Article
Chemistry, Multidisciplinary
Sudha Ramasamy, Kristina M. Eriksson, Fredrik Danielsson, Mikael Ericsson
Summary: This article investigates a suitable path planning algorithm for online multi-agent-based Plug & Produce systems. Comparative study between existing sampling-based path planning algorithms reveals that adaptive RRT and adaptive RRT* are more suitable for online applications in multi-agent systems.
APPLIED SCIENCES-BASEL
(2023)
Article
Automation & Control Systems
Shanen Yu, Jianke Chen, Guangyu Liu, Xiaolong Tong, Yingyi Sun
Summary: Sampling-based algorithms have shown their advantages in complex and high-dimensional environments. This article proposes the SOF-RRT* algorithm to improve the efficiency of the RRT* algorithm, by introducing a spatial probability weight sampling strategy and a target bias and obstacle tangential bias strategy to enhance sampling and tree expansion efficiency.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Chemistry, Multidisciplinary
Zhenping Wu, Zhijun Meng, Wenlong Zhao, Zhe Wu
Summary: Fast-RRT is a pathfinding algorithm based on RRT that aims to quickly find a near-optimal path by introducing strategies such as Fast-Sampling, Random Steering expansion, and path fusion and adjustment. It outperforms RRT and RRT* in speed and stability during experiments.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Artificial Intelligence
Bin Liao, Fangyi Wan, Yi Hua, Ruirui Ma, Shenrui Zhu, Xinlin Qing
Summary: This paper proposes a modified RRT* algorithm, F-RRT*, which optimizes the cost of paths by creating a parent node for the random point. This results in a better initial solution and faster convergence rate compared to RRT*, demonstrating higher performance.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Automation & Control Systems
Fujie Yu, Yuan Chen
Summary: This article proposes a cylinder-based informed rapidexploration random tree (Cyl-iRRT*) algorithm, which aims to efficiently and safely reach the target position in a complex 3-D environment. The algorithm focuses the search space on a gradually shrinking cylinder to find the homotopy optimal path. It introduces a proportional shrinkage method and obstacle-based sampling strategy for fast convergence response and robust stability. The probabilistic completeness and homotopic optimality of Cyl-iRRT* are proven effective. both simulation and real-world experimental results demonstrate the superiorities of the Cyl-iRRT* algorithm.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Article
Chemistry, Analytical
Yiyang Liu, Yang Zhao, Shuaihua Yan, Chunhe Song, Fei Li
Summary: This paper proposes a two-phase motion planning algorithm named Metropolis RRT* (M-RRT*) based on the Metropolis acceptance criterion. It improves the convergence rate of RRT* algorithm by defining dynamic vertex acceptance criteria in two phases. The effectiveness of M-RRT* is verified through simulation results.
Article
Computer Science, Interdisciplinary Applications
Jun Ding, Yinxuan Zhou, Xia Huang, Kun Song, Shiqing Lu, Lusheng Wang
Summary: The Rapidly-exploring Random Tree Star (RRT*) algorithm and its variants based on random sampling can provide collision-free and asymptotic optimal solutions for many path planning problems. However, in environments with long corridors, many RRT* based variants have low sampling efficiency and slow convergence rate due to the need for a large number of iterations in critical node sampling. To overcome this problem, the paper proposes the Expanding Path RRT* (EP-RRT*) based on heuristic sampling in the path expansion area. EP-RRT* combines the greedy heuristic of Rapidly exploring Random Tree (RRT)-Connect to quickly explore the environment and find a feasible path, which is then expanded to obtain the heuristic sampling area. It iteratively searches in the heuristic sampling area, which changes with the continuous optimization of the path, and finally obtains an optimal or suboptimal path connecting the starting point and target point. Comparisons with RRT* and Informed RRT* in four simulation environments show that EP-RRT* improves node utilization, accelerates convergence rate, and obtains a better path for the same number of iterations.
JOURNAL OF COMPUTATIONAL SCIENCE
(2023)
Article
Engineering, Marine
Shouqi Mao, Ping Yang, Diju Gao, Chunteng Bao, Zhenyang Wang
Summary: This paper proposes a motion planning method called state prediction rapidly exploring random tree (spRRT) to solve the problem of the path search rules in traditional path planning methods being divorced from the actual maneuverability of an unmanned surface vehicle (USV). The method combines the discrete search of RRT with the continuity of USV motion by calculating the state information based on the mathematical model of USV's motion and adding it to the RRT path search rules. The simulation results show that spRRT can effectively plan smooth paths for USV and improve steering performance by over 40% on average.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Yan-ming Liang, Hai -yang Zhao
Summary: In this paper, a new algorithm called CCPF-RRT* is proposed, which addresses the issues of slow convergence, high path cost, and planning suitable paths in congested environments. The algorithm integrates artificial potential field into RRT* to reduce the number of iterations and speed up convergence. It also incorporates a movement cost function to consider congestion intensity and path length when generating paths. Experimental simulation results show that the algorithm outperforms other algorithms in terms of initial solution, convergence speed, and optimal path design in crowded environments.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Robotics
Zhi-wei Zhang, Yun-wei Jia, Qi-qi Su, Xiao-tong Chen, Bang-peng Fu
Summary: This paper proposes an improved RRT* algorithm based on alternative paths and triangular area sampling (ATS-RRT*), which aims to enhance path quality and planning speed.
Article
Robotics
Nils Funk, Juan Tarrio, Sotiris Papatheodorou, Pablo Alcantarilla, Stefan Leutenegger
Summary: This study proposes a new method for path planning of UAVs in challenging environments with narrow openings, taking into account the attitude. The method uses global and local A* algorithms and an efficient approach to introduce attitude. Compared to baselines, the method achieves significantly higher success rates while reducing computational burden.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Robotics
Xusheng Luo, Yiannis Kantaros, Michael M. Zavlanos
Summary: The article proposes a new sampling-based LTL planning algorithm that incrementally builds trees to explore the product state-space without requiring discrete abstraction of robot mobility, thus increasing the scalability of the algorithm. By introducing bias in the sampling process to speed up the construction of feasible plans, the algorithm is shown to be probabilistically complete and asymptotically optimal. Numerical experiments demonstrate that the method outperforms relevant temporal logic planning methods.
IEEE TRANSACTIONS ON ROBOTICS
(2021)
Article
Automation & Control Systems
Wenzheng Chi, Zhiyu Ding, Jiankun Wang, Guodong Chen, Lining Sun
Summary: This article presents a heuristic path planning algorithm based on generalized Voronoi diagram (GVD) to improve the motion planning efficiency of mobile robots. The algorithm can automatically identify environment features and provide reasonable heuristic paths. It utilizes lightweight feature extraction, feature node fusion, and GVD feature matrix to achieve real-time motion planning.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2022)
Article
Computer Science, Information Systems
Yiyang Liu, Chengjin Li, Hongxia Yu, Chunhe Song
Summary: This paper proposes a novel non-threshold adaptive region sampling RRT (NT-ARS-RRT) algorithm for path planning, which addresses the issues of low solution efficiency, no search guidance, poor quality of the obtained path, and reduction of search efficiency in narrow exit environments. The proposed algorithm improves path search efficiency, optimizes node selection, reduces unnecessary node generation, and enhances the speed and quality of the algorithm.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2023)
Article
Computer Science, Interdisciplinary Applications
Xianpeng Wang, Xinglu Ma, Xiaoxu Li, Xiaoyu Ma, Chunxu Li
Summary: This paper proposes an improved RRT* path planning algorithm based on the target-biased sampling strategy and heuristic optimization strategy, which combines target bias and heuristic sampling to efficiently generate paths and optimize convergence capability. The experimental results demonstrate that the algorithm has high search efficiency and convergence capability in complex environments.
JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING
(2022)
Article
Engineering, Civil
Donggyun Ku, Minje Choi, Haram Oh, Seungheon Shin, Seungjae Lee
Summary: This study focuses on quickly identifying and addressing pedestrian path conditions using discrimination automation, enhancing pedestrian resilience, assessing safety and economic issues associated with transportation vulnerabilities through quantitative analysis, and demonstrating the benefits of improving pedestrian paths in a case study in Seoul.
PROCEEDINGS OF THE INSTITUTION OF CIVIL ENGINEERS-MUNICIPAL ENGINEER
(2022)
Article
Engineering, Marine
Daesoo Lee, Seungjae Lee, Jaeyong Lee
Summary: This paper investigates the ANN-based mooring line top tension prediction systems. It studies the prediction performances concerning the distribution shape, number, and simulation length of wave states, and explores the effects of Batch Normalization (BN) and Learning Rate Decay (LRD) on prediction performances. Additionally, it proposes a guideline for selecting wave states and simulation length in order to improve prediction performance.
INTERNATIONAL JOURNAL OF NAVAL ARCHITECTURE AND OCEAN ENGINEERING
(2022)
Article
Multidisciplinary Sciences
Seung Jae Lee, Mina Rho
Summary: The study developed a method called MDL4Microbiome, which achieved high accuracy in predicting disease status in human microbiomes using various features from metagenome sequences and a multimodal deep learning model. The method combined different features and accurately predicted patients with inflammatory bowel disease, type 2 diabetes, liver cirrhosis, and colorectal cancer.
SCIENTIFIC REPORTS
(2022)
Article
Transportation
Yoonjung Jang, Donggyun Ku, Seungjae Lee
Summary: In this research, algorithms are studied for detecting pedestrians based on mobile data and GPS base station information, with key variables including travel speed, time, distance, and departure time. Pedestrian groups are categorized into main and access modes based on whether they go to a destination and use transportation vehicles.
TRANSPORTMETRICA A-TRANSPORT SCIENCE
(2023)
Article
Agriculture, Dairy & Animal Science
Eunkyung Choi, Seung Jae Lee, Euna Jo, Jinmu Kim, Steven J. Parker, Jeong-Hoon Kim, Hyun Park
Summary: In this study, the genome profile of Patagonian moray cod was characterized using genome survey and microsatellite marker analysis. The results provided genomic data such as genome size and microsatellite motifs, which may facilitate further whole-genome sequencing and population genetics research.
Article
Construction & Building Technology
Sang-Hyun Park, Ngoc Hieu Dinh, Seung-Hee Kim, Ji-Woo Hwang, Huu Hiep Pham, Seung-Jae Lee, Kyoung-Kyu Choi
Summary: In this study, a practical seismic retrofit technique using precast panels of fiber-reinforced cementitious composites (FRCC) was developed for unreinforced masonry (URM) walls. The test results show that the URM walls retrofitted with the proposed shear keys and reinforcement details exhibited significant improvement in terms of load-carrying capacity, deformation capacity, stiffness degradation, and energy dissipation capacity. Specimens with additional reinforcement also showed increased load-carrying capacity.
JOURNAL OF BUILDING ENGINEERING
(2022)
Article
Chemistry, Analytical
Seungjae Lee, Ho Bin Hwang, Seongryul Park, Sanghag Kim, Jung Hee Ha, Yoojin Jang, Sejin Hwang, Hoon-Ki Park, Jongshill Lee, In Young Kim
Summary: This study introduces new features based on heart rate variability (HRV) and detects acute mental stress through short-term and ultra-short-term HRV analysis. A SVM classification model effectively distinguishes stress and non-stress states, achieving high classification accuracies. Ultra-short-term HRV analysis provides insight into the optimal duration for detecting mental stress, with potential applications in wearable devices or healthcare systems.
Article
Chemistry, Applied
Wonjin Jeon, Ji-Yeon Park, Min-Cheol Kim, Seung-Jae Lee, Deog-Keun Kim
Summary: Various transition metal-based Al2O3 catalysts show significantly different activities in the epoxidation of methyl oleate using H2O2 and O2 as oxidants. The reactivity in H2O2-based epoxidation is proportional to the acidity of the catalysts, while in O2-based epoxidation, it depends on the redox properties of the catalysts and O2 behavior on the catalyst surface. Mo and Cu-based catalysts exhibit outstanding performance with H2O2 and O2 via different reaction pathways. These findings provide valuable insights for designing catalytic reaction processes based on the type of oxidizing agent.
Article
Engineering, Civil
Donggyun Ku, Minje Choi, Haram Oh, Sungyoung Na, Seungjae Lee
Summary: Recently, the need to redefine the modal split model has arisen due to the diversification of transportation systems. This paper proposes a modal split model that reflects the characteristics and preferences of passengers by applying latent class analysis.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Thermodynamics
Minje Choi, DongGyun Ku, Sion Kim, Juhyeon Kwak, Yoonjung Jang, Doyun Lee, Seungjae Lee
Summary: Personal Mobility (PM) in Seoul, South Korea has gained popularity as an eco-friendly mode of transportation. However, there is a risk of collision when riding PM vehicles on sidewalks. Studies have been conducted to create a safer environment through the use of PM-only lanes and PM-based playgrounds. The implementation of PM-only lanes can lead to a reduction in vehicle kilometers traveled and contribute to environmental benefits. Similarly, creating PM-based playgrounds can promote safer driving through education and data collection. These measures have the potential to activate public transportation usage and reduce energy consumption while ensuring safety and convenience.
Article
Engineering, Civil
Sion Kim, Donggyun Ku, Seungjae Lee
Summary: This study applies percolation theory to analyze the connectivity of transportation networks. It explores the impact of penalties on network travel time by imposing wait times on public transportation nodes. The results demonstrate that penalizing transfer stations has a significant and global effect on travel time, and using a trip frequency weight increases the impact of penalties on medium- or short-timed trips. These findings could inform the development of quarantine policies for controlling public transportation networks.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Engineering, Civil
Yoonjung Jang, Donggyun Ku, Minje Choi, Dahye Kim, Doyun Lee, Seungjae Lee
Summary: Since being declared a pandemic by the World Health Organization in March 2020, Covid-19 has had a significant impact on daily life. Studies in Korea have shown a decrease in public transportation use, particularly during widespread infection. Additionally, the number of people shopping in commercial districts has significantly decreased. This study analyzes the factors influencing the spread of Covid-19, including transportation demand, revitalization of commercial districts, population movement, and socio-economic indicators, aiming to identify infection factors in different districts of Seoul and provide a foundation for proactive measures to control infectious diseases.
PROCEEDINGS OF THE INSTITUTION OF CIVIL ENGINEERS-MUNICIPAL ENGINEER
(2023)
Article
Engineering, Civil
Donggyun Ku, Dahye Kim, Seungjae Lee
Summary: This paper aims to clarify the differences in the factors influencing subway traffic behaviour of senior passengers and non-senior passengers during the Covid-19 pandemic in Seoul, South Korea, using big data. The study analyzes the influencing factors of subway use and identifies the factors affecting senior passengers and non-senior passengers through statistical analysis and regression models. The results show that senior passengers are more affected by subway use, with cultural gathering facilities and the number of subway stations being the most influential factors. The regression model has high explanatory power in southern Seoul, where the influencing factors are concentrated.
PROCEEDINGS OF THE INSTITUTION OF CIVIL ENGINEERS-MUNICIPAL ENGINEER
(2023)
Article
Multidisciplinary Sciences
Ilho Jeong, Minje Choi, Juhyeon Kwak, Donggyun Ku, Seungjae Lee
Summary: This study develops a walkability evaluation system considering the characteristics of a large city and calculates the walkability of Seoul. It finds that considering high betweenness stations and UNA index is essential for evaluating a pedestrian-oriented metropolis. Setting a mobility hub or station at a high-value location in the city center is functionally important for a walkable city.
SCIENTIFIC REPORTS
(2023)
Article
Energy & Fuels
Madiha Bencekri, Donggyun Ku, Doyun Lee, Yee Van Fan, Jiri Jaromir Klemes, Petar Sabev Varbanov, Seungjae Lee
Summary: This study fills the knowledge gaps in evaluating the effectiveness of transport carbon policies and offers a comprehensive comparative overview. Mobility hubs and electric vehicles are considered the most effective policies, while shared bikes and hydrogen vehicles rank lower.
ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS
(2023)
Review
Computer Science, Artificial Intelligence
Wei Gao, Shuangshuang Ge
Summary: This study provides a comprehensive review of slope stability research based on artificial intelligence methods, focusing on slope stability computation and evaluation. The review covers studies using quasi-physical intelligence methods, simulated evolutionary methods, swarm intelligence methods, hybrid intelligence methods, artificial neural network methods, vector machine methods, and other intelligence methods. The merits, demerits, and state-of-the-art research advancement of these studies are analyzed, and possible research directions for slope stability investigation based on artificial intelligence methods are suggested.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Khuong Le Nguyen, Hoa Thi Trinh, Saeed Banihashemi, Thong M. Pham
Summary: This study investigated the influence of input parameters on the shear strength of RC squat walls and found that ensemble learning models, particularly XGBoost, can effectively predict the shear strength. The axial load had a greater influence than reinforcement ratio, and longitudinal reinforcement had a more significant impact compared to horizontal and vertical reinforcement. The performance of XGBoost model outperforms traditional design models and reducing input features still yields reliable predictions.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Bo Hu, Huiyan Zhang, Xiaoyi Wang, Li Wang, Jiping Xu, Qian Sun, Zhiyao Zhao, Lei Zhang
Summary: A deep hierarchical echo state network (DHESN) is proposed to address the limitations of shallow coupled structures. By using transfer entropy, candidate variables with strong causal relationships are selected and a hierarchical reservoir structure is established to improve prediction accuracy. Simulation results demonstrate that DHESN performs well in predicting algal bloom.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Limin Wang, Lingling Li, Qilong Li, Kuo Li
Summary: This paper discusses the urgency of learning complex multivariate probability distributions due to the increase in data variability and quantity. It introduces a highly scalable classifier called TAN, which utilizes maximum weighted spanning tree (MWST) for graphical modeling. The paper theoretically proves the feasibility of extending one-dependence MWST to model high-dependence relationships and proposes a heuristic search strategy to improve the fitness of the extended topology to data. Experimental results demonstrate that this algorithm achieves a good bias-variance tradeoff and competitive classification performance compared to other high-dependence or ensemble learning algorithms.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Zhejing Hu, Gong Chen, Yan Liu, Xiao Ma, Nianhong Guan, Xiaoying Wang
Summary: Anxiety is a prevalent issue and music therapy has been found effective in reducing anxiety. To meet the diverse needs of individuals, a novel model called the spatio-temporal therapeutic music transfer model (StTMTM) is proposed.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Nur Ezlin Zamri, Mohd. Asyraf Mansor, Mohd Shareduwan Mohd Kasihmuddin, Siti Syatirah Sidik, Alyaa Alway, Nurul Atiqah Romli, Yueling Guo, Siti Zulaikha Mohd Jamaludin
Summary: In this study, a hybrid logic mining model was proposed by combining the logic mining approach with the Modified Niche Genetic Algorithm. This model improves the generalizability and storage capacity of the retrieved induced logic. Various modifications were made to address other issues. Experimental results demonstrate that the proposed model outperforms baseline methods in terms of accuracy, precision, specificity, and correlation coefficient.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
David Jacob Kedziora, Tien-Dung Nguyen, Katarzyna Musial, Bogdan Gabrys
Summary: The paper addresses the problem of efficiently optimizing machine learning solutions by reducing the configuration space of ML pipelines and leveraging historical performance. The experiments conducted show that opportunistic/systematic meta-knowledge can improve ML outcomes, and configuration-space culling is optimal when balanced. The utility and impact of meta-knowledge depend on various factors and are crucial for generating informative meta-knowledge bases.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
G. Sophia Jasmine, Rajasekaran Stanislaus, N. Manoj Kumar, Thangamuthu Logeswaran
Summary: In the context of a rapidly expanding electric vehicle market, this research investigates the ideal locations for EV charging stations and capacitors in power grids to enhance voltage stability and reduce power losses. A hybrid approach combining the Fire Hawk Optimizer and Spiking Neural Network is proposed, which shows promising results in improving system performance. The optimization approach has the potential to enhance the stability and efficiency of electric grids.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Zhijiang Wu, Guofeng Ma
Summary: This study proposes a natural language processing-based framework for requirement retrieval and document association, which can help to mine and retrieve documents related to project managers' requirements. The framework analyzes the ontology relevance and emotional preference of requirements. The results show that the framework performs well in terms of iterations and threshold, and there is a significant matching between the retrieved documents and the requirements, which has significant managerial implications for construction safety management.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Yung-Kuan Chan, Chuen-Horng Lin, Yuan-Rong Ben, Ching-Lin Wang, Shu-Chun Yang, Meng-Hsiun Tsai, Shyr-Shen Yu
Summary: This study proposes a novel method for dog identification using nose-print recognition, which can be applied to controlling stray dogs, locating lost pets, and pet insurance verification. The method achieves high recognition accuracy through two-stage segmentation and feature extraction using a genetic algorithm.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Shaohua Song, Elena Tappia, Guang Song, Xianliang Shi, T. C. E. Cheng
Summary: This study aims to optimize supplier selection and demand allocation decisions for omni-channel retailers in order to achieve supply chain resilience. It proposes a two-phase approach that takes into account various factors such as supplier evaluation and demand allocation.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Jinyan Hu, Yanping Jiang
Summary: This paper examines the allocation problem of shared parking spaces considering parking unpunctuality and no-shows. It proposes an effective approach using sample average approximation (SAA) combined with an accelerating Benders decomposition (ABD) algorithm to solve the problem. The numerical experiments demonstrate the significance of supply-demand balance for the operation and user satisfaction of the shared parking system.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Review
Computer Science, Artificial Intelligence
Soroor Motie, Bijan Raahemi
Summary: Financial fraud is a persistent problem in the finance industry, but Graph Neural Networks (GNNs) have emerged as a powerful tool for detecting fraudulent activities. This systematic review provides a comprehensive overview of the current state-of-the-art technologies in using GNNs for financial fraud detection, identifies gaps and limitations in existing research, and suggests potential directions for future research.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Review
Computer Science, Artificial Intelligence
Enhao Ning, Changshuo Wang, Huang Zhang, Xin Ning, Prayag Tiwari
Summary: This review provides a detailed overview of occluded person re-identification methods and conducts a systematic analysis and comparison of existing deep learning-based approaches. It offers important theoretical and practical references for future research in the field.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Jiajun Ma, Songyu Hu, Jianzhong Fu, Gui Chen
Summary: The article presents a novel visual hierarchical attention detector for multi-scale defect location and classification, utilizing texture, semantic, and instance features of defects through a hierarchical attention mechanism, achieving multi-scale defect detection in bearing images with complex backgrounds.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
