computing and Artificial Intelligence, ACM Publications, 2019, p. 190-195Conference paper (Refereed)
    Abstract [en]

    Massive Open Online Courses (MOOCs) have transformed the way educational institutions deliver high-quality educational material to the onsite and distance learners across the globe. As a result, a new paradigm shifts as to how learners acquire and benefit from the wealth of knowledge provided by a MOOC at their doorstep nowadays in contrast to the brick and mortar settings is visible. Learners are therefore showing a profound interest in the MOOCs offered by top universities and industry giants. They have also attracted a vast number of students from far-flung areas of the world. The massive number of registered students in MOOCs, however, pose one major challenge, i.e., 'the dropouts'. Course planners and content providers are struggling to retain the registered students, which give rise to a new research agenda focusing on predicting and explaining student dropout and low completion rates in a MOOC. Machine learning techniques utilizing deep learning approaches can efficiently predict the potential dropouts and can raise an alert well before time. In this paper, we have focused our study on the application of feed-forward deep neural network architectures to address this problem. Our model achieves not only high accuracy, but also low false negative rate while predicting dropouts on the MOOC data. Moreover, we also provide an in-depth comparison of the proposed architectures concerning precision, recall, and F1 measure.

  • 185.
    Imran, Ali Shariq
    et al.
    Norwegian University of Science and Technology, Norway.
    Kastrati, Zenun
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Svendsen, Torbjorn Karl
    Norwegian University of Science and Technology, Norway.
    Kurti, Arianit
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Text-Independent Speaker ID Employing 2D-CNN for Automatic Video Lecture Categorization in a MOOC Setting2019In: 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI), IEEE Press, 2019, p. 273-277Conference paper (Refereed)
    Abstract [en]

    A new form of distance and blended education has hit the market in recent years with the advent of massive open online courses (MOOCs) which have brought many opportunities to the educational sector. Consequently, the availability of learning content to vast demographics of people and across locations has opened up a plethora of possibilities for everyone to gain new knowledge through MOOCs. This poses an immense issue to the content providers as the amount of manual effort required to structure properly and to organize the content automatically for millions of video lectures daily become incredibly challenging. This paper, therefore, addresses this issue as a small part of our proposed personalized content management system by exploiting the voice pattern of the lecturer for identification and for classifying video lectures to the right speaker category. The use of Mel frequency Cepstral coefficients (MFCC) as 2D input features maps to 2D-CNN has shown promising results in contrast to machine learning and deep learning classifiers - making text-independent speaker identification plausible in MOOC setting for automatic video lecture categorization. It will not only help categorize educational videos efficiently for easy search and retrieval but will also promote effective utilization of micro-lectures and multimedia video learning objects (MLO).

  • 186.
    Imran, Ali Shariq
    et al.
    Norwegian University of Science and Technology, Norway.
    Kastrati, Zenun
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Svendsen, Torbjørn Karl
    Norwegian University of Science and Technology (NTNU), Norway.
    Kurti, Arianit
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Text-Independent Speaker ID for Automatic Video Lecture Classification Using Deep Learning2019In: Proceedings of the 2019 5th International Conference on Computing and Artificial Intelligence, April 19-22, 2019, Bali, Indonesia, ACM Publications, 2019, p. 175-180Conference paper (Refereed)
    Abstract [en]

    This paper proposes to use acoustic features employing deep neural network (DNN) and convolutional neural network (CNN) models for classifying video lectures in a massive open online course (MOOC). The models exploit the voice pattern of the lecturer for identification and for classifying the video lecture according to the right speaker category. Filter bank and Mel frequency cepstral coefficient (MFCC) feature along with first and second order derivatives (Δ/ΔΔ) are used as input features to the proposed models. These features are extracted from the speech signal which is obtained from the video lectures by separating the audio from the video using FFmpeg.

    The deep learning models are evaluated using precision, recall, and F1 score and the obtained accuracy is compared for both acoustic features with traditional machine learning classifiers for speaker identification. A significant improvement of 3% to 7% classification accuracy is achieved over the DNN and twice to that of shallow machine learning classifiers for 2D-CNN with MFCC. The proposed 2D-CNN model with an F1 score of 85.71% for text-independent speaker identification makes it plausible to use speaker ID as a classification approach for organizing video lectures automatically in a MOOC setting.

  • 187.
    Jakub, Nilsson
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Pose AR: Assessing Pose Based Input in an AR Context2019Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    Despite the rapidly growing adoption of augmented reality (AR) applications, existing methods for interacting with AR content are rated poorly, with surveyors of the area calling for better means of interaction, while researchers strive to create more natural input methods, mainly focusing on gesture input.

    This thesis aims to contribute to the aforementioned efforts by recognizing that technologies for consumer-grade smartphone-based pose estimation have been rapidly improving in recent years and due to their increased accuracy may have untapped potential ready to be utilized for user input. To this end, a rudimentary system for pose based input is integrated into prototype applications, which are constructed with both pose based input and touch input in mind.

    In this work, pose, pose estimation, and posed based input refer to using the distance and orientation of the user (or more precisely, the distance and orientation of their device) in relation to the AR content.

    Using said prototypes within a user interaction study allowed the identification of user preferences which indicate the approaches that future efforts into utilizing pose for input in an AR context ought to adopt. By comparing questionnaire answers and logged positional data across four prototype scenarios, it can be clearly identified that to perceive pose input as intuitive, the AR experiences shouldn’t employ a scale which is so large that it requires substantial shifts in the position of the user, as opposed to merely shifts in the position of the user’s device.

    Download full text (pdf)
    fulltext
  • 188.
    Jansen, Marc
    et al.
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM). University of Applied Sciences Ruhr West, Germany.
    Kohen-Vacs, Dan
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM). Holon Institute of Technology (HIT), Israel.
    Otero, Nuno
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM). ISCTE Lisbon University Institute, Portugal.
    Milrad, Marcelo
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    A Complementary View for Better Understanding the Term Computational Thinking2018In: Proceedings of the International Conference on Computational Thinking Education 2018, Hong Kong: The Education University of Hong Kong , 2018, p. 2-7Conference paper (Refereed)
    Abstract [en]

    The term Computational Thinking is closely related to efforts connected to teach a systematic and well-structured way of problem solving that includes a set of tools and techniques used in Computer Science. While substantial research in this field has shown promising outcomes concerning distinct intervention programs and teaching initiatives, the term Computational Thinking itself requires to be revised in order to get a wider consensus about its meaning and purpose. This paper contributes to the ongoing quest concerning the definition of the term by starting with a fundamental perspective on computational theory and corresponding concepts in order to describe the theoretical building blocks of a systematic view to further elaborate on an approach for teaching and learning about Computational Thinking. Additionally, based on this foundational effort, more advanced concepts are presented and discussed in order to better understand this domain. Finally, the paper identifies and discusses a set of relevant challenges taking a cognitive psychology perspective on Computational Thinking.

  • 189.
    Jansson, Martin
    et al.
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Petersson, Simon
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Object detection and single-board computers: En förstudie gjord på Saab AB2018Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Saab is currently using an old and complex system to perform tests of their products. The system is based on filming from different angles which will be merged to one film from which Saab can analyze the results of their products. Single-board computers is something that have become increasingly popular in the recent years, therefore, we are to investigate whether it is possible or not to replace the older systems with SBCs and cameras.We will also investigate whether the BeagleBoard is capable of detecting objects while filming, synchronizing, encoding and saving the video for later use.The result showed that the processor isn’t powerful enough to handle object identification without full hardware support. Instead, it needs to be performed afterwards by a computer which will identify objects in the video. A better method has been proposed to make object identification smarter and learning, which will work better in Saab’s case and their future work.

    Download full text (pdf)
    fulltext
  • 190.
    Jercic, Petar
    et al.
    Blekinge institute of technology, Sweden.
    Hagelbäck, Johan
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Lindley, Craig
    CSIRO, Australia.
    An affective serious game for collaboration between humans and robots2019In: Entertainment Computing, ISSN 1875-9521, E-ISSN 1875-953X, Vol. 32, p. 1-10, article id 100319Article in journal (Refereed)
    Abstract [en]

    Elicited physiological affect in humans collaborating with their robot partners was investigated to determine its influence on decision-making performance in serious games. A turn-taking version of the Tower of Hanoi game was used, where physiological arousal and valence underlying such human-robot proximate collaboration were investigated. A comparable decision performance in the serious game was found between human and non-humanoid robot arm collaborator conditions, while higher physiological affect was found in humans collaborating with such robot collaborators. It is suggested that serious games which are carefully designed to take into consideration the elicited physiological arousal might witness a better decision-making performance and more positive valence using non-humanoid robot partners instead of human ones.

  • 191.
    Jercic, Petar
    et al.
    Blekinge Tekniska Högskola.
    Wen, Wei
    Blekinge Tekniska Högskola.
    Hagelbäck, Johan
    Linnaeus University, Faculty of Technology, Department of Computer Science.
    Sundstedt, Veronica
    Blekinge Tekniska Högskola.
    The Effect of Emotions and Social Behavior on Performance in a Collaborative Serious Game Between Humans and Autonomous Robots2018In: International Journal of Social Robotics, ISSN 1875-4791, E-ISSN 1875-4805, Vol. 10, no 1, p. 115-129Article in journal (Refereed)
    Abstract [en]

    The aim of this paper is to investigate performance in a collaborative human–robot interaction on a shared serious game task. Furthermore, the effect of elicited emotions and perceived social behavior categories on players’ performance will be investigated. The participants collaboratively played a turn-taking version of the Tower of Hanoi serious game, together with the human and robot collaborators. The elicited emotions were analyzed in regards to the arousal and valence variables, computed from the Geneva Emotion Wheel questionnaire. Moreover, the perceived social behavior categories were obtained from analyzing and grouping replies to the Interactive Experiences and Trust and Respect questionnaires. It was found that the results did not show a statistically significant difference in participants’ performance between the human or robot collaborators. Moreover, all of the collaborators elicited similar emotions, where the human collaborator was perceived as more credible and socially present than the robot one. It is suggested that using robot collaborators might be as efficient as using human ones, in the context of serious game collaborative tasks.

  • 192.
    Jerčić, Petar
    et al.
    Blekinge Tekniska Högskola.
    Hagelbäck, Johan
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Lindley, Craig
    CSIRO ICT Centre, Hobart, Australia.
    Physiological Affect and Performance in a Collaborative Serious Game Between Humans and an Autonomous Robot2018In: Entertainment Computing – ICEC 2018: 17th IFIP TC 14 International Conference, Held at the 24th IFIP World Computer Congress, WCC 2018, Poznan, Poland, September 17–20, 2018 / [ed] Clua E., Roque L., Lugmayr A., Tuomi P., Springer, 2018, p. 127-138Conference paper (Refereed)
    Abstract [en]

    This paper sets out to examine how elicited physiological affect influences the performance of human participants collaborating with the robot partners on a shared serious game task; furthermore, to investigate physiological affect underlying such human-robot proximate collaboration. The participants collaboratively played a turn-taking version of a serious game Tower of Hanoi, where physiological affect was investigated in a valence-arousal space. The arousal was inferred from the galvanic skin response data, while the valence was inferred from the electrocardiography data. It was found that the robot collaborators elicited a higher physiological affect in regard to both arousal and valence, in contrast to their human collaborator counterparts. Furthermore, a comparable performance between all collaborators was found on the serious game task.

  • 193.
    Johansson, Albin
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Increasing the robustness of a service in a complex information flow2019Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    In complex information flows where a lot of varied data is transmitted through many companies and divisions, incidents will occur. When Visma Spcs had an incident where invoices sent from Visma to Visma's customers were duplicated and the service meant to receive the transactions did not handle the duplicates properly. They decided that the receiver service was to be upgraded to prevent this incident from happening again, as well as fixing some other issues the service had had. Incidents like this one must be investigated and a solution must be implemented to decrease the likelihood that similar incidents will happen again. In this report, the reader will see examples on how this can be handled and the benefits of tackling technical debt, along with how much more complicated the solutions might get if the service is not allowed to be taken offline.

    Download full text (pdf)
    fulltext
  • 194.
    Johansson, Daniel
    Linnaeus University, School of Business and Economics, Department of Organisation and Entrepreneurship. Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM), Department of Computer Science.
    From products to consumption: changes on the Swedish music market as a result of streaming technologies2013Report (Other academic)
    Abstract [en]

    Since the year 2009, the Swedish music market has changed drastically. In the first six months of 2013, 75 percent of total revenues to Swedish repertoire owners came from digital distribution. More than 90 percent of those revenues came from streaming. More than half of the population has a streaming subscription, and streaming has become the dominant format for consuming music on this specific market. As a result of this paradigm shift, changes have occurred in the Swedish music industrial system, as well as in user behaviors. This report examines how the Swedish music market has changed as a result of à la carte on demand streaming, explains the streaming model as such and give a picture of what these changes could mean for the future.

    Download full text (pdf)
    fulltext
  • 195.
    Johansson, Daniel
    Linnaeus University, School of Business and Economics, Department of Organisation and Entrepreneurship. Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM), Department of Computer Science.
    Music festivals in Sweden - an analysis of the ten largest commercial festivals 2000 - 20132014Report (Other academic)
    Abstract [en]

    This study examines the development for commercial music festivals in Sweden during the time period 2000 - 2013. Although it is clear that some legendary Swedish music festivals have disappeared during the latest years, this study indicates that the number of paying visitors of the largest festivals continues to increase. In fact, 2013 was the record year during the studied time frame regarding the number of paying visitors to the ten largest commercial festivals, with official visitor figures validated through STIM data. Nevertheless, the Swedish music festival market has changed considerably. The purpose of the paper is to describe some of these changes as well as provide a quantitative foundation for further research questions to be dealt with in the future.

    Download full text (pdf)
    fulltext
  • 196.
    Johansson, Elias
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Separation and Extraction of Valuable Information From Digital Receipts Using Google Cloud Vision OCR.2019Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Automatization is a desirable feature in many business areas. Manually extracting information from a physical object such as a receipt is something that can be automated to save resources for a company or a private person. In this paper the process will be described of combining an already existing OCR engine with a developed python script to achieve data extraction of valuable information from a digital image of a receipt. Values such as VAT, VAT%, date, total-, gross-, and net-cost; will be considered as valuable information. This is a feature that has already been implemented in existing applications. However, the company that I have done this project for are interested in creating their own version. This project is an experiment to see if it is possible to implement such an application using restricted resources. To develop a program that can extract the information mentioned above. In this paper you will be guided though the process of the development of the program. As well as indulging in the mindset, findings and the steps taken to overcome the problems encountered along the way. The program achieved a success rate of 86.6% in extracting the most valuable information: total cost, VAT% and date from a set of 53 receipts originated from 34 separate establishments.

    Download full text (pdf)
    fulltext
  • 197.
    Johansson, Michael
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Internet of things security in healthcare: A test-suite and standard review2018Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Internet of things is getting more and more popular in healthcare as it comes with benefits that help with efficiency in saving lives and reduce its cost, but it also presents a new attack vector for an attacker to steal or manipulate information sent between them. This report will focus on three properties in the definition of security, confidentiality, integrity and access control. The report will look into what challenges there is in healthcare IoT today through a literature review and from those challenges look into what could minimise these challenges before a device gets into production. The report found that the lack of standardisation has lead to errors that could be easily prevented by following a guideline of tests as those from the European Union Agency for Network and Information Security, or by running a penetration test with the tools brought up in the report on the device to see what vulnerabilities are present.

    Download full text (pdf)
    Johansson_IoT_Security_bachelor2018
  • 198.
    Johansson, Oscar
    et al.
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM), Department of Computer Science.
    Forsman, Max
    Shared computer systems and groupware development: Escaping the personal computer paradigm2018Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    For the majority of the computers existence, we humans have interacted with them in a similar way, usually with a strict one-to-one relationship between user and machine. This is reflected by the design of most computers, operating systems and user applications on the market today, which are typically intended to only be operated by a single user. When computers are used for teamwork and cooperation, this design philosophy can be restricting and problematic. This paper investigates the development of shared software intended for multiple users and the impact of the single user bias in this context. A prototype software system was developed in order to evaluate different development methods for shared applications and discover potential challenges and limitations with this kind of software. It was found that the development of applications for multiple users can be severely limited by the target operating system and hardware platform. The authors conclude that new platforms are required to develop shared software more efficiently. These platforms should be tailored to provide robust support for multiple concurrent users. This work was carried out together with SAAB Air Traffic Management in Växjö, Sweden and is a bachelor's thesis in computer engineering at Linnaeus University.

    Download full text (pdf)
    Shared computer systems and groupware development
  • 199.
    Johansson, Pauline
    et al.
    Linnaeus University, Faculty of Health and Life Sciences, Department of Health and Caring Sciences.
    Wilde Björling, Camilla
    Kalmar County Council, Sweden.
    Axelsson, Clara
    Linnaeus University, Faculty of Health and Life Sciences, Department of Medicine and Optometry.
    Östlund, Martin
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM), Department of Media Technology.
    Widell, Ingela
    Kalmar County Council, Sweden.
    Jonsson, Stefan
    Kalmar County Council, Sweden.
    Tablet computers as a mean to strengthen patients undergoing radiotherapy2015In: Presented at the 6th International Carers Conference - Care and caring: future proofing the new demographics, Gothenburg, Sweden, September 3-6, 2015, 2015Conference paper (Refereed)
  • 200.
    Jusufi, Ilir
    et al.
    Linnaeus University, Faculty of Technology, Department of computer science and media technology (CM).
    Memedi, Mevludin
    Örebro University, Sweden.
    Interactive visualization of sensor and self-reported data of patients with Parkinson's disease2019In: MIRAI AGEING Seminar, November 13-14, 2019, Stockh, 2019Conference paper (Other academic)
    Abstract [en]

    Advancements in telemedicine have been helpful for frequent monitoring of patients with Parkinson's disease (PD) from remote locations and assessment of their individual symptoms and treatment-related complications. These data can be useful for helping clinicians and patients to interpret symptom states and individually tailor the treatments by visualizing the physiological information collected by sensor-based systems as well as patient self-reported states. Here we present various visualization and interaction techniques to help physicians explore patient’s daily activities, which could be useful for guiding them during the decision-making process. An interface is designed to visualize symptom and medication information, collected by an Internet of Things-based system comprising of a smartphone, electronic dosing device, wrist sensor and a bed sensor.

    Download full text (pdf)
    fulltext
1234567 151 - 200 of 512
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf