Article
Engineering, Multidisciplinary
Hesheng Tang, Yajuan Xie
Summary: In this study, transfer learning is employed to identify defects in structural health monitoring using deep convolutional neural networks. Experimental results demonstrate that this approach can improve identification models in cases of data scarcity.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2023)
Article
Agronomy
Muhammad Mostafa Monowar, Md. Abdul Hamid, Faris A. Kateb, Abu Quwsar Ohi, M. F. Mridha
Summary: This paper introduces a self-supervised leaf disease clustering system for classifying plant diseases, which is cost-effective and applicable to various plants. It utilizes a deep convolutional neural network to generate clusterable embeddings and combines with k-means algorithm for classification.
Article
Computer Science, Information Systems
Anupama Namburu, Prabha Selvaraj, Senthilkumar Mohan, Sumathi Ragavanantham, Elsayed Tag Eldin
Summary: Forest fires are caused by natural factors like lightning, high temperatures, and dryness. India has experienced an increase in the frequency of forest fires, with 136,604 fire points detected between January and March 2022. While satellite monitoring provides valuable information, video-based fire detection on the ground using unmanned aerial vehicles equipped with high-resolution cameras can identify fires more quickly. This paper proposes a cheaper UAV with deep learning capabilities to classify forest fires (97.26%) and share the detection and GPS location with state forest departments.
Article
Engineering, Electrical & Electronic
Yifan Zhao, Qiong Wu, Jianyi Yu, Hanjun Gao
Summary: The engine lining plays a crucial role in maintaining the stability of the engine structure by preventing fuel debonding, heat isolation, combustion prevention, and stress buffering. Identifying defects in the formed lining and conducting comprehensive detection is of great significance. This study utilizes an image acquisition system and improved detectors and network components to achieve high-precision identification of image defects.
IEEE SENSORS JOURNAL
(2023)
Article
Geosciences, Multidisciplinary
Haizhou Wang, Chufan Li, Zhifei Zhang, Stephen Kershaw, Lars E. Holmer, Yang Zhang, Keyi Wei, Peng Liu
Summary: The study introduces a new and efficient method for automatically identifying brachiopod fossils using a tailored Transpose Convolutional Neural Network (TCNN). Compared to the traditional Convolution Neural Network (CNN), the TCNN achieves higher identification accuracy on a smaller training dataset.
Article
Food Science & Technology
R. Nithya, B. Santhi, R. Manikandan, Masoumeh Rahimi, Amir H. Gandomi
Summary: The article highlights the importance of machine learning techniques in agricultural applications, specifically in developing a computer-assisted system for mango quality grading and defect detection. Efficient classification results were achieved using deep learning methods, particularly CNN.
Article
Computer Science, Information Systems
Xianwei Lv, Zhenfeng Shao, Xiao Huang, Wen Zhou, Dongping Ming, Jiaming Wang, Chengzhuo Tong
Summary: Object-based convolutional neural networks (OCNNs) have shown great performance in land-cover and land-use classification, with the proposed morphology-based binary tree sampling (BTS) method outperforming other competing methods by generating evenly distributed object convolutional positions (OCPs). Further experiments suggest that the efficiency of BTS can be improved with multi-thread technology implementation.
INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE
(2022)
Article
Engineering, Chemical
Yo-Ping Huang, Chun-Ming Su, Haobijam Basanta, Yau-Liang Tsai
Summary: The complexity of defect detection in ceramic substrates leads to interclass and intraclass imbalance problems. Traditional methods rely on identifying flaws based on aberrant material occurrences and characteristic quantities. The proposed method utilizes unsupervised learning and deep learning to address the challenges of detecting defects in ceramic substrates, outperforming other methods according to experimental results.
Article
Engineering, Chemical
Ling Wang, Xinbo Liu, Juntao Ma, Wenzhi Su, Han Li
Summary: Steel surface defect detection is crucial for producing high-quality materials. Traditional methods are time-consuming and uneconomical, requiring manual design or additional supervision. This paper proposes a real-time detection technology based on YOLO-v5 network, effectively exploring multi-scale information with a special block and focusing on defect information with a spatial attention mechanism. Experimental results show an approximately 72% mAP and real-time performance.
Article
Engineering, Multidisciplinary
Junjie Xing, Minping Jia
Summary: An automatic detection method based on convolutional neural networks is proposed in this paper and its detection performance is evaluated and compared with other models, showing that the method has better performance in real-time automatic detection of workpiece surface defects.
Article
Engineering, Electrical & Electronic
Jiao Wang, Chunrui Tang, Hao Huang, Hong Wang, Jianqing Li
Summary: Blind identification of channel codes is crucial in signal interception and intelligent communication systems. This paper proposes a deep residual network-based deep learning approach that achieves high recognition accuracy for various forms of convolutional codes without prior information. Experimental results demonstrate that this method outperforms traditional algorithms and existing DL-based algorithms in blind identification of convolutional codes.
DIGITAL SIGNAL PROCESSING
(2021)
Article
Computer Science, Software Engineering
Dong An, Ronghua Hu, Liting Fan, Zhili Chen, Zetong Liu, Peng Zhou
Summary: In this paper, a dual-path neural network based on shearlet transform (STDPNet) is proposed for defect detection systems. By utilizing shearlet transform in multi-scale analysis and combining it with an improved object detection algorithm, this method achieves high accuracy and speed in image defect detection.
Article
Computer Science, Artificial Intelligence
Ram Krishn Mishra, Siddhaling Urolagin, J. Angel Arul Jothi, Pramod Gaur
Summary: Image processing is a technique used to apply various operations to images to improve them or extract information, with facial recognition being a prominent application. This study examines the accuracy of categorizing human facial expressions using deep learning and transfer learning methods, proposing a deep hybrid learning approach that combines multiple deep learning models.
IMAGE AND VISION COMPUTING
(2022)
Review
Medicine, General & Internal
Sujit Kumar Das, Pinki Roy, Prabhishek Singh, Manoj Diwakar, Vijendra Singh, Ankur Maurya, Sandeep Kumar, Seifedine Kadry, Jungeun Kim
Summary: Diabetes is a chronic condition caused by uncontrolled blood sugar levels, and early diagnosis of complications such as diabetic foot ulcers (DFUs) can help prevent severe consequences. The use of deep learning, machine learning, and computer vision techniques provides promising solutions for assisting clinicians in diagnosing DFUs. This article provides a comprehensive overview of the current status of automatic DFU identification and highlights the dominance of CNN-based solutions in the field. It emphasizes the importance of combining traditional ML and advanced DL techniques for more reliable and efficient diagnostic decisions.
Article
Environmental Sciences
Xinyue Wang, Hironobu Iwabuchi, Takaya Yamashita
Summary: In this study, an image-based deep neural network (DNN) model is developed for cloud identification and retrieval of cloud top height and cloud optical thickness. The model shows high consistency with the target values and has a strong accuracy derived from learning spatial features and integrating information from neighboring pixels. It can be used for severe weather monitoring and cloud system studies.
REMOTE SENSING OF ENVIRONMENT
(2022)
Article
Engineering, Mechanical
Dawei Li, Hesheng Tang, Songtao Xue, Yu Su
PROBABILISTIC ENGINEERING MECHANICS
(2018)
Article
Computer Science, Information Systems
Songtao Xue, Bo Wen, Rui Huang, Liyuan Huang, Tadanobu Sato, Liyu Xie, Hesheng Tang, Chunfeng Wan
INTERNATIONAL JOURNAL OF DISTRIBUTED SENSOR NETWORKS
(2018)
Article
Engineering, Multidisciplinary
Songtao Xue, Hesheng Tang, Qiang Xie
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2009)
Article
Materials Science, Multidisciplinary
Zhenwei Zhou, Chunfeng Wan, Da Fang, Liyu Xie, Hesheng Tang, Caiqian Yang, Youliang Ding, Songtao Xue
JOURNAL OF INTELLIGENT MATERIAL SYSTEMS AND STRUCTURES
(2020)
Article
Chemistry, Multidisciplinary
Chunfeng Wan, Huachen Jiang, Liyu Xie, Caiqian Yang, Youliang Ding, Hesheng Tang, Songtao Xue
APPLIED SCIENCES-BASEL
(2020)
Article
Construction & Building Technology
Dawei Li, Hesheng Tang, Songtao Xue
Summary: A robust design method for a tuned mass damper (TMD) is proposed in this study, which combines aleatory and epistemic uncertainties to minimize worst system response and improve the robustness of the primary structure through global optimization. Case studies validate the effectiveness of the designed TMD in reducing seismic responses.
STRUCTURAL CONTROL & HEALTH MONITORING
(2021)
Article
Engineering, Multidisciplinary
Hesheng Tang, Yajuan Xie
Summary: In this study, transfer learning is employed to identify defects in structural health monitoring using deep convolutional neural networks. Experimental results demonstrate that this approach can improve identification models in cases of data scarcity.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2023)
Article
Construction & Building Technology
Yunjia Tong, Songtao Xue, Liyu Xie, Hesheng Tang
Summary: This paper analyzes the recorded seismic response of an eight-story passively-controlled steel building in Sendai. It extracts the dynamic properties of the building and updates the model parameters using a data-driven approach to assess the seismic performance of the structure.
STRUCTURAL CONTROL & HEALTH MONITORING
(2023)