作者： Chen, Zengzhao;Li, Jiawen;Liu, Hai;Wang, Xuyang;Wang, Hu;...

期刊： Expert Systems with Applications,2023年214:118943 ISSN：0957-4174

通讯作者： Chen, Zengzhao(zzchen@ccnu.edu.cn)

作者机构： [Wang, Hu; Chen, Zengzhao; Li, Jiawen; Liu, Hai; Zheng, Qiuyu] Cent China Normal Univ, Fac Artificial Intelligence Educ, Wuhan 430079, Peoples R China.;[Li, Jiawen; Zheng, Qiuyu] Cent China Normal Univ, Natl Engn Lab Educ Big Data, Wuhan 430079, Peoples R China.;[Wang, Hu; Chen, Zengzhao; Liu, Hai] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.;[Wang, Xuyang] Aviat Ind Corp, Luoyang Inst Electroopt Equipment, Luoyang 471023, Henan, Peoples R China.

通讯机构： [Zengzhao Chen] F;Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan 430079, China<&wdkj&>National Engineering Research Center for E-Learning, Central China Normal University, Wuhan 430079, China

关键词： Connection attention mechanism;Features fusion;Frame-level features;Speech emotion recognition;Utterance-level features

摘要： Speech emotion recognition (SER) has become a crucial topic in the field of human–computer interactions. Feature representation plays an important role in SER, but there are still many challenges in feature representation such as the inability to predict which features are most effective for SER and the cultural differences in emotion expression. Most previous studies use a single type of feature for the recognition task or conduct early fusion of features. However, a single type of feature cannot well reflect the emotions of speech signals. Also, different features contain different information, direct fusion cannot integrate the advantages of different features. To overcome these challenges, this paper proposes a parallel network for multi-scale SER based on a connection attention mechanism (AMSNet). AMSNet fuses fine-grained frame-level manual features with coarse-grained utterance-level deep features. Meanwhile, it adopts different speech emotion feature extraction modules according to the temporal and spatial features of speech signals, which enriches features and improves feature characterization. The network consists of a frame-level representation learning module (FRLM) based on the time structure and an utterance-level representation learning module (URLM) based on the global structure. Besides, improved attention-based long short-term memory (LSTM) is introduced into FRLM to focus on the frames that contribute more to the final emotion recognition result. In URLM, a convolutional neural network with the squeeze-and-excitation block (SCNN) is introduced to extract deep features. In addition, the connection attention mechanism is proposed for feature fusion, which applies different weights to different features. Extensive experiments are conducted on the IEMOCAP and EmoDB datasets, and the results demonstrate the effectiveness and performance superiority of AMSNet. Our code will be publicly available at https://elksslcd79b4207c66ae6affb42465c239896eelksslengineer.csmar666.98tsg.com:4443/capsule/8636967/tree/v1. © 2022 Elsevier Ltd

语种： 英文

作者： Zhang, Hao;Min, Yuandong;Liu, Sanya;Tong, Hang;Li, Yaopeng

作者机构： [Zhang, H; Tong, Hang; Liu, Sanya; Li, Yaopeng; Zhang, Hao; Min, Yuandong] Cent China Normal Univ, Fac Artificial Intelligence Educ, Natl Engn Res Ctr Learning, Wuhan 430079, Peoples R China.;[Zhang, H; Tong, Hang; Liu, Sanya; Li, Yaopeng; Zhang, Hao; Min, Yuandong] Cent China Normal Univ, Fac Artificial Intelligence Educ, Natl Engn Lab Educ Big Data, Wuhan 430079, Peoples R China.

会议名称： IEEE International Performance, Computing, and Communications Conference (IPCCC)

会议时间： NOV 11-13, 2022

会议地点： Austin, TX

会议主办单位： [Zhang, Hao;Min, Yuandong;Liu, Sanya;Tong, Hang;Li, Yaopeng] Cent China Normal Univ, Fac Artificial Intelligence Educ, Natl Engn Res Ctr Learning, Wuhan 430079, Peoples R China.^[Zhang, Hao;Min, Yuandong;Liu, Sanya;Tong, Hang;Li, Yaopeng] Cent China Normal Univ, Fac Artificial Intelligence Educ, Natl Engn Lab Educ Big Data, Wuhan 430079, Peoples R China.

会议论文集名称： IEEE International Performance Computing and Communications Conference (IPCCC)

关键词： Modbus;DoS;Deep Learning;Fine-grained Classification

摘要： With the rapid development of technology, the scale of traffics in industrial control networks is increasing day by day. More malicious traffics brought terrible impacts on industrial areas. Modbus plays a momentous role in the communications of Industrial Control Systems (ICS), but it's vulnerable to Denial of Service attacks(DoS). Traditional methods cannot perform well on fine-grained detection tasks which could contribute to locating targets of DoS and preventing the destruction. Considering the temporal locality and high dimension of malicious traffic, we proposed a Neural Network architecture named MODLSTM, which consists of three parts: input preprocessing, feature recoding, and traffic classification. By virtue of the design, MODLSTM can perform high-precision identification and fine-grained classification of DOS attacks in the Modbus/TCP-based system. To test our model's performances, we conducted experiments on our traffic dataset collected from the industrial control network, and the models achieved excellent performances in comparison with previous work(accuracy increased by 0.74%). The results show that our proposed method has satisfactory abilities to detect DoS attacks related to Modbus, it could help to build a reliable firewall to address the DoS traffic in industrial environments © 2022 IEEE.

语种： 英文

作者： Zhang, Wei;Qu, Kaiyuan;Han, Yahui;Tan, Longan

作者机构： [Zhang, Wei] Central China Normal University, National Engineering Research Center for E-Learning, China;[Qu, Kaiyuan; Han, Yahui; Tan, Longan] Central China Normal University, China

会议名称： 6th International Conference on Innovation in Artificial Intelligence, ICIAI 2022

会议时间： March 4, 2022 - March 6, 2022

会议地点： Virtual, Online, China

摘要： Online education is playing a more and more important role in today's education. The key link of online education is to model students' knowledge mastery according to their historical behaviors, so as to obtain the knowledge tracing represented by students' current knowledge state. Previous Transformer-based knowledge tracing models have disadvantages such as inefficient model computation and redundant information on the one hand. On the other hand, the traditional knowledge tracing model cannot solve the problem of imbalanced positive and negative samples in the data well. In order to better model the current knowledge state of students, this paper proposes a knowledge tracing model based on the collaborative multi-head attention mechanism. The model uses a collaborative multi-head attention mechanism to solve the information redundancy problem in the previous Transformer-based knowledge tracing model, and improves the computational efficiency and performance of the model. The model also introduces a focal loss function, which not only solves the problem of imbalanced question labeling divisions in knowledge tracing but also improves the differentiation of difficulty level among the questions and enhances the accuracy of model prediction. The experimental results on three public experimental datasets show that the knowledge tracing model based on the collaborative multi-head attention mechanism proposed in this paper outperforms other recent knowledge tracing models in terms of evaluation metric AUC and also has better performance in predicting students' responses. © 2022 ACM.

语种： 英文

作者： Geng, Jing;Zhu, Junya;Yang, Huali;Hu, Shengze;Huang, Tao

作者机构： [Geng, Jing; Hu, Shengze; Huang, Tao] National Engineering Research Center of Educational Big Data, Central China Normal University, Wuhan;430079, China;[Zhu, Junya] Central China Normal University, Wuhan;[Yang, Huali] National Engineering Research Center for E-Learning, Central China Normal University, Wuhan;[Geng, Jing; Zhu, Junya; Yang, Huali; Hu, Shengze; Huang, Tao] 430079, China

会议名称： 7th International Conference on Distance Education and Learning, ICDEL 2022

会议时间： May 20, 2022 - May 23, 2022

会议地点： Virtual, Online, China

摘要： The domain knowledge graph is the key to help realize personalized education as the basic program for realizing intelligent diagnosis. As the foundation of science and engineering studies such as mathematics, physics and chemistry, operation is also one of the important qualities of the 21st century's core literacy of mathematics. It is particularly important to construct domain graph of operation and use it to carry out diagnostic teaching. To this end, in view of the characteristics of elementary school mathematics operations, the domain graph of elementary school mathematics operation is constructed with knowledge as the carrier, cognitive level as the goal, and ability as the comprehensive performance, so as to realize the fine-grained of operational literacy. With the aid of the 'learning big data Platform'and the design of evaluation tools based on the domain graph of operation, a large-scale diagnosis and evaluation experiment was carried out among fifth-grade students in a primary school in Wuhan, and the weak skills of learners in the field of primary school mathematics were discovered by using cognitive diagnostic model to make precise remedy for their weak points. © 2022 ACM.

语种： 英文

作者： Zhang, Junsong;Zhu, Shaoqiang;Liu, Kunxiang;Liu, Xiaoyu

期刊： Computer Animation and Virtual Worlds,2022年33(1):e2032- ISSN：1546-4261

通讯作者： Zhang, Junsong(jszhang@outlook.com)

作者机构： [Liu, Xiaoyu; Liu, Kunxiang; Zhang, Junsong; Zhu, Shaoqiang] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.;[Zhang, Junsong] Xiamen Univ, Dept Artificial Intelligence, Mind Art & Computat Grp, Xiamen 361005, Fujian, Peoples R China.

通讯机构： [Junsong Zhang; Junsong Zhang Junsong Zhang Junsong Zhang] N;National Engineering Research Center for E-learning, Central China Normal University, Wuhan, China<&wdkj&>Mind, Art and Computation Group, Department of Artificial Intelligence, Xiamen University, Xiamen, Fujian 361005, P.R, China

关键词： colorization;generative adversarial networks;painting;sketch

摘要： Inspired by the creating process of human paintings, we propose a novel adversarial architecture for multiple sketch colorization which is a scribble-based, automatic, and exemplar-based colorization method. The proposed framework has two stages, namely, imitating stage and shading stage. In the imitating stage, to address the challenge of lack of texture in the sketch, we train a grayscale generation network to accomplish a mapping task, namely, generating a grayscale map with textured, grayscale, boundary information from the input sparse sketch. In the shading stage, the model can accurately colorize the objects in the gray image generated in the previous stage, and generate high-quality colorized images. With the proposed model trained on our database, the experimental results show that our method can generate vivid colorized images and achieve a better performance than previous methods evaluated by FID metric. © 2021 John Wiley & Sons, Ltd.

语种： 英文

作者： Sun, Jianwen;Zou, Rui;Liang, Ruxia;Gao, Lu;Liu, Sannyuya;...

期刊： Expert Systems with Applications,2022年207:117680 ISSN：0957-4174

通讯作者： Liu, Sannyuya(lsy5918@mail.ccnu.edu.cn)

作者机构： [Liu, Sannyuya; Zou, Rui; Li, Qing; Liang, Ruxia; Sun, Jianwen] Cent China Normal Univ, Natl Engn Lab Educ Big Data, Wuhan 430079, Peoples R China.;[Liu, Sannyuya; Gao, Lu] Cent China Normal Univ, Natl Engn Res Ctr Elearning, Wuhan 430079, Peoples R China.;[Liu, Sannyuya; Zou, Rui; Gao, Lu; Li, Qing; Liang, Ruxia; Sun, Jianwen] Cent China Normal Univ, Fac Artificial Intelligence Educ, Wuhan 430079, Peoples R China.;[Zhang, Kai] Yangtze Univ, Sch Comp Sci, Jingzhou 434025, Peoples R China.;[Jiang, Lulu] Nanhai Expt Sch, Foshan 528299, Peoples R China.

通讯机构： [Sannyuya Liu; Qing Li] N;National Engineering Laboratory for Educational Big Data, Central China Normal University, Wuhan, 430079, China<&wdkj&>Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan, 430079, China<&wdkj&>National Engineering Laboratory for Educational Big Data, Central China Normal University, Wuhan, 430079, China<&wdkj&>National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, 430079, China<&wdkj&>Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan, 430079, China

关键词： Deep neural network;Knowledge Tracing;Learning interactions;User modeling

摘要： Knowledge Tracing (KT) aims to continuously estimate students’ evolving knowledge state during their learning process, which has attracted much research attention due to its potential for delivering personalized and optimal experiences to students in intelligent learning systems. The learning process is essentially the pairwise interactions of Students, Concepts, and Questions (S–C, S–Q, C–Q for short). Modeling all these interactions will improve the performance of KT. However, existing KT methods hardly exploit all the interactions in a single model. Specifically, Bayesian Knowledge Tracing (BKT) and most of its variants neglect C–Q; Deep Knowledge Tracing (DKT) and other deep neural network approaches mostly neglect S–Q and C–Q. We propose the Ensemble Knowledge Tracing (EnKT), which models all three types of interactions. The base model of EnKT is a hybrid of BKT and DKT. We also present an ensemble algorithm Recurrent Boosting (RB), which extends AdaBoost to deal with KT sequential data. Inspired by BKT, EnKT represents S–C and S–Q using learning and performance parameters, respectively. Besides, EnKT defines C–Q as the correlation complexity among the concepts involved in a question. Experiments show EnKT significantly outperforms state-of-the-art methods (by up to 6% in AUC in some cases) on four real-world benchmark datasets and illustrate better interpretability by several typical case studies. © 2022 Elsevier Ltd

语种： 英文

作者： Zeng, Zhi-zhong;Lue, Zhi-peng;Yu, Xin-guo;Wu, Qing-hua;Wang, Yang;...

期刊： Expert Systems with Applications,2022年209:118077 ISSN：0957-4174

通讯作者： Lue, ZP

作者机构： [Zeng, Zhi-zhong; Yu, Xin-guo; Zhou, Zhou] Cent China Normal Univ, Fac Artificial Intelligence Educ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.;[Lue, Zhi-peng] Huazhong Univ Sci & Technol, Sch Comp Sci & Technol, Wuhan 430074, Peoples R China.;[Wu, Qing-hua] Huazhong Univ Sci & Technol, Sch Management, Wuhan 430074, Peoples R China.;[Wang, Yang] Northwestern Polytech Univ, Sch Management, Xian 710072, Peoples R China.

通讯机构： [Lue, ZP ] H;Huazhong Univ Sci & Technol, Sch Comp Sci & Technol, Wuhan 430074, Peoples R China.

关键词： Combinatory optimization;EDA algorithms;Max-cut;Memetic algorithm;Metaheuristics;Path relinking

摘要： Max-cut is one of the most classic NP-hard combinatorial optimization problems. The symmetry nature of it leads to special difficulty in extracting meaningful configuration information for learning; none of the state-of-the-art algorithms has employed any learning operators. This paper proposes an original learning method for max-cut, namely post-flip edge-state learning (PF-ESL). Different from previous algorithms, PF-ESL regards edge-states (cut or not cut) rather than vertex-positions as the critical information of a configuration, and extracts their statistics over a population for learning. It is based on following observations. 1) Edges are the only factors considered by the objective function. 2) Edge-states keep invariant when rotating a local configuration to its symmetry position, but vertex-positions do not. These suggest that edge-states contain more meaningful information about a configuration than vertex-positions do. It is impossible to set the state of an edge without influencing some other edges’ states due to their dependencies. Therefore, instead of setting edge-states directly, PF-ESL samples the flips on vertices. Flips on vertices are sampled according to their capacities in increasing the similarity on edge-states between the given solution and a population. PF-ESL is employed in an EDA (Estimation of Distribution Algorithm) perturbation operator and a path-relinking operator. Experimental results show that our algorithm is competitive, and show that edge-state learning is value-added for both the two operators. The main contributions of this paper are as follows. Firstly, previous state-of-the-art evolutionary algorithms for max-cut focus on vertex positions in their evolutionary operation, this paper proposes a new and more reasonable perspective suggesting that edge-states are the critical information of divided graphs rather than vertex positions, and introduces a novel method to measure and utilize their similarities based on it. Such a perspective is fundamental to learning based algorithms design for max-cut and other graph partitioning problems, and can shed lights on future researches. Furthermore, since max-cut is one of the most classic and fundamental NP hard problems, many real-world problems involve dividing graph data into different parts to optimize certain functions, this new perspective may inspire related or similar problems. Secondly, besides the original edge-states based perspective, and the post-flip edge-states learning (PFESL) operator based on it, our memetic algorithm also incorporates a novel evolutionary framework which alternates between EDA based Iterated Tabu search (ITS) and path relinking based genetic algorithm. Finally, the proposed algorithm provides competitive results on two mostly used benchmark sets and improves the best-known results of 6 most challenging instances. © 2022

语种： 英文

作者： Yang, Juan*;Du, Xu;Hung, Jui-Long;Tu, Chih-Hsiung

期刊： DATA TECHNOLOGIES AND APPLICATIONS,2022年56(2):303-326 ISSN：2514-9288

通讯作者： Yang, Juan

作者机构： [Yang, Juan] Wuhan Univ Sci & Technol, Sch Comp Sci & Technol, Wuhan, Peoples R China.;[Yang, Juan; Du, Xu] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.;[Hung, Jui-Long] Boise State Univ, Dept Educ Technol, Boise, ID 83725 USA.;[Tu, Chih-Hsiung] No Arizona Univ, Dept Educ Specialties, Flagstaff, AZ 86011 USA.

通讯机构： [Yang, Juan] W;Wuhan Univ Sci & Technol, Sch Comp Sci & Technol, Wuhan, Peoples R China.

关键词： Online discussion;Critical thinking;Text mining;Multi-feature fusion;Predictive modeling;Instructional decision-making

摘要： Purpose: Critical thinking is considered important in psychological science because it enables students to make effective decisions and optimizes their performance. Aiming at the challenges and issues of understanding the student's critical thinking, the objective of this study is to analyze online discussion data through an advanced multi-feature fusion modeling (MFFM) approach for automatically and accurately understanding the student's critical thinking levels. Design/methodology/approach: An advanced MFFM approach is proposed in this study. Specifically, with considering the time-series characteristic and the high correlations between adjacent words in discussion contents, the long short-term memory–convolutional neural network (LSTM-CNN) architecture is proposed to extract deep semantic features, and then these semantic features are combined with linguistic and psychological knowledge generated by the LIWC2015 tool as the inputs of full-connected layers to automatically and accurately predict students' critical thinking levels that are hidden in online discussion data. Findings: A series of experiments with 94 students' 7,691 posts were conducted to verify the effectiveness of the proposed approach. The experimental results show that the proposed MFFM approach that combines two types of textual features outperforms baseline methods, and the semantic-based padding can further improve the prediction performance of MFFM. It can achieve 0.8205 overall accuracy and 0.6172 F1 score for the “high” category on the validation dataset. Furthermore, it is found that the semantic features extracted by LSTM-CNN are more powerful for identifying self-introduction or off-topic discussions, while the linguistic, as well as psychological features, can better distinguish the discussion posts with the highest critical thinking level. Originality/value: With the support of the proposed MFFM approach, online teachers can conveniently and effectively understand the interaction quality of online discussions, which can support instructional decision-making to better promote the student's knowledge construction process and improve learning performance. © 2021, Emerald Publishing Limited.

语种： 英文

作者： Song, Ting;Chen, Mao;Xu, Yulong;Wang, Dong;Song, Xuekun;...

期刊： Applied Soft Computing,2021年110:107624 ISSN：1568-4946

通讯作者： Chen, Mao(chenmao@mail.ccnu.edu.cn)

作者机构： [Song, Ting; Xu, Yulong; Song, Xuekun] School of Information Technology, Henan University of Chinese Medicine, Zhengzhou;450008, China;[Chen, Mao; Tang, Xiangyang] National Engineering Research Center for E-learning, Central China Normal University, Wuhan;430079, China;[Wang, Dong] School of Information and Management Science, Henan Agricultural University, Zhengzhou

通讯机构： [Mao Chen] N;National Engineering Research Center for E-learning, Central China Normal University, Wuhan, 430079, China

关键词： Course timetabling;Hybrid meta-heuristic;Multi-neighborhood local search;Simulated annealing

摘要： This paper proposes a novel competition-guided multi-neighborhood local search (CMLS) algorithm for solving the curriculum-based course timetabling problem. In comparison with the classical metaheuristic methods in the literature, the proposed algorithm includes three main contributions. Firstly, a new way of combining multiple neighborhoods is presented, according to which, only one neighborhood is selected at each iteration to make a trade-off between large search space and high computational efficiency. Secondly, two heuristic rules are proposed to determine the probabilities of selecting the neighborhood. Thirdly, a competition-based restart strategy is proposed, i.e., two SA-based multi-neighborhood local search procedures are implemented during the search process, and the elite one is selected from the two results obtained by the two procedures as the initial solution for the next round of search. The proposed algorithm is evaluated on the well-known benchmark instances, and the computational results show that the proposed algorithm is highly competitive compared with 6 state-of-the-art algorithms in the literature. Analysis of the essential ingredients of the proposed algorithm is also presented. © 2021 Elsevier B.V.

语种： 英文

作者： 李旻;何婷婷

期刊： 电子与信息学报,2021年43(4):948-955 ISSN：1009-5896

通讯作者： Li, Min(limin_ha139@139.com)

作者机构： [李旻; 何婷婷] National Engineering Research Center for E-Learning (Central China Normal University), Wuhan;430079, China;Computer and Information Engineering College, Henan University, Kaifeng;475001, China;[李旻] 430079, China<&wdkj&>Computer and Information Engineering College, Henan University, Kaifeng

通讯机构： [Li, M.] N;National Engineering Research Center for E-Learning (Central China Normal University)China

关键词： 初始中心生成;三角矩阵映射;随机整数;高维大数据聚类;线性算法

摘要： Bisecting K-means算法通过使用一组初始中心对分割簇,得到多个二分聚类结果,然后从中选优以减轻局部最优收敛问题对算法性能的不良影响。然而,现有的随机采样初始中心对生成方法存在效率低、稳定性差、缺失值等不同问题,难以胜任大数据聚类场景。针对这些问题,该文首先创建出了初始中心对组合三角阵和初始中心对编号三角阵,然后通过建立两矩阵中元素及元素位置间的若干映射,从而实现了一种从随机整数集合中生成二分聚类初始中心对的线性复杂度算法。理论分析与实验结果均表明,该方法的时间效率及效率稳定性均明显优于常用的随机采样方法,特别适用于高维大数据聚类场景。

语种： 中文

作者： Chen, Wei;Cheng, Hercy N. H.

作者机构： [Chen, Wei] National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, Hubei, China;[Cheng, Hercy N. H.] National Engineering Laboratory for Educational Big Data, Central China Normal University, Wuhan, Hubei, China

会议名称： 8th International Conference on Information and Education Technology, ICIET 2020

会议时间： March 28, 2020 - March 30, 2020

会议地点： Okayama, Japan

摘要： Previous studies have shown that learners' self-regulated learning in blended learning is closely related to their learning performance. However, it is unclear how self-regulated learners demonstrate their behaviors in blended learning environments. In this study, an academic reading and writing system was taken as a tool to collect graduate students' learning behaviors. The participants were the first-year graduate students, who took a blended course. In the course, they were required to read literature, do in/post-reading activities, take assessment and write essays in the system before classes every week. In order to further understand the behavior patterns of self-regulated graduate students, the participants were divided as high and low self-regulated learning group. The results showed that although both groups used similar times of system functions, they demonstrated different behavior patterns in terms of lag sequential analysis. Furthermore, the high self-regulated learners tended to look back at what they had done, and flexibly adjust their actions of reading and writing papers. On the contrary, instead of paper writing, the low self-regulated learners might treat tests as their goals and demonstrate simpler behavior patterns. © 2020 ACM.

语种： 英文

作者： Xu, Ruyi;Chen, Jingying*;Han, Jiaxu;Tan, Lei;Xu, Luhui

期刊： Computing,2020年102(3):765-780 ISSN：0010-485X

通讯作者： Chen, Jingying

作者机构： [Xu, Luhui; Xu, Ruyi; Tan, Lei; Chen, Jingying; Han, Jiaxu] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.;[Xu, Luhui; Xu, Ruyi; Tan, Lei; Chen, Jingying; Han, Jiaxu] Cent China Normal Univ, Natl Engn Lab Educ Big Data, Wuhan, Peoples R China.

通讯机构： [Chen, Jingying] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.;Cent China Normal Univ, Natl Engn Lab Educ Big Data, Wuhan, Peoples R China.

关键词： Learning cognitive state analysis;Multi-task learning;Head pose estimation;Facial expression recognition;Expression intensity evaluation

摘要： The boom of big data in education has provided an unrivalled opportunity for educators to evaluate the learners’ cognitive state. However, most existing cognitive state analysis methods focus on attention, ignoring the roles of emotion in human learning. Therefore, this study proposes an emotion-sensitive learning cognitive state analysis framework, which automatically estimates the learners’ attention based on head pose and emotion based on facial expression in a non-invasive way. The proposed framework includes two modules. In the first module, a multi-task learning implementation with a cascaded convolutional neural network (CNN) is presented for face detection, landmark location, and head pose estimation simultaneously. The located landmarks are used to align the faces as the preprocessing step for the facial expression analysis. The estimated head pose and landmarks are used to recognize the visual focus of attention of the learner. In the second module, an expression intensity ranking CNN is proposed to recognize the facial expression and evaluate its intensity using ordinal information of the sequences. Then, the learners’ emotions are estimated based on the facial expression. Experimental results show that this method can estimate a learner’s attention and emotion with correctness rates of 79.5% and 88.6%, respectively. The results obtained suggest that the method has strong potential as an alternative method for analyzing emotion-sensitive learning cognitive state. © 2019, Springer-Verlag GmbH Austria, part of Springer Nature.

语种： 英文

作者： Xu, Shun;Zhu, Sha

期刊： Computers in the Schools,2020年37(4):292-309 ISSN：0738-0569

通讯作者： Zhu, Sha(zhusha@mail.ccnu.edu.cn)

作者机构： [Xu, Shun] College of Education, Huanggang Normal University, Huanggang, China;[Zhu, Sha] National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China

通讯机构： [Sha Zhu] N;National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China

关键词： Influencing factors;intention to adopt;K-12 teachers;mobile devices

摘要： Based on an extensive literature review, in this study we proposed a model of influencing factors that affect teachers’ intention to adopt mobile devices in teaching. An online survey questionnaire was developed to investigate K-12 teachers’ intention to adopt mobile devices in teaching and the influencing factors of that intention. Partial least squares (PLS) was employed to validate the proposed model and hypotheses using data collected from 132 primary and secondary school teachers. Results showed that teachers’ attitude and technology beliefs, and their self-efficacy regarding mobile-based teaching had significant positive impacts on their intention to adopt mobile devices in teaching. Meanwhile, teachers’ mobile device skills and mobile-based pedagogical knowledge strongly influenced their self-efficacy of mobile device-based teaching. Finally, the subject culture clash had a significant negative influence on teachers’ attitudes, technology beliefs, and self-efficacy toward mobile-based teaching. Based on these findings, we put forward a number of suggestions to promote teaching using mobile devices. © 2020 Taylor & Francis Group, LLC.

语种： 英文

作者： Pi, Zhongling;Xu, Ke;Liu, Caixia;Yang, Jiumin*（杨九民）

期刊： Computers & Education,2020年144:103713 ISSN：0360-1315

通讯作者： Yang, Jiumin（杨九民）

作者机构： [Yang, Jiumin; Xu, Ke; Pi, Zhongling] Cent China Normal Univ, Sch Educ Informat Technol, Wuhan 430079, Hubei, Peoples R China.;[Liu, Caixia] Cent China Normal Univ, Collaborat Innovat Ctr Informat Technol & Balance, Wuhan 430079, Hubei, Peoples R China.;[Yang, Jiumin] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Hubei, Peoples R China.;[Yang, Jiumin] Cent China Normal Univ, 152 Luoyu Rd, Wuhan 430079, Hubei, Peoples R China.

通讯机构： [Yang, Jiumin] C;Cent China Normal Univ, 152 Luoyu Rd, Wuhan 430079, Hubei, Peoples R China.

关键词： Distance education and;Multimedia/hypermedia systems;Pedagogical issues;Teaching/learning strategies;telelearning

摘要： The instructor's on-screen presence, rather than just voice, has rapidly become a popular feature in video lectures. Eye gaze and body orientation are core indicators of an instructor's attentional focus in classroom settings, but it is not well known how these factors influence learners' attention allocation and learning performance in video lectures with the on-screen presence of instructors presenting slides. This study tested the effects of the instructor's eye gaze and body orientation on attention and learning from a video lecture in a sample of 174 undergraduates. Specifically, the instructor's presence was manipulated in terms of eye gaze (direct, guided, or averted) and body orientation (frontal or lateral). Eye tracking data revealed that regardless of an instructor's body orientation, learners who viewed the video lectures with the instructor's guided gaze paid greater attention to the slides, and those who viewed the video lectures with the instructor's direct gaze paid greater attention to her face; paper-and-pencil assessments showed that learners who viewed the video lectures with guided gaze showed better retention and transfer. These results held regardless of body orientation, suggesting that an instructor's eye gaze has a stronger influence than body orientation on attention and learning from video lectures. The findings suggest that an instructor should not look directly at the camera continuously throughout the lecture, and should instead use guided gaze to draw learners' attention to the learning materials. © 2019

语种： 英文

作者： Chen, Mao（陈矛）;Tang, Xiangyang;Song, Ting;Wu, Chao;Liu, Sanya*;...

期刊： Computers & Operations Research,2020年123:105007 ISSN：0305-0548

通讯作者： Liu, Sanya

作者机构： [Chen, Mao; Peng, Xicheng; Tang, Xiangyang; Wu, Chao; Liu, Sanya] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.;[Song, Ting] Henan Univ Chinese Med, Sch Informat Technol, Zhengzhou 450008, Peoples R China.

通讯机构： [Liu, Sanya] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.

关键词： Controlled randomization;Tabu search;Threshold mechanism;University course timetabling problem

摘要： University Course Timetabling Problem (UCTP) is one of the most studied timetabling problems. In this work, the problem of finding a feasible solution for the UCTP, i.e., a solution that satisfies all hard constraints, is addressed. To cater for the algorithm design, the problem is firstly reformulated into a version where only one hard constraint needs to be considered in the minimization procedure. Then a novel Tabu search algorithm is proposed, which integrates the controlled randomization strategy and threshold mechanism into the original Tabu search framework. Experiments on a set of 60 well-known Lewis benchmark instances show that the proposed algorithm achieves competitive results compared with eight reference algorithms. In particular, when the stop condition is relaxed, the proposed algorithm can find feasible solutions for all the 60 instances, two of which are missed in previous study. © 2020 Elsevier Ltd

语种： 英文

作者： Yuan, Shuai;He, Tingting*（何婷婷）;Huang, Huan;Hou, Rui;Wang, Meng

期刊： 计算机、材料和连续体(英文),2020年65(1):817-833 ISSN：1546-2218

通讯作者： He, Tingting

作者机构： [Yuan, Shuai] Cent China Normal Univ, Natl Engn Res Ctr E Leaming, Wuhan 430079, Peoples R China.;[He, Tingting] Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.;[He, Tingting] Cent China Normal Univ, Informat Retrieval & Knowledge Management Res Lab, Wuhan 430079, Peoples R China.;[Huang, Huan] South Cent Univ Nationalities, Sch Educ, Wuhan 430074, Peoples R China.;[Hou, Rui] South Cent Univ Nationalities, Coll Comp Sci, Wuhan 430074, Peoples R China.

通讯机构： [He, Tingting] C;Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.;Cent China Normal Univ, Informat Retrieval & Knowledge Management Res Lab, Wuhan 430079, Peoples R China.

关键词： Automated essay scoring;Chinese essay;Convolutional neural network;Deep learning

摘要： Writing is an important part of language learning and is considered the best approach to demonstrate the comprehensive language skills of students. Manually grading student essays is a time-consuming task; however, it is necessary. An automated essay scoring system can not only greatly improve the efficiency of essay scoring, but also provide more objective score. Therefore, many researchers have been exploring automated essay scoring techniques and tools. However, the technique of scoring Chinese essays is still limited, and its accuracy needs to be enhanced further. To improve the accuracy of the scoring model for a Chinese essay, we propose an automated scoring approach based on a deep learning model and validate its effect by conducting two comparison experiments. The experimental results indicate that the accuracy of the proposed model is significantly higher than that of multiple linear regression (MLR), which was commonly used in the past. The three accuracy rates of the proposed model are comparable to those of the novice teacher. The root mean square error (RMSE) of the proposed model is slightly lower than that of the novice teacher, and the correlation coefficient of the proposed model is also significantly higher than that of the novice teacher. Besides, when the predicted scores are not very low or very high, the two predicted models are as good as a novice teacher. However, when the predicted score is very high or very low, the results should be treated with caution. © 2020 Tech Science Press. All rights reserved.

语种： 英文

作者： He, Bin;Yu, Xinguo（余新国）;Jian, Pengpeng;Zhang, Ting*

期刊： Applied Intelligence,2020年50(7):2293-2309 ISSN：0924-669X

通讯作者： Zhang, Ting

作者机构： [Yu, Xinguo; He, Bin; Zhang, Ting; Jian, Pengpeng] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.

通讯机构： [Zhang, Ting] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.

关键词： Problem solving;Relation acquisition;Syntax-semantics model;Schematics understanding;Unit-theorem inference

摘要： This paper addresses the challenging problem of developing the automatic algorithm for solving direct current circuit problem. Leveraging on the innovated methods it proposes a high-performance relation based algorithm, called RaDCC. The challenges of the problem lie in relation acquisition and relation inference presentation after adopting the newly-established relation principle of solving problems. A high-performance procedure is developed for the challenging task of relation acquisition by leveraging on three innovated methods. Three methods are an enhanced schematics understanding method that can understand complicated structures of schematics, an extended syntax-semantics model method and a unit-theorem inference method to acquire schematic relations, explicit text relations and implicit text relations, respectively. To address another challenging problem of readable solution generation an action-schema presentation method is proposed to convert relation inference actions into relation inference presentations. The experimental results show that the proposed algorithm is high-performance since it achieves an accuracy of over 83.2% for solving problems from textbooks and 70.6% for solving problems from examination papers on a dataset that contains 1012 direct current circuit problems collected from the authority sources, much higher than the performance of the baseline algorithm. © 2020, Springer Science+Business Media, LLC, part of Springer Nature.

语种： 英文

作者： Chen, Shaohui;Yang, Ningyu;Chen, Jiamin;Zheng, Qiuyu

作者机构： [Chen, Shaohui; Yang, Ningyu; Chen, Jiamin; Zheng, Qiuyu] National Engineering Research Center for E-Learning, Central China Normal University, Wuhan;430079, China;Zhejiang Lab, Hangzhou;310018, China;[Chen, Shaohui] 430079, China<&wdkj&>Zhejiang Lab, Hangzhou

会议名称： 4th International Conference on Innovation in Artificial Intelligence, ICIAI 2020

会议时间： May 8, 2020 - May 11, 2020

会议地点： Xiamen, China

摘要： In automatic solution for mathematical problem by machines, problem understanding is an indispensable prerequisite to answer correctly. In the current methods, problem understanding refers to obtaining equivalent representations of the problems, such as linear equations, polynomials, and so on. However, in the solution process, the problem equivalent representation does not guarantee semantic interoperability with the problem, and it is not easy to generate a human-like solution by backtracking the solution process. Therefore, creating a clear equivalent representation of the question is the direction of the automatic solution. Based on the WordEmbedding technology, this paper proposes a new method to convert the math problems of natural language descriptions into equivalent semantic vector representations that are easy to understand by computers, and to identify the types of problems based on deep learning. In this paper, we take the famous Chinese ancient math problem of 'chicken and rabbit in the same cage' as an example, and obtain a good recognition rate of 72%. © 2020 ACM.

语种： 英文

作者： Zhang, Hao;Xia, Yu;Huang, Tao;Li, Jia;Wang, HaiJin

作者机构： [Zhang, Hao; Xia, Yu; Huang, Tao; Li, Jia; Wang, HaiJin] National Engineering Research Center for E-Learning, National Engineering Laboratory for Educational Big Data, Central China Normal University, Wuhan, China

会议名称： 2020 Asia Service Sciences and Software Engineering Conference, ASSE 2020

会议时间： May 13, 2020 - May 15, 2020

会议地点： Nagoya, Japan

会议论文集名称： ASSE '20: Proceedings of the 2020 Asia Service Sciences and Software Engineering Conference

摘要： With the rise of blockchain technology, data sharing between organizations is often established in a distributed blockchain ledger that is decentralized and tamperproof and has a low trust cost. However, traditional blockchain technology does not adequately support the on-chain storage of massive data, and all the on-chain stored data are completely open and transparent to participants; consequently, it is impossible to meet the user's needs for privacy protection. In this study, we designed a scalable data access control method for blockchains; this method extends the storage forms of the blockchain to support the chaining and sharing of large files, ensures that the traceable data in the chaining process cannot be tampered with, and introduces the attribute authority mechanism in peer nodes to improve the reliability and efficiency of attribute authorization. To verify the correctness and security of the method, we built a complete prototype system based on the Hyperledger Fabric license chain and performed rigorous evaluations on the indicators of physical resource consumption and performance using the Hyperledger Caliper evaluation model. The results showed that the proposed method achieved a good balance in terms of performance, safety, and resource consumption indicators. © 2020 ACM.

语种： 英文

作者： Yang, Zongkai;Su, Zhu*;Liu, Sannyuya*;Liu, Zhi;Ke, Wenxiang;...

期刊： Expert Systems with Applications,2020年158:113519 ISSN：0957-4174

通讯作者： Su, Zhu;Liu, Sannyuya

作者机构： [Yang, Zongkai; Liu, Sannyuya; Su, Zhu; Liu, SYY; Liu, Zhi; Ke, Wenxiang; Zhao, Liang] Cent China Normal Univ, Natl Engn Lab Educ Big Data, Wuhan 430079, Peoples R China.;[Yang, Zongkai; Liu, Sannyuya] Cent China Noma Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.

通讯机构： [Su, Z; Liu, SYY] C;Cent China Normal Univ, Natl Engn Lab Educ Big Data, Wuhan 430079, Peoples R China.

关键词： Evolution feature;Behavior character;Friendship network;Percolation theory

摘要： Analyzing and mining students' behaviors and interactions from big data is an essential part of education data mining. Based on the data of campus smart cards, which include not only static demographic information but also dynamic behavioral data from more than 30000 anonymous students, in this paper, the evolution features of friendship and the relations between behavior characters and student interactions are investigated. On the one hand, four different evolving friendship networks are constructed by means of the friend ties proposed in this paper, which are extracted from monthly consumption records. In addition, the features of the giant connected components (GCCs) of friendship networks are analyzed via social network analysis (SNA) and percolation theory. On the other hand, two high-level behavior characters, orderliness and diligence, are adopted to analyze their associations with student interactions. Our experiment/empirical results indicate that the sizes of friendship networks have declined with time growth and both the small-world effect and power-law degree distribution are found in friendship networks. Second, the results of the assortativity coefficient of both orderliness and diligence verify that there are strong peer effects among students. Finally, the percolation analysis of orderliness on friendship networks shows that a phase transition exists, which is enlightening in that swarm intelligence can be realized by intervening the key students near the transition point. (C)2020 Elsevier Ltd. All rights reserved.

语种： 英文