Högskolan Dalarnas logga och länk till högskolans webbplats

du.sePublikationer
Ändra sökning
Avgränsa sökresultatet
1234 1 - 50 av 152
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Träffar per sida
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sortering
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
Markera
Maxantalet träffar du kan exportera från sökgränssnittet är 250. Vid större uttag använd dig av utsökningar.
  • 1.
    Al-Hammadi, Mustafa
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Fleyeh, Hasan
    Högskolan Dalarna, Institutionen för information och teknik, Datateknik.
    Åberg, Anna Cristina
    Högskolan Dalarna, Institutionen för hälsa och välfärd, Medicinsk vetenskap.
    Halvorsen, Kjartan
    Högskolan Dalarna, Institutionen för hälsa och välfärd, Medicinsk vetenskap.
    Thomas, Ilias
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Machine Learning Approaches for Dementia Detection Through Speech and Gait Analysis: A Systematic Literature Review2024Ingår i: Journal of Alzheimer's Disease, ISSN 1387-2877, E-ISSN 1875-8908Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    BACKGROUND: Dementia is a general term for several progressive neurodegenerative disorders including Alzheimer's disease. Timely and accurate detection is crucial for early intervention. Advancements in artificial intelligence present significant potential for using machine learning to aid in early detection.

    OBJECTIVE: Summarize the state-of-the-art machine learning-based approaches for dementia prediction, focusing on non-invasive methods, as the burden on the patients is lower. Specifically, the analysis of gait and speech performance can offer insights into cognitive health through clinically cost-effective screening methods.

    METHODS: A systematic literature review was conducted following the PRISMA protocol (Preferred Reporting Items for Systematic Reviews and Meta-Analyses). The search was performed on three electronic databases (Scopus, Web of Science, and PubMed) to identify the relevant studies published between 2017 to 2022. A total of 40 papers were selected for review.

    RESULTS: The most common machine learning methods employed were support vector machine followed by deep learning. Studies suggested the use of multimodal approaches as they can provide comprehensive and better prediction performance. Deep learning application in gait studies is still in the early stages as few studies have applied it. Moreover, including features of whole body movement contribute to better classification accuracy. Regarding speech studies, the combination of different parameters (acoustic, linguistic, cognitive testing) produced better results.

    CONCLUSIONS: The review highlights the potential of machine learning, particularly non-invasive approaches, in the early prediction of dementia. The comparable prediction accuracies of manual and automatic speech analysis indicate an imminent fully automated approach for dementia detection.

  • 2.
    Almlof, Erik
    et al.
    KTH Royal Inst Technol.
    Zhao, Xiaoyun
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys. KTH Royal Inst Technol.
    Pernestal, Anna
    KTH Royal Inst Technol.
    Jenelius, Erik
    KTH Royal Inst Technol, Div Transport Planning, Stockholm, Sweden..
    Nybacka, Mikael
    KTH Royal Inst Technol.
    Frameworks for assessing societal impacts of automated driving technology2022Ingår i: Transportation planning and technology (Print), ISSN 0308-1060, E-ISSN 1029-0354, Vol. 45, nr 7, s. 545-572Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Numerous studies have studied the impacts of automated driving (AD) technology on e.g. accident rates or CO2 emissions using various frameworks. In this paper we present an overview of previous frameworks used for societal impacts and review their advantages and limitations. Additionally, we introduce the Total Impact Assessment (TIA) framework developed by the Swedish Transport Administration and use this framework to evaluate three scenarios for AD bus services in Stockholm. We conclude that the reviewed frameworks cover different aspects of AD technology, and that e.g. cybersecurity and biodiversity are areas largely neglected. Furthermore, most frameworks assume effects to be homogenous, when there may be large variation in e.g. perceived security. The TIA framework does not manage to include all societal aspects of AD technology, but has great benefits and manages to provide important insights of the societal impacts of AD technology, especially how effects may wary for different actors.

    Ladda ner fulltext (pdf)
    fulltext
  • 3. Ardestani, Seyed Faraz Mahdavi
    et al.
    Adibi, Sasan
    Golshan, Arman
    Högskolan Dalarna.
    Sadeghian, Paria
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Factors Influencing the Effectiveness of E-Learning in Healthcare: A Fuzzy ANP Study2023Ingår i: Healthcare, E-ISSN 2227-9032, Vol. 11, nr 14, artikel-id 2035Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    E-learning has transformed the healthcare education system by providing healthcare professionals with training and development opportunities, regardless of their location. However, healthcare professionals in remote or rural areas face challenges such as limited access to educational resources, lack of reliable internet connectivity, geographical isolation, and limited availability of specialized training programs and instructors. These challenges hinder their access to e-learning opportunities and impede their professional development. To address this issue, a study was conducted to identify the factors that influence the effectiveness of e-learning in healthcare. A literature review was conducted, and two questionnaires were distributed to e-learning experts to assess primary variables and identify the most significant factor. The Fuzzy Analytic Network Process (Fuzzy ANP) was used to identify the importance of selected factors. The study found that success, satisfaction, availability, effectiveness, readability, and engagement are the main components ranked in order of importance. Success was identified as the most significant factor. The study results highlight the benefits of e-learning in healthcare, including increased accessibility, interactivity, flexibility, knowledge management, and cost efficiency. E-learning offers a solution to the challenges of professional development faced by healthcare professionals in remote or rural areas. The study provides insights into the factors that influence the effectiveness of e-learning in healthcare and can guide the development of future e-learning programs.

    Ladda ner fulltext (pdf)
    fulltext
  • 4.
    Ayubu, Victoria Said
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Khan, Mohammed Shahid
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Exploring Swedish Attitudes and Needs Regarding Sustainable Food through Sentiment Analysis in Social Media2024Självständigt arbete på avancerad nivå (magisterexamen), 10 poäng / 15 hpStudentuppsats (Examensarbete)
    Abstract [en]

    Social media has recently become an essential component of our daily modern life, with platforms like Facebook, YouTube, and Twitter serving as popular venues for people to share their opinions on various topics, including sustainable food. The interest in consumer sentiments towards sustainable practices has increased particularly after Covid-2019. This study investigates the attitudes and needs of Swedish consumers regarding sustainable food consumption as reflected in their social media interactions using 4588 comments from Facebook and YouTube. The methodology used are sentiment analysis and topic modelling with VADER and Latent Dirichlet Allocation (LDA) respectively. The results reveal a generally strong positive attitude toward sustainable food. However, the study observes further a decline in positive sentiments over time, indicating changing consumer opinions. The primary topic identified is market challenges, such as high pricing. Furthermore, health concerns and environmental considerations are identified both as important factors influencing the choice of sustainable food. The findings highlight the necessity for policy interventions to enhance the affordability and accessibility of sustainable food, as well as the effective use of social media for raising consumer awareness.

    Ladda ner fulltext (pdf)
    fulltext
  • 5. Bai, W.
    et al.
    Johanson, Martin
    Högskolan Dalarna, Institutionen för kultur och samhälle, Företagsekonomi. Uppsala University.
    Oliveira, Luis
    Högskolan Dalarna, Institutionen för kultur och samhälle, Företagsekonomi. Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys. Center for International Business Studies, Fundação Getúlio Vargas, Brazil.
    Ratajczak-Mrozek, M.
    Francioni, B.
    Where business networks and institutions meet: Internationalization decision-making under uncertainty2022Ingår i: Journal of International Management, ISSN 1075-4253, E-ISSN 1873-0620, Vol. 28, nr 1, artikel-id 100904Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Both business networks and institutional forces are relevant to firm internationalization but they have seldom been studied together. We investigate under what circumstances firms are more likely to adopt non-predictive strategy in light of the influence of the business networks, the institutional forces, and the home market background affecting their internationalization. Based on survey data from 758 small and medium-sized enterprises (SMEs) from Brazil, China, Poland, Italy, and Sweden, our results support the effects of formal institutional distance and cultural differences on the use of non-predictive strategies by SMEs in internationalization decisions, as well as the contingency effects of business network stability and of having an emerging market background. We integrate research on the liability of foreignness and the liability of outsidership and find that business network stability is critical. It does not moderate the relation between cultural difference and NPS adoption but attenuates the negative relation between institutional distance and NPS adoption, indicating that the liabilities of foreignness and outsidership play different roles in internationalization. © 2021 The Author(s)

    Ladda ner fulltext (pdf)
    fulltext
  • 6.
    Bai, Wensong
    et al.
    Högskolan Dalarna, Institutionen för kultur och samhälle, Företagsekonomi. Zhejiang University of Technology, Hangzhou, China; Uppsala University.
    Hilmersson, M.
    Johanson, Martin
    Högskolan Dalarna, Institutionen för kultur och samhälle, Företagsekonomi. Uppsala University.
    Oliveira, Luis
    Högskolan Dalarna, Institutionen för kultur och samhälle, Företagsekonomi. Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    SMEs' regional diversification: dynamic patterns and home market institutional determinants2023Ingår i: International Marketing Review, ISSN 0265-1335, E-ISSN 1758-6763Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Purpose: The authors seek to advance the understanding of small- and medium-sized enterprise (SME) internationalization at the regional level and examine the role of home market institutions in this process. Design/methodology/approach: The authors analyze hypotheses with data from SMEs in five country markets and from the Global Entrepreneurship Monitor. A cluster analysis establishes the regional diversification patterns (based on regional diversification scope, speed and rhythm) and a multinomial regression tests the effect of home market institutions on their adoption. Findings: The results offer a refined picture of SME regional diversification by revealing three patterns: intra-regionally focused firms, late inter-region diversifiers and early inter-region diversifiers. They also suggest that the adoption of these patterns is determined by SMEs' home market institutions. Originality/value: The authors develop a nuanced understanding of SME internationalization by building upon and expanding the regionalization rationale in the internationalization patterns literature. Additionally, the authors address the acknowledged, yet rarely investigated, country-level determinants of internationalization patterns. © 2023, Emerald Publishing Limited.

  • 7.
    Bai, Wensong
    et al.
    Högskolan Dalarna, Institutionen för kultur och samhälle, Företagsekonomi. Zhejiang University of Technology, China; Uppsala University.
    Johanson, Martin
    Högskolan Dalarna, Institutionen för kultur och samhälle, Företagsekonomi. Uppsala University; University of Huddersfield, UK.
    Oliveira, Luis
    Högskolan Dalarna, Institutionen för kultur och samhälle, Företagsekonomi. Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys. Center for International Business Studies, Fundação Getúlio Vargas, Brazil.
    Ratajczak-Mrozek, Milena
    Poznan University.
    The Role of Business and Social Networks in the Effectual Internationalization: Insights from Emerging Market SMEs2021Ingår i: Journal of Business Research, ISSN 0148-2963, E-ISSN 1873-7978, Vol. 129, s. 96-109Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    This study investigates the performance implications of the distinct mechanisms represented by business and social networks in the effectual internationalization. Our hypotheses consider the influence of both network types on firms’ decision-making during internationalization, including the use of effectuation’s overarching principle of non-predictive strategy and the analysis of affordable losses as preferred criterion for selecting between action paths. We test our structural model on a sample of 469 SMEs from Brazil, China, and Poland. The analysis demonstrates that the knowledge circulating in the firms’ business networks negatively moderates the relationship between non-predictive strategy and affordable losses, while social networking mediates the relationships between both non-predictive strategy and affordable losses, on the one hand, and international performance, on the other.

  • 8.
    Bhat, Adhyapadi Apoorva
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Koothenparambil Joy, Jomin
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Fault Detection in PV System using Machine Learning Technique2023Självständigt arbete på avancerad nivå (masterexamen), 10 poäng / 15 hpStudentuppsats (Examensarbete)
    Abstract [en]

    With the steady and rapid reliance on solar power as a viable alternative to traditional fuel-based energy, maintenance of solar panels is becoming an unavoidable issue for both producers and consumers. Machine learning techniques are useful in detecting solar panel faults and their life span. In recent years, Machine learning technology has emerged that helps to extract meaningful information and detect the fault in PV Systems. This paper reviews and involves identifying faulty features and predicting the fault in residential PV Systems that causes power degradation. We have built a linear regression model and performed hierarchical clustering to identify the faulty group of data, and from that faulty group, we identified that the features such as Radiation, Module Temperature, and IS values play an important role in the degradation of the power generation in the solar panels. Additionally, in this study fault prediction in a PV system has also been attempted. We evaluated the performance using 6 different models SVM, KNN, Naive Bayes Random Forest, Decision Tree and Logistic Regression. Finally, we concluded that the Random Forest, KNN and Decision Tree performed better in predicting with an accuracy of 99 %.

    Ladda ner fulltext (pdf)
    fulltext
  • 9. Bodell, Victor
    et al.
    Ekstrom, Lukas
    Aghanavesi, Somayeh
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys. KTH, Royal Institute of Technology, Stockholm.
    Comparing Machine Learning Estimation of Fuel Consumption of Heavy-Duty Vehicles2021Ingår i: World Academy of Science, Engineering and Technology: An International Journal of Science, Engineering and Technology, ISSN 2010-376X, Vol. 15, nr 2, s. 97-101, artikel-id 10011850Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Fuel consumption (FC) is one of the key factors indetermining expenses of operating a heavy-duty vehicle. A customermay therefore request an estimate of the FC of a desired vehicle.The modular design of heavy-duty vehicles allows their constructionby specifying the building blocks, such as gear box, engine andchassis type. If the combination of building blocks is unprecedented,it is unfeasible to measure the FC, since this would first r equire theconstruction of the vehicle. This paper proposes a machine learningapproach to predict FC. This study uses around 40,000 vehiclesspecific a nd o perational e nvironmental c onditions i nformation, suchas road slopes and driver profiles. A ll v ehicles h ave d iesel enginesand a mileage of more than 20,000 km. The data is used to investigatethe accuracy of machine learning algorithms Linear regression (LR),K-nearest neighbor (KNN) and Artificial n eural n etworks ( ANN) inpredicting fuel consumption for heavy-duty vehicles. Performance ofthe algorithms is evaluated by reporting the prediction error on bothsimulated data and operational measurements. The performance of thealgorithms is compared using nested cross-validation and statisticalhypothesis testing. The statistical evaluation procedure finds thatANNs have the lowest prediction error compared to LR and KNNin estimating fuel consumption on both simulated and operationaldata. The models have a mean relative prediction error of 0.3% onsimulated data, and 4.2% on operational data.

    Ladda ner fulltext (pdf)
    fulltext
  • 10. Bohm, Clifford
    et al.
    Hintze, Arend
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys. Michigan State University, USA.
    Schossau, Jory
    A Simple Sparsity Function to Promote Evolutionary Search2023Ingår i: ALIFE 2023: Ghost in the Machine: Proceedings of the 2023 Artificial Life Conference, 2023, s. 368-376Konferensbidrag (Refereegranskat)
  • 11.
    Bohm, Clifford
    et al.
    Michigan State University, Department of Integrative Biology and BEACON Center for the Study of Evolution in Action, East Lansing, U.S.A..
    Kirkpatrick, Douglas
    Michigan State University, BEACON Center for the Study of Evolution in Action and Department of Computer Science and Engineering, East Lansing, U.S.A.
    Hintze, Arend
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys. Michigan State University, BEACON Center for the Study of Evolution in Action, East Lansing, U.S.A..
    Understanding Memories of the Past in the Context of Different Complex Neural Network Architectures.2022Ingår i: Neural Computation, ISSN 0899-7667, E-ISSN 1530-888X, Vol. 34, nr 3, s. 754-780Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Deep learning (primarily using backpropagation) and neuroevolution are the preeminent methods of optimizing artificial neural networks. However, they often create black boxes that are as hard to understand as the natural brains they seek to mimic. Previous work has identified an information-theoretic tool, referred to as R, which allows us to quantify and identify mental representations in artificial cognitive systems. The use of such measures has allowed us to make previous black boxes more transparent. Here we extend R to not only identify where complex computational systems store memory about their environment but also to differentiate between different time points in the past. We show how this extended measure can identify the location of memory related to past experiences in neural networks optimized by deep learning as well as a genetic algorithm.

  • 12. Cajas, V.
    et al.
    Urbieta, M.
    Rossi, G.
    Rybarczyk, Yves
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Migrating legacy Web applications2021Ingår i: Cluster Computing, ISSN 1386-7857, E-ISSN 1573-7543, Vol. 24, nr 2, s. 1033-1049Artikel i tidskrift (Refereegranskat)
  • 13.
    Carling, Kenneth
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    The emergence of Microdata Analysis and its intellectual history over the past two decades2021Rapport (Övrigt vetenskapligt)
    Abstract [en]

    By 2020, students of Dalarna University had produced some 100 Bachelor and Master’s theses and 25 Licentiate or Doctoral theses in the academic discipline of Microdata Analysis guided by the university’s faculty. While firmly rooted in the tradition and the format of the formal sciences Computer Science and Mathematics, the theses are disparate with regard to area of investigation, research method, and epistemology. The research carried out in these theses is recognized internationally by learned societies and their journals and conferences, yet Dalarna University remains globally unique in labelling an academic discipline Microdata Analysis. This paper attempts to narrate the history of the forming process of Microdata Analysis at the university and grasp its nature.

    Ladda ner fulltext (pdf)
    fulltext
  • 14.
    Carling, Kenneth
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Håkansson, Johan
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Privacy and data: Some research venues2021Ingår i: A Research Agenda for Knowledge Management and Analytics, Edward Elgar Publishing, 2021, s. 191-203Kapitel i bok, del av antologi (Refereegranskat)
    Abstract [en]

    The issue of data privacy is often reduced to secure data transactions by cryptographic techniques. However, in a liberal democracy the issue of privacy connects to fundamental questions about the co-existence and collaboration between its citizens. One is the conflict between self-interest and the interest of the commons, whereby research on privacy topics is found in distant and disparate research streams. Sharing of data perceived as private may drastically increase collective welfare, while reducing it for single citizens. In this chapter, we present a metaphor to highlight the fundamentals of privacy and explain how the access to new data-processing technologies provokes new questions to be addressed. Furthermore, we illustrate how various research streams differ in presumptions and privacy topics of interest, and we stress the potential knowledge-producing value of bridging these streams. We end by pointing out some particularly interesting research venues for privacy and data. © Jay Liebowitz 2021.

  • 15.
    Carling, Kenneth
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Lindgren, Charlie
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Rudholm, Niklas
    Institute of Retail Economics, Stockholm.
    Market integration in Nordic online retail markets: Do cross-border transaction costs still matter?2023Rapport (Övrigt vetenskapligt)
    Abstract [en]

    If online retail markets are integrated, in that cost shocks in one country also affect pricing in other countries, asymmetric shocks to any one country in the region will spill over to neighboring countries as well. Using web-scraped productlevel prices from a group of retail firms selling identical products in at least two of the four Nordic markets under study, we investigate if national markets are segmented at the borders. Contrary to previous studies, we use differences in product characteristics to divide the data into products that are easily transported across borders and those that are not. At the extreme end of the transportability spectrum, we investigate market integration for four types of games for computers or game consoles that are delivered via downloads, where the cross-border transaction costs should be close to zero. Our results show that markets for product categories where cross-border transaction costs are high are also segmented at the border, while markets for product categories that can easily be traded andtransported between countries are not. We find an even higher level of market integration for games delivered via downloads than for the same games sold through traditional channels. As such, cross-border transaction costs still matter for market segmentation, but only for the sub-set of products where such costs are high. 

    Ladda ner fulltext (pdf)
    fulltext
  • 16.
    Carling, Kenneth
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Paidi, Vijay
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Rudholm, Niklas
    Institute of Retail Economics.
    Minimizing travel distance and CO2 emissions when reconfiguring retail store networks2024Rapport (Övrigt vetenskapligt)
    Abstract [en]

    Retail chains continually expand, reconfigure, and contract their store networks to serve their customers and maximize profits. One notable consequence of these actions is changes in the distances between consumers’ residences andnearest stores, altering their transportation-related CO2 emissions. Therefore, this study aims to examine the environmental impact of the reconfiguration of the IKEA store network in Sweden during the twenty-first century and compare the actual reconfiguration to one that minimizes consumers’ travel distances and, thus, CO2emissions. The expansion of the IKEA network in Sweden between 2004 and 2016, adding four (2004–2007) and then three (2013–2016) additional stores, reduced consumers’ average travel distance to their nearest store from 87 to 65.2 km. However, had IKEA managers used our web-available decision support tool,eCOmpass, this reduction could have been achieved after the first round of store additions since the distance-minimizing locations for the four new stores established in 2004–2007 would have reduced average travel distance to 64.9 km. 

  • 17.
    Carling, Kenneth
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Paidi, Vijay
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Rudholm, Niklas
    Institute of Retail Economics, Stockholm.
    On deploying eCOmpass: a decision support tool for environmentally friendly retail locations2024Rapport (Övrigt vetenskapligt)
    Abstract [en]

    Much focus in the joint retailing and transportation domain has been on the transition to e-tailing and the reformation of supply-chain logistics. However, traditional retailing, where consumers visit stores for shopping, dominates and will continue to do so for the foreseeable future. Retailers continuously expand, contract, and reconfigure their store network for strategic reasons. This paper reports on a project aiming to facilitate the incorporation of environmental consequences into the retailer’s reconfiguration decision process. It describes the design and deployment process of eCOmpass, an online decision support tool that enables retailers to estimate the change in transportation-related CO2 emissions caused by a reconfiguration of their store network. This description encompasses the judgmental choices of data acquisition, optimization technology, and user interface. 

    Ladda ner fulltext (pdf)
    fulltext
  • 18.
    Dar, Ravi
    et al.
    Högskolan Dalarna, Institutionen för kultur och samhälle, Företagsekonomi.
    Huq, Asif M
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Sundberg, Klas
    Högskolan Dalarna, Institutionen för kultur och samhälle, Företagsekonomi.
    Pricing for 55: Implementing corporate climate strategy in choice architecture through internal pricing2021Konferensbidrag (Övrigt vetenskapligt)
    Abstract [en]

    The job of management accounting and management control is not only to gather data/information about the company’s or organization’s past, but also to use and develop tools to form the future. While some tools are simple cost calculations to find breakeven points in price-setting, other tools can include far-reaching strategic purposes. Strategy decisions within business that focus on sustainability and mitigate climate change generally tend to focus on specific components or activities (even in the supply change) to make replacements or even cancel altogether. Onus is on the big decisions with major impact. There is another perception of strategy: practices through which strategy is enacted. Less as a grand plan by the top management, and more as a gradual managing that takes key decisions close to the everyday of business life.  With the global emergency of mitigating climate change, an area of near-untapped potential is management accounting. Research has pointed to the importance of middle level management and the role of the controller, where change happens, and problems need solutions. Recently there has been an increased interest in the way internal pricing (which includes transfer pricing) within a corporation can support a corporate strategy on climate change mitigation. Traditionally seen mainly as a manipulative method to avoid tax in multinational companies, there is new interest on the possibility of creating price mechanisms within companies that mimic the supply-demand curves of market economies, for example ways that cap-and-trade mechanisms on GHG emissions can be utilized inside corporations. The concept that underlies market price-setting is scarcity, but rather than using market price as a reflection of scarcity, the interest is in using corporate control and accounting devices to create situations of scarcity. This would create an accounted price on specific goods and services that reflects strategic concerns and a way of implementing corporate policies on climate change into the ‘nitty-gritty’ of everyday business decisions has choices between different burdens on the climate. It is our suggestion that similar mechanisms could broadly support and serve companies’ transition into a circular economy through the design of business choices. The concept of “choice architecture” from  behavorial economics with influence from marketing, most notably with the term ‘nudging’ in order to promote individual choices through design and gradually form norms in a way that would be beneficial to the environment. We want to make the point that the perception of strategizing ties in well with the ideas both of choice architectures and of implementing a circular economy policy in a business. If the concept (or ideal) of the circular economy is a promotion of resource re-use that can reach levels of complete or near-complete containment, then the switch from a linear perspective (of reducing waste, emissions and of not depleting finite resources) to a circular perspective means that ‘only’ megaprojects for re-use and production with lower energy consumption are not sufficient. The realization of the need for re-using spent materials and an avoidance of virgin resources has to permeate the organization. A first step is to review existing survey research of internal pricing that deviate from a cost accounting mandate and instead implement strategic ambitions and outcomes, and among such efforts, focus on those that can support business development towards GHG emission mitigation and circular thinking. 

  • 19. Davari, Mahtab
    et al.
    Edward Okon, Charles
    Aghanavesi, Somayeh
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Predictive Analytics of Student Performance Determinants in Education2022Ingår i: International Journal of Educational and Pedagogical Sciences, E-ISSN 1307-6892, Vol. 16, s. 716-721, artikel-id 10012800Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Every institute of learning is usually interested in the performance of enrolled students. The level of these performances determines the approach an institute of study may adopt in rendering academic services. The focus of this paper is to evaluate students' academic performance in given courses of study using machine learning methods. This study evaluated various supervised machine learning classification algorithms such as Logistic Regression (LR), Support Vector Machine (SVM), Random Forest, Decision Tree, KNearestNeighbors, Linear Discriminant Analysis (LDA), and quadratic Discriminant Analysis, using selected features to predict study performance. The accuracy, precision, recall, and F1 score obtained from a 5-Fold Cross-Validation were used to determine the best classification algorithm to predict students’ performances. SVM(using a linear kernel), LDA, and LR were identified as the best-performing machine-learning methods. Also, using the LR model, this study identified students' educational habits such as reading and paying attention in class as strong determinants for a student to have an above-average performance. Other important features include the academic history of the student and work. Demographic factors such as age, gender, high school graduation, etc., had no significant effect on a student's performance.

  • 20. Dong, Bing
    et al.
    Liu, Yapan
    Fontenot, Hannah
    Ouf, Mohamed
    Osman, Mohamed
    Chong, Adrian
    Qin, Shuxu
    Han, Mengjie
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Zhang, Xingxing
    Högskolan Dalarna, Institutionen för information och teknik, Energiteknik.
    Carlucci, Salvatore
    Occupant behavior modeling methods for resilient building design,operation and policy at urban scale: a review2021Ingår i: Applied Energy, ISSN 0306-2619, E-ISSN 1872-9118, Vol. 293, artikel-id 116856Artikel i tidskrift (Refereegranskat)
  • 21.
    Ereminaite, Marija
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Jayasinghe, Yasas
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Causal relationship between Air Quality (AQ) and the Urban Heat Island (UHI)2024Självständigt arbete på avancerad nivå (magisterexamen), 10 poäng / 15 hpStudentuppsats (Examensarbete)
    Abstract [en]

    This study critically examines the (UHI) effect in urban and suburban neighbourhoods of Quito, Ecuador, over a 19-year period, focusing on the interplay between atmospheric pollution and urban/ suburban temperature. Utilizing Empirical Dynamic Modeling(EDM) and Convergent Cross-Mapping (CCM), this study dives into the nonlinear dynamics of environmental factors, a method that traditional linear models fail to address effectively.The results unveil a consistent and strong positive correlation across various neighbourhoods, with temperature fluctuations indicating a typical UHI effect. This is most noticeable in urbanized areas where the temperature is significantly higher due to dense infrastructure and reduced greenery, a pattern that diminishes as one moves towards the outskirts. Specifically, pollutants like PM2.5 exhibit a non-uniform positive correlation, suggesting their collective increase or decrease across different regions, whereas CO shows a very slight and inconsistent inverse relationship across locations. The causal analysis further substantiates a significant interaction between PM2.5 concentrations and temperature, with the data revealing a reciprocal predictive capacity between these variables. The CCM analysis, through its graphical representation of predictive skills, confirms the causal effect of PM2.5 on urban temperature, marking an essential contribution to understanding the UHI effect and its implications for urban environmental dynamics. This study provides a comprehensive overview of the UHI phenomenon, highlighting the intricate relationship between urbanization, atmospheric pollution, and climate. The findings emphasize the necessity for urban planning and policy to consider these complex interactions to mitigate the effects of climate change on urban environments.

    Ladda ner fulltext (pdf)
    fulltext
  • 22. Fjellström, D.
    et al.
    Bai, W.
    Oliveira, Luis
    Högskolan Dalarna, Institutionen för kultur och samhälle, Företagsekonomi. Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Fang, T.
    Springboard internationalisation in times of geopolitical tensions2023Ingår i: International Business Review, ISSN 0969-5931, E-ISSN 1873-6149, Vol. 32, nr 6, artikel-id 102144Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Geopolitical tensions and a world where state interventions are driven by national security and ideology present novel challenges for emerging market multinational enterprises (EMNEs). Often, individual companies are targeted, and their corporate growth gets curbed. These phenomena are derived from non-market factors, which are generally absent in the springboard view of the international business discourse that explains the foreign expansion of EMNEs by viewing these firms as ambidextrous organisations capable of handling conflicting requirements. This research aims to understand the international expansion of EMNEs under geopolitical tensions by incorporating non-market factors into the ambidexterity model to enrich the springboard view. A case study of Huawei and its exclusion from the telecommunications industry in Sweden forms the empirical base of this research. The contributions are twofold. First, within the springboard view, the ambidexterity model can be upgraded by incorporating non-market factors that better explain the international expansion of EMNEs in changing geopolitical and business contexts. Second, the research highlights the management of EMNEs' subsidiaries while considering geopolitical tensions. © 2023 Elsevier Ltd

  • 23.
    Grek, Åsa
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Government Support for SMEs in Time of Crisis – A Study On Firm-Level Data2023Konferensbidrag (Refereegranskat)
  • 24.
    Grek, Åsa
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Short-Time Work: A Potential Lifeline for Firms in Turbulent Times2023Konferensbidrag (Refereegranskat)
  • 25.
    Grek, Åsa
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    The Effect of Short-Time Work on SME Firm Survival during the COVID-19 PandemicManuskript (preprint) (Övrigt vetenskapligt)
  • 26.
    Grek, Åsa
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Hartwig, Fredrik
    Department of Business and Economics Studies, University of Gävle, 801 76 Gävle, Sweden.
    Dougherty, Mark
    School of Information Technology, Halmstad University, 301 18 Halmstad, Sweden.
    An Inductive Approach to Quantitative Methodology—Application of Novel Penalising Models in a Case Study of Target Debt Level in Swedish Listed Companies2024Ingår i: Journal of Risk and Financial Management, E-ISSN 1911-8074, Vol. 17, nr 5, artikel-id 207Artikel i tidskrift (Refereegranskat)
    Abstract [en]

     This paper proposes a method for conducting quantitative inductive research on survey data when the variable of interest follows an ordinal distribution. A methodology based on novel and traditional penalising models is described. The main aim of the study is to pedagogically present the method utilising the new penalising methods in a new application. A case was employed to outline the methodology. The purpose of the case is to select explanatory variables correlated with the target debt level in Swedish-listed companies. 

    The survey respondents were matched with accounting information from the companies’ annual reports. However, missing data were present: to fully utilise penalising models, we employed classification and regression trees (CART)-based imputations by multiple imputations chained equations (MICE) to address this problem.

    The imputed data were subjected to six penalising models: grouped multinomial lasso, ungrouped multinomial lasso, parallel Element Linked Multinomial-Ordinal (ELMO), semi-parallel ELMO, nonparallel ELMO, and cumulative generalised monotone incremental forward stagewise (GMIFS). While the older models yielded several explanatory variables for the hypothesis formation process, the new models (ELMO and GMIFS) identified only one; the quick asset ratio. Subsequent testing revealed that this variable was the only statistically significant variable to affect the target debt level.

    Ladda ner fulltext (pdf)
    fulltext
  • 27.
    Grek, Åsa
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Hartwig, Fredrik
    University of Gävle.
    Dougherty, Mark
    Halmstad University.
    Determinants of Debt Leverage Ratios in Swedish Listed Companies2022Konferensbidrag (Refereegranskat)
  • 28.
    Grek, Åsa
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Hartwig, Fredrik
    Dougherty, Mark
    Enhancing Firm Modelling Precision: Insights from a Variable Selection MethodManuskript (preprint) (Övrigt vetenskapligt)
  • 29.
    Grek, Åsa
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Mortazavi, Reza
    Högskolan Dalarna, Institutionen för kultur och samhälle, Nationalekonomi.
    Nordström, Carin
    Högskolan Dalarna, Institutionen för information och teknik, Entreprenörskap och innovationsteknik.
    Short-Time Work as a Response to the COVID-19 Crisis: A Study on SME Firm-Level Data in SwedenManuskript (preprint) (Övrigt vetenskapligt)
  • 30.
    Grek, Åsa
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Mortazavi, Reza
    Högskolan Dalarna, Institutionen för kultur och samhälle, Nationalekonomi.
    Nordström, Carin
    Högskolan Dalarna, Institutionen för information och teknik, Entreprenörskap och innovationsteknik.
    Was short-time work effective for SMEs in response to the COVID-19 pandemic2023Konferensbidrag (Refereegranskat)
  • 31.
    Grek, Åsa
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Nordström, Carin
    Högskolan Dalarna, Institutionen för information och teknik, Entreprenörskap och innovationsteknik.
    Cialani, Catia
    Högskolan Dalarna, Institutionen för kultur och samhälle, Nationalekonomi.
    Unravelling the Dynamics: Which Macro-factors are Shaping the SME Sector Landscape Within the European Union?Manuskript (preprint) (Övrigt vetenskapligt)
  • 32.
    Grek, Åsa
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Nordström, Carin
    Högskolan Dalarna, Institutionen för information och teknik, Entreprenörskap och innovationsteknik.
    Cialani, Catia
    Högskolan Dalarna, Institutionen för kultur och samhälle, Nationalekonomi.
    What macroeconomic factors determines growth in micro, small and medium-sized firms in Europe?2022Konferensbidrag (Refereegranskat)
  • 33.
    Grek, Åsa
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Nordström, Carin
    Högskolan Dalarna, Institutionen för information och teknik, Entreprenörskap och innovationsteknik.
    Cialani, Catia
    Högskolan Dalarna, Institutionen för kultur och samhälle, Nationalekonomi.
    What Macroeconomic Factors Determines Growth in Micro, Small and Medium-Sized Firms in Europe: An Aggregated Panel Analysis2022Konferensbidrag (Refereegranskat)
  • 34. Halabi, Ramzi
    et al.
    Hintze, Arend
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Ortiz, Abigail
    Multi-resolution Time-frequency Spectral Derivative Spike Detection for Episode Onset Detection using Passively Collected Sensor Data2023Manuskript (preprint) (Övrigt vetenskapligt)
  • 35.
    Halabi, Ramzi
    et al.
    Campbell Family Research Institute, Centre for Addiction and Mental Health (CAMH), Toronto, Ontario, Canada, CA.
    Mulsant, Benoit H
    Campbell Family Research Institute, Centre for Addiction and Mental Health (CAMH), Toronto, Ontario, Canada, CA; Department of Psychiatry, Temerty Faculty of Medicine, University of Toronto, Toronto, Ontario, Canada, CA.
    Alda, Martin
    Department of Psychiatry, Dalhousie University, Halifax, Nova Scotia, Canada, CA; National Institute of Mental Health, Klecany, Czech Republic, CZ.
    DeShaw, Alexandra
    Nova Scotia Health Authority, Halifax, Nova Scotia, Canada, CA.
    Hintze, Arend
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Husain, Muhammad I
    Campbell Family Research Institute, Centre for Addiction and Mental Health (CAMH), Toronto, Ontario, Canada, CA; Department of Psychiatry, Temerty Faculty of Medicine, University of Toronto, Toronto, Ontario, Canada, CA.
    O'Donovan, Claire
    Department of Psychiatry, Dalhousie University, Halifax, Nova Scotia, Canada, CA.
    Patterson, Rachel
    Campbell Family Research Institute, Centre for Addiction and Mental Health (CAMH), Toronto, Ontario, Canada, CA.
    Ortiz, Abigail
    Campbell Family Research Institute, Centre for Addiction and Mental Health (CAMH), Toronto, Ontario, Canada, CA; Department of Psychiatry, Temerty Faculty of Medicine, University of Toronto, Toronto, Ontario, Canada, CA.
    Not missing at random: Missing data are associated with clinical status and trajectories in an electronic monitoring longitudinal study of bipolar disorder2024Ingår i: Journal of Psychiatric Research, ISSN 0022-3956, E-ISSN 1879-1379, Vol. 174, s. 326-331, artikel-id S0022-3956(24)00242-5Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    There is limited information on the association between participants' clinical status or trajectories and missing data in electronic monitoring studies of bipolar disorder (BD). We collected self-ratings scales and sensor data in 145 adults with BD. Using a new metric, Missing Data Ratio (MDR), we assessed missing self-rating data and sensor data monitoring activity and sleep. Missing data were lowest for participants in the midst of a depressive episode, intermediate for participants with subsyndromal symptoms, and highest for participants who were euthymic. Over a mean ± SD follow-up of 246 ± 181 days, missing data remained unchanged for participants whose clinical status did not change throughout the study (i.e., those who entered the study in a depressive episode and did not improve, or those who entered the study euthymic and remained euthymic). Conversely, when participants' clinical status changed during the study (e.g., those who entered the study euthymic and experienced the occurrence of a depressive episode), missing data for self-rating scales increased, but not for sensor data. Overall missing data were associated with participants' clinical status and its changes, suggesting that these are not missing at random.

    Ladda ner fulltext (pdf)
    fulltext
  • 36.
    Han, Mengjie
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Canli, Ilkim
    Department of Architecture, Middle East Technical University, Ankara 06800, Türkiye;Center for Solar Energy Research and Applications (ODTÜ-GÜNAM), Middle East Technical University, Ankara 06800, Türkiye.
    Shah, Juveria
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Zhang, Xingxing
    Högskolan Dalarna, Institutionen för information och teknik, Energiteknik.
    Dino, Ipek Gursel
    Department of Architecture, Middle East Technical University, Ankara 06800, Türkiye;METU Robotics and AI Technologies Application and Research Center (METU-ROMER), Middle East Technical University (METU), Ankara 06800, Türkiye.
    Kalkan, Sinan
    METU Robotics and AI Technologies Application and Research Center (METU-ROMER), Middle East Technical University (METU), Ankara 06800, Türkiye;Department of Computer Engineering, Middle East Technical University, Ankara 06800, Türkiye.
    Perspectives of Machine Learning and Natural Language Processing on Characterizing Positive Energy Districts2024Ingår i: Buildings, E-ISSN 2075-5309, Vol. 14, nr 2, artikel-id 371Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    The concept of a Positive Energy District (PED) has become a vital component of the efforts to accelerate the transition to zero carbon emissions and climate-neutral living environments. Research is shifting its focus from energy-efficient single buildings to districts, where the aim is to achieve a positive energy balance across a given time period. Various innovation projects, programs, and activities have produced abundant insights into how to implement and operate PEDs. However, there is still no agreed way of determining what constitutes a PED for the purpose of identifying and evaluating its various elements. This paper thus sets out to create a process for characterizing PEDs. First, nineteen different elements of a PED were identified. Then, two AI techniques, machine learning (ML) and natural language processing (NLP), were introduced and examined to determine their potential for modeling, extracting, and mapping the elements of a PED. Lastly, state-of-the-art research papers were reviewed to identify any contribution they can make to the determination of the effectiveness of the ML and NLP models. The results suggest that both ML and NLP possess significant potential for modeling most of the identified elements in various areas, such as optimization, control, design, and stakeholder mapping. This potential is realized through the utilization of vast amounts of data, enabling these models to generate accurate and useful insights for PED planning and implementation. Several practical strategies have been identified to enhance the characterization of PEDs. These include a clear definition and quantification of the elements, the utilization of urban-scale energy modeling techniques, and the development of user-friendly interfaces capable of presenting model insights in an accessible manner. Thus, developing a holistic approach that integrates existing and novel techniques for PED characterization is essential to achieve sustainable and resilient urban environments.

    Ladda ner fulltext (pdf)
    fulltext
  • 37.
    Han, Mengjie
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Johari, Fatemeh
    Uppsala University.
    Huang, Pei
    Högskolan Dalarna, Institutionen för information och teknik, Energiteknik.
    Zhang, Xingxing
    Högskolan Dalarna, Institutionen för information och teknik, Energiteknik.
    Generating hourly electricity demand data for large-scale single-family buildings by a decomposition-recombination method2022Ingår i: Energy and Built Environment, ISSN 2666-1233Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Household electricity demand has substantial impacts on local grid operation, energy storage and the energy performance of buildings. Hourly demand data at district or urban level helps stakeholders understand the demand patterns from a granular time scale and provides robust evidence in energy management. However, such type of data is often expensive and time-consuming to collect, process and integrate. Decisions built upon smart meter data have to deal with challenges of privacy and security in the whole process. Incomplete data due to confidentiality concerns or system failure can further increase the difficulty of modeling and optimization. In addition, methods using historical data to make predictions can largely vary depending on data quality, local building environment, and dynamic factors. Considering these challenges, this paper proposes a statistical method to generate hourly electricity demand data for large-scale single-family buildings by decomposing time series data and recombining them into synthetics. The proposed method used public data to capture seasonality and the distribution of residuals that fulfill statistical characteristics. A reference building was used to provide empirical parameter settings and validations for the studied buildings. An illustrative case in a city of Sweden using only annual total demand was presented for deploying the proposed method. The results showed that the proposed method can mimic reality well and represent a high level of similarity to the real data. The average monthly error for the best month reached 15.9% and the best one was below 10% among 11 tested months. Less than 0.6% improper synthetic values were found in the studied region.

  • 38.
    Han, Mengjie
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    May, Ross
    Zhang, Xingxing
    Högskolan Dalarna, Institutionen för information och teknik, Energiteknik.
    Reinforcement Learning Methodologies for Controlling Occupant Comfort in Buildings2021Ingår i: Data-driven Analytics for Sustainable Buildings and Cities, Switzerland: Springer, 2021, s. 179-205Kapitel i bok, del av antologi (Övrigt vetenskapligt)
  • 39.
    Han, Mengjie
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Shah, Juveria
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Zhang, Xingxing
    Högskolan Dalarna, Institutionen för information och teknik, Energiteknik.
    Review of natural language processing techniques for characterizing positive energy districts2023Ingår i: journal of Physics; Conference series, Institute of Physics Publishing (IOPP), 2023, Vol. 2600, nr 8, artikel-id 082024Konferensbidrag (Refereegranskat)
    Abstract [en]

    The concept of Positive Energy Districts (PEDs) has emerged as a crucial aspect of endeavours aimed at accelerating the transition to zero carbon emissions and climate-neutral living spaces. The focus of research has shifted from energy-efficient individual buildings to entire districts, where the objective is to achieve a positive energy balance over a specific timeframe. The consensus on the conceptualization of a PED has been evolving and a standardized checklist for identifying and evaluating its constituent elements needs to be addressed. This study aims to develop a methodology for characterizing PEDs by leveraging natural language processing (NLP) techniques to model, extract, and map these elements. Furthermore, a review of state-of-the-art research papers is conducted to ascertain their contribution to assessing the effectiveness of NLP models. The findings indicate that NLP holds significant potential in modelling the majority of the identified elements across various domains. To establish a systematic framework for AI modelling, it is crucial to adopt approaches that integrate established and innovative techniques for PED characterization. Such an approach would enable a comprehensive and effective implementation of NLP within the context of PEDs, facilitating the creation of sustainable and resilient urban environments. © 2023 Institute of Physics Publishing. All rights reserved.

  • 40.
    Han, Mengjie
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Wang, Zhenwu
    Zhang, Xingxing
    Högskolan Dalarna, Institutionen för information och teknik, Energiteknik.
    An Approach to Data Acquisition for Urban Building Energy Modeling Using a Gaussian Mixture Model and Expectation-Maximization Algorithm2021Ingår i: Buildings, E-ISSN 2075-5309, Vol. 11, nr 1Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    In recent years, a building’s energy performance is becoming uncertain because of factors such as climate change, the Covid-19 pandemic, stochastic occupant behavior and inefficient building control systems. Sufficient measurement data is essential to predict and manage a building’s performance levels. Assessing energy performance of buildings at an urban scale requires even larger data samples in order to perform an accurate analysis at an aggregated level. However, data are not only expensive, but it can also be a real challenge for communities to acquire large amounts of real energy data. This is despite the fact that inadequate knowledge of a full population will lead to biased learning and the failure to establish a data pipeline. Thus, this paper proposes a Gaussian mixture model (GMM) with an Expectation-Maximization (EM) algorithm that will produce synthetic building energy data. This method is tested on real datasets. The results show that the parameter estimates from the model are stable and close to the true values. The bivariate model gives better performance in classification accuracy. Synthetic data points generated by the models show a consistent representation of the real data. The approach developed here can be useful for building simulations and optimizations with spatio-temporal mapping.

    Ladda ner fulltext (pdf)
    fulltext
  • 41.
    Han, Mengjie
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Zhao, Jing
    Zhang, Xingxing
    Högskolan Dalarna, Institutionen för information och teknik, Energiteknik.
    Shen, Jingchun
    Högskolan Dalarna, Institutionen för information och teknik, Byggteknik.
    Li, Yu
    The reinforcement learning method for occupant behavior in building control: A review2021Ingår i: Energy and Built Environment, ISSN 2666-1233, Vol. 2, nr 2, s. 137-148Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Occupant behavior in buildings has been considered the major source of uncertainty for assessing energy consumption and building performance. Modeling frameworks are usually built to accomplish a certain task, but the stochasticity of the occupant makes it difficult to apply that experience to a similar but distinct environment. For complex and dynamic environments, the development of smart devices and computing power makes intelligent control methods for occupant behaviors more viable. It is expected that they will make a substantial contribution to reducing global energy consumption. Among these control techniques, the reinforcement learning (RL) method seems distinctive and applicable. The success of the reinforcement learning method in many artificial intelligence applications has given an explicit indication of how this method might be used to model and adjust occupant behavior in building control. Fruitful algorithms complement each other and guarantee the quality of the optimization. However, the examination of occupant behavior based on reinforcement learning methodologies is not well established. The way that occupant interacts with the RL agent is still unclear. This study briefly reviews the empirical applications using reinforcement learning, how they have contributed to shaping the modeling paradigms and how they might suggest a future research direction.

    Ladda ner fulltext (pdf)
    fulltext
  • 42.
    Hintze, Arend
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys. BEACON Center for the Study of Evolution in Action, Michigan State University, USA .
    ChatGPT believes it is conscious2023Manuskript (preprint) (Övrigt vetenskapligt)
  • 43.
    Hintze, Arend
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    The Role Weights Play in Catastrophic Forgetting2021Ingår i: 2021 8TH INTERNATIONAL CONFERENCE ON SOFT COMPUTING & MACHINE INTELLIGENCE (ISCMI 2021), IEEE, 2021, s. 160-166Konferensbidrag (Refereegranskat)
    Abstract [en]

    Catastrophic forgetting is the sudden loss of performance when a neural network is trained on a new task or when experiencing unbalanced training. It often limits the ability of neural networks to learn new tasks. Previous work focused on the training data by changing the training regime, balancing the data, or replaying previous training episodes. Other methods used selective training to either allocate portions of the network to individual tasks or otherwise preserve prior task expertise. However, those approaches assume that network attractors are finely tuned, and even small changes to the weights cause misclassification. This fine-tuning is also believed to happen during overfitting and can be addressed with regularization. This paper introduces a method that quantifies how individual weights contribute to different tasks independent of weight strengths or previous training gradients. Applying this method reveals that backpropagation recruits all weights to contribute to a new task and that single weights may be somewhat more robust to noise than previously assumed.

  • 44.
    Hintze, Arend
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys. Michigan State University, East Lansing, MI, USA.
    Adami, Christoph
    Michigan State University, East Lansing, MI, USA; .
    Detecting Information Relays in Deep Neural Networks2023Ingår i: Entropy, E-ISSN 1099-4300, Vol. 25, nr 3, artikel-id 401Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Deep learning of artificial neural networks (ANNs) is creating highly functional processes that are, unfortunately, nearly as hard to interpret as their biological counterparts. Identification of functional modules in natural brains plays an important role in cognitive and neuroscience alike, and can be carried out using a wide range of technologies such as fMRI, EEG/ERP, MEG, or calcium imaging. However, we do not have such robust methods at our disposal when it comes to understanding functional modules in artificial neural networks. Ideally, understanding which parts of an artificial neural network perform what function might help us to address a number of vexing problems in ANN research, such as catastrophic forgetting and overfitting. Furthermore, revealing a network's modularity could improve our trust in them by making these black boxes more transparent. Here, we introduce a new information-theoretic concept that proves useful in understanding and analyzing a network's functional modularity: the relay information IR. The relay information measures how much information groups of neurons that participate in a particular function (modules) relay from inputs to outputs. Combined with a greedy search algorithm, relay information can be used to identify computational modules in neural networks. We also show that the functionality of modules correlates with the amount of relay information they carry.

    Ladda ner fulltext (pdf)
    fulltext
  • 45.
    Hintze, Arend
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Adami, Christoph
    Neuroevolution gives rise to more focused information transfer compared to backpropagation in recurrent neural networks2022Ingår i: Neural Computing & Applications, ISSN 0941-0643, E-ISSN 1433-3058Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Artificial neural networks (ANNs) are one of the most promising tools in the quest to develop general artificial intelligence. Their design was inspired by how neurons in natural brains connect and process, the only other substrate to harbor intelligence. Compared to biological brains that are sparsely connected and that form sparsely distributed representations, ANNs instead process information by connecting all nodes of one layer to all nodes of the next. In addition, modern ANNs are trained with backpropagation, while their natural counterparts have been optimized by natural evolution over eons. We study whether the training method influences how information propagates through the brain by measuring the transfer entropy, that is, the information that is transferred from one group of neurons to another. We find that while the distribution of connection weights in optimized networks is largely unaffected by the training method, neuroevolution leads to networks in which information transfer is significantly more focused on small groups of neurons (compared to those trained by backpropagation) while also being more robust to perturbations of the weights. We conclude that the specific attributes of a training method (local vs. global) can significantly affect how information is processed and relayed through the brain, even when the overall performance is similar.

    Ladda ner fulltext (pdf)
    fulltext
  • 46.
    Huang, Pei
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Energiteknik.
    Han, Mengjie
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Zhang, Xingxing
    Högskolan Dalarna, Institutionen för information och teknik, Energiteknik.
    Hussain, Sayed Asad
    The University of British Columbia, Canada.
    Jayprakash Bhagat, Rohit
    Hogarehalli Kumar, Deepu
    Characterization and optimization of energy sharing performances in energy-sharing communities in Sweden, Canada and Germany2022Ingår i: Applied Energy, ISSN 0306-2619, E-ISSN 1872-9118, Vol. 326, artikel-id 120044Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Peer-to-peer (P2P) renewable power sharing within a building community is a promising solution to enhance the community's self-sufficiency and relieve the grid stress posed by the increased deployment of distributed renewable power. Existing studies have pointed out that the energy sharing potentials of a building community are affected by various factors including location, community scale, renewable energy system (RES) capacity, energy system type, storage integration, etc. However, the impacts of these factors on the energy sharing potentials in a building community are not fully studied. Being unaware of those factors’ impacts could lead to reduced energy sharing potentials and thus limit the associated improvement in energy and economic performances. Thus, this study conducts a comprehensive analysis of various factors’ impacts on the energy sharing performances in building communities. Two performance indicators are first proposed to quantify the energy sharing performances: total amount of energy sharing and energy sharing ratio (ESR). Then, parametric studies are conducted based on real electricity demand data in three countries to reveal how these factors affect the proposed indictors and improvements in self-sufficiency, electricity costs, and energy exchanges with the power grid. Next, a genetic algorithm based design method is developed to optimize the influential parameters to maximize the energy sharing potentials in a community. The study results show that the main influential factors are RES capacity ratio, PV capacity ratio, and energy storage system capacity. A large energy storage capacity can enhance the ESR. To achieve the maximized ESR, the optimal RES capacity ratio should be around 0.4 ∼ 1.1. The maximum energy sharing ratio is usually smaller in high latitude districts such as Sweden. This study characterizes the energy sharing performances and provides a novel perspective to optimize the design of energy systems in energy sharing communities. It can pave the way for the large integration of distributed renewable power in the future. © 2022 The Author(s)

    Ladda ner fulltext (pdf)
    fulltext
  • 47.
    Huang, Pei
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Energiteknik.
    Tu, Ran
    Zhang, Xingxing
    Högskolan Dalarna, Institutionen för information och teknik, Energiteknik.
    Han, Mengjie
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Sun, Yongjun
    Hussain, Syed Asad
    Zhang, Linfeng
    Investigation of electric vehicle smart charging characteristics on the power regulation performance in solar powered building communities and battery degradation in Sweden2022Ingår i: Journal of Energy Storage, ISSN 2352-152X, E-ISSN 2352-1538, Vol. 56, s. 105907-105907, artikel-id 105907Artikel i tidskrift (Refereegranskat)
  • 48.
    Huq, Asif M
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Corporate Disclosures Regulations: Social Solution or a Problem?2021Doktorsavhandling, sammanläggning (Övrigt vetenskapligt)
    Abstract [en]

    Regulations are argued to have the answer to solving various social and economic problems that society faces today (e.g., climate change, tax evasion, etc.). However, regulations may instead become the problem (e.g., overregulation). The central research question of this doctoral thesis is “are corporate disclosures regulations a social solution or a problem?” 

    To answer the central research question, Papers I and II examine the economic effects of an EU-wide audit reform, the Annual Accounts Directive: 2013/34/EU, on firms and the society. Papers III, IV, and V examine firm behavior to assess the need for public regulation of nonfinancial reporting in the light of an EU-wide reform, the Nonfinancial Reporting Directive: 2014/95/EU, commonly known as the NFRD.

    The thesis posits that the current implementations of these reforms in some settings are imperfect and thus costly for the firms and society. It recommends deregulation of the monitoring of financial disclosure, i.e., to allow more small firms the option of deciding if an audit is beneficial for them or not. On the other hand, recommends a different approach for regulating nonfinancial reporting, e.g., sustainability reporting. For instance, regulations that can influence firms’ governance structure, e.g., board diversity. A firm with a diverse board is more likely to adopt a sustainability agenda which is better aligned with the expectations of the EU regulators. 

    Stakeholders use firms’ disclosures to evaluate its performance and behavior for various decision making. For example, shareholders, in their investing or divesting decisions; analysts, in making various forecasts and recommendations; or governments, in assessing the need for reforms. Historically, stakeholders commonly used financial information for these types of decision making. Hence, there are well established generic measures to evaluate firms’ financial information (e.g., earnings quality measures and financial-statement ratios). Nowadays, stakeholders are increasingly using firms’ sustainability related information in their decision-making process as well. However, replicable and scalable generic measures to evaluate such information are missing. This thesis develops objective approaches and a generic measure, to evaluate firms’ sustainability related disclosures. The developed approaches for analyzing unstructured text data may be applied to other fields that can benefit from the use of natural language processing tools.

    Ladda ner fulltext (pdf)
    fulltext
    Ladda ner (jpg)
    presentationsbild
  • 49.
    Huq, Asif M
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys. Dalarna University.
    Carling, Kenneth
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys. Dalarna University.
    Measuring Accountable Information in CSR Reports: A New Operationalization and Analysis Applied to Greenhouse Gas Disclosures2024Ingår i: Journal of Emerging Technologies in Accounting, ISSN 1554-1908, E-ISSN 1558-7940, Vol. 21, nr 1, s. 59-88Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    We develop a novel and generic text-based measure to classify and evaluate greenhouse gas (GHG) disclosures. We construct the measure using collocation analysis of GHG-related words and regular expressions. Automated implementation achieved high concordance compared to manual investigations. We move beyond the “bag-of-words” approach in classifying voluminous nonfinancial corporate disclosure. We also outline a methodology that is manyfold scalable and makes replicability straightforward. Compared to past studies, we work with a significantly larger sample of 5,017 reports across 80 countries, thereby dealing with greater complexity and leading to better generalizability. We also contribute to the debate on whether nonfinancial disclosures exhibit accountability or are merely greenwashing. We find a negative trend in accountability worldwide, and firm-level accountability in GHG disclosures is not detectable in a country-level reduction of GHG emissions. Moreover, firms disclose significantly higher accountable information in a civil-law legal environment compared to those in a common-law legal environment.

  • 50.
    Huq, Asif M
    et al.
    Högskolan Dalarna, Institutionen för information och teknik, Mikrodataanalys.
    Daunfeldt, Sven-Olov
    Högskolan Dalarna, Institutionen för kultur och samhälle, Nationalekonomi. Institute of Retail Economics, Stockholm.
    Hartwig, Fredrik
    University of Gävle.
    Rudholm, Niklas
    Institute of Retail Economics, Stockholm.
    Free to Choose: Do Voluntary Audit Reforms Increase Employment Growth?2021Ingår i: International Journal of the Economics of Business, ISSN 1357-1516, E-ISSN 1466-1829, Vol. 28, nr 1, s. 163-178Artikel i tidskrift (Refereegranskat)
1234 1 - 50 av 152
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf