Aiyan Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Aiyan Wu has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Qian Guo
School of Computer Science and Technology, North China University of Technology, Beijing 100144, China
1 shared publication Shang Yang
School of Information Science and Technology, North China University of Technology, 100144, China
1 shared publicationYongmei Zhang
School of Information Science and Technology, North China University of Technology, 100144, China
1 shared publication- Yongmei Zhang
School of Information Science and Technology, North China University of Technology, Beijing, China
1 shared publication - Zhirong Du
School of Computer Science and Technology, North China University of Technology, Beijing 100144, China
1 shared publication
Latest Publications
- Open Access
- 20 January 2023
- Published by MDPI AG in Electronics
- Vol. 12 (3) , 538
Human Action Recognition for Dynamic Scenes of Emergency Rescue Based on Spatial-Temporal Fusion Network
Targeting the problems of the insufficient utilization of temporal and spatial information in videos and a lower accuracy rate, this paper proposes a human action recognition method for dynamic videos of emergency rescue based on a spatial-temporal fusion network. A time domain segmentation strategy based on random sampling maintains the overall time domain structure of the video. Considering the spatial-temporal asynchronous relationship, multiple asynchronous motion sequences are increased as input of the temporal convolutional network. spatial-temporal features are fused in convolutional layers to reduce feature loss. Because time series information is crucial for human action recognition, the acquired mid-layer spatial-temporal fusion features are sent into Bidirectional Long Short-Term Memory (Bi-LSTM) to obtain the human movement features in the whole video temporal dimension. Experiment results show the proposed method fully fuses spatial and temporal dimension information and improves the accuracy of human action recognition in dynamic scenes. It is also faster than traditional methods.
- 20 January 2023
- Published by MDPI AG in Electronics
- Vol. 12 (3) , 538
Open AccessHuman Action Recognition for Dynamic Scenes of Emergency Rescue Based on Spatial-Temporal Fusion Network
Targeting the problems of the insufficient utilization of temporal and spatial information in videos and a lower accuracy rate, this paper proposes a human action recognition method for dynamic videos of emergency rescue based on a spatial-temporal fusion network. A time domain segmentation strategy based on random sampling maintains the overall time domain structure of the video. Considering the spatial-temporal asynchronous relationship, multiple asynchronous motion sequences are increased as input of the temporal convolutional network. spatial-temporal features are fused in convolutional layers to reduce feature loss. Because time series information is crucial for human action recognition, the acquired mid-layer spatial-temporal fusion features are sent into Bidirectional Long Short-Term Memory (Bi-LSTM) to obtain the human movement features in the whole video temporal dimension. Experiment results show the proposed method fully fuses spatial and temporal dimension information and improves the accuracy of human action recognition in dynamic scenes. It is also faster than traditional methods.
- Open Access
- 13 December 2022
- Published by IOS Press
- p. 40-47
A Method for Scientific Cultivation Analysis Based on Knowledge Graphs
The development of big data and artificial intelligence has improved the intelligence and informatization of scientific planting. A scientific cultivation analysis method based on knowledge graphs is proposed in this paper. First, the logical representation and the ontological representation are combined to realize the access of static cultivation information and dynamic cultivation experience, as well as their representation with graphs. Second, according to the characteristics of plant cultivation information, knowledge extraction is realized via relational computing. A relationship determination method based on the first derivative and a multi-level classification retrieval method based on a tree structure are proposed to extract cultivation experience from the experimental data. Then, multimedia technology is embedded in the RDF framework and implemented, which further realizes the display of decision suggestions after scientific cultivation information analysis. Finally, taking perennial flowers as an example, the realization and application performance of cultivation knowledge graphs are demonstrated.
- 13 December 2022
- Published by IOS Press
- p. 40-47
Open AccessA Method for Scientific Cultivation Analysis Based on Knowledge Graphs
The development of big data and artificial intelligence has improved the intelligence and informatization of scientific planting. A scientific cultivation analysis method based on knowledge graphs is proposed in this paper. First, the logical representation and the ontological representation are combined to realize the access of static cultivation information and dynamic cultivation experience, as well as their representation with graphs. Second, according to the characteristics of plant cultivation information, knowledge extraction is realized via relational computing. A relationship determination method based on the first derivative and a multi-level classification retrieval method based on a tree structure are proposed to extract cultivation experience from the experimental data. Then, multimedia technology is embedded in the RDF framework and implemented, which further realizes the display of decision suggestions after scientific cultivation information analysis. Finally, taking perennial flowers as an example, the realization and application performance of cultivation knowledge graphs are demonstrated.