Search results for "SVI"
showing 10 items of 4456 documents
Enhancing Attention’s Explanation Using Interpretable Tsetlin Machine
2022
Explainability is one of the key factors in Natural Language Processing (NLP) specially for legal documents, medical diagnosis, and clinical text. Attention mechanism has been a popular choice for such explainability recently by estimating the relative importance of input units. Recent research has revealed, however, that such processes tend to misidentify irrelevant input units when explaining them. This is due to the fact that language representation layers are initialized by pre-trained word embedding that is not context-dependent. Such a lack of context-dependent knowledge in the initial layer makes it difficult for the model to concentrate on the important aspects of input. Usually, th…
What is it about humanity that we can't give away to intelligent machines? A European perspective
2021
Abstract One of the most significant recent technological developments concerns the development and implementation of ‘intelligent machines’ that draw on recent advances in artificial intelligence (AI) and robotics. However, there are growing tensions between human freedoms and machine controls. This article reports the findings of a workshop that investigated the application of the principles of human freedom throughout intelligent machine development and use. Forty IS researchers from ten different countries discussed four contemporary AI and humanity issues and the most relevant IS domain challenges. This article summarizes their experiences and opinions regarding four AI and humanity th…
Doppler Shift Characterization of Wideband Mobile Radio Channels
2019
The prevailing approach for characterizing the Doppler shift (DS) of mobile radio channels assumes the transmission of an unmodulated carrier. This consideration is valid for the analysis of narrowband channels, but its pertinence is questionable in regards to the modeling of wideband channels. In this correspondence, we redefine the DS from a time-frequency analysis perspective that does not depend on the aforementioned assumption. We systematically demonstrate that the DS can be characterized by the instantaneous frequency of the channel transfer function. This generic definition makes evident a fundamental aspect of the DS that is seldom acknowledged, namely, the DS is a frequency-varyin…
Exploring Lightweight Deep Learning Solution for Malware Detection in IoT Constraint Environment
2022
The present era is facing the industrial revolution. Machine-to-Machine (M2M) communication paradigm is becoming prevalent. Resultantly, the computational capabilities are being embedded in everyday objects called things. When connected to the internet, these things create an Internet of Things (IoT). However, the things are resource-constrained devices that have limited computational power. The connectivity of the things with the internet raises the challenges of the security. The user sensitive information processed by the things is also susceptible to the trusability issues. Therefore, the proliferation of cybersecurity risks and malware threat increases the need for enhanced security in…
Seeking Information on Social Commerce: An Examination of the Impact of User- and Marketer-generated Content Through an Eye-tracking Study
2021
Following the growing popularity of social commerce sites, there is an increased interest in understanding how consumers decide what products to purchase based on the available information. Consumers nowadays are confronted with the task of assessing marketer-generated (MGC) as well as user-generated information (UGC) in a range of different forms to make informed purchase-related decisions. This study examines the information types and forms that influence consumers in their decision-making process on social commerce. Building on uses and gratifications and dual-process theories, we distinguish between marketer and user generated content, and differentiate formats into informational and no…
Evaluation of Deep Learning and Conventional Approaches for Image Recaptured Detection in Multimedia Forensics
2022
Image recaptured from a high-resolution LED screen or a good quality printer is difficult to distinguish from its original counterpart. The forensic community paid less attention to this type of forgery than to other image alterations such as splicing, copy-move, removal, or image retouching. It is significant to develop secure and automatic techniques to distinguish real and recaptured images without prior knowledge. Image manipulation traces can be hidden using recaptured images. For this reason, being able to detect recapture images becomes a hot research topic for a forensic analyst. The attacker can recapture the manipulated images to fool image forensic system. As far as we know, ther…
Familiarity with digital twin totality: Exploring the relation and perception of affordances through a Heideggerian perspective
2022
The concept of affordances has become central in information systems literature. However, existing perspectives fall short in providing details on the relational aspect of affordances, which can influence actors' perception of them. To increase granularity and specificity in this regard, researchers have suggested that it be supplemented with other concepts or theories. In this article, we argue that the Heideggerian concepts of ‘familiarity’ and ‘referential totality’ are well suited for increasing our understanding of the relational aspects of affordances in information systems research. To explore this idea, we conducted a case study of a project concerning the development of a digital t…
A Bayesian unified framework for risk estimation and cluster identification in small area health data analysis.
2020
Many statistical models have been proposed to analyse small area disease data with the aim of describing spatial variation in disease risk. In this paper, we propose a Bayesian hierarchical model that simultaneously allows for risk estimation and cluster identification. Our model formulation assumes that there is an unknown number of risk classes and small areas are assigned to a risk class by means of independent allocation variables. Therefore, areas within each cluster are assumed to share a common risk but they may be geographically separated. The posterior distribution of the parameter representing the number of risk classes is estimated using a novel procedure that combines its prior …
A hybrid virtual–boundary element formulation for heterogeneous materials
2021
Abstract In this work, a hybrid formulation based on the conjoined use of the recently developed Virtual Element Method (VEM) and the Boundary Element Method (BEM) is proposed for the effective computational analysis of multi-region domains, representative of heterogeneous materials. VEM has been recently developed as a generalisation of the Finite Element Method (FEM) and it allows the straightforward employment of elements of general polygonal shape, maintaining a high level of accuracy. For its inherent features, it allows the use of meshes of general topology, including non-convex elements. On the other hand, BEM is an effective technique for the numerical solution of sets of boundary i…
Performing transnational family with the affordances of mobile apps : a case study of Polish mothers living in Finland
2020
Affordances provided by digital technologies and mobile apps (WhatsApp, Skype, Messenger) help in maintaining familyhood. These mobile apps enable the creation of in-app family groups. They also afford image sharing, which is used for phatic purposes. Digital connectivity provides the illusions of togetherness and belonging, and allows for performing family in a transnational context (emotional transnationalism). However, it also generates the feelings of guilt through infrequent communication. In the auto-driven visual elicitation interviews, the study looks at family constellations and technologically mediated communication from the perspective of five Polish mothers living in Finland. Ap…