1. |
- Afzaal, Muhammad, 1989-
(author)
-
Explainable AI for Data-Driven Feedback and Intelligent Action Recommendations to Support Student Self-Regulation
- 2024
-
Doctoral thesis (other academic/artistic)abstract
- Self-regulated learning (SRL) is a cognitive ability with demonstrable significance in facilitating students’ ability to effectively strategize, monitor, and assess their own learning actions. Studies have indicated that a lack of selfregulated learning skills negatively impacts students’ academic performance. Effective data-driven feedback and action recommendations are considered crucial for SRL and significantly influence student learning and performance. However, the task of delivering personalised feedback to every student poses a significant challenge for teachers. Moreover, the task of identifying appropriate learning activities and resources for individualised recommendations poses a significant challenge for teachers, given the large number of students enrolled in most courses.To address these challenges, several studies have examined how learning analytics-based dashboards can support students’ self-regulation. These dashboards offered several visualisations (as feedback) on student success and failure. However, while such feedback may be beneficial, it does not offer insightful information or actionable recommendations to help students improve academically. Explainable artificial intelligence (xAI) approaches have been proposed to explain such feedback and generate insights from predictive models, with a focus on the relevant actions a student needs to take to improve in ongoing courses. Such intelligent activities could be offered to students as data-driven behavioural change recommendations.This thesis offers an xAI-based approach that predicts course performance and computes informative feedback and actionable recommendations to promote student self-regulation. Unlike previous research, this thesis integrates a predictive approach with an xAI approach to analyse and manipulate students’ learning trajectories. The aim is to offer detailed, data-driven actionable feedback to students by providing in-depth insights and explanations for the predictions provided by the approach. The technique provides students with more practical and useful knowledge compared to the predictions alone.The proposed approach was implemented in the form of a dashboard to support self-regulation by students in university courses, and it was evaluated to determine its effects on the students’ academic performance. The results revealed that the dashboard significantly enhanced students’ learning achievements and improved their self-regulated learning skills. Furthermore, it was found that the recommendations generated by the proposed approach positively affected students’ performance and assisted them in self-regulation.
|
|
2. |
- Alam, Mahbub Ul, 1988-
(author)
-
Advancing Clinical Decision Support Using Machine Learning & the Internet of Medical Things : Enhancing COVID-19 & Early Sepsis Detection
- 2024
-
Doctoral thesis (other academic/artistic)abstract
- This thesis presents a critical examination of the positive impact of Machine Learning (ML) and the Internet of Medical Things (IoMT) for advancing the Clinical Decision Support System (CDSS) in the context of COVID-19 and early sepsis detection.It emphasizes the transition towards patient-centric healthcare systems, which necessitate personalized and participatory care—a transition that could be facilitated by these emerging fields. The thesis accentuates how IoMT could serve as a robust platform for data aggregation, analysis, and transmission, which could empower healthcare providers to deliver more effective care. The COVID-19 pandemic has particularly stressed the importance of such patient-centric systems for remote patient monitoring and disease management.The integration of ML-driven CDSSs with IoMT is viewed as an extremely important step in healthcare systems that could offer real-time decision-making support and enhance patient health outcomes. The thesis investigates ML's capability to analyze complex medical datasets, identify patterns and correlations, and adapt to changing conditions, thereby enhancing its predictive capabilities. It specifically focuses on the development of IoMT-based CDSSs for COVID-19 and early sepsis detection, using advanced ML methods and medical data.Key issues addressed cover data annotation scarcity, data sparsity, and data heterogeneity, along with the aspects of security, privacy, and accessibility. The thesis also intends to enhance the interpretability of ML prediction model-based CDSSs. Ethical considerations are prioritized to ensure adherence to the highest standards.The thesis demonstrates the potential and efficacy of combining ML with IoMT to enhance CDSSs by emphasizing the importance of model interpretability, system compatibility, and the integration of multimodal medical data for an effective CDSS.Overall, this thesis makes a significant contribution to the fields of ML and IoMT in healthcare, featuring their combined potential to enhance CDSSs, particularly in the areas of COVID-19 and early sepsis detection.The thesis hopes to enhance understanding among medical stakeholders and acknowledges the need for continuous development in this sector.
|
|
3. |
- Araújo, Marco, 1982-
(author)
-
Infrastructure deployment in unprofitable areas : A techno-economic model for multiple criteria decision analysis under the European Union telecommunications regulatory framework
- 2020
-
Doctoral thesis (other academic/artistic)abstract
- In the European Union significant asymmetries prevail among member states in the most diverse areas. The telecom sector is no exception to this, with some members being much more advanced than others. Within the member states asymmetries also occur. And if we extrapolate this to a broader audience, for example the OECD, the European Union has been far away from some other members in what concerns asymmetries within own countries, with Japan and South Korea being the most evident. In 2016 the European Commission proposed a new regulatory framework for the telecom sector which was adopted in late 2018 by the European Parliament and must be transposed to national laws by member-states by late 2020. As we move towards the digital revolution, the so-called industry 4.0, the new EU regulatory framework has the aim of removing most of these asymmetries, by guaranteeing that most citizens will have access to a very fast Internet connection regardless of where they live. This regulatory framework provides some guidance and goals and funding objectives, but for operators and governments this is just not sufficient per se. Against this background, the overall research issue of this thesis is a methodological approach to how to determine the best access technology from a multi-criteria and multi-stakeholder perspective. In particular, to provide coverage in a certain region who lacks service a priori (therefore unprofitable by nature), problematics to be addressed include: i) what are exactly the new regulatory framework guidelines; ii) which strategic operational model to use; iii) what is the most appropriate technology to achieve these objectives; iv) how to handle the pricing incognita and all the financial component; v) how risky it is to make these objectives a reality.
|
|
4. |
- Aspling, Fredrik, 1980-
(author)
-
Unleashing Animal-Computer Interaction : A Theoretical Investigation of the “I” in ACI
- 2020
-
Doctoral thesis (other academic/artistic)abstract
- Non-human animals have had a long co-existence and relationship with human culture and society, and we interact with them in a number of ways, and for various reasons. Their involvement in technology can be traced back more than half a century, initially restricted to scientific contexts, for example, for the study of animal behavior, cognition, or language learning abilities. The advancement and growing ubiquity of technology has extended their interactions with technology beyond scientific settings to other domains and everyday contexts, and for a broader set of reasons. This development is also driven by the emerging research area of animal-computer interaction (ACI), in which scholars of human-computer interaction (HCI) are starting to explore the possibilities of designing interactive technology for and with animals. This requires engagement with the difficult task of understanding this new set of actors and the types of interactions and functionality they possibly would like to have with computing. This is a challenge even when it comes to humans, but the challenge escalates when considering other animals, and presents even more challenges. Animals live different lives to us, and include a broad and diverse category of species, with different ways of experiencing and being in the world, and we have difficulty understanding each other due to these interspecies differences. The shift from human to animal interaction is far from straightforward.This new and embryonic situation contests traditional notions of what a “user” is and can be, and how both digital technologies and other species, are being used. Consequently, it also challenges previous theoretical foundations and methods for understanding and designing user-computer interactions. The latter has received special attention, where user-centered design approaches and methods from the field of HCI and interaction design (IxD) has become a natural point of departure. As a complement, ACI needs a bolder and more creative way of progressing when it comes to building a theoretical framework to account for these new forms of interaction. There is a need to extend our thinking and the conventional ways of doing research and design, and to preserve curiosity and theoretical and methodological openness. As an alternative to many other design approaches, this thesis advocates the theoretical investigation of the “I” in ACI, aiming to extend the conventional notion of how interaction is conceptualized, a topic that has suffered from negligence. Drawing on ethnomethodological and ethnographic fieldwork – covering a maximum variation of extreme and deviant of cases – this thesis investigates the boundaries of the field and different theoretical perspectives and empirical insights, in order to increase our understanding of the emerging dynamics of multispecies-computer interactions, and also how these insights can excite the imagination and generate topics for zoocentric design and computing.
|
|
5. |
- Ayele, Workneh Yilma, 1978-
(author)
-
A toolbox for idea generation and evaluation : Machine learning, data-driven, and contest-driven approaches to support idea generation
- 2022
-
Doctoral thesis (other academic/artistic)abstract
- Ideas are sources of creativity and innovation, and there is an increasing demand for innovation. For example, the start-up ecosystem has grown in both number and global spread. As a result, established companies need to monitor more start-ups than before and therefore need to find new ways to identify, screen, and collaborate with start-ups.The significance and abundance of data are also increasing due to the growing digital data generated from social media, sensors, scholarly literature, patents, different forms of documents published online, databases, product manuals, etc. Various data sources can be used to generate ideas, yet, in addition to bias, the size of the available digital data is a major challenge when it comes to manual analysis.Hence, human-machine interaction is essential for generating valuable ideas where machine learning and data-driven techniques generate patterns from data and serve human sense-making. However, the use of machine learning and data-driven approaches to generate ideas is a relatively new area. Moreover, it is also possible to stimulate innovation using contest-driven idea generation and evaluation. However, the measurement of contest-driven idea generation processes needs to be supported to manage the process better. In addition, post-contest challenges hinder the development of viable ideas. A mixed-method research methodology is applied to address these challenges.The results and contributions of this thesis can be viewed as a toolbox of idea-generation techniques, including a list of data-driven and machine learning techniques with corresponding data sources and models to support idea generation. In addition, the results include two models, one method and one framework, to better support data-driven and contest-driven idea generation. The beneficiaries of these artefacts are practitioners in data and knowledge engineering, data mining project managers, and innovation agents. Innovation agents include incubators, contest organizers, consultants, innovation accelerators, and industries.Future projects could develop a technical platform to explore and exploit unstructured data using machine learning, visual analytics, network analysis, and bibliometric for supporting idea generation and evaluation activities. It is possible to adapt and integrate methods included in the proposed toolbox in developer platforms to serve as part of an embedded idea management system. Future research could also adapt the framework to barriers that constrain the development required to elicit post-contest digital service. In addition, since the proposed artefacts consist of process models augmented with AI techniques, human-centred AI is a promising area of research that can contribute to the artefacts' further development and promote creativity.
|
|
6. |
- Bampa, Maria, 1992-
(author)
-
Data-Driven AI for Patient and Public Health : On the Use of Multisource and Multimodal Data in Machine Learning to Improve Healthcare
- 2024
-
Doctoral thesis (other academic/artistic)abstract
- The integration of artificial intelligence in healthcare has created a new era of advancements, reshaping patient care and revolutionizing public health interventions. Through artificial intelligence, healthcare providers and public health authorities can optimize interventions, leading to more precise and efficient responses that enhance patient outcomes and address public health challenges effectively. The past decade has witnessed a rapid digital transformation across industries, and healthcare is no exception. This evolution is evident in the widespread adoption of electronic health records and healthcare information systems and the integration of diverse technologies, including handheld, wearable, and smart devices.A central challenge in this digital shift lies in representing data from multiple sources and modalities for downstream machine learning tasks. This complexity stems from the varied longitudinal or contextual events in patients' historical records, encompassing lab tests, vital signs, diagnoses, and drug administration. Additionally, the challenge extends to predictive modeling and constructing robust models that accurately classify future health events, taking into consideration heterogeneous health-related data. Electronic phenotyping, crucial for identifying fine-grained disease/patient clusters, is also a central problem when utilizing multisource and multimodal information effectively to create meaningful patient profiles. In the context of public health interventions, exemplified by crises like the COVID-19 pandemic, decision-making requires a delicate balance between optimizing intervention effectiveness and considering economic and societal well-being.This Ph.D. thesis seeks to unravel the potential of multisource and multimodal health observational data in generating patient phenotypes and predictions for both individual health and public health surveillance. It addresses the following central question: How can multisource and multimodal observational health data be effectively harnessed, using machine learning, to enhance patient and public health? Comprising five studies, the thesis confronts challenges posed by diverse data sources and modalities, exploring strategies for creating comprehensive patient profiles, developing robust classification models, and employing clustering methods tailored to observational health data. The research seeks to provide valuable insights into integrating AI in healthcare, with a specific emphasis on the complexities of multisource and multimodal data integration. It underscores the importance of exploring heterogeneous health observational data to deepen our understanding of patient health and optimize machine learning applications. Emphasizing the intricate nature of health data, the thesis discusses careful data handling and innovative methodologies to maximize its potential impact on improving patient outcomes and informing public health strategies. The effective management of heterogeneous observational health data requires thoughtful consideration due to their varied sources and inherent complexities.
|
|
7. |
- Bergdahl, Nina, 1971-
(author)
-
Upper Secondary School Student Engagement and Disengagement : in Blended Learning
- 2020
-
Doctoral thesis (other academic/artistic)abstract
- The present research approaches Swedish upper secondary school students’ engagement and disengagement in Technology-enhanced Learning (TEL). To date, research on engagement in TEL have mainly focused on university-level students and have overlooked the dimension of disengagement. The aim of the thesis is to explore how to facilitate students’ academic engagement in TEL by considering both student engagement and disengagement when students learn with digital technologies. While a mixed-methods approach was adopted across all sub-studies, sub-studies I-III emphasised qualitative methods, and sub-studies IV-V were more quantitatively orientated.Results revealed that teachers’ orchestration of digital technologies for learning varied more between the individual teachers than the subjects taught, and that the orchestration of digital technologies and the design of learning activities covaried with the observed and self-reported levels of student engagement. A Design-Based Research intervention showed that teachers could orchestrate digital technologies and design learning activities that increase student engagement in TEL, but may find it challenging to sustain the practice without support. A student evaluation showed that only the students with the highest engagement levels reported interest as their reason to engage. Instead, the most common reasons to engage were related to the social dimension of engagement. Building on the results of this intervention, design principles that facilitate student engagement when designing for engagement in TEL were identified.After the intervention, the focus was expanded to include student disengagement along with engagement and The Learner-Engagement-Technology (LET) instrument was developed using interviews and theory. The LET instrument was tested and validated to reflect multi-dimensional aspects of upper secondary school student engagement and disengagement in TEL. The LET-instrument revealed that low-, average- and high-performance students engage and disengage differently in TEL; that students’ IT skills played a role for engagement in TEL, but are not sufficient to redeem disengagement and that a majority of students use digital technologies to escape when the lesson is perceived to be boring. The results also showed that indicators of disengagement in TEL do not have a natural opposite in the engagement scale; that is; disengagement in TEL is more than the mere absence of, or lower levels of, engagement in TEL. Overlooking disengagement, when students learn with technologies, might fail to uncover critical insights that hinder student engagement.The main contributions of this thesis are: (i) derived design principles and practical insights on conditions related to student engagement and disengagement in TEL that may inform designs of learning activities to facilitate engagement (ii) a methodological contribution that reflects an attempt to combine critical realism and Design-Based Research, and (iii) a theoretical contribution that suggests how engagement and disengagement may be understood and conceptualised in TEL. Future research should explore engagement and disengagement in TEL, relating to the uptake of digital technologies in earlier school years, and other school forms. The thesis is relevant for teachers, decision makers, researchers and others interested in understanding the challenges and possibilities that may affect students in a digitalised school.
|
|
8. |
- Berns, Katie, 1990-
(author)
-
Designing Community Economies : Exploring Alternatives for Infrastructuring Food Waste Activism
- 2023
-
Doctoral thesis (other academic/artistic)abstract
- By drawing on past CSCW and SHCI scholarship engaged with how technology can support the collaborative work of organising activism and empowering people to respond to diverse sustainability challenges– my research contributes to the emerging field of digital civics by introducing the human geography concept ‘community economies’ as a new way to frame and determine the scope of the design of digital technologies for infrastructuring food waste activism. Using a combination of ethnographic research and participatory action research (PAR), the empirical data were collected through two long-term collaborations with food-sharing communities in Denmark and Sweden and through a collaboration with researchers on a related project that focused on a food-sharing community in Germany. The findings and contributions of the work include (1) the identification of the key concerns, values, and existing sociotechnical practices involved in establishing and maintaining activist food-sharing communities, (2) insights into and reflections on the design of sociotechnical practices that support food-sharing as a form of community economy, considering challenges such as recognising the variegated capacities of participants and balancing diverse and sometimes conflicting community values, and (3) the determination of how new food-sharing communities scale their impact in different ways such by growing larger, joining forces with other local food initiatives, or proliferating by learning from similar, more established communities in different locations. The discussion centres around three key dimensions that address the research questions; food-sharing as activism, designing sociotechnical sharing and governance practices, and designing community economies. Within these areas, I discuss the tensions that emerged regarding the role of technology in the three communities and unpack how a combination of existing mainstream technologies and bespoke civic technologies act as an infrastructure for the organisation, enactment, and proliferation of community-led food-sharing initiatives.
|
|
9. |
- Bohman, Samuel, 1975-
(author)
-
Web Applications for Large-Scale Decision Support : Preference Elicitation, Modeling and Visualization
- 2021
-
Doctoral thesis (other academic/artistic)abstract
- This thesis addresses the lack of effective and efficient technology design in current e-participation research by investigating two approaches that yet have not been explored to any great extent in the literature: decision science and data visualization. It is concerned with the problem of how to combine techniques from these two fields to achieve decision support in the context of e-participation; from preference elicitation and modeling to data analysis, visualization and final recommendations, such that it can provide value to practitioners. The work was carried out in two separate research projects, but which shared a common research strategy: to develop, demonstrate, and evaluate e-participation technologies in real-life settings. The first project was a pilot designed to provide European universities with a web-based e-participation platform to empower students in the Bologna Process. Thirteen universities in Europe participated as end-users of the platform. Using a mixed methods research design, the results showed that ICT is poorly conceptualized in e-participation research and practice, typically conceived informally and simply as tools, independent of the political and social context within which they are developed and used. With regard to sociotechnical challenges in e-participation, the results confirm much of previous research that has underlined the prevalence of technological determinism, institutional resistance, privacy and trust issues, among many other factors. In the second project we developed a decision analytic framework for structuring, evaluating, and analyzing stakeholder conflicts in land-use planning. The Municipality of Upplands Väsby in Stockholm, Sweden, participated as a trial. Using agile design principles and methods we implemented the framework as a prototype spatial decision support system using the R programming language. Our prototype shows that a combination of decision science and data visualization has the potential to become a powerful tool in the hands of governments to enable members of society to identify where their differences really matter and where they are unimportant, thus providing structure and new insight to democratic debate. Furthermore, we believe it has the potential to alleviate some of the barriers and limitations associated with traditional methods of community engagement, including distance and time constraints, issues of scale, and high costs.
|
|
10. |
- De Alwis, Sulakshana, 1988-
(author)
-
Technology-Assisted Supplemental Work in Sri Lanka : The Role of Information Communication Technologies in Work-life Boundaries and Work-life Conflict
- 2023
-
Doctoral thesis (other academic/artistic)abstract
- Due to increased affordability and accessibility, information and communication technologies (ICTs) are omnipresent in the daily lives of many individuals and consequently influence how people think, feel, and react in day-to-day life experiences. Workplaces are increasingly becoming less bounded by place and time, and employees can connect with work anywhere, anytime. The limitless connectivity enabled by ICTs has created paradoxical experiences for employees. On the one hand, connectivity increases flexibility, empowering employees to work whenever they prefer and wherever they want to be. On the other hand, connectivity creates after-hours expectations where employees are expected to be available anytime to work (i.e. Technology-Assisted Supplemental Work - TASW). However, ICTs alone cannot create these paradoxical experiences, and it is the constitutive entanglements between ICTs, social, organisational and individual factors that create paradoxical experiences. Employing the sociomaterial perspective, in this thesis, we looked at how ICTs have become entangled with different social, organisational, and individual factors in the work-life boundary experiences of individuals and how these entanglements contribute to Technology-Assisted Supplemental Work (TASW) and the work-life conflict of employees. The findings showed that TASW and work-life boundary experiences are outcomes of complex web relations between different sociomaterial assemblages. The flexibility availability paradox is an outcome of these constitutive entanglements between ICTs and human factors. Hence, the same technological constellations could create different boundary experiences for individuals due to the specific nature of the entanglements. Cultural values such as collectivism and power distance could elevate after-hours expectations if top management support such work norms. The findings also showed that female employees can be further disadvantaged due to TASW, especially if they are from a society that upholds traditional gender norms. In such circumstances, introducing technology as a facilitator of work-life balance through flexibility is questionable. All in all, the entanglement of ICTs with social, cultural and individual factors can decide the work-life conflict of employees. These findings suggest that the role of technology needs to be conceptualised carefully in work-life research. Assuming technology to be an exogenous factor or completely absent from work-life experiences will not give a complete picture of the work-life experiences of individuals. Thus, looking at work-life experiences from the sociomaterial perspective would assist researchers in finding more richer insights about this phenomenon and such new insights would be beneficial for organisations to implement formal guidelines to manage TASW requirements to reduce the negative consequences of TASW.
|
|
11. |
- Deegalla, Sampath, 1976-
(author)
-
Nearest Neighbor Classification in High Dimensions
- 2024
-
Doctoral thesis (other academic/artistic)abstract
- The simple k nearest neighbor (kNN) method can be used to learn from high dimensional data such as images and microarrays without any modification to the original version of the algorithm. However, studies show that kNN's accuracy is often poor in high dimensions due to the curse of dimensionality; a large number of instances are required to maintain a given level of accuracy in high dimensions. Furthermore, distance measurements such as the Euclidean distance may be meaningless in high dimensions. As a result, dimensionality reduction could be used to assist nearest neighbor classifiers in overcoming the curse of dimensionality. Although there are success stories of employing dimensionality reduction methods, the choice of which methods to use remains an open problem. This includes understanding how they should be used to improve the effectiveness of the nearest neighbor algorithm.The thesis examines the research question of how to learn effectively with the nearest neighbor method in high dimensions. The research question was broken into three smaller questions. These were addressed by developing effective and efficient nearest neighbor algorithms that leveraged dimensionality reduction. The algorithm design was based on feature reduction and classification algorithms constructed using the reduced features to improve the accuracy of the nearest neighbor algorithm. Finally, forming nearest neighbor ensembles was investigated using dimensionality reduction.A series of empirical studies were conducted to determine which dimensionality reduction techniques could be used to enhance the performance of the nearest neighbor algorithm in high dimensions. Based on the results of the initial studies, further empirical studies were conducted and they demonstrated that feature fusion and classifier fusion could be used to improve the accuracy further. Two feature and classifier fusion techniques were proposed, and the circumstances in which these techniques should be applied were examined. Furthermore, the choice of the dimensionality reduction method for feature and classifier fusion was investigated. The results indicate that feature fusion is sensitive to the selection of the dimensionality reduction method. Finally, the use of dimensionality reduction in nearest neighbor ensembles was investigated. The results demonstrate that data complexity measures such as the attribute-to-instance ratio and Fisher's discriminant ratio can be used to select the nearest neighbor ensemble depending on the data type.
|
|
12. |
- Firouzi, Ramin, 1993-
(author)
-
Distributed Intelligence for IoT Systems Using Edge Computing
- 2023
-
Doctoral thesis (other academic/artistic)abstract
- Over the past decade, the Internet of Things (IoT) has undergone a paradigm shift away from centralized cloud computing to edge computing. Hundreds of billions of things are estimated to be deployed in the rapidly advancing IoT paradigm, resulting in an enormous amount of data. Sending all the data to the cloud has recently proven to be a performance bottleneck, as it causes many network issues, including high latency, high power consumption, security issues, privacy issues, etc. However, the existing paradigms do not use edge devices for decision-making. Distributed intelligence could strengthen the IoT in several ways by distributing decision-making tasks among edge devices within the network instead of sending all data to a central server. All computational tasks and data are shared among edge devices. Edge computing offers many advantages, including distributed processing, low latency, fault tolerance, better scalability, better security, and data protection. These advantages are helpful for critical applications that require higher reliability, real-time processing, mobility support, and context awareness. This thesis investigated the application of different types of intelligence (e.g., rule-based, machine learning, etc.) to implementing distributed intelligence at the edge of the network and the network challenges that arise. The first part of this thesis presents a novel and generalizable distributed intelligence architecture that leverages edge computing to enable the intelligence of things by utilizing information closer to IoT devices. The architecture is comprised of two tiers, which address the heterogeneity and constraints of IoT devices. Additionally, the first part of this thesis identifies a suitable reasoner for two-level distributed intelligence and an efficient way of applying it in the architecture via an IoT gateway. To mitigate communication challenges in edge computing, the second part of the thesis proposes two-level mechanisms by leveraging the benefits of software-defined networking (SDN) and 5G networks based on open radio access network (O-RAN) as part of a communication overlay for the distributed intelligence architecture. The third part of this thesis investigates integrating the two-tier architecture and the communication mechanisms in order to provide distributed intelligence in IoT systems in an optimal manner.
|
|
13. |
- Gurung, Ram Bahadur, 1983-
(author)
-
Random Forest for Histogram Data : An application in data-driven prognostic models for heavy-duty trucks
- 2020
-
Doctoral thesis (other academic/artistic)abstract
- Data mining and machine learning algorithms are trained on large datasets to find useful hidden patterns. These patterns can help to gain new insights and make accurate predictions. Usually, the training data is structured in a tabular format, where the rows represent the training instances and the columns represent the features of these instances. The feature values are usually real numbers and/or categories. As very large volumes of digital data are becoming available in many domains, the data is often summarized into manageable sizes for efficient handling. To aggregate data into histograms is one means to reduce the size of the data. However, traditional machine learning algorithms have a limited ability to learn from such data, and this thesis explores extensions of the algorithms to allow for more effective learning from histogram data.The thesis focuses on the decision tree and random forest algorithms, which are easy to understand and implement. Although, a single decision tree may not result in the highest predictive performance, one of its benefits is that it often allows for easy interpretation. By combining many such diverse trees into a random forest, the performance can be greatly enhanced, however at the cost of reduced interpretability. By first finding out how to effectively train a single decision tree from histogram data, these findings could be carried over to building robust random forests from such data. The overarching research question for the thesis is: How can the random forest algorithm be improved to learn more effectively from histogram data, and how can the resulting models be interpreted? An experimental approach was taken, under the positivist paradigm, in order to answer the question. The thesis investigates how the standard decision tree and random forest algorithms can be adapted to make them learn more accurate models from histogram data. Experimental evaluations of the proposed changes were carried out on both real world data and synthetically generated experimental data. The real world data was taken from the automotive domain, concerning the operation and maintenance of heavy-duty trucks. Component failure prediction models were built from the operational data of a large fleet of trucks, where the information about their operation over many years have been summarized as histograms. The experimental results showed that the proposed approaches were more effective than the original algorithms, which treat bins of histograms as separate features. The thesis also contributes towards the interpretability of random forests by evaluating an interactive visual tool for assisting users to understand the reasons behind the output of the models.
|
|
14. |
- Huskaj, Gazmend, 1978-
(author)
-
Offensive Cyberspace Operations : Implications for Sweden
- 2024
-
Doctoral thesis (other academic/artistic)abstract
- This PhD thesis describes how Sweden can organise its offensive cyberspace capabilities for strategic objectives, including cyber deterrence and defence, in response to escalating threats from nations like Russia, China, and Iran. The research develops a multi-level and multi-domain (MLMD) theoretical framework, integrating deterrence theory, intelligence the- ory, and offensive cyberspace operations. Adopting an interpretivist research philosophy, the research employs a case study research strategy, reviewing scientific and military literature and conducting semi-structured interviews with key respondents in Swedish policy and defence. The findings suggest the need for a comprehensive national deterrence strategy encompassing offensive cyberspace capabilities, the operational organisation of cyberspace units supported by policy and intelligence, and a tactical emphasis on identifying and exploiting zero-day vulnerabilities. This research contributes to the field by offering models and frameworks for planning and executing offensive cyberspace operations, providing insights and increasing the knowledge base for professionals and researchers. Additionally, it advances the field by applying the MLMD framework for evaluating the research papers and using the general method for theory building in applied disciplines to assess the utility of the proposed model for offensive cyberspace operations.
|
|
15. |
- Jaber, Razan, 1988-
(author)
-
Towards Designing Better Speech Agent Interaction : Using Eye Gaze for Interaction
- 2023
-
Doctoral thesis (other academic/artistic)abstract
- This research is about addressing the need to better understand interaction with conversational user interfaces (CUIs) and how human-technology `conversations' can be improved by drawing on the lessons learned from human-human interaction. It focuses on incorporating abstractions of complex human behaviour, specifically gaze, to enhance interactions with speech agents in conversations. Across four empirical studies, a mix of methods is used to look closely at the interaction between the user and the system.I offer empirical and conceptual contributions for interaction designers and researchers. First, I present a novel speech interface, Tama, which is a gaze-aware speech agent designed to explore the use of gaze in conversational interactions with smart speakers. Second, I present the empirical contributions, that is, the studies that document the interactions with and around speech interfaces, including ongoing, non-system-directed speech. A moment-by-moment analysis of these interactions highlights the opportunities that the gaze offers as a modality to enhance the interaction with the speech agent, as well as the problems and limitations when such a modality is used. The third contribution is a conceptual contribution made by providing perspective on minimal anthropomorphic design. This produces interactions that are not human-like in terms of behaviour but do take advantage of the skills used in human interaction as a key to advancing interactions with speech agents.Based on my research work and contributions, I reflect upon advancing interactions with speech interfaces, focusing on what different technologies can offer and the possibility of taking the next step in designing CUIs. I then discuss the need to bridge the work of different fields (i.e. conversation analysis (CA), human-computer interaction (HCI), and human-robot interaction (HRI)) to combine models and approaches from all these fields in order to guide designers building speech systems. I see three competing yet complementary interaction paradigms across CUIs. I call these paradigms Direct Speech Interaction, Agent-Mediated Interaction, and Para-Speech Interaction. Each of these paradigms has specific challenges and opportunities for interaction.
|
|
16. |
- Jonathan, Gideon Mekonnen, 1982-
(author)
-
Information Technology Alignment : The Role of Organisational Structure
- 2020
-
Licentiate thesis (other academic/artistic)abstract
- Information technology (IT) alignment studies which focus on conceptual debates have left little room for studies investigating practical issues such as organisational structure. On the other hand, the attention paid to private and commercial organisations has resulted in findings that might not apply to public organisations. To address this gap in the literature, and respond to calls for further research, this study explored the influence of formal and informal organisational structures on IT alignment in a public organisation.This thesis is a compilation of three studies—a systematic literature review and two case studies. The literature review revealed the lack of IT alignment studies in public organisations focusing on organisational structure. The findings of the case studies, conducted in one Swedish municipality, indicate the simultaneous existence of a formal and informal organisational structure which influenced IT alignment. The result of the qualitative case study revealed a centralised formal organisational structure, and three forms of informal organisational structure—interpersonal relationships, cross-departmental relationships, and professional networks—were identified. The findings also seem to indicate that the identified organisational structure forms have influence on IT alignment. The second (i.e. quantitative) case study established the strength of these effects.Among the identified organisational structure forms, cross-departmental relationships were found to have the most substantial influence on IT alignment, particularly on communications, partnership and the dynamic IT scope. The influence of a centralised organisation structure on IT governance was also confirmed. While the influence of interpersonal relationships on the three dimensions of IT alignment—communications, IT governance and skills development—was established, the influence of professional networks on IT alignment could not be substantiated.This study makes several contributions to research and practice in IT alignment. Although prior studies have investigated the role of different organisational structures in IT alignment, the contribution of this research is that it looked into the influence of both formal and informal organisational structures on IT alignment, simultaneously. The research has also assessed the relative significance of various forms of organisational structure on IT alignment. Leaders and managers in the public sector can make use of the findings of this research to help them identify different organisational structure forms and make the necessary adjustments to improve IT alignment.
|
|
17. |
- Jonathan, Gideon Mekonnen, 1982-
(author)
-
Information Technology Alignment in Public Organisations : Towards Successful Digital Transformation
- 2023
-
Doctoral thesis (other academic/artistic)abstract
- The widespread acceptance of digital transformation has brought the topic to the top of researchers’ and practitioners’ agendas. However, despite the anticipated benefits and opportunities, evidence suggests that many organisations still struggle to realise the results of successful digital transformation. The recent data from academic literature, consultancy firms and media reports indicate that, on average, between 70 and 80 per cent of digital transformation projects fail. According to the Boston Consulting Group, the figure for organisations in the public sector stands at 78 per cent. Among others, one of the reasons cited for this challenge is a phenomenon referred to as ‘IT alignment’—the appropriate and timely application of information technology (IT) in congruence with the overall organisational goals, internal organisational settings, and external environments.The recognition of the critical role IT alignment plays in digital transformation has triggered calls for studies investigating the relationship between the two constructs, in various organisational contexts. However, a closer look at the extant literature reveals that public organisations were not the focus of studies exploring IT alignment’s role in successful digital transformation. This paucity of knowledge needs to be addressed since the differences between private and public organisations influence the adoption of emerging technologies. Thus, scholars argue that our comprehension of the relationship between the two constructs, based on studies conducted in private organisations, might not apply to public organisations. To address this gap and respond to the calls for further research, this study investigated the role of IT alignment in the digital transformation of public organisations. In addition to two systematic literature reviews, the thesis presents the results of two case studies with two follow-up confirmatory surveys.The research question answered in this thesis is: “How can public organisations pursue IT alignment to enable successful digital transformation?” The main results of the study presented are the following. First, three roles of IT alignment for digital transformation in a public organisation are identified, i.e., enabling organisational agility, improving the value derived from IT investments, and enabling integration of digital technologies. Second, the organisational and managerial factors that influence IT alignment are revealed: i.e., organisational agility, organisational structure, organisational culture, leadership skills, digital metrics, HR management, stakeholder relationships, and external domain alignment. The study also ranked the relative degree of influence of the identified factors on IT alignment. Third, based on two systematic literature reviews and the analysis of interviews and survey data, the thesis proposed a framework with 19 actions that decision-makers could take to improve IT alignment, thereby enabling successful digital transformation. These 19 actions are linked to six IT alignment dimensions, which, in turn, are used for improving the degree of IT alignment.The findings of the study presented in this thesis have various research and practical implications. First, the study contributes to research on the relationships between various organisational and managerial factors, the six dimensions of IT alignment, and the success of digital transformation in public organisations. Second, the study contributes to practice, as leaders in the public sector can use the findings, especially the 19 actions, as they make the necessary organisation-wide adjustments to improve IT alignment. As the finds of the studies presented in the thesis indicate, public organisations can succeed in their digital transformation endeavours when they improve the degree of IT alignment. To this end, understanding the relative degree of influence of the identified factors and the order of priority of the proposed actions will be invaluable.
|
|
18. |
- Koutsopoulos, Georgios, 1982-
(author)
-
KYKLOS - A modeling method and tool for managing changing capabilities in organizations
- 2024
-
Doctoral thesis (other academic/artistic)abstract
- The environments within which modern organizations are operating are characterized by constantly increasing volatility and diversity, which act as a driving force that continuously presents opportunities and threats to the organizations. The result of this situation is that these environments have become so dynamic that the phenomenon of organizational change is slowly becoming the new constant, rather than being an exception as in earlier years. The challenges arising from the need to handle constant change and evolution naturally lead to changing organizational capabilities. Information systems, as one aspect of an organization, can provide efficient support for the design and analysis of capabilities, and enterprise modeling can facilitate the development of specialized methods for this task. Hitherto, a plethora of capability modeling methods exist, providing a wide spectrum of perspectives.However, the support provided for managing the phenomenon of changing organizational capabilities remains limited, since existing methods have omitted to capture the elements necessary to depict organizational capabilities in motion and the motivations triggering such transitions. In addition, managing change requires more structured approaches, which should be methodologically supported and conceptualized.The goal of this PhD thesis is to develop a capability modeling method, called KYKLOS, that can support organizational change by modeling the changing capabilities of organizations and all the relevant aspects of this phenomenon. This work followed the Design Science Research framework, and started by explicating the problem via a literature review of existing capability meta-models; this was followed by the elicitation of method requirements, drawn from both the existing literature and a case study conducted in the domain of public healthcare in Sweden. Based on these requirements, an initial meta-model was developed, which was then demonstrated using the same case study and evaluated by experts through interviews. This activity resulted in an extension to the initial version of the meta-model, which was then instantiated via a case study conducted in the domain of public arts and culture in Greece. In parallel, the compatibility of other modeling approaches was explored. An extended version of the meta-model was then converted to its final version, which was suitable for the implementation of the modeling language in a tool, using the ADOxx meta-modeling platform. Simultaneously with the development of the tool, the syntax, semantics and procedure of the modeling method were created. The complete method was demonstrated through a case study at a company providing ERP solutions and consulting in Sweden, and the results were used to evaluate the method by two groups representing the stakeholder roles.The thesis contributes towards an improved management of change in organizations through the development of a method and complementary supporting tool, with the capability perspective as the focal point for the design and analysis of organizational change.
|
|
19. |
- Koutsopoulos, Georgios
(author)
-
Managing Capability Change in Organizations : Foundations for a Modeling Approach
- 2020
-
Licentiate thesis (other academic/artistic)abstract
- The ongoing digital transformation of modern society results in dynamic environments that present changes, opportunities and threats for modern organizations. This is a driving force for constant organizational change and evolution, a situation that is associated with change in organizational capabilities. Capability design and analysis can be supported by Information Systems, whose design can be facilitated by Enterprise Modeling, and in particular, capability modeling. Several approaches exist for modeling capabilities; however, there can be improvements regarding capability change by modeling the necessary elements for depicting not only organizational capabilities in motion, but also the motivation for change.The objective of this thesis is to set the basis for the provision of methodological and tool support for organizations whose capabilities are undergoing or need to undergo changes.This thesis project follows the Design Science Research paradigm to proceed with the development of a method artifact. Initially, during the problem explication step, a literature review was performed that was followed by an analysis of the capability meta-models that exist in the literature, based on the introduction of a classification framework that facilitated the mapping of meta-model concepts to specific change functions. This activity resulted in the development of function-specific concept sets that were visualized and presented as concept maps. In addition, information for capability change was derived from the literature review, along with insight on the dimensions of capability and change, which was introduced as a new capability typology, structured and presented in a StateMachine diagram.This information was used in the second step of the process, which concerns the elicitation of requirements for a meta-model, which is the main component of the method artifact, an activity that combined information from a case study conducted in a Swedish public healthcare organization, whose capabilities are undergoing changes. The combined sources resulted in a goal model, depicting the artifact goals.Finally, moving to the artifact development step, a meta-model for capability change was developed. The thesis contributes by establishing the foundations for the development of a method with the purpose of setting the basis for the development of a method and tool for supporting changing organizations.
|
|
20. |
- Larsson, Ken
(author)
-
Managing Thesis Projects in Higher Education - Through Learning Analytics
- 2020
-
Doctoral thesis (other academic/artistic)abstract
- For the student, the graduation project is in most universities the final step towards graduation and increased opportunities in the professional career. It is not uncommon for students to struggle with the thesis in order to complete their graduation, resulting in disrupted plans, delays in completion and the worst case, non-completion of their degrees. This outcome is undesirable for not only the individual student or the university but also society at large.The effects of a failed thesis are waste of resources and the supply of qualified individual in the society, for the student, the effects include lesser possibilities in the career, lower pay. Thus, the dissertation is addressing the problem of the management of resources in higher education, especially in undergraduate thesis supervision.There are three aspects of the overall problem addressed in this dissertation; a practical problem in respect of too many uncompleted theses, or not completed on time. Another practical problem is increasing of the demand that is not accompanied by increased resources on a comparable scale. The third aspect of the problem is lack of knowledge in understanding the factors affecting the thesis process resulting in dropouts or delays. The lack of knowledge may result in a blind management process.Two research questions investigate the problem, what factors influence the thesis completion or non-completion that can be useful for management, secondly, what management principles can be helpful to secure high quality in higher education.The questions are answered through several studies that employ mixed-methods and learning analytics techniques which include data mining and the application of statistics and machine learning algorithms. In total, over 3000 thesis projects have been studied.The thesis contributes with a better understanding of the factors that influence completion and non-completion of thesis projects, management guidelines for the thesis process, and a novel methodological approach using learning analytics and machine learning to support data-driven decision-making about thesis processes.
|
|
21. |
- Lee, Zed, 1992-
(author)
-
Z-Series : Mining and learning from complex sequential data
- 2023
-
Doctoral thesis (other academic/artistic)abstract
- The amount and complexity of sequential data collected across various domains have grown rapidly, posing significant challenges for extracting useful knowledge from such data sources. The complexity arises from diverse sequence representations with varying granularities, such as multivariate time series, histogram snapshots, and heterogeneous health records, which often describe a single data instance with multiple sequences. Due to this complexity, the underlying temporal relations between sequences may not be clear and can change over time, making knowledge discovery even more challenging.To address these challenges, this thesis proposes event intervals as a unified representation for complex sequential data. Event intervals capture the underlying temporal relations between sequences by comparing the relative locations of event intervals in both the time and value dimensions, making them suitable for describing diverse sequential data. The proposed artifacts aim to efficiently and effectively discover patterns of interest, transform sequential data in different application domains through temporal abstraction, and provide interpretable features for machine learning tasks without compromising performance. The effectiveness of the proposed artifacts is evaluated through empirical experiments and practical evaluations, which demonstrate their applicability and performance. The thesis is structured into three parts. First, it introduces state-of-the-art frameworks for mining event interval sequences, including frequent arrangement mining, classification, and clustering. The utility of these frameworks is demonstrated through comparative empirical evaluations against other frameworks. Second, the thesis applies temporal abstraction to complex sequential data in different application domains, showcasing its applicability through tasks such as disproportionality analysis and local grouping detection for time series. Lastly, event intervals are used as interpretable features for learning tasks, outperforming competitive algorithms using different feature representations. This part focuses on univariate and multivariate time series, and extensive experiments are performed on the publicly available benchmark datasets with statistical tests.
|
|
22. |
- Linusson, Henrik, 1986-
(author)
-
Nonconformity Measures and Ensemble Strategies : An Analysis of Conformal Predictor Efficiency and Validity
- 2021
-
Doctoral thesis (other academic/artistic)abstract
- Conformal predictors are a family of predictive models that associate with each of their predictions a measure of confidence, enabling them to provide quantitative information about their own trustworthiness. In risk-laden machine learning applications, where bad predictions may lead to economic loss, personal injury, or worse, such inherent quality control appears highly beneficial, if not required. While the foundations of conformal prediction were initially published some twenty years ago, their use, and further development, is still (at the time of writing this thesis) not widespread in the machine learning community, and several open questions remain regarding the proper design and use of conformal prediction systems. In this thesis, we attempt to tackle some of these questions, focusing our attention on three specific characteristics of conformal predictors. First, conformal predictors rely on so-called nonconformity functions, which are mappings from the object space onto the real line, typically based on traditional classification or regression models; here, we investigate properties of the underlying learning algorithm and characteristics of the resulting conformal predictor. Second, conformal predictors output predictions on a form that is distinct from traditional prediction methods, by supplying multi-valued prediction regions with a statistically valid coverage probability; we propose two procedures for post-processing the output from conformal classification models that provide interpretations more closely related to traditional predictive models, while still retaining meaningful confidence information. Finally, we provide contributions relating to the construction of conformal predictor ensembles, illustrating potential issues with existing ensemble procedures, as well as proposing and evaluating an alternative ensemble method.
|
|
23. |
- Máthé, Melinda
(author)
-
Mapping the Landscape of Digital Game-Based Learning in Swedish Compulsory and Upper Secondary Schools : Opportunities and Challenges for Teachers
- 2020
-
Licentiate thesis (other academic/artistic)abstract
- Interest in the use of digital games in education has been increasing over the past few decades. Advocates argue that digital games are powerful learning tools with the potential to support increased motivational, cognitive, behavioural, affective, physiological and social outcomes. However, empirical evidence for their effectiveness is mixed. Research has focused primarily on measuring the effect of games on learning in researcher-controlled experiments, whilst relatively less attention has been paid to the role of teachers. The thesis addresses the research gap by investigating how teachers in Swedish compulsory and upper secondary schools use digital games on their own initiative and how they develop their competencies. It also considers the challenges they face.Data from in-depth qualitative interviews and a mixed method survey are used to investigate the research questions. Both the data collection and analysis have been informed by activity theory. This is also used to problematise the adaptation of digital games as teaching and learning tools. In addition, the analysis explores teachers´ self-reported activities in relation to their disposition towards digital games.The findings show that a diversity of digital games and gamification tools have found a foothold in Swedish classrooms. The participating teachers are interested in introducing and further developing digital game-based approaches, though there are limitations in their use of gaming resources and the extent to which they can leverage these to achieve educational outcomes. The research identifies and discusses four general categories of teachers: non-game users, sceptics, curious adopters and advanced adopters. Results indicate that the more positive disposition of game-using teachers tends to be related to a higher level of pedagogical integration, a greater variety of game use, and a wider range of educational outcomes, as well as an interest in professional development. Digital game-based learning is often understood as the use of gamification tools in the form of quizzes, whereas complex games and longer gameplay are less typical. Whilst most teachers agree on the motivational benefits of digital games, not as many perceive them as effective in teaching new knowledge and cognitive skills. The introduction of digital games is hampered by the lack of access to relevant and good-quality products, financial resources, preparation time and adequate technology, as well as contextualised and flexible forms of professional development. These challenges hint at deeper issues with preexisting education structures. Future research should have a twofold focus: the development of adequate game resources that can support collaborative forms of learning and higher-level skills, and flexible and contextualised competence-development solutions for teachers which are relevant to their needs.The thesis contributes to the current literature by mapping the landscape of digital game-based learning in Swedish compulsory and upper secondary schools. It provides a nuanced understanding of the perspectives of teachers on digital game use and the opportunities and challenges presented by digital game-based learning.
|
|
24. |
- McGregor, Moira, 1963-
(author)
-
Social Order of the Co-Located Mobile Phone : Practices of collaborative mobile phone use
- 2020
-
Doctoral thesis (other academic/artistic)abstract
- This thesis examines mundane practices of everyday phone use to make conceptual, empirical and methodological contributions to ongoing research on mobile technology. It argues that we do not yet have a clear understanding of how the mobile phone is used–who does what, when and why. Yet these details are important if we are to judge the impact of mobile technology, understand the possibilities and dangers it offers, or evaluate claims about its broader impact on our sociality.The participation of both the phone user and those co-located is examined–to understand how we actively create and maintain a new ‘social order’ with mobile phones. Across five separate studies, a mix of methods is used to look closely at phone use. Drawing extensively on in situ video recording of device use, as well as interviews and ethnographic observations, the empirical chapters cover three different types of device use: search, messaging, and way-finding. The chapters look at the specifics of how the applications manifest themselves in practice (such as message notifications, or the ‘blue dot’ in map apps), as well as the practices adopted to use, manage and balance those applications within ongoing co-located, face-to-face interactions.Empirically, the studies document how co-located phone use is dependent upon the technology, but is also reliant upon new practices of collaboration and co-operation. I discuss how participation is managed (who is involved), the temporal organisation of action (when use occurs), and the recurrent actions and materiality of those practices (what happens). Moment-by-moment analysis of the practices highlights the importance and value of making phone use publicly accountable to avoid disturbing the ‘local order’, but also for sharing knowledge and making sense of the world together, as well as having fun and maintaining friendships.The methodological contribution is found in the hybridity of methods adopted to meet the challenge of collecting and analysing data relevant to studying what is happening when we use our phones. A combination of ethnography with video and conversation analysis, and the creative use of probes to support interviews is proposed, to gain access to a broader perspective on phone use. Through reliance upon empirical observation, we can avoid abstract and reductive generalisations about phone use, discussing instead the observable action and resources that do occur recurrently around mobile phone use–how things get done with mobiles.Conceptually, the thesis draws on ethnomethodology and conversation analysis for a perspective on how we make sense of the day-to-day interactions we have with one another–how we bring about and sustain the ‘local’ social order. I argue that practices of mobile phone use are constituent parts of local order in everyday life, and that their examination is key to understanding what social order is now like. A conceptual ‘diamond’ of mobile phone practice, broken down into elements of time, body, materiality, and repair is proposed. In conclusion, the thesis highlights the prevalence of phone practices beyond individual, task-oriented pursuits and I finish by reflecting on possible future research to enhance the collaborative, social aspects of mobile technology.
|
|
25. |
- Peiris, Colombage Ranil, 1973-
(author)
-
A Framework for Designing Learning Management Systems to Support Undergraduate Thesis Projects : With a Focus on Sri Lankan Universities
- 2022
-
Doctoral thesis (other academic/artistic)abstract
- In Sri Lankan public universities about 41000 undergraduate projects are conducted every year, and on average, the total man-hours spent on the thesis projects is about 1.2 million. Although the universities widely use information technology to support teaching and learning, a specific system supporting undergraduate thesis projects is lacking and literature documents many problems related to these projects. Hence, the present research endeavour was commenced in a Sri Lankan university to develop a framework to guide the design process of a Learning Management System (LMS) that can be used to address those problems and support Undergraduate Thesis Projects (UTP). The following three research questions guided the study: 1) What are the problems of UTP? 2) Which learning theories and pedagogical concepts should be considered when designing an LMS to support the UTP? 3) What are the requirements and components of an LMS which would support the UTP? The Soft Design Science Research Methodology was applied to answer three research questions, and the main findings are as follows: 1) Six main problems areas were identified based on a specific case, 2) These problems were related to unsatisfied requirements of student student-supervisor interaction, scaffolding, and self-regulation processes 3) These requirements further analysed using related learning theories and specific problems were condensed into a general problem. The general problem is the lack of a learning environment that supports the theoretical foundation (pedagogical implications) and practical facilitation (Information and Communication Technology tools), which could support the student-supervisor interaction, scaffolding, and self-regulation processes, 4) The general problem was analysed, comparing the theoretical foundations and pedagogical implications and a framework was suggested as a general solution for designing an LMS with four basic modules. These modules include software subcomponents that can be used to enhance student-supervisor interaction, peer collaboration, students’ self-regulation skills, and students’ motivation, 5) The general solution was evaluated, and it was shown that supervisors accepted the proposed components as parts of an LMS that supports UTP. The findings show that this framework offers features and components that enhance the quality and importance of thesis projects.
|
|