A Novel Deep Convolutional Neural Network Based on ResNet‐18 and Transfer Learning for Detection of Wood Knot Defects

Gao, Mingyu; Song, Peng; Wang, Fei; Liu, Junyan; Mandelis, Andreas; Qi, Dawei

doi:10.1155/2021/4428964

Cited by 27 publications

(22 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Reference [12] used the deep network built by CNN and LSTM to classify and identify vibration signals. On the basis of previous research, this paper proposes a mental health state prediction method based on ResNet combined with LSTM [13][14][15][16]. Taking the collected mental health data of primary and middle school students as the model input, the 1DCNN network is used to extract the signal feature information, and the ResNet improves the model training depth to avoid the disappearance of the model gradient.…”

Section: Introductionmentioning

confidence: 99%

Mental Health Education in Primary and Secondary Schools Based on Deep Learning

Wang¹,

An²

2022

Journal of Sensors

View full text Add to dashboard Cite

Strengthening the mental health education of primary and middle school students is a key measure to lead their healthy growth. This paper takes mental health early warning as the starting point to carry out research on mental health education in primary and secondary schools. Aiming at the defect that the existing methods cannot effectively warn the mental health of primary and secondary school students, this paper proposes a mental health early warning research method based on the deep learning models. The method firstly obtains the mental health data of college students through the symptom self-rating scale. Then, a mental health prediction model combining convolutional neural networks (CNN), deep residual networks (ResNet), and long short-term memory (LSTM) is adopted. Through in-depth processing and analysis of mental health data, the mental health status of students can be determined. Experiments show that this method can effectively improve the accuracy of mental health early warning compared with the currently commonly used mental health early warning methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Mental Health Education in Primary and Secondary Schools Based on Deep Learning

Wang¹,

An²

2022

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…Parameters (M) PV-CrackNet 7.01 VGG-19 [19] 143.67 ResNet-18 [20] 11.69 AlexNet [21] 61.0 GoogleNet [22] 13.0 To provide a more robust analysis, the precision, recall, and F1-score were also inspected. Precision was the highest at 98%, whilst the recall stood at a respective 96%.…”

Section: Architecturementioning

confidence: 99%

PV-CrackNet Architecture for Filter Induced Augmentation and Micro-Cracks Detection within a Photovoltaic Manufacturing Facility

2022

View full text Add to dashboard Cite

Photovoltaic cell manufacturing is a rigorous process involving many stages where the cell surface is exposed to external pressure and temperature differentials. This provides fertile ground for micro-cracks to develop on the cell surface. At present, domain experts carry out a manual inspection of the cell surface to judge if any micro-cracks are present. This research looks to overcome the issue of cell data scarcity through the proposed filter-induced augmentations, thus providing developers with an effective, cost-free mechanism for generating representative data samples. Due to the abstract nature of the cell surfaces, the proposed augmentation strategy is effective in generating representative samples for better generalization. Furthermore, a custom architecture is developed that is computationally lightweight compared to state-of-the-art architectures, containing only 7.01 million learnable parameters while achieving an F1-score of 97%.

show abstract

“…e new residual module Swish Gated Block proposed in this paper improves the residual module in ResNet [12][13][14]. e Swish Gated Block is composed of Swish module and residual, Swish module contains a convolutional layer and Swish activation function.…”

Section: Swish Module and Loss Functionmentioning

confidence: 99%

“…e network of the discriminator uses ResNet, and the data are after the convolutional layer so that the data will not be too large and lead to unstable training [14,15]. e loss of the discriminator here is the discriminator loss proposed by GANS.…”

mentioning

confidence: 99%

Research on Automatic Intelligent Coloring of Animation Sketch Based on Enhanced Deep Learning

Wang

2022

Scientific Programming

View full text Add to dashboard Cite

An automatic intelligent coloring model of animation sketch based on enhanced deep learning is proposed. In the proposed model, generative adversarial networks (GANS) are adopted. The U-net network based on the Swish function residual enhancement is used in the generative model, and the ResNet network is used in the discriminant model. The U-net embedded with the Swish Gate module is adopted to transmit feature map information. The perceptual network on the discriminator is used to perceive the perceptual features of the generated image and the actual image and calculate the perceptual loss. Experiment results show that perceptual loss can better capture the difference between black-and-white images and color images, so as to better train the network end-to-end. After comparative analysis, it can be concluded that compared with the existing methods, the proposed model has greater advantages in processing animation sketches. The color images it generates have higher visual quality and richer color diversity and matching.

show abstract

A Novel Deep Convolutional Neural Network Based on ResNet‐18 and Transfer Learning for Detection of Wood Knot Defects

Cited by 27 publications

References 41 publications

Mental Health Education in Primary and Secondary Schools Based on Deep Learning

Mental Health Education in Primary and Secondary Schools Based on Deep Learning

PV-CrackNet Architecture for Filter Induced Augmentation and Micro-Cracks Detection within a Photovoltaic Manufacturing Facility

Research on Automatic Intelligent Coloring of Animation Sketch Based on Enhanced Deep Learning

Contact Info

Product

Resources

About