Pub Date : 2022-12-18DOI: 10.1109/IEIR56323.2022.10050082
Xinguo Yu, Jing Xia, Weina Cheng
Equipping mathematics tutoring systems with per-sonalized learning strategies is a crucial task in providing personalized learning service. The advance of intelligent educational technology sheds a touchable prospect for practicing personalized learning model. The cloud-based education systems have already provided the platform that can support the scale personalized service. The solving algorithms in mathematics is going to support the personalized learning for mathematics. The educational robots have potential to provide the personalized interactions with learners. However, we still face the challenges in building personalized learning strategies for mathematics. The challenges lie in that we still have difficulty in acquiring the trust learner profile, building strategies of learning mathematics, and finding the relations between profiles and strategies.
{"title":"Prospects and Challenges of Equipping Mathematics Tutoring Systems with Personalized Learning Strategies","authors":"Xinguo Yu, Jing Xia, Weina Cheng","doi":"10.1109/IEIR56323.2022.10050082","DOIUrl":"https://doi.org/10.1109/IEIR56323.2022.10050082","url":null,"abstract":"Equipping mathematics tutoring systems with per-sonalized learning strategies is a crucial task in providing personalized learning service. The advance of intelligent educational technology sheds a touchable prospect for practicing personalized learning model. The cloud-based education systems have already provided the platform that can support the scale personalized service. The solving algorithms in mathematics is going to support the personalized learning for mathematics. The educational robots have potential to provide the personalized interactions with learners. However, we still face the challenges in building personalized learning strategies for mathematics. The challenges lie in that we still have difficulty in acquiring the trust learner profile, building strategies of learning mathematics, and finding the relations between profiles and strategies.","PeriodicalId":183709,"journal":{"name":"2022 International Conference on Intelligent Education and Intelligent Research (IEIR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128571670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-18DOI: 10.1109/IEIR56323.2022.10050053
Wenxin Huang, Wenxuan Liu, Xuemei Jia
Scene parsing is a hot topic in the field of computer vision communities. It has extensive applications in visual perception e.g. education system, human-object robots, etc. However, there exists a huge size difference among objects in the scene image because of the diversity of objects and the influence of observation distance and other factors. How to better solve the varying scale problem has become a challenging problem in scene parsing. Thus, a tree-structure is proposed to handle the varying scale problem, where the feature maps of different levels are gradually nested and connected, which strengthens the connection between multiple feature maps, and captures more representative information. For real-time, we propose a framework named tree structure enhancement lightweight network (TSELight), which introduces the depth-wise separable dilated convolution (DSDC) into the tree structure and decomposes the middle nodes in the tree structure along the channel direction, thus improving the efficiency. Experimental results demonstrate that our TSELight architecture outperforms state-of-the-art methods on Cityscapes dataset, and provides consistent improvements on the real-time scene parsing performance.
{"title":"Scene Parsing via Tree Structure Enhancement Lightweight Network","authors":"Wenxin Huang, Wenxuan Liu, Xuemei Jia","doi":"10.1109/IEIR56323.2022.10050053","DOIUrl":"https://doi.org/10.1109/IEIR56323.2022.10050053","url":null,"abstract":"Scene parsing is a hot topic in the field of computer vision communities. It has extensive applications in visual perception e.g. education system, human-object robots, etc. However, there exists a huge size difference among objects in the scene image because of the diversity of objects and the influence of observation distance and other factors. How to better solve the varying scale problem has become a challenging problem in scene parsing. Thus, a tree-structure is proposed to handle the varying scale problem, where the feature maps of different levels are gradually nested and connected, which strengthens the connection between multiple feature maps, and captures more representative information. For real-time, we propose a framework named tree structure enhancement lightweight network (TSELight), which introduces the depth-wise separable dilated convolution (DSDC) into the tree structure and decomposes the middle nodes in the tree structure along the channel direction, thus improving the efficiency. Experimental results demonstrate that our TSELight architecture outperforms state-of-the-art methods on Cityscapes dataset, and provides consistent improvements on the real-time scene parsing performance.","PeriodicalId":183709,"journal":{"name":"2022 International Conference on Intelligent Education and Intelligent Research (IEIR)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126698342","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-18DOI: 10.1109/IEIR56323.2022.10050085
Mengjuan Li, L. Niu, Jinhua Zhao, Yuchen Wang
Personalized exercise recommendation is a key research direction of personalized learning. In personalized exercise recommendation, we recommend suitable exercises for students according to their knowledge mastery status to improve their learning efficiency. Therefore, the accuracy of predicting students’ knowledge state in personalized exercise recommendation affects the goodness of the exercise recommendation. In the process of students’ learning, learning behavior and forgetting behavior are intertwined, and students’ forgetting behavior has a great influence on the knowledge state. In order to accurately model students’ learning and forgetting, we propose a Learning and Forgetting Convolutional Knowledge Tracking model (LFCKT) that takes into account both learning and forgetting behaviors. The model takes into account three factors that affect knowledge forgetting, including the interval time of target knowledge interaction, the count of past target knowledge interaction and student’s state of knowledge. LFCKT model uses students’ answer results as indirect feedback of knowledge mastery in the process of knowledge tracking, and integrates individual personalized learning behavior and individual forgetting behavior. Through experiments on the real online education public dataset, LFCKT can better track students’ knowledge mastery status and has better predictive performance than current knowledge tracking models.
{"title":"LFCKT: A Learning and Forgetting Convolutional Knowledge Tracking Model","authors":"Mengjuan Li, L. Niu, Jinhua Zhao, Yuchen Wang","doi":"10.1109/IEIR56323.2022.10050085","DOIUrl":"https://doi.org/10.1109/IEIR56323.2022.10050085","url":null,"abstract":"Personalized exercise recommendation is a key research direction of personalized learning. In personalized exercise recommendation, we recommend suitable exercises for students according to their knowledge mastery status to improve their learning efficiency. Therefore, the accuracy of predicting students’ knowledge state in personalized exercise recommendation affects the goodness of the exercise recommendation. In the process of students’ learning, learning behavior and forgetting behavior are intertwined, and students’ forgetting behavior has a great influence on the knowledge state. In order to accurately model students’ learning and forgetting, we propose a Learning and Forgetting Convolutional Knowledge Tracking model (LFCKT) that takes into account both learning and forgetting behaviors. The model takes into account three factors that affect knowledge forgetting, including the interval time of target knowledge interaction, the count of past target knowledge interaction and student’s state of knowledge. LFCKT model uses students’ answer results as indirect feedback of knowledge mastery in the process of knowledge tracking, and integrates individual personalized learning behavior and individual forgetting behavior. Through experiments on the real online education public dataset, LFCKT can better track students’ knowledge mastery status and has better predictive performance than current knowledge tracking models.","PeriodicalId":183709,"journal":{"name":"2022 International Conference on Intelligent Education and Intelligent Research (IEIR)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128900012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-18DOI: 10.1109/IEIR56323.2022.10050079
Mengxi Yang, Yanyan Jin, Zhengyang Zhang, S. Lian, Xian Peng
Vocabulary apps with their high accessibility and contextualization have made it a trend for college students for English learning. However, with the emergence of a new type of learning, it is a matter of concern how to improve user’s usage intention. This paper takes college students who use Maimemo App for learning as an example. Based on the Technology Acceptance Model, this paper explores the factors influencing user’s usage intention with words APP. The following conclusions are drawn: 1) According to the analyses of the moderating and mediating effects, memory pattern and resource optimization have positive effect on perceived usefulness and perceived ease of use; perceived usefulness and perceived ease of use indirectly affects users’ usage intention through self-efficacy; 2) This paper conducted multifactor analysis of variance on the data. The results show that the different duration and the learning contexts of people’s use with the English Vocabulary APP, the different extent of people’s usage intention. Users who have used the APP for “two to three months” are the ones who need more attention, and the demands of this group of users should be considered more deeply, so as to provide reference for the improvement of the English vocabulary apps.
{"title":"An empirical study on the factors influencing college students’ intention to use the English Vocabulary APP","authors":"Mengxi Yang, Yanyan Jin, Zhengyang Zhang, S. Lian, Xian Peng","doi":"10.1109/IEIR56323.2022.10050079","DOIUrl":"https://doi.org/10.1109/IEIR56323.2022.10050079","url":null,"abstract":"Vocabulary apps with their high accessibility and contextualization have made it a trend for college students for English learning. However, with the emergence of a new type of learning, it is a matter of concern how to improve user’s usage intention. This paper takes college students who use Maimemo App for learning as an example. Based on the Technology Acceptance Model, this paper explores the factors influencing user’s usage intention with words APP. The following conclusions are drawn: 1) According to the analyses of the moderating and mediating effects, memory pattern and resource optimization have positive effect on perceived usefulness and perceived ease of use; perceived usefulness and perceived ease of use indirectly affects users’ usage intention through self-efficacy; 2) This paper conducted multifactor analysis of variance on the data. The results show that the different duration and the learning contexts of people’s use with the English Vocabulary APP, the different extent of people’s usage intention. Users who have used the APP for “two to three months” are the ones who need more attention, and the demands of this group of users should be considered more deeply, so as to provide reference for the improvement of the English vocabulary apps.","PeriodicalId":183709,"journal":{"name":"2022 International Conference on Intelligent Education and Intelligent Research (IEIR)","volume":"2002 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127399584","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The study of cognitive engagement in collaborative learning is increasingly becoming a hot topic in the research field. This study is based on ICAP theory, automatic labeling of data, and a clear definition and analysis of group collaborative learning behavior considering the behavioral transition process of the group. The study was conducted on 69 learners who participated in three online collaborative learning activities over a period of 18 weeks to collect, analyze the behavioral transitions of the learners’ groups, and cluster the collaborative groups to obtain three different learning engagement styles with significant differences in their characteristics. The study shows that the behavioral transition characteristics of the learning groups discovered through the learning log data based on ICAP theory can be used as a reference for the analysis of cognitive input in online learning and the improvement of learning assistance.
{"title":"Analysis of Group Online Collaborative Learning Based on Log Data and ICAP","authors":"Xiuling He, Chenyang Wang, Yangyang Li, Zhipin Peng, Jing Fang","doi":"10.1109/IEIR56323.2022.10050064","DOIUrl":"https://doi.org/10.1109/IEIR56323.2022.10050064","url":null,"abstract":"The study of cognitive engagement in collaborative learning is increasingly becoming a hot topic in the research field. This study is based on ICAP theory, automatic labeling of data, and a clear definition and analysis of group collaborative learning behavior considering the behavioral transition process of the group. The study was conducted on 69 learners who participated in three online collaborative learning activities over a period of 18 weeks to collect, analyze the behavioral transitions of the learners’ groups, and cluster the collaborative groups to obtain three different learning engagement styles with significant differences in their characteristics. The study shows that the behavioral transition characteristics of the learning groups discovered through the learning log data based on ICAP theory can be used as a reference for the analysis of cognitive input in online learning and the improvement of learning assistance.","PeriodicalId":183709,"journal":{"name":"2022 International Conference on Intelligent Education and Intelligent Research (IEIR)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124082444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-18DOI: 10.1109/IEIR56323.2022.10050042
Zhifeng Wang, Jialong Yao, Chunyan Zeng, Wanxuan Wu, Hongmin Xu, Yang Yang
Deep learning-based computer vision technology has grown stronger in recent years, and cross-fertilization using computer vision technology has been a popular direction in recent years. The use of computer vision technology to identify students’ learning behavior in the classroom can reduce the workload of traditional teachers in supervising students in the classroom, and ensure greater accuracy and comprehensiveness. However, existing student learning behavior detection systems are unable to track and detect multiple targets precisely, and the accuracy of learning behavior recognition is not high enough to meet the existing needs for the accurate recognition of student behavior in the classroom. To solve this problem, we propose a YOLOv5s network structure based on you only look once (YOLO) algorithm to recognize and analyze students’ classroom behavior in this paper. Firstly, the input images taken in the smart classroom are pre-processed. Then, the pre-processed image is fed into the designed YOLOv5 networks to extract deep features through convolutional layers, and the Squeeze-and-Excitation (SE) attention detection mechanism is applied to reduce the weight of background information in the recognition process. Finally, the extracted features are classified by the Feature Pyramid Networks (FPN) and Path Aggregation Network (PAN) structures. Multiple groups of experiments were performed to compare with traditional learning behavior recognition methods to validate the effectiveness of the proposed method. When compared with YOLOv4, the proposed method is able to improve the mAP performance by 11%.
基于深度学习的计算机视觉技术近年来发展壮大，利用计算机视觉技术进行交叉受精是近年来的热门方向。利用计算机视觉技术识别学生在课堂上的学习行为，可以减少传统教师在课堂上监督学生的工作量，保证更大的准确性和全面性。然而，现有的学生学习行为检测系统无法对多个目标进行精确的跟踪和检测，学习行为识别的精度也不够高，无法满足现有对课堂学生行为准确识别的需求。为了解决这一问题，本文提出了一种基于YOLO (you only look once)算法的YOLOv5s网络结构来识别和分析学生的课堂行为。首先，对智能教室中采集的输入图像进行预处理。然后，将预处理后的图像输入到设计的YOLOv5网络中，通过卷积层提取深度特征，并采用挤压激励(sse)注意检测机制降低识别过程中背景信息的权重。最后，利用特征金字塔网络(FPN)和路径聚合网络(PAN)结构对提取的特征进行分类。通过多组实验与传统的学习行为识别方法进行比较，验证了所提方法的有效性。与YOLOv4相比，该方法的mAP性能提高了11%。
{"title":"YOLOv5 Enhanced Learning Behavior Recognition and Analysis in Smart Classroom with Multiple Students","authors":"Zhifeng Wang, Jialong Yao, Chunyan Zeng, Wanxuan Wu, Hongmin Xu, Yang Yang","doi":"10.1109/IEIR56323.2022.10050042","DOIUrl":"https://doi.org/10.1109/IEIR56323.2022.10050042","url":null,"abstract":"Deep learning-based computer vision technology has grown stronger in recent years, and cross-fertilization using computer vision technology has been a popular direction in recent years. The use of computer vision technology to identify students’ learning behavior in the classroom can reduce the workload of traditional teachers in supervising students in the classroom, and ensure greater accuracy and comprehensiveness. However, existing student learning behavior detection systems are unable to track and detect multiple targets precisely, and the accuracy of learning behavior recognition is not high enough to meet the existing needs for the accurate recognition of student behavior in the classroom. To solve this problem, we propose a YOLOv5s network structure based on you only look once (YOLO) algorithm to recognize and analyze students’ classroom behavior in this paper. Firstly, the input images taken in the smart classroom are pre-processed. Then, the pre-processed image is fed into the designed YOLOv5 networks to extract deep features through convolutional layers, and the Squeeze-and-Excitation (SE) attention detection mechanism is applied to reduce the weight of background information in the recognition process. Finally, the extracted features are classified by the Feature Pyramid Networks (FPN) and Path Aggregation Network (PAN) structures. Multiple groups of experiments were performed to compare with traditional learning behavior recognition methods to validate the effectiveness of the proposed method. When compared with YOLOv4, the proposed method is able to improve the mAP performance by 11%.","PeriodicalId":183709,"journal":{"name":"2022 International Conference on Intelligent Education and Intelligent Research (IEIR)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122374497","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-18DOI: 10.1109/IEIR56323.2022.10050045
Xuebi Xu, Shishun Wu, Shiwen Gu, Bin He, Xinguo Yu
Nowadays, e-Learning systems especially in science and technology subjects, are faced with a large number of symbol input tasks. And the traditional methods have the problem of low efficiency and difficulties in inputting unfamiliar symbols. To improve the efficiency of symbol input, this paper proposes a framework of the dynamic keyboard module with hierarchical mathematical symbol recommendation, which is based on the exercise-symbol patterns. Then a dynamic keyboard is designed to generate hierarchical mathematical symbols for multi-subject e-Learning systems, and the dynamic keyboard can improve the efficiency of symbol input. Finally, the proposed framework was evaluated on the learning system for Discrete mathematics and Statistics students. The experiment results demonstrate the effectiveness of our approach for symbol input.
{"title":"A Dynamic Keyboard with Hierarchical Mathematical Symbols for Multi-Subject e-Learning Systems","authors":"Xuebi Xu, Shishun Wu, Shiwen Gu, Bin He, Xinguo Yu","doi":"10.1109/IEIR56323.2022.10050045","DOIUrl":"https://doi.org/10.1109/IEIR56323.2022.10050045","url":null,"abstract":"Nowadays, e-Learning systems especially in science and technology subjects, are faced with a large number of symbol input tasks. And the traditional methods have the problem of low efficiency and difficulties in inputting unfamiliar symbols. To improve the efficiency of symbol input, this paper proposes a framework of the dynamic keyboard module with hierarchical mathematical symbol recommendation, which is based on the exercise-symbol patterns. Then a dynamic keyboard is designed to generate hierarchical mathematical symbols for multi-subject e-Learning systems, and the dynamic keyboard can improve the efficiency of symbol input. Finally, the proposed framework was evaluated on the learning system for Discrete mathematics and Statistics students. The experiment results demonstrate the effectiveness of our approach for symbol input.","PeriodicalId":183709,"journal":{"name":"2022 International Conference on Intelligent Education and Intelligent Research (IEIR)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122951502","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-18DOI: 10.1109/IEIR56323.2022.10050068
Tianran Li, Sheng Huang, Yuxin Ding, Mingxuan Cai
To meet the needs of training new engineering talents in electrical engineering, the development of a virtual simulation experiment platform for intelligent substations can solve the difficulties in traditional substation experimental teaching, and realize the resource integration and interactive empowerment between “Industry” and “ Education”. It can achieve the organic unity of students’ engineering practice ability and knowledge innovation ability. Based on this platform, the experimental teaching operation mechanism of “university-enterprise cooperation & equal emphasis on learning and research” is constructed to provide a good paradigm for integrating the superior resources of universities and enterprises to jointly carry out the talent cultivation of industry-education integration.
{"title":"Development of a Virtual Simulation Experiment Platform for Intelligent Substation to Promote the Integration between Industry and Education","authors":"Tianran Li, Sheng Huang, Yuxin Ding, Mingxuan Cai","doi":"10.1109/IEIR56323.2022.10050068","DOIUrl":"https://doi.org/10.1109/IEIR56323.2022.10050068","url":null,"abstract":"To meet the needs of training new engineering talents in electrical engineering, the development of a virtual simulation experiment platform for intelligent substations can solve the difficulties in traditional substation experimental teaching, and realize the resource integration and interactive empowerment between “Industry” and “ Education”. It can achieve the organic unity of students’ engineering practice ability and knowledge innovation ability. Based on this platform, the experimental teaching operation mechanism of “university-enterprise cooperation & equal emphasis on learning and research” is constructed to provide a good paradigm for integrating the superior resources of universities and enterprises to jointly carry out the talent cultivation of industry-education integration.","PeriodicalId":183709,"journal":{"name":"2022 International Conference on Intelligent Education and Intelligent Research (IEIR)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126578795","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-18DOI: 10.1109/IEIR56323.2022.10050060
Lu Xu, Daojian Zeng, Jianhua Dai, Lin Gui
A fundamental aspect of peer review is the as-signment of reviewers. With the help of artificial intelligence, assigning reviewers can save time and effort and even achieve better results. The purpose of this paper is to explore how to assign reviewers to a paper based on matching multiple aspects of expertise. So that the assigned reviewer group covers all the aspects of a paper in a complementary manner, rather than covering the expertise only in the major research field of a paper. We extract research domain sets of the papers by prompt tuning. And calculate the research domain coverage score and TMPS score based on the review candidates and the pending papers. Then, we utilize a greedy round algorithm to establish the assigned reviewer groups for each paper. Finally, the reviewer groups will undergo a discrete check for conflicts of interest to validate the ultimate results. Experiments demonstrate that the proposed method considers the coverage of the research domain adequately. Furthermore, it arranges a proper selection order of reviewers for papers.
{"title":"Combining Coverage with TMPS for Reviewer Assignment","authors":"Lu Xu, Daojian Zeng, Jianhua Dai, Lin Gui","doi":"10.1109/IEIR56323.2022.10050060","DOIUrl":"https://doi.org/10.1109/IEIR56323.2022.10050060","url":null,"abstract":"A fundamental aspect of peer review is the as-signment of reviewers. With the help of artificial intelligence, assigning reviewers can save time and effort and even achieve better results. The purpose of this paper is to explore how to assign reviewers to a paper based on matching multiple aspects of expertise. So that the assigned reviewer group covers all the aspects of a paper in a complementary manner, rather than covering the expertise only in the major research field of a paper. We extract research domain sets of the papers by prompt tuning. And calculate the research domain coverage score and TMPS score based on the review candidates and the pending papers. Then, we utilize a greedy round algorithm to establish the assigned reviewer groups for each paper. Finally, the reviewer groups will undergo a discrete check for conflicts of interest to validate the ultimate results. Experiments demonstrate that the proposed method considers the coverage of the research domain adequately. Furthermore, it arranges a proper selection order of reviewers for papers.","PeriodicalId":183709,"journal":{"name":"2022 International Conference on Intelligent Education and Intelligent Research (IEIR)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125015834","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-18DOI: 10.1109/IEIR56323.2022.10050056
Kai Li, Lei Niu, Yang Yang, Yuchen Wang
China’s higher education level is rising year by year, the traditional method of allocating “One seat per person” cannot cope with the growth in the number of students in universities. Existing approaches focus more on space utilization and less on the students’ feelings. But in fact, students are more willing to go to the lab and are more productive if they have a satisfactory lab-seat. Therefore, new and more effective methods are needed. This paper uses multi-agent negotiation method to solve the problem. Students and laboratory administrator are independent agents and the negotiations between agents determine the final allocation. Both parties adjust their offer during the negotiation process using a concession strategy based on time constraints and result in a max overall utility finally.
{"title":"An Approach to Optimize Lab-Seat Allocation Problem Based on Multi-Agent Negotiation","authors":"Kai Li, Lei Niu, Yang Yang, Yuchen Wang","doi":"10.1109/IEIR56323.2022.10050056","DOIUrl":"https://doi.org/10.1109/IEIR56323.2022.10050056","url":null,"abstract":"China’s higher education level is rising year by year, the traditional method of allocating “One seat per person” cannot cope with the growth in the number of students in universities. Existing approaches focus more on space utilization and less on the students’ feelings. But in fact, students are more willing to go to the lab and are more productive if they have a satisfactory lab-seat. Therefore, new and more effective methods are needed. This paper uses multi-agent negotiation method to solve the problem. Students and laboratory administrator are independent agents and the negotiations between agents determine the final allocation. Both parties adjust their offer during the negotiation process using a concession strategy based on time constraints and result in a max overall utility finally.","PeriodicalId":183709,"journal":{"name":"2022 International Conference on Intelligent Education and Intelligent Research (IEIR)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132270173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：