Malmö University Publications
Change search
Refine search result
1 - 7 of 7
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.
    Abdul Sater, Malek
    et al.
    Malmö University, Faculty of Technology and Society (TS), Department of Computer Science and Media Technology (DVMT).
    Mohamed, Reem
    Malmö University, Faculty of Technology and Society (TS), Department of Computer Science and Media Technology (DVMT).
    Parkinson’s disease tremor assessment: Leveragingsmartphones for symptom measurement2023Independent thesis Basic level (university diploma), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Parkinson's disease (PD) is a progressive, chronic neurodegenerative disorder that impacts patients' quality of life. Hand tremor is a hallmark motor symptom of PD. However, current clinical tremor assessment methods are time-consuming and expensive and may not capture the full extent of tremor fluctuations. The built-in sensors in smartphones offer an accessible and cost-effective alternative for objective tremor assessment.

    This study presents a systematic approach to developing a quantitative algorithm for Parkinson's disease tremor assessment using Inertial Measurement Unit (IMU) data. This study begins with a comprehensive data visualisation and understanding phase, leading to the design decision to implement a multiple linear regression model for tremor severity prediction. The IMU data, collected from 10 patients, is pre-processed and normalised to ensure consistency and account for varying degrees of tremor severity.

    Feature extraction is conducted based on insights from literature, resulting in 16 unique features. These unique features are extracted for each of the acceleration and rotation rate data, resulting in 582 total features over both hands and all three tremor types. Recursive Feature Elimination with Cross-Validation (RFECV) is employed for feature selection, identifying the most relevant features contributing to tremor severity prediction. A multiple linear regression model is implemented and trained using the Leave-One-Out with Cross-Validation (LOOCV) method.

    The model's performance is evaluated resulting in a mean MSE of 0.88, a mean MAE of 0.69, and an R² of 0.88. The results indicate a strong correlation between predicted and actual tremor severity, suggesting the model's high validity. The selected features show a high correlation with the patient's MDS-UPDRS scores, further validating their relevance in predicting tremor severity. Greater results could be achieved, but sample size was the greatest limitation during this study.

    This study demonstrates the potential of using IMU data and multiple linear regression modelling for accurate PD tremor assessment within Mobistudy, contributing to the field of quantitative PD analysis.

    Download full text (pdf)
    fulltext
  • 2.
    Hellstrand, Elliott
    et al.
    Malmö University, Faculty of Technology and Society (TS).
    Tu, Jacky
    Malmö University, Faculty of Technology and Society (TS).
    Mobile-first? - En Utredning av det Moderna Webbutvecklingsfältet2021Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
    Abstract [en]

    Billions of people around the world use their mobile phone to surf on the web, and in recentdecades, we have seen new web technologies that facilitate the development of mobile webapplications. The purpose of this study is to investigate whether mobile-first will be thestandard for the future and how the ecosystem for web development will be affected by this.Mobile-first means that you prioritize the mobile platform first, compared with the traditio-nal desktop platform. In addition to this, we also want to investigate multi-platform toolssuch as progressive web applications and hybrid applications, but also how responsive webdesign affects web development. We will conduct two literature studies and an online surveywill be sent out to answer our research questions. Based on our selected methods, the resultsindicate that the mobile-first would be the way one chooses to prioritize for the current si-tuation. The reason is that mobile phone users have increased drastically in recent decadesdue to the lower prices of mobile phones, and internet telecommunications that have attrac-ted a larger market of users. In addition, it turns out that the web technologies between hy-brid applications and progressive web applications are still unexplored for most developers.This is due, for example, to a lack of interest in developing or that they are not compatiblewith the business’ system/product. The responsive web design was shown to be the one thathas had the most impact on web development, and is the concept that is the most famili-ar to developers. The definition of mobile-first in the literature and the online survey lar-gely agreed with each other, however, the literature provided a more well-defined answer.

  • 3.
    Holmberg, Lars
    Malmö University, Faculty of Technology and Society (TS), Department of Computer Science and Media Technology (DVMT). Malmö University, Internet of Things and People (IOTAP).
    A Conceptual Approach to Explainable Neural NetworksManuscript (preprint) (Other academic)
    Abstract [en]

    The success of neural networks largely builds on their ability to create internal knowledge representations from real-world high-dimensional data, such as images, sound, or text. Approaches to extract and present these representations, in order to explain a neural network’s decision, is an active and multifaceted research field. To gain a deeper understanding of a central aspect of this field, we performed a targeted literature review focusing on research that aims to associate internal representations with human understandable concepts. By using deductive nomological explanations combined with causality theories as an analytical lens, we analyse nine carefully selected research papers. We find our analytical lens, the explanation structure and causality, useful to understand what can be expected, and not expected, from explanations inferred from neural networks. The analysis additionally uncovers an ambiguity in the reviewed literature related to the goal: is it (a) understanding the ML model, (b) the training data or (c) actionable explanations that are true-to-the-domain?

  • 4.
    Holmberg, Lars
    Malmö University, Faculty of Culture and Society (KS), School of Arts and Communication (K3).
    Ageing and sexing birds2023Conference paper (Other academic)
    Abstract [en]

    Ageing and sexing birds require specialist knowledge and training concerning which characteristics to focus on for different species. An expert can formulate an explanation for a classification using these characteristics and, additionally, identify anomalies. Some characteristics require practical training, for example, the difference between moulted and non-moulted feathers, while some knowledge, like feather taxonomy and moulting patterns, can be learned without extensive practical training. An explanation formulated for a classification, by a human, stands in sharp contrast to an explanation produced by a trained neural network. These machine explanations are more an answer to a how-question, related to the inner workings of the neural network, not an answer to a why-question, presenting domain-related characteristics useful for a domain expert. For machine-created explanations to be trustworthy neural networks require a static use context and representative independent and identically distributed training data. These prerequisites do seldom hold in real-world settings. Some challenges related to this are neural networks' inability to identify exemplars outside the training distribution and aligning internal knowledge creation with characteristics used in the target domain. These types of questions are central in the active research field of explainable artificial intelligence (XAI), but, there is a lack of hands-on experiments involving domain experts. This work aims to address the above issues with the goal of producing a prototype where domain experts can train a tool that builds on human expert knowledge in order to produce useful explanations. By using internalised domain expertise we aim at a tool that can produce useful explanations and even new insights for the domain. By working together with domain experts from Ottenby Observatory our goal is to address central XAI challenges and, at the same time, add new perspectives useful to determine age and sex on birds. 

  • 5.
    Holmberg, Lars
    Malmö University, Faculty of Technology and Society (TS), Department of Computer Science and Media Technology (DVMT). Malmö University, Internet of Things and People (IOTAP).
    Human In Command Machine Learning2021Licentiate thesis, comprehensive summary (Other academic)
    Abstract [en]

    Machine Learning (ML) and Artificial Intelligence (AI) impact many aspects of human life, from recommending a significant other to assist the search for extraterrestrial life. The area develops rapidly and exiting unexplored design spaces are constantly laid bare. The focus in this work is one of these areas; ML systems where decisions concerning ML model training, usage and selection of target domain lay in the hands of domain experts. 

    This work is then on ML systems that function as a tool that augments and/or enhance human capabilities. The approach presented is denoted Human In Command ML (HIC-ML) systems. To enquire into this research domain design experiments of varying fidelity were used. Two of these experiments focus on augmenting human capabilities and targets the domains commuting and sorting batteries. One experiment focuses on enhancing human capabilities by identifying similar hand-painted plates. The experiments are used as illustrative examples to explore settings where domain experts potentially can: independently train an ML model and in an iterative fashion, interact with it and interpret and understand its decisions. 

    HIC-ML should be seen as a governance principle that focuses on adding value and meaning to users. In this work, concrete application areas are presented and discussed. To open up for designing ML-based products for the area an abstract model for HIC-ML is constructed and design guidelines are proposed. In addition, terminology and abstractions useful when designing for explicability are presented by imposing structure and rigidity derived from scientific explanations. Together, this opens up for a contextual shift in ML and makes new application areas probable, areas that naturally couples the usage of AI technology to human virtues and potentially, as a consequence, can result in a democratisation of the usage and knowledge concerning this powerful technology.

    Download full text (pdf)
    fulltext
    Download (jpg)
    preview image
  • 6.
    Holmberg, Lars
    et al.
    Malmö University, Faculty of Technology and Society (TS), Department of Computer Science and Media Technology (DVMT). Malmö University, Internet of Things and People (IOTAP).
    Alvarez, Alberto
    Malmö University, Faculty of Technology and Society (TS), Department of Computer Science and Media Technology (DVMT).
    Deep Learning, generalisation and conceptsManuscript (preprint) (Other academic)
    Abstract [en]

    Central to deep learning is an ability to generalise within a target domain consistent with human beliefs within the same domain. A label inferred by the neural network then maps to a human mental representation of a, to the label, corresponding concept. If an explanation concerning why a specific decision is promoted it is important that we move from average case performance metrics towards interpretable explanations that build on human understandable concepts connected to the promoted label. In this work, we use Explainable Artificial Intelligence (XAI) methods to investigate if internal knowledge representations in trained neural networks are aligned and generalise in correspondence to human mental representations. Our findings indicate an, in neural networks, epistemic misalignment between machine and human knowledge representations. Consequently, if the goal is classifications explainable for en users we can question the usefulness of neural networks trained without considering concept alignment. 

  • 7.
    John, Meenu Mary
    et al.
    Malmö University, Faculty of Technology and Society (TS), Department of Computer Science and Media Technology (DVMT).
    Olsson, Helena Holmström
    Malmö University, Faculty of Technology and Society (TS), Department of Computer Science and Media Technology (DVMT).
    Bosch, Jan
    Chalmers University.
    AI Deployment Architecture: Multi-Case Study for Key Factor Identification2020In: 2020 27th Asia-Pacific Software Engineering Conference (APSEC), IEEE, 2020, Vol. 1, p. 395-404Conference paper (Refereed)
    Abstract [en]

    Machine learning and deep learning techniques are becoming increasingly popular and critical for companies as part of their systems. However, although the development and prototyping of ML/DL systems are common across companies, the transition from prototype to production-quality deployment models are challenging. One of the key challenges is how to determine the selection of an optimal architecture for AI deployment. Based on our previous research, and to offer support and guidance to practitioners, we developed a framework in which we present five architectural alternatives for AI deployment ranging from centralized to fully decentralized edge architectures. As part of our research, we validated the framework in software-intensive embedded system companies and identified key challenges they face when deploying ML/DL models. In this paper, and to further advance our research on this topic, we identify factors that help practitioners determine what architecture to select for the ML/D L model deployment. For this, we conducted a follow-up study involving interviews and workshops in seven case companies in the embedded systems domain. Based on our findings, we identify three key factors and develop a framework in which we outline how prioritization and trade-offs between these result in certain architecture. The contribution of the paper is threefold. First, we identify key factors critical for AI system deployment. Second, we present the architecture selection framework that explains how prioritization and trade-offs between key factors result in the selection of a certain architecture. Third, we discuss additional factors that may or may not influence the selection of an optimal architecture.

1 - 7 of 7
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