Department of Software Science

Abiodun Emmanuel Onile, the PhD student of the Department of Software Science, defended his PhD thesis ”Innovative Energy Services based on Behavioural–Reflective–Attributes and Intelligent Recommendation Systems“ (”Arukatel soovitussüsteemidel põhinevad uuenduslikud energiateenused“) on November 12, 2024 in room ICT-638 (Akadeemia tee 15a, ICT building of TalTech) and was also followed via Zoom.

The thesis ”Innovative Energy Services based on Behavioural–Reflective–Attributes and Intelligent Recommendation Systems“ is published in the Digital Collection of TalTech Library.

Supervisor Prof. Juri Belikov (TalTech) and co-supervisor Prof. Eduard Petlenkov (TalTech).

Oponents:

• Prof. Bo Nørregaard Jørgensen, SDU Center for Energy Informatics, University of Southern Denmark, Denmark;
• Prof. Lucio Tommaso de Paolis, Department of Engineering for Innovation, University of Salento, Italy.

In recent times, the escalating impact of urban climate change and the increasing demand for electrical energy have become pressing concerns. Broadly, electricity conservation strategies rely on efficient utilization. Yet, challenges arise due to consumers facing difficulties in executing these measures. In order to achieve the desired efficiency in energy usage, innovative solutions aimed at influencing the behavior of energy consumers are necessary. Personalized recommendations play a crucial role in stimulating behavioral changes among consumers, thereby contributing to sustainable advancements in energy efficiency. Addressing this challenge, this thesis centers on innovative energy services reliant on intelligent recommendation systems and digital twins. The thesis ”Innovative Energy Services based on Behavioural–Reflective–Attributes and Intelligent Recommendation Systems“ examines various trends related to modeling and the adoption of energy services, considering the positive connections between recommendation systems and the energy behaviour of consumers on the demand side. Through a comprehensive content analysis of leading research works in the IEEE Xplore and Scopus databases, our study validates the innovative use of data-driven twin technologies for demand-side recommendation services.

Industry 4.0 plays a role in end-consumers progression towards energy efficiency by enabling more sophisticated analytics and creating avenues for end-consumers and decentralized grid assets to be modeled similarly to their Digital Twin (DT) counterparts. This development opens pathways for asset-level analytics. This study introduces an innovative approach employing an ensemble of hybrid DT asset models, combining ordinary differential equation (ODE) physics engines and data-driven recurrent neural network (RNN) prediction methods. The emerging real-time information technology (IT) applications and innovative modeling of DT for individual electricity assets are disrupting this landscape. Particularly, in relation to integration of intermittent renewable energy sources which offers promising demand-response (DR) solutions, but also brings about emerging stability issues for the electricity grid. Similarly, aggregators are increasingly pivotal in the DR electricity market, yet they frequently grapple with substantial market monopolization and a lack of transparency by profiteering or taking advantage of transitive RES. Additionally, following modelling of individual asset based predictive DT, this study introduces an novel graph-based ranking approach using PageRank model for demand side recommendation service provision.

There are specific scenarios where end-users might disregard recommended advice, contributing to a widening ’knowledge-action gap’. A demand-side recommender system, complemented by Generative Pre-trained Transformers (GPT) for a conversational chatbot interface technology and Extended Reality (XR) proves effective in engaging and extending end-consumer interest in recommended advice. The novelty of this research lies in developing a new approach that enables individual end-user assets to contribute to demand-response initiatives.

Results from the study demonstrate that employing BESS through the multi-agent reinforcement learning control strategy yielded a maximum peak load reduction of approximately 24.5%, alongside a 94% and 69% improvement in comfort for specific loads and users’ engagement respectively. Furthermore, efficiency-related recommendations for BESS contributed to a linear reduction in peak load, surpassing the baseline scenario. The study’s outcomes also show that the hybrid Digital Twin approach accomplished an impressive 84.132% reduction in prediction error, as measured by MSE metrics.

Eric Blake Jackson, the PhD student of the Department of Software Science, defended his PhD thesis „Cross-Border Data Exchange In the Nordic-Baltic Region: Data Intermediaries, Interoperability, and e-Services Orchestration“ on Friday, October 11, 2024 in room ICT-638 (Akadeemia tee 15a, ICT building of TalTech) and was also followed via Zoom.

In today’s interconnected world, sharing data across national borders can drive innovation, improve public services, and help different sectors—business, government, academia, and society—collaborate on solving complex problems like aging populations and global pandemics. The European Union (EU) is making strides toward this goal by passing new regulations to create a unified digital market for data exchange across member states.

A key part of this effort involves the rise of data intermediaries like X-Road and eDelivery. These third-party organizations use open-source technologies to help government agencies and private companies securely exchange data, allowing them to work together more effectively. However, despite this growing momentum, sharing data across borders remains limited. Different countries use different systems, and navigating the EU’s complex regulatory environment presents significant challenges for organizations trying to exchange information.

This research explores the dynamics of cross-border data exchange, particularly in the Nordic-Baltic region, including Estonia, Finland, Latvia, and Lithuania. The focus is on how data sharing can enhance the Silver Economy, a market that provides products and services to people over the age of 50. The research also investigates broader issues of cross-border collaboration, using both regional case studies and a global example from the World Health Organization.

A critical framework guiding this research is the European Interoperability Framework (EIF), which outlines four layers—legal, technical, semantic, and organizational—that must be aligned for successful data exchange between countries. The study uses a blend of qualitative and quantitative methods to understand these challenges and provide solutions.

The findings are wide-ranging. One part of the research looks at how the principles of X-Road can be applied to future cross-border services. Another examines the barriers faced by Estonia and Finland in connecting their e-services. Additionally, the research maps out the technical infrastructure needed to support data sharing in the Silver Economy. It analyzes the impact of the Data Governance Act on small and medium enterprises (SMEs). This new law could make it easier for businesses to navigate the EU’s regulatory landscape and participate in cross-border data exchanges.

Future research must explore emerging concepts like Data Spaces, which aim to enable even greater cross-border data collaboration across Europe. Ultimately, enhancing cross-border data sharing will be crucial for tackling many global challenges that societies face today, from aging populations to health crises.

The thesis „Cross-Border Data Exchange In the Nordic-Baltic Region: Data Intermediaries, Interoperability, and e-Services Orchestration“ is published in the Digital Collection of TalTech Library.

Supervisor:

• Prof. Ingrid Pappel, TalTech, Estonia.

Co-supervisors:

• Prof. Sadok Ben Yahia,TalTech, Estonia;
• Prof. Dirk Draheim, TalTech, Estonia.

Oponents:

• Prof. Nitesh Bharosa, Delft University of Technology, Netherlands;
• Dr. Anastasija Nikiforova, University of Tartu, Estonia.

Markko Liutkevičius, the PhD student of the Department of Software Science, defended his PhD thesis „Enhancing Public Employment Services with AI-enabled Virtual Competence Assistant“ on September 30, 2024 in room ICT-638 (Akadeemia tee 15a, ICT building of TalTech) and was also followed via Zoom.

The Markko Liutkevičius thesis „Enhancing Public Employment Services with AI-enabled Virtual Competence Assistant“ explores how AI can transform Public Employment Services (PES) to address labor market challenges caused by rapid technological changes and external factors like the COVID-19 pandemic and geopolitical conflicts. With traditional skills becoming outdated and new skills in demand, the EU has set ambitious targets to ensure a skilled, adaptable workforce. Moreover, labor shortages and demographic trends—such as an aging workforce—require urgent action, especially for underrepresented groups. The research focuses on AI-enabled solutions to improve PES, exploring the current situation in the Estonian PES as an example labor market service provider in the EU.

Two critical problems are identified: first, the lack of intelligent matching between citizens’ CVs and job advertisements; second, the failure to incorporate skills in job matching. Currently, Estonian citizens must manually search job listings, and there are no modern solutions to assist them in finding appropriate job or training opportunities based on their skills. This leads to inefficiencies for both job seekers and employers. To address these challenges, the thesis proposes developing a Virtual Competence Assistant (VCA), an AI-powered service designed to enhance job matching and skills development while incorporating local labor market intelligence (LMI). The initial scope of the VCA is on matching citizens' skills with job opportunities, as job recommendation systems are more developed in existing research compared to training recommendation systems or local LMI.

A key aspect of the research is integrating the European Classification of Skills/Competences, Qualifications, and Occupations (ESCO) into AI-enabled services to match job seekers with opportunities. The thesis stresses the importance of continuous, iterative development of AI services in PES, focusing on user feedback and ethical deployment. Future research should explore training recommendation systems, local LMI, and the use of AI in PES across multiple languages and regions. The goal is to create a more efficient, inclusive, and dynamic labor market by matching not only the unemployed but all citizens with jobs and training opportunities, utilizing insights from the local labor market, and required skills.

The thesis „Enhancing Public Employment Services with AI-enabled Virtual Competence Assistant“ is published in the Digital Collection of TalTech Library.

Supervisor Prof. Sadok Ben Yahia (TalTech) and co-supervisor Prof. Innar Liiv (TalTech).

Oponents:

• Dr. Marisa Ponti, University of Gothenburg, Sweden;
• Prof. Ricardo Colomo-Palacios, Universidad Politécnica de Madrid, Spain.

Nzamba Bignoumba, the PhD student of the Department of Software Science, defended his PhD thesis „Predictive Systems Using Machine Learning Tools to Forecast Adverse Events During Medical Stays“ on September 27, 2024 in room ICT-638 (Akadeemia tee 15a, ICT building of TalTech) and was also followed via Zoom.

Before the advent of AI, medicine was more preventive and curative. Since the introduction of machine learning, a sub-field of AI, a new paradigm known as predictive medicine has emerged. Researchers have developed and are still developing several machine learning tools to predict adverse medical events, enabling physicians to take early action and prevent the worst. This thesis is a continuation of this work. It aims to use machine learning tools, namely deep learning models, to predict adverse medical events during patients' medical stays. The medical events addressed throughout the thesis include the prediction of mortality in intensive care units, the detection of depression, and the prediction of unplanned hospital readmissions. Extensive experiments and comparisons with cutting-edge models have shown that the newly introduced deep learning models improve the accuracy of tackled medical tasks. Overall, the thesis findings demonstrate that machine-learning tools, specifically deep-learning models, are ideal candidates for predicting or detecting adverse events during a patient's medical stay. Although that is the immediate thesis goal, the long-term goal is to improve these models to be more accurate, robust, and explainable. This would facilitate their adoption in real-world medical settings and help physicians in their daily decision-making processes.

The thesis is published in the Digital Collection of TalTech Library.

Supervisor Prof. Sadok Ben Yahia and co-supervisor Prof. Nédra Mellouli-Nauwynck.

Oponents:

• Prof. Vannary Meas-Yedid Hardy, Institut Pasteur-Paris, France;
• Prof. Henning Christiansen, Roskilde University, Denmark.

Mahtab Shahin, the PhD student of the Department of Software Science, defended her PhD thesis „Efficient and Effective Association Rule Mining on Big Data and Cloud Technology: A Multifaceted Analysis“ on September 27, 2024 in room ICT-638 (Akadeemia tee 15a, ICT building of TalTech) and was also followed via Zoom.

The PhD thesis titled "Association Rule Mining in High-Performance Computing: A Comparative Study of Apollo-ARM and Distributed Techniques" by Mahtab Shahin investigates the application of association rule mining algorithms across domains like healthcare, meteorology, and transportation. It evaluates the performance, efficiency, and scalability of the Apollo-ARM algorithm compared to distributed association rule mining techniques in high-performance computing (HPC) environments.

The research focuses on the efficiency of Apollo-ARM in uncovering meaningful associations that drive decision-making in various fields. In healthcare, the algorithm identifies significant associations between patient attributes and disease outcomes, improving clinical decision-making and personalized treatment.

In meteorology, the study explores correlations between climate variables, uncovering hidden patterns for improved weather prediction and climate change studies. The transportation domain analysis reveals associations influencing traffic accidents, informing data-driven strategies for road safety.

Comparing Apollo-ARM with distributed techniques, Apollo-ARM outperformed in speed, scalability, and resource utilization, particularly in environments with limited computational resources. While distributed methods improve with more nodes, Apollo-ARM proves more efficient overall, especially where hardware scaling isn't feasible.

Mahtab Shahin’s research offers valuable insights into association rule mining applications across multiple sectors, demonstrating Apollo-ARM’s robust and scalable approach for extracting patterns from large datasets.

The thesis "Efficient and Effective Association Rule Mining on Big Data and Cloud Technology: A Multifaceted Analysis" is published in the Digital Collection of TalTech Library.

Supervisors:

• Prof. Dirk Draheim, Tallinn University of Technology, Estonia;
• Dr. Tara Ghasempouri, Tallinn University of Technology, Estonia;
• Dr. Syed Attique Shah, Birmingham City University, United Kingdom.

Oponents:

• Prof. Tania Cerquitelli, Politecnico di Torino, Italy;
• Prof. Arun Kumar Sangaiah, National Yunlin University of Science and Technology, Taiwan.

Richard Michael Dreyling III defended his PhD thesis "Digital Transformation: Artificial Intelligence Enablement in Public Services" on September 25, 2024 in room ICT-638 (Akadeemia tee 15a, ICT building of TalTech) and was also followed via Zoom.

The PhD thesis titled "Digital Transformation: Artificial Intelligence Enablement in Public Services" by Richard Michael Dreyling III examines the adoption of artificial intelligence (AI) within public services, with a particular focus on Estonia's pioneering efforts. The thesis explores digital transformation from multiple perspectives—technical, organizational, legal, and social—and aims to provide both academic insights and practical guidance for decision-makers in government sectors contemplating AI adoption.

Estonia, renowned for its e-governance systems, is developing an AI-enabled platform known as "Bürokratt," designed to facilitate the interaction between citizens and the government through chatbots and virtual assistants. Bürokratt represents Estonia's vision of AI-driven public services, with its core goal being the integration of AI into over 3,000 digital services provided by the government. The research investigates the challenges and steps involved in transforming traditional public services into AI-enabled systems. It discusses the importance of pre-existing digital infrastructures, such as Estonia’s X-Road, which enables data exchange across public and private sectors, and highlights the importance of leadership that embraces experimentation and innovation.

The thesis covers several critical themes: the importance of an organizational readiness assessment before embarking on AI projects, the legal and ethical implications of AI in public services, and the necessity for continuous evaluation and adaptation during AI implementation. The author emphasizes the need for a maturity model to evaluate public sector readiness for AI adoption, which would help governments anticipate challenges related to competence, technology integration, and social trust.

Dreyling’s work offers valuable insights into how public organizations can leverage digital transformation to adopt AI services, illustrating that successful AI implementation requires a blend of technical competence, organizational agility, and a clear strategic vision. His findings are not only relevant to Estonia but also applicable to any government or institution looking to navigate the complex process of AI enablement in public services. The thesis provides a framework for analyzing readiness and maturity, suggesting a path forward for public sector entities aiming to embrace the future of digital transformation through AI.

The thesis is published in the Digital Collection of TalTech Library.

Supervisors:

• Prof. Ingrid Pappel, TalTech, Estonia;
• co-supervisor Prof. Tanel Tammet, TalTech, Estonia.

Oponents:

• Prof. Mihkel Solvak, University of Tartu, Estonia;
• Prof. Anis Yazidi, Oslo Metropolitan University, Norway.

Antonio Carlo defended his PhD thesis "The Space-Cyber Nexus: Ensuring the Resilience, Security and Defence of Critical Infrastructure" in the Department of Software Science on June 20, 2024 in room ICT-315 (Akadeemia tee 15a, ICT building of TalTech) and was also followed via Zoom.

Nathan Joseph Haydon defended his PhD thesis "Peirce’s Existential Graphs and the Logic of String Diagrams" on June 6, 2024 in room ICT-638 (Akadeemia tee 15a, ICT building of TalTech) and was also followed via Zoom.

Chahinez Ounoughi, the PhD student of the Department of Software Science, defended her PhD thesis "Urban Traffic: Data Fusion and Vehicle Flow Prediction in Smart Cities" on March 12, 2024 in room ICT-638 (Akadeemia tee 15a, ICT building of TalTech) and was also followed via Zoom.

Ph.D. thesis "Urban Traffic: Data Fusion and Vehicle Flow Prediction in Smart Cities" proposes a holistic solution to urban traffic congestion, promising significant improvements in traffic prediction and management efficiency, utilizing advanced deep-learning architecture and data fusion techniques. 

The research introduces four critical contributions to traffic management and Intelligent Transportation Systems (ITS). The first contribution presents a highly efficient hybrid deep neural network solution in terms of time while maintaining high accuracy in predicting traffic speeds within road segments. This method streamlines the process of identifying congestion-prone areas, allowing timely interventions to manage traffic flow effectively.

Once congestion is detected, it is essential to alleviate congestion and improve traffic flow. The second contribution proposes an enhanced, sustainable, and proactive traffic signal control system driven by noise prediction in response to this need. By integrating sustainability considerations and proactive decision-making, this innovative method optimizes traffic signals to reduce congestion and enhance overall traffic management efficiency.

To harness the wealth of available traffic data, the third contribution delves into a systematic exploration of data fusion techniques within the realm of Intelligent Transportation Systems (ITS). This comprehensive review identifies methodologies that effectively integrate data from various sources. 

The fourth contribution introduces an innovative data fusion technique that integrates features from both traffic and environmental sensors. This integration represents a significant advancement, as it enriches the precision of traffic prediction models and enables well-informed decisions in traffic light management. By dynamically adjusting signal timings based on real-time traffic conditions and predicted congestion levels, this approach optimizes traffic flow and contributes to the effective management of urban transportation systems. The author argues that these contributions offer valuable insights for transportation planning and policymaking, ultimately enhancing urban citizens' quality of life and the operational efficiency of transportation systems.

The thesis is published in the Digital Collection of TalTech Library.

Supervisor: Prof. Sadok Ben Yahia, TalTech.

Oponents:

• Ass. Prof. Mahdi Zargayouna, University Gustave Eiffel, France;
• Prof. Mauro Vallati, University of Huddersfield, Great Britain.

Minakshi Kaushik, the PhD student of the Department of Software Science, defended her PhD thesis "Generalized Association Rule Mining – Dimensional Unsupervised Learning" on February 15, 2024 in room ICT-315 (Akadeemia tee 15a, ICT building of TalTech) and was also followed via Zoom.

Chad Mitchell Nester, the PhD student of the Department of Software Science, defended his PhD thesis "Partial and Relational Algebraic Theories" on February 1, 2024 in room ICT-638 (Akadeemia tee 15a, ICT building of TalTech) and was also followed via Zoom.

Sidra Azmat Butt defended her PhD thesis "A Digital Collaborative Platform to Facilitate Innovative Solutions for the Silver Economy" on Thursday, December 14, 2023 at 14:00 in room ICT-315 and via Zoom.

As the world’s population ages, empowering the silver generation to participate in economic activities becomes highly imperative. This thesis investigates the integration of Information and Communication Technology (ICT) into the silver economy, scrutinizing technology readiness, knowledge resources, and ethical ramifications related to ICT adoption among silver generation. 
The thesis identifies barriers and challenges faced by the silver generation toward ICT adoption, and to overcome these challenges, a design science approach led to the creation of the Digital Silver Hub, a digital collaborative platform. Utilizing the generic Collective Intelligence (CI) framework, the co-creation process engaged quadruple helix actors from the Baltic Sea Region, tailoring the platform to the unique needs of each actor, especially the two age groups within the silver population, those aged 55-65 and those aged 65 and over. 
The development process involved rigorous research for requirement elicitation, expert validation, and comprehensive analysis through various qualitative research methods. System interactions were mapped out through user dialogue models, customer journeys were detailed, web implementation with basic features of the platforms was developed, and wireframes of the platform were constructed. The platform underwent thorough evaluation, ensuring alignment with stakeholder goals and adherence to user-centred evaluation principles outlined in ISO 9241-210. 
The Digital Silver Hub serves as an ecosystem to develop and accelerate the uptake of innovative solutions to the challenges faced by the silver generation. The findings of this study have important implications for policymakers, industry experts, and service providers involved in designing and implementing ICT solutions for the silver generation. The Digital Silver Hub serves as a template for other digital platforms targeting the silver generation. The primary objective is to enhance participation and encourage social and digital inclusion of the silver population. By linking theory with practical applications, this research contributes to the applicability and influence of ICT solutions, leading to the growth of the silver economy.

Supervisors: Prof. Dr. Dirk Draheim (Tallinn University of Technology) and co-supervisor: Assoc.-Prof. Dr. Ingrid Pappel (Tallinn University of Technology).

Opponents:

• Professor Il-Yeol Song, PhD, Drexel University, Philadelphia, United States of America;
• Doc. Dr. Tina Jukić, University of Ljubljana, Ljubljana, Slovenia.

The thesis is published in the Digital Collection of TalTech Library.

Elena Di Lavore defended her PhD thesis "Monoidal Width" on Friday, November 17, 2023 at 14:00 in room ICT-638 and via Zoom.

Compositionality lies at the core of abstraction: local windows on a problem can be combined into a global understanding of it; models and code can be written so that parts can be reused or replaced without breaking the whole; problems can be solved by combining partial solutions. Compositionality may give algorithmic advantages as well. This is the case of divide-and-conquer algorithms, which use the compositional structure of problems to solve them efficiently. Courcelle's theorems are a remarkable example. They rely on a divide-and-conquer algorithm to show that checking monadic second order formulae is tractable on graphs of bounded tree or clique width.

The idea behind fixed-parameter tractability results of this kind is that divide-and-conquer algorithms are efficient on inputs that are structurally simple. In the case of graphs, tree and clique widths measure their structural complexity. When a graph has low width, combining partial solutions on it is tractable. This work aims to bring the techniques from parametrised complexity to monoidal categories.

This thesis introduces monoidal width to measure the structural complexity of morphisms in monoidal categories and investigates some of its properties. By choosing suitable categorical algebras, monoidal width captures tree width and clique width. Monoidal width relies on monoidal decompositions in the same way graph widths rely on graph decompositions and graph expressions. Monoidal decompositions are terms in the language of monoidal categories that specify the compositional structure needed by divide-and-conquer algorithms. A general strategy to obtain fixed-parameter tractability results for problems on monoidal categories highlights the conceptual importance of monoidal width: compositional algorithms make functorial problems tractable on morphisms of bounded monoidal width.

Supervisor: prof Pawel Maria Sobocinski.

Opponents:

• prof Samson Abramsky, University College London, UK;
• prof Dan Marsden, University of Nottingham, UK.

The thesis is published in the Digital Collection of TalTech Library.

Mario Román García defended his PhD thesis „Monoidal Context Theory“ on Thursday, November  16, 2023 in room ICT-638 and via Zoom.

The mathematical description of processes is a relatively new branch of mathematics: we use diagrams to depict electrical networks, flowcharts or algorithms, but a unified mathematical formalism for these diagrams was only proposed in the 1970s, with category theory.

However, in a complex electrical network, or a complex intelligent system, we may not know how some of the components work - some components are only "black boxes". This thesis studies how diagrams with black boxes can be also given a mathematical description.

As a result of this thesis, we can develop a graphical programming language (where programs are diagrams!) and implement the language with multiple backends (e.g. a probabilistic version, or a concurrent version).

Supervisor: prof Pawel Maria Sobocinski.

Opponents: 

• Guy McCusker, Professor of Computer Science, University of Bath, United Kingdom;
• Paul Andre Mellies, CNRS Researcher, Université Paris Denis Diderot, France.

The thesis is published in the Digital Collection of TalTech Library.

Rahul Sharma defended his PhD thesis "Unification of Decision Support Techniques: Mitigating Statistical Paradoxes for Enabling Trustworthy Decision Making" on Monday, October 30, 2023 at 15:00 in room ICT-638 and via Zoom.

The PhD thesis is all about improving decision-making tools that are used in various fields. The author has created a framework to make these tools more reliable and effective and discussed various ways to handle statistical paradoxes in machine learning.

This doctoral thesis provides six significant contributions to address existing technological and knowledge gaps to foster fair and trustworthy decision-making processes. These contributions are the outcomes of two primary research questions and six supplementary research questions answered within the thesis. The thesis utilizes design science research methodology to create innovative artifacts and methods, providing new insights to widen understanding of the domain under the research.

The first contribution provides ways to establish semantic correspondence between the three major decision support techniques, i.e., statistical reasoning, online analytical processing and association rule mining. It examines various approaches to bridge the gap between them. The second contribution is a novel framework for unifying decision-support techniques for developing a unified platform to interpret results from one DST (Desicion Support Technique) to another. The third contribution discusses two measures for identifying confounding effects in categorical and continuous datasets. The fourth contribution discusses the measure for adjusting the confounding effects. Further, the fifth contribution provides a framework for mitigating the impact of bias resulting from statistical paradoxes. The sixth contribution is a web-based application that automatically detects and addresses confounding effects. This application is an invaluable tool for data scientists and researchers, offering automated detection and mitigation of confounding effects and providing a streamlined approach to effectively addressing and overcoming such data analysis challenges. The author argues that the suggested framework and application possess substantial potential for further extensions beyond their current scope of application.

Supervisor: Prof Dirk Draheim.

Opponents:

• Divesh Srivastava, PhD, Head of AT&T Labs, New Jersey, USA;
• prof Ladjel Bellatreche, ISAE-ENSMA, Poitiers, France.

The thesis is published in the Digital Collection of TalTech Library.

Vjatšeslav Škiparev defended his PhD thesis „Virtual Inertia Control of Microgrids Using Deep Reinforcement Learning Methods“ on Thursday, September 14, 2023 at 15:30 in room ICT-638 and via Zoom.

Environmental problem arising from the global warming are motivating evolution of the power infrastructure by increasing the deployment of variable renewable energy technologies such as wind turbines and solar panels. This approach holds the promise of reducing CO2 emissions and facilitating a transition toward a sustainable future. On the other hand, the massive integration of variable renewable energy sources has led to a decline in the overall rotational inertia in the power grid, making it more susceptible and reliant on meteorological fluctuations. To counterbalance the lack of mechanical inertia, certain researchers have proposed emulating virtual inertia. The effective implementation of this concept necessitates development of a more robust and flexible control algorithms. This thesis proposes a hybrid solution that amalgamates the advantages of both paradigms – AI and classical PID controller. Specifically, it combines the adaptability inherent to neural networks with the robustness characteristic of classical controllers. Supported by deep reinforcement learning techniques, the proposed controller can acquire insights into system dynamics through a data-driven approach and can even be employed for coordinated or multi-node control strategies. Computational intelligence harbors considerable potential for emerging power systems in which renewable energy sources are dominant.

Supervisors:

• prof Juri Belikov;
• co-supervisor:  prof Eduard Petlenkov.

Opponents:

• prof Gaber Magdy (Aswan University, Aswan, Egypt);
• prof João Martins (Nova University of Lisbon, Caparica, Portugal).

The thesis is published in the Digital Collection of TalTech Library.

Silvia Lips defended her PhD thesis „A Multifaceted Assessment Framework for Electronic Identity Schemes“ on Monday, September 4, 2023 at 15:00 in room ICT-638 and via Zoom.

In order for society to function effectively, reliable personal identification of people at any point in time is essential, and the physical and electronic identity of the person needs to be uniquely linked. In Estonia, the uniqueness of identity is ensured through the personal identification code, and there are different ways to prove identity in both the physical and digital worlds. More and more members of society want to use the services offered by other European countries, which requires a cross-border user-friendly, and interoperable personal identification solution. In order to use the electronic identity (eID) tools of different countries across the borders in the EEA, each country must notify its eID scheme for cross-border use according to the European Union regulation on trust services required for e-identification and e-transactions in the internal market (eIDAS). The eID scheme can be notified at ’low’, ’substantial’, and ’high’ levels.

Unfortunately, the current eID scheme notification procedure at the EU level is excessively complex in practice, and therefore the cross-border usability of eIDs is relatively modest. In addition, member states use solutions with different levels of security, and it is difficult to compare solutions with the same level. All this adds additional complexity to the eID schemes notification process, makes it difficult for the interoperable use of eID schemes, and limits the provision of e-services in the EU.

The general framework for the eID schemes assessment proposed as a result of the Ph.D. thesis “A Multifaceted Assessment Framework for Electronic Identity Schemes” remarkably simplifies the eID schemes assessment process that enables the cross-border use of national eID schemes in Europe. Simply said, this means individuals can use the e-services of other European countries with the eID tools already issued by some EU member states.

On the other hand, it is possible to ensure access to e-services offered by a specific member state (for example, Estonia) with the eID means of European countries that have undergone the corresponding notification procedure. Considering the limited size of the Estonian domestic market, an effectively functioning interoperable framework of eIDs creates good prerequisites for developing new digital services and the general development of the Estonian economy.

However, the doctoral thesis focuses on more than just European countries. It deals with the recognition of eID schemes more broadly, proposing a general model for cross-national recognition of eID schemes. The aim is to enable the cross-border use of eID means of the same level between any two countries. This research results propose a framework that enables recognizing of the eID schemes of countries outside the European Economic Area and further revitalizing the economic environment.

Supervisors:

• prof Dirk Draheim (TalTech);
• co-supervisor: prof Ingrid Pappel (TalTech);
• co-supervisor: prof Robert Krimmer (University of Tartu).

Opponents:

• prof Marijn Janssen (Delft University of Technology, Delft, the Netherlands);
• prof Gabriele Kotsis (Johannes Kepler University Linz, Linz, Austria).

The thesis is published in the Digital Collection of TalTech Library.

Kaur Kullman defended his PhD thesis „Interactive Stereoscopically Perceivable Multidimensional Data Visualizations for Cybersecurity“ on Tuesdays, April 25, 2023 at 15.00 in room ICT-315.

Supervisors:

• Professor Olaf Manuel Maennel, The University of Adelaide, Adelaide, Australia;
• Professor Don Engel, University of Maryland, Baltimore, Maryland, USA;
• Professor Stefan Sütterlin, Tallinn University of Technology, Tallinn, Estonia.

Opponents:

• Dr Alexander Kott, U.S. Army Research Laboratory, Adelphi, Maryland, USA;
• Dr Simon Su, National Institute of Standards and Technology, Gaithersburg, Maryland, USA;
• Dr Matthew, The University of Adelaide, Adelaide, Australia.

The thesis is published in the Digital Collection of TalTech Library.

Rozha Kamal Ahmed defended her PhD thesis "Digital Transformation of Court Processes: Driving Forces, Success Factors, Regulations and Technology Acceptance" on Friday, March 31, 2023 at 15:00 in room ICT-315 and via Zoom.

This thesis presents nine publications outlining the implementation of an e-court system in the Kurdistan Region of Iraq (KRI). In the context of design science, the publications demonstrate the development and evaluation activities undertaken to implement an e-court system.  
The results found significant improvements in court processes, analyzed drivers and barriers that affect implementation success, assessed user satisfaction with the new system and their perspective on change management, and proposed a new legal framework to support the successful implementation of a fully paperless e-court system. 
This e-court system, which has been introduced as the first pilot e-service in the justice sector of the KRI, has significantly contributed to the enhancement of the court's organizational performance through the improvement of internal administrative processes and the promotion of better justice services to citizens.

Supervisors:

• prof. Dirk Draheim, Tallinn University of Technology;
• co-supervisor prof. Ingrid Pappel, Tallinn University of Technology;
• co-supervisor Dr. Aleksander Reitsakas, Aktors OÜ, Tallinn.

Opponents:

• prof. Nitesh Bharosa, Delft University of Technology, Netherlands;
• prof. Josef Küng, Johannes Kepler University Linz, Austria.

The thesis is published in the Digital Collection of TalTech Library.

Alejandro Guerra Menzanares defended his PhD thesis "Machine Learning-Based Detection and Characterization of Evolving Threats in Mobile and IoT Systems" on Thursday, Sept 1, 2022 at 14:00 in room ICT-315 and via Zoom.

This dissertation explores the application of machine learning methods to overcome the present challenges that affect two significant research areas in the cyber security domain: Android malware detection and Internet of Things (IoT) botnet detection. For Android malware detection, concept drift and cross-device detection issues are thoroughly explored, whereas, in the IoT domain, the impact of feature selection for attack detection systems and the feasibility of early IoT botnet detection are investigated.

Supervisors:

• prof. Hayretdin Bahsi, Tallinn University of Technology;
• co-supervisor: Senior Researcher Sven Nõmm, Tallinn University of Technology;
• co-supervisor: prof. Marcin Luckner, Warsaw University of Technology, Poland.

Opponents:

• prof. dr. Juan Manuel Corchado Rodriguez, University of Salamanca, Spain;

prof. dr. Ali Akbar Ghorbani, University of New Brunswick, Canada.

The thesis is published in the Digital Collection of TalTech Library.

Vishwajeet Pattanaik defended his PhD thesis „Robust Web Annotations in Support of Knowledge Co-Creation“ on Wednesday, July 27, 2022 at 13:00 via zoom and at room ICT-638.

Supervisor:

• Prof. Dr. Dirk Draheim, Tallinn University of Technology.

Opponents:

• Prof. Dr. Peter Thiemann, University of Freiburg, Germany;
• Assoc.-Prof. Dr. Ismail Khalil, Johannes Kepler University Linz, Austria.

The thesis is published in the Digital Collection of TalTech Library.

Shweta Suran defended her PhD thesis "A Generic Framework for Collective Intelligence Systems" on Thursday, May 26, 2022 at 14:00 via zoom and at room ICT-315.

Empowered by advancements in social media technologies, Collective Intelligence (CI) systems in recent decades have enabled effective and efficient mobilization and utilization of the skills and knowledge of crowds over the web. Unfortunately, even with the plethora of CI solutions available on the web, the development of CI systems remains an exhaustive and costly venture. Literature suggests that this is because there is a fundamental gap in our understanding of CI systems in general. This work addresses this gap, through a first of its kind ‘generic’ CI framework and model, designed to empower researchers, developers, and stakeholders by enabling them to better understand existing and develop new CI platforms.

Supervisors:

• Prof. Dr. Dirk Draheim, Tallinn University of Technology;
• co-supervisor: Assoc.-Prof. Dr. Ingrid Pappel, Tallinn University of Technology;
• co-supervisor: Assoc.-Prof. Dr. Alexander Norta, Tallinn University of Technology.

Opponents:

• Prof. Dr. Gerhard Schwabe, Department of Informatics, University of Zurich Zurich, Switzerland;
• Prof. Dr. Anna De Liddo, Knowledge Media Institute, The Open University Milton Keynes, United Kingdom.

The thesis is published in the Digital Collection of TalTech Library.

Vimal Kumar Dwivedi defended his PhD thesis „A Legally Relevant Socio-Technical Language Development for Smart Contracts“ on Wednesday, May 25, 2022 at 13:00 via Zoom.

This thesis develops a new smart contract choreography language that comprises the legally binding and collaborative business contractual properties. The main artifacts developed in this thesis are a novel framework for designing SCLs, SCL ontology, a workflow model in the CPN tool, and finally an XML-based Smart-Legal Contract Markup (SLCML) language. The proposed framework can be used to improve current state-of-the-art SCLs to make them legally binding, as well as for developing novel SCLs. The proposed SCL ontology is general in nature and can be used to configure contractual properties for a variety of other blockchains and SC applications, such as Defi ecosystems. Although the thesis develops the SLCML for a specific business-to-business use case, the approach used in SLCML development could be applied to SCL development for other blockchain applications.

Supervisors:

• dots. dr. Alex Norta, Tallinn University of Technology;
• co-supervisor: prof. dr. Dirk Draheim, Tallinn University of Technology.

Opponents:

• prof. Ingo Weber (PhD), Technische Universitaet Berlin, Germany;
• prof. Ulf Bodin (PhD), Luleå University of Technology, Sweden.

The thesis is published in the Digital Collection of TalTech Library. 

Valentyna Tsap defended her PhD thesis "eID Public Acceptance: Success Factors, Citizen Perception, and Impact of Electronic Identity" on Wednesday, May 18, 2022 at 12:00 in , room ICT-315 and via Zoom

The thesis is the first comprehensive study on eID public acceptance. The goal of the thesis is to unfold and examine how and why public acceptance of eID impacts the success of e-government. A case study of the Estonian eID is conducted. In the process of research, eID public acceptance factors are defined and utilized further to interpret, and understand the Estonian citizens’ perceptions of, and attitudes towards eID. The findings are validated through in-depth interviews with the top experts in the field, who explain and report on the importance of eID public acceptance in the overall success of e-government. Using an institutional design analysis framework, eID public acceptance is presented as a crucial part of a large-scale information e-government system.

Supervisors:

• prof. dr. Dirk Draheim, Tallinn University of Technology;
• co-supervisor: dots. dr. Ingrid Pappel, Tallinn University of Technology.

Opponents:

• prof. dr. Robert Krimmer, University of Tartu;
• prof. dr. Nitesh Bharosa, Delft University of Technology, the Netherlands.

The thesis is published in the Digital Collection of TalTech Library

Tiia Sõmer defended her PhD thesis "Modelling Financially Motivated Cyber Crime" on Tuesday, May 3, 2022 at 15:00 via Zoom.

Cyber crime is a relatively new area of academic research, and has led to both theoretical and practical interest in the subject. Researchers agree in general on the scope and scale of cyber crime and acknowledge the extent of the problem. This thesis is based on a collection of published and cited publications that explore cyber crime, related definitions and taxonomies. It proposes a definition and taxonomy to map financially motivated cyber crime, and introduces a Criminal JMAP model to provide understanding of financially motivated cyber crime as a process.

Supervisors:

• Rain Ottis, Tenured Associate Professor, Tallinn University of Technology;
• Co-supervisor: Dr Patrick Voss de Haan, Bundeskriminalamt, Germany.

Opponents:

• Dr Hervé Borrion, Associate Professor - Deputy Head of Department, University College London / UCL Department of Security and Crime Science, UCL Jill Dando Institute of Security and Crime Science;
• Dr Matti Näsi, University Lecturer, Criminology, Institute of Criminology and Legal Policy, University of Helsinki.

The thesis is published in the Digital Collection of TalTech Library.

Mauno Pihelgas defended his PhD thesis "Automating Defences against Cyber Operations in Computer Networks" on Wednesday, Aug 11, 2021 at 10 AM via Zoom.

This thesis explores the improvement of organisational security monitoring capability and readiness to advance towards intelligent autonomous cyber defence systems.
Additionally, the thesis aims to reduce the gap between suggestions derived from academic research and practical guidelines that are useful for cyber defenders. The feasibility of utilising theoretical research outcomes in practice has been criticised in related publications by several different authors. To relieve this issue, this thesis and the bundled collection of publications provide numerous actionable recommendations and practical examples.

Supervisors Senior Research Scientist Risto Vaarandi and Prof. Olaf Manuel Maennel (Tallinn University of Technology).

Opponents:

• Prof. Jan Vykopal (Masaryk University, Brno, Czech Republic)
• Prof. Anja Feldmann (Max Planck Institute for Informatics, Saarbrücken, Germany)

The PhD thesis is available in Tallinn University of Technology digital library.

Kaie Maennel defended her PhD thesis "Consolidation of Crowd-Sourced Geo-Tagged Data for Parameterized Travel Recommendations" on Thursday, May 27, 2021 at 12 noon via zoom.

The study focuses on novel aspects of incorporating LA as an evidence-based approach within CSXs and trainings. As CSXs come in a variety of formats, this thesis focuses on technical exercises with both individual and team-based designs. Collecting data from the technical exercises (which forms the basis for LA) is a computer science problem and requires good understanding of the technical aspects of the exercises. However, interdisciplinary approach combining knowledge from cybersecurity, pedagogy and psychology is needed to achieve effective application of LA in cybersecurity education.
The overall contribution of this research is a practical LA approach and theoretical methods for the CSXs and/or awareness/hygiene training that have been implemented at several training platforms and audiences, i.e., LS/XS, Rangeforce, TalTech students. By implementing and incorporating evidence based learning analytics methods and measurements into the cybersecurity exercises, the cybersecurity community can establish more evidence-based and systematic approach for evaluation of learning impact that will enable designing more eective learning experiences. This work is ongoing, and several research gaps and further work is proposed to advance research in LA and CSXs.

Supervisor: Supervisor: Professor Dr Rain Ottis, Department of Software Science, School of Information Technologies, Tallinn University of Technology, Tallinn, Estonia

Co-supervisor: Professor Dr Stefan Sütterlin, Faculty of Computer Science, Albstadt-Sigmaringen University, Sigmaringen, Germany

Opponents:

• Professor Dr Nickolas Falkner, University of Adelaide, Adelaide, Australia
• Professor Dr Cornelius König, Saarland University, Saarbrücken, Germany

The PhD thesis is available in Tallinn University of Technology digital library.

Ago Luberg defended his PhD thesis "Consolidation of Crowd-Sourced Geo-Tagged Data for Parameterized Travel Recommendations" on Thursday, May 27, 2021 at 12 noon via zoom.

The research covered in this thesis is focused on different aspects of the task of creating automated recommendations for tourism, focusing mostly on places of interest like beautiful views, architectural landmarks, charming areas etc.
A significant amount of work has been spent on designing and developing actual recommender systems - Sightsplanner, Sightsmap and the automated recommender of Visit Estonia - and their data harvesting methods in order to create a platform for showing the feasibility of the new methods designed and experimented with.

Supervisor Professor Tanel Tammet (Tallinn University of Technology).

Opponents:

• Dr. Chiara Renso, Senior Researcher at ISTI-CNR, Pisa, Tuscany, Italy
• Dr. Wolfgang Wörndl, Technical University of Munich, München, Germany

The PhD thesis is available in Tallinn University of Technology digital library.

Sten Mäses Evaluating Cybersecurity-Related Competences through Simulation Exercises
16.12.2020 at 9 AM in ICT-411 and via zoom
Supervisor: Prof. Olaf Manuel Maennel, Liina Randmann (Tallinn University of Technology), and Prof. Stefan Sütterlin (Østfold University College, Norway)
Opponents: Prof Nickolas Falkner (University of Adelaide, Australia) and Prof Petri Ihantola (University of Helsinki, Finland)
more...

Deepak Pal Model Based Test Generation for Distributed Systems
10.12.2020 at 2 PM in ICT-411 and via zoom
Supervisor: Prof. Jüri Vain
Opponents: Prof Johan Lilius (Åbo Akademi University, Finland) and Artem Boyarchuk (KhAI - Aerospace University, Kiiev, Ukraine)
more...

Anton Vedešin Smart Cyber-Physical System for Personal Manufacturing
7.12.2020 at 11 AM in ICT-315 and via zoom
Supervisors: Assoc. Prof. Innar Liiv and Prof. Dirk Draheim
Opponents: Prof. Dieter Kranzlmüller (Ludwig-Maximilians University of Munich, Germany) Prof. Josef Küng (Johannes Kepler University Linz, Austria)
more...

Jaanus Kaugerand Mediated Interactions for Collection and Exchange of Situational Information in Smart Environments
18.08.2020 at 10 AM in U05-210 and via zoom
Supervisor: Jürgo-Sören Preden, PhD
Opponents: Prof Michael Henshaw (Loughborough University, UK) and Senior Researcher Gabriel Jakobson (CyberGem Consulting, USA)
more...

Gert Kanter Model-Based Testing Framework for Autonomous Multi-Robot Systems
03.07.2020 at 10 AM in ICT-315 and via zoom
Supervisor: Prof. Jüri Vain
Opponents: Senior Lecturer Anatoliy Gorbenko (Leeds Beckett University, UK) and Senior Lecturer Dragos Truscan (Åbo Akademi University, Turku, Finland)
more...

Hendrik Maarand Operational Semantics of Weak Sequential Composition
26.06.2020 at 10 AM in ICT-507 A/B and via zoom
Supervisor: Lead Research Scientist Tarmo Uustalu
Opponents: Senior Lecturer Brijesh Dongol (Univ. of Surrey, UK) and Professor Peter Thiemann (Univ of Freiburg, Germany)
more...

Ahto Truu Hash-Based Server-Assisted Digital Signature Solutions
28.05.2020 at 2:30 PM in ICT-315
Supervisor: Prof. Ahto Buldas
Opponents: Ass. Prof. Andreas Hülsing (Eindhoven Univ. of Technology, Netherlands) Dr. Elena Andreeva (Catholic Univ. of Leuven, Belgium)

Priit Järv Place Recommendation with Geo-tagged Photos
24.03.2020 at 10 AM in ICT-638
Supervisor: Prof. Tanel Tammet
Opponents: Professor Francesco Ricci (Free University of Bozen-Bolzano, Italy) and Professor Christian S. Jensen (University of Aalborg, Denmark)
First online defended PhD in Taltech.