Aidi Tan
Aidi Tan has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Junkai Wang
School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin 150001, China
2 shared publications - Lianlei Lin
School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, China
2 shared publications - Licheng Wang
Beijing Institute of Technology
2 shared publications - Yan Gao
Handan Polytechnic College, Handan, 056001 Hebei, China
2 shared publications - Yuan Liu
Nanjing University of Science and Technology
2 shared publications Fuyuan Zhang
Nanjing University of Science and Technology
1 shared publication
Latest Publications
- 2 September 2026
- Published by Springer Nature
- p. 333-353
A Blockchain-Based Revocable and Fine-Grained Access Control Scheme Against EDoS Attacks
- 2 September 2026
- Published by Springer Nature
- p. 333-353
A Blockchain-Based Revocable and Fine-Grained Access Control Scheme Against EDoS Attacks
- 20 August 2024
- Published by Springer Nature in Applied Intelligence
- Vol. 54 (21) , 10473-10489
Spatio-temporal data generation based on separated attention for ENSO prediction
- 20 August 2024
- Published by Springer Nature in Applied Intelligence
- Vol. 54 (21) , 10473-10489
Spatio-temporal data generation based on separated attention for ENSO prediction
- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21 (1545598X) , 1-5
CSACL: A Channel Spatial Attention Convolutional LSTM Model for Short-Term Sea Surface Temperature Prediction
Accurate predicting sea surface temperature (SST) is practically important to ocean-related fields. However, due to the nonlinear temporal characteristics and complex spatial correlation of SST, fully extracting its spatiotemporal features for dependable short-term SST prediction remains challenging. In this work, we presented a multi-layer channel spatial attention Convolutional LSTM (CSACL) network to better capture the spatiotemporal information of SST recordings. Utilizing multi-scale spatial attention to obtain global-local spatial information and dynamic channel attention for inter-channel interaction, the CSA module achieves comprehensive extraction of spatial features in SST data. Moreover, the multilayer LSTM structure ensures that the network can capture the temporal dependency of short-term SST very well. Finally, we proposed a novel two-stage adaptive loss function training method to solve the accuracy degradation problem for longer prediction cycles. We have evaluated CSACL on three public datasets, and the results demonstrate its superior performance over other classical methods in short-term SST prediction.
- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21 (1545598X) , 1-5
CSACL: A Channel Spatial Attention Convolutional LSTM Model for Short-Term Sea Surface Temperature Prediction
Accurate predicting sea surface temperature (SST) is practically important to ocean-related fields. However, due to the nonlinear temporal characteristics and complex spatial correlation of SST, fully extracting its spatiotemporal features for dependable short-term SST prediction remains challenging. In this work, we presented a multi-layer channel spatial attention Convolutional LSTM (CSACL) network to better capture the spatiotemporal information of SST recordings. Utilizing multi-scale spatial attention to obtain global-local spatial information and dynamic channel attention for inter-channel interaction, the CSA module achieves comprehensive extraction of spatial features in SST data. Moreover, the multilayer LSTM structure ensures that the network can capture the temporal dependency of short-term SST very well. Finally, we proposed a novel two-stage adaptive loss function training method to solve the accuracy degradation problem for longer prediction cycles. We have evaluated CSACL on three public datasets, and the results demonstrate its superior performance over other classical methods in short-term SST prediction.
- RetractedOpen Access
- 8 June 2022
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2022, 1-11
Higher Education Teaching Quality Evaluation Model Based on Improved RBF Neural Network
In order to improve the reliability of higher education quality evaluation, this paper improves the RBF neural network algorithm based on the characteristics of higher education teaching data. Using RBF neural network technology, the predictive model established after learning from samples of actual teaching data can be used to evaluate teaching quality. Moreover, this paper combines the improved RBF neural network to construct a higher education teaching quality evaluation model. The model built in this article needs the support of a support vector machine (SVM) to build a sentiment analysis module and a teaching quality evaluation module. After the model is constructed, the performance of the model built in this article is evaluated, and the performance of the model is displayed by combing statistics. The teaching quality assessment of the higher education model is between 80% and 85%.The test results show that the higher education teaching quality appraise model depended on the improved RBF neural network put forward in this paper has certain effects.
- 8 June 2022
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2022, 1-11
RetractedOpen AccessHigher Education Teaching Quality Evaluation Model Based on Improved RBF Neural Network
In order to improve the reliability of higher education quality evaluation, this paper improves the RBF neural network algorithm based on the characteristics of higher education teaching data. Using RBF neural network technology, the predictive model established after learning from samples of actual teaching data can be used to evaluate teaching quality. Moreover, this paper combines the improved RBF neural network to construct a higher education teaching quality evaluation model. The model built in this article needs the support of a support vector machine (SVM) to build a sentiment analysis module and a teaching quality evaluation module. After the model is constructed, the performance of the model built in this article is evaluated, and the performance of the model is displayed by combing statistics. The teaching quality assessment of the higher education model is between 80% and 85%.The test results show that the higher education teaching quality appraise model depended on the improved RBF neural network put forward in this paper has certain effects.
- RetractedOpen Access
- 23 April 2022
- Published by Hindawi Limited in Wireless Communications and Mobile Computing
- Vol. 2022, 1-14
The Construction of the Development Mode of School-Enterprise Cooperation in Higher Vocational Education with the Aid of Sensitive Neural Network
In-depth school-enterprise cooperation can promote the transformation of higher vocational colleges’ school-running concept and talent training mode, deepen the teaching reform of higher vocational colleges, and improve the employment rate of higher vocational colleges. In the context of school-enterprise cooperation, general higher vocational schools face huge challenges and opportunities in employment guidance. Under the school-enterprise cooperation model, the internship management of students during the internship process is a joint management behavior between the school and the enterprise, which is of great significance to deepen the school-enterprise cooperation. This paper changes the traditional analysis mode of school-enterprise cooperation in higher vocational education and applies sensitive neural network to the construction of school-enterprise cooperation development model in higher vocational education. On the basis of the sensitivity of Adaline neurons, this paper further gives the definition of the sensitivity of the Madaline network structure, deduces the sensitivity calculation of the Madaline network structure without too many constraints, and constructs an intelligent model. Through experimental research, we know that the school-enterprise cooperative development model of higher vocational education based on sensitive neural network proposed in this paper has good results.
- 23 April 2022
- Published by Hindawi Limited in Wireless Communications and Mobile Computing
- Vol. 2022, 1-14
RetractedOpen AccessThe Construction of the Development Mode of School-Enterprise Cooperation in Higher Vocational Education with the Aid of Sensitive Neural Network
In-depth school-enterprise cooperation can promote the transformation of higher vocational colleges’ school-running concept and talent training mode, deepen the teaching reform of higher vocational colleges, and improve the employment rate of higher vocational colleges. In the context of school-enterprise cooperation, general higher vocational schools face huge challenges and opportunities in employment guidance. Under the school-enterprise cooperation model, the internship management of students during the internship process is a joint management behavior between the school and the enterprise, which is of great significance to deepen the school-enterprise cooperation. This paper changes the traditional analysis mode of school-enterprise cooperation in higher vocational education and applies sensitive neural network to the construction of school-enterprise cooperation development model in higher vocational education. On the basis of the sensitivity of Adaline neurons, this paper further gives the definition of the sensitivity of the Madaline network structure, deduces the sensitivity calculation of the Madaline network structure without too many constraints, and constructs an intelligent model. Through experimental research, we know that the school-enterprise cooperative development model of higher vocational education based on sensitive neural network proposed in this paper has good results.
- RetractedOpen Access
- 31 March 2022
- Published by Hindawi Limited in Wireless Communications and Mobile Computing
- Vol. 2022, 1-11
Prediction of Vocational Education Coursework Assessment Results Based on the Simulated Annealing Neural Network
In order to improve the predictive effect of vocational education assessment results and provide a reliable boundary assessment platform for vocational education, this paper uses the simulated annealing neural network algorithm to process vocational education assessment data. Moreover, this article uses the SA algorithm based on the simulated annealing fish school algorithm (SAFSA) in the local search in the later stage of the AFSA algorithm to help the AFSA algorithm jump out of the local optimal solution. Finally, this article combines the improved algorithm to construct a simulated annealing neural network algorithm and builds a vocational education coursework assessment result prediction system, which verifies the prediction effect and assessment effect of this system through experimental research.
- 31 March 2022
- Published by Hindawi Limited in Wireless Communications and Mobile Computing
- Vol. 2022, 1-11
RetractedOpen AccessPrediction of Vocational Education Coursework Assessment Results Based on the Simulated Annealing Neural Network
In order to improve the predictive effect of vocational education assessment results and provide a reliable boundary assessment platform for vocational education, this paper uses the simulated annealing neural network algorithm to process vocational education assessment data. Moreover, this article uses the SA algorithm based on the simulated annealing fish school algorithm (SAFSA) in the local search in the later stage of the AFSA algorithm to help the AFSA algorithm jump out of the local optimal solution. Finally, this article combines the improved algorithm to construct a simulated annealing neural network algorithm and builds a vocational education coursework assessment result prediction system, which verifies the prediction effect and assessment effect of this system through experimental research.
- 15 March 2022
- Published by Springer Nature
- p. 265-275
A Privacy-Preserving Auditable Approach Using Threshold Tag-Based Encryption in Consortium Blockchain
- 15 March 2022
- Published by Springer Nature
- p. 265-275
A Privacy-Preserving Auditable Approach Using Threshold Tag-Based Encryption in Consortium Blockchain