Human behavior recognition model based on improved EfficientNet

Luo, Chen-Yun; Cheng, Shuyan; Xu, He; Li, Peng

doi:10.1016/j.procs.2022.01.045

Cited by 12 publications

(19 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Too many MBConv modules in EfficientNet will result in high model complexity and computational workload. Therefore, this study adjusts and reduces the number of MBConv modules [ 22 ]. Adjustments were initially performed to the number of MBConv modules and the internal structure of the original network.…”

Section: Methodsmentioning

confidence: 99%

Corn Harvester Bearing Fault Diagnosis Based on ABC-VMD and Optimized EfficientNet

Liu,

Sun,

Chang

et al. 2023

Entropy

View full text Add to dashboard Cite

The extraction of the optimal mode of the bearing signal in the drive system of a corn harvester is a challenging task. In addition, the accuracy and robustness of the fault diagnosis model are low. Therefore, this paper proposes a fault diagnosis method that uses the optimal mode component as the input feature. The vibration signal is first decomposed by variational mode decomposition (VMD) based on the optimal parameters searched by the artificial bee colony (ABC). Moreover, the key components are screened using an evaluation function that is a fusion of the arrangement entropy, the signal-to-noise ratio, and the power spectral density weighting. The Stockwell transform is then used to convert the filtered modal components into time–frequency images. Finally, the MBConv quantity and activation function of the EfficientNet network are optimized, and the time–frequency pictures are imported into the optimized network model for fault diagnosis. The comparative experiments show that the proposed method accurately extracts the optimal modal component and has a fault classification accuracy greater than 98%.

show abstract

Section: Methodsmentioning

confidence: 99%

Corn Harvester Bearing Fault Diagnosis Based on ABC-VMD and Optimized EfficientNet

Liu,

Sun,

Chang

et al. 2023

Entropy

View full text Add to dashboard Cite

show abstract

“…The edge matching error 𝐸 can be viewed as the Chamfer distance from the edge of the model projection to the edge of the image [18][19][20]. Assume that the model projects an edge profile of r(s), 0<s<1 for a given human body state 𝑥 The corresponding edge profile in the image is z(s), There exists a mapping g(s) which associates each point z(s) on the edge curve in the image with the corresponding point r(g(s)) on the edge curve of the model projection.Thus the edge matching function a natural definition.…”

Section: ) Edge Matching Errormentioning

confidence: 99%

Target Perception and Behavioral Recognition Algorithms Based on Saliency and Feature Extraction

Ni,

Zhang,

Zhang

et al. 2024

IEEE Access

View full text Add to dashboard Cite

In response to the problems of target loss and insufficient accuracy in existing target perception and action recognition algorithms, this paper proposes a target perception and action recognition algorithm based on saliency and feature extraction. This algorithm uses saliency detection techniques to obtain salient regions in images or videos to focus attention on the target. At the same time, feature extraction techniques are combined to extract key nodes and inter-frame correlations from the target information. The experimental results of the measurement data show that this algorithm is superior to traditional detection methods in detecting target behaviour. In addition, it has successfully solved the problems of motion misalignment and jumping in pedestrian detection. Although the node localisation of the algorithm needs further improvement, it has shown good application prospects in smart cities and intelligent surveillance. Future work will focus on improving the positioning accuracy of key nodes to enhance its adaptability to different environments and scenarios, providing better support for smart city and other applications.

show abstract

“…Ref. [ 35 ] improves EfficientNetB0 by adjusting the number of MBConv modules and using the residual structure and LeakRelu, with the parameter of 1.03 M, achieving 99.69% accuracy on the self-built human behavioral point cloud dataset. Ref.…”

Section: Related Workmentioning

confidence: 99%

An Intelligent Waste-Sorting and Recycling Device Based on Improved EfficientNet

Feng

Yang

Chen

et al. 2022

IJERPH

View full text Add to dashboard Cite

The main source of urban waste is the daily life activities of residents, and the waste sorting of residents’ waste is important for promoting economic recycling, reducing labor costs, and protecting the environment. However, most residents are unable to make accurate judgments about the categories of household waste, which severely limits the efficiency of waste sorting. We have designed an intelligent waste bin that enables automatic waste sorting and recycling, avoiding the extensive knowledge required for waste sorting. To ensure that the waste-classification model is high accuracy and works in real time, GECM-EfficientNet is proposed based on EfficientNet by streamlining the mobile inverted bottleneck convolution (MBConv) module, introducing the efficient channel attention (ECA) module and coordinate attention (CA) module, and transfer learning. The accuracy of GECM-EfficientNet reaches 94.54% and 94.23% on the self-built household waste dataset and TrashNet dataset, with parameters of only 1.23 M. The time of one recognition on the intelligent waste bin is only 146 ms, which satisfies the real-time classification requirement. Our method improves the computational efficiency of the waste-classification model and simplifies the hardware requirements, which contributes to the residents’ waste classification based on intelligent devices.

show abstract

Human behavior recognition model based on improved EfficientNet

Cited by 12 publications

References 8 publications

Corn Harvester Bearing Fault Diagnosis Based on ABC-VMD and Optimized EfficientNet

Corn Harvester Bearing Fault Diagnosis Based on ABC-VMD and Optimized EfficientNet

Target Perception and Behavioral Recognition Algorithms Based on Saliency and Feature Extraction

An Intelligent Waste-Sorting and Recycling Device Based on Improved EfficientNet

Contact Info

Product

Resources

About