Web accessibility is becoming a relevant topic with an increased number of people with disabilities and the elderly using the web. Numerous legislations are being passed that require the web to be universally accessible to all people, regardless of their abilities and age. Despite this trend, university curricula still teach traditional web development without addressing accessibility as a topic. To investigate this matter closely, we studied the syllabi of web development courses at one university to evaluate whether the topic of accessibility was taught there. Additionally, we conducted a survey with nineteen students who were enrolled in a web development course, and we interviewed three lecturers from the same university. Our findings suggest that the topic of accessibility is not covered in web development courses, although both students and lecturers think that it should. This generates lack of competence in accessibility. The findings also confirm the finding of previous studies that, among web developers, there is a low familiarity with accessibility guidelines and policies. An interesting finding we uncovered was that gender affects the motivation to learn about accessibility. Females were driven by personal reasons, which we attribute to females having an increased sense of empathy. Finally, our participants were divided in their opinions whether accessibility contributes to usability.

In order to distinguish themselves from their competitors, software service providers constantly try to assess and improve customer satisfaction. However, measuring customer satisfaction in a continuous way is often time and cost intensive, or requires effort on the customer side. Especially in B2B contexts, a continuous assessment of customer satisfaction is difficult to achieve due to potential restrictions and complex provider-customer-end user setups. While concepts such as web usage mining enable software providers to get a deep understanding of how their products are used, its application to quantitatively measure customer satisfaction has not yet been studied in greater detail. For that reason, our study aims at combining existing knowledge on customer satisfaction, web usage mining, and B2B service characteristics to derive a model that enables an automated calculation of quantitative customer satisfaction scores. We apply web usage mining to validate these scores and to compare the usage behavior of satisfied and dissatisfied customers. This approach is based on domain-specific service quality and web usage metrics and is, therefore, suitable for continuous measurements without requiring active customer participation. The applicability of the model is validated by instantiating it in a real-world B2B online platform.

Nowadays, machine learning (ML) is an integral component in a wide range of areas, including software analytics (SA) and business intelligence (BI). As a result, the interest in custom ML-based software analytics and business intelligence solutions is rising. In practice, however, such solutions often get stuck in a prototypical stage because setting up an infrastructure for deployment and maintenance is considered complex and time-consuming. For this reason, we aim at structuring the entire process and making it more transparent by deriving an end-to-end framework from existing literature for building and deploying ML-based software analytics and business intelligence solutions. The framework is structured in three iterative cycles representing different stages in a model’s lifecycle: prototyping, deployment, update. As a result, the framework specifically supports the transitions between these stages while also covering all important activities from data collection to retraining deployed ML models. To validate the applicability of the framework in practice, we compare it to and apply it in a real-world ML-based SA/BI solution.

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.

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 gets stuck in a prototypical stage and the results are rarely used to make decisions based on data. To understand the underlying root causes of this phenomenon, we conduct both an explanatory case 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 analytics to continuous and productively usable software analytics and business intelligence based on AI.

A wide variety of tools to monitor and track software systems, such as websites or smartphone applications, during runtime already exists. However, their aggregated results are often not sufficient to answer questions on a product management level since these questions address several levels of complexity and abstractions, and tend to be formulated on a rather high level, for instance concerning the efficiency of their website structure for their users. A straightforward mapping between low level metrics and high level insights is typically not possible. This causes a gap that makes it challenging to continuously provide quantitative high-level insights in real-time. In order to address this challenge, we conducted a study within three distinct platforms and products, and propose a model based on our results. After defining a case for each of the independent platforms and products, we implemented a process to measure high level insights using low level metrics for each of these cases. Next, we compared the procedures and steps that were taken in each of the cases and derived a model that describes a generic approach how to utilize and process data in order to gain higher level insights. Our model structures the steps from data to knowledge over different levels of complexity and abstraction, namely operational, tactical, and strategic. Thereby, the knowledge acquired in each phase serves as input in the next phase which increases the measurable level of complexity with each iteration. Since the steps in our model are specifically arranged as a pipeline, it enables practitioners to automate a continuous and quantitative measurement of high level insights in real-time.

Context: Nowadays, the hype around artificial intelligence is at its absolute peak. Large amounts of data are collected every second of the day and a variety of tools exists to enable easy analysis of data. In practice, however, making meaningful use of it is way more challenging. For instance, affected stakeholders often struggle to specify their information needs and to interpret the results of such analyses. Objective: In this study we investigate how to enable continuous monitoring of information needs, and the generation of knowledge and insights for various stakeholders involved in the lifecycle of software-intensive products. The overarching goal is to support their decision making by providing relevant insights related to their area of responsibility. Methods: We implement multiple monitoringand decision-making frameworks for six individual, real-world cases selected from three different platforms and covering four types of stakeholders. We compare the individual procedures to derive a generic process for instantiating such frameworks as well as a model to scale it up for multiple stakeholders. Results: For one, we discovered that information needs of stakeholders are often related to a limited subset of data sources and should be specified in stages. For another, stakeholders often benefit from sharing and reusing existing components among themselves in later phases. Specifically, we identify three types of reuse: (1) Data and knowledge, (2) tools and methods, and (3) concepts. As a result, key aspects of our model are iterative feedback and specification cycles as well as the reuse of appropriate components to speed up the instantiation process and maximize the efficiency of the model. Conclusion: Our results indicate that knowledge and insights can be generated much faster and stakeholders feel the benefits of the analysis very early on by iteratively specifying information needs and by systematically sharing and reusing knowledge, tools and concepts.

The shift from sequential to agile software development originates from relatively small and co-located teams but soon gained prominence in larger organizations. How to apply and scale agile practices to fit the needs of larger projects has been studied to quite an extent in previous research. However, scaling agile beyond organizational boundaries, for instance in a software ecosystem context, raises additional challenges that existing studies and approaches do not yet investigate or address in great detail. For that reason, we conducted a case study in two software ecosystems that comprise several agile actors from different organizations and, thereby, scale development across organizational boundaries, in order to elaborate and understand their coordination challenges. Our results indicate that most of the identified challenges are caused by long communication paths and a lack of established processes to facilitate these paths. As a result, the participants in our study, among others, experience insufficient responsivity, insufficient communication of prioritizations and deliverables, and alterations or loss of information. As a consequence, agile practices need to be extended to fit the identified needs.

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.

During the last decade, the way people learn has seen a big shift from the traditional classroom that purely uses printed material to the contemporary classroom that utilizes digital technologies for the teaching material (Al-Emran and Shaalan, 2015). In this paper we present Vault!, an Android mobile app that combines the benefits of mobile learning and relational learning, while at the same time reaps the reward of the community-based learning model existing in parkour. We also provide a theoretical support for parkour as a general-purpose challenge-based educational model, as well as an analysis of popular mobile learning apps, both of them resulting in the design and development of the presented application.

Multiplayer online battle arena (MOBA) games are a recent huge success both in the video game industry and the international eSports scene. These games encourage team coordination and cooperation, short and long-term planning, within a real-time combined action and strategy gameplay. Artificial intelligence (AI) and computational intelligence (CI) in games research competitions offer a wide variety of challenges regarding the study and application of AI techniques to different game genres. These events are widely accepted by the AI/CI community as a sort of AI benchmarking that strongly influences many other research areas in the field. This paper presents and describes in detail the Dota 2 (Defense of the Ancients 2) Bot competition and the Dota 2 AI framework that supports it. This challenge aims to join both the MOBAs and AI/CI game competitions, inviting participants to submit AI controllers for the successful MOBA Dota 2 to play in 1v1 matches, which aims for fostering research on AI techniques for real-time games. The Dota 2 AI framework makes use of the actual Dota 2 game mudding capabilities to enable to connect external AI controllers to actual Dota 2 game matches using the original F2P game.

As technology has become more advanced, self-tracking devices and data have become normal elements of everyday life. Imagining Personal Data examines the implications of the rise of body monitoring and digital self-tracking for how we inhabit, experience and imagine our everyday worlds. Through a focus on how it feels to live in environments where data is emergent, present, and characterised by a sense of uncertainty, the authors argue for a new approach to understanding the implications of self-tracking, and questions what this means for the status of big data. With contributions ranging across the social sciences, the book brings together the concerns of scholars working in design, social sciences, philosophy, and human-computer interaction. It problematizes the body and senses in relation to data and tracking devices, and presents an accessible analytical account of the sensory and affective experiences of self-tracking.

The world is gearing towards renewable energy sources, due to the numerous negative repercussions of fossil fuels. There is a need to increase the efficiency of power generation, transmission, distribution, and use. The proposed work intends to decrease household electricity use and provide an intelligent home automation solution with ensembled machine learning algorithms. It also delivers organized information about the usage of each item while automating the use of electrical appliances in a home. Experimental results show that with XGBoost and Random Forest classifiers, electricity usage can be fully automated at an accuracy of 79%, thereby improving energy utilization efficiency and improving quality of life of the user.

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.

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.

This paper presents a new practical approach to optimally allocate charging stations in large-scale transportation networks for electric vehicles (EVs). The problem is of particular importance to meet the charging demand of the growing fleet of alternative fuel vehicles. Considering the limited driving range of EVs, there is need to supply EV owners with accessible charging stations to reduce their range anxiety. The aim of the Route Node Coverage (RNC) problem, which is considered in the current paper, is to find the minimum number of charging stations, and their locations in order to cover the most probable routes in a transportation network. We propose an iterative approximation technique for RNC, where the associated Integer Problem (IP) is solved by exploiting a probabilistic random walk route selection, and thereby taking advantage of the numerical stability and efficiency of the standard IP software packages. Furthermore, our iterative RNC optimization procedure is both pertinent and straightforward to implement in computer coding and the design technique is therefore highly applicable. The proposed optimization technique is applied on the Sioux-Falls test transportation network, and in a large-scale case study covering the southern part of Sweden, where the focus is on reaching the maximum coverage with a minimum number of charging stations. The results are promising and show that the flexibility, smart route selection, and numerical efficiency of the proposed design technique, can pick out strategic locations for charging stations from thousands of possible locations without numerical difficulties.

Traffic flows play a very important role in transportation engineering. In particular, link flows are a source of information about the traffic state, which is usually available from the authorities that manage road networks. Link flows are commonly used in both short-term and long-term planning models for operation and maintenance, and to forecast the future needs of transportation infrastructure. In this paper, we propose a model to study how traffic flow in one location can be expected to reflect the traffic flow in a nearby region. The statistical basis of the model is derived from link flows to find estimates of the distribution of traffic flows in junctions. The model is evaluated in a numerical study, which uses real link flow data from a transportation network in southern Sweden. The results indicate that the model may be useful for studying how large departing flows from a node reflect the link flows in a neighboring geographic region.

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.

With the increased availability of new and better computer processing units (CPUs) as well as graphical processing units (GPUs), the interest in statistical learning and deep learning algorithms for classification tasks has grown exponentially. These classification algorithms often require the presence of fully labeled instances during the training period for maximum classification accuracy. However, in industrial applications, data is commonly not fully labeled, which both reduces the prediction accuracy of the learning algorithms as well as increases the project cost to label the missing instances. The purpose of this paper is to survey the current state-of-the-art literature on machine learning algorithms that are used for assisted or automatic labeling and to understand where these are used. We performed a systematic mapping study and identified 52 primary studies relevant to our research. This paper provides three main contributions. First, we identify the existing machine learning algorithms for labeling and we present a taxonomy of these algorithms. Second, we identify the datasets that are used to evaluate the algorithms and we provide a mapping of the datasets based on the type of data and the application area. Third, we provide a process to support people in industry to optimally label their dataset. The results presented in this paper can be used by both researchers and practitioners aiming to improve the missing labels with the aid of machine algorithms or to select appropriate datasets to compare new state-of-the art algorithms in their respective application area.

The lack of labeled data is a major problem in both research and industrial settings since obtaining labels is often an expensive and time-consuming activity. In the past years, several machine learning algorithms were developed to assist and perform automated labeling in partially labeled datasets. While many of these algorithms are available in open-source packages, there is a lack of research that investigates how these algorithms compare to each other for different types of datasets and with different percentages of available labels. To address this problem, this paper empirically evaluates and compares seven algorithms for automated labeling in terms of their accuracy. We investigate how these algorithms perform in twelve different and well-known datasets with three different types of data, images, texts, and numerical values. We evaluate these algorithms under two different experimental conditions, with 10% and 50% labels of available labels in the dataset. Each algorithm, in each dataset for each experimental condition, is evaluated independently ten times with different random seeds. The results are analyzed and the algorithms are compared utilizing a Bayesian Bradley-Terry model. The results indicate that the active learning algorithms using the query strategies uncertainty sampling, QBC and random sampling are always the best algorithms. However, this comes with the expense of increased manual labeling effort. These results help machine learning practitioners in choosing optimal machine learning algorithms to label their data.

Labeling is a cornerstone of supervised machine learning. However, in industrial applications, data is often not labeled, which complicates using this data for machine learning. Although there are well-established labeling techniques such as crowdsourcing, active learning, and semi-supervised learning, these still do not provide accurate and reliable labels for every machine learning use case in the industry. In this context, the industry still relies heavily on manually annotating and labeling their data. This study investigates the challenges that companies experience when annotating and labeling their data. We performed a case study using a semi-structured interview with data scientists at two companies to explore their problems when labeling and annotating their data. This paper provides two contributions. We identify industry challenges in the labeling process, and then we propose mitigation strategies for these challenges.

Welfare technologies have been proposed in Scandinavian countries as way to ensure accessible and efficient care to those who need it. Significant investments have been made to develop and deploy these technologies. This study used a multiple case study design to explore how welfare technologies are implemented in Swedish eldercare practices. The multiple case study generated detailed knowledge and insights from a broad perspective on the employment of welfare technologies within various municipalities. The study revealed three approaches for integrating welfare technologies into municipal eldercare services: as an end-product, as a project, and as a strategy. Findings indicate that municipal welfare technology practices are diverse and multifaceted, yet implementing such practices is a complex process. This study proposes a focus shift, from technological solutions to organizational context, eldercare personnel, and care receivers.

We do not yet know how the robotization of eldercare will unfold, but one thing is clear: technology mediates human practices and experiences [1]. As such, care robots will co-shape the actions of care givers and older people and influence the perceptions and experiences of old age. The robotization of eldercare means that it is essential for developers, policy makers, and researchers to become increasingly aware of the intertwined and implicit expectations that older people impose on care robots. This paper both zooms in towards older people’s individual expectations and zooms out towards expectation configurations at a group level and the expectation imagery of care robots in future eldercare.

Digital health and welfare technologies and artificial intelligence are proposed to revolutionise healthcare systems around the world by enabling new models of care. Digital health and welfare technologies enable remote monitoring and treatments, and artificial intelligence is proposed as a means of prediction instead of reaction to individuals' health and as an enabler of proactive care and rehabilitation. The digital transformation not only affects hospital and primary care but also how the community meets older people's needs. Community care is often provided by informal and formal care-givers, most of whom are women. Gender equality is at the heart of many national strategies, but do all genders have equal rights, responsibilities and opportunities when it comes to community care and its digital transformation? The digital transformation of community care is entangled with how care is provided to older people and the working conditions of community-care professionals. Current and, even more so, future community-care systems are and will be partly constituted by networks of technological artefacts. These health and welfare technological artefacts and the discourse surrounding them mediate and constitute social relations and community care. This article looks into how health and welfare technology and artificial intelligence-based devices and systems mediate and constitute gender relations in community care and presents an argument for reflexivity, embodiment, pluralism, participation and ecology as an alternative strategy to treating community care as one-size-fit-all and being blind to gender-related issues.

AIM: Technology affects almost all aspects of modern eldercare. Ensuring ethical decision-making is essential as eldercare becomes more digital; each decision affects a patient's life, self-esteem, health and wellness.

METHODS: We conducted a survey and interviews with eldercare professionals to better understand the behavioural ethics and decision making involved in the digital transition of eldercare.

CONCLUSION: Our qualitative analysis showed three recurrent roles among eldercare professionals in regard to digital service transformation; makers, implementers and maintainers. All three encountered challenging and stressful ethical dilemmas due to uncertainty and a lack of control. The matter of power relations, the attempts to standardize digital solutions and the conflict between cost efficiency and if digital care solutions add value for patients, all caused moral dilemmas for eldercare professionals. The findings suggest a need for organizational infrastructure that promotes ethical conduct and behaviour, ethics training and access to related resources. Implications for rehabilitation The transition to digital care service is not neutral, but value-laden. Digital transformation affects ethical behaviour and decision-making. The decision as to which digital services should be developed and deployed must include eldercare professionals and not lay solely in the hands of managers, technologists and economists. We must move away from attempting to fit standardized solutions to a heterogenous group of older patients; accommodating the pluralism of patients' needs and wants protects their dignity, autonomy and independence. As digital care practices evolve, so too must organizational structures that promote ethical conduct.

Care robots are often portrayed as an exciting new technology for improving care practices. Whether these robots will be accepted and integrated into care work or not, is likely to be affected by the assumptions, expectations and understandings held by potential end users, such as frontline staff and the people that are cared for. This paper describes how the conceptual framework of technological frames was used to identify the nature of care robots, care robots in use and care robot strategy as shared group level assumptions, expectations and understandings of care robots among care staff and potential care receivers. Focus groups were conducted with 94 participants. These groups consisted of line managers, frontline care staff, older people and students training to become carers. The technological frame of the nature of care robots revealed two complementary components: care robots as a threat to the quality of care, and care robots as substitute for humans and human care, held together by imaginaries of care robots. The technological frame of care robots in use revealed aspects of prospective end-users' uncertainty of their ability to handle care robots, and their own perceived lack of competence and knowledge about care robots. In addition, the following potential criteria for successful use of care robots were identified: adequate training, incentives for usage (needs and motives), usability, accessibility and finances. The technological frame of care robot strategy was revealed as believed cost savings and staff reduction. The novelty of the results, and their relevance for science and practice, is derived from the theoretical framework which indicates that adoption of care robots will be dependent on how well societies succeed in collectively shaping congruent technological frames among different stakeholders and aligning technological development accordingly.

Practice-based Experiential Learning Analytics Research and Support (PELARS) is a project about learning and making. The PELARS project finds ways of generating "analytics" (data about the learning process and analysis of this data), which helps learners and teachers by providing feedback from hands-on, project-based and experiential learning situations. In this paper, we present our proposal for improving analytics education with hands-on, project-based and experimental scenarios for engineering students. This is done through teacher and learner engagement, user studies and evaluated trials, performed at UCV (University of Craiova, Romania) and DTU Diplom (Technical University of Denmark, Campus Ballerup, Denmark). The PELARS project provides technological tools and ICT-based methods for collecting activity data ( moving image-based and embedded sensing) for learning analytics (data-mining and reasoning) of practice-based and experiential STEM.

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.

Henzinger et al. posed the so-called Online Boolean Matrix-vector Multiplication (OMv) conjecture and showed that it implies tight hardness results for several basic dynamic or partially dynamic problems [STOC'15]. We first show that the OMv conjecture is implied by a simple off-line conjecture that we call the MvP conjecture. We then show that if the definition of the OMv conjecture is generalized to allow individual (i.e., it might be different for different matrices) polynomial-time preprocessing of the input matrix, then we obtain another conjecture (called the OMvP conjecture) that is in fact equivalent to our MvP conjecture. On the other hand, we demonstrate that the OMv conjecture does not hold in restricted cases where the rows of the matrix or the input vectors are clustered, and develop new efficient randomized algorithms for such cases. Finally, we present applications of our algorithms to answering graph queries. (c) 2021 Elsevier Inc. All rights reserved.

The rapid pace with which software needs to be built, together with the increasing need to evaluate changes for end users both quantitatively and qualitatively calls for novel software engineering approaches that focus on short release cycles, continuous deployment and delivery, experiment-driven feature development, feedback from users, and rapid tool-assisted feedback to developers. To realize these approaches there is a need for research and innovation with respect to automation and tooling, and furthermore for research into the organizational changes that support flexible data-driven decision-making in the development lifecycle. Most importantly, deep synergies are needed between software engineers, managers, and data scientists. This paper reports on the results of the joint 5th International Workshop on Rapid Continuous Software Engineering (RCoSE 2019) and the 1st International Workshop on Data-Driven Decisions, Experimentation and Evolution (DDrEE 2019), which focuses on the challenges and potential solutions in the area of continuous data-driven software engineering.  

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.

We exhibit two linear time approximation algorithms for guarding rectilinear staircase polygons both having approximation factor 2. The first algorithm benefits from its simplicity, whereas the second provides more insight to the problem.

In this paper, we consider the variant of the art gallery problem where the input polygon is a staircase polygon. Previous works on this problem gave a 2-approximation for point guarding a staircase polygon (where guards can be placed anywhere in the interior of the polygon and we wish to guard the entire polygon). It is still unknown whether this point guarding variant is NP-hard. In this paper we consider the vertex guarding problem, where guards are only allowed to be placed at the vertices of the polygon, and we wish to guard only the vertices of the polygon. We show that this problem is NP-hard, and we give a polynomial-time 2-approximation algorithm. 

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.

There is a growing awareness that the complexity of managing Big Data is one of the main challenges in the developing field of the Internet of Things (IoT). Complexity arises from several aspects of the Big Data life cycle, such as gathering data, storing them onto cloud servers, cleaning and integrating the data, a process involving the last advances in ontologies, such as Extensible Markup Language (XML) and Resource Description Framework (RDF), and the application of machine learning methods to carry out classifications, predictions, and visualizations. In this review, the state of the art of all the aforementioned aspects of Big Data in the context of the Internet of Things is exposed. The most novel technologies in machine learning, deep learning, and data mining on Big Data are discussed as well. Finally, we also point the reader to the state-of-the-art literature for further in-depth studies, and we present the major trends for the future.

Family life is no longer confined to geographically shared spaces. More often, families are separated. T echnology offers countless means of keeping families connected, which has been subject of extensive research. Yet, connection between families goes beyond interpersonal communication. Being separated from extended family means to be separated from familiar rituals, habits, and values. In this paper we present an ethnographic study of mobile families to understand how families are dealing with this kind of separation in their everyday life. We analyze situated practices and discuss how these families create a sense of connectedness to their country of origin. Our observations show that design for connectedness should address practices and materialities that are part of the family home. Furthermore, we argue that there should be more consideration for what the family connects to: Instead of connecting between people, connectedness can also be seen as staying in touch with familiar routines, customs, and environments.

Understanding the character of natural organic matter (NOM) and assessing its impact on water quality is paramount for managers of catchments and water utilities. For drinking-water producers, NOM affects disinfectant demand and the formation of by-products which can have adverse health effects. NOM content in raw waters also has an impact on water treatment processes by increasing required coagulant dosages, reducing the effectiveness of adsorption processes and fouling membrane systems. This study investigated the effects of calcium chloride (CaCl2) as a co-coagulant in Al3+ and Fe3+ assisted coagulation, flocculation and sedimentation processes for NOM-removal from raw water collected from Lake Bolmen, in southern Sweden. Jar tests were conducted at Ringsjo Water Works (WW), a surface water treatment plant (WTP), to investigate the potential reduction in primary coagulants aluminum sulphate (Al-2(SO4)(3)) and ferric chloride (FeCl3). This work shows that CaCl2 can, in certain situations, reduce the need for primary coagulants, which would reduce the environmental impact and costs associated with primary coagulant consumption.

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. 

This paper presents a novel cooperative USV-UAV platform to form a powerful combination, which offers foundations for collaborative task executed by the coupled USV-UAV systems. Adjustable buoys and unique carrier deck for the USV are designed to guarantee landing safety and transportation of UAV. The deck of USV is equipped with a series of sensors, and a multi-ultrasonic joint dynamic positioning algorithm is introduced for resolving the positioning problem of the coupled USV-UAV systems. To fulfill effective guidance for the landing operation of UAV, we design a hierarchical landing guide point generation algorithm to obtain a sequence of guide points. By employing the above sequential guide points, high quality paths are planned for the UAV. Cooperative dynamic positioning process of the USV-UAV systems is elucidated, and then UAV can achieve landing on the deck of USV steadily. Our cooperative USV-UAV platform is validated by simulation and water experiments.

Daily water level forecasting is of significant importance for the comprehensive utilization of water resources. An improved least squares support vector machine (LSSVM) model was introduced by including an extra bias error control term in the objective function. The tuning parameters were determined by the cross-validation scheme. Both conventional and improved LSSVM models were applied in the short term forecasting of the water level in the middle reaches of the Yangtze River, China. Evaluations were made with both models through metrics such as RMSE (Root Mean Squared Error), MAPE (Mean Absolute Percent Error) and index of agreement (d). More accurate forecasts were obtained although the improvement is regarded as moderate. Results indicate the capability and flexibility of LSSVM-type models in resolving time sequence problems. The improved LSSVM model is expected to provide useful water level information for the managements of hydroelectric resources in Rivers.

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.

Online controlled experiments (e.g., A/B tests) are an integral part of successful data-driven companies. At Microsoft, supporting experimentation poses a unique challenge due to the wide variety of products being developed, along with the fact that experimentation capabilities had to be added to existing, mature products with codebases that go back decades. This paper describes the Microsoft ExP Platform (ExP for short) which enables trustworthy A/B experimentation at scale for products across Microsoft, from web properties (such as bing.com) to mobile apps to device drivers within the Windows operating system. The two core tenets of the platform are trustworthiness (an experiment is meaningful only if its results can be trusted) and scalability (we aspire to expose every single change in any product through an A/B experiment). Currently, over ten thousand experiments are run annually. In this paper, we describe the four core components of an A/B experimentation system: experimentation portal, experiment execution service, log processing service and analysis service, and explain the reasoning behind the design choices made. These four components work together to provide a system where ideas can turn into experiments within minutes and those experiments can provide initial trustworthy results within hours.

Modern healthcare's need for knowledge sharing and bridging the research–practice gap requires new forms of collaboration, in which clinicians of varying clinical and research expertise work together over geographical and organisational borders. To support such distributed communities of practice (CoPs), an understanding of their collaboration processes, outcomes, challenges and enablers is needed. The article examines these issues through a case study of a long-running CoP, the Swedish Oral Medicine Network (SOMNet). SOMNet's main form of collaboration is monthly telephone conference meetings centred on case consultations. Cases are submitted by the clinicians via a Web-based system. The methods used were interviews, observations, and a questionnaire. The work adds to previous research by studying a distributed CoP explicitly focused on supporting the transfer of scientific results from researchers to practitioners. We found that the regular meetings give a rhythm to the community. The centrality of cases means an immediate benefit for the submitter while the community is provided an authentic context for learning. SOMNet yields opportunities for help and learning for diverse expertise levels; the type of benefits is affected by the participant's degree of oral medicine knowledge and collaboration involvement. There are challenges in accommodating varying levels of expertise and encouraging those less experienced to participate. Enablers of the collaboration include the participation of experts, meeting facilitators and well-adapted ITs.

With increasing amounts of open data, especially where data can be connected with various additional information resources, new ways of visualizing and making sense of this data become possible and necessary. This paper proposes, discusses and exemplifies the concept of data games, games that allow the player(s) to explore data that is derived from outside the game, by transforming the data into something that can be played with. The transformation takes the form of procedural content generation based on real-world data. As an example of a data game, we describe Open Data Monopoly, a game board generator that uses economic and social indicator data for local governments in the UK. Game boards are generated by first collecting user input on which indicators to use and how to weigh them, as well as what criteria should be used for street selection. Sets of streets are then evolved that maximize the selected criteria, and ordered according to “prosperity” as defined subjectively by the user. Chance and community cards are created based on auxiliary data about the local political entities.

This paper presents an experimental study of the thermal inertia of a pallet loaded with returnable plastic crates containing primary packages of smoked ham. Based on this, food quality variations within the pallet were also investigated. Thermal time constants from 83 sensor locations were identified by studying the temperature changes when the pallet was exposed to instant temperature drops (16 C - 2 C) and temperature elevations (2 C - 16 C). The thermal time constants were used in microbiological prediction models to calculate the maximum difference in shelf life between packages at the two most extreme spots in the pallet unit load, when temperature elevated from 4 C to a higher temperature (ranging from 4.5 C to 12 C), during different periods of time (ranging from 0.5 h to 200 h). The results showed a maximum difference in shelf life of approximately 1.8 days. The identified thermal time constants were also used to calculate the maximum difference in shelf life between packages at the two most extreme spots of a pallet unit load, in a real chilled food supply chain lasting for about 2.5 days. This resulted in a maximum difference of 0.1 days. The results imply that the location of a product in a pallet has a relatively low influence on the product shelf life. This means that a temperature sensor used for calculating the predicted shelf life of a product, can be placed relatively far from the product itself (e.g. on the secondary package or even on the pallet) without jeopardizing the reliability of the resulting shelflife prediction. However, the results also emphasize the importance of continuous temperature monitoring along the entire chilled food supply chains.

A challenge in perishable food industry today is variable and unknown food quality caused by different temperature conditions. This sometimes leads to unreliable printed shelf lives (best before dates) and food waste. Hence, temperature monitoring and control along cold food supply chains (FSCs) are essential for maintaining food quality and safety of perishable food products. This paper evaluates the temperature performance of cold food supply chains in relation to dynamically predicted shelf life and printed shelf life. Based on an in-depth study of actual temperature conditions of food products collected from field tests made in Swedish FSCs (from production to retail cold storage and retail displays), complete FSC scenarios were created. The results showed a significant difference in product shelf life between the most and least efficient FSCs, and between dynamically predicted and printed shelf life. Overall, the distribution from production to retail represents an efficient part of the FSC, in contrast to retail display storage. This study emphasizes the importance of a full-time temperature monitoring system to confirm food quality. A temperature monitoring system can be used to enable dynamic shelf life prediction, increase FSC transparency, and support food producers to proactively improve printed shelf lives.

Reviewing previous studies on using computational models for analyzing the effect of transport policies on transportation systems shows that agentbased models have not been used much in spite of their great potential for simulating dynamic aspects of policy instruments and travel behavior. The main reason can be the need for a lot of input data which is hard to prepare for the modeler. This has led to limited use of agent-based models in previous studies and even in those studies the scope of simulation is limited to only particular scenarios. In this thesis, I proposed a general-purpose agent-based simulation model for urban transportation that supports simulation of a wide range of policy instruments. The proposed model is designed in a way that a large part of the input data can be generated automatically using online web-services. The thesis also reports an empirical study on using our proposed generalpurpose model together with on-line travel planners in agent-based simulation for predicting the effect of different policy instruments on travel behavior. The results from our empirical study showed that our generalpurpose agent-based model predicts 72% of the real travel decisions correctly. Furthermore, the results of the simulation for various scenarios and combination of them seem to be acceptable. Finally, we found out that the use of on-line services for data collection increases the speed and flexibility of the system for defining and running new scenarios. However, the scalability of using on-line services in simulation is constrained by limitations of online service providers. The main contributions of this thesis are a general-purpose agentbased simulation model for urban transportation and a novel approach to automatically generate input data to the simulation using online travel planners and other web-services. This novel approach mitigates the challenge of agent-based simulation as a data-intensive method. This can lead to more widespread use for agent-based simulation in solving complex and realistic transportation scenarios. Another contribution of this thesis is on visualization of simulation output. One of the main challenges of using simulation systems by transport planners and decision makers as end-users is to understand the complex output of the simulation. In this thesis, I empirically demonstrated how the usability of a freight transport simulation system is improved by adding a visualization module that illustrates the results of the simulation for the end-users.