Multiple Attention Mechanism Graph Convolution HAR Model Based on Coordination Theory

Hu, Kai; Ding, Yiwu; Jin, Junlan; Xia, Min; Huaming, Huang

doi:10.3390/s22145259

Cited by 8 publications

(4 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the complexity of socioeconomic environments and the fuzziness of human cognition [28,29], the expectations of different users regarding cloud manufacturing platform services are often inconsistent. Similarly, the expected benefits of different cloud manufacturing platforms may differ.…”

Section: Contributionsmentioning

confidence: 99%

Resource Scheduling Method for Equipment Maintenance Based on Dynamic Pricing Model in Cloud Manufacturing

Wu,

Zhou,

Xia

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Cloud manufacturing, as a novel service mode in the manufacturing field with the features of flexible resource assignment, timely service, and quantity-based pricing, has attracted extensive attention in recent years. The cloud manufacturing industry uses a significant amount of smart equipment. In this context, equipment maintenance resource scheduling (EMRS) is an important subject that needs to be studied. Cloud manufacturing platforms must provide effective services for equipment maintenance in a timely manner. In order to improve the efficiency of cloud manufacturing platforms and meet the needs of users, an effective EMRS scheme is required. In this paper, we propose a dynamic resource allocation model for cloud manufacturing to meet the needs of users and maximize the benefit of a cloud manufacturing platform. The model takes into account the needs of users and the benefits of a cloud production platform. The contributions of this paper are divided into the following three aspects. First, the E-CARGO model using role-based collaboration theory is introduced to formally model EMRS activities, forming a solvable optimization model. Second, a dynamic pricing model with a center symmetric curve is designed to realize the flexible conversion between time, cost, and price. Third, the concept of satisfaction in fuzzy mathematics is introduced, in order to meet the different needs of users and platforms, in terms of time, price, and cost, while ensuring service quality and the platform’s benefits. Finally, an improved genetic algorithm is used to solve the cloud manufacturing resource scheduling problem, and good experimental results are obtained. These results demonstrate that the proposed dynamic pricing model is reasonable, and the allocation scheme obtained through a genetic algorithm is feasible and effective.

show abstract

Section: Contributionsmentioning

confidence: 99%

Resource Scheduling Method for Equipment Maintenance Based on Dynamic Pricing Model in Cloud Manufacturing

Wu,

Zhou,

Xia

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Nguyen combined best practices at each stage of the estimation process to achieve an accurate estimation of the human body [ 16 ]. Hu proposed a coordination feature and strengthened the attention of the model, improving the accuracy of action recognition [ 17 ]. Some of these methods are based on indoor datasets, while others are based on routine human actions.…”

Section: Introductionmentioning

confidence: 99%

Optically Non-Contact Cross-Country Skiing Action Recognition Based on Key-Point Collaborative Estimation and Motion Feature Extraction

et al. 2023

Sensors

View full text Add to dashboard Cite

Technical motion recognition in cross-country skiing can effectively help athletes to improve their skiing movements and optimize their skiing strategies. The non-contact acquisition method of the visual sensor has a bright future in ski training. The changing posture of the athletes, the environment of the ski resort, and the limited field of view have posed great challenges for motion recognition. To improve the applicability of monocular optical sensor-based motion recognition in skiing, we propose a monocular posture detection method based on cooperative detection and feature extraction. Our method uses four feature layers of different sizes to simultaneously detect human posture and key points and takes the position deviation loss and rotation compensation loss of key points as the loss function to implement the three-dimensional estimation of key points. Then, according to the typical characteristics of cross-country skiing movement stages and major sub-movements, the key points are divided and the features are extracted to implement the ski movement recognition. The experimental results show that our method is 90% accurate for cross-country skiing movements, which is equivalent to the recognition method based on wearable sensors. Therefore, our algorithm has application value in the scientific training of cross-country skiing.

show abstract

“…In this paper, based on existing artificial intelligence techniques, such as transfer learning and SSD (Single Shot MultiBox Detector), an intelligent detection system for microchip appearance defects based on transfer learning is proposed for the current stage of chip appearance defect detection. First, the appearance defect samples of larger chips in the past are migrated to the microchips in this paper as knowledge to provide a better initial value for the detection algorithm in the intelligent detection system [2] for appearance defects of small chips, thus improving the accuracy of defect detection. Second, given the poor performance of the current detection algorithm for small targets, this paper improves the SSD (Single Shot MultiBox Detector) algorithm to enhance the features of the image.…”

Section: Introductionmentioning

confidence: 99%

An intelligent recognition system and method for appearance defects of microchips

Yan¹

2023

Second International Conference on Algorithms, Microchips, and Network Applications (AMNA 2023)

View full text Add to dashboard Cite

The appearance of small microchips has few defect samples, and the effective defect sample data of previous largepackaged chips can support the training of defect detection algorithms to obtain high accuracy. The current mainstream detection algorithms have a poor ability to detect small targets, which can lead to missed detection and false detection. In this paper, based on existing artificial intelligence techniques, such as transfer learning and SSD (Single Shot MultiBox Detector), we propose an intelligent detection system for microchip appearance defects based on transfer learning for the current stage of the chip appearance defect detection problem. In this paper, the appearance defect samples of larger chips in the past are migrated to microchips as knowledge to improve the accuracy of defect detection. The SSD algorithm is improved to enhance the image features, and the idea of cross-level feature fusion is used to improve the feature expression and strengthen the semantic information.

show abstract

Multiple Attention Mechanism Graph Convolution HAR Model Based on Coordination Theory

Cited by 8 publications

References 45 publications

Resource Scheduling Method for Equipment Maintenance Based on Dynamic Pricing Model in Cloud Manufacturing

Resource Scheduling Method for Equipment Maintenance Based on Dynamic Pricing Model in Cloud Manufacturing

Optically Non-Contact Cross-Country Skiing Action Recognition Based on Key-Point Collaborative Estimation and Motion Feature Extraction

An intelligent recognition system and method for appearance defects of microchips

Contact Info

Product

Resources

About