A privacy-preserving student status monitoring system
Abstract Timely feedback of students’ listening status is crucial for teaching work. However, it is often difficult for teachers to pay attention to all students at the same time. By leveraging surveillance cameras in the classroom, we are able to assist the teaching work. However, the existing meth...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2022-07-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-022-00796-5 |
| _version_ | 1797863123968851968 |
|---|---|
| author | Haopeng Wu Zhiying Lu Jianfeng Zhang |
| author_facet | Haopeng Wu Zhiying Lu Jianfeng Zhang |
| author_sort | Haopeng Wu |
| collection | DOAJ |
| description | Abstract Timely feedback of students’ listening status is crucial for teaching work. However, it is often difficult for teachers to pay attention to all students at the same time. By leveraging surveillance cameras in the classroom, we are able to assist the teaching work. However, the existing methods either lack the protection of students’ privacy, or they have to reduce the accuracy of success, because they are concerned about the leakage of students’ privacy. We propose federated semi-supervised class assistance system to evaluate the listening status of students in the classroom. Rather than training the semi-supervised model in a centralized manner, we train a semi-supervised model in a federated manner among various monitors while preserving students’ privacy. We also formulate a new loss function according to the difference between the pre-trained initial model and the expected model to restrict the training process of the unlabeled data. By applying the pseudo-label assignment method on the unlabeled data, the class monitors are able to recognize the student class behavior. In addition, simulation and real-world experimental results demonstrate that the performance of the proposed system outperforms that of the baseline models. |
| first_indexed | 2024-04-09T22:31:37Z |
| format | Article |
| id | doaj.art-4c347c27487d4c2ebace5c0d726a58ec |
| institution | Directory Open Access Journal |
| issn | 2199-4536 2198-6053 |
| language | English |
| last_indexed | 2024-04-09T22:31:37Z |
| publishDate | 2022-07-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj.art-4c347c27487d4c2ebace5c0d726a58ec2023-03-22T12:44:12ZengSpringerComplex & Intelligent Systems2199-45362198-60532022-07-019159760810.1007/s40747-022-00796-5A privacy-preserving student status monitoring systemHaopeng Wu0Zhiying Lu1Jianfeng Zhang2School of Electrical and Information Engineering, Tianjin UniversitySchool of Electrical and Information Engineering, Tianjin UniversitySchool of Information Science and Engineering, Shandong Normal UniversityAbstract Timely feedback of students’ listening status is crucial for teaching work. However, it is often difficult for teachers to pay attention to all students at the same time. By leveraging surveillance cameras in the classroom, we are able to assist the teaching work. However, the existing methods either lack the protection of students’ privacy, or they have to reduce the accuracy of success, because they are concerned about the leakage of students’ privacy. We propose federated semi-supervised class assistance system to evaluate the listening status of students in the classroom. Rather than training the semi-supervised model in a centralized manner, we train a semi-supervised model in a federated manner among various monitors while preserving students’ privacy. We also formulate a new loss function according to the difference between the pre-trained initial model and the expected model to restrict the training process of the unlabeled data. By applying the pseudo-label assignment method on the unlabeled data, the class monitors are able to recognize the student class behavior. In addition, simulation and real-world experimental results demonstrate that the performance of the proposed system outperforms that of the baseline models.https://doi.org/10.1007/s40747-022-00796-5Facial expression recognitionImage sequenceTeaching evaluationPrivacy policy |
| spellingShingle | Haopeng Wu Zhiying Lu Jianfeng Zhang A privacy-preserving student status monitoring system Complex & Intelligent Systems Facial expression recognition Image sequence Teaching evaluation Privacy policy |
| title | A privacy-preserving student status monitoring system |
| title_full | A privacy-preserving student status monitoring system |
| title_fullStr | A privacy-preserving student status monitoring system |
| title_full_unstemmed | A privacy-preserving student status monitoring system |
| title_short | A privacy-preserving student status monitoring system |
| title_sort | privacy preserving student status monitoring system |
| topic | Facial expression recognition Image sequence Teaching evaluation Privacy policy |
| url | https://doi.org/10.1007/s40747-022-00796-5 |
| work_keys_str_mv | AT haopengwu aprivacypreservingstudentstatusmonitoringsystem AT zhiyinglu aprivacypreservingstudentstatusmonitoringsystem AT jianfengzhang aprivacypreservingstudentstatusmonitoringsystem AT haopengwu privacypreservingstudentstatusmonitoringsystem AT zhiyinglu privacypreservingstudentstatusmonitoringsystem AT jianfengzhang privacypreservingstudentstatusmonitoringsystem |