SINTEF Digital

Digital twin can be defined as a virtual representation of a physical asset enabled through data and simulators for real-time prediction, optimization, monitoring, controlling, and improved decision making. Recent advances in computational pipelines, multiphysics solvers, artificial intelligence, big data cybernetics, data processing and management tools bring the promise of digital twins and their impact on society closer to reality. Digital twinning is now an important and emerging trend in many applications. Also referred to as a computational megamodel, device shadow, mirrored system, avatar or a synchronized virtual prototype, there can be no doubt that a digital twin plays a transformative role not only in how we design and operate cyber-physical intelligent systems, but also in how we advance the modularity of multi-disciplinary systems to tackle fundamental barriers not addressed by the current, evolutionary modeling practices. In this work, we review the recent status of methodologies and techniques related to the construction of digital twins mostly from a modeling perspective. Our aim is to provide a detailed coverage of the current challenges and enabling technologies along with recommendations and reflections for various stakeholders.

In a short span of time since its introduction, generative artificial intelligence (AI) has garnered much interest at both personal and organizational levels. This is because of its potential to cause drastic and widespread shifts in many aspects of life that are comparable to those of the Internet and smartphones. More specifically, generative AI utilizes machine learning, neural networks, and other techniques to generate new content (e.g. text, images, music) by analyzing patterns and information from the training data. This has enabled generative AI to have a wide range of applications, from creating personalized content to improving business operations. Despite its many benefits, there are also significant concerns about the negative implications of generative AI. In view of this, the current article brings together experts in a variety of fields to expound and provide multi-disciplinary insights on the opportunities, challenges, and research agendas of generative AI in specific industries (i.e. marketing, healthcare, human resource, education, banking, retailing, the workplace, manufacturing, and sustainable IT management).

Artificial intelligence is currently a hot topic in medicine. However, medical data is often sparse and hard to obtain due to legal restrictions and lack of medical personnel for the cumbersome and tedious process to manually label training data. These constraints make it difficult to develop systems for automatic analysis, like detecting disease or other lesions. In this respect, this article presents HyperKvasir, the largest image and video dataset of the gastrointestinal tract available today. The data is collected during real gastro- and colonoscopy examinations at Bærum Hospital in Norway and partly labeled by experienced gastrointestinal endoscopists. The dataset contains 110,079 images and 374 videos, and represents anatomical landmarks as well as pathological and normal findings. The total number of images and video frames together is around 1 million. Initial experiments demonstrate the potential benefits of artificial intelligence-based computer-assisted diagnosis systems. The HyperKvasir dataset can play a valuable role in developing better algorithms and computer-assisted examination systems not only for gastro- and colonoscopy, but also for other fields in medicine.

Today, most organizations are undergoing a digital transformation. At the same time, the gravity of environmental issues has put sustainability and the circular economy at the top of corporate agendas. To this end, information systems, in particular business analytics, are being highlighted as essential enablers of an accelerated circular economy transition. However, effectively managing this joint transformation is a challenge. Firms struggle to identify which organizational resources they should target and how those should be leveraged towards a firm-wide business analytics capability for circular economy. To address these questions, this study draws on recent literature dealing with smart circular economy and business analytics capabilities along with the resource-based and resource orchestration view to (1) create an instrument to measure firms’ business analytics capability for circular economy, and (2) examine the relationship among a circular economy-specific business analytics capability, circular economy implementation, resource orchestration capability, and firm performance. The proposed research model was tested using partial least squares structural equation modeling of survey data from 125 top-level managers at companies across Europe. The results show that firms with a strong business analytics capability have an increased resource orchestration capability and a greater ability to excel in the circular economy, resulting in improved organizational performance in building a more sustainable competitive advantage in an increasingly competitive business landscape. The effect of business analytics capability on firm performance is not direct but fully mediated through resource orchestration capability and circular economy implementation. The results empirically validate the proposed research model and offer pathways to future information systems research streams to support the operationalization of circular strategies. The study provides the first empirical evidence of a business analytics capability for circular economy and its effect on firm performance.

BACKGROUND: Diabetes mellitus (DM) is a metabolic disorder that causes abnormal blood glucose (BG) regulation that might result in short and long-term health complications and even death if not properly managed. Currently, there is no cure for diabetes. However, self-management of the disease, especially keeping BG in the recommended range, is central to the treatment. This includes actively tracking BG levels and managing physical activity, diet, and insulin intake. The recent advancements in diabetes technologies and self-management applications have made it easier for patients to have more access to relevant data. In this regard, the development of an artificial pancreas (a closed-loop system), personalized decision systems, and BG event alarms are becoming more apparent than ever. Techniques such as predicting BG (modeling of a personalized profile), and modeling BG dynamics are central to the development of these diabetes management technologies. The increased availability of sufficient patient historical data has paved the way for the introduction of machine learning and its application for intelligent and improved systems for diabetes management. The capability of machine learning to solve complex tasks with dynamic environment and knowledge has contributed to its success in diabetes research. MOTIVATION: Recently, machine learning and data mining have become popular, with their expanding application in diabetes research and within BG prediction services in particular. Despite the increasing and expanding popularity of machine learning applications in BG prediction services, updated reviews that map and materialize the current trends in modeling options and strategies are lacking within the context of BG prediction (modeling of personalized profile) in type 1 diabetes. OBJECTIVE: The objective of this review is to develop a compact guide regarding modeling options and strategies of machine learning and a hybrid system focusing on the prediction of BG dynamics in type 1 diabetes. The review covers machine learning approaches pertinent to the controller of an artificial pancreas (closed-loop systems), modeling of personalized profiles, personalized decision support systems, and BG alarm event applications. Generally, the review will identify, assess, analyze, and discuss the current trends of machine learning applications within these contexts. METHOD: A rigorous literature review was conducted between August 2017 and February 2018 through various online databases, including Google Scholar, PubMed, ScienceDirect, and others. Additionally, peer-reviewed journals and articles were considered. Relevant studies were first identified by reviewing the title, keywords, and abstracts as preliminary filters with our selection criteria, and then we reviewed the full texts of the articles that were found relevant. Information from the selected literature was extracted based on predefined categories, which were based on previous research and further elaborated through brainstorming among the authors. RESULTS: The initial search was done by analyzing the title, abstract, and keywords. A total of 624 papers were retrieved from DBLP Computer Science (25), Diabetes Technology and Therapeutics (31), Google Scholar (193), IEEE (267), Journal of Diabetes Science and Technology (31), PubMed/Medline (27), and ScienceDirect (50). After removing duplicates from the list, 417 records remained. Then, we independently assessed and screened the articles based on the inclusion and exclusion criteria, which eliminated another 204 papers, leaving 213 relevant papers. After a full-text assessment, 55 articles were left, which were critically analyzed. The inter-rater agreement was measured using a Cohen Kappa test, and disagreements were resolved through discussion. CONCLUSION: Due to the complexity of BG dynamics, it remains difficult to achieve a universal model that produces an accurate prediction in every circumstance (i.e., hypo/eu/hyperglycemia events). Recently, machine learning techniques have received wider attention and increased popularity in diabetes research in general and BG prediction in particular, coupled with the ever-growing availability of a self-collected health data. The state-of-the-art demonstrates that various machine learning techniques have been tested to predict BG, such as recurrent neural networks, feed-forward neural networks, support vector machines, self-organizing maps, the Gaussian process, genetic algorithm and programs, deep neural networks, and others, using various group of input parameters and training algorithms. The main limitation of the current approaches is the lack of a well-defined approach to estimate carbohydrate intake, which is mainly done manually by individual users and is prone to an error that can severely affect the predictive performance. Moreover, a universal approach has not been established to estimate and quantify the approximate effect of physical activities, stress, and infections on the BG level. No researchers have assessed model predictive performance during stress and infection incidences in a free-living condition, which should be considered in future studies. Furthermore, a little has been done regarding model portability that can capture inter- and intra-variability among patients. It seems that the effect of time lags between the CGM readings and the actual BG levels is not well covered. However, in general, we foresee that these developments might foster the advancement of next-generation BG prediction algorithms, which will make a great contribution in the effort to develop the long-awaited, so-called artificial pancreas (a closed-loop system).

The latest technical and interaction advancements that took place in the Virtual Reality (VR) field have marked a new era, not only for VR, but also for VR locomotion. Although the latest advancements in VR locomotion have raised the interest of both researchers and users in analyzing and experiencing current VR locomotion techniques, the field of research on VR locomotion, in its new era, is still uncharted. In this work, VR locomotion is explored through a systematic literature review investigating empirical studies of VR locomotion techniques from 2014–2017. The review analyzes the VR locomotion techniques that have been studied, their interaction-related characteristics and the research topics that were addressed in these studies. Thirty-six articles were identified as relevant to the literature review, and the analysis of the articles resulted in 73 instances of 11 VR locomotion techniques, such as real-walking, walking-in-place, point and teleport, joystick-based locomotion, and more. Results showed that since the VR revival, the focus of VR locomotion research has been on VR technology and various technological aspects, overshadowing the investigation of user experience. From an interaction perspective, the majority of the utilized and studied VR locomotion techniques were found to be based on physical interaction, exploiting physical motion cues for navigation in VR environments. A significant contribution of the literature review lies in the proposed typology for VR locomotion, introducing four distinct VR locomotion types: motion-based, room scale-based, controller-based and teleportation-based locomotion.

In this investigation, a data-driven turbulence closure framework is introduced and deployed for the subgrid modelling of Kraichnan turbulence. The novelty of the proposed method lies in the fact that snapshots from high-fidelity numerical data are used to inform artificial neural networks for predicting the turbulence source term through localized grid-resolved information. In particular, our proposed methodology successfully establishes a map between inputs given by stencils of the vorticity and the streamfunction along with information from two well-known eddy-viscosity kernels. Through this we predict the subgrid vorticity forcing in a temporally and spatially dynamic fashion. Our study is both a priori and a posteriori in nature. In the former, we present an extensive hyper-parameter optimization analysis in addition to learning quantification through probability-density-function-based validation of subgrid predictions. In the latter, we analyse the performance of our framework for flow evolution in a classical decaying two-dimensional turbulence test case in the presence of errors related to temporal and spatial discretization. Statistical assessments in the form of angle-averaged kinetic energy spectra demonstrate the promise of the proposed methodology for subgrid quantity inference. In addition, it is also observed that some measure of a posteriori error must be considered during optimal model selection for greater accuracy. The results in this article thus represent a promising development in the formalization of a framework for generation of heuristic-free turbulence closures from data.

In this investigation, a data-driven turbulence closure framework is introduced and deployed for the subgrid modelling of Kraichnan turbulence. The novelty of the proposed method lies in the fact that snapshots from high-fidelity numerical data are used to inform artificial neural networks for predicting the turbulence source term through localized grid-resolved information. In particular, our proposed methodology successfully establishes a map between inputs given by stencils of the vorticity and the streamfunction along with information from two well-known eddy-viscosity kernels. Through this we predict the subgrid vorticity forcing in a temporally and spatially dynamic fashion. Our study is both a priori and a posteriori in nature. In the former, we present an extensive hyper-parameter optimization analysis in addition to learning quantification through probability-density-function-based validation of subgrid predictions. In the latter, we analyse the performance of our framework for flow evolution in a classical decaying two-dimensional turbulence test case in the presence of errors related to temporal and spatial discretization. Statistical assessments in the form of angle-averaged kinetic energy spectra demonstrate the promise of the proposed methodology for subgrid quantity inference. In addition, it is also observed that some measure of a posteriori error must be considered during optimal model selection for greater accuracy. The results in this article thus represent a promising development in the formalization of a framework for generation of heuristic-free turbulence closures from data.

Renal failure, a public health concern, and the scarcity of nephrologists around the globe have necessitated the development of an AI-based system to auto-diagnose kidney diseases. This research deals with the three major renal diseases categories: kidney stones, cysts, and tumors, and gathered and annotated a total of 12,446 CT whole abdomen and urogram images in order to construct an AI-based kidney diseases diagnostic system and contribute to the AI community's research scope e.g., modeling digital-twin of renal functions. The collected images were exposed to exploratory data analysis, which revealed that the images from all of the classes had the same type of mean color distribution. Furthermore, six machine learning models were built, three of which are based on the state-of-the-art variants of the Vision transformers EANet, CCT, and Swin transformers, while the other three are based on well-known deep learning models Resnet, VGG16, and Inception v3, which were adjusted in the last layers. While the VGG16 and CCT models performed admirably, the swin transformer outperformed all of them in terms of accuracy, with an accuracy of 99.30 percent. The F1 score and precision and recall comparison reveal that the Swin transformer outperforms all other models and that it is the quickest to train. The study also revealed the blackbox of the VGG16, Resnet50, and Inception models, demonstrating that VGG16 is superior than Resnet50 and Inceptionv3 in terms of monitoring the necessary anatomy abnormalities. We believe that the superior accuracy of our Swin transformer-based model and the VGG16-based model can both be useful in diagnosing kidney tumors, cysts, and stones.

Artificial intelligence (AI) is predicted to have profound effects on the future of video capsule endoscopy (VCE) technology. The potential lies in improving anomaly detection while reducing manual labour. Existing work demonstrates the promising benefits of AI-based computer-assisted diagnosis systems for VCE. They also show great potential for improvements to achieve even better results. Also, medical data is often sparse and unavailable to the research community, and qualified medical personnel rarely have time for the tedious labelling work. We present Kvasir-Capsule, a large VCE dataset collected from examinations at a Norwegian Hospital. Kvasir-Capsule consists of 117 videos which can be used to extract a total of 4,741,504 image frames. We have labelled and medically verified 47,238 frames with a bounding box around findings from 14 different classes. In addition to these labelled images, there are 4,694,266 unlabelled frames included in the dataset. The Kvasir-Capsule dataset can play a valuable role in developing better algorithms in order to reach true potential of VCE technology.

• Synthesizes empirical studies on responsible AI and the underlying principles. • Differentiates between principles and governance of AI in a responsible way. • Analyzes through a critical lens existing studies and uncovers underlying assumptions. • Defines the notion of responsible AI governance based on the synthesis and critical reflection. • Develops a research agenda and identifies important areas for future research within the IS domain. The widespread and rapid diffusion of artificial intelligence (AI) into all types of organizational activities necessitates the ethical and responsible deployment of these technologies. Various national and international policies, regulations, and guidelines aim to address this issue, and several organizations have developed frameworks detailing the principles of responsible AI. Nevertheless, the understanding of how such principles can be operationalized in designing, executing, monitoring, and evaluating AI applications is limited. The literature is disparate and lacks cohesion, clarity, and, in some cases, depth. Subsequently, this scoping review aims to synthesize and critically reflect on the research on responsible AI. Based on this synthesis, we developed a conceptual framework for responsible AI governance (defined through structural, relational, and procedural practices), its antecedents, and its effects. The framework serves as the foundation for developing an agenda for future research and critically reflects on the notion of responsible AI governance.

Human Activity Recognition (HAR) systems are devised for continuously observing human behavior - primarily in the fields of environmental compatibility, sports injury detection, senior care, rehabilitation, entertainment, and the surveillance in intelligent home settings. Inertial sensors, e.g., accelerometers, linear acceleration, and gyroscopes are frequently employed for this purpose, which are now compacted into smart devices, e.g., smartphones. Since the use of smartphones is so widespread now-a-days, activity data acquisition for the HAR systems is a pressing need. In this article, we have conducted the smartphone sensor-based raw data collection, namely H-Activity, using an Android-OS-based application for accelerometer, gyroscope, and linear acceleration. Furthermore, a hybrid deep learning model is proposed, coupling convolutional neural network and long-short term memory network (CNN-LSTM), empowered by the self-attention algorithm to enhance the predictive capabilities of the system. In addition to our collected dataset (H-Activity), the model has been evaluated with some benchmark datasets, e.g., MHEALTH, and UCI-HAR to demonstrate the comparative performance of our model. When compared to other models, the proposed model has an accuracy of 99.93% using our collected H-Activity data, and 98.76% and 93.11% using data from MHEALTH and UCI-HAR databases respectively, indicating its efficacy in recognizing human activity recognition.We hope that our developed model could be applicable in the clinical settings and collected data could be useful for further research.

With the advent of the Internet of Things (IoT), artificial intelligence (AI), machine learning (ML), and deep learning (DL) algorithms, the landscape of data-driven medical applications has emerged as a promising avenue for designing robust and scalable diagnostic and prognostic models from medical data. This has gained a lot of attention from both academia and industry, leading to significant improvements in healthcare quality. However, the adoption of AI-driven medical applications still faces tough challenges, including meeting security, privacy, and Quality-of-Service (QoS) standards. Recent developments in federated learning (FL) have made it possible to train complex machine-learned models in a distributed manner and have become an active research domain, particularly processing the medical data at the edge of the network in a decentralized way to preserve privacy and address security concerns. To this end, in this article, we explore the present and future of FL technology in medical applications where data sharing is a significant challenge. We delve into the current research trends and their outcomes, unraveling the complexities of designing reliable and scalable FL models. This article outlines the fundamental statistical issues in FL, tackles device-related problems, addresses security challenges, and navigates the complexity of privacy concerns, all while highlighting its transformative potential in the medical field. Our study primarily focuses on medical applications of FL, particularly in the context of global cancer diagnosis. We highlight the potential of FL to enable computer-aided diagnosis tools that address this challenge with greater effectiveness than traditional data-driven methods. Recent literature has shown that FL models are robust and generalize well to new data, which is essential for medical applications. We hope that this comprehensive review will serve as a checkpoint for the field, summarizing the current state of the art and identifying open problems and future research directions.

Governments in countries across the world increasingly adopt the “green growth” discourse to underline their ambition for the greening of their economies. The central tenet of this narrative is the economic opportunities rather than challenges arising from the pursuit of environmental sustainability. Our paper synthesises insights from 113 recent scientific articles, dealing with both environmental issues and economic growth, as well as innovation. Our ambition is exploratory in attempting to take stock of heterogeneous contributions across the spectrum of social science. The articles have been reviewed with a focus on six themes, derived from current discussions in economic geography and transition studies: skills, technology, physical resources, markets, institutions and policies. Four major implications emerge from the review. First, green growth requires competences that allow for handling complex, non-routine situations – in both the private and the public sector. Second, technological progress should be directed towards greener technologies, to avoid investments funds being channelled to brown technologies for short-term returns. Third, our knowledge of the opportunities for achieving green growth must base upon a joint assessment of market failures, structural system failures and transformational system failures. Finally, greater attention should be devoted to the geography of green growth processes at different scales.

The rapid growth and use of artificial intelligence (AI)-based systems have raised concerns regarding explainability. Recent studies have discussed the emerging demand for explainable AI (XAI); however, a systematic review of explainable artificial intelligence from an end user's perspective can provide a comprehensive understanding of the current situation and help close the research gap. The purpose of this study was to perform a systematic literature review of explainable AI from the end user's perspective and to synthesize the findings. To be precise, the objectives were to 1) identify the dimensions of end users' explanation needs; 2) investigate the effect of explanation on end user's perceptions, and 3) identify the research gaps and propose future research agendas for XAI, particularly from end users' perspectives based on current knowledge. The final search query for the Systematic Literature Review (SLR) was conducted on July 2022. Initially, we extracted 1707 journal and conference articles from the Scopus and Web of Science databases. Inclusion and exclusion criteria were then applied, and 58 articles were selected for the SLR. The findings show four dimensions that shape the AI explanation, which are format (explanation representation format), completeness (explanation should contain all required information, including the supplementary information), accuracy (information regarding the accuracy of the explanation), and currency (explanation should contain recent information). Moreover, along with the automatic representation of the explanation, the users can request additional information if needed. We have also described five dimensions of XAI effects: trust, transparency, understandability, usability, and fairness. We investigated current knowledge from selected articles to problematize future research agendas as research questions along with possible research paths. Consequently, a comprehensive framework of XAI and its possible effects on user behavior has been developed.

Abstract Chatbots are predicted to play a key role in customer service. Users’ trust in such chatbots is critical for their uptake. However, there is a lack of knowledge concerning users’ trust in chatbots. To bridge this knowledge gap, we present a questionnaire study (N = 154) that investigated factors of relevance for trust in customer service chatbots. The study included two parts: an explanatory investigation of the relative importance of factors known to predict trust from the general literature on interactive systems and an exploratory identification of other factors of particular relevance for trust in chatbots. The participants were recruited as part of their dialogue with one of four chatbots for customer service. Based on the findings, we propose an initial model of trust in chatbots for customer service, including chatbot-related factors (perceived expertise and responsiveness), environment-related factors (risk and brand perceptions) and user-related factors (propensity to trust technology). RESEARCH HIGHLIGHTS We extend the current knowledge base on natural language interfaces by investigating factors affecting users’ trust in chatbots for customer service. Chatbot-related factors, specifically perceived expertise and responsiveness, are found particularly important to users’ trust in such chatbots, but also environment-related factors such as brand perception and user-related factors such as propensity to trust technology. On the basis of the findings, we propose an initial model of users’ trust chatbots for customer service.

The deployment of Artificial Intelligence (AI) has been accelerating in several fields over the past few years, with much focus placed on its potential in Business-to-Business (B2B) marketing. Early reports highlight promising benefits of AI in B2B marketing such as offering important insights into customer behaviors, identifying critical market insight, and streamlining operational inefficiencies. Nevertheless, there is a lack of understanding concerning how organizations should structure their AI competencies for B2B marketing, and how these ultimately influence organizational performance. Drawing on AI competencies and B2B marketing literature, this study develops a conceptual research model that explores the effect that AI competencies have on B2B marketing capabilities, and in turn on organizational performance. The proposed research model is tested using 155 survey responses from European companies and analyzed using partial least squares structural equation modeling. The results highlight the mechanisms through which AI competencies influence B2B marketing capabilities, as well as how the later impact organizational performance.

Abstract Purpose of Review This paper provides an overview of the role of humans and robots in smart factories, their connection to Industry 4.0, and which progress they make when it comes to related technologies. Recent Findings The current study shows that a decade was not enough to provide a reference implementation or application of Industry 4.0, like smart factories. In 2011, Industry 4.0 was mentioned for the first time in the scientific community. Industry 4.0 arrived with many new enabling technologies and buzzwords, e.g., Internet of Things (IoT), Cyber-Physical Systems (CPS), and Digital Twins (DT). Summary This paper first defines smart factories and smart manufacturing in relation to the role of humans and robots. Followed by an overview of selected technologies in smart factories. Concluded by future prospects and its’ relation to smart manufacturing.

The latest technical and interaction advancements within the virtual reality (VR) field have marked a new era, not only for VR, but also for VR locomotion. In this era, well-established, prevalent VR locomotion techniques are mostly used as points of comparison for benchmarking of new VR locomotion designs. At the same time, there is the need for more exploratory, comparative studies of contemporary VR locomotion techniques, so that their distinguished interaction aspects can be documented and guide the design process of new techniques. This article presents a comparative, empirical evaluation study of contemporary and prevalent VR locomotion techniques, examining the user experience (UX) they offer. First, the prevalent VR locomotion techniques are identified based on literature, i.e., walking-in-place, controller/joystick, and teleportation. Twenty-six adults are enrolled in the study and perform a game-like task using the techniques. The study follows a mixed methods approach, utilising the System Usability Scale survey, the Game Experience Questionnaire, and a semistructured interview to assess user experiences. Results indicate that the walking-in-place technique offers the highest immersion but also presents high levels of psychophysical discomfort. Controller/joystick VR locomotion is perceived as easy-to-use due to the users’ familiarity with controllers, whereas teleportation is considered to be effective due to its fast navigation, although its visual ‘jumps’ do break the users’ sense of immersion. Based on the interviews, the users focused on the following interaction dimensions to describe their VR locomotion experiences: (i) immersion and flow, (ii) ease-of-use and mastering, (iii) competence and sense of effectiveness, and (iv) psychophysical discomfort. The study implications for VR locomotion are discussed, along with the study limitations and the future direction for research.

Contemporary autopilot systems for unmanned aerial vehicles (UAVs) are far more limited in their flight envelope as compared to experienced human pilots, thereby restricting the conditions UAVs can operate in and the types of missions they can accomplish autonomously. This paper proposes a deep reinforcement learning (DRL) controller to handle the nonlinear attitude control problem, enabling extended flight envelopes for fixed-wing UAVs. A proof-of-concept controller using the proximal policy optimization (PPO) algorithm is developed, and is shown to be capable of stabilizing a fixed-wing UAV from a large set of initial conditions to reference roll, pitch and airspeed values. The training process is outlined and key factors for its progression rate are considered, with the most important factor found to be limiting the number of variables in the observation vector, and including values for several previous time steps for these variables. The trained reinforcement learning (RL) controller is compared to a proportional-integral-derivative (PID) controller, and is found to converge in more cases than the PID controller, with comparable performance. Furthermore, the RL controller is shown to generalize well to unseen disturbances in the form of wind and turbulence, even in severe disturbance conditions.