Yaojie Ke
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Yaojie Ke has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Chen Dong
College of Computer and Data Science, Fuzhou University, Fuzhou, Fujian, China
1 shared publication Hepeng Xie
College of Computer and Data Science Fuzhou University,Fuzhou,China
1 shared publicationHui Lin
College of Computer and Cyber Security Fujian Normal University,Fuzhou,China
1 shared publication- Qiaowen Wu
College of Computer and Data Science, Fuzhou University, China
1 shared publication - Qiyan Wu
College of Computer and Data Science, Fuzhou University, China
1 shared publication Yinan Yao
College of Computer and Data Science Fuzhou University,Fuzhou,China
1 shared publication
Latest Publications
- Open Access
- 6 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 82-87
Marine litter detection based on YOLOv7 algorithm and data encryption protection
Marine litter can cause significant damage to marine biodiversity, threatening the marine food chain and spreading harmful substances, posing a significant impact on the ocean ecosystem. Autonomous Underwater Vehicles (AUVs) can automatically remove marine litter using sensors and trained models. this paper evaluates the YOLOv7 series of models that utilize deep learning to detect targets in a real underwater environment. In order to improve the performance of the model, we introduced two attention mechanisms, and the experimental results showed a 2.5% increase in Mean Average Precision(mAP) values. We used a large publicly available dataset of re-annotated open-water debris to train convolutional neural networks for target detection, and we evaluated the trained models on a subset of the dataset, to provide insights into the ability of deep learning to detect marine litter. In addition, to prevent attacks by malicious actors during AUVs cloud platform access, we introduced data encryption protection to ensure that the model’s predicted results can be correctly received by AUVs.
- 6 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 82-87
Open AccessMarine litter detection based on YOLOv7 algorithm and data encryption protection
Marine litter can cause significant damage to marine biodiversity, threatening the marine food chain and spreading harmful substances, posing a significant impact on the ocean ecosystem. Autonomous Underwater Vehicles (AUVs) can automatically remove marine litter using sensors and trained models. this paper evaluates the YOLOv7 series of models that utilize deep learning to detect targets in a real underwater environment. In order to improve the performance of the model, we introduced two attention mechanisms, and the experimental results showed a 2.5% increase in Mean Average Precision(mAP) values. We used a large publicly available dataset of re-annotated open-water debris to train convolutional neural networks for target detection, and we evaluated the trained models on a subset of the dataset, to provide insights into the ability of deep learning to detect marine litter. In addition, to prevent attacks by malicious actors during AUVs cloud platform access, we introduced data encryption protection to ensure that the model’s predicted results can be correctly received by AUVs.
- 14 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 0942-0949
Empowering Intelligent Home Safety: Indoor Family Fall Detection with YOLOv5
As we all know, population aging is a significant challenge faced by Chinese society, and ensuring the health and safety of elderly individuals has become an urgent topic of concern. Within the context of family safety, elderly individuals often experience falls or fainting due to age-related physical decline or underlying medical conditions. In response to this phenomenon, this paper presents a method for enhancing the wellbeing of family members by utilizing the YOLOv5 model to detect falls. Moreover, due to the built-in capability of YOLOv5 to read video from webcam, this technology can also be integrated into loT devices, turning these devices into a part of smart homes. Considering the specific nature of the home environment, CAU CAFall is considered to be the most suitable dataset. Various variations of the YOLOv5 model are experi-mented on a CAUCAFall dataset and achieve promising results. The YOLOv5x model achieved a precision of 82.2%, while the YOLOv5s model, with improved running speed, achieved an precision of 79.6%. Finally, we explored and selected the most suitable YOLOv5 model for home fall detection considering comprehensive evaluation metrics, and it is YOLOv5s.
- 14 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 0942-0949
Empowering Intelligent Home Safety: Indoor Family Fall Detection with YOLOv5
As we all know, population aging is a significant challenge faced by Chinese society, and ensuring the health and safety of elderly individuals has become an urgent topic of concern. Within the context of family safety, elderly individuals often experience falls or fainting due to age-related physical decline or underlying medical conditions. In response to this phenomenon, this paper presents a method for enhancing the wellbeing of family members by utilizing the YOLOv5 model to detect falls. Moreover, due to the built-in capability of YOLOv5 to read video from webcam, this technology can also be integrated into loT devices, turning these devices into a part of smart homes. Considering the specific nature of the home environment, CAU CAFall is considered to be the most suitable dataset. Various variations of the YOLOv5 model are experi-mented on a CAUCAFall dataset and achieve promising results. The YOLOv5x model achieved a precision of 82.2%, while the YOLOv5s model, with improved running speed, achieved an precision of 79.6%. Finally, we explored and selected the most suitable YOLOv5 model for home fall detection considering comprehensive evaluation metrics, and it is YOLOv5s.