Internet of Things (IoT) can work as a useful tool for clinical research. We developed a software platform that allows researchers to publish clinical studies and volunteers to participate into them using an app and connected IoT devices. The platform includes a REST API, a web interface for researchers and an app that collects data during tasks volunteers are invited to contribute. Nine tasks have been developed: Forms, Positioning, Finger tapping, Pulse-oximetry, Peak Flow measurement, Activity tracking, Data query, Queen’s College step test and Six-minute walk test. These leverage sensors embedded in the phone, connected Bluetooth devices and additional APIs like HealthKit and Google Fit. Currently, the platform is used in two clinical studies by 25 patients: an asthma management study in the United Kingdom, and a neuropathic pain management study in Spain.

This Open Access book brings the experiences of automation as part of quotidian life into focus. It asks how, where and when automated technologies and systems are emerging in everyday life across different global regions? What are their likely impacts in the present and future? How do engineers, policy makers, industry stakeholders and designers envisage artificial intelligence (AI) and automated decision-making (ADM) as a solution to individual and societal problems? How do these future visions compare with the everyday realities, power relations and social inequalities in which AI and ADM are experienced? What do people know about automation and what are their experiences of engaging with ‘actually existing’ AI and ADM technologies? An international team of leading scholars bring together research developed across anthropology, sociology, media and communication studies, and ethnology, which shows how by re-humanising automation, we can gain deeper understandings of its societal impacts.

This chapter discusses the Sarah Pink discusses how ethics and trust in AI and ADM have become bound up in industry and government frameworks which treat them as commodities which can be extracted from faceless publics and invested in machines. The second reason that automated technologies receive high levels of publicity or promotion is when they have saved, or are predicted to save, lives: for instance, through accident prevention, medical and pharmaceutical interventions or in humanitarian domains. In contrast, experiences and processes of automation as part of quotidian routines in our everyday lives in our homes, transport, at work and in education have slipped under the radar of much popular and academic attention. The messiness of the ADM and AI fields might be seen as a problem, and one way forward involves engaging in a cross-disciplinary mapping of ADM and AI definitions to produce taxonomies and classifications for a shared vocabulary.

Online routing in a planar embedded graph is central to a number of fields and has been studied extensively in the literature. For most planar graphs no O (1)-competitive online routing algorithm exists. A notable exception is the Delaunay triangulation for which Bose and Morin (SIAM J Comput 33(4):937-951, 2004) showed that there exists an online routing algorithm that is O(1)-competitive. However, a Delaunay triangulation can have Omega (n) vertex degree and a total weight that is a linear factor greater than the weight of a minimum spanning tree. We show a simple construction, given a set V of n points in the Euclidean plane, of a planar geometric graph on V that has small weight (within a constant factor of the weight of a minimum spanning tree on V), constant degree, and that admits a local routing strategy that is O (1)-competitive. Moreover, the technique used to bound the weight works generally for any planar geometric graph whilst preserving the admission of an O (1)-competitive routing strategy.

The German engineering sector is one of the most prominent industries in Germany in terms of revenues, the number of employees, and reputation for the “Made in Germany” brand. In this industry, digital transformation (DT) has become a significant trend. DT is more than optimizing internal processes by digital means. It entails the offer of digital services and products and the enhancement of customer experience. Complex barriers need to be overcome to drive this transformation forward. Therefore, our study analysis the organizational barriers to DT within the German engineering industry. We follow a quantitative approach to gain insight on organizational barriers by a comparison of digitalized and less digitalized enterprises and their DTs. Our research demonstrates that digitalized enterprises perceive lower degrees of certain barriers in leadership, culture, employees, and skills, which are essential parts in a socio-technical view. However, there are still barriers that digitalized enterprises are struggling with.

This article investigates the event-triggered adaptive fuzzy output feedback setpoint regulation control for the surface vessels. The vessel velocities are noisy and small in the setpoint regulation operation and the thrusters have saturation constraints. A high-gain filter is constructed to obtain the vessel velocity estimations from noisy position and heading. An auxiliary dynamic filter with control deviation as the input is adopted to reduce thruster saturation effects. The adaptive fuzzy logic systems approximate vessel's uncertain dynamics. The adaptive dynamic surface control is employed to derive the event-triggered adaptive fuzzy setpoint regulation control depending only on noisy position and heading measurements. By the virtue of the event-triggering, the vessel's thruster acting frequencies are reduced such that the thruster excessive wear is avoided. The computational burden is reduced due to the differentiation avoidance for virtual stabilizing functions required in the traditional backstepping. It is analyzed that the event-triggered adaptive fuzzy setpoint regulation control maintains position and heading at desired points and ensures the closed-loop semi-global stability. Both theoretical analyses and simulations with comparisons validate the effectiveness and the superiority of the control scheme. 

In this paper, we investigate the dynamic task scheduling problem with stochastic task arrival times and due dates in the UAV-based intelligent on-demand meal delivery system (UIOMDS) to improve the efficiency. The objective is to minimize the total tardiness. The new constraints and characteristics introduced by UAVs in the problem model are fully studied. An iterated heuristic framework SES (Stochastic Event Scheduling) is proposed to periodically schedule tasks, which consists of a task collection and a dynamic task scheduling phases. Two task collection strategies are introduced and three Roulette-based flight dispatching approaches are employed. A simulated annealing based local search method is integrated to optimize the solutions. The experimental results show that the proposed algorithm is robust and more effective compared with other two existing algorithms.

This paper investigates the tracking control problem of marine surface vessels (MSVs) in the presence of uncertain dynamics and external disturbances. The facts that actuators are subject to undesirable faults and input saturation are taken into account. Benefiting from the smoothness of the Gaussian error function, a novel saturation function is introduced to replace each nonsmooth actuator saturation nonlinearity. Applying the hand position approach, the original motion dynamics of underactuated MSVs are transformed into a standard integral cascade form so that the vector design method can be used to solve the control problem for underactuated MSVs. By combining the neural network technique and virtual parameter learning algorithm with the vector design method, and introducing an event triggering mechanism, a novel event-triggered indirect neuroadaptive fault-tolerant control scheme is proposed, which has several notable characteristics compared with most existing strategies: 1) it is not only robust and adaptive to uncertain dynamics and external disturbances but is also tolerant to undesirable actuator faults and saturation; 2) it reduces the acting frequency of actuators, thereby decreasing the mechanical wear of the MSV actuators, via the event-triggered control (ETC) technique; 3) it guarantees stable tracking without the a priori knowledge of the dynamics of the MSVs, external disturbances or actuator faults; and 4) it only involves two parameter adaptations--a virtual parameter and a lower bound on the uncertain gains of the actuators--and is thus more affordable to implement. On the basis of the Lyapunov theorem, it is verified that all signals in the tracking control system of the underactuated MSVs are bounded. Finally, the effectiveness of the proposed control scheme is demonstrated by simulations and comparative results. 

In recent years, the application of artificial intelligence (AI) has become an integral part of a wide range of areas, including software engineering. By analyzing various data sources generated in software engineering, it can provide valuable insights into customer behavior, product performance, bugs and errors, and many more. In practice, however, AI for software analytics and business intelligence often remains at a prototypical stage, and the results are rarely used to make decisions based on data. To understand the underlying causes of this phenomenon, we conduct an explanatory case study consisting of and interview study and a survey on the challenges of realizing and utilizing artificial intelligence in the context of software-intensive businesses. As a result, we identify a vicious circle that prevents practitioners from moving from prototypical AI-based analytics to continuous and productively usable software analytics and business intelligence solutions. In order to break the vicious circle in a targeted manner, we identify a set of solutions based on existing literature as well as the previously conducted interviews and survey. Finally, these solutions are validated by a focus group of experts. (C) 2021 Elsevier Inc. All rights reserved.

Acoustic indices are valuable tools for measuring and tracking changes in biodiversity. However, the method used to collect acoustic index data can be made more effective by recent developments in electronics. The current process requires recording high-quality audio in the field and computing acoustic indices in the lab. This produces vast quantities of raw audio data, which limits the time that sensors can spend in the field and complicates data processing and analysis. Additionally, most field audio recorders are unable to log the full range of contextual environmental data that would help explain short-term variations. In this paper, we present the BioAcoustic Index Tool, a smart acoustic index and environmental sensor. The BioAcoustic Index Tool computes acoustic indices as audio is captured, storing only the index information, and logs temperature, humidity, and light levels. The sensor was able to operate completely autonomously for the entire five-month duration of the field study. In that time, it recorded over 4000 measurements of acoustic complexity and diversity all while producing the same amount of data that would be used to record 3 minutes of raw audio. These factors make the BioAcoustic Index Tool well-suited for large-scale, long-term acoustic biodiversity monitoring.

The importance of providing mechanisms and tools that effectively support the transition from implicit to explicit representations of Learning Design has been emphasised by previous research in the field of Technology-Enhanced Learning (TEL). In addition, the benefits of Game-based learning approaches have been long documented in the educational research literature. The paper presents the design, implementation and evaluation of a card game that aims to support the design process of TEL activities in higher education. The game was tested by a group of 36 students and tutors (n = 36) in higher education during an interactive workshop. Feedback was asked by the participants using an anonymous survey. The results reveal that the participants a) are satisfied with the game process, b) appreciate the groupwork and interaction taking place, and c) believe that they used their communication and collaboration skills. The paper includes the description of the outputs of a group (i.e., the cards selected for their TEL scenario and their actual TEL scenario) to exemplify that it is possible to use the game in order to elicit or diagnose existing LD knowledge from the game participants. The paper concludes on the usefulness of the approach suggested, limitations, and plans for future work.

Better home care and home care technologies are no longer requested solely by nonimmigrant older adults but also by members of the fast-growing older adult immigrant population. However, limited attention has been given to this issue, or to the use of technology in meeting the needs of aging populations. The objective of this review is to map existing knowledge of older adult immigrants' use of information and communication technologies for home care service published in scientific literature from 2014 to 2020. Twelve studies met the established eligibility criteria in a systematic literature search. The results showed older adult immigrants faced similar barriers, which were independent of their ethnic backgrounds but related to their backgrounds as immigrants including lower socioeconomic status, low language proficiency, and comparatively lower levels of social inclusion. Technology use could be facilitated if older adult immigrants received culturally-tailored products and support from family members and from society. The results imply that the included studies do not address or integrate cultural preferences in the development of information and communication technology for home care services. Caregivers might provide an opportunity to bridge gaps between older immigrants' cultural preferences and technology design. This specific research field would also benefit from greater interest in the development of novel methodologies.

We propose the Interactive Constrained MAP-Elites, a quality-diversity solution for game content generation, implemented as a new feature of the Evolutionary Dungeon Designer (EDD): a mixed-initiative co-creativity tool for designing dungeons. The feature uses the MAP-Elites algorithm, an illumination algorithm that segregates the population among several cells depending on their scores with respect to different behavioral dimensions. Users can flexibly and dynamically alternate between these dimensions anytime, thus guiding the evolutionary process in an intuitive way, and then incorporate suggestions produced by the algorithm in their room designs. At the same time, any modifications performed by the human user will feed back into MAP-Elites, closing a circular workflow of constant mutual inspiration. This paper presents the algorithm followed by an in-depth evaluation of the expressive range of all possible dimension combinations in several scenarios, and discusses their influence in the fitness landscape and in the overall performance of the procedural content generation in EDD.

The rise of digital technologies is a macro trend, forcing organizations to transform digitally. This so-called digital transformation (DT) is affecting the field of higher education, too. Higher education institutions (HEI) digitalize internal processes and offer digitally-enabled education services. Different types of barriers are challenging a successful DT and need to be mastered. Our study follows a longitudinal research design by surveying different student cohorts in the same courses. Before the pandemic, we identified the barriers to DT and transferred them into a research model. Pre-pandemic, we surveyed the influence of barriers perceived by management students on the DT process of their HEI. Taking the pandemic as a solid external driver on DT, we examined students’ intra-pandemic perception in the same courses as the pre-pandemic analysis. With pre-pandemic data, the projection explains over 50% of the adjustment problems of the DT process. Based on intra-pandemic data, the explanation decreases to 45%. Hypothetically, we expected a better explanation degree as an impact of the pandemic. Interestingly, results indicate that intra-pandemic perceptions got more complex and, therefore, less significant. 

Artificial intelligence (AI) and machine learning (ML) are increasingly broadly adopted in industry. However, based on well over a dozen case studies, we have learned that deploying industry-strength, production quality ML models in systems proves to be challenging. Companies experience challenges related to data quality, design methods and processes, performance of models as well as deployment and compliance. We learned that a new, structured engineering approach is required to construct and evolve systems that contain ML/DL components. In this chapter, the authors provide a conceptualization of the typical evolution patterns that companies experience when employing ML as well as an overview of the key problems experienced by the companies that they have studied. The main contribution of the chapter is a research agenda for AI engineering that provides an overview of the key engineering challenges surrounding ML solutions and an overview of open items that need to be addressed by the research community at large.

Given a set S of regions with piece-wise linear boundary and a positive angle α < 90°, we consider the problem of computing the locations and orientations of the minimum number of α-floodlights positioned at points in S which suffice to illuminate the entire x-axis. We show that the problem can be solved in O(n log n) time and O(n) space, where n is the number of vertices of the set S.

The impact of the Artificial Intelligence revolution is undoubtedly substantial in our society, life, firms, and employment. With data being a critical element, organizations are working towards obtaining high-quality data to train their AI models. Although data, data management, and data pipelines are part of industrial practice even before the introduction of ML models, the significance of data increased further with the advent of ML models, which force data pipeline developers to go beyond the traditional focus on data quality. The objective of this study is to analyze the impact of ML use cases on data pipelines. We assume that the data pipelines that serve ML models are given more importance compared to the conventional data pipelines. We report on a study that we conducted by observing software teams at three companies as they develop both conventional(Non-ML) data pipelines and data pipelines that serve ML-based applications. We study six data pipelines from three companies and categorize them based on their criticality and purpose. Further, we identify the determinants that can be used to compare the development and maintenance of these data pipelines. Finally, we map these factors in a two-dimensional space to illustrate their importance on a scale of low, moderate, and high.

Nearly every real-world deployment of machine learning models suffers from some form of shift in data distributions in relation to the data encountered in production. This aspect is particularly pronounced when dealing with streaming data or in dynamic settings (e.g. changes in data sources, behaviour and the environment). As a result, the performance of the models degrades during deployment. In order to account for these contextual changes, domain adaptation techniques have been designed for scenarios where the aim is to learn a model from a source data distribution, which can perform well on a different, but related target data distribution. In this paper we introduce a variational autoencoder-based multi-modal approach for the task of domain adaptation, that can be trained on a large amount of labelled data from the source domain, coupled with a comparably small amount of labelled data from the target domain. We demonstrate our approach in the context of human activity recognition using various IoT sensing modalities and report superior results when benchmarking against the effective mSDA method for domain adaptation.

Randomised field experiments, such as A/B testing, have long been the gold standard for evaluating the value that new software brings to customers. However, running randomised field experiments is not always desired, possible or even ethical in the development of automotive embedded software. In the face of such restrictions, we propose the use of the Bayesian propensity score matching technique for causal inference of observational studies in the automotive domain. In this paper, we present a method based on the Bayesian propensity score matching framework, applied in the unique setting of automotive software engineering. This method is used to generate balanced control and treatment groups from an observational online evaluation and estimate causal treatment effects from the software changes, even with limited samples in the treatment group. We exemplify the method with a proof-of-concept in the automotive domain. In the example, we have a larger control (Nc = 1100) fleet of cars using the current software and a small treatment fleet (Nt = 38), in which we introduce a new software variant. We demonstrate a scenario that shipping of a new software to all users is restricted, as a result, a fully randomised experiment could not be conducted. Therefore, we utilised the Bayesian propensity score matching method with 14 observed covariates as inputs. The results show more balanced groups, suitable for estimating causal treatment effects from the collected observational data. We describe the method in detail and share our configuration. Furthermore, we discuss how can such a method be used for online evaluation of new software utilising small groups of samples.

Data collected from in-service products play an important role in enabling software-intensive embedded systems suppliers to embrace data-driven practices. Data can be used in many different ways such as to continuously learn and improve the product, enhance post-deployment services, reduce operational cost or create a better user experience. While there is no shortage of possible use cases leveraging data from in-service products, software-intensive embedded systems companies struggle to continuously collect data from their in-service products. Often, data collection is done in an ad-hoc way and targeting specific use cases or needs. Besides, few studies have investigated data collection challenges in relation to the data dimensions, which are the minimum set of quantifiable data aspects that can define software-intensive embedded product data from a collection point of view. To help address data collection challenges, and to provide companies with guidance on how to improve this process, we conducted a case study at a large multinational telecommunications supplier focusing on data characteristics and collection challenges from the Radio Access Networks (RAN) products. We further investigated the relations of these challenges to the data dimensions to increase our understanding of how data dominions contribute to the challenges.

Interactive Machine Learning (ML) has the potential to lower the manual labelling effort needed, as well as increase classification performance by incorporating a human-in-the loop component. However, the assumptions made regarding the interactive behaviour of the human in experiments are often not realistic. Active learning typically treats the human as a passive, but always correct, participant. Machine teaching provides a more proactive role for the human, but generally assumes that the human is constantly monitoring the learning process. In this paper, we present an interactive online framework and perform experiments to compare active learning, machine teaching and combined approaches. We study not only the classification performance, but also the effort (to label samples) and attention (to monitor the ML system) required of the human. Results from experiments show that a combined approach generally performs better with less effort compared to active learning and machine teaching. With regards to attention, the best performing strategy varied depending on the problem setup.

A/B testing is gaining attention in the automotive sector as a promising tool to measure casual effects from software changes. Different from the web-facing businesses, where A/B testing has been well-established, the automotive domain often suffers from limited eligible users to participate in online experiments. To address this shortcoming, we present a method for designing balanced control and treatment groups so that sound conclusions can be drawn from experiments with considerably small sample sizes. While the Balance Match Weighted method has been used in other domains such as medicine, this is the first paper to apply and evaluate it in the context of software development. Furthermore, we describe the Balance Match Weighted method in detail and we conduct a case study together with an automotive manufacturer to apply the group design method in a fleet of vehicles. Finally, we present our case study in the automotive software engineering domain, as well as a discussion on the benefits and limitations of the A/B group design method.

Federated Learning, as a distributed learning technique, has emerged with the improvement of the performance of IoT and edge devices. The emergence of this learning method alters the situation in which data must be centrally uploaded to the cloud for processing and maximizes the utilization of edge devices' computing and storage capabilities. The learning approach eliminates the need to upload large amounts of local data and reduces data transfer latency with local data processing. Since the Federated Learning technique does not require centralized data for model training, it is better suited to edge learning scenarios in which nodes have limited data. However, despite the fact that Federated Learning has significant benefits, we discovered that companies struggle with integrating Federated Learning components into their systems. In this paper, we present case study research that describes reasons why companies anticipate Federated Learning as an applicable technique. Secondly, we summarize the services that a complete Federated Learning system needs to support in industrial scenarios and then identify the key challenges for industries to adopt and transition to Federated Learning. Finally, based on our empirical findings, we suggest five criteria for companies implementing reliable Federated Learning systems.

In this paper, we study explanations in a setting where human capabilities are in parity with Machine Learning (ML) capabilities. If an ML system is to be trusted in this situation, limitations in the trained ML model’s abilities have to be exposed to the end-user. A majority of current approaches focus on the task of creating explanations for a proposed decision, but less attention is given to the equally important task of exposing limitations in the ML model’s capabilities, limitations that in turn affect the validity of created explanations. Using a small-scale design experiment we compare human explanations with explanations created by an ML system. This paper explores and presents how the structure and terminology of scientific explanations can expose limitations in the ML models knowledge and be used as an approach for research and design in the area of explainable artificial intelligence.

The objective of this work is presenting a mobile platform for improving the individual development of social skills of people with mental disorders, offering them a mobile application which promotes independence and enhances social and cognitive abilities by means of geolocation and ludic reward. First, in order to improve the independence of the people with mental disorders we promote outings and physical activity by means of a mobile application which provides a personal map where familiar living places are located. In the map, the current location of the user is referenced between the familiar places. Additionally, the location is collected in a cloud server, where relatives and caregivers can locate him/her in case of need by SMS. Second, in order to improve their social skills, a mobile system of ludic rewards has been implemented using NFC tags. In this way, when the person with social disorder fulfills his/her tasks properly, the caregiver or family member brings closer an NFC tag with the value of the corresponding reward to the smartphone. So, the person with disabilities is able to check in the mobile application the reward points which he/she keeps based on his/her middle-term behavior. The virtual ludic money allows the child or person to enjoy activities, such as, watching TV, subtracting those points when they spend this reward. The system is developed as an easily scalable and configurable module to enable the personalization of parameters for each person with social disorder. 

Frequentist statistical methods, such as hypothesis testing, are standard practices in studies that provide benchmark comparisons. Unfortunately, these methods have often been misused, e.g., without testing for their statistical test assumptions or without controlling for familywise errors in multiple group comparisons, among several other problems. Bayesian data analysis (BDA) addresses many of the previously mentioned shortcomings but its use is not widely spread in the analysis of empirical data in the evolutionary computing community. This article provides three main contributions. First, we motivate the need for utilizing BDA and provide an overview of this topic. Second, we discuss the practical aspects of BDA to ensure that our models are valid and the results are transparent. Finally, we provide five statistical models that can be used to answer multiple research questions. The online Appendix provides a step-by-step guide on how to perform the analysis of the models discussed in this article, including the code for the statistical models, the data transformations, and the discussed tables and figures. 

Quantifying the number of occupants in an indoor space is useful for a wide variety of applications. Attempts have been made at solving the task using passive infrared (PIR) motion sensor data together with supervised learning methods. Collecting a large labeled dataset containing both PIR motion sensor data and ground truth people count is however time-consuming, often requiring one hour of observation for each hour of data gathered. In this paper, a method is proposed for generating such data synthetically. A simulator is developed in the Unity game engine capable of producing synthetic PIR motion sensor data by detecting simulated occupants. The accuracy of the simulator is tested by replicating a real-world meeting room inside the simulator and conducting an experiment where a set of choreographed movements are performed in the simulated environment as well as the real room. In 34 out of 50 tested situations, the output from the simulated PIR sensors is comparable to the output from the real-world PIR sensors. The developed simulator is also used to study how a PIR sensor’s output changes depending on where in a room a motion is carried out. Through this, the relationship between sensor output and spatial position of a motion is discovered to be highly non-linear, which highlights some of the difficulties associated with mapping PIR data to occupancy count. 

In recent years, with more edge devices being put into use, the amount of data that is created, transmitted and stored is increasing exponentially. Moreover, due to the development of machine learning algorithms, modern software-intensive systems are able to take advantage of the data to further improve their service quality. However, it is expensive and inefficient to transmit large amounts of data to a central location for the purpose of training and deploying machine learning models. Data transfer from edge devices across the globe to central locations may also raise privacy and concerns related to local data regulations. As a distributed learning approach, Federated Learning has been introduced to tackle those challenges. Since Federated Learning simply exchanges locally trained machine learning models rather than the entire data set throughout the training process, the method not only protects user data privacy but also improves model training efficiency. In this paper, we have investigated an advanced machine learning algorithm, Deep Neural Decision Forests (DNDF), which unites classification trees with the representation learning functionality from deep convolutional neural networks. In this paper, we propose a novel algorithm, AF-DNDF which extends DNDF with an asynchronous federated aggregation protocol. Based on the local quality of each classification tree, our architecture can select and combine the optimal groups of decision trees from multiple local devices. The introduction of the asynchronous protocol enables the algorithm to be deployed in the industrial context with heterogeneous hardware settings. Our AF-DNDF architecture is validated in an automotive industrial use case focusing on road objects recognition and demonstrated by an empirical experiment with two different data sets. The experimental results show that our AF-DNDF algorithm significantly reduces the communication overhead and accelerates model training speed without sacrificing model classification performance. The algorithm can reach the same classification accuracy as the commonly used centralized machine learning methods but also greatly improve local edge model quality.

The adoption of continuous software engineering practices such as DevOps (Development and Operations) in business operations has contributed to significantly shorter software development and deployment cycles. Recently, the term MLOps (Machine Learning Operations) has gained increasing interest as a practice that brings together data scientists and operations teams. However, the adoption of MLOps in practice is still in its infancy and there are few common guidelines on how to effectively integrate it into existing software development practices. In this paper, we conduct a systematic literature review and a grey literature review to derive a framework that identifies the activities involved in the adoption of MLOps and the stages in which companies evolve as they become more mature and advanced. We validate this framework in three case companies and show how they have managed to adopt and integrate MLOps in their large-scale software development companies. The contribution of this paper is threefold. First, we review contemporary literature to provide an overview of the state-of-the-art in MLOps. Based on this review, we derive an MLOps framework that details the activities involved in the continuous development of machine learning models. Second, we present a maturity model in which we outline the different stages that companies go through in evolving their MLOps practices. Third, we validate our framework in three embedded systems case companies and map the companies to the stages in the maturity model. 

In practice, supervised learning algorithms require fully labeled datasets to achieve the high accuracy demanded by current modern applications. However, in industrial settings supervised learning algorithms can perform poorly because of few labeled instances. Semi-supervised learning (SSL) is an automatic labeling approach that utilizes complete labels to infer missing labels in partially complete datasets. The high number of available SSL algorithms and the lack of systematic comparison between them leaves practitioners without guidelines to select the appropriate one for their application. Moreover, each SSL algorithm is often validated and evaluated in a small number of common datasets. However, there is no research that examines what datasets are suitable for comparing different SSL algorihtms. The purpose of this paper is to empirically evaluate the suitability of the datasets commonly used to evaluate and compare different SSL algorithms. We performed a simulation study using twelve datasets of three different datatypes (numerical, text, image) on thirteen different SSL algorithms. The contributions of this paper are two-fold. First, we propose the use of Bayesian congeneric item response theory model to assess the suitability of commonly used datasets. Second, we compare the different SSL algorithms using these datasets. The results show that with except of three datasets, the others have very low discrimination factors and are easily solved by the current algorithms. Additionally, the SSL algorithms have overlapping 90% credible intervals, indicating uncertainty in the difference between the accuracy of these SSL models. The paper concludes suggesting that researchers and practitioners should better consider the choice of datasets used for comparing SSL algorithms.

In the complex study to obtain indicators in the autism spectrum disorder it is very common to perform many and very complex tasks. Often, these tasks require the completion of a series of forms and surveys that are even more complex and tedious, which means that the accuracy of the reports is not always satisfactory. In this paper, we propose a general architecture based on machine learning techniques and data mining for prediction of the main indicators in the diagnosis and intervention of the autistic spectrum disorder. The main idea of this approach is to replace those print documents by mobile tests, tablet or smartphones tests through games, store them in databases and analyse them. Furthermore, very often these last two steps are not undertaken with the lack of quantitative and qualitative analysis that could be generated. Finally, the presented architecture is oriented to data collection with the objective of the creation of large specialized datasets. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Data pipelines play an important role throughout the data management process whether these are used for data analytics or machine learning. Data-driven organizations can make use of data pipelines for producing good quality data applications. Moreover, data pipelines ensure end-to-end velocity by automating the processes involved in extracting, transforming, combining, validating, and loading data for further analysis and visualization. However, the robustness of data pipelines is equally important since unhealthy data pipelines can add more noise to the input data. This paper identifies the essential elements for a robust data pipeline and analyses the trade-off between data pipeline robustness and complexity.

In recent years, with the development of computation capability in devices, companies are eager to investigate and utilize suitable ML/DL methods to improve their service quality. However, with the traditional learning strategy, companies need to first build up a powerful data center to collect and analyze data from the edge and then perform centralized model training, which turns out to be inefficient. Federated Learning has been introduced to solve this challenge. Because of its characteristics such as model-only exchange and parallel training, the technique can not only preserve user data privacy but also accelerate model training speed. The method can easily handle real-time data generated from the edge without taking up a lot of valuable network transmission resources. In this paper, we introduce an approach to end-to-end on-device Machine Learning by utilizing Federated Learning. We validate our approach with an important industrial use case in the field of autonomous driving vehicles, the wheel steering angle prediction. Our results show that Federated Learning can significantly improve the quality of local edge models and also reach the same accuracy level as compared to the traditional centralized Machine Learning approach without its negative effects. Furthermore, Federated Learning can accelerate model training speed and reduce the communication overhead, which proves that this approach has great strength when deploying ML/DL components to various real-world embedded systems.

For patients suffering from a stroke, the time until the start of the treatment is a crucial factor with respect to the recovery from this condition. In rural regions, transporting the patient to an adequate hospital typically delays the diagnosis and treatment of a stroke, worsening its prognosis. To reduce the time to treatment, different policies can be applied. This includes, for instance, the use of Mobile Stroke Units (MSUs), which are specialized ambulances that can provide adequate care closer to where the stroke occurred. To simulate and assess different stroke logistics policies, such as the use of MSUs, a major challenge is the realistic modeling of the patients. In this article, we present an approach for generating an artificial population of stroke patients to simulate when and where strokes occur. We apply the model to the region of Skåne, where we investigated the relevance of travel behavior on the spatial distribution of stroke patients.

The Scandinavian countries are often seen as a unity. However, during the COVID-19 pandemic striking differences on how the countries approached the crisis became evident. This quantitative-ethnographic (QE) study aimed to understand political and cultural similarities and differences between the three Scandinavian countries – Denmark, Norway and Sweden – through their crisis communications during the COVID-19 pandemic. Specifically, we focused on how the health authorities of the three countries, in their press releases, treated information about COVID-19 and acted in four fields: reorganization of population behavior, containment of viral transmission, preparation of health systems, and management of socioeconomic impacts. As a methodology, the QE tools nCoder and ENA were applied, respectively: to code the press releases and to correlate the treatment of information with the four fields of action. © 2021, Springer Nature Switzerland AG.

A significant amount of research effort is put into studying machine learning (ML) and deep learning (DL) technologies. Real-world ML applications help companies to improve products and automate tasks such as classification, image recognition and automation. However, a traditional “fixed” approach where the system is frozen before deployment leads to a sub-optimal system performance. Systems autonomously experimenting with and improving their own behavior and performance could improve business outcomes but we need to know how this could actually work in practice. While there is some research on autonomously improving systems, the focus on the concepts and theoretical algorithms. However, less research is focused on empirical industry validation of the proposed theory. Empirical validations are usually done through simulations or by using synthetic or manually alteration of datasets. The contribution of this paper is twofold. First, we conduct a systematic literature review in which we focus on papers describing industrial deployments of autonomously improving systems and their real-world applications. Secondly, we identify open research questions and derive a model that classifies the level of autonomy based on our findings in the literature review. 

With the increasing attention on Machine Learning applications, more and more companies are involved in implementing AI components into their software products in order to improve the service quality. With the rapid growth of distributed edge devices, Federated Learning has been introduced as a distributed learning technique, which enables model training in a large decentralized network without exchanging collected edge data. The method can not only preserve sensitive user data privacy but also save a large amount of data transmission bandwidth and the budget cost of computation equipment. In this paper, we provide a state-of-the-art overview of the empirical results reported in the existing literature regarding Federated Learning. According to the problems they expressed and solved, we then categorize those deployments into different application domains, identify their challenges and then propose six open research questions. 

Technological artefacts loaded with user representations, implicit or explicit, tell us something about the expectations of older people. The provision of technology for older people does not arise from a straightforward relationship between engineers and designers and older users. Against this background, it is reasonable to ask what we can learn from exploring user representations over time. An obvious assumption might be that user representations originating from the 1960s or 1970s are quite different from current user representations. If we consider the extensive technology development that has taken place since then, and the increase in life expectancy, changing lifestyles and changing expectations of later life, it would be reasonable to assume that user representations of older people have changed at the same pace. But have they? This chapter explores representations of older users in technological innovations implemented in home-care and home-help services in Sweden during the period 1960–2018.

The introduction of this book sets the stage of performing social simulations in a crisis. The contents of the book are based on the experience of creating a large scale and complex social simulation for the Covid-19 crisis. However, the contents are reaching much further than just this experience. We will show the general contribution that social simulations based on fundamental social-psychological principles can have in times of crises. In times of big societal changes due to a pandemic or other disaster, these simulations can give handles to support decision makers in their difficult task to act in a very short time with many uncertainties. Besides giving our results, we also will indicate why the results are trustworthy and interesting. Finally we also look what challenges should be picked up to convert the successful project into a sustainable research area.

The reliance on data donation from citizens as a driver for research, known as citizen science, has accelerated during the Sars-Cov-2 pandemic. An important enabler of this is Internet of Things (IoT) devices, such as mobile phones and wearable devices, that allow continuous data collection and convenient sharing. However, potentially sensitive health data raises privacy and security concerns for citizens, which research institutions and industries must consider. In e-commerce or social network studies of citizen science, a privacy calculus related to user perceptions is commonly developed, capturing the information disclosure intent of the participants. In this study, we develop a privacy calculus model adapted for IoT-based health research using citizen science for user engagement and data collection. Based on an online survey with 85 participants, we make use of the privacy calculus to analyse the respondents' perceptions. The emerging privacy personas are clustered and compared with previous research, resulting in three distinct personas which can be used by designers and technologists who are responsible for developing suitable forms of data collection. These are the 1) Citizen Science Optimist, the 2) Selective Data Donor, and the 3) Health Data Controller. Together with our privacy calculus for citizen science based digital health research, the three privacy personas are the main contributions of this study.

Smart Learning Environments and Learning Analytics hold promise of providing personalized support to learners according to their individual needs and context. This support can be achieved by collecting and analyzing data from the different learning tools and systems that are involved in the learning experience. This paper presents a first exploration of requirements and considerations for the integration of two systems: MBOX, a Multimodal Learning Analytics system for the physical space (human behavior and learning context), and SCARLETT, an SLE for the support during across-spaces learning situations combining different learning systems. This integration will enable the SLE to have access to a new and wide range of information, notably students’ behavior and social interactions in the physical learning context (e.g. classroom). The integration of multimodal data with the data coming from the digital learning environments will result in a more holistic system, therefore producing learning analytics that trigger personalized feedback and learning resources. Such integration and support is illustrated with a learning scenario that helps to discuss how these analytics can be derived and used for the intervention by the SLE.

Multimodal Learning Analytics (MMLA) provides opportunities for understanding and supporting collaborative problem-solving. However, the implementation of MMLA systems is challenging due to the lack of scalable technologies and limited solutions for collecting data from group work. This paper proposes the Multimodal Box (MBOX), an IoT-based system for MMLA, allowing the collection and processing of multimodal data from collaborative learning tasks. MBOX investigates the development and design for an IoT focusing on small group work in real-world settings. Moreover, MBOX promotes adaptation to different learning environments and enables a better scaling of computational resources used within the learning context.

Digitization is among the macro-trends that significantly determine the business world of the 21st century. Firms striving to succeed in this environment have to develop new strategic approaches. The accelerating development of information technology drives digitization. Thus, IT strategy and business strategy need to be integrated. In this context, information systems literature promotes the concept of digital business strategy, reflecting a fusion between IT strategy and business strategy. However, currently, we do not know much about the characteristics and different types of such digital business strategies. To this end, we develop a conceptually and empirically grounded typology of digital business strategies. Based on a dataset of 281 firms worldwide, we carry out a cluster analysis, identify basic types of digital business strategies and evaluate their effects on firm performance. The paper contributes to a better understanding of new business strategy concepts. It thus enriches the extant insights from innovation management, strategic management, and information systems literature in the context of digitization.

Objectives: Digital transformation (DT) has become an imperative within research and practice. Still, companies experience obstacles when trying to pursue a successful DT. Numerous scientific sources have dealt with the identification of barriers to DT. In doing so, scientists have already produced reviews to identify and classify the barriers to DT. However, the scientific work often relates to specific company contexts. In addition, there is no structured overview of the literature on how to overcome barriers to DT. The mere identification provides an incomplete view on the barriers to DT and needs to be complemented by approaches to overcome them. Thus, our research question is: Which barriers and recommendations for action to DT exist within the scientific literature and how can they be clustered according to a holistic sociotechnical perspective?

Data and Method: Our study follows the approach of a structured literature review combined with additional focus group work to generate a concept matrix to structure barriers and recommendations for action. The conducted literature search generated 562 articles (without duplicates). After a first screening 148 articles were deemed to be applicable for our study. A more in-depth qualitative check generated 99 relevant articles. Different sections of these articles were openly coded into 178 barriers and 161 recommendations for action. These codes were then clustered in focus group sessions.

Results: The result of our research approach is a framework containing clustered barriers and cluster-related recommendations for overcoming. The following clusters were identified: individual, technical, financial, organizational alignment, organizational design, organizational culture, market environment, and regulatory. Our review discloses that not all clusters receive equal attention in the literature. In particular, organizational culture is given less consideration, while especially individual, technical and financial is in focus. The identified recommendations for action show that not all barriers can be solved by the companies themselves but require governmental support instead.

Conclusions: Our study generated a holistic framework. As barriers either slow down or even entirely hinder DT, understanding their nature is essential. Our discussion reveals that several barriers are contrasting each other. This implies that managers need to carefully balance DT initiatives. The framework provides guidance on doing so. The findings also provide a solid foundation for future research, as our literature review presents a state-of-the-art of current research and reveals research gaps.

Drones have been discussed frequently in both governmental and commercial sectors for their normalization in the airspace. Nonetheless, drones bring diverse privacy concerns to users. In this paper, we explore the ramifications to data privacy from the perspective of drone owners. To investigate privacy in this context, four experiments targeting a commercial drone were conducted using open-source software. The experiments identified personal data (e.g., audio, video, and location) that are at risk of being compromised particularly through the execution of a basic deauthentication attack launched at a commercial drone. Our findings indicate the severity of risks affecting commercial drones. This makes the case for more effective privacy regulations and better guidelines suitable for securing drones.

Remote health monitoring is a trend for better health management which necessitates the need for secure monitoring and privacy-preservation of patient data. Moreover, accurate and continuous monitoring of personal health status may require expert validation in an active learning strategy. As a result, this paper proposes a Federated Interactive Learning IoT-based Health Monitoring Platform (FIL-IoT-HMP) which incorporates multi-expert feedback as ‘Human-in-the-loop’ in an active learning strategy in order to improve the clients’ Machine Learning (ML) models. The authors have proposed an architecture and conducted an experiment as a proof of concept. Federated learning approach has been preferred in this context given that it strengthens privacy by allowing the global model to be trained while sensitive data is retained at the local edge nodes. Also, each model’s accuracy is improved while privacy and security of data has been upheld.

How augmented reality and virtual reality are taking their places in contemporary media culture alongside film and television.

This book positions augmented reality (AR) and virtual reality (VR) firmly in contemporary media culture. The authors view AR and VR not as the latest hyped technologies but as media—the latest in a series of what they term “reality media,” taking their place alongside film and television. Reality media inserts a layer of media between us and our perception of the world; AR and VR do not replace reality but refashion a reality for us. Each reality medium mediates and remediates; each offers a new representation that we implicitly compare to our experience of the world in itself but also through other media.

The authors show that as forms of reality media emerge, they not only chart a future path for media culture, but also redefine media past. With AR and VR in mind, then, we can recognize their precursors in eighteenth-century panoramas and the Broadway lights of the 1930s. A digital version of Reality Media, available through the book's website, invites readers to visit a series of virtual rooms featuring interactivity, 3-D models, videos, images, and texts that explore the themes of the book.

Electric vehicles (EVs) are environmentally friendly and are considered to be a promising approach toward a green transportation infrastructure with lower greenhouse gas emissions. However, the limited driving range of EVs demands a strategic allocation of charging facilities, hence providing recharging opportunities that help reduce EV owners' anxiety about their vehicles' range. In this paper, we study a set covering method where self-avoiding walks are utilized to find the most significant locations for charging stations. In the corresponding optimization problem, we derive a lower bound of the number of charging stations in a transportation network to obtain full coverage of the most probable routes. The proposed method is applied to a transportation network of the southern part of Sweden.