This paper addresses the problem of hazard recognition and risk assessment in open and non-predictive environments to support decision making and action selection for UAS. Decision making and action selection incorporate decreasing situational risks and maintain safety as operational constraints. Commonly, neither existing safety standards nor the situation modeling or knowledge representation is considered in that context. This contribution applies a novel approach denoted as a Safety-Driven Behavior Management for UAS focusing on situation modeling, and the problem of knowledge representation in the context of situational risks. It combines the safety standards-oriented hazards analysis and the risk assessment approach with the machine learning-based situation recognition. The illustrative scenario and first experimental results underline the feasibility of the novel approach.

Indoor positioning is important for applications within Internet of Things, such as equipment tracking and indoor maps. Inexpensive Bluetooth-beacons have become common for such applications, where the distance is estimated using the Received Signal Strength. Large installations require substantial efforts, either in determining the exact location of all beacons to facilitate lateration, or collecting signal strength data from a grid over all locations to facilitate fingerprinting. To reduce this initial setup cost, one may infer the positions using Simultaneous Location and Mapping. In this paper, we use a mobile phone equipped with an Inertial Measurement Unit, a Bluetooth receiver, and an Unscented Kalman Filter to infer beacon positions. Further, we apply adaptive noise modeling in the filter based on the estimated distance of the beacons, in contrast to using a fixed noise estimate which is the common approach. This gives us more granular control of how much impact each signal strength reading has on the position estimates. The adaptive model decreases the beacon positioning errors by 27% and the user positioning errors by 21%. The positioning accuracy is 0.3 m better compared to using known beacon positions with fixed noise, while the effort to setup and maintain the position of each beacon is also substantially reduced. Therefore, adaptive noise modeling of Received Signal Strength is a significant improvement over static noise modeling for indoor positioning.

The InvisibleAI (InvAI’20) workshop aims to systematically discuss a growing class of interactive systems that invisibly remove some decision-making tasks away from humans to machines, based on recent advances in artificial intelligence (AI), data science, and sensor or actuation technology. While the interest in the affordances as well as the risks of hidden pervasive AI are high on the agenda in public debate, discussion on the topic is needed within the human-computer interaction (HCI) community. In particular, we want to gather insights, ideas, and models for approaching the use of barely noticeable AI decision-making in systems design from a human-centered perspective, so as to make the most out of the automated systems and algorithms that support human activity both as designers and users. Concurrently, these systems should safeguard that humans remain in charge when it counts (high stakes decisions, privacy, monitoring lack of explainability and fairness, etc.). What to automate and what not to automate is often a system designer’s choice [8]. By taking the established concept of explicit interaction between a system and its user as a point of departure, and inviting authors to provide examples from their own research, we aim to stimulate dynamic discussion while keeping the workshop concrete and system design-focused. The workshop especially directs itself to participants from the interaction design, AI, and HCI communities. The targeted scientific outcome of the workshop is an up-to-date ontology of invisible AI-HCI systems and hybrid human-AI collaboration mechanisms, and approaches. Additionally, we expect that the workgroups and the roundtables will provide starting points shaping continued discussions, new collaborations, and innovative scientific contributions that springboard from the workgroups’ findings. The focus of the proposed workshop involves the bridging of two spaces of computational research that impact user experiences and societal domains (HCI and AI). Thus, the proposed workshop topic aligns well with the theme of this year’s NordiCHI conference which is Shaping Experiences, Shaping Society.

While the Internet of Things (IoT) is still gaining rapid adoption in an upward trajectory means across many smart areas in recent years, still, there is a need to develop a scalable ecosystem that is able to support future IoT implementations, given the heterogeneity and increased information flow among IoT devices. The lack of effective interoperability, availability, reliability, and performance in IoT are a few challenges that hinder the effectiveness of IoT deployment and communication, and this has acted as a stumbling block for the optimisation of IoT platforms. That notwithstanding, the advent of the Fifth Generation (5G) networks, has seen a significant shift on how the IoT-paradigm operates. This article introduces a discussion on the generic 5G infrastructure for IoT environment that can support future deployments. The article begins by conducting a technical review of the evolution of the First generation (1G) through 5G cellular networks. Thereafter, an illustration of the Fourth Generation (4G) architecture, stating its features as a precedent that shows to what extent 5G network may thrive or support IoT ecosystems, is given. Furthermore, the paper explores both the architectural requirements and futuristic vision of 5G infrastructure in the perspective of IoT applications. Most importantly, the paper has also explored the IoT market share and forecast on growth and how it affects different industrial sectors. The authors believe that the conclusions that have been made in this paper will act as a pacesetter and give a direction worth exploring once the 5G infrastructure for IoT ecosystems is implemented.

För studenter inom IT-relaterade ämnen är programmering en grundläggande kunskap som borde utvecklas tidigt i deras utbildning. Det innebär inte bara lärandet av syntax och semantik av ett visst programmeringsspråk, men också att utveckla förmågan att kunna kombinera olika enskilda instruktioner till en algoritm eller ett dataprogram som kan lösa ett visst problem. Hittills genomfördes många programmeringskurser inom högre utbildning som campuskurser och skiftet till distansundervisning medförde behovet att identifiera nya lämpliga undervisningsformer.

Syftet med den här artikeln är att analysera befintliga online-lärandemiljöer för att identifiera innovativa verktyg samt didaktiska angreppssätt som kan användas i distansundervisning av programmering inom högre utbildning. I artikeln presenteras det en diskussion av deras lämplighet för digitalisering av olika moment i programmeringskurser, ur både studentens och lärarens perspektiv, men också hur den konstruktiva länkningen med aktuella kursmål kan uppnås eller styrkas. Digitaliseringspotentialen visas genom exemplet av kursen DA343A (”Objektorienterad programutveckling, trådar och datakommunikation”) på Malmö universitet, som riktar sig till studenter i kandidatprogrammet i datavetenskap med inriktning systemutveckling och högskoleingenjörsutbildningen i datateknik. 

A potential security incident may go unsolved if standardized forensic approaches are not applied during lawfulinvestigations. This paper highlights the importance of mapping the digital forensic application requirementspecification to an international standard, precisely ISO/IEC 27043. The outcome of this work is projected tocontribute to the problem of secure DF tool creation, and in the process address Software Requirements Specification(SRS) as a process of digital evidence admissibility.

We present an O(nrG) time algorithm for computing and maintaining a minimum length shortest watchman tour that sees a simple polygon under monotone visibility in direction θ, while θ varies in[0, 180 ◦ ), obtaining the directions for the tour to be the shortest one overall tours, where n is the number of vertices, r is the number of reflex vertices, and G ≤ r is the maximum number of gates of the polygon used at any time in the algorithm.

Home health care (HHC) providers face an increasing demand in care services, while the labor market only offers a limited number of professionals. To cope with this challenge from a HHC provider’s perspective, available resources must be deployed efficiently taking into account individual human needs and desires of employees as well as customers. On the one hand, corresponding strategic management questions arise, e.g., distribution or relocation of establishments or expansion of the vehicle fleet. On the other hand, logistical challenges such as the flexible and robust planning and scheduling of HHC service provision must be addressed by operational HHC management. This paper targets both perspectives by providing an integrated simulation-based framework for the evaluation of different business processes. Methods from Agent-based Simulation, Dynamic Microsimulation, and (Distributed) Artificial Intelligence are combined to investigate HHC service provision and to support practical decision-making. The presented approach aims to facilitate the reasonable development of the HHC provider’s organization to ensure the sustainable delivery of required medical care.

A Cloud Forensic Readiness as a Service (CFRaaS) model allows an environmentto preemptively accumulate relevant potential digital evidence (PDE) which maybe needed during a post-event response process. The benefit of applying a CFRaaSmodel in a cloud environment, is that, it is designed to prevent the modification/tampering of the cloud architectures or the infrastructure during the reactive pro-cess, which if it could, may end up having far-reaching implications. The authorsof this article present the reactive processasaverycostlyexercisewhentheinfra-structure must be reprogrammed every time the process is conducted. This mayhamper successful investigation from the forensic experts and law enforcementagencies perspectives. The CFRaaS model, in its current state, has not been pres-ented in a way that can help to classify or visualize the different types of potentialevidence in all the cloud deployable models, and this may limit the expectationsof what or how the required PDE may be collected. To address this problem, thearticle presents the CFRaaS from a holistic ontology-driven perspective, whichallows the forensic experts to be able to apply the CFRaaS based on its simplicityof the concepts, relationship or semantics between different form of potential evi-dence, as well as how the security of a digital environment being investigatedcould be upheld. The CFRaaS in this context follows a fundamental ontologyengineering approach that is based on the classical Resource Description Frame-work. The proposed ontology-driven approach to CFRaaS is, therefore, aknowledge-base that uses layer-dependencies, which could be an essential toolkitfor digital forensic examiners and other stakeholders in cloud-security. The imple-mentation of this approach could further provide a platform to develop otherknowledge base components for cloud forensics and security

While security is often recognized as a top priority for organizations and a push for competitive advantage, repeatedly, Internet of Things (IoT) products have become a target of diverse security attacks. Thus, orchestrating smart services and devices in a more open, standardized and secure way in IoT environments is yet a desire as much as it is a challenge. In this paper, we propose a model for IoT practitioners and researchers, who can adopt a sound security thinking in parallel with open IoT technological developments. We present the state-of-the-art and an empirical study with IoT practitioners. These efforts have resulted in identifying a set of openness and security thinking criteria that are important to consider from an IoT ecosystem point of view. Openness in terms of open standards, data, APIs, processes, open source and open architectures (flexibility, customizability and extensibility aspects), by presenting security thinking tackled from a three-dimensional point of view (awareness, assessment and challenges) that highlight the need to develop an IoT security mindset. A novel model is conceptualized with those characteristics followed by several key aspects important to design and secure future IoT systems.

Machine learning has been shown as a promising approach to mine larger datasets, such as those that comprise datafrom a broad range of Internet of Things devices, across complex environment(s) to solve different problems. Thispaper surveys existing literature on the potential of using supervised classical machine learning techniques, such asK-Nearest Neigbour, Support Vector Machines, Naive Bayes and Random Forest algorithms, in performing livedigital forensics for different IoT configurations. There are also a number of challenges associated with the use ofmachine learning techniques, as discussed in this paper.

We propose an optimization model to tackle the problem of determining how projects are assigned to student groups based on a bidding procedure. In order to improve student experience in project-based learning we resort to actively involving them in a transparent and unbiased project allocation process. To evaluate our work, we collected information about the students' own views on how our approach influenced their level of learning and overall learning experience and provide a detailed analysis of the results. The results of our evaluation show that the large majority of students (i.e., 91%) increased or maintained their satisfaction ratings with the proposed procedure after the assignment was concluded, as compared to their attitude towards the process before the project assignment occurred.

In this paper, we study the complementary characteristics of stationary and mobile devices for traffic data collection. Since stationary devices continuously collect traffic data at fixed locations in a network, they can give insight of the traffic at particular locations over a longer period of time. Mobile devices have wider range and are able to collect traffic data over a larger geographic region. Thus, we argue that both types of technology should be considered to obtain high-quality information about vehicle movements. We present a traffic simulation model, which we use to study the share of successfully identified vehicles when considering both stationary and mobile technologies with varying identification rate. The results of our study, where we focus on freight transport in southern Sweden, confirms that it is possible to identify the majority of vehicles, even when the identification rate is low, and that the share of identified vehicles can be increased by using both stationary and mobile measurement devices.

As an alternative to the car, the bicycle is considered important for obtaining more sustainable urban transport. The bicycle has many positive effects; however, bicyclists are more vulnerable than users of other transport modes, and the number of bicycle related injuries and fatalities are too high. We present a clustering analysis aiming to support the identification of the locations of bicyclists' perceived unsafety in an urban traffic network, so-called bicycle impediments. In particular, we used an iterative k-means clustering approach, which is a contribution of the current paper, and DBSCAN. In contrast to standard k-means clustering, our iterative k-means clustering approach enables to remove outliers from the data set. In our study, we used data collected by bicyclists travelling in the city of Lund, Sweden, where each data point defines a location and time of a bicyclist's perceived unsafety. The results of our study show that 1) clustering is a useful approach in order to support the identification of perceived unsafe locations for bicyclists in an urban traffic network and 2) it might be beneficial to combine different types of clustering to support the identification process. (C) 2020 The Authors. Published by Elsevier B.V.

A set of GPS traces for bicyclists and a set of notifications by bicyclists of problematic situations (spots identified by GPS records) had been collected independently. The data collection periods did not coincide but overlapped and none was contained in the other one. The aim is to use both datasets to determine an optimal action plan for problem solving given a limited budget. First, problematic locations are clustered. Each cluster corresponds to an impediment. Impediments are then associated with trips using a distance function. The aim is to find out which impediments to solve under a given budget constraint in order to maximize the number of impediment free trips. Thereto the trip set is partitioned by matching each trip with the largest set of its affecting impediments. Solving all impediments in such set induces a cost and makes the associated part of trips impediment free. An optimizer is presented and evaluated. (C) 2020 The Authors. Published by Elsevier B.V.

In data science, the application of most approaches requires the existence of big data from a real-world system. Due to access limitations, nonexistence of the system, or temporal as well as economic restrictions, such data might not be accessible or available. To overcome a lack of real-world data, this chapter introduces simulation-based data acquisition as method for the generation of artificial data that serves as a substitute when applying data science techniques. Instead of gathering data from the real-world system, computer simulation is used to model and execute artificial systems that can provide a more accessible, economic, and robust source of big data. To this end, it is outlined how data science can benefit from simulation and vice versa. Specific approaches are introduced for the design and execution of experiments, and a selection of simulation frameworks is presented that facilitates the conducting of simulation studies for novice and professional users.

Research on barriers to Digital Transformation (DT) in German non-digitally born (NDB) companies exists. This existing research could potentially be extended into different directions to validate and contrast results. We have chosen to continue the current research into Barriers to DT in Turkish digitally born (DB) companies. As a country, Turkey has a lower degree of digitalization than Germany. At the same time, DB companies might face fewer obstacles within their DT journey than NDB companies.

With the rise of digital technologies, digital transformation (DT) has become an issue in nearly all industries. In enterprises, DT means to digitalize internal processes, offer digital services as well as products, and enhance the customer experience. As the transformation is complex, barriers hinder the successful transformation. However, an instrument for the measurement of barriers and their effects on the DT of an organization is missing. Our research questions are therefore: What are the barriers to DT in industry and industry-related areas? How can they be described and measured?

For the efficient execution of Deep Neural Networks (DNN) in the Internet of Things, computation tasks can be distributed and deployed on edge nodes. In contrast to deploying all computation to the cloud, the use of Distributed DNN (DDNN) often results in a reduced amount of data that is sent through the network and thus might increase the overall performance of the system. However, finding an appropriate deployment scenario is often a complex task and requires considering several criteria. In this paper, we introduce a multi-criteria decision-making method based on the Analytical Hierarchy Process for the comparison and selection of deployment alternatives. We use the RECAP simulation framework to model and simulate DDNN deployments on different scales to provide a comprehensive assessment of deployments to system designers. In a case study, we apply the method to a smart city scenario where different distributions and deployments of a DNN are analyzed and compared.

Internet of Things (IoT) systems are complex and multifaceted, and the design of their architectures needs to consider many aspects at a time. Design decisions concern, for instance, the modeling of software components and their interconnections, as well as where to deploy the components within the available hardware infrastructure in the Edge-Cloud continuum. A relevant and challenging task, in this context, is to identify optimal deployment models due to all the different aspects involved, such as extra-functional requirements of the system, heterogeneity of the hardware resources concerning their processing and storage capabilities, and constraints like legal issues and operational cost limits. To gain insights about the deployment decisions concerning IoT systems in practice, and the factors that influence those decisions, we report about an industrial survey we conducted with 66 IoT architects from 18 countries across the world. Each participant filled in a questionnaire that comprises 15 questions. By analyzing the collected data, we have two main findings: (i) architects rely on the Cloud more than the Edge for deploying the software components of IoT systems, in the majority of the IoT application domains; and (ii) the main factors driving deployment decisions are four: reliability, performance, security, and cost.

Engineering Internet of Things (IoT) systems is a challenging task partly due to the dynamicity and uncertainty of the environment including the involvement of the human in the loop. Users should be able to achieve their goals seamlessly in different environments, and IoT systems should be able to cope with dynamic changes. Several approaches have been proposed to enable the automated formation, enactment, and self-adaptation of goal-driven IoT systems. However, they do not address deployment issues. In this paper, we propose a goal-driven approach for deploying self-adaptive IoT systems in the Edge-Cloud continuum. Our approach supports the systems to cope with the dynamicity and uncertainty of the environment including changes in their deployment topologies, i.e., the deployment nodes and their interconnections. We describe the architecture and processes of the approach and the simulations that we conducted to validate its feasibility. The results of the simulations show that the approach scales well when generating and adapting the deployment topologies of goal-driven IoT systems in smart homes and smart buildings.

The Internet of Things (IoT) has enabled physical objects and devices, often referred to as things, to connect and communicate. This has opened up for the development of novel types of services that improve the quality of our daily lives. The dynamicity and uncertainty of IoT environments, including the mobility of users and devices, make it hard to foresee at design time available things and services. Further, users should be able to achieve their goals seamlessly in arbitrary environments. To address these challenges, we exploit Artificial Intelligence (AI) to engineer smart IoT systems that can achieve user goals and cope with the dynamicity and uncertainty of their environments. More specifically, the main contribution of this paper is an approach that leverages the notion of Belief-Desire-Intention agents and Machine Learning (ML) techniques to realize Emergent Configurations (ECs) in the IoT. An EC is an IoT system composed of a dynamic set of things that connect and cooperate temporarily to achieve a user goal. The approach enables the distributed formation, enactment, adaptation of ECs, and conflict resolution among them. We present a conceptual model of the entities of the approach, its underlying processes, and the guidelines for using it. Moreover, we report about the simulations conducted to validate the feasibility of the approach and evaluate its scalability. View Full-Text

Internet of Things (IoT) environments encompass different types of devices and objects that offer a wide range of services. The dynamicity and uncertainty of those environments, including the mobility of users and devices, make it hard to foresee at design time available devices, objects, and services. For the users to benefit from such environments, they should be proposed services that are relevant to the specific context and can be provided by available things. Moreover, environments should be configured automatically based on users' preferences. To address these challenges, we propose an approach that leverages Artificial Intelligence techniques to recognize users' activities and provides relevant services to support users to perform their activities. Moreover, our approach learns users' preferences and configures their environments accordingly by dynamically forming, enacting, and adapting goal-driven IoT systems. In this paper, we present a conceptual model, a multi-tier architecture, and processes of our approach. Moreover, we report about how we validated the feasibility and evaluated the scalability of the approach through a prototype that we developed and used.

Technology-based business improvements characterize the so-called digital transformation (DT). For non-profit organizations (NPOs), with their unique value creation structure and specific preconditions in terms of staff and resources, keeping up with the DT is challenging. Still, opportunities for the DT are unknown. Thus far, there are no comprehensive guidelines for DT strategy development in NPOs. Both digital value creation and digitally supported communication with customers can lead to competitive advantages. Therefore, NPO decision-makers must understand the opportunities and the challenges of DT. In our research approach, we aim to answer the research question: What are the fields of action for the digital transformation in NPOs? Following a grounded theory approach, we have developed a theoretical framework including fields of action and guidance for the strategic advancement of DT in NPOs. The results show that NPOs need to be aware of their digital communications channels with volunteer staff, customers and donors. A clear DT vision and new roles help NPOs meet this challenge.

For the provision of efficient and high-quality public transport services in rural areas with a low population density, the introduction of Demand Responsive Transport (DRT) services is reasonable. The optimal design of such services depends on various socio-demographical and environmental factors, which is why the use of simulation is feasible to support planning and decision-making processes. A key challenge for sound simulation results is the generation of realistic demand, i.e., requests for DRT journeys. In this paper, a method for modelling and simulating commuting activities is presented, which is based on statistical real-world data. It is applied to Sjöbo and Tomelilla, two rural municipalities in southern Sweden.

With the rapid development of Machine Learning technology applied in electroencephalography (EEG) signals, Brain-Computer Interface (BCI) has emerged as a novel and convenient human-computer interaction for smart home, intelligent medical and other Internet of Things (IoT) scenarios. However, security issues such as sensitive information disclosure and unauthorized operations have not received sufficient concerns. There are still some defects with the existing solutions to encrypted EEG data such as low accuracy, high time complexity or slow processing speed. For this reason, a classification and recognition method of encrypted EEG data based on neural network is proposed, which adopts Paillier encryption algorithm to encrypt EEG data and meanwhile resolves the problem of floating point operations. In addition, it improves traditional feed-forward neural network (FNN) by using the approximate function instead of activation function and realizes multi-classification of encrypted EEG data. Extensive experiments are conducted to explore the effect of several metrics (such as the hidden neuron size and the learning rate updated by improved simulated annealing algorithm) on the recognition results. Followed by security and time cost analysis, the proposed model and approach are validated and evaluated on public EEG datasets provided by PhysioNet, BCI Competition IV and EPILEPSIAE. The experimental results show that our proposal has the satisfactory accuracy, efficiency and feasibility compared with other solutions. (C) 2020 Elsevier Ltd. All rights reserved.

The digitalization of higher education institutions is progressing significantly. Though the use of digital assets enhances the students’ learning experience and offers new opportunities for administration, there are no uniform standards for the use of digital media in teaching and student services. As educational service providers, universities are dependent on students being able to cope with the structures offered. Thus it is essential to ascertain students’ attitudes of the technologies used. We asked students from three blended learning courses about their perceptions. We further asked the students what should be done and by whom. Our results show that students see structural changes occurring not only in themselves but also at the level of the university management. Our research contributes to the actual discussion about the digitalization of higher education by offeringsuggestions for development from a students’ view. The results are valuable for lecturers and faculty managers who want to advance the digitalization of services and learning.

Mobile Forensics (MF) field uses prescribed scientific approaches with a focus on recovering Potential Digital Evidence (PDE) from mobile devices leveraging forensic techniques. Consequently, increased proliferation, mobile-based services, and the need for new requirements have led to the development of the MF field, which has in the recent past become an area of importance. In this article, the authors take a step to conduct a review on Mobile Forensics Investigation Process Models (MFIPMs) as a step towards uncovering the MF transitions as well as identifying open and future challenges. Based on the study conducted in this article, a review of the literature revealed that there are a few MFIPMs that are designed for solving certain mobile scenarios, with a variety of concepts, investigation processes, activities, and tasks. A total of 100 MFIPMs were reviewed, to present an inclusive and up-to-date background of MFIPMs. Also, this study proposes a Harmonized Mobile Forensic Investigation Process Model (HMFIPM) for the MF field to unify and structure whole redundant investigation processes of the MF field. The paper also goes the extra mile to discuss the state of the art of mobile forensic tools, open and future challenges from a generic standpoint. The results of this study find direct relevance to forensic practitioners and researchers who could leverage the comprehensiveness of the developed processes for investigation.

The bicycle has many positive effects; however, bicyclists are more vulnerablethan users of other transport modes, andthe number of bicycle related injuries and fatalities are toohigh.We present a clustering analysis aiming to support the identification of the locations ofbicyclists' perceived unsafety in an urban trafficnetwork, so-called bicycle impediments.In  particular,  we presentan  iterative  k-means  clustering approach,  which  in  contrast  to  standard  k-means  clustering, enables to remove outliers and solitary points from the data set. In our study, we used data collected by bicyclists travelling inthe city of Lund, Sweden, where each data point defines a location andtime of a bicyclist's perceived unsafety.The results of our study show that 1) clustering is a usefulapproach in order to support the identification of perceived unsafelocations forbicyclists in an urban traffic networkand2) it might bebeneficial to combine different types of clustering to support theidentification process. Furthermore, using the adjusted Rand index, our results indicate highrobustness of our iterative k-means clustering approach.

Machine Learning (ML) has been a prominent area of research within Artificial Intelligence (AI). ML uses mathematical models to recognize patterns in large and complex data sets to aid decision making in different application areas, such as image and speech recognition, consumer recommendations, fraud detection and more. ML systems typically go through a training period in which the system encounters and learns about the data; further, this training often requires some degree of human intervention. Interactive machine learning (IML) refers to ML applications that depend on continuous user interaction. From an HCI perspective, how humans interact with and experience ML models in training is the main focus of this workshop proposal. In this workshop we focus on the user experience (UX) of Interactive Machine Learning, a topic with implications not only for usability but also for the long-term success of the IML systems themselves.

Uncertainty is intrinsic in most of the complex systems, especially when the systems have to interact with the physical environment; therefore, handling uncertainty is critical in the Internet of Things (IoT). In this paper, we propose a semantic-based approach to build the belief network in IoT systems to handle the uncertainties. Semantics is the functionality description of any system component. Semantic Match mechanisms can construct the appropriate structures to compare the consistency between different sources of data based on the same functionality. In the approach, we define the belief property of every system component and develop the related algorithms to update the belief value. Furthermore, the related mechanisms and algorithms for data fusion and fault detection based on the belief property are described to explain how the approach works in the IoT systems. Several simulation experiments are used to evaluate the proposed approach, and the results indicate that the approach can work as expected. More accurate data are fused from the inaccurate devices and the fault in one node is automatically detected.

In this study, we describe the results of our research to model collaborative problem-solving (CPS) competence based on analytics generated from video data. We have collected similar to 500 mins video data from 15 groups of 3 students working to solve design problems collaboratively. Initially, with the help of OpenPose, we automatically generated frequency metrics such as the number of the face-in-the-screen; and distance metrics such as the distance between bodies. Based on these metrics, we built decision trees to predict students' listening, watching, making, and speaking behaviours as well as predicting the students' CPS competence. Our results provide useful decision rules mined from analytics of video data which can be used to inform teacher dashboards. Although, the accuracy and recall values of the models built are inferior to previous machine learning work that utilizes multimodal data, the transparent nature of the decision trees provides opportunities for explainable analytics for teachers and learners. This can lead to more agency of teachers and learners, therefore can lead to easier adoption. We conclude the paper with a discussion on the value and limitations of our approach.

Deep learning (DL) models have emerged in recent years as the state-of-the-art technique across numerous machine learning application domains. In particular, image processing-related tasks have seen a significant improvement in terms of performance due to increased availability of large datasets and extensive growth of computing power. In this paper we investigate the problem of group activity recognition in office environments using a multimodal deep learning approach, by fusing audio and visual data from video. Group activity recognition is a complex classification task, given that it extends beyond identifying the activities of individuals, by focusing on the combinations of activities and the interactions between them. The proposed fusion network was trained based on the audio-visual stream from the AMI Corpus dataset. The procedure consists of two steps. First, we extract a joint audio-visual feature representation for activity recognition, and second, we account for the temporal dependencies in the video in order to complete the classification task. We provide a comprehensive set of experimental results showing that our proposed multimodal deep network architecture outperforms previous approaches, which have been designed for unimodal analysis, on the aforementioned AMI dataset.

Smart connected home systems bring different privacy challenges to residents. The contribution of this paper is a novel privacy grounded classification of smart connected home systems that is focused on personal data exposure. This classification is built empirically through k-means cluster analysis from the technical specification of 81 commercial Internet of Things (IoT) systems as featured in PrivacyNotIncluded – an online database of consumer IoT systems. The attained classification helps us better understand the privacy implications and what is at stake with different smart connected home systems. Furthermore, we survey the entire spectrum of analyzed systems for their data collection capabilities. Systems were classified into four tiers: app-based accessors, watchers, location harvesters, and listeners, based on the sensing data the systems collect. Our findings indicate that being surveilled inside your home is a realistic threat, particularly, as the majority of the surveyed in-home IoT systems are installed with cameras, microphones, and location trackers. Finally, we identify research directions and suggest some best practices to mitigate the threat of in-house surveillance.

Background : Developing and maintaining large scale machine learning (ML) based software systems in an in-dustrial setting is challenging. There are no well-established development guidelines, but the literature contains reports on how companies develop and maintain deployed ML-based software systems. Objective : This study aims to survey the literature related to development and maintenance of large scale ML -based systems in industrial settings in order to provide a synthesis of the challenges that practitioners face. In addition, we identify solutions used to address some of these challenges. Method : A systematic literature review was conducted and we identified 72 papers related to development and maintenance of large scale ML-based software systems in industrial settings. The selected articles were qualita-tively analyzed by extracting challenges and solutions. The challenges and solutions were thematically synthe-sized into four quality attributes: adaptability, scalability, safety and privacy. The analysis was done in relation to ML workflow, i.e. data acquisition, training, evaluation, and deployment. Results : We identified a total of 23 challenges and 8 solutions related to development and maintenance of large scale ML-based software systems in industrial settings including six different domains. Challenges were most often reported in relation to adaptability and scalability. Safety and privacy challenges had the least reported solutions. Conclusion : The development and maintenance on large-scale ML-based systems in industrial settings introduce new challenges specific for ML, and for the known challenges characteristic for these types of systems, require new methods in overcoming the challenges. The identified challenges highlight important concerns in ML system development practice and the lack of solutions point to directions for future research.

Mobile phones, wearable trackers and Internet of Things devices continuously produce data about our health and lifestyle that can be used for medical research. However, how data is accessed, by whom and for what purpose is not always understood. This lack of transparency undermines citizens trust in the use of such technologies for research purposes. This paper proposes a set of 6 use cases and related mock-up interfaces for citizen science, mobile-based health research: “Curated information about the institution”, “Sequential consent of shared data”, “Updates from the institution”, “Privacy notifications”, “Overview of donated data” and “Personal impact in medical research”. Interviews and Kano analysis of the interfaces with 6 prospective users show that all except “Privacy notifications” are perceived as important and beneficial for increasing users’ trust. The defined use cases can guide the development of future data collection platforms.

Commercial wearable devices and fitness trackers are commonly sold as black boxes of which little is known about their accuracy. This poses serious issues especially in health-related contexts such as clinical research, where transparency about accuracy and reliability are paramount.

We present a validated algorithm for computing step counting that is optimised for use in constrained computing environments. Released as open source, the algorithm is based on the windowed peak detection approach, which has previously shown high accuracy on smartphones. The algorithm is optimised to run on a programmable smartwatch (Pine Time) and tested on 10 subjects in 8 scenarios, with varying varying positions of the wearable and walking paces.

Our approach achieves a 89% average accuracy, with the highest average accuracy when walking outdoor (98%) and the lowest in a slow-walk scenario (77%). This result can be compared with the built-in step counter of the smartwatch (Bosch BMA421), which yielded a 94% average accuracy for the same use cases. Our work thus shows that an open-source approach for extracting physical activity data from wearable devices is possible and achieves an accuracy comparable to the one produced by proprietary embedded algorithms.

The Internet of Things (IoT) is a fast-spreading technology that enables new types of services in several domains such as transportation, health, and building automation. To exploit the potential of the IoT effectively, several challenges have to be tackled, including the following ones that we study in this thesis. First, the proposed IoT visions provide a fragmented picture, leading to a lack of consensus about IoT systems and their constituents. To piece together the fragmented picture of IoT systems, we systematically identified their characteristics by analyzing existing taxonomies. More specifically, we identified seventeen characteristics of IoT systems, and grouped them into two categories, namely, elements and quality aspects of IoT systems. Moreover, we conducted a survey to identify the factors that drive the deployment decisions of IoT systems in practice. A second set of challenges concerns the environment of IoT systems that is often dynamic and uncertain. For instance, due to the mobility of users and things, the set of things available in users' environment might change suddenly. Similarly, the status of IoT systems’ deployment topologies (i.e., the deployment nodes and their interconnections) might change abruptly. Moreover, environmental conditions monitored and controlled through IoT devices, such as ambient temperature and oxygen levels, might fluctuate suddenly. The majority of existing approaches to engineer IoT systems rely on predefined processes to achieve users’ goals. Consequently, such systems have significant shortcomings in coping with dynamic and uncertain environments. To address these challenges, we used the concept of Emergent Configurations (ECs) to engineer goal-driven IoT systems. An EC is an IoT system that consists of a dynamic set of things that cooperate temporarily to achieve a user goal. To realize ECs, we proposed an abstract architectural approach, comprising an architecture and processes, as well as six novel approaches that refine the abstract approach. The developed approaches support users to achieve their goals seamlessly in arbitrary environments by enabling the dynamic formation, deployment, enactment, and self-adaptation of IoT systems. The approaches exploit different techniques and focus on different aspects of ECs. Moreover, to better support users in dynamic and uncertain environments, we investigated the automated configuration of those environments based on users' preferences. 

As AI develops, grows, and expands, the more benefits we can have from it. AI is used in multiple fields to assist humans, such as object recognition, self-driving cars, or design tools. However, AI could be used for more than assisting humans in their tasks. It could be employed to collaborate with humans as colleagues in shared tasks, which is usually described as Mixed-Initiative (MI) paradigm. This paradigm creates an interactive scenario that leverage on AI and human strengths with an alternating and proactive initiative to approach a task. However, this paradigm introduces several challenges. For instance, there must be an understanding between humans and AI, where autonomy and initiative become negotiation tokens. In addition, control and expressiveness need to be taken into account to reach some goals. Moreover, although this paradigm has a broader application, it is especially interesting for creative tasks such as games, which are mainly created in collaboration. Creating games and their content is a hard and complex task, since games are content-intensive, multi-faceted, and interacted by external users. 

Therefore, this thesis explores MI collaboration between human game designers and AI for the co-creation of games, where the AI's role is that of a colleague with the designer. The main hypothesis is that AI can be incorporated in systems as a collaborator, enhancing design tools, fostering human creativity, reducing their workload, and creating adaptive experiences. Furthermore, This collaboration arises several dynamic properties such as control, expressiveness, and initiative, which are all central to this thesis. Quality-Diversity algorithms combined with control mechanisms and interactions for the designer are proposed to investigate this collaboration and properties. Designer and Player modeling is also explored, and several approaches are proposed to create a better workflow, establish adaptive experiences, and enhance the interaction. Through this, it is demonstrated the potential and benefits of these algorithms and models in the MI paradigm.

Building interpretable machine learning agents is a challenge that needs to be addressed to make the agents trustworthy and align the usage of the technology with human values. In this work, we focus on how to evaluate interpretability in a machine teaching setting, a settingthat involves a human domain expert as a teacher in relation to a machine learning agent. By using a prototype in a study, we discuss theinterpretability denition and show how interpretability can be evaluatedon a functional-, human- and application level. We end the paperby discussing open questions and suggestions on how our results can be transferable to other domains.

For every contact that is made in a database, a digital trace will potentially be left and most of the database breaches are mostly aimed at defeating the major security goals (Confidentiality, Integrity, and Authenticity) of data that reside in the database. In order to prove/refute a fact during litigation, it is important to identify suitable investigation techniques that can be used to link a potential incident/suspect to the digital crime. As a result, this paper has proposed suitable steps of constructing and Integrated Incident Response Model (IIRM) that can be relied upon in the database forensic investigation field. While developing the IIRM, design science methodology has been adapted and the outcome of this study has shown significant and promising approaches that could be leveraged by digital forensic experts, legal practitioners and law enforcement agencies. This is owing to the fact, that IIRM construction has followed incident investigation principles that are stipulated in ISO guidelines.

This paper presents the Designer Preference Model, a data-driven solution that pursues to learn from user generated data in a Quality-Diversity Mixed-Initiative Co-Creativity (QD MI-CC) tool, with the aims of modelling the user’s design style to better assess the tool’s procedurally generated content with respect to that user’s preferences. Through this approach, we aim for increasing the user’s agency over the generated content in a way that neither stalls the user-tool reciprocal stimuli loop nor fatigues the user with periodical suggestion handpicking. We describe the details of this novel solution, as well as its implementation in the MI-CC tool the Evolutionary Dungeon Designer. We present and discuss our findings out of the initial tests carried out, spotting the open challenges for this combined line of research that integrates MI-CC with Procedural Content Generation through Machine Learning.

With the rapid development of Internet services, mobile communications, and IoT applications, Location-Based Service (LBS) has become an indispensable part in our daily life in recent years. However, when users benefit from LBSs, the collection and analysis of users' location data and trajectory information may jeopardize their privacy. To address this problem, a new privacy-preserving method based on historical proximity locations is proposed. The main idea of this approach is to substitute one existing historical adjacent location around the user for his/her current location and then submit the selected location to the LBS server. This method ensures that the user can obtain location-based services without submitting the real location information to the untrusted LBS server, which can improve the privacy-preserving level while reducing the calculation and communication overhead on the server side. Furthermore, our scheme can not only provide privacy preservation in snapshot queries but also protect trajectory privacy in continuous LBSs. Compared with other location privacy-preserving methods such ask-anonymity and dummy location, our scheme improves the quality of LBS and query efficiency while keeping a satisfactory privacy level.

Heart diseases are in the front rank among several kinds of life threats, due to its high incidence and mortality. Regarded as a powerful tool in the diagnosis of the cardiac disorder and arrhythmia detection, analysis of electrocardiogram (ECG) signals has become the focus of numerous researches. In this study, a feature extraction method based on the bispectrum and 2D graph Fourier transform (GFT) was developed. High-order matrix founded on bispectrum are extended into structured datasets and transformed into the eigenvalue spectrum domain by GFT, so that features can be extracted from statistical quantities of eigenvalues. Spectral features have been computed to construct the feature vector. Support vector machine based on the radial basis function kernel (SVM-RBF) was used to classify different arrhythmia heartbeats downloaded from the Massachusetts Institute of Technology - Beth Israel Hospital (MIT-BIH) Arrhythmia Database, according to the Association for the Advancement of Medical Instrumentation (AAMI) standard. Based on the cross-validation method, the experimental results depicted that our proposed model, the combination of bispectrum and 2D-GFT, achieved a high classification accuracy of 96.2%.

Smart connected homes are integrated with heterogeneous Internet-connected devices interacting with the physical environment and human users. While they have become an established research area, there is no common understanding of what composes such a pervasive environment making it challenging to perform a scientific analysis of the domain. This is especially evident when it comes to discourse about privacy threats. Recognizing this, we aim to describe a generic smart connected home, including the data it deals with in a novel privacy-centered system model. Such is done using concepts borrowed from the theory of Contextual Integrity. Furthermore, we represent privacy threats formally using the proposed model. To illustrate the usage of the model, we apply it to the design of an ambient-assisted living use-case and demonstrate how it can be used for identifying and analyzing the privacy threats directed to smart connected homes.

Using Malmö Turism-a tourist bureau in the south of Sweden-as a case, this chapter examines its digital transformation; from being based foremost on promoting storytelling of real-life interactions with a few expert assistants at a physical tourist bureau, towards becoming a primary digitally based cross-and transmedia operation, where support of the hosting relied on a larger number of connected media and actors. Based on interviews with the organization before and after the reorganization, the chapter analyses the drivers, determinants and challenges that faced the organization during the transformation. It contributes with insight and understanding from a novel case that other tourism organizations may contrast their findings with, a challenge many of them are likely to embrace in the future.

Database forensic investigation (DBFI) is an important area of research within digital forensics. It & x2019;s importance is growing as digital data becomes more extensive and commonplace. The challenges associated with DBFI are numerous, and one of the challenges is the lack of a harmonized DBFI process for investigators to follow. In this paper, therefore, we conduct a survey of existing literature with the hope of understanding the body of work already accomplished. Furthermore, we build on the existing literature to present a harmonized DBFI process using design science research methodology. This harmonized DBFI process has been developed based on three key categories (i.e. planning, preparation and pre-response, acquisition and preservation, and analysis and reconstruction). Furthermore, the DBFI has been designed to avoid confusion or ambiguity, as well as providing practitioners with a systematic method of performing DBFI with a higher degree of certainty.

Since the advent of mobile computing and IoT, a large amount of data is distributed around the world. Companies are increasingly experimenting with innovative ways of implementing edge/cloud (re)training of AI systems to exploit large quantities of data to optimize their business value. Despite the obvious benefits, companies face challenges as the decision on how to implement edge/cloud (re)training depends on factors such as the task intent, the amount of data needed for (re)training, edge-to-cloud data transfer, the available computing and memory resources. Based on action research in a software-intensive embedded systems company where we study multiple use cases as well as insights from our previous collaborations with industry, we develop a generic framework consisting of five architectural alternatives to deploy AI on the edge utilizing transfer learning. We validate the framework in four additional case companies and present the challenges they face in selecting the optimal architecture. The contribution of the paper is threefold. First, we develop a generic framework consisting of five architectural alternatives ranging from a centralized architecture where cloud (re)training is given priority to a decentralized architecture where edge (re)training is instead given priority. Second, we validate the framework in a qualitative interview study with four additional case companies. As an outcome of validation study, we present two variants to the architectural alternatives identified as part of the framework. Finally, we identify the key challenges that experts face in selecting an ideal architectural alternative.

Calibration is an essential prerequisite for the combined application of light detection and ranging (LiDAR) and inertial measurement unit (IMU). However, current LiDAR-IMU calibration usually relies on particular artificial targets or facilities and the intensive labor greatly limits the calibration flexibility. For these reasons, this article presents a novel multifeature based on-site calibration method for LiDAR-IMU system without any artificial targets or specific facilities. This new on-site calibration combines the point/sphere, line/cylinder, and plane features from LiDAR scanned data to reduce the labor intensity. The main contribution is that a new method is developed for LiDAR extrinsic parameters on-site calibration and this method could incorporate two or more calibration models to generate more accurate calibration results. First of all, the calibration of LiDAR extrinsic parameters is performed through estimating the geometric features and solving the multifeature geometric constrained optimization problem. Then, the relationships between LiDAR and IMU intrinsic calibration parameters are determined by the coordinate transformation. Lastly, the full information maximum likelihood estimation (FIMLE) method is applied to solve the optimization of the IMU intrinsic parameters calibration. A series of experiments are conducted to evaluate the proposed method. The analysis results demonstrate that the proposed on-site calibration method can improve the performance of the LiDAR-IMU.