hh.sePublications
Change search
Refine search result
12 1 - 50 of 65
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.
  • 1.
    Abdulrazzaq, Mohammed
    et al.
    Halmstad University, School of Information Technology.
    Wei, Yuan
    Halmstad University, School of Information Technology.
    Industrial Control System (ICS) Network Asset Identification and Risk Management2018Independent thesis Advanced level (degree of Master (One Year)), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Setting against the significant background of Industrial 4.0, the Industrial Control System (ICS) accelerates and enriches the upgrade the existing production infrastructure. To make the infrastructures “smart”, huge parts of manual operations have been automated in this upgrade and more importantly, the isolated controlled processes have been connected through ICS. This has also raised the issues in asset management and security concerns. Being the starting point of securing the ICS, the asset identification is, nevertheless, first dealt by exploring the definition of assets in the ICS domain due to insufficient documentation and followed by the introduction of ICS constituents and their statuses in the whole network. When the definition is clear, a well-received categorization of assets in the ICS domain is introduced, while mapping out their important attributes and their significance relating the core of service they perform. To effectively tackle the ever-increasing amount of assets, identification approaches are compared and a case study was performed to test the effectiveness of two open source software. Apart from the identification part, this thesis describes a framework for efficient asset management from CRR. The four cyclic modules proposed give an overview on how the asset management should be managed according the dynamics of the assets in the production environment.

    Download full text (pdf)
    fulltext
  • 2.
    Abiri, Najmeh
    et al.
    Department of Astronomy and Theoretical Physics, Lund University, Lund, Sweden.
    Linse, Björn
    Department of Astronomy and Theoretical Physics, Lund University, Lund, Sweden.
    Edén, Patrik
    Department of Astronomy and Theoretical Physics, Lund University, Lund, Sweden.
    Ohlsson, Mattias
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research. Department of Astronomy and Theoretical Physics, Lund University, Lund, Sweden.
    Establishing strong imputation performance of a denoising autoencoder in a wide range of missing data problems2019In: Neurocomputing, ISSN 0925-2312, E-ISSN 1872-8286, Vol. 65, p. 137-146Article in journal (Refereed)
    Abstract [en]

    Dealing with missing data in data analysis is inevitable. Although powerful imputation methods that address this problem exist, there is still much room for improvement. In this study, we examined single imputation based on deep autoencoders, motivated by the apparent success of deep learning to efficiently extract useful dataset features. We have developed a consistent framework for both training and imputation. Moreover, we benchmarked the results against state-of-the-art imputation methods on different data sizes and characteristics. The work was not limited to the one-type variable dataset; we also imputed missing data with multi-type variables, e.g., a combination of binary, categorical, and continuous attributes. To evaluate the imputation methods, we randomly corrupted the complete data, with varying degrees of corruption, and then compared the imputed and original values. In all experiments, the developed autoencoder obtained the smallest error for all ranges of initial data corruption. © 2019 Elsevier B.V.

  • 3.
    Alendal, Gunnar
    et al.
    Norwegian University of Science and Technology, Gjovik, Norway.
    Axelsson, Stefan
    Norwegian University of Science and Technology, Gjovik, Norway.
    Dyrkolbotn, Geir Olav
    Norwegian University of Science and Technology, Gjovik, Norway.
    Exploiting Vendor-Defined Messages in the USB Power Delivery Protocol2019In: Advances in Digital Forensics XV: 15th IFIP WG 11.9 International Conference, Orlando, FL, USA, January 28–29, 2019, Revised Selected Papers / [ed] Gilbert Peterson & Sujeet Shenoi, Cham: Springer, 2019, p. 101-118Conference paper (Refereed)
    Abstract [en]

    The USB Power Delivery protocol enables USB-connected devices to negotiate power delivery and exchange data over a single connection such as a USB Type-C cable. The protocol incorporates standard commands; however, it also enables vendors to add non-standard commands called vendor-defined messages. These messages are similar to the vendor-specific commands in the SCSI protocol, which enable vendors to specify undocumented commands to implement functionality that meets their needs. Such commands can be employed to enable firmware updates, memory dumps and even backdoors.

    This chapter analyzes vendor-defined message support in devices that employ the USB Power Delivery protocol, the ultimate goal being to identify messages that could be leveraged in digital forensic investigations to acquire data stored in the devices.

    © IFIP International Federation for Information Processing 2019

  • 4.
    Alm, Ilkoo
    et al.
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS), Man and Information technology laboratory (MI-lab).
    Johansson, Ingegerd
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS), Man and Information technology laboratory (MI-lab).
    Cognitive aspects in visualisation of complex data2001In: CISST'2001: proceedings of the International Conference on Imaging Science, Systems, and Technology : Las Vegas, Nevada, USA, June 25-28, 2001 / [ed] Arabnia, H.R., Avalon, Athens, USA: CSREA Press, 2001, p. 633-638Conference paper (Refereed)
    Abstract [en]

    Information Visualization applications are dealing with fundamental difficulties related to overlap in cognitive models between designers and users, goal ambiguity, and accuracy in search strategies These difficulties are more obvious in applications aimed at reducing information overload by general users, than in applications aimed at visualising scientific data. General users have very likely quite different cognitive reference for approaching an abstract complex task, than designers. This can result in designs which can unintentionally increase information overload by users. In visualisation of scientific data the overlap of cognitive reference between specialists and designs is very likely much higher, but we need methods which can facilitate data exploration in real-time interaction. One possibility to facilitate exploration in a more or less systematic way is by means of metaphors which can support human perception in searching for patterns.

  • 5.
    Andersson, Oscar
    Halmstad University, School of Information Technology.
    En värdering av molntjänsters risker och förebyggande åtgärder2022Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Physical storage is not enough to handle the amount of data created each day. As a result of the pandemic the need to create and share information over the Internet has increased. As a result, the importance of cloud services in our society increases, as they offer storage solutions that their customers do not have to maintain themselves. However, there are several security risks and threats, as for everything that is handled over the Internet. This study highlights these threats and describes the current countermeasures. A survey is conducted to examine private individuals' use of cloud services and the security functions offered. A comparative analysis found differences between the four largest cloud storage services through which security features are offered, the effectiveness of which is also compared with the survey results. The study found that both cloud service providers and their customers each have an important role to play in maintaining security.

    Download full text (pdf)
    fulltext
  • 6.
    Askfelt, Simone
    et al.
    Halmstad University, School of Information Technology.
    Arbenita, Osmani
    Halmstad University, School of Information Technology.
    Ekologiskt hållbar med Business Intelligence: Stöd från BI vid ekologiskt hållbart arbete2016Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Working ecologically sustainable is in some cases essential for a business to continue to be active on the market. There is a larger demand on businesses today to work ecologically sustainable. This has led to businesses reviewing the way they work in order to reduce their environmental impact. The demand on businesses to reduce their environmental impact has led to implementations of new systems with the purpose of supporting their ecological sustainability. A system that is able to support working with ecological sustainability is BI. With the support from BI, businesses can collect, store and analyze data and hence become more informed about how their processes affect the ecological sustainability. However, studies regarding the relationship between BI and ecological sustainability are few. In many cases businesses overview their work with ecological sustainability separate from remaining part of the business. The main purpose of the study is to identify and map how businesses work with ecological sustainability in practice with support from BI. This is mapped in order to finally compose and present proposals on how BI could strengthen the way businesses work with ecological sustainability. The empirical data for this study were collected through semi-structured interviews. The result of the study shows that manufacturing businesses do not take full support from BI regarding their work with ecological sustainability. The study presents proposals of how BI could strengthen businesses work with ecological sustainability

    Download full text (pdf)
    fulltext
  • 7.
    Bergius, Johan
    et al.
    Halmstad University, School of Information Technology.
    Holmblad, Jesper
    Halmstad University, School of Information Technology.
    LiDAR Point Cloud De-noising for Adverse Weather2022Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    Light Detection And Ranging (LiDAR) is a hot topic today primarily because of its vast importance within autonomous vehicles. LiDAR sensors are capable of capturing and identifying objects in the 3D environment. However, a drawback of LiDAR is that they perform poorly under adverse weather conditions. Noise present in LiDAR scans can be divided into random and pseudo-random noise. Random noise can be modeled and mitigated by statistical means. The same approach works on pseudo-random noise, but it is less effective. For this, Deep Neural Nets (DNN) are better suited. The main goal of this thesis is to investigate how snow can be detected in LiDAR point clouds and filtered out. The dataset used is Winter Adverse DrivingdataSet (WADS). Supervised filtering contains a comparison between statistical filtering and segmentation-based neural networks and is evaluated on recall, precision, and F1. The supervised approach is expanded by investigating an ensemble approach. The supervised result indicates that neural networks have an advantage over statistical filters, and the best result was obtained from the 3D convolution network with an F1 score of 94.58%. Our ensemble approaches improved the F1 score but did not lead to more snow being removed. We determine that an ensemble approach is a sub-optimal way of increasing the prediction performance and holds the drawback of being more complex. We also investigate an unsupervised approach. The unsupervised networks are evaluated on their ability to find noisy data and correct it. Correcting the LiDAR data means predicting new values for detected noise instead of just removing it. Correctness of such predictions is evaluated manually but with the assistance of metrics like PSNR and SSIM. None of the unsupervised networks produced an acceptable result. The reason behind this negative result is investigated and presented in our conclusion, along with a model that suffers none of the flaws pointed out.

    Download full text (pdf)
    fulltext
  • 8.
    Björkelund, Anders
    et al.
    Department of Astronomy and Theoretical Physics, Lund University, Lund, Sweden.
    Ohlsson, Mattias
    Department of Astronomy and Theoretical Physics, Lund University, Lund, Sweden.
    Lundager Forberg, Jakob
    Department of Cardiology, Skåne University Hospital, Lund, Sweden.
    Mokhtari, Arash
    Department of Cardiology, Skåne University Hospital, Lund, Sweden; Department of Clinical Sciences at Lund, Lund University, Lund, Sweden.
    Olsson de Capretz, Pontus
    Department of Clinical Sciences at Lund, Lund University, Lund, Sweden; Department of Emergency Medicine, Skåne University Hospital, Lund, Sweden.
    Ekelund, Ulf
    Department of Clinical Sciences at Lund, Lund University, Lund, Sweden; Department of Emergency Medicine, Skåne University Hospital, Lund, Sweden.
    Björk, Jonas
    Division of Occupational and Environmental Medicine, Lund University, Lund, Sweden; Clinical Studies Sweden, Forum South, Skåne University Hospital, Lund, Sweden.
    Machine learning compared with rule‐in/rule‐out algorithms and logistic regression to predict acute myocardial infarction based on troponin T concentrations2021In: Journal of the American College of Emergency Physicians Open, E-ISSN 2688-1152, Vol. 2, no 2, article id e12363Article in journal (Refereed)
    Abstract [en]

    Abstract

    ObjectiveComputerized decision-support tools may improve diagnosis of acute myocardial infarction (AMI) among patients presenting with chest pain at the emergency department (ED). The primary aim was to assess the predictive accuracy of machine learning algorithms based on paired high-sensitivity cardiac troponin T (hs-cTnT) concentrations with varying sampling times, age, and sex in order to rule in or out AMI.

    Methods

    In this register-based, cross-sectional diagnostic study conducted retrospectively based on 5695 chest pain patients at 2 hospitals in Sweden 2013–2014 we used 5-fold cross-validation 200 times in order to compare the performance of an artificial neural network (ANN) with European guideline-recommended 0/1- and 0/3-hour algorithms for hs-cTnT and with logistic regression without interaction terms. Primary outcome was the size of the intermediate risk group where AMI could not be ruled in or out, while holding the sensitivity (rule-out) and specificity (rule-in) constant across models.

    Results

    ANN and logistic regression had similar (95%) areas under the receiver operating characteristics curve. In patients (n = 4171) where the timing requirements (0/1 or 0/3 hour) for the sampling were met, using ANN led to a relative decrease of 9.2% (95% confidence interval 4.4% to 13.8%; from 24.5% to 22.2% of all tested patients) in the size of the intermediate group compared to the recommended algorithms. By contrast, using logistic regression did not substantially decrease the size of the intermediate group.

    Conclusion

    Machine learning algorithms allow for flexibility in sampling and have the potential to improve risk assessment among chest pain patients at the ED.

  • 9.
    Chen, Lei
    et al.
    Research Institutes of Sweden, RISE Viktoria, Lindholmspiren 3A, Gothenburg, 417 56, Sweden.
    Englund, Cristofer
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Every Second Counts: Integrating Edge Computing and Service Oriented Architecture for Automatic Emergency Management2018In: Journal of Advanced Transportation, ISSN 0197-6729, E-ISSN 2042-3195, p. 13-, article id 7592926Article in journal (Refereed)
    Abstract [en]

    Emergency management has long been recognized as a social challenge due to the criticality of the response time. In emergency situations such as severe traffic accidents, minimizing the response time, which requires close collaborations between all stakeholders involved and distributed intelligence support, leads to greater survival chance of the injured. However, the current response system is far from efficient, despite the rapid development of information and communication technologies. This paper presents an automated collaboration framework for emergency management that coordinates all stakeholders within the emergency response system and fully automates the rescue process. Applying the concept of multiaccess edge computing architecture, as well as choreography of the service oriented architecture, the system allows seamless coordination between multiple organizations in a distributed way through standard web services. A service choreography is designed to globally model the emergency management process from the time an accident occurs until the rescue is finished. The choreography can be synthesized to generate detailed specification on peer-to-peer interaction logic, and then the specification can be enacted and deployed on cloud infrastructures. © 2018 Lei Chen and Cristofer Englund.

  • 10.
    Ekman, Sebastian
    Halmstad University.
    En IT Forensik utredning med fria verktyg2019Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Download full text (pdf)
    fulltext
  • 11.
    Gelzinis, Adas
    et al.
    Department of Electric Power Systems, Kaunas University of Technology, Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research. Department of Electric Power Systems, Kaunas University of Technology, Kaunas, Lithuania.
    Vaiciukynas, Evaldas
    Department of Electric Power Systems, Kaunas University of Technology, Kaunas, Lithuania.
    Bacauskiene, Marija
    Department of Electric Power Systems, Kaunas University of Technology, Kaunas, Lithuania.
    Minelga, Jonas
    Department of Electric Power Systems, Kaunas University of Technology, Kaunas, Lithuania.
    Hållander, Magnus
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Uloza, Virgilijus
    Department of Otolaryngology, Lithuanian University of Health Sciences, Kaunas, Lithuania.
    Padervinskis, Evaldas
    Department of Otolaryngology, Lithuanian University of Health Sciences, Kaunas, Lithuania.
    Exploring sustained phonation recorded with acoustic and contact microphones to screen for laryngeal disorders2014In: 2014 IEEE Symposium on Computational Intelligence in Healthcare and e-health (CICARE), Piscataway, NJ: IEEE Press, 2014, p. 125-132Conference paper (Refereed)
    Abstract [en]

    Exploration of various features and different structures of data dependent random forests in screening for laryngeal disorders through analysis of sustained phonation recorded by acoustic and contact microphones is the main objective of this study. To obtain a versatile characterization of voice samples, 14 different sets of features were extracted and used to build an accurate classifier to distinguish between normal and pathological cases. We proposed a new, data dependent random forest-based, way to combine information available from the different feature sets. An approach to exploring data and decisions made by a random forest was also presented. Experimental investigations using a mixed gender database of 273 subjects have shown that the Perceptual linear predictive cepstral coefficients (PLPCC) was the best feature set for both microphones. However, the LP-coefficients and LPCT-coefficients feature sets exhibited good performance in the acoustic microphone case only. Models designed using the acoustic microphone data significantly outperformed the ones built using data recorded by the contact microphone. The contact microphone did not bring any additional information useful for classification. The proposed data dependent random forest significantly outperformed traditional designs. © 2014 IEEE.

  • 12.
    Granberg, Richard
    Halmstad University, School of Information Technology.
    Bedrägeribrottslighetens utveckling: INFORMATIONSTEKNOLOGINS PÅVERKAN PÅ BROTTET2016Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [sv]

    Syftet med rapporten är att ge svar på hur de IT-relaterade bedrägeribrotten utvecklatsunder perioden 2006 tom 2015, ge förklaringar till orsaker och vilka förutsättningar somligger bakom. Samt ge svar på om det föreligger en skillnad i antalet lagförda IT-relate-rade bedrägeribrott, jämfört med bedrägeribrott i övrigt, och orsak till detta. Jag har ihuvudsak begränsat mig till ett fåtal väldokumenterade källor, och utifrån dessa tagitfram statistik som bearbetats. Materialet redovisas i tabeller och diagram. Utifrån dessahar därefter jämförelser gjorts mellan de IT-relaterade bedrägeribrotten och de totalt an-tal handlagda bedrägeribrotten för 2015 för att kunna påvisa en eventuell skillnad. Re-sultatet analyserades med hjälp av tidigare forskning och inom kriminilogin erkända te-orier. Vi kan konstatera utifrån denna studie, att de IT-relaterade bedrägeribrotten haften makalös utvecklingskurva, och det finns inget som tyder på att denna kurva håller påatt mattas av. Antalet anmälda brott i dessa kategorier följer den upplevda utsatthetenför brott, så man kan på goda grunder konstatera att det föreligger en faktisk ökning.Dessvärre finns det ett stort mörkertal då endast var 4:e brott uppges anmälas. De fak-torer som kan antas ligga bakom denna ökning är flera. Svenskarnas tillgång till och an-vändning av internet är en förklaring, då tillgången till dator, internet och bredband lig-ger på en hög nivå på 90 procent eller över. Vi har anammat den nya tekniken till attförenkla vår vardag och utför därför allt fler tjänster och hanterar allt mer känslig in-formation över internet. Här finns bland användare en okunskap om de risker man utsät-ter sig för men även en övertro till säkerheten över internet. Incitamenten för att somkriminell befinna sig i detta forum är flera. Den ökade användningen har resulterat i flerlättillgängliga brottsofferkandidater, samt att det är stora värden som hanteras via inter-net i form av handel, spel mm. Avsaknaden av en kapabel väktare miskar risken att bliupptäckt, och kombinationen av myndigheters kompetens- och resursbrist att handläggaärenden, gör sannoliketen att tilldelas en fällande dom mycket liten, då antalet fällandedomar är lägre i dessa brottskategorier än för övriga. Anledningen till att utvecklingenhar tagit denna riktning kan i sin tur härledas till flera orsaker. Polis och rättväsendet iövrigt hinner inte med i den takt ökningen sker, men då det inte är ovanligt att dessabrott utförs på en internationell arena, försvåras också utredning och åtkomst till bevis.Det framkommer i utredningar från såväl Rikspolisstyrelsen och Riksrevisionen, att detråder en tydlig kompetensbrist i området, men också det faktum att man ännu inte lyck-ats enas om definitionen om vad ett IT-brott faktiskt är. Språket i sig är också en viktigfaktor i hur väl myndigheterna lyckas i sitt uppdrag. Allt detta sammantaget får så långt-gående konsekvenser som att svensk polis klarar upp allt färre brott. Detta i sin turruckar förtroendet för berörda myndigheter och rättsväsendet som helhet. Det finns yt-terligare ett scenario, att om dessa brott fortsätter att ligga på höga nivåer eller öka i nu-varande takt, riskerar vi också att tappa tilltro till att utföra och använda oss av alla defantastiska tjänser som vi nu vant oss vid.

    Download full text (pdf)
    fulltext
  • 13.
    Gray, Struan
    et al.
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), Centre for Research on Embedded Systems (CERES).
    Axelsson, Stefan
    Norwegian University of Science and Technology, Gjovik, Norway.
    Digital Forensic Atomic Force Microscopy of Semiconductor Memory Arrays2019In: Advances in Digital Forensics XV: 15th IFIP WG 11.9 International Conference, Orlando, FL, USA, January 28–29, 2019, Revised Selected Papers, Cham: Springer, 2019, p. 219-237Conference paper (Refereed)
    Abstract [en]

    Atomic force microscopy is an analytical technique that provides very high spatial resolution with independent measurements of surface topography and electrical properties. This chapter assesses the potential for atomic force microscopy to read data stored as local charges in the cells of memory chips, with an emphasis on simple sample preparation (“delidding”) and imaging of the topsides of chip structures, thereby avoiding complex and destructive techniques such as backside etching and polishing. Atomic force microscopy measurements of a vintage EPROM chip demonstrate that imaging is possible even when sample cleanliness, stability and topographical roughness are decidedly sub-optimal. As feature sizes slip below the resolution limits of optical microscopy, atomic force microscopy offers a promising route for functional characterization of semiconductor memory structures in RAM chips, microprocessors and cryptographic hardware. © IFIP International Federation for Information Processing 2019. Published by Springer Nature Switzerland AG 2019

  • 14.
    Hall, Ola
    et al.
    Lund University, Lund, Sweden.
    Ohlsson, Mattias
    Halmstad University, School of Information Technology. Lund University, Lund, Sweden.
    Rögnvaldsson, Thorsteinn
    Halmstad University, School of Information Technology.
    A review of explainable AI in the satellite data, deep machine learning, and human poverty domain2022In: Patterns, E-ISSN 2666-3899, Vol. 3, no 10, article id 100600Article, review/survey (Refereed)
    Abstract [en]

    Recent advances in artificial intelligence and deep machine learning have created a step change in how to measure human development indicators, in particular asset-based poverty. The combination of satellite imagery and deep machine learning now has the capability to estimate some types of poverty at a level close to what is achieved with traditional household surveys. An increasingly important issue beyond static estimations is whether this technology can contribute to scientific discovery and, consequently, new knowledge in the poverty and welfare domain. A foundation for achieving scientific insights is domain knowledge, which in turn translates into explainability and scientific consistency. We perform an integrative literature review focusing on three core elements relevant in this context—transparency, interpretability, and explainability—and investigate how they relate to the poverty, machine learning, and satellite imagery nexus. Our inclusion criteria for papers are that they cover poverty/wealth prediction, using survey data as the basis for the ground truth poverty/wealth estimates, be applicable to both urban and rural settings, use satellite images as the basis for at least some of the inputs (features), and the method should include deep neural networks. Our review of 32 papers shows that the status of the three core elements of explainable machine learning (transparency, interpretability, and domain knowledge) is varied and does not completely fulfill the requirements set up for scientific insights and discoveries. We argue that explainability is essential to support wider dissemination and acceptance of this research in the development community and that explainability means more than just interpretability. (c) 2022 The Author(s). 

  • 15.
    Halvordsson, Julia
    et al.
    Halmstad University, School of Information Technology.
    Olsson, Madeleine
    Halmstad University, School of Information Technology.
    Tönsberg, Malin
    Halmstad University, School of Information Technology.
    Genomsökning på distans: - det moderna straffprocessuella tvångsmedlet2023Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [sv]

    Den 1 juni 2022 infördes en ny lag i Rättegångsbalken vilket öppnade upp nya möjligheter för brottsbekämpande myndigheter att kunna genomsöka information som inte är lagrad internt på en kommunikationsutrustning. Denna lag fick namnet genomsökning på distans. Syftet med detta arbete var att granska lagen med koppling till de kränkningar som görs i den personliga integriteten. Vi har även undersökt avvägningen av jurisdiktion i beslutsfattningen vid inhämtning av data som inte är lagrad i Sverige samt att ett mindre experiment har genomförts för att belysa svårigheter med den praktiska tillämpningen av lagen. 

    Download full text (pdf)
    fulltext
  • 16.
    Holst, Anders
    et al.
    RISE SICS, Stockholm, Sweden.
    Karlsson, Alexander
    School of Informatics, University of Skövde, Sweden.
    Bae, Juhee
    School of Informatics, University of Skövde, Sweden.
    Bouguelia, Mohamed-Rafik
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research. Department of Intelligent Systems and Digital Design, Halmstad University, Sweden.
    Interactive clustering for exploring multiple data streams at different time scales and granularity2019In: Proceedings of the Workshop on Interactive Data Mining, WIDM 2019, Association for Computing Machinery (ACM), 2019Conference paper (Refereed)
    Abstract [en]

    We approach the problem of identifying and interpreting clusters over different time scales and granularity in multivariate time series data. We extract statistical features over a sliding window of each time series, and then use a Gaussian mixture model to identify clusters which are then projected back on the data streams. The human analyst can then further analyze this projection and adjust the size of the sliding window and the number of clusters in order to capture the different types of clusters over different time scales. We demonstrate the effectiveness of our approach in two different application scenarios: (1) fleet management and (2) district heating, wherein each scenario, several different types of meaningful clusters can be identified when varying over these dimensions. © 2019 Copyright held by the owner/author(s). Publication rights licensed to ACM.

  • 17.
    Hämäläinen, Ari
    et al.
    Halmstad University, School of Information Technology.
    Nadesan, Rekha
    Halmstad University, School of Information Technology.
    Enhancing Supply Chain Cybersecurity with Blockchain2022Independent thesis Advanced level (degree of Master (One Year)), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Supply chains have become targets for hostile cyber actors. Motivations for cyber crimes include intellectual property theft, customer data theft and industrial espionage. The cyber threat landscape in which businesses operate is constantly evolving. The consequences of a successful cyber attack can be devastating for a business. Increasing the resilience of the supply chain in the digital environment is a complex task because the supply chain consists of different organisations with varying levels of cybersecurity defence capability. Orchestrating cybersecurity improvement in a supply chain requires visibility into the security posture of each participating organisation and this is generally lacking. This thesis studies the potential use of blockchain for enhancing the cybersecurity of the supply chain. The study simulates a permissioned blockchain among supply chain members to monitor digital assets important for cybersecurity. The blockchain is analysed to extract insights from the perspective of a supply chain cybersecurity oversight role. The study finds that a blockchain can provide visibility by sharing cybersecurity-related information among supply chain members. It can also provide a digital forensic record for incident response and forensic investigations.

    Download full text (pdf)
    fulltext
  • 18.
    Ihlström, Carina
    et al.
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS).
    Lundberg, Jonas
    Linköping University, Linköping, Sweden.
    Perdrix, Ferran
    University of Lleida, Lleida, Spain.
    Audience of Local Online Newspapers in Sweden, Slovakia and Spain – a comparative study2003In: Human-Centred Computing: Cognitive, Social and Ergonomic Aspects / [ed] Don Harris, Vincent Duffy, Michael Smith & Constantine Stephanidis, London: Lawrence Erlbaum Associates, 2003, Vol. 3, p. 749-753Conference paper (Refereed)
    Abstract [en]

    Since a new online audience for local newspapers has emerged during the last years, in response to the growth of the Internet, we need to know who they are, what their reading habits are, and what their view on emerging technologies are, to be able to design good online newspapers. We have conducted a study using online questionnaires at three local online newspapers in three different countries: Sweden, Slovakia and Spain. The objective of this paper is to describe the differences and similarities between the three countries regarding audience profiles, scenarios of use, opinions of current and future issues and to discuss design implications.

  • 19.
    Ihlström, Carina
    et al.
    Univ Gothenburg, Viktoria Inst, Gothenburg, Sweden.
    Magnusson, M.
    Univ Gothenburg, Viktoria Inst, Gothenburg, Sweden.
    Scupola, A.
    Univ Gothenburg, Viktoria Inst, Gothenburg, Sweden.
    Tuunainen, Virpi Kristiina
    Univ Gothenburg, Viktoria Inst, Gothenburg, Sweden.
    Myths and reality of electronic commerce barriers for SMES?2002In: Issues and trends of information technology management in contemporary organizations, Hershey: Idea Group Publishing, 2002, p. 282-284Conference paper (Refereed)
    Abstract [en]

    In this paper we look into earlier empirical research on the barriers to electronic commerce (EC) for small and medium sized enterprises (SMEs). We look into research conducted in the context of information and communications technologies (ICT) in general, as well as EDI and Internet based EC. We divide the barriers, inhibitors or factors slowing down the diffusion of new technologies found in literature into those internal to an organization, and those imposed by external forces. The basic premise of this paper is, that technologies advance or change, but the barriers for SMEs to adopt them do not.

  • 20.
    Ihlström, Carina
    et al.
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS). Viktoria Institute, Gothenburg University, Gothenburg, Sweden.
    Nilsson, Malin
    Viktoria Institute, Gothenburg University, Gothenburg, Sweden & Department of Computer Science and Business, University of Borås, Borås, Sweden.
    SMEBIZ: Transforming t-Business to e-Business2000In: IRIS 23 : Doing IT together 12-15 August, 2000, at Lingatan, Sweden: Proceedings of the 23rd Information Systems Research Seminar in Scandinavia / [ed] L. Svensson, U. Snis, C. Sørensen, H. Fägerlind, T. Lindroth, M. Magnusson & C. Östlund, Uddevalla: Laboratorium for Interaction Technology, University of Trollhättan/Uddevalla , 2000, Vol. 2, p. 835-843Conference paper (Refereed)
    Abstract [en]

    The context for this research is the organizational process of transforming small- and medium-sized enterprises (SME) from traditional (t-) business to e-business and the accompanying development of the knowledge and competence among amployees. The aim of this research is to investigate SMEs with the purpose of designing, implementing and evaluating IT-supported activities that will allow SMEs to approach e-business.

  • 21.
    Ihlström, Carina
    et al.
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS).
    Nilsson, Malin
    University of Borås, Borås, Sweden.
    Transformation of SMEs towards E-business - The Initial Stage2000Conference paper (Refereed)
  • 22.
    Ihlström, Carina
    et al.
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS). Viktoria Institute, Gothenburg University, Gothenburg, Sweden.
    Örtenblad, Anders
    Halmstad University, School of Business and Engineering (SET).
    IT-companies: Playgrounds or Serious Businesses?2000In: IRIS 23 – doing IT together 12-15 August, 2000, at Lingatan, Sweden: Proceedings of the 23rd Information Systems Research Seminar in Scandinavia / [ed] L. Svensson, U. Snis, C. Sørensen, H. Fägerlind, T. Lindroth, M. Magnusson & C. Östlund, Uddevalla: Laboratorium for Interaction Technology, University of Trollhättan/Uddevalla , 2000, Vol. 2, p. 1605-1616Conference paper (Refereed)
  • 23.
    Ihlström Eriksson, Carina
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).
    Mot e-papper och läsplattor - tidningarnas förberedelser2013In: På väg mot medievärlden 2020: Journalistik, teknik och marknad / [ed] Gunnar Nygren, Ingela Wadbring, Lund: Studentlitteratur, 2013, 5, p. 59-76Chapter in book (Other academic)
  • 24.
    Ihlström Eriksson, Carina
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS), Man and Information technology laboratory (MI-lab).
    The e-newspaper innovation - converging print and online2005Conference paper (Other academic)
    Abstract [en]

    The new e-paper technology has provided the newspaper companies with the possibility of publishing a portable digital e-newspaper with the same readability as in print media. The e-newspaper is converging print and online with the best from two worlds, i.e. the overview and familiar design of the printed edition and the interactivity and continuous updates of the web. Based on six workshops and 14 interviews with newspaper managers, and three brainstorming sessions with the e-paper steering group (consisting of representatives from the Swedish Newspaper Publishers’ Association and eight Swedish newspaper managers) I will discuss the challenges of introducing this new innovation.

    Download full text (pdf)
    fulltext
  • 25.
    Ihlström Eriksson, Carina
    et al.
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), Man and Information technology laboratory (MI-lab).
    Åkesson, Maria
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), Man and Information technology laboratory (MI-lab).
    An Interorganizational Learning Approach to New Innovations: Exploring the e-newspaper Case2007In: Proceedings of the 4th International Conference on Intellectual Capital, Knowledge Management and Organisational Learning / [ed] Dan Remenyi, Reading, U.K.: Academic Conferences Limited, 2007, p. 179-187Conference paper (Refereed)
    Abstract [en]

    In this paper we are addressing the following research question: How can an interorganizational learning approach influence an industry business strategy for a new innovation? When adopting new innovations organizations need to learn about the innovation’s gains and how it functions in the organizations line of business. This organizational learning process varies between “trial and error”, information seeking or a“wait and see” approach etc. When new innovations have the potential to cause paradigm shifts to whole industries interorganizational learning approaches are called for. We have explored the e-newspaper case, i.e. the introduction of e-paper technology in the newspaper industry. E-paper is a reflecting display technology with properties very close toprint on paper, with high contrast and readability. Thus, an e-newspaper, i.e. a newspaper service published on an e-paper device, holds the potential of replacing the printed editionin the long run, thereby heavily reducing printing and distribution cost, making it an interesting prospect for the industry. In two research projects, DigiNews and UbiMedia, we have conducted interviews, future workshops, design focus group and steering committee meetings with newspaper representatives from nine Swedish newspaper companies and the Swedish Newspaper Publishers´ Association. The purpose of this paper is to analyze how an interorganizational learning approach between competing organizations to new innovations can play out using the four modes of knowledge conversion by Nonaka and Takeuchi (1995). The results indicates that by taking such an approach, Swedish newspaper organizations were able to reach an agreement on collaborating on distribution, possible standards and business models while still competing on content, thereby initiating a joint business strategy for the e-newspaper introduction. Summing up, the findings show that an interorganizational learning approach benefits from: (1) being organized at very early in the innovation process; and (2) being organized by a neutral facilitator and academics are suitable for that role.

  • 26.
    Islam, Mohammad Shahidul
    et al.
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE).
    Mehdi, Syed Nasir
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE).
    How Different QoS Mechanisms Affect VoIP QoS Metrics2010Independent thesis Advanced level (degree of Master (One Year)), 15 credits / 22,5 HE creditsStudent thesis
    Abstract [en]

    Voice over Internet Protocol (VoIP) has become a key technology of communication. Our work has been a practical implemenation of different scenarios to show that VoIP voice quality can be improved by adopting certain Quality of Service(QoS) measures such as classification, marking or queuing. It has been discussed that different QoS metrics like delay, packet loss and jitter could affect the voice quality of VoIP. To reduce the negative affects, one option is to implement certain QoS mechanisms with some set of configurations. For this purpose, Cisco IP phones have been configured in our topology with routers, switches, traffic generators, end stations and VoIP quality monitoring software called VQmanager. Tests have been divided into two sets. In one test a fixed bandwidth of 70 kbps is set while in the other test a random bandwidth is set with trafic generators unleashing packets of traffic. In both these tests further scenarios with configurations are worked out. They include no QoS, Auto Qos and Customized Qos mechanisms. Results have been indicative of top performance by the Customized QoS mechanism, in both sets of tests, followed by Auto QoS and no QoS mechanisms. It has been observed that a customized scenario could be a particular configuration to any organization’s needs and that will have the lowest delay, jitter and packet loss which are the main QoS metrics that impact the voice quality of VoIP. It  can be fundamentally composed of classification of voice, data or web-traffic, marking and queuing depending upon the need of the organization. It is finally suggested to carry more tests in companies to get more data for analysis

    Download full text (pdf)
    fulltext
  • 27.
    Jäverbo, Niklas
    et al.
    Halmstad University, School of Information Technology.
    Hörnfalk, David
    Halmstad University, School of Information Technology.
    Nätfiske: Vad är den underliggande orsaken till att personer faller för nätfiske?2018Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [sv]

    Nätfiske inom cybervärlden är ett stort och återkommande problem. Detta är det störst växande viset att sprida malware genom internet. Att utforma en nätfiskeattack kan generera många olika typer av resultat. Få ut känslig information, få den utsatta att ladda ned bifogad fil, för att sprida malware till den utsattas dator eller exempelvis låsa personens system genom ett ransomware.

    I detta arbete undersöks problematiken med nätfiske, vad det är för något, hur det går till när en nätfiskekampanj utförs samt vad som går att göra för att motverka detta på en mänsklig nivå. Det finns mycket forskning om olika typer av anti- nätfiskesystem och metoder. Detta arbete baserar sig på vad som går att göra för att öka säkerhetsmedvetenhet hos personer.

    Genom att utföra en enkätundersökning och ett penetrationstest om nätfiske hos en organisation undersöks kunskapen och säkerhetsmedvetenheten hos personalen för denna organisation. Undersökningen genomfördes för att kartlägga vad orsaken är att personer faller för dessa typer av attacker.

    Download full text (pdf)
    fulltext
  • 28.
    Kahlqvist, Johanna
    et al.
    Halmstad University, School of Information Technology.
    Falk, Ebba
    Halmstad University, School of Information Technology.
    Extremism på digitala plattformar: En kvalitativ studie av TikToks rekommendationsalgoritm2022Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    The threat of violent extremism is considered by authorities as one of the largest today. Political extremism has increased over the years and the number of politically motivated terrorist incidents in the Western world is higher than religiously motivated. The role of digital platforms when it comes to recruitment and radicalization is widely debated. This study specifically examines TikTok which is one of the fastest growing and leading digital platforms. TikTok's recommendation system differs from other social media by being the main product for the platform. Experiments show how TikTok's algorithms recommend hateful content exponentially, and that the different types of hateful content that are examined have a high correlation to one another. In some cases, extremist content was also recommended. Furthermore, it is stated that TikTok does not take enough action when videos and/or profiles are being reported for hateful and/or extremist content. The literature study also showed that the Swedish Police Authority's handling of hate crimes on the Internet is insufficient despite pressure to improve from the government.

    Download full text (pdf)
    fulltext
  • 29.
    Kalsyte, Zivile
    et al.
    Kaunas University of Technology, Kaunas, Lithuania.
    Verikas, Antanas
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent systems (IS-lab). Kaunas University of Technology, Kaunas, Lithuania.
    Vasiliauskaite, Asta
    Kaunas University of Technology, Kaunas, Lithuania.
    Predicting trends of financial attributes by an adaptive committee of models2012In: Proceedings of the 7th International Conference on Electrical and Control Technologies ECT 2012 / [ed] A. Navickas (Editor-in-Chief), A. Sauhats, A. Virbalis, M. Ažubalis, V. Galvanauskas, K. Brazauskas & A. Jonaitis, Kaunas: Kaunas University of Technology , 2012, p. 48-53Conference paper (Refereed)
    Abstract [en]

    This paper presents an approach to designing an adaptive, data dependent, committee of multilayer perceptrons (MLP) for predicting trends (positive or negative change) of five financial attributes used for assessing future performance of a company. Total Asset Turnover [TAT], Current Ratio [CR], Gross Margin [GM], Operating Margin [OM], and Return on Equity [ROE] are the attributes used in this paper. A two- and three-years ahead prediction of change is considered. A Self-Organizing Map (SOM) used for data mapping and analysis enables building committees, which are specific (committee size and aggregation parameters) for each data point analyzed. When tested on data concerning 59 companies of the United States biotechnology sector, committees built according to the proposed technique outperformed both averaging and weighted averaging committees.

  • 30.
    Karresand, Martin
    et al.
    Norwegian University of Science and Technology (NTNU), Gjorvik, Norway & Intelligence, Surveillance and Reconnaissance (C4ISR), Swedish Defence Research Agency (FOI), Sweden.
    Axelsson, Stefan
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS). Norwegian University of Science and Technology (NTNU), Gjorvik, Norway.
    Dyrkolbotn, Geir Olav
    Norwegian University of Science and Technology (NTNU), Gjorvik, Norway.
    Using NTFS Cluster Allocation Behavior to Find the Location of User Data2019In: Digital Investigation. The International Journal of Digital Forensics and Incident Response, ISSN 1742-2876, E-ISSN 1873-202X, Vol. 29, no Supplement, p. S51-S60Article in journal (Refereed)
    Abstract [en]

    Digital forensics is heavily affected by the large and increasing amount of data to be processed. To solve the problem there is ongoing research to find more efficient carving algorithms, use parallel processing in the cloud, and reduce the amount of data by filtering uninteresting files. Our approach builds on the principle of searching where it is more probable to find what you are looking for. We therefore have empirically studied the behavior of the cluster allocation algorithm(s) in the New Technology File System (NTFS) to see where new data is actually placed on disk. The experiment consisted of randomly writing, increasing, reducing and deleting files in 32 newly installed Windows 7, 8, 8.1 and 10 virtual computers using VirtualBox. The result show that data are (as expected) more frequently allocated closer to the middle of the disk. Hence that area should be getting higher attention during a digital forensic investigation of a NTFS formatted hard disk. Knowledge of the probable position of user data can be used by a forensic investigator to prioritize relevant areas in storage media, without the need for a working file system. It can also be used to increase the efficiency of hash-based carving by dynamically changing the sampling frequency. Our findings also contributes to the digital forensics processes in general, which can now be focused on the interesting regions on storage devices, increasing the probability of getting relevant results faster. © 2019 Martin Karresand, Stefan Axelsson, Geir Olav Dyrkolbotn

  • 31.
    Karresand, Martin
    et al.
    Norwegian University of Science and Technology, Gjovik, Norway.
    Warnqvist, Åsalena
    National Forensic Centre, Swedish Police Authority, Linköping, Sweden.
    Lindahl, David
    Swedish Defence Research Agency, Linköping, Sweden.
    Axelsson, Stefan
    Norwegian University of Science and Technology, Gjovik, Norway.
    Dyrkolbotn, Geir Olav
    Norwegian University of Science and Technology, Gjovik, Norway.
    Creating a Map of User Data in NTFS to Improve File Carving2019In: Advances in Digital Forensics XV: 15th IFIP WG 11.9 International Conference, Orlando, FL, USA, January 28–29, 2019,Revised Selected Papers / [ed] Gilbert Peterson & Sujeet Shenoi, Cham: Springer, 2019, p. 133-158Conference paper (Refereed)
    Abstract [en]

    Digital forensics, and espesially, file carving are burdened by the large amounts of data that need to be processed. Attempts to solve this problem include efficient carving algorithms, parallel processing in the cloud and data reduction by filtering uninteresting files. This research addresses the problem by searching for data wher it is more likely to be found. This is accomplished by creating a probability map for finding unique data at various logical block addressing positions in storage media. SHA-1 hashes of 512B sectors are used to represent the data. The results, which are based on a collection of 30 NTFS partitions from computers runnign Microsoft Windows 7 and later versions, reveal that the mean probability of finding unique hash values at different logical block addressing positions vary between 12% and 41% in an NTFS partition. The probability map can be used by forensic analyst to prioritize relevant areas in storage media without the need for a working filesystem. It can also be used to increase the efficienty of hash-based carving by dinamically changing the random sampling frequency. The approach contributes to digital forensic processes by enabling them to focus on interesting regions in storage media, increasing the probability of obtaining relevant results faster. © IFIP International Federation for Information Processing 2019

  • 32.
    Lindblom, Greger
    et al.
    Halmstad University, School of Information Technology.
    Svensson, Rikard
    Halmstad University, School of Information Technology.
    Aktivitetsarmband: En studie om aktivitetsarmband sett från ett integritetsperspektiv2017Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [sv]

    Aktivitetsarmband, bärbara enheter i grunden avsedda för loggande och mätning av fysisk aktivitet, är ett av många exempel på uppkopplade enheter som på kort tid har blivit en del av det vardagliga livet för en betydande andel av det svenska folket.

    Säkerheten kring dessa produkter varierar kraftigt och något sätt för den enskilda individen att avgöra vilken produkt som är säker att använda finns inte.

    Det huvudsakliga syfte med studien är att öka förståelsens kring konsumenters bild och uppfattning kopplat till aktivitetsarmband och den integritetsproblematik insamling, sammanställning och presentation av denna typ av personlig information innebär.

    De frågeställningar som studien behandlar fokuserar på huruvida en oro för integriteten kopplat till användandet av aktivitetsarmband kan identifieras bland konsumenter. Vidare ställs frågan om det finns något som tyder på skillnader i synen på användande av aktivitetsarmband sett från ett integritetsperspektiv. Denna studie behandlar även frågan hur konsumenter ställer sig till att betala mer för ett aktivitetsarmband som sett från ett integritetsperspektiv är att anse som säkrare.

    Studien bygger på en kombination utav kvantitativ och kvalitativ metod där en enkätundersökning har genomförts vilken sedan kompletterats med semi-strukturerade intervjuer.

    Avsikten med denna studie är inte att redogöra för den faktiska allmänna uppfattningen eller att besvara eller säkerställa hur framtagna ställda frågeställningar förhåller sig till den allmänna uppfattningen. Denna studie fokuserar på en för produkten intressant kategori individer och studiens syfte är endast att undersöka huruvida en oro för den personliga integriteten kan identifieras inom denna population. Avsikten med studiens resultat är snarare att det skall kunna utgöra grund för beslut om behov av vidare mer omfattande undersökningar.

    Denna studie ger i förhållande till dess undersöknings omfattning tydliga indikationer på en allmän oro bland konsumenter kopplat till användandet av aktivitetsarmband. Studien visar även indikationer på ett bland konsumenter utbrett intresse för produkter med en högre säkerhetsnivå.

    Studiens resultat pekar på ett tydligt behov av vidare studier inom området.

    Download full text (pdf)
    fulltext
  • 33.
    Lisander, Joakim
    et al.
    Halmstad University.
    Lyxell, Niklas
    Halmstad University.
    Problem kring mobilforensik: En sammanställning om hur mobiltelefoner och forensiska verktyg hanterar kryptering, utvinning och molnlagring2015Independent thesis Basic level (degree of Bachelor), 180 HE creditsStudent thesis
    Abstract [sv]

    Mobiltelefoner innehåller idag en stor mängd information som är av stort forensiskt intresse. Att skydda informationen i sin telefon är en självklarhet för många och utvecklarna av de mobila operativsystemen lägger nu större vikt på säkerhet och skydd av information. Kryptering är idag standard i de flesta mobiltelefoner och det leder till problem vid utvinning. Arbetet tar upp och jämför hur kryptering hanteras av iOS, Android och Windows Phone och vilka tillvägagångssätt som finns vid utvinning av data genom att kringgå skärmlåsen som krävs för att krypteringen ska fungera. Arbetet ger även en inblick på molnlagring i och med att det blir allt vanligare och kan komma att bli mer relevant för forensiker eftersom telefonerna blir allt svårare att utvinna data ifrån. Dessutom ges en liten inblick på forensiska verktyg som finns idag, vilka brister de har och vad som är oklart hos dem.  Frågeställningarna har besvarats genom att en grundläggande litteraturstudie genomförts för att få den bakgrundsfakta som krävs. Därefter gjordes det experiment för att visa på brister i de forensiska verktygen. Avslutningsvis svarade två it-forensiker från polisen på intervjufrågor via mail, det gjordes för att lyfta fram problematiken och visa på hur situationen ser ut i arbetslivet idag.  Arbetets resultat visar på att alla operativsystem ger, beroende på hur användaren har anpassat telefonen, möjlighet till fullt skydd mot utvinning. Och därmed klarar de forensiska verktygen som finns idag inte av att utvinna någon relevant information ifrån de senaste mobiltelefonerna. Som forensiker borde man utnyttja att molnlagring börjat användas mer och mer, då det där kan finns mycket bra information. Slutsatser som kan dras efter arbetet är att det behövs nya metoder för att utvinna data ifrån mobiltelefoner då de metoder som tidigare använts inte är kompatibla med de senaste telefonerna på grund utav de krypteringsfunktioner som används. Det finns metoder som kan fungera, men dessa metoder fungerar bara med rätt förutsättningar, vilket gör att det inte är en lösning som man alltid kan applicera. Forensiker borde även utforska möjligheten att få fram information ifrån molnlagringstjänster ifall data på telefonen är oåtkomlig för alla utom ägaren. Arbetet syftar inte till att ta fram nya metoder för utvinning eller arbetssätt inom det stora området forensik, utan kartlägger problemområdet inom mobilforensik och ger förslag på och diskuterar möjliga lösningar.

    Download full text (pdf)
    Kandidatuppsats
  • 34.
    Marchand, Judicaël
    et al.
    École polytechnique de l’Université de Nantes, Nantes, France.
    Puissochet, Gaël
    École polytechnique de l’Université de Nantes, Nantes, France.
    Lithén, Thomas
    Halmstad University, School of Information Technology.
    Taha, Walid
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), Centre for Research on Embedded Systems (CERES).
    MicroITS: A scaled-down ITS platform2019In: Lecture Notes in Computer Science, Springer, 2019, p. 214-221Conference paper (Refereed)
    Abstract [en]

    Intelligent Transportation Systems (ITS) are an excellent illustration of the types of challenges that future technologists must address. In previous work we presented a course designed to engage students with theoretical aspects of embedded and cyber-physical systems. In this paper we present MicroITS, a platform addressing applied aspects. We articulate the design goals that we believe are needed to achieve engagement in an educational setting, and describe the platform and its baseline functionality. We briefly describe example projects that can be realized using MicroITS. Our hope is that this report will encourage the development of a community of educators and students interested in the use and the continued development of the platform. © Springer Nature Switzerland AG 2019.

  • 35.
    Mashad Nemati, Hassan
    et al.
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Sant´Anna, Anita
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Nowaczyk, Sławomir
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Bayesian Network Representation of Meaningful Patterns in Electricity Distribution Grids2016In: 2016 IEEE International Energy Conference (ENERGYCON), IEEE, 2016Conference paper (Refereed)
    Abstract [en]

    The diversity of components in electricity distribution grids makes it impossible, or at least very expensive, to deploy monitoring and fault diagnostics to every individual element. Therefore, power distribution companies are looking for cheap and reliable approaches that can help them to estimate the condition of their assets and to predict the when and where the faults may occur. In this paper we propose a simplified representation of failure patterns within historical faults database, which facilitates visualization of association rules using Bayesian Networks. Our approach is based on exploring the failure history and detecting correlations between different features available in those records. We show that a small subset of the most interesting rules is enough to obtain a good and sufficiently accurate approximation of the original dataset. A Bayesian Network created from those rules can serve as an easy to understand visualization of the most relevant failure patterns. In addition, by varying the threshold values of support and confidence that we consider interesting, we are able to control the tradeoff between accuracy of the model and its complexity in an intuitive way. © 2016 IEEE

    Download full text (pdf)
    fulltext
  • 36.
    Matas, J.
    et al.
    Center for Vision Speech and Signal Processing, University of Surrey, Guildfor, GU2, UK. Center for Machine Perception CTU Prague, Karlovo nám. 13, 121 35 Czech republic.
    Hamouz, M.
    Center for Vision Speech and Signal Processing, University of Surrey, Guildfor, GU2, UK.
    Jonsson, K.
    Center for Vision Speech and Signal Processing, University of Surrey, Guildfor, GU2, UK.
    Kittler, J.
    Center for Vision Speech and Signal Processing, University of Surrey, Guildfor, GU2, UK.
    Li, Y.
    Center for Vision Speech and Signal Processing, University of Surrey, Guildfor, GU2, UK.
    Kotropoulos, C.
    Department of Informatics, Aristotle University of Thessaloniki, Greece.
    Tefas, A.
    Department of Informatics, Aristotle University of Thessaloniki, Greece.
    Patas, I.
    Department of Informatics, Aristotle University of Thessaloniki, Greece.
    Tan, T.
    University of Sydney, NSW 2006 Australia.
    Yan, H
    University of Sydney, NSW 2006 Australia.
    Smeraldi, F
    Swiss Federal Institute of Technology, DI, 1015 Lausanne, Swtizerland.
    Bigun, J.
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS).
    Capdevielle, N.
    Swiss Federal Institute of Technology, DI, 1015 Lausanne, Swtizerland.
    Gerstner, W.
    Swiss Federal Institute of Technology, DI, 1015 Lausanne, Swtizerland.
    Ben-Yacoub, S.
    Swisscom AG.
    Abdeljaoued, Y.
    Swiss Federal Institute of Technology, DI, 1015 Lausanne, Swtizerland.
    Mayoraz, E.
    Motorola Inc..
    Comparison of face verification results on the XM2VTS database2000In: Proceedings of the 15th International Conference on Pattern Recognition (ICPR'00) - Volume 4, 2000, p. 858-863Conference paper (Other academic)
    Abstract [en]

    The paper presents results of the face verification contest that was organized in conjunction with International Conference on Pattern Recognition 2000 [14]. Participants had to use identical data sets from a large, publicly available multimodal database XM2VTSDB. Training and evaluation was carried out according to an a priori known protocol ([7]). Verification results of all tested algorithms have been collected and made public on the XM2VTSDB website [15], facilitating large scale experiments on classifier combination and fusion. Tested methods included, among others, representatives of the most common approaches to face verification - elastic graph matching, Fisher's linear discriminant and Support vector machines.

  • 37.
    Munir, Sundas
    et al.
    Halmstad University, School of Information Technology.
    Baig, Mirza Sanam Iqbal
    Halmstad University, School of Information Technology.
    Challenges and Security Aspects of Blockchain Based Online Multiplayer Games​2019Independent thesis Advanced level (degree of Master (One Year)), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Video gaming has always been a blooming industry. With the emergence of online multi- player video games , this industry’s worth have sky rocketed. Online multiplayer video games store data of player’s credentials, in-game progress, in-game virtual assets and payment details etc. Which mean security threats to these systems are nothing new and securing these games have always meant to protect player’s data from unauthorized breach.

    Integration of Blockchain technology in online multiplayer video games apart from other amazing features, provides a way to prove digital ownership of virtual assets with their verifiable scarcity. Trade of these in-game virtual assets have always been a goal for online multiplayer gaming companies, but there was none enough trust-able infrastructure available which can be relied on. Blockchain just solved that problem. It provided a platform for these asset’s secure and transparent transaction between players.

    Topic for our research not only consider the security challenges in online games but specifi- cally blockchain based online multiplayer games. This adaptation is still new and there is need of consideration of new security challenges. In this dissertation we try to bring out some important challenges related to security of blockchain based online multiplayer video games. There are currently no studies around security concerns and challenges of the integration of the online multiplayer video games in the emerging blockchain systems. In order to fill in the gap, this dissertation discusses and identifies two main security concerning questions related to this domain. Also this dissertation provides basic steps for expanding future research and application in this joint domain.

    Download full text (pdf)
    fulltext
  • 38.
    Najmeh, Abiri
    et al.
    Department of Astronomy and Theoretical Physics, Lund University, Lund, Sweden.
    Ohlsson, Mattias
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Variational auto-encoders with Student’s t-prior2019In: ESANN 2019 Proceedings, 27th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning: Bruges – 24-26 April 2019, Bruges: ESANN , 2019, p. 415-420Conference paper (Refereed)
    Abstract [en]

    We propose a new structure for the variational auto-encoders (VAEs) prior, with the weakly informative multivariate Student’s t-distribution. In the proposed model all distribution parameters are trained, thereby allowing for a more robust approximation of the underlying data distribution. We used Fashion-MNIST data in two experiments to compare the proposed VAEs with the standard Gaussian priors. Both experiments showed a better reconstruction of the images with VAEs using Student’s t-prior distribution. © 2019 ESANN (i6doc.com). All rights reserved.

  • 39.
    Nordvik, Rune
    et al.
    Norwegian University of Science and Technology, Trondheim, Norway & Norwegian Police University College, Oslo, Norway.
    Georges, Henry
    Norwegian University of Science and Technology, Trondheim, Norway.
    Toolan, Fergus
    Norwegian Police University College, Oslo, Norway.
    Axelsson, Stefan
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS). Norwegian University of Science and Technology, Trondheim, Norway.
    Reverse engineering of ReFS2019In: Digital Investigation. The International Journal of Digital Forensics and Incident Response, ISSN 1742-2876, E-ISSN 1873-202X, Vol. 30, p. 127-147Article in journal (Refereed)
    Abstract [en]

    File system forensics is an important part of Digital Forensics. Investigators of storage media have traditionally focused on the most commonly used file systems such as NTFS, FAT, ExFAT, Ext2-4, HFS+, APFS, etc. NTFS is the current file system used by Windows for the system volume, but this may change in the future. In this paper we will show the structure of the Resilient File System (ReFS), which has been available since Windows Server 2012 and Windows 8. The main purpose of ReFS is to be used on storage spaces in server systems, but it can also be used in Windows 8 or newer. Although ReFS is not the current standard file system in Windows, while users have the option to create ReFS file systems, digital forensic investigators need to investigate the file systems identified on a seized media. Further, we will focus on remnants of non-allocated metadata structures or attributes. This may allow metadata carving, which means searching for specific attributes that are not allocated. Attributes found can then be used for file recovery. ReFS uses superblocks and checkpoints in addition to a VBR, which is different from other Windows file systems. If the partition is reformatted with another file system, the backup superblocks can be used for partition recovery. Further, it is possible to search for checkpoints in order to recover both metadata and content. Another concept not seen for Windows file systems, is the sharing of blocks. When a file is copied, both the original and the new file will share the same content blocks. If the user changes the copy, new data runs will be created for the modified content, but unchanged blocks remain shared. This may impact file carving, because part of the blocks previously used by a deleted file might still be in use by another file. The large default cluster size, 64 KiB, in ReFS v1.2 is an advantage when carving for deleted files, since most deleted files are less than 64 KiB and therefore only use a single cluster. For ReFS v3.2 this advantage has decreased because the standard cluster size is 4 KiB. Preliminary support for ReFS v1.2 has been available in EnCase 7 and 8, but the implementation has not been documented or peer-reviewed. The same is true for Paragon Software, which recently added ReFS support to their forensic product. Our work documents how ReFS v1.2 and ReFS v3.2 are structured at an abstraction level that allows digital forensic investigation of this new file system. At the time of writing this paper, Paragon Software is the only digital forensic tool that supports ReFS v3.x. It is the most recent version of the ReFS file system that is most relevant for digital forensics, as Windows automatically updates the file system to the latest version on mount. This is why we have included information about ReFS v3.2. However, it is possible to change a registry value to avoid updating. The latest ReFS version observed is 3.4, but the information presented about 3.2 is still valid. In any criminal case, the investigator needs to investigate the file system version found. © 2019 The Authors

  • 40.
    Nugent, Christopher
    et al.
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research. University of Ulster, Jordanstown, North Ireland.
    Synnott, Jonathan
    University of Ulster, Jordanstown, North Ireland.
    Gabrielli, Celeste
    Marche Polytechnic University, Ancona, Italy.
    Zhang, Shuai
    University of Ulster, Jordanstown, North Ireland.
    Espinilla, Macarena
    University of Jaén, Jaen, Spain..
    Calzada, Alberto
    University of Ulster, Jordanstown, North Ireland.
    Lundström, Jens
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Cleland, Ian
    University of Ulster, Jordanstown, North Ireland.
    Synnes, Kare
    Luleå university of Technology, Luleå, Sweden.
    Hallberg, Josef
    Luleå university of Technology, Luleå, Sweden.
    Spinsante, Susanna
    Marche Polytechnic University, Ancona, Italy.
    Ortiz Barrios, Miguel Angel
    Universidad de la Costa CUC, Barranquilla, Colombia.
    Improving the Quality of User Generated Data Sets for Activity Recognition2016In: Ubiquitous Computing and Ambient Intelligence, UCAMI 2016, PT II / [ed] Garcia, CR CaballeroGil, P Burmester, M QuesadaArencibia, A, Amsterdam: Springer Publishing Company, 2016, p. 104-110Conference paper (Refereed)
    Abstract [en]

    It is fully appreciated that progress in the development of data driven approaches to activity recognition are being hampered due to the lack of large scale, high quality, annotated data sets. In an effort to address this the Open Data Initiative (ODI) was conceived as a potential solution for the creation of shared resources for the collection and sharing of open data sets. As part of this process, an analysis was undertaken of datasets collected using a smart environment simulation tool. A noticeable difference was found in the first 1-2 cycles of users generating data. Further analysis demonstrated the effects that this had on the development of activity recognition models with a decrease of performance for both support vector machine and decision tree based classifiers. The outcome of the study has led to the production of a strategy to ensure an initial training phase is considered prior to full scale collection of the data.

  • 41.
    Ohlsson, Oliver
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE).
    En forensisk analys av iOS2013Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [sv]

    Sedan Apple introducerade sin iPhone 2007 har användadet av smarta telefoner ökat ständigt. De används inte bara i hemmet utan även på företag och i militären. På företagsmobiler finns det mer och mer viktig information såsom mail, sms och viktiga filer. För en hacker skulle det därför vara möjligt att komma åt hela företaget genom att gå in på en mobiltelefon som används i verksamheten. För att motverka det har det implementerats säkerhetsfunktioner i dagens mobiltelefoner som tex kryptering.

    I detta arbetet har målet varit att undersöka dessa säkerhetsfunktioner och vad för information som går att utvinna ur en iPhone. Genom att undersöka vilka säkerhetsfunktioner som implementerats och hur mycket information som går att få ut kommer frågeställningarna besvaras.

    Det har skrivits ett antal arbeten om iOS-säkerhet, men de flesta är skrivna om äldre versioner av operativsystemet. I det här arbetet kommer det senaste, iOS 6.1.4, testas i programmet XRY. 

    Download full text (pdf)
    fulltext
  • 42.
    Ortiz-Barrios, Miguel Angel
    et al.
    Department of Industrial Management, Agroindustry and Operations, Universidad de la Costa CUC, Barranquilla, Colombia.
    Lundström, Jens
    Convergia Consulting, Halmstad, Sweden.
    Synnott, Jonathan
    School of Computing, Computer Science Research Institute, Ulster University, Belfast, United Kingdom.
    Järpe, Eric
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Pinheiro Sant'Anna, Anita
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS).
    Complementing real datasets with simulated data: a regression-based approach2020In: Multimedia tools and applications, ISSN 1380-7501, E-ISSN 1573-7721, no 79, p. 34301-34324Article in journal (Refereed)
    Abstract [en]

    Activity recognition in smart environments is essential for ensuring the wellbeing of older residents. By tracking activities of daily living (ADLs), a person’s health status can be monitored over time. Nonetheless, accurate activity classification must overcome the fact that each person performs ADLs in different ways and in homes with different layouts. One possible solution is to obtain large amounts of data to train a supervised classifier. Data collection in real environments, however, is very expensive and cannot contain every possible variation of how different ADLs are performed. A more cost-effective solution is to generate a variety of simulated scenarios and synthesize large amounts of data. Nonetheless, simulated data can be considerably different from real data. Therefore, this paper proposes the use of regression models to better approximate real observations based on simulated data. To achieve this, ADL data from a smart home were first compared with equivalent ADLs performed in a simulator. Such comparison was undertaken considering the number of events per activity, number of events per type of sensor per activity, and activity duration. Then, different regression models were assessed for calculating real data based on simulated data. The results evidenced that simulated data can be transformed with a prediction accuracy of R2 = 97.03%.

    © Springer Science+Business Media, LLC, part of Springer Nature 2020

  • 43.
    Ortíz-Barrios, Miguel Angel
    et al.
    Department of Industrial Management, Agroindustry and Operations, Universidad de la Costa CUC, Barranquilla, Colombia.
    Cleland, Ian
    School of Computing, Computer Science Research Institute, Ulster University, Belfast, United Kingdom.
    Nugent, Chris
    School of Computing, Computer Science Research Institute, Ulster University, Belfast, United Kingdom.
    Pancardo, Pablo
    Academic Division of Information Science and Technology, Juarez Autonomous University of Tabasco, Tabasco, Mexico.
    Järpe, Eric
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Synnott, Jonathan
    School of Computing, Computer Science Research Institute, Ulster University, Belfast, United Kingdom.
    Simulated Data to Estimate Real Sensor Events—A Poisson-Regression-Based Modelling2020In: Remote Sensing, E-ISSN 2072-4292, Vol. 12, no 5, article id 771Article in journal (Refereed)
    Abstract [en]

    Automatic detection and recognition of Activities of Daily Living (ADL) are crucial for providing effective care to frail older adults living alone. A step forward in addressing this challenge is the deployment of smart home sensors capturing the intrinsic nature of ADLs performed by these people. As the real-life scenario is characterized by a comprehensive range of ADLs and smart home layouts, deviations are expected in the number of sensor events per activity (SEPA), a variable often used for training activity recognition models. Such models, however, rely on the availability of suitable and representative data collection and is habitually expensive and resource-intensive. Simulation tools are an alternative for tackling these barriers; nonetheless, an ongoing challenge is their ability to generate synthetic data representing the real SEPA. Hence, this paper proposes the use of Poisson regression modelling for transforming simulated data in a better approximation of real SEPA. First, synthetic and real data were compared to verify the equivalence hypothesis. Then, several Poisson regression models were formulated for estimating real SEPA using simulated data. The outcomes revealed that real SEPA can be better approximated ( R2pred = 92.72 % ) if synthetic data is post-processed through Poisson regression incorporating dummy variables. © 2020 MDPI (Basel, Switzerland)

  • 44.
    Parsapoor, Mahboobeh
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), Centre for Research on Embedded Systems (CERES).
    Brain Emotional Learning-Inspired Models2014Licentiate thesis, comprehensive summary (Other academic)
    Abstract [en]

    In this thesis the mammalian nervous system and mammalian brain have been used as inspiration to develop a computational intelligence model based on the neural structure of fear conditioning and to extend the structure of the previous proposed amygdala-orbitofrontal model. The proposed model can be seen as a framework for developing general computational intelligence based on the emotional system instead of traditional models on the rational system of the human brain. The suggested model can be considered a new data driven model and is referred to as the brain emotional learning-inspired model (BELIM). Structurally, a BELIM consists of four main parts to mimic those parts of the brain’s emotional system that are responsible for activating the fear response. In this thesis the model is initially investigated for prediction and classification. The performance has been evaluated using various benchmark data sets from prediction applications, e.g. sunspot numbers from solar activity prediction, auroral electroject (AE) index from geomagnetic storms prediction and Henon map, Lorenz time series. In most of these cases, the model was tested for both long-term and short-term prediction. The performance of BELIM has also been evaluated for classification, by classifying binary and multiclass benchmark data sets.

    Download full text (pdf)
    fulltext
  • 45.
    Pashami, Sepideh
    et al.
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Holst, Anders
    RISE SICS, Stockholm, Sweden.
    Bae, Juhee
    School of Informatics, University of Skövde, Sweden.
    Nowaczyk, Sławomir
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Causal discovery using clusters from observational data2018Conference paper (Refereed)
    Abstract [en]

    Many methods have been proposed over the years for distinguishing causes from effects using observational data only, and new ones are continuously being developed – deducing causal relationships is difficult enough that we do not hope to ever get the perfect one. Instead, we progress by creating powerful heuristics, capable of capturing more and more of the hints that are present in real data.

    One type of such hints, quite surprisingly rarely explicitly addressed by existing methods, is in-homogeneities in the data. Clusters are a very typical occurrence that should be taken into account, and exploited, in the process of identifying causes and effects. In this paper, we discuss the potential benefits, and explore the hints that clusters in the data can provide for causal discovery. We propose a new method, and show, using both artificial and real data, that accounting for clusters in the data leads to more accurate learning of causal structures.

    Download full text (pdf)
    fulltext
  • 46.
    Persson, Maria
    Chalmers University of Technology.
    Crop and weed discrimination using computer vision2006Licentiate thesis, comprehensive summary (Other academic)
    Abstract [en]

    The thesis is concerned with computer vision in ecological and precision agriculture aiming to identify crops and weeds in images of crop rows. The identification of plants can be done by extracting the plants in the image and classifying them as a crop or weed depending on the shape and color. The extraction of plants can be accomplished in two ways, either by extracting the separate leaves and combining them into plants or by extracting the plants directly. Plant overlapping each other, plants missing parts of leaves or whole leaves, variations in plant appearance, and missing plants in crop rows are the main problems the computer vision-based plant identification needs to tackle.

    The main objective in this thesis is to develop and investigate methods for both ways of extracting the plants and classification of extracted plans into crop or weed classes. A new method for extraction of separate leaves, called cutting, is presented and compared to the watershed and erosion followed by dilation methods, which have been used in other applications of leaf extraction. For the direct extraction of plants, the active shape models (ASM) method is adapted and evaluated. The initial position is one of the main prameters affecting the robustness of the result obtained from the ASM. Therefore the robustness regarding different initial positions is studied experimentally.

    The experimental investigations are performed on images of crop rows taken from different ecologically grown sugar beet fields, including images of both overlapping plants and plants missing part of leaves or whole leaves. The investigation results show that the cutting method produces crop leaf segments that resemble the leaves with about 80% average accuracy and removes 61% of the occluding weed pixels. The active shape model method removes up to 83% of the occluding weed pixels and categorizes up to 83% of the crop pixels correctly. Arround 84% of the plants extracted using the active shape model were correctly classified. This is fairly close to what can be achieved by manual extraction of the plants. The active shape model robustness test regarding the initial position shows that the plant is extracted properly if the model is placed within half a leaf distance from center, mosrotated by at most +/- 18.5 degrees and the scale parameter of the model does not exceed twice the plant size.

  • 47.
    Qu, Zhiguo
    et al.
    Nanjing University Of Information Science And Technology, Nanjing, China.
    Li, Yang
    Nanjing University Of Information Science And Technology, Nanjing, China.
    Liu, Bo
    Hubei University Of Science And Technology, Xianning, China.
    Gupta, Deepak
    Maharaja Agrasen Institute Of Technology, New Delhi, India.
    Tiwari, Prayag
    Halmstad University, School of Information Technology.
    DTQFL: A Digital Twin-Assisted Quantum Federated Learning Algorithm for Intelligent Diagnosis in 5G Mobile Network2023In: IEEE journal of biomedical and health informatics, ISSN 2168-2194, E-ISSN 2168-2208, p. 1-10Article in journal (Refereed)
    Abstract [en]

    Smart healthcare aims to revolutionize med-ical services by integrating artificial intelligence (AI). The limitations of classical machine learning include privacy concerns that prevent direct data sharing among medical institutions, untimely updates, and long training times. To address these issues, this study proposes a digital twin-assisted quantum federated learning algorithm (DTQFL). By leveraging the 5G mobile network, digital twins (DT) of patients can be created instantly using data from various Internet of Medical Things (IoMT) devices and simultane-ously reduce communication time in federated learning (FL) at the same time. DTQFL generates DT for patients with specific diseases, allowing for synchronous training and updating of the variational quantum neural network (VQNN) without disrupting the VQNN in the real world. This study utilized DTQFL to train its own personalized VQNN for each hospital, considering privacy security and training speed. Simultaneously, the personalized VQNN of each hospital was obtained through further local iterations of the final global parameters. The results indicate that DTQFL can train a good VQNN without collecting local data while achieving accuracy comparable to that of data-centralized algorithms. In addition, after personalized train-ing, the VQNN can achieve higher accuracy than that with-out personalized training.

  • 48.
    Ryttergard, Henrik
    et al.
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE).
    Klemens, Livia
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE).
    Undersökning & Utvinning av Smartphones: En djupgående analys av positionsdata2013Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    The ordinary phone of today is not the same as it was 10 years ago. We still use them tomake phone calls and to send text messages, but the ordinary phone of today has muchmore uses, it is essentially a computer. To put into context to 10 years ago, it is a verypowerful computer, capable of processing wide array of information and presenting it tothe user. Nearly every single device today has a wireless connection, which makes everyuser connectable and able to use online services and internet at any time and place.This gives the user the possibility to integrate his or hers everyday actions with socialmedia and different search functions. Being able to search the internet for persons,restaurants, public transportation and a lot more is very useful to most. Searching andinteracting in the near vicinity where you currently are is even more useful, this presents uswith location data.The usage of location data grants computer forensics a unique possibility to position adevice at a specific date and time. This can be helpful in court to sentence a perpetrator orto free an innocent.In this paper, we will try to explain the different methods used for mobile devicepositioning and present information how some popular applications make use of andmanage geographic positioning.

    Download full text (pdf)
    fulltext
  • 49.
    Said, Alan
    et al.
    University of Skövde, Skövde, Sweden.
    Parra, Denis
    Pontificia Universidad Católica de Chile, Santiago, Chile.
    Bae, Juhee
    University of Skövde, Skövde, Sweden.
    Pashami, Sepideh
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    IDM-WSDM 2019: Workshop on Interactive Data Mining2019In: WSDM '19: Proceedings of the Twelfth ACM International Conference on Web Search and Data, New York, NY: Association for Computing Machinery (ACM), 2019, p. 846-847Conference paper (Refereed)
    Abstract [en]

    The first Workshop on Interactive Data Mining is held in Melbourne, Australia, on February 15, 2019 and is co-located with 12th ACM International Conference on Web Search and Data Mining (WSDM 2019). The goal of this workshop is to share and discuss research and projects that focus on interaction with and interactivity of data mining systems. The program includes invited speaker, presentation of research papers, and a discussion session.

  • 50.
    Sheikholharam Mashhadi, Peyman
    et al.
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Nowaczyk, Sławomir
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Pashami, Sepideh
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.
    Stacked Ensemble of Recurrent Neural Networks for Predicting Turbocharger Remaining Useful Life2020In: Applied Sciences, E-ISSN 2076-3417, Vol. 10, no 1, article id 69Article in journal (Refereed)
    Abstract [en]

    Predictive Maintenance (PM) is a proactive maintenance strategy that tries to minimize a system’s downtime by predicting failures before they happen. It uses data from sensors to measure the component’s state of health and make forecasts about its future degradation. However, existing PM methods typically focus on individual measurements. While it is natural to assume that a history of measurements carries more information than a single one. This paper aims at incorporating such information into PM models. In practice, especially in the automotive domain, diagnostic models have low performance, due to a large amount of noise in the data and limited sensing capability. To address this issue, this paper proposes to use a specific type of ensemble learning known as Stacked Ensemble. The idea is to aggregate predictions of multiple models—consisting of Long Short-Term Memory (LSTM) and Convolutional-LSTM—via a meta model, in order to boost performance. Stacked Ensemble model performs well when its base models are as diverse as possible. To this end, each such model is trained using a specific combination of the following three aspects: feature subsets, past dependency horizon, and model architectures. Experimental results demonstrate benefits of the proposed approach on a case study of heavy-duty truck turbochargers. © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). 

    Download full text (pdf)
    fulltext
12 1 - 50 of 65
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