Högskolan i Skövde

Accelerating Digital Transformation with the Cloud and the Internet of Things (IoT) is a reference for IT engineers and decision-makers who may engage in IoT platform pilot projects. The resources covered in this book help establish plans for sustainable operations and management and assist with the long-term procurement of relevant IoT technologies. The aim of the book is to be exhaustive and holistic by pointing out numerous issues and related solution options that guide with daily challenges when deploying and running IoT platforms.

The book is divided into three parts where each part includes relevant theoretical chapters and applied case studies. Part One focuses on architectural and federation options for the design and implementation of IoT platforms that foster strategic collaboration opportunities. Part Two addresses vertical security challenges across IoT platform layers. Finally, Part Three shows how IoT is driving the digital transformation wheel through existing and forthcoming case studies.

This paper presents a hybrid machine learning framework to enhance traffic safety in urban road intersections. The framework employs a two-stage approach: Decision Trees predict vehicle trajectories by identifying turning behaviors, while Random Forests estimate collision probabilities involving vehicles and vulnerable road users (VRUs) such as pedestrians and cyclists. Engineered spatial, temporal, and motion-related features are derived from high-resolution trajectory data collected via connected camera systems in busy urban cores. The experimental results demonstrate high predictive accuracy, achieving an F1-Score of 0.97 for turning vehicle classification and a ROC-AUC of 0.98 for collision risk estimation. Compared to computationally intensive deep learning models, the proposed framework balances robust performance with computational efficiency, making it suitable for realtime deployment in complex urban environments. The framework integrates with in-vehicle Human-Machine Interfaces (HMIs) to enhance driver awareness and enable proactive safety interventions. This study addresses the need for interpretable and scalable road safety solutions in connected traffic systems.

The metaverse presents a new opportunity to construct personalized learning paths and to promote practices that scale the development of future skills and collective intelligence. The attitudes, knowledge and skills that are necessary to face the challenges of the 21st century should be developed through iterative cycles of continuous learning, where learners are enabled to experience, reflect, and produce new ideas while participating in a collective creativity process. In this paper, we propose an architecture to develop a metaverse-intensive learning experience (MiLEx) platform with an illustrative scenario that reinforces the development of 21st century career practices and collective intelligence. The learning ecosystem of MiLEx integrates four key elements: (1) key players that define the main actors and their roles in the learning process; (2) a learning context that defines the learning space and the networks of expected interactions among human and non-human objects; (3) experiential learning instances that deliver education via a real-life–virtual merge; and (4) technology support for building practice communities online, developing experiential cycles and transforming knowledge between human and non-human objects within the community. The proposed MiLEx architecture incorporates sets of technological and data components to (1) discover/profile learners and design learner-centric, theoretically grounded and immersive learning experiences; (2) create elements and experiential learning scenarios; (3) analyze learner’s interactive and behavioral patterns; (4) support the emergence of collective intelligence; (5) assess learning outcomes and monitor the learner’s maturity process; and (6) evaluate experienced learning and recommend future experiences. We also present the MiLEx continuum as a cyclic flow of information to promote immersive learning. Finally, we discuss some open issues to increase the learning value and propose some future work suggestions to further shape the transformative potential of metaverse-based learning environments.

Despite their wide proliferation, complex cyber–physical systems (CPSs) are subject to cybersecurity vulnerabilities and potential attacks. Vulnerability assessment for such complex systems are challenging, partly due to the discrepancy among mechanisms used to evaluate their cyber-security weakness levels. Several sources do report these weaknesses like the National Vulnerability Database (NVD), as well as manufacturer websites besides other security scanning advisories such as Cyber Emergency Response Team (CERT) and Shodan databases. However, these multiple sources are found to face inconsistency issues, especially in terms of vulnerability severity scores. We advocate an artificial intelligence based approach to streamline the computation of vulnerability severity magnitudes. This approach decreases the error rate induced by manual calculation processes, that are traditionally used in cybersecurity analysis. Popular repositories such as NVD and SecurityFocus are employed to validate the proposed approach, assisted with a query method to retrieve vulnerability instances. In doing so, we report discovered correlations among reported vulnerability scores to infer consistent magnitude values of vulnerability instances. The method is applied to a case study featuring a CPS application to illustrate the automation of the proposed vulnerability scoring mechanism, used to mitigate cybersecurity weaknesses.

Dynamic data-driven vulnerability assessments face massive heterogeneous data contained in, and produced by SOCs (Security Operations Centres). Manual vulnerability assessment practices result in inaccurate data and induce complex analytical reasoning. Contemporary security repositories’ diversity, incompleteness and redundancy contribute to such security concerns. These issues are typical characteristics of public and manufacturer vulnerability reports, which exacerbate direct analysis to root out security deficiencies. Recent advances in machine learning techniques promise novel approaches to overcome these notorious diversity and incompleteness issues across massively increasing vulnerability reports corpora. Yet, these techniques themselves exhibit varying degrees of performance as a result of their diverse methods. We propose a cognitive cybersecurity approach that empowers human cognitive capital along two dimensions. We first resolve conflicting vulnerability reports and preprocess embedded security indicators into reliable data sets. Then, we use these data sets as a base for our proposed ensemble meta-classifier methods that fuse machine learning techniques to improve the predictive accuracy over individual machine learning algorithms. The application and implication of this methodology in the context of vulnerability analysis of computer systems are yet to unfold the full extent of its potential. The proposed cognitive security methodology in this paper is shown to improve performances when addressing the above-mentioned incompleteness and diversity issues across cybersecurity alert repositories. The experimental analysis conducted on actual cybersecurity data sources reveals interesting tradeoffs of our proposed selective ensemble methodology, to infer patterns of computer system vulnerabilities.

The development of systems that can generate automatically instructional material is a challenging goal for the e-learning community. These systems pave the way towards large scale e-learning deployment as they produce instruction on-demand for users requesting to learn about any topic, anywhere and anytime. However, realizing such systems is possible with the availability of vast repositories of web information in different formats that can be searched, reused and integrated into information-rich environments for interactive learning. This paradigm of learning relieves instructors from the tedious authoring task, making them focusing more on the design and quality of instruction. This paper presents a mobile learning system (Mole) that supports the generation of instructional material in M-Learning (Mobile Learning) contexts, by reusing and integrating heterogeneous hypermedia web resources. Mole uses open hypermedia repositories to build a Learning Web and to generate learning objects including various hypermedia resources that are adapted to the user context. Learning is delivered through a nice graphical user interface allowing the user to navigate conveniently while building their own learning path. A test case scenario illustrating Mole is presented along with a system evaluation which shows that in 90% of the cases Mole was able to generate learning objects that are related to the user query.

Within a community, social relationships are paramount to profile individuals’ conduct. For instance, an individual within a social network might be compelled to embrace a behaviour that his/her companion has recently adopted. Such social attitude is labelled social influence, which assesses the extent by which an individual’s social neighbourhood adopt that individual’s behaviour. We suggest an original approach to influence maximization using a fuzzy-logic based model, which combines influence-weights associated with historical logs of the social network users, and their favourable location in the network. Our approach uses a two-phases process to maximise influence diffusion. First, we harness the complexity of the problem by partitioning the network into significantly-enriched community-structures, which we then use as modules to locate the most influential nodes across the entire network. These key users are determined relatively to a fuzzy-logic based technique that identifies the most influential users, out of which the seed-set candidates to diffuse a behaviour or an innovation are extracted following the allocated budget for the influence campaign. This way to deal with influence propagation in social networks, is different from previous models, which do not compare structural and behavioural attributes among members of the network. The performance results show the validity of the proposed partitioning-approach of a social network into communities, and its contribution to “activate” a higher number of nodes overall. Our experimental study involves both empirical and real contemporary social-networks, whereby a smaller seed set of key users, is shown to scale influence to the high-end compared to some renowned techniques, which employ a larger seed set of key users and yet they influence less nodes in the social network.

Criticalmanufacturingprocessesinsmartnetworkedsystems such as Cyber-Physical Production Systems (CPPSs) typically require guaranteed quality-of-service performances, which is supported by cyber- security management. Currently, most existing vulnerability-assessment techniques mostly rely on only the security department due to limited communication between di↵erent working groups. This poses a limitation to the security management of CPPSs, as malicious operations may use new exploits that occur between successive analysis milestones or across departmental managerial boundaries. Thus, it is important to study and analyse CPPS networks’ security, in terms of vulnerability analysis that accounts for humans in the production process loop, to prevent potential threats to infiltrate through cross-layer gaps and to reduce the magnitude of their impact. We propose a semantic framework that supports the col- laboration between di↵erent actors in the production process, to improve situation awareness for cyberthreats prevention. Stakeholders with dif- ferent expertise are contributing to vulnerability assessment, which can be further combined with attack-scenario analysis to provide more prac- tical analysis. In doing so, we show through a case study evaluation how our proposed framework leverages crucial relationships between vulner- abilities, threats and attacks, in order to narrow further the risk-window induced by discoverable vulnerabilities.

Current vulnerability scoring mechanisms in complex cyber-physical systems (CPSs) face challenges induced by the proliferation of both component versions and recurring scoring-mechanism versions. Different data-repository sources like National Vulnerability Database (NVD), vendor websites as well as third party security tool analysers (e.g. ICS CERT and VulDB) may provide conflicting severity scores. We propose a machine-learning pipeline mechanism to compute vulnerability severity scores automatically. This method also discovers score correlations from established sources to infer and enhance the severity consistency of reported vulnerabilities. To evaluate our approach, we show through a CPS-based case study how our proposed scoring system automatically synthesises accurate scores for some vulnerability instances, to support remediation decision-making processes. In this case study, we also analyse the characteristics of CPS vulnerability instances. 

Cutting-edge sensors and devices are increasingly deployed within urban areas to make-up the fabric of transmission control protocol/internet protocol con- nectivity driven by Internet of Things (IoT). This immersion into physical urban environments creates new data streams, which could be exploited to deliver novel cloud-based services. Connected vehicles and road-infrastructure data are leveraged in this article to build applications that alleviate notorious parking and induced traffic-congestion issues. To optimize the utility of parking lots, our proposed SmartPark algorithm employs a discrete Markov-chain model to demystify the future state of a parking lot, by the time a vehicle is expected to reach it. The algorithm features three modular sections. First, a search pro- cess is triggered to identify the expected arrival-time periods to all parking lots in the targeted central business district (CBD) area. This process utilizes smart-pole data streams reporting congestion rates across parking area junc- tions. Then, a predictive analytics phase uses consolidated historical data about past parking dynamics to infer a state-transition matrix, showing the transfor- mation of available spots in a parking lot over short periods of time. Finally, this matrix is projected against similar future seasonal periods to figure out the actual vacancy-expectation of a lot. The performance evaluation over an actual busy CBD area in Stockholm (Sweden) shows increased scalability capa- bilities, when further parking resources are made available, compared to a baseline case algorithm. Using standard urban-mobility simulation packages, the traffic-congestion-aware SmartPark is also shown to minimize the journey duration to the selected parking lot while maximizing the chances to find an available spot at the selected lot.