Creating Intelligent Computational Edge through Semantic Mediation

2023 | HICSS | Citations: 0

Authors: Juric, Radmila; Ronchieri, Elisabetta; Suh, Sang

Abstract: This research proposes semantic mediation based on reasoning and the first order ... Expand

Abstract: This research proposes semantic mediation based on reasoning and the first order logic for mediating the best possible configuration of Computational Edge, relevant for software applications which may benefit for running computations with proximity to their data sources. The mediation considers the context in which these applications exist and exploits the semantic of that context for decision making on where computational elements should reside and which data they should use. The application of semantic mediation could address the initiative to accommodate algorithms from predictive and learning technologies, push AI towards computational edges and potentially contribute towards creating a computing continuum. Collapse

Topics: cloud computing mobile system internet of things edge computing artificial intelligence

Methods: ontological modelling computational algorithm literature study literature sample

Introduction to the Minitrack on Intelligent Edge Computing in Pervasive Environments

2023 | HICSS | Citations: 0

Authors: Juric, Radmila; Ronchieri, Elisabetta

Abstract: This is a new minitrack in the software technology track aiming to address the ... Expand

Abstract: This is a new minitrack in the software technology track aiming to address the newest trends in software development, where more power is given to computational edges in accommodating new software technologies and therefore potentially creating an intelligent edge computing paradigm. The submissions to the minitrack were interesting, but we chose only two. They are rather different papers, but they both reflect upon the complexity of modern computing in pervasive spaces, difficulties in maintaining the presence of powerful clouds and attempts to accommodate learning and predictive technologies within modern software solutions across many problem domains.The first paper gives an insight into designing, prototyping and testing pervasive and connected digital twins for edge computing enabled industrial applications. The second comes from collaborative work on creating a flexible computational space between clouds and edges of networks using reasoning and mediation.The paper entitled "Pervasive and Connected Digital Twins for Edge Computing Enabled Industrial Applications" comes from Norway and is the result of collaborative work with academia and industry. Their proposed paradigm allows for the creation of computational models for cloud computing as well as the transmission of data and computational intelligence through analytic platforms. It is very interesting that they exploit the power of digital twins in this case, which has not yet been used in configuring edge computing. This paradigm sits within the architecture, showing the potential convergence of humans, "things" and AI in creating edge intelligence. Their case study shows a Norwegian company, that provides cleaning solutions for entrepreneurs, process industries, mining, and energy operations, being designated as a digital twin. The computational paradigm and suggested architecture in the paper facilitates the proper maintenance and management of infrastructures and facilities of the company. However, the interesting outcome is that there is scope to use this paradigm with "digital twins" in a wide range of applications in future, which opens a new chapter for research and industrial applications of edge computing.The paper entitled "Creating Intelligent Computational Edge through Semantic Mediations" focuses on the constantly changeable computational space between clouds and edges of computer networks, with the goal of creating the best possible configuration of edge computing according to the semantics of the context in which we wish to perform computing. The authors put forward the ideas of mediation on the best possible configuration of computational edges, by using new software technologies which enable reasoning within the given context. This exploration in creating intelligent computational edge is secured by making it independent in terms of deciding through reasoning, which computations we wish to run at the edge and which data the edge needs. These decisions are constantly changeable, and dependent on contexts in which we empower the edge. The authors claim that this might be the first step towards creating a computing continuum which would accommodate complex and data centric applications, currently dominating modern software engineering and shaping the current AI technology. Collapse

Topics: digital twin edge computing

Methods: design artifact

Introduction to Accountability, Evaluation and Obscurity of AI Algorithms Minitrack (CC BY-NC-ND 4.0)

2023 | HICSS | Citations: 0

Authors: Juric, R.; Steele, R.

Abstract: This Minitrack has attracted very interesting submissions and we have chosen to ... Expand

Abstract: This Minitrack has attracted very interesting submissions and we have chosen to accept two.It is obvious that we are still puzzled with the evaluation and obscurity of AI algorithms, and research communities across the world are clear that have not conquered AI accountability. The co-chairs have agreed that it is quite difficult to address the visible shortcomings of AI and guarantee that we will have a means of evaluating its algorithms very soon, but we are also very excited, with the submitted papers, because they pave the way towards AI algorithms which address all three: evaluation, obscurity and accountability.The accepted submissions are very different and illustrate various ways of thinking and ideas which are hidden behind our concerns on AI. One paper gives a comprehensive explanation and possibilities of removing human bias when using natural language processing methods and the other is focused on ethical principles in AI which have been overlooked, and potentially harmed marginalized communities.The paper entitled "Comparing Methods for Mitigating Gender Bias in Word Embedding" gives a comprehensive comparison of debiasing methods, built on top of GloVe, in order to determine which method is the best in removing bias. It would be of interest to natural language processing and AI evaluation enthusiasts, because word embedding, which transforms texts into numeric vectors and reproduces similar words with similar vector representations, can carry forward prejudices of societies and thus bring along human biases. The authors have defined HSR-RAN-GloVe method and compared it with different debiasing methods with the aim of determining a) which methods perform the best at removing bias and b) if these methods truly remove bias from word embedding. The results are interesting. There is no method that outperforms throughout their analysis and no method leads to a decrease in performance for either similarity or semantics. However, RAN-GloVe is probably the method that on average gets better results in debiasing word embedding.In addition, it is worthwhile extracting from this paper that, for their SemBias dataset, the RAN-GloVe word embedding has remarkable accuracy in identifying the genderdefinition pairs. It does not confuse the genderdefinition with the gender-stereotype pairs, which can be extremely useful in any real-life applications.The paper entitled "Applying Reflexivity to Artificial Intelligence for Researching Marginalized Communities and Real-World Problems" has been created by US social scientists who claimed that the problems of ethical AI are due to a lack of critical insight into the complex positionality of the researcher, power dynamics between scholars and the communities being studied, and the structural impact on real-world problems when AI systems appear to be accurate but ethically fail. When addressing AI ethics, the authors apply 5 stages of "reflexivity", a process that yields a better understanding of community-specific nuances, areas requiring local expertise, and the potential consequences of scholastic interventions for real-world problems. They claim that as the focus of AI shifts to more practical, real-world interventions, it begins to enter the space that social work has inhabited. Therefore they advocate for AI researchers to be flexible by engaging in a more reflexive and ethical approach with the understanding that their AI model may produce unintended consequences that affect lives and livelihoods of vulnerable/ marginalized communities. We encourage readers to pay attention to the last paragraph of the paper, where the authors say that they "believe that the application of social work ethics and approaches to data science can possibly prevent future mistakes in our research with communities". Collapse

Topics: artificial intelligence

Methods: word embedding GloVe natural language processing literature sample

Introduction to the Minitrack on IT Architectures and Implementations in Healthcare Environments

2023 | HICSS | Citations: 0

Authors: Juric, Radmila; Suh, Sang; Chou, Ying-Chyi

Abstract: Environments has attracted a variety of papers, but we have selected only two.T ... Expand

Abstract: Environments has attracted a variety of papers, but we have selected only two.The selected papers are rather different but they both show architectures and software implementations in two different healthcare settings. The first one focuses on digital innovation and cocreation of novel digital services in a specific setting of 27 hospitals in Norway. The second promotes possibilities of implementing novel computational models for polypharmacology which could address numerous problems in drug discoveries and repurposing.The paper entitled "Institutionalization of Digital Innovation Practices in Large and Complex User Organizations", comes from Norway and examines the complex organizational structure of its hospitals, with centralized IT services, which therefore might not push forward digital innovation in their environments.The authors collected information and data from 27 hospitals and, as an illustration, explored 70 different trajectories for digital remote care, which are expected to have an impact on digital innovation. The results show that interplay among key mechanisms, such as idealistic entrepreneurship, organizational anchoring, and remote infrastructure, does have a positive impact on these healthcare environments, because it increased the pace of innovation, improved the innovations' scalability, and made hospitals robust in implementing digital innovation practices. Their interesting case studies helped to find these key mechanisms for institutionalizing digital innovation, but at the same time contributed towards a model of productive scalable innovations. The case studies show how entrepreneurship of new organizational structures in healthcare delivery unfolds over time and how institutionalized practices can empower employees to innovate. The paper entitled "Semantic Computational Models for Polypharmacology: Applications in DrugRepurposing" is a collaborative work of authors with different research backgrounds in biomedicine, translational informatics and computer science, which explores software technologies for creating potentially new computational models for polypharmacology.The purpose is to address problems related to drug discoveries, with relation to potential drug repurposing.The proposal uses software technologies which enable reasoning through first order logic, in order to understand if drugs can be repurposed by exploiting their unintended therapeutical targets.However, the novelty, in terms of computational polypharmacology, is in trying to come closer to the ideal polypharmacological world of finding, developing, and approving multitargeted drugs and using them in drug repurposing. The implemented prototype shows numerous possibilities of using the proposed conceptual model, but they all have the joint goal of moving away from the one-drug-onetarget philosophy, which has been advocated by polypharmacology. Collapse

Topics: innovation management digital innovation entrepreneurship organization structure enterprise architecture

Methods: conceptual modelling design artifact

Relativity of Mindfulness: Team Collaboration in Digital and Physical Educational Escape Rooms

2023 | Communications of the Association for Information Systems | Citations: 0

Authors: Järveläinen, Jonna

Abstract: This study focuses on collaboration among team members in educational escape ro ... Expand

Abstract: This study focuses on collaboration among team members in educational escape rooms in higher education. The objective of this study was to understand how collective mindfulness and less mindful behavior unfold in physical and digital game-based learning. The video data were collected from three different courses comprising 107 students on 28 teams, totaling more than 16 hours of material. The qualitative analysis revealed both collectively mindful and less mindful behaviors in team interactions. This paper contributes to collective mindfulness literature in understanding team collaboration by observing that mindfulness may be relative depending on the observation perspective. It also presents factors that affect member equality in both digital and physical escape rooms. Lastly, a nuanced description of how team collaboration occurred in a short-term problem-solving situation is developed. Collapse

Topics: mindfulness problem solving video game gamification

Methods: theoretical contribution sequential analysis case study qualitative coding grounded theory

Assessing and Controlling the Social Desirability Bias in the Context of Victims, Perpetrators, and Bystanders of Cyberbullying

2023 | Americas Conference on Information Systems | Citations: 0

Authors: KIM, DONGYEON; Jang, Kyungmyung; Kang, Martin; Kwak, Dong-Heon; Knaff, Deborah

Abstract: Cyberbullying refers to intentional and repeated aggressive acts using electron ... Expand

Abstract: Cyberbullying refers to intentional and repeated aggressive acts using electronic communication against victims who cannot defend themselves. This widespread phenomenon can affect individuals of any age or gender, severely disrupting the lives of victims and their families. While previous research has focused on understanding the determinants and consequences of cyberbullying from the perspectives of perpetrators, victims, and bystanders, social desirability (SD) bias has been overlooked in the perspectives of bystanders and victims. Our study examines SD bias in the context of cyberbullying perpetrators, victims, and bystanders. To assess and control SD bias, this study uses the 16-item Balanced Inventory of Desirable Responding and the covariance technique. Collapse

Topics: cyberbullying self efficacy behavioral intention crowdsourcing

Methods: survey

Theories: protection motivation theory

Introduction to Minitrack Big Data and Analytics: Pathways to Maturity

2023 | HICSS | Citations: 0

Authors: Kaisler, S.; Armour, F.; Espinosa, J.

Abstract: This minitrack features six papers describing and assessing several aspects of ... Expand

Abstract: This minitrack features six papers describing and assessing several aspects of Big Data and Analytics. Key papers include two on assessing concept drift in machine learning applications and a continuing investigation of the issues and challenges facing Big Data and Analytics over the next several years. Collapse

Topics: big data computer system armed conflict cloud computing explainable artificial intelligence

Methods: experiment cluster analysis machine learning computational algorithm convolutional neural network

Reframing the Discourse on Work-Life Balance in the Digital Age

2023 | International Conference on Information Systems | Citations: 0

Authors: Kajtazi, Miranda; Johnson, Desmond; Sarker, Saonee; Faith, Becky; Venkatesh, Viswanath

Abstract: This paper reframes our understanding of the discourse on work-life balance (WL ... Expand

Abstract: This paper reframes our understanding of the discourse on work-life balance (WLB) from a global perspective, where life on the four income levels (from bottom of the wealth to top of the wealth) is equally considered. Based on a systematic literature review, our initial insights are that WLB of workers in the highest economic sectors has received significant attention from scholars and practitioners in the west, while the global rest and those in other economic sectors, which represents the majority of the world's population, has almost entirely been overlooked. We argue for a new understanding of WLB that addresses the needs of all people across the globe, regardless of their economic status or geographic position, and independent of their formal or informal work contexts. In our future work, we aim to address how disparities in: (1) agency and dependence; (2) privacy and exposure; (3) connection and disconnection; and (4) formality and informality can affect people's dignity, equality, and healthy environments. Collapse

Topics: Sustainable Development Goal innovation management IS impact information system use systems design

Methods: structured literature research cross sectional research literature study theory development

Theories: theory of economic growth

Have the Agile Principles Endured? An Empirical Investigation Post 20th Anniversary of the Agile Manifesto (2001)

2023 | HICSS | Citations: 0

Authors: Kakar, Adarsh Kumar; Kakar, Ashish

Abstract: This study investigates whether the Agile principles introduced in the Agile Man ... Expand

Abstract: This study investigates whether the Agile principles introduced in the Agile Manifesto (2001) have endured today two decades later and whether they are still relevant to software developers. Further, are they positively correlated with work and affective outcomes of software development projects? We find out by conducting a survey with team members of 58 software development project in one of the largest global IT firms. To our surprise we find that overall, the Agile principles have endured and were positively correlated with team motivation, project effectiveness and project innovation. However, they were negative correlated with project efficiency. As expected, projects using Agile and plan-driven methodologies showed differential findings. Collapse

Topics: systems development innovation management intrinsic motivation IT project IT development project

Methods: survey multiple regression data transformation factor analysis

Cognitive load during planned and unplanned virtual shopping: Evidence from a neurophysiological perspective

2023 | International Journal of Information Management | Citations: 0

Authors: Kakaria, Shobhit; Saffari, Farzad; Z. Ramsøy, Thomas; Bigné, Enrique

Abstract: Rapid adoption of virtual-reality-assisted retail applications is inadvertently ... Expand

Abstract: Rapid adoption of virtual-reality-assisted retail applications is inadvertently reshaping consumer buying pat­ terns, making it crucial for businesses to enhance their shopping experience. This new scenario challenges marketers with unique hurdles in both the commercialization of products and in managing information cues derived via VR retailing. Therefore, this study examined consumers’ impulsive behavior and unplanned pur­ chases in a virtual retail store, using self-reports and electroencephalography. Borrowing assorted perspectives from retailing, virtual reality, and neuromarketing literature, we extended the stimulus-organism-response framework to evaluate how unplanned behavior evolves through conscious and unconscious measures. We found that consumers’ impulsiveness was significantly associated with their unplanned expenditure and the number of unplanned purchases. Using mediation analysis, we observed that flow experience during shopping partially mediated the relationship between the sense of presence and the desire to stay longer in a virtual shopping store. Desire to stay in the virtual store positively influenced store satisfaction, basket-size deviation, and budget deviation. Additionally, cognitive workload obtained via electroencephalogram revealed significant differences during both planned and unplanned purchases. These findings provide fresh opportunities for re­ tailers to leverage the disruptive potential of immersive and interactive virtual technology to transform consumer shopping experiences. Collapse

Topics: virtual reality decision making psychological ownership social media marketing management

Methods: electroencephalography self reported survey longitudinal research neurophysiology experiment