scholarly journals A High-Performance Deep Learning Algorithm for the Automated Optical Inspection of Laser Welding

2020 ◽  
Vol 10 (3) ◽  
pp. 933 ◽  
Author(s):  
Yatao Yang ◽  
Longhui Pan ◽  
Junxian Ma ◽  
Runze Yang ◽  
Yishuang Zhu ◽  
...  
Keyword(s):  
Laser Welding ◽  
High Performance ◽  
Learning Algorithm ◽  
Production Quality ◽  
Great Success ◽  
Defect Classification ◽  
Training Time ◽  
Deep Learning Algorithm ◽  
Positive Rate ◽  
Automated Optical Inspection

The battery industry has been growing fast because of strong demand from electric vehicle and power storage applications.Laser welding is a key process in battery manufacturing. To control the production quality, the industry has a great desire for defect inspection of automated laser welding. Recently, Convolutional Neural Networks (CNNs) have been applied with great success for detection, recognition, and classification. In this paper, using transfer learning theory and pre-training approach in Visual Geometry Group (VGG) model, we proposed the optimized VGG model to improve the efficiency of defect classification. Our model was applied on an industrial computer with images taken from a battery manufacturing production line and achieved a testing accuracy of 99.87%. The main contributions of this study are as follows: (1) Proved that the optimized VGG model, which was trained on a large image database, can be used for the defect classification of laser welding. (2) Demonstrated that the pre-trained VGG model has small model size, lower fault positive rate, shorter training time, and prediction time; so, it is more suitable for quality inspection in an industrial environment. Additionally, we visualized the convolutional layer and max-pooling layer to make it easy to view and optimize the model.

scholarly journals Research on improved wavelet convolutional wavelet neural networks

2020 ◽  
Author(s):  
Jing-Wei Liu ◽  
Fang-Ling Zuo ◽  
Ying-Xiao Guo ◽  
Tian-Yue Li ◽  
Jia-Ming Chen
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
High Performance ◽  
Learning Algorithm ◽  
Wavelet Neural Network ◽  
Deep Learning Algorithm ◽  
Main Work ◽  
Good Ability ◽  
Fully Connected

AbstractConvolutional neural network (CNN) is recognized as state of the art of deep learning algorithm, which has a good ability on the image classification and recognition. The problems of CNN are as follows: the precision, accuracy and efficiency of CNN are expected to be improved to satisfy the requirements of high performance. The main work is as follows: Firstly, wavelet convolutional neural network (wCNN) is proposed, where wavelet transform function is added to the convolutional layers of CNN. Secondly, wavelet convolutional wavelet neural network (wCwNN) is proposed, where fully connected neural network (FCNN) of wCNN and CNN are replaced by wavelet neural network (wNN). Thirdly, image classification experiments using CNN, wCNN and wCwNN algorithms, and comparison analysis are implemented with MNIST dataset. The effect of the improved methods are as follows: (1) Both precision and accuracy are improved. (2) The mean square error and the rate of error are reduced. (3) The complexitie of the improved algorithms is increased.

A lightweight deep learning algorithm for inspection of laser welding defects on safety vent of power battery

2020 ◽  
Vol 123 ◽  
pp. 103306
Author(s):  
Yatao Yang ◽  
Runze Yang ◽  
Longhui Pan ◽  
Junxian Ma ◽  
Yishuang Zhu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Laser Welding ◽  
Learning Algorithm ◽  
Deep Learning Algorithm ◽  
Power Battery ◽  
Welding Defects

scholarly journals Hybrid Deep Learning Based on a Heterogeneous Network Profile for Functional Annotations of Plasmodium falciparum Genes

2021 ◽  
Vol 22 (18) ◽  
pp. 10019
Author(s):  
Apichat Suratanee ◽  
Kitiporn Plaimas
Keyword(s):  
Plasmodium Falciparum ◽  
Deep Learning ◽  
Unknown Function ◽  
Heterogeneous Network ◽  
High Performance ◽  
Striated Muscle ◽  
Learning Algorithm ◽  
Enrichment Analysis ◽  
Biomedical Science ◽  
Deep Learning Algorithm

Functional annotation of unknown function genes reveals unidentified functions that can enhance our understanding of complex genome communications. A common approach for inferring gene function involves the ortholog-based method. However, genetic data alone are often not enough to provide information for function annotation. Thus, integrating other sources of data can potentially increase the possibility of retrieving annotations. Network-based methods are efficient techniques for exploring interactions among genes and can be used for functional inference. In this study, we present an analysis framework for inferring the functions of Plasmodium falciparum genes based on connection profiles in a heterogeneous network between human and Plasmodium falciparum proteins. These profiles were fed into a hybrid deep learning algorithm to predict the orthologs of unknown function genes. The results show high performance of the model’s predictions, with an AUC of 0.89. One hundred and twenty-one predicted pairs with high prediction scores were selected for inferring the functions using statistical enrichment analysis. Using this method, PF3D7_1248700 and PF3D7_0401800 were found to be involved with muscle contraction and striated muscle tissue development, while PF3D7_1303800 and PF3D7_1201000 were found to be related to protein dephosphorylation. In conclusion, combining a heterogeneous network and a hybrid deep learning technique can allow us to identify unknown gene functions of malaria parasites. This approach is generalized and can be applied to other diseases that enhance the field of biomedical science.

User-friendly image-activated microfluidic cell sorting technique using an optimized, fast deep learning algorithm

Lab on a Chip ◽  
2021 ◽  
Author(s):  
Keondo Lee ◽  
Seong-Eun Kim ◽  
Junsang Doh ◽  
Keehoon Kim ◽  
Wan Kyun Chung
Keyword(s):  
Deep Learning ◽  
Piezoelectric Actuator ◽  
Cell Sorting ◽  
High Performance ◽  
Learning Algorithm ◽  
Cell Sorter ◽  
Operational Procedure ◽  
Deep Learning Algorithm ◽  
Sorting Technique ◽  
User Friendly

The image-activated cell sorter employs a significantly simplified operational procedure based on a syringe connected to a piezoelectric actuator and high-performance inference with TensorRT Integration.

scholarly journals Efficient Depth Map Creation with a Lightweight Deep Neural Network

Electronics ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 479
Author(s):  
Join Kang ◽  
Seong-Won Lee
Keyword(s):  
Graphics Processing Units ◽  
High Performance ◽  
Stereo Matching ◽  
Learning Algorithm ◽  
Vision System ◽  
Depth Map ◽  
Small Scale ◽  
Depth Information ◽  
Deep Learning Algorithm ◽  
Convolution Filter

Finding depth information with stereo matching using a deep learning algorithm for embedded systems has recently gained significant attention owing to emerging high-performance mobile graphics processing units (GPUs). Several researchers have proposed feasible small-scale CNNs that can run on a local GPU, but they still suffer from low accuracy and/or high computational requirements. In the method proposed in this study, pooling layers with padding and an asymmetric convolution filter are used to reduce computational costs and simultaneously maintain the accuracy of disparity. The patch size and number of layers are adjusted by analyzing the feature and activation maps. The proposed method forms a small-scale network algorithm suitable for a vision system at the edge and still exhibits high-disparity accuracy and low computational loads as compared to existing stereo-matching networks.

scholarly journals An Optimal Feature Extraction using Deep Learning Technique for Trojan Detection and Validation using Game Theory

2020 ◽  
Vol 13 (6) ◽  
pp. 318-329
Author(s):  
Priyatharishini Murugesan ◽  
◽  
Nirmala Manickam ◽  
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
True Positive Rate ◽  
Hardware Trojan ◽  
Deep Learning Algorithm ◽  
Positive Rate ◽  
Game Theoretical Approach ◽  
Zero Sum ◽  
Optimal Feature

In modern electronic design, hardware Trojan has emerged as a major threat in the hardware security. To detect the hardware Trojan is a major problem in testing process because of their inherent concealed nature. In this work, we propose a deep learning-based Trojan classification approach, which extracts the optimal feature to indicate the nets affected by the Trojan module. In this approach, a handcrafted algorithm along with the structural report is also analyzed for extracting further features of the gate level netlist, which stamp out the requirement of golden chip. This detection technique is also validated using game theoretical approach, which is modelled as zero-sum game between the attacker and the defender. The Simulation is employed on ISCAS’85, ISCAS’89 and Trust-HUB circuits and the deep learning algorithm performs the best in detection and classification of Trojan type with an average True positive rate of 96.69% and an accuracy of 96.25%.

scholarly journals Deep learning neural networks to differentiate Stafne’s bone cavity from pathological radiolucent lesions of the mandible in heterogeneous panoramic radiography

PLoS ONE ◽  
2021 ◽  
Vol 16 (7) ◽  
pp. e0254997
Author(s):  
Ari Lee ◽  
Min Su Kim ◽  
Sang-Sun Han ◽  
PooGyeon Park ◽  
Chena Lee ◽  
...  
Keyword(s):  
Deep Learning ◽  
High Performance ◽  
Imaging System ◽  
Panoramic Radiography ◽  
Learning Algorithm ◽  
Odontogenic Cysts ◽  
Surgical Removal ◽  
Imaging Features ◽  
Deep Learning Algorithm ◽  
Dentigerous Cysts

This study aimed to develop a high-performance deep learning algorithm to differentiate Stafne’s bone cavity (SBC) from cysts and tumors of the jaw based on images acquired from various panoramic radiographic systems. Data sets included 176 Stafne’s bone cavities and 282 odontogenic cysts and tumors of the mandible (98 dentigerous cysts, 91 odontogenic keratocysts, and 93 ameloblastomas) that required surgical removal. Panoramic radiographs were obtained using three different imaging systems. The trained model showed 99.25% accuracy, 98.08% sensitivity, and 100% specificity for SBC classification and resulted in one misclassified SBC case. The algorithm was approved to recognize the typical imaging features of SBC in panoramic radiography regardless of the imaging system when traced back with Grad-Cam and Guided Grad-Cam methods. The deep learning model for SBC differentiating from odontogenic cysts and tumors showed high performance with images obtained from multiple panoramic systems. The present algorithm is expected to be a useful tool for clinicians, as it diagnoses SBCs in panoramic radiography to prevent unnecessary examinations for patients. Additionally, it would provide support for clinicians to determine further examinations or referrals to surgeons for cases where even experts are unsure of diagnosis using panoramic radiography alone.

scholarly journals Adversarial examples attack based on random warm restart mechanism and improved Nesterov momentum

2021 ◽  
Author(s):  
Tiangang Li
Keyword(s):  
Deep Learning ◽  
Success Rate ◽  
Learning Algorithm ◽  
Training Model ◽  
Great Success ◽  
Deep Learning Algorithm ◽  
Gradient Descent Algorithm ◽  
Adversarial Examples ◽  
Projected Gradient Descent ◽  
Public Datasets

The deep learning algorithm has achieved great success in the field of computer vision, but some studies have pointed out that the deep learning model is vulnerable to attacks adversarial examples and makes false decisions. This challenges the further development of deep learning, and urges researchers to pay more attention to the relationship between adversarial examples attacks and deep learning security. This work focuses on adversarial examples, optimizes the generation of adversarial examples from the view of adversarial robustness, takes the perturbations added in adversarial examples as the optimization parameter. We propose RWR-NM-PGD attack algorithm based on random warm restart mechanism and improved Nesterov momentum from the view of gradient optimization. The algorithm introduces improved Nesterov momentum, using its characteristics of accelerating convergence and improving gradient update direction in optimization algorithm to accelerate the generation of adversarial examples. In addition, the random warm restart mechanism is used for optimization, and the projected gradient descent algorithm is used to limit the range of the generated perturbations in each warm restart, which can obtain better attack effect. Experiments on two public datasets show that the algorithm proposed in this work can improve the success rate of attacking deep learning models without extra time cost. Compared with the benchmark attack method, the algorithm proposed in this work can achieve better attack success rate for both normal training model and defense model. Our method has average attack success rate of 46.3077%, which is 27.19% higher than I-FGSM and 9.27% higher than PGD. The attack results in 13 defense models show that the attack algorithm proposed in this work is superior to the benchmark algorithm in attack universality and transferability.

Computer vision for automatic detection and classification of fabric defect employing deep learning algorithm

2019 ◽  
Vol 31 (4) ◽  
pp. 510-521 ◽  
Author(s):  
Pandia Rajan Jeyaraj ◽  
Edward Rajan Samuel Nadar
Keyword(s):  
Defect Detection ◽  
Classification Accuracy ◽  
Learning Algorithm ◽  
Data Sets ◽  
Defect Classification ◽  
Content Type ◽  
Deep Learning Algorithm ◽  
Average Accuracy ◽  
Fabric Defect

Purpose The purpose of this paper is to focus on the design and development of computer-aided fabric defect detection and classification employing advanced learning algorithm. Design/methodology/approach To make a fast and effective classification of fabric defect, the authors have considered a characteristic of texture, namely its colour. A deep convolutional neural network is formed to learn from the training phase of various defect data sets. In the testing phase, the authors have utilised a learning feature for defect classification. Findings The improvement in the defect classification accuracy has been achieved by employing deep learning algorithm. The authors have tested the defect classification accuracy on six different fabric materials and have obtained an average accuracy of 96.55 per cent with 96.4 per cent sensitivity and 0.94 success rate. Practical implications The authors had evaluated the method by using 20 different data sets collected from different raw fabrics. Also, the authors have tested the algorithm in standard data set provided by Ministry of Textile. In the testing task, the authors have obtained an average accuracy of 94.85 per cent, with six defects being successfully recognised by the proposed algorithm. Originality/value The quantitative value of performance index shows the effectiveness of developed classification algorithm. Moreover, the computational time for different fabric processing was presented to verify the computational range of proposed algorithm with the conventional fabric processing techniques. Hence, this proposed computer vision-based fabric defects detection system is used for an accurate defect detection and computer-aided analysis system.

Sign in / Sign up

Export Citation Format

Share Document