Pub Date : 2021-09-24DOI: 10.1109/ICISCAE52414.2021.9590797
Shaosong Lin, Yong Yue, Xiaohui Zhu
Emotion recognition is a growing area of facial recognition, to detect the basic emotion state of a person and then operate further analysis. For practical applications, high speed and accuracy are required as an efficient and precise system. To this end, the paper proposes an effective emotion recognition system using a representative geometric feature mask for feature extraction and a CNN model for classification. Compared with traditional emotion recognition systems, which usually extract facial key features and then convert them into mathematical information variables by equations, the system implemented in this paper extracts necessary features in facial expression through landmarks, and operates a further extraction by a transformation that converts features into a pure geometric feature mask to represent a simplified human face. Then, the mask that can be used to express the human facial emotion with fewer noise features, is input into a deep learning training CNN (Convolutional Neural Network) model. The improvement of this work is that the system combines pure geometric method to extract facial features with CNN algorithm properties in image processing, where local connectivity and shared parameter properties were fully used in further geometric feature extraction. Finally, the system achieves high accuracy and low time costs with KDEF (Karolinska Directed Emotional Faces) and CK+ (Cohn-Kanade AU-Coded Expression Database).
{"title":"Emotion Recognition Using Representative Geometric Feature Mask Based on CNN","authors":"Shaosong Lin, Yong Yue, Xiaohui Zhu","doi":"10.1109/ICISCAE52414.2021.9590797","DOIUrl":"https://doi.org/10.1109/ICISCAE52414.2021.9590797","url":null,"abstract":"Emotion recognition is a growing area of facial recognition, to detect the basic emotion state of a person and then operate further analysis. For practical applications, high speed and accuracy are required as an efficient and precise system. To this end, the paper proposes an effective emotion recognition system using a representative geometric feature mask for feature extraction and a CNN model for classification. Compared with traditional emotion recognition systems, which usually extract facial key features and then convert them into mathematical information variables by equations, the system implemented in this paper extracts necessary features in facial expression through landmarks, and operates a further extraction by a transformation that converts features into a pure geometric feature mask to represent a simplified human face. Then, the mask that can be used to express the human facial emotion with fewer noise features, is input into a deep learning training CNN (Convolutional Neural Network) model. The improvement of this work is that the system combines pure geometric method to extract facial features with CNN algorithm properties in image processing, where local connectivity and shared parameter properties were fully used in further geometric feature extraction. Finally, the system achieves high accuracy and low time costs with KDEF (Karolinska Directed Emotional Faces) and CK+ (Cohn-Kanade AU-Coded Expression Database).","PeriodicalId":121049,"journal":{"name":"2021 IEEE 4th International Conference on Information Systems and Computer Aided Education (ICISCAE)","volume":"211 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124732497","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}
In this paper, we study the electricity price policy text title summarization problem. Comparing with conventional summarization tasks, title summarization of policy text has an extra characteristic. Policy texts always contain many professional keywords. In order to retain the main information in title summarization as much as possible, we propose keyword-fusion pointer-generator network with additional consideration of keywords of policy text. We incorporate keywords information from the original policy texts into our model by a new attention mechanism called keyword-fusion attention mechanism so that keywords can be generated in the title. What's more, our keyword-fusion pointer-generator network contains a more useful coverage vector using exponentially weighted averages method in order to solve the problem of repetition. Experimental results show that our model outperforms the other baselines.
{"title":"Keyword-fusion Pointer-Generator Network for Policy Text Title Summarization","authors":"Ziyin Gu, Li Chen, Qing-jin Zhu, Lingbo Li, Zelin Zhang, Xin Zhou","doi":"10.1109/ICISCAE52414.2021.9590673","DOIUrl":"https://doi.org/10.1109/ICISCAE52414.2021.9590673","url":null,"abstract":"In this paper, we study the electricity price policy text title summarization problem. Comparing with conventional summarization tasks, title summarization of policy text has an extra characteristic. Policy texts always contain many professional keywords. In order to retain the main information in title summarization as much as possible, we propose keyword-fusion pointer-generator network with additional consideration of keywords of policy text. We incorporate keywords information from the original policy texts into our model by a new attention mechanism called keyword-fusion attention mechanism so that keywords can be generated in the title. What's more, our keyword-fusion pointer-generator network contains a more useful coverage vector using exponentially weighted averages method in order to solve the problem of repetition. Experimental results show that our model outperforms the other baselines.","PeriodicalId":121049,"journal":{"name":"2021 IEEE 4th International Conference on Information Systems and Computer Aided Education (ICISCAE)","volume":"18 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120902163","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 : 2021-09-24DOI: 10.1109/ICISCAE52414.2021.9590713
Biao Mei
Appropriate affinity/similarity measures always play a critical role in data mining. The complex interactions among multiple features and personality of each individual object makes it still a challenging problem. Existing methods simply consider the relevance in a feature-pair manner, and they treat the features for each object equally without considering the personality. In this paper, we propose a hierarchical affinity learning method on categorical data with unsupervised personalized feature weighting, called HAL. HAL captures the interactions by exploring the affinities among objects, features and values, which carry intrinsic data characteristics, via hierarchical affinity learning to handle this complex data. The inferred affinities between objects and features can be treated as the personalized feature weights which is used to refine the initial affinity matrix. The learned affinities between objects obtained by reinforcement affinity learning can be exploited for clustering. Experimental results on 16 real world datasets with diverse characteristics from 6 different domains confirm the superiority of our method. Compared to the state-of-the-art measures, it averagely achieves 8.8% improvement in terms of F-score.
{"title":"Hierarchical Affinity Learning for Training Evaluation","authors":"Biao Mei","doi":"10.1109/ICISCAE52414.2021.9590713","DOIUrl":"https://doi.org/10.1109/ICISCAE52414.2021.9590713","url":null,"abstract":"Appropriate affinity/similarity measures always play a critical role in data mining. The complex interactions among multiple features and personality of each individual object makes it still a challenging problem. Existing methods simply consider the relevance in a feature-pair manner, and they treat the features for each object equally without considering the personality. In this paper, we propose a hierarchical affinity learning method on categorical data with unsupervised personalized feature weighting, called HAL. HAL captures the interactions by exploring the affinities among objects, features and values, which carry intrinsic data characteristics, via hierarchical affinity learning to handle this complex data. The inferred affinities between objects and features can be treated as the personalized feature weights which is used to refine the initial affinity matrix. The learned affinities between objects obtained by reinforcement affinity learning can be exploited for clustering. Experimental results on 16 real world datasets with diverse characteristics from 6 different domains confirm the superiority of our method. Compared to the state-of-the-art measures, it averagely achieves 8.8% improvement in terms of F-score.","PeriodicalId":121049,"journal":{"name":"2021 IEEE 4th International Conference on Information Systems and Computer Aided Education (ICISCAE)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121165448","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 : 2021-09-24DOI: 10.1109/ICISCAE52414.2021.9590642
Bingxin Du, Guoying Liu, Wenying Ge
In this paper, we design a two-branch deep learning framework to tackle the problem of self-supervised representation learning for Oracle Bone Inscriptions (OBIs). This problem is very complicated in that, unlike natural-photos, OBI images present more abstract content and suffer from different drawing styles, resulting in the failure of many existing self-supervised learning methods to describe them accurately. The core idea of our framework is that we design two OBI-specific pretext tasks, i.e. rotation and deformation. These two kinds of pretext tasks can provide strong supervision signals for OBI features learning. And we perform OBI recognition downstream task to evaluate our self-supervised learned features. Experimental results show that, under the same dataset, our proposed method outperforms jigsaw and matting based self-supervised learning methods.
{"title":"Deep Self-Supervised Learning for Oracle Bone Inscriptions Features Representation","authors":"Bingxin Du, Guoying Liu, Wenying Ge","doi":"10.1109/ICISCAE52414.2021.9590642","DOIUrl":"https://doi.org/10.1109/ICISCAE52414.2021.9590642","url":null,"abstract":"In this paper, we design a two-branch deep learning framework to tackle the problem of self-supervised representation learning for Oracle Bone Inscriptions (OBIs). This problem is very complicated in that, unlike natural-photos, OBI images present more abstract content and suffer from different drawing styles, resulting in the failure of many existing self-supervised learning methods to describe them accurately. The core idea of our framework is that we design two OBI-specific pretext tasks, i.e. rotation and deformation. These two kinds of pretext tasks can provide strong supervision signals for OBI features learning. And we perform OBI recognition downstream task to evaluate our self-supervised learned features. Experimental results show that, under the same dataset, our proposed method outperforms jigsaw and matting based self-supervised learning methods.","PeriodicalId":121049,"journal":{"name":"2021 IEEE 4th International Conference on Information Systems and Computer Aided Education (ICISCAE)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114536254","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 : 2021-09-24DOI: 10.1109/ICISCAE52414.2021.9590675
Haoshen Li, H. Xu, Ruihan Jiang, Linlin Zhao
Aiming at the situation that traditional PI controllers cannot flexibly change their parameters when the converter operating point changes, this paper designs a double-loop mode variable universe fuzzy PI controller based on the combination of variable universe thinking and fuzzy PI, and establishes The small signal model of the buck-boost converter is proposed, and the transfer function of the buck-boost converter is proposed. Finally, Matlab is used for simulation experiments. The experimental results show that, compared with the traditional PI controller, the dual-loop mode variable domain control method has better stability, higher control accuracy, and higher resistance under static operation, load resistance disturbance and input voltage disturbance. The interference ability and adaptive ability are strong, which can better improve the dynamic characteristics of the system and effectively improve the stability of the system.
{"title":"Research on Variable Universe Fuzzy Control of Double-Loop Mode Buck-Boost Converter Based on Matlab","authors":"Haoshen Li, H. Xu, Ruihan Jiang, Linlin Zhao","doi":"10.1109/ICISCAE52414.2021.9590675","DOIUrl":"https://doi.org/10.1109/ICISCAE52414.2021.9590675","url":null,"abstract":"Aiming at the situation that traditional PI controllers cannot flexibly change their parameters when the converter operating point changes, this paper designs a double-loop mode variable universe fuzzy PI controller based on the combination of variable universe thinking and fuzzy PI, and establishes The small signal model of the buck-boost converter is proposed, and the transfer function of the buck-boost converter is proposed. Finally, Matlab is used for simulation experiments. The experimental results show that, compared with the traditional PI controller, the dual-loop mode variable domain control method has better stability, higher control accuracy, and higher resistance under static operation, load resistance disturbance and input voltage disturbance. The interference ability and adaptive ability are strong, which can better improve the dynamic characteristics of the system and effectively improve the stability of the system.","PeriodicalId":121049,"journal":{"name":"2021 IEEE 4th International Conference on Information Systems and Computer Aided Education (ICISCAE)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133699452","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 : 2021-09-24DOI: 10.1109/ICISCAE52414.2021.9590674
Jingjun Gu, Jiadi Mo, P. Li, Yue Zhang, Wen Wang
Fog computing can effectively reduce latency and improve resource utilization by extending cloud services to the edge of the network. However, due to the wide variety of fog equipment and different computing capabilities, the theoretical knowledge and practical work related to fog computing task scheduling are insufficient. When scheduling tasks, factors such as cost of computing resources, power costs, and network cost were not considered comprehensively. Therefore, we propose a multi-objective fog computing task scheduling algorithm based on improved ant colony algorithm, which optimize the ant colony algorithm to make it more suitable for the characteristics of the fog node, use time and cost (TAC) to comprehensively consider the cost of the node, and introduce the critical factor in task allocation to improve the convergence speed of the algorithm. Different simulation experiments show that the efficiency of the improved ant colony algorithm is enhanced in processing time, cost, and load balance.
{"title":"A multi-objective fog computing task scheduling strategy based on ant colony algorithm","authors":"Jingjun Gu, Jiadi Mo, P. Li, Yue Zhang, Wen Wang","doi":"10.1109/ICISCAE52414.2021.9590674","DOIUrl":"https://doi.org/10.1109/ICISCAE52414.2021.9590674","url":null,"abstract":"Fog computing can effectively reduce latency and improve resource utilization by extending cloud services to the edge of the network. However, due to the wide variety of fog equipment and different computing capabilities, the theoretical knowledge and practical work related to fog computing task scheduling are insufficient. When scheduling tasks, factors such as cost of computing resources, power costs, and network cost were not considered comprehensively. Therefore, we propose a multi-objective fog computing task scheduling algorithm based on improved ant colony algorithm, which optimize the ant colony algorithm to make it more suitable for the characteristics of the fog node, use time and cost (TAC) to comprehensively consider the cost of the node, and introduce the critical factor in task allocation to improve the convergence speed of the algorithm. Different simulation experiments show that the efficiency of the improved ant colony algorithm is enhanced in processing time, cost, and load balance.","PeriodicalId":121049,"journal":{"name":"2021 IEEE 4th International Conference on Information Systems and Computer Aided Education (ICISCAE)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115443400","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 : 2021-09-24DOI: 10.1109/ICISCAE52414.2021.9590676
J. Dong, Qingpeng Han
The advantages of robot are obvious. It won't feel as tired as human beings. As long as the energy source is sufficient, it can work around the clock. The stability of robot work is stronger than that of human beings. It moves accurately according to the set procedures and has high repetition accuracy. However, the cost of using robot is far lower than that of users. Machine vision technology refers to the use of cameras and computers to simulate people's visual functions. It is widely used in the fields of electronic appliances, aerospace, automobiles and pharmaceuticals. It has the characteristics of non-contact measurement, high reliability and good flexibility, and has been widely used in industrial automation, visual navigation and virtual reality. This paper studies the industrial robot sorting system based on machine vision. The system mainly includes three modules: robot body and workpiece platform, machine vision and motion control; Finally, the key technologies applied in the sorting system are analyzed.
{"title":"Research on High Speed Robot Sorting System Based on Machine Vision Technology","authors":"J. Dong, Qingpeng Han","doi":"10.1109/ICISCAE52414.2021.9590676","DOIUrl":"https://doi.org/10.1109/ICISCAE52414.2021.9590676","url":null,"abstract":"The advantages of robot are obvious. It won't feel as tired as human beings. As long as the energy source is sufficient, it can work around the clock. The stability of robot work is stronger than that of human beings. It moves accurately according to the set procedures and has high repetition accuracy. However, the cost of using robot is far lower than that of users. Machine vision technology refers to the use of cameras and computers to simulate people's visual functions. It is widely used in the fields of electronic appliances, aerospace, automobiles and pharmaceuticals. It has the characteristics of non-contact measurement, high reliability and good flexibility, and has been widely used in industrial automation, visual navigation and virtual reality. This paper studies the industrial robot sorting system based on machine vision. The system mainly includes three modules: robot body and workpiece platform, machine vision and motion control; Finally, the key technologies applied in the sorting system are analyzed.","PeriodicalId":121049,"journal":{"name":"2021 IEEE 4th International Conference on Information Systems and Computer Aided Education (ICISCAE)","volume":"202 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121888177","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 : 2021-09-24DOI: 10.1109/ICISCAE52414.2021.9590678
Hailong Ge, Lifei Geng, Zhifei Yang, Bingyin Ren
In this paper, according to the electromagnetic environment of battlefield communication, the signal model of continuous phase frequency shift keying (CPFSK) is established, the anti-jamming performance is analyzed, and the influence of electromagnetic environment on CPFSK communication signal is studied by using physical communication equipment.
{"title":"Influence of electromagnetic environment on CPFSK communication signal","authors":"Hailong Ge, Lifei Geng, Zhifei Yang, Bingyin Ren","doi":"10.1109/ICISCAE52414.2021.9590678","DOIUrl":"https://doi.org/10.1109/ICISCAE52414.2021.9590678","url":null,"abstract":"In this paper, according to the electromagnetic environment of battlefield communication, the signal model of continuous phase frequency shift keying (CPFSK) is established, the anti-jamming performance is analyzed, and the influence of electromagnetic environment on CPFSK communication signal is studied by using physical communication equipment.","PeriodicalId":121049,"journal":{"name":"2021 IEEE 4th International Conference on Information Systems and Computer Aided Education (ICISCAE)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125935137","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 : 2021-09-24DOI: 10.1109/ICISCAE52414.2021.9590801
Longkai Zhang, Xingquan Teng, Xue-Zhen Ma, Ruize Wang
With the rapid development of science and technology, network communication technology has been widely used in various industries, but there are many communication security problems. In order to further improve the security of information data, related staff should use data encryption technology (DES) to strengthen security protection and ensure the integrity of information transmission. In the information age, information can help and benefit groups or individuals. Similarly, information can also be used to threaten and destroy them. We often need a measure to protect our data from being seen or destroyed by people with ulterior motives. In this paper, combining the principle and thought of genetic algorithm (GA), DES is studied in computer network communication security, and its application in computer communication network security is discussed.
{"title":"Research on Data Encryption Technology in Computer Network Communication Security Based on Genetic Algorithms","authors":"Longkai Zhang, Xingquan Teng, Xue-Zhen Ma, Ruize Wang","doi":"10.1109/ICISCAE52414.2021.9590801","DOIUrl":"https://doi.org/10.1109/ICISCAE52414.2021.9590801","url":null,"abstract":"With the rapid development of science and technology, network communication technology has been widely used in various industries, but there are many communication security problems. In order to further improve the security of information data, related staff should use data encryption technology (DES) to strengthen security protection and ensure the integrity of information transmission. In the information age, information can help and benefit groups or individuals. Similarly, information can also be used to threaten and destroy them. We often need a measure to protect our data from being seen or destroyed by people with ulterior motives. In this paper, combining the principle and thought of genetic algorithm (GA), DES is studied in computer network communication security, and its application in computer communication network security is discussed.","PeriodicalId":121049,"journal":{"name":"2021 IEEE 4th International Conference on Information Systems and Computer Aided Education (ICISCAE)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130825699","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 : 2021-09-24DOI: 10.1109/ICISCAE52414.2021.9590639
Hao Wang
Matrix factorization is a widely adopted recommender system technique that fits scalar rating values by dot products of user feature vectors and item feature vectors. However, the formulation of matrix factorization as a scalar fitting problem is not friendly to side information incorporation or multi-task learning. In this paper, we replace the scalar values of the user rating matrix by matrices, and fit the matrix values by matrix products of user feature matrix and item feature matrix. Our framework is friendly to multitask learning and side information incorporation. We use popularity data as side information in our paper in particular to enhance the performance of matrix factorization techniques. In the experiment section, we prove the competence of our method compared with other approaches using both accuracy and fairness metrics. Our framework is an ideal substitute for tensor factorization in context-aware recommendation and many other scenarios.
{"title":"MatMat: Matrix Factorization by Matrix Fitting","authors":"Hao Wang","doi":"10.1109/ICISCAE52414.2021.9590639","DOIUrl":"https://doi.org/10.1109/ICISCAE52414.2021.9590639","url":null,"abstract":"Matrix factorization is a widely adopted recommender system technique that fits scalar rating values by dot products of user feature vectors and item feature vectors. However, the formulation of matrix factorization as a scalar fitting problem is not friendly to side information incorporation or multi-task learning. In this paper, we replace the scalar values of the user rating matrix by matrices, and fit the matrix values by matrix products of user feature matrix and item feature matrix. Our framework is friendly to multitask learning and side information incorporation. We use popularity data as side information in our paper in particular to enhance the performance of matrix factorization techniques. In the experiment section, we prove the competence of our method compared with other approaches using both accuracy and fairness metrics. Our framework is an ideal substitute for tensor factorization in context-aware recommendation and many other scenarios.","PeriodicalId":121049,"journal":{"name":"2021 IEEE 4th International Conference on Information Systems and Computer Aided Education (ICISCAE)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128861181","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：