An Automatic Recognition Method of Fruits and Vegetables Based on Depthwise Separable Convolution Neural Network

Zhan, Yuhui; Chen, Mengyao; Chen, Yuefen; Luo, Zhaoqian; Luo, Yiyong; Kedi, Li

doi:10.1088/1742-6596/1871/1/012075

Cited by 7 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each attribute needs to be coded as a feature. The likelihood probability of the existence of scenario attributes is used to evaluate the coding, as shown in Equation (5).…”

Section: Tourism Scenario Attribute-oriented Semantic Feature Relatio...mentioning

confidence: 99%

See 1 more Smart Citation

Geographic Information Visualization and Sustainable Development of Low-Carbon Rural Slow Tourism under Artificial Intelligence

Jiang

Gao

et al. 2023

Sustainability

View full text Add to dashboard Cite

This study conducts in-depth research on geographic information visualization and the sustainable development of low-carbon rural slow tourism under artificial intelligence (AI) to analyze and discuss the visualization of geographic information and the sustainable development of low-carbon slow tourism in rural areas. First, the development options related to low-carbon tourism in rural areas are discussed. Then, a low-carbon rural slow tourism recommendation method based on AI and a low-carbon rural tourism scene recognition method based on Cross-Media Retrieval (CMR) data are proposed. Finally, the proposed scheme is tested. The test results show that the carbon dioxide emissions of one-day tourism projects account for less than 10% of the total tourism industry. From the proportion, it is found that air transport accounts for the largest proportion, more than 40%. With the development of time, the number of rural slow tourists in Guizhou has increased the most, while the number of rural slow tourists in Yunnan has increased to a lesser extent. In the K-means clustering model, the accuracy of scenario classification based on the semantic features of scene attributes is 5.26% higher than that of attribute likelihood vectors. On the Support Vector Machine classifier, the scene classification accuracy based on the semantic features of scene attributes is 19.2% higher than that of the scene classification based on attribute likelihood vector features. CMR techniques have also played a satisfying role in identifying rural tourism scenarios. They enable passengers to quickly identify tourist attractions to save preparation time and provide more flexible time for the tour process. The research results have made certain contributions to the sustainable development of low-carbon rural slow tourism.

show abstract

“…Each attribute needs to be coded as a feature. The likelihood probability of the existence of scenario attributes is used to evaluate the coding, as shown in Equation (5).…”

Section: Tourism Scenario Attribute-oriented Semantic Feature Relatio...mentioning

confidence: 99%

“…They achieved the goal of cross-media semantic space sharing. Meanwhile, the crossmedia scenes were uniformly represented to construct the cross-media scenario recognition dataset [5]. Zhang et al (2022) proposed a CMR knowledge transfer method based on Deep Learning (DL) [6].…”

Section: Introductionmentioning

confidence: 99%

Geographic Information Visualization and Sustainable Development of Low-Carbon Rural Slow Tourism under Artificial Intelligence

Jiang

Gao

et al. 2023

Sustainability

View full text Add to dashboard Cite

show abstract

“…The standard convolution is decomposed into deep convolution and point-wise convolution by depth-separable convolution [23][24][25]. First, each channel of the input…”

Section: Depth-separable Convolutionmentioning

confidence: 99%

Bearing Fault Diagnosis Based on a Novel Adaptive ADSD-gcForest Model

2022

View full text Add to dashboard Cite

With the continuous improvement of industrial production requirements, bearings work significantly under strong noise interference, which makes it difficult to extract fault features. Deep Learning-based approaches are promising for bearing diagnosis. They can extract fault information efficiently and conduct accurate diagnosis. However, the structure of deep learning is often determined by trial and error, which is time-consuming and lacks theoretical support. To address the above problems, an adaptive (Adaptive Depthwise Separable Dilated Convolution and multi-grained cascade forest) ADSD-gcForest fault diagnosis model is proposed in this paper. Multiscale convolution combined with convolutional attention mechanism (CBAM) concentrates on effectively extracting fault information under strong noise, and the Meta-Activate or Not (Meta-ACON) activation function is integrated to adaptively optimize the model structure according to the characteristics of input samples, then gcForest outputs the final diagnosis result as the classifier. The experiment compares the effects of three bearings failure diagnoses under various noise and load conditions. The experimental results show the effectiveness and practicability of the proposed method.

show abstract

“…One is to make the network efficient without deepening the number of network layers, the other is to improve the phase unwrapping performance of the network and retain more image details. In terms of optimize networks, existing research has demonstrated that depthwise separable convolution (DSC) module [32] is effective in significantly reducing the number of parameters. On the second aspect, it is shown that adding atrous spatial pyramid pooling (ASPP) [33] module to the network is beneficial for expanding the feature receptive field.…”

Section: Introductionmentioning

confidence: 99%

Depth_ASPP_UNet++: a novel 2D ESPI phase unwrapping based on convolutional neural network

Wang,

Liang,

Xue

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Phase unwrapping is a key step in optical metrology and physical optics to obtain accurate phase distributions. In practice, phase images obtained from electronic speckle pattern interferometry (ESPI) exhibit diverse and complex morphology, with significant shape variations and non-uniform densities among different individuals. This takes challenges for accurately extracting phase information and unwrapping the phase. With the progress of deep learning technology in optical image processing, real-time performance and accuracy have become concerned issues. In this paper, an ESPI phase unwrapping method based on convolutional neural network (CNN) UNet++ is proposed. The proposed network combines the depthwise separable convolution (DSC), atrous spatial pyramid pooling (ASPP), defined as Depth_ ASPP_ UNet++. In this model, the use of DSC improves network computational efficiency and provides better feature representation capability. In addition, ASPP is introduced to pay more attention to the phase information of the phase image, and then obtain better phase unwrapping results. The experimental results show that our proposed method can obtain excellent results, especially with various of variable density, different noise levels, and different speckle sizes.

show abstract

An Automatic Recognition Method of Fruits and Vegetables Based on Depthwise Separable Convolution Neural Network

Cited by 7 publications

References 0 publications

Geographic Information Visualization and Sustainable Development of Low-Carbon Rural Slow Tourism under Artificial Intelligence

Geographic Information Visualization and Sustainable Development of Low-Carbon Rural Slow Tourism under Artificial Intelligence

Bearing Fault Diagnosis Based on a Novel Adaptive ADSD-gcForest Model

Depth_ASPP_UNet++: a novel 2D ESPI phase unwrapping based on convolutional neural network

Contact Info

Product

Resources

About