IEEE Communications Magazine · 2018 · 115 citations · 14 references
EngineeringMobile InteractionAffective DesignAffective NeuroscienceCommunicationSocial SciencesDynamic Spectrum ManagementData SciencePervasive ComputingAffective ComputingEmotion-aware SolutionCognitive RadioCognitive NetworkUser ExperienceMobile ComputingComputer ScienceMobile ApplicationsCognitive Radio Resource ManagementWireless Cooperative NetworkHuman-computer InteractionEmotion-aware Cognitive SystemEmotionContext-aware Pervasive SystemEmotion Recognition
The development of multi‑channel cognitive radio ad hoc networks (mCRAHNs) enables a growing range of mobile applications and services. The paper proposes an emotion‑aware cognitive system (ECS) to systematically support deployment of emotion‑aware mobile applications in mCRAHNs. ECS comprises multidimensional emotional data collection and processing modules, a flow of emotion‑aware solution, and integrates key technologies and schemes for runtime orchestration of mobile applications in mCRAHNs. The feasibility of ECS is demonstrated through the iSmile application, showing that the system performs effectively for emotion‑aware mobile tasks in mCRAHNs.
With the development of mCRAHNs, more emerging mobile applications and services could be foreseen and applied in our human society. In this article, we propose an emotion-aware cognitive system (ECS), which aims to provide a systematic approach that can facilitate deployment of different emotion-aware mobile applications in mCRAHNs. ECS is constructed to provide multidimensional emotional data collection and processing approaches for mobile applications working in mCRAHNs. Also, we present a flow of emotion-aware solution designed on ECS, and highlight the implementation and orchestration of several key technologies and schemes we apply in this system for different emotion-aware mobile applications in runtime. In addition, we demonstrate the feasibility of the proposed ECS by presenting a novel emotion-aware mobile application, iSmile, and evaluate the system performance based on this application.
14
Xin Luo, MengChu Zhou, Shuai Li et al. · IEEE Transactions on Neural Networks and Learning Systems · 2015 · 324 citations
Engineering, Machine Learning, Nonnegative Matrix Factorization +16