1 April 2020 in Computer Methods and Programs in Biomedicine
AEAmir Ebrahimighahnavieh
1 August 2021 in Computers in Biology and Medicine
1 January 2019 in IEEE Transactions on Affective Computing
Automatic human affect recognition is a key step towards more natural human-computer interaction. Recent trends include recognition in the wild using a fusion of audiovisual and physiological sensors, a challenging setting for conventional machine learning algorithms. Since 2010, novel deep learning algorithms have been applied increasingly in this field. In this paper, we review the literature on human affect recognition between 2010 and 2017, with a special focus on approaches using deep neural networks. By classifying a total of 950 studies according to their usage of shallow or deep architectures, we are able to show a trend towards deep learning. Reviewing a subset of 233 studies that employ deep neural networks, we comprehensively quantify their applications in this field. We find that deep learning is used for learning of (i) spatial feature representations, (ii) temporal feature representations, and (iii) joint feature representations for multimodal sensor data. Exemplary state-of-the-art architectures illustrate the recent progress. Our findings show the role deep architectures will play in human affect recognition, and can serve as a reference point for researchers working on related applications.
4 February 2019 in Industrial Management & Data Systems
Purpose: The purpose of this paper is to identify the key facilitators and inhibitors of fitness wearable technology (FWT) adoption and the intention to recommend this technology. Design/methodology/approach: An innovative and integrated research model was developed by combining constructs from two well-established theoretical models, the extended unified theory of acceptance and use of technology (UTAUT2) and diffusion of innovation (DOI). The proposed research model was empirically validated using data collected from 392 respondents in China. The data was analyzed using the partial least squares method, a statistical analysis technique based on structural equation modeling. Findings: The results indicate that performance expectancy, effort expectancy, social influence, habit, compatibility and innovativeness have significant direct and indirect effects on FWT adoption and the intention to recommend it. The significance of people’s intention to recommend FWT to others in social networking sites (e.g. Facebook, Weibo, and WeChat) is also confirmed. Practical implications: The findings may facilitate the design and implementation of FWT products, applications and functionalities that can achieve high consumer acceptance and positive recommendations in social networks. Originality/value: This study is among the first to investigate FWT adoption from behavioral, social and environmental perspectives. It also highlights the importance of social marketing campaigns and suggests directions of future wearable technology adoption research.
6 December 2017 in Frontiers of Computer Science
1 July 2021 in Computers in Biology and Medicine