Search

Your search keyword '"Shou, Zhaoyu"' showing total 41 results
Start Over Author "Shou, Zhaoyu"
41 results on '"Shou, Zhaoyu"'

2. Key Student Nodes Mining in the In-Class Social Network Based on Combined Weighted GRA-TOPSIS Method

Author

Shou, Zhaoyu, Tang, Mengxue, Wen, Hui, Liu, Jinghua, Mo, Jianwen, and Zhang, Huibing

Abstract

In this paper, a key node mining algorithm of entropy-CRITIC combined weighted GRA-TOPSIS method is proposed, which is based on the network structure features. First, the method obtained multi-dimensional data of students' identities, seating relationships, social relationships, and so on to build a database. Then, the seating similarity among students was used to construct the in-class social networks and analyze the structural characteristics of them. Finally, the CRITIC and entropy weight method was introduced for obtaining the combined weight values and the GRA-TOPSIS multi-decision fusion algorithm to mine the key student nodes that have negative impact. The experiments showed that the algorithm of this paper can evaluate students objectively based on their classroom social networks, providing technical support for process-oriented comprehensive quality education evaluation.

Published
2023
Full Text
View/download PDF

6. A Dynamic Position Embedding-Based Model for Student Classroom Complete Meta-Action Recognition.

Author

Shou, Zhaoyu, Yuan, Xiaohu, Li, Dongxu, Mo, Jianwen, Zhang, Huibing, Zhang, Jingwei, and Wu, Ziyong

Subjects
*TRANSFORMER models, *SPATIAL ability, *PSYCHOLOGY of students, *RECOGNITION (Psychology), *DYNAMIC models
Abstract

The precise recognition of entire classroom meta-actions is a crucial challenge for the tailored adaptive interpretation of student behavior, given the intricacy of these actions. This paper proposes a Dynamic Position Embedding-based Model for Student Classroom Complete Meta-Action Recognition (DPE-SAR) based on the Video Swin Transformer. The model utilizes a dynamic positional embedding technique to perform conditional positional encoding. Additionally, it incorporates a deep convolutional network to improve the parsing ability of the spatial structure of meta-actions. The full attention mechanism of ViT3D is used to extract the potential spatial features of actions and capture the global spatial–temporal information of meta-actions. The proposed model exhibits exceptional performance compared to baseline models in action recognition as observed in evaluations on public datasets and smart classroom meta-action recognition datasets. The experimental results confirm the superiority of the model in meta-action recognition. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

12. Outlier Detection Based on Local Density of Vector Dot Product in Data Stream

Author

Shou, Zhaoyu, Zou, Fengbo, Tian, Hao, Li, Simin, Kacprzyk, Janusz, Series Editor, Pal, Nikhil R., Advisory Editor, Bello Perez, Rafael, Advisory Editor, Corchado, Emilio S., Advisory Editor, Hagras, Hani, Advisory Editor, Kóczy, László T., Advisory Editor, Kreinovich, Vladik, Advisory Editor, Lin, Chin-Teng, Advisory Editor, Lu, Jie, Advisory Editor, Melin, Patricia, Advisory Editor, Nedjah, Nadia, Advisory Editor, Nguyen, Ngoc Thanh, Advisory Editor, Wang, Jun, Advisory Editor, Yang, Ching-Nung, editor, Peng, Sheng-Lung, editor, and Jain, Lakhmi C., editor

Published
2020
Full Text
View/download PDF

14. Spatial Outlier Information Hiding Algorithm Based on Complex Transformation

Author

Shou, Zhaoyu, Liu, Akang, Li, Simin, Cheng, Xiawei, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, Wang, Guojun, editor, Atiquzzaman, Mohammed, editor, Yan, Zheng, editor, and Choo, Kim-Kwang Raymond, editor

Published
2017
Full Text
View/download PDF

20. The NEDC-GTOPSIS Node Influence Evaluation Algorithm Based on Multi-Layer Heterogeneous Classroom Networks

Author

Shou, Zhaoyu, Wen, Hui, Zhang, Huibing, Xie, Jinling, Tang, Jinghang, and Li, Dongxu

Abstract

To address the deficiency in the analysis of individual students within existing research on in-classroom social networks and the constraints of traditional centrality metrics in identifying influential nodes, this paper presents the NEDC-GTOPSIS evaluation method for evaluating node influence in multi-layer heterogeneous networks. Initially, students' friendship, interaction, and attribute information are leveraged to compute neighborhood overlap and attribute similarity between nodes, to construct the Composite Relationship Network. Subsequently, the Seat Similarity Network is constructed by applying the Nearest-Neighbor Effective Distance Criterion to compute seat similarity across various class sessions among nodes. Finally, the structure characteristics of two networks serve as influence decision indicators, and the GRA-TOPSIS algorithm, based on the combined weight method, evaluates nodes' influence. Experiments demonstrate that, compared to traditional single-layer relational networks and classical algorithms, this method can more effectively assess influential student nodes.

Published
2023
Full Text
View/download PDF

35. Fine grained sentiment analysis based on Bert

Author

Xiaoli Hu, Shou Zhaoyu, Chao Chen, and Zhang Huibing

Subjects
History, business.industry, Political science, Sentiment analysis, Artificial intelligence, business, computer.software_genre, computer, Natural language processing, Computer Science Applications, Education
Abstract

The fine-grained sentiment mining based on online review data is helpful to analyze user pain points and improve user experience and business marketing. A fine-grained sentiment analysis model based on Bert is proposed. Commodity feature words and emotion words are extracted by dependency parsing; the polarity of emotion was analyzed by the combination of Bert and emotional words; through the corresponding emotional polarity of feature words, we can get the emotional tendency of commodity features. The experimental results in movie review data set and film review data set show that, the accuracy and F1 value of Bert with feature words and emotional words were 94.67% and 94.55%, which were better than other models.

Published
2020

39. Constraint Mechanism of Reputation Formation Based on Signaling Model in Social Commerce

Author

Shou Zhaoyu, Zhang Huibing, and Hu Xiaoli

Subjects
Sequential game, Process (engineering), media_common.quotation_subject, TheoryofComputation_GENERAL, Constraint (information theory), Microeconomics, Bayes' theorem, Interpersonal ties, Key (cryptography), ComputingMilieux_COMPUTERSANDSOCIETY, Business, Marketing, Reputation, media_common, Meaning (linguistics)
Abstract

A typical feature of weak relationship between the users and sellers emerges in social commerce. The seller's reputation is a key element to ensure smooth online transactions in this weak ties environment. This paper constructs a model which integrated Bayes rule and signaling model to analyses the key factors constraining reputation formation. First, to get the reputation constraint factors under separating equilibrium conditions by setting up a model based on the seller's reputation signal between sellers and users' dynamic game process; then, to establish computing model of the seller's reputation in social commerce according to Bayes' theorem; last, analyzing the meaning of constraints to reputation calculation. This research will provide theoretical guidance to reasonable setting of two key elements affecting the seller's reputation.

Published
2015

41. A Metadata-P2P Framework for Discovery of File-sharing.

Author

Huang, Zhensheng and Shou, Zhaoyu

Subjects
METADATA, PEER-to-peer architecture (Computer networks), COMPUTER file sharing, SEARCH engines, APPLICATION software, INFORMATION sharing, DATA structures
Abstract

Abstract: Peer-to-peer file-sharing systems offer a simple way to store and access large amounts of data in a distributed and fault-tolerant manner. These systems enable users to form communities for sharing different types of files. One important feature is the ability to search, but many existing systems provide only limited ability to search using metadata. Metadata-P2P is a new application framework that exploits metadata to improve search in file-sharing communities. Additionally, Metadata-P2P simplifies the creation and discovery of file-sharing communities. Each community allows the sharing of a particular type of structured document. Users can easily create new formats and communities. [Copyright &y& Elsevier]

Published
2011
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results