A5043375633- Complex Network Analysis Techniques
- Face and Expression Recognition
- Mental Health Research Topics
- Opinion Dynamics and Social Influence
- Functional Brain Connectivity Studies
- Online Learning and Analytics
- Sparse and Compressive Sensing Techniques
- Bioinformatics and Genomic Networks
- Advanced Clustering Algorithms Research
- Advanced Graph Neural Networks
- Remote-Sensing Image Classification
- Sentiment Analysis and Opinion Mining
- Dementia and Cognitive Impairment Research
- Video Surveillance and Tracking Methods
- Advanced Statistical Methods and Models
- Educational Technology and Pedagogy
- Complex Systems and Time Series Analysis
- Emotion and Mood Recognition
- Time Series Analysis and Forecasting
- Speech Recognition and Synthesis
- Stock Market Forecasting Methods
- Neural dynamics and brain function
- Big Data Technologies and Applications
Anhui University of Finance and Economics
2022-2024
Nanjing University of Science and Technology
2018-2022
Emotion recognition plays an essential role in interpersonal communication. However, existing systems use only features of a single modality for emotion recognition, ignoring the interaction information from different modalities. Therefore, our study, we propose global-aware Cross-modal feature Fusion Network (GCF2-Net) recognizing emotion. We construct residual cross-modal fusion attention module (ResCMFA) to fuse multiple modalities and design capture global details. More specifically,...
Multi-view graph clustering has garnered tremendous interest for its capability to effectively segregate data by harnessing information from multiple graphs representing distinct views. Despite the advances, conventional methods commonly construct similarity straightway raw features, leading suboptimal outcomes due noise or outliers. To address this, latent representation-based emerged. However, it often hypothesizes that views share a fixed-dimensional coefficient matrix, potentially...
Community detection is a critical issue in the field of complex networks. Recently, nonnegative matrix factorization (NMF) method has successfully uncovered community structure However, this significant drawback; most methods using NMF require number communities to be preassigned or determined by searching for best among all candidates. To address problem, paper, we use density peak clustering (DPC) obtain centers as pre-defined parameter factorization. due sparse and high dimensional...
A novel method for fuzzy time series (FTS) forecasting is presented based on improved C-means clustering algorithm (IFCM) and first-order difference. Traditional approaches have weighted the central values of intervals corresponding to sets, but may not be accurate enough since assumed membership functions different. To avoid problem even distribution, in this paper, we weight cluster centers derived from IFCM that defines initial traditional (FCM). There are many unstable characteristics...
With the increasing demands of computer science-related human resources, universities have gradually adjusted curricular scheme undergraduate students, incorporating more computer-oriented courses, such as data mining, Python programming, and database application. Conventional off-line teaching is limited to imparting theoretical knowledge failing enhance their practical abilities, which are crucial in realm courses. Therefore, based on our experience about mining course, we analyze benefits...
In order to better focus on ability cultivation and stimulate students' innovative abilities, this paper proposes a teaching model based the Educoder platform for machine learning courses. This analyzes drawbacks of traditional teaching, combines needs as discipline, through mode reform, combined with platform, demonstrates operational application it in teaching. It not only greatly improves interest, but also allows students truly become main body learning, consequently yielding substantial...
Constructing functional connectivity/interactions networks enables better understanding of pathological underpinnings neurological disorders. Functional connectivity network, as a simplified representation those structural or interactions, has been widely used for diagnosis and classification neurodegenerative diseases. Motivated by recent progress in network analysis Alzheimer's disease (AD). In this paper, we propose novel adjusted cosine similarity weighted group sparse (ACS-WGS) method...