Guanxiong Pei

Guanxiong Pei

Auto-generated profile, based on publicly available information

Guanxiong Pei

Zhejiang Laboratory of Philosophy and Social Sciences - Laboratory of Intelligent Society and Governance, Zhejiang Lab, Hangzhou 311121, China; Development Strategy and Cooperation Center, Zhejiang Lab, Hangzhou 311121, China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 January 2024 in Intelligent Computing
Verified
Journal Article
Closed access
GPGuanxiong Pei
Guanxiong Pei
HLHaiying Li
Haiying Li
YLYandi Lu
Yandi Lu
YWYanlei Wang
Yanlei Wang
SHShizhen Hua
Shizhen Hua
TLTaihao Li
Taihao Li
Affective computing is a rapidly growing multidisciplinary field that encompasses computer science, engineering, psychology, neuroscience, and other related disciplines. Although the literature in this field has progressively grown and matured, the lack of a comprehensive bibliometric analysis limits the overall understanding of the theory, technical methods, and applications of affective computing. This review presents a quantitative analysis of 33,448 articles published in the period from 1997 to 2023, identifying challenges, calling attention to 10 technology trends, and outlining a blueprint for future applications. The findings reveal that the emerging forces represented by China and India are transforming the global research landscape in affective computing, injecting transformative power and fostering extensive collaborations, while emphasizing the need for more consensus regarding standard setting and ethical norms. The 5 core research themes identified via cluster analysis not only represent key areas of international interest but also indicate new research frontiers. Important trends in affective computing include the establishment of large-scale datasets, the use of both data and knowledge to drive innovation, fine-grained sentiment classification, and multimodal fusion, among others. Amid rapid iteration and technology upgrades, affective computing has great application prospects in fields such as brain–computer interfaces, empathic human–computer dialogue, assisted decision-making, and virtual reality.

10 September 2024 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Open access
MWMinchao Wu
Minchao Wu
WTWei Teng
Wei Teng
CFCunhang Fan
Cunhang Fan
SPShengbing Pei
Shengbing Pei
PLPing Li
Ping Li
ZLZhao Lv
Zhao Lv
Affective data is the basis of emotion recognition, which is mainly acquired through extrinsic elicitation. To investigate the enhancing effects of multi-sensory stimuli on emotion elicitation and emotion recognition, we designed an experimental paradigm involving visual, auditory, and olfactory senses. A multimodal emotional dataset (OVPD-II) that employed the video-only or video-odor patterns as the stimuli materials, and recorded the electroencephalogram (EEG) and electrooculogram (EOG) signals, was created. The feedback results reported by subjects after each trial demonstrated that the video-odor pattern outperformed the video-only pattern in evoking individuals’ emotions. To further validate the efficiency of the video-odor pattern, the transformer was employed to perform the emotion recognition task, where the highest accuracy reached 86.65% (66.12%) for EEG (EOG) modality with the video-odor pattern, which improved by 1.42% (3.43%) compared with the video-only pattern. What’s more, the hybrid fusion (HF) method combined with the transformer and joint training was developed to improve the performance of the emotion recognition task, which achieved classify accuracies of 89.50% and 88.47% for the video-odor and video-only patterns, respectively.

18 April 2023 in Neuroscience Letters
Verified
Journal Article
Closed access
QSQian Shang
Qian Shang
JCJialiang Chen
Jialiang Chen
HFHuijian Fu
Huijian Fu
CWCuicui Wang
Cuicui Wang
GPGuanxiong Pei
Guanxiong Pei
JJJia Jin
Jia Jin

24 September 2022 in Neuropsychologia
Verified
Journal Article
Closed access
DLDong Lyu
Dong Lyu
QLQingsong Liu
Qingsong Liu
YPYu Pan
Yu Pan
AWAilian Wang
Ailian Wang
GPGuanxiong Pei
Guanxiong Pei
JJJia Jin
Jia Jin

21 February 2018 in PLOS ONE
Verified
Journal Article
Open access
PDF file
QSQian Shang
Qian Shang
GPGuanxiong Pei
Guanxiong Pei
JJJia Jin
Jia Jin
WZWuke Zhang
Wuke Zhang
YWYuran Wang
Yuran Wang
Xiaoyi WangXiaoyi Wang
Xiaoyi Wang
Copycat brands mimic brand leaders to free ride on the latter's equity. However, little is known regarding if and how consumers confuse copycat as leading brand in purchasing. In this study, we applied a word-pair evaluation paradigm in which the first word was a brand name (copycat vs. normal brand both similar with a leading brand in category), followed by a product name (near vs. far from the leading brand’s category). Behavioral results showed that, when the product is near the leader’s category, the copycat strategy (CN) was more preferred compared to the normal brand (NN) but not different in the far product condition (CF and NF). Event-related potential (ERP) data provided further insight into the mechanism. The N400 amplitude elicited by the CN condition was significantly smaller than NN. However, when products are far from the leader’s category, there was no significant difference in N400 amplitudes. For the late positive component (LPC), the CN gave rise to a larger amplitude than the CF. The N400 amplitude was suggested to reflect the categorization process, and the LPC demonstrated the recollection process in long-term memory. These findings imply that the copycat brand strategy is generally only effective when products are within the category of the leading brand, which offers important implications for marketing practices.

17 February 2023
Verified
Conference Paper
Open access
GPGuanxiong Pei
Guanxiong Pei
CFCunhang Fan
Cunhang Fan
TLTaihao Li
Taihao Li
JJJia Jin
Jia Jin
RWRui Wang
Rui Wang
Virtual reality technology provides a strong sense of immersion and interactivity. It is widely used in the fields of anxiety relief, fear therapy, and depression regulation. However, objectively evaluating the emotional intervention effect of virtual reality technology is a difficult problem. The main purpose of this paper is to explore the use of EEG signals to identify individual emotional states in virtual reality scenarios and to improve the computational efficiency and recognition accuracy of emotional valence. To induce the target emotional state of the participants, we established a relatively standard emotion-induced virtual reality video library. The EEG data of the participants were collected synchronously as they watched the virtual reality video. The results show that the emotion recognition performance of multiple features (energy spectrum, differential entropy, differential asymmetry, and rational asymmetry) is better than that of a single feature. The radial basis function neural network (RBFNN) performed better than the deep belief network (DBN). RBFNN achieves the highest average classification accuracy of 91.1%. By combining the feature selection (F-test) method with the RBFNN, an ideal classification performance can be maintained with computational efficiency improvements. Furthermore, it is demonstrated that the features extracted from the theta band outperform features extracted from other bands in emotional valence decoding. These results may contribute to the application of EEG-based affective computing technology in the field of psychological rehabilitation and assessment.