Query：
学者姓名：郑相涵
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract ：
The Parkinson’s disease gait classification method proposed in this paper consists of five steps. Firstly, gait data collection includes gait videos of both normal individuals and Parkinson’s patients provided by the Gait Laboratory of Fujian University of Traditional Chinese Medicine. After gait data collection, preprocessing of the data is conducted, including data augmentation, cropping, resizing, and adding dynamic blur. Next, the Attention-LSTM model is constructed to effectively capture long-term dependencies in time series. After training and testing, the model can achieve effective classification of normal individuals and Parkinson’s patients based on gait video data, yielding results. The experiments demonstrate that the model constructed in this paper outperforms baseline models and previous Parkinson’s disease classification studies based on video data. Our research reduces the difficulty and cost of gait data collection, enabling contactless gait analysis. This will further reduce the complexity and cost of Parkinson’s disease diagnosis and lay a solid foundation for remote diagnosis of Parkinson’s disease. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2025.
Keyword ：
Diagnosis Diagnosis Neurodegenerative diseases Neurodegenerative diseases
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Jianxian , Zheng, Xianghan , Wang, Huan et al. A Parkinson’s Disease Gait Identification Model Based on Attention Mechanism and Long Short-Term Memory Network [C] . 2025 : 251-263 . |
| MLA | Zhang, Jianxian et al. "A Parkinson’s Disease Gait Identification Model Based on Attention Mechanism and Long Short-Term Memory Network" . (2025) : 251-263 . |
| APA | Zhang, Jianxian , Zheng, Xianghan , Wang, Huan , Cai, Jing , Liu, Ying . A Parkinson’s Disease Gait Identification Model Based on Attention Mechanism and Long Short-Term Memory Network . (2025) : 251-263 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Secure group communication in Vehicle Ad hoc Networks (VANETs) over open channels remains a challenging task. To enable secure group communications with conditional privacy, it is necessary to establish a secure session using Authenticated Key Agreement (AKA). However, existing AKAs suffer from problems such as cross-domain dynamic group session key negotiation and heavy computational burdens on the Trusted Authority (TA) and vehicles. To address these challenges, we propose a dynamic privacy-preserving anonymous authentication scheme for condition matching in fog-cloud-based VANETs. The scheme employs general Elliptic Curve Cryptosystem (ECC) technology and fog-cloud computing methods to decrease computational overhead for On-Board Units (OBUs) and supports multiple TAs for improved service quality and robustness. Furthermore, certificateless technology alleviates TAs of key management burdens. The security analysis indicates that our solution satisfies the communication security and privacy requirements. Experimental simulations verify that our method achieves optimal overall performance with lower computational costs and smaller communication overhead compared to state-of-the-art solutions.
Keyword ：
authenticated key agreement authenticated key agreement conditional privacy-preserving conditional privacy-preserving dynamic group dynamic group fog-cloud computing fog-cloud computing VANETs VANETs
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhan, Yonghua , Xie, Weipeng , Shi, Rui et al. Dynamic Privacy-Preserving Anonymous Authentication Scheme for Condition-Matching in Fog-Cloud-Based VANETs [J]. | SENSORS , 2024 , 24 (6) . |
| MLA | Zhan, Yonghua et al. "Dynamic Privacy-Preserving Anonymous Authentication Scheme for Condition-Matching in Fog-Cloud-Based VANETs" . | SENSORS 24 . 6 (2024) . |
| APA | Zhan, Yonghua , Xie, Weipeng , Shi, Rui , Huang, Yunhu , Zheng, Xianghan . Dynamic Privacy-Preserving Anonymous Authentication Scheme for Condition-Matching in Fog-Cloud-Based VANETs . | SENSORS , 2024 , 24 (6) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Semi-supervised learning (SSL) employs unlabeled data with limited labeled samples to enhance deep networks, but imbalance degrades performance due to biased pseudo-labels skewing decision boundaries. To address this challenge, we propose two optimization conditions inspired by our theoretical analysis. These conditions focus on aligning class distributions and representations. Additionally, we introduce a plug-and-play method called Basis Transformation based distribution alignment (BTDA) that efficiently aligns class distributions while considering inter-class relationships. BTDA mitigates the negative impact of biased pseudo-labels through basis transformation, which involves a learnable transition matrix. Extensive experiments demonstrate the effectiveness of integrating existing SSL methods with BTDA in image classification tasks with class imbalance. For example, BTDA achieves accuracy improvements ranging from 2.47 to 6.66% on CIFAR10-LT and SVHN-LT datasets, and a remarkable 10.95% improvement on the tail class, even under high imbalanced rates. Despite its simplicity, BTDA achieves state-of-the-art performance in SSL with class imbalance on representative datasets.
Keyword ：
Basis transformation Basis transformation Class-imbalanced datasets Class-imbalanced datasets Distribution alignment Distribution alignment Image classification Image classification Inter-class bias Inter-class bias Semi-supervised learning Semi-supervised learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Ye, Jinhuang , Gao, Xiaozhi , Li, Zuoyong et al. Btda: basis transformation based distribution alignment for imbalanced semi-supervised learning [J]. | INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS , 2024 , 15 (9) : 3829-3845 . |
| MLA | Ye, Jinhuang et al. "Btda: basis transformation based distribution alignment for imbalanced semi-supervised learning" . | INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 15 . 9 (2024) : 3829-3845 . |
| APA | Ye, Jinhuang , Gao, Xiaozhi , Li, Zuoyong , Wu, Jiawei , Xu, Xiaofeng , Zheng, Xianghan . Btda: basis transformation based distribution alignment for imbalanced semi-supervised learning . | INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS , 2024 , 15 (9) , 3829-3845 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Semi-supervised learning (SSL) is a successful paradigm that can use unlabelled data to alleviate the labelling cost problem in supervised learning. However, the excellent performance brought by SSL does not transfer well to the task of class imbalance. The reason is that the class bias of pseudo-labelling further misleads the decision boundary. To solve this problem, we propose a new plug-and-play approach to handle the class imbalance problem based on a theoretical extension and analysis of distribution alignment. The method, called Basis Transformation Based Distribution Alignment (BTDA), efficiently aligns class distributions while taking into account inter-class relationships.BTDA implements the basis transformation through a learnable transfer matrix, thereby reducing the performance loss caused by pseudo-labelling biases. Extensive experiments show that our proposed BTDA approach can significantly improve performance in class imbalance tasks in terms of both accuracy and recall metrics when integrated with advanced SSL algorithms. Although the idea of BTDA is not complex, it can show advanced performance on datasets such as CIFAR and SVHN. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.
Keyword ：
Classification (of information) Classification (of information) Image classification Image classification Linear transformations Linear transformations Machine learning Machine learning Transfer matrix method Transfer matrix method
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Ye, Jinhuang , Wu, Jiawei , Li, Zuoyong et al. Rethinking Distribution Alignment for Inter-class Fairness [C] . 2024 : 10-21 . |
| MLA | Ye, Jinhuang et al. "Rethinking Distribution Alignment for Inter-class Fairness" . (2024) : 10-21 . |
| APA | Ye, Jinhuang , Wu, Jiawei , Li, Zuoyong , Zheng, Xianghan . Rethinking Distribution Alignment for Inter-class Fairness . (2024) : 10-21 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Numerous users from diverse domains access information and perform various operations in multi-domain environments. These users have complex permissions that increase the risk of identity falsification, unauthorized access, and privacy breaches during cross-domain interactions. Consequently, implementing an access control architecture to prevent users from engaging in illicit activities is imperative. This paper proposes a novel blockchain-based access control architecture for multi-domain environments. By integrating the multi-domain environment within a federated chain, the architecture utilizes Decentralized Identifiers (DIDs) for user identification and relies on public/secret key pairs for operational execution. Verifiable credentials are used to authorize permissions and release resources, thereby ensuring authentication and preventing tampering and forgery. In addition, the architecture automates the authorization and access control processes through smart contracts, thereby eliminating human intervention. Finally, we performed a simulation evaluation of the architecture. The most time-consuming process had a runtime of 1074 ms, primarily attributed to interactions with the blockchain. Concurrent testing revealed that with a concurrency level of 2000 demonstrated that the response times for read and write operations were maintained within 1000 ms and 4600 ms, respectively. In terms of storage efficiency, except for user registration, which incurred two gas charges, all the other processes required only one charge.
Keyword ：
Access control Access control Blockchain Blockchain DIDs DIDs Multi-domain environments Multi-domain environments Smart contracts Smart contracts Verifiable credentials Verifiable credentials
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Du, Zhiqiang , Li, Yunliang , Fu, Yanfang et al. Blockchain-based access control architecture for multi-domain environments [J]. | PERVASIVE AND MOBILE COMPUTING , 2024 , 98 . |
| MLA | Du, Zhiqiang et al. "Blockchain-based access control architecture for multi-domain environments" . | PERVASIVE AND MOBILE COMPUTING 98 (2024) . |
| APA | Du, Zhiqiang , Li, Yunliang , Fu, Yanfang , Zheng, Xianghan . Blockchain-based access control architecture for multi-domain environments . | PERVASIVE AND MOBILE COMPUTING , 2024 , 98 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
With the rapid development of Ethereum, vast amounts of data are recorded on the blockchain through transactions, encompassing diverse and extensive textual information. While Long Short-Term Memory (LSTM) models have shown remarkable effectiveness in sentiment analysis tasks in recent years, they often encounter situations where different features have equal importance when processing such textual data. Therefore, this study introduces a Bidirectional LSTM model with a Multi-Head Attention mechanism (MABLSTM) designed for sentiment analysis tasks in Ethereum transaction texts. BLSTM consists of two distinct and independent LSTMs that consider information flow from two directions, capturing contextual information from both the past and the future. The outputs from the BLSTM layer are enhanced using a multi-head attention mechanism to amplify the importance of sentiment words and blockchain-specific terms. This paper evaluates the effectiveness of MABLSTM on Ethereum transaction data through experiments conducted on an Ethereum transaction dataset, comparing MABLSTM with CNN, SVM, ABLSTM and ABCDM. The results demonstrate the effectiveness and superiority of MABLSTM in sentiment analysis tasks. This approach accurately analyzes sentiment polarity in Ethereum transaction texts, providing valuable information for Ethereum participants and researchers to support decision-making and emotional analysis.
Keyword ：
Attention Mechanism Attention Mechanism BLSTM BLSTM Deep Learning Deep Learning Ethereum Ethereum MABLST MABLST Sentiment Analysis Sentiment Analysis
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zheng, Xianghan , Zhang, Wenyan , Zhang, Jianxian et al. Ethereum Public Opinion Analysis Based on Attention Mechanism [J]. | COGNITIVE COMPUTING - ICCC 2023 , 2024 , 14207 : 100-115 . |
| MLA | Zheng, Xianghan et al. "Ethereum Public Opinion Analysis Based on Attention Mechanism" . | COGNITIVE COMPUTING - ICCC 2023 14207 (2024) : 100-115 . |
| APA | Zheng, Xianghan , Zhang, Wenyan , Zhang, Jianxian , Xie, Weipeng . Ethereum Public Opinion Analysis Based on Attention Mechanism . | COGNITIVE COMPUTING - ICCC 2023 , 2024 , 14207 , 100-115 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Objective In large-scale motion simulation problems, the search efficiency for nearest neighbor points critically influences the overall operational efficiency. This study applies correlation analysis to establish an adaptive relationship between the maximum depth of the kd-tree (dmax) and the total number of particles (N). A novel automatic termination criterion for the kd-tree, known as ATC-kd-tree, addresses the impact of the leaf node size threshold (n0) on nearest neighbor search efficiency. This method effectively addresses the challenges of recalibrating dmax as N varies, enhancing the efficiency and applicability of the kd-tree in various scenarios. Methods The ATC-kd-tree framework is designed to dynamically adjust the kd-tree structure based on the current particle count, ensuring optimal performance for efficient searches in real-time applications. This method involves a comprehensive analysis of particle distributions, enabling the algorithm to adaptively modify dmax based on the specific characteristics of the particle set at any given time. The ATC-kd-tree effectively responds to the spatial arrangement of particles, enhancing search accuracy and speed by integrating data-driven adjustments. In addition, a two-step parameter optimization algorithm that combines grid search with coordinate descent methods (GSCD) is introduced. This hybrid approach expedites the calibration of variable parameters crucial for optimizing ATC-kd-tree performance, facilitating a more precise search process. The GSCD method accelerates the pace of parameter adjustment and increases accuracy by ensuring that the most appropriate parameters are selected based on empirical evidence. A comprehensive series of experimental trials is conducted involving various particle distribution models, such as uniform, random, and clustered configurations. These trials are designed to assess the efficiency of the ATC-kd-tree and the GSCD optimization process. Key performance metrics, including search time, cache miss rates, and overall computational efficiency, are diligently monitored and analyzed. Rigorous comparisons against baseline methods, comprising traditional kd-trees and alternative sorting algorithms, are executed to ensure a thorough evaluation of the proposed techniques. Results and Discussions The study’s findings demonstrated that the ATC-kd-tree framework significantly improves the efficiency of nearest neighbor searches, especially in large-scale motion simulations characterized by dynamically fluctuating particle distributions. Experiments involving particle distribution shapes, such as rectangular, cuboidal, notched cuboidal, spherical, and annular, are frequently employed in fluid dynamics studies to corroborate their efficiency. The ATC-kd-tree achieved an impressive average reduction in search time of up to 30.3% compared to traditional unsorted kd-tree implementations across all tested configurations. When analyzing datasets comprising 40 000 and 575 000 particles, the search times exhibit significant enhancement: the ATC-kd-tree reduces the search time from 1.75 seconds with traditional methods to 1.22 seconds for the former dataset and from 7.12 seconds to 4.97 seconds for the latter. This performance improvement is particularly marked in environments with high spatial divergence among particles, where traditional methods often falter with inconsistent search paths. In addition, an average reduction of 24.2% in cache miss rates is observed when employing the ATC-kd-tree. In scenarios with larger particle counts, the cache miss rate decreases from 35% in the traditional unsorted kd-tree to 26% with the ATC-kd-tree, which directly contributes to enhanced computational efficiency, facilitating quicker data retrieval during neighbor searches. The ATC-kd-tree demonstrated exceptional adaptability to rapidly evolving particle configurations in computational fluid dynamics (CFD) simulations. In a specific experiment involving 50 000 particles exposed to external forces causing irregular movements, the ATC-kd-tree shows a 20% reduction in cache misses and a 15% decrease in overall computational time compared to traditional methods. This capacity to effectively manage irregular particle movements underscores the ATC-kd-tree’s robustness for real-time applications that demand rapid adaptability to dynamic changes. The GSCD optimization method further augments the performance of the ATC-kd-tree, as the analysis indicates that GSCD accelerates parameter calibration by 205% relative to traditional grid search methods. In experiments, the GSCD method reduces calibration time significantly, from over 120 seconds in traditional methods to approximately 40 seconds. This enhancement enables rapid adjustments to the parameters of the kd-tree and ensures that the tree remains optimally configured to the specific characteristics of the particle distributions encountered during simulations. The adaptability of the ATC-kd-tree is evident across various particle distribution scenarios. This algorithm consistently surpasses traditional unsorted kd-trees and alternative sorting methods in clustered configurations, such as the Z-index sort. In these configurations, the search time is significantly reduced, demonstrating the ATC-kd-tree’ s ability to dynamically reorganize its structure based on real-time analysis of particle distributions. This capability maximizes cache utilization and minimizes cache misses. The findings indicated that the ATC-kd-tree is particularly effective in scenarios involving non-uniform particle distributions, as its capacity to adjust dmax based on the number of particles eliminates the cumbersome recalibration processes typically required by traditional methods. Hence, this leads to a smoother and more efficient search process, even as particle distributions experience significant changes. These results highlight the critical importance of incorporating adaptive techniques into kd-tree implementations to improve search efficiency in large-scale simulations. The improvements in search time and cache utilization achieved by the ATC-kd-tree provide compelling evidence of its potential to transform how nearest neighbor searches are conducted in dynamic environments. Conclusions The introduction of the ATC-kd-tree provides a valuable approach to optimizing kd-tree-based nearest neighbor searches, particularly in dynamic and large-scale motion simulations. This research aims to enhance search efficiency and deliver a scalable solution for managing varying particle distributions by integrating an automatic termination criterion with a rapid parameter optimization method. The results showed that the ATC-kd-tree can improve operational performance, reducing computational overhead and cache misses, which is crucial for real-time applications where efficiency is paramount. In addition, the principles explored in this study can extend beyond the kd-tree framework, demonstrating new avenues for research into adaptive data access techniques that can prove beneficial across various computational domains, including machine learning, computer graphics, and robotics. Future efforts will concentrate on integrating the ATC-kd-tree with advanced cache management strategies to optimize performance and investigate methods to reduce computational complexity in high-dimensional contexts, which remains a critical area of investigation. This study aims to address these challenges and broaden the applicability of kd-tree methods in real-time environments, making them more adaptable to complex and dynamic conditions. It contributes to enhancing the functionality of kd-trees and provides insights into the broader field of data structure optimization, laying a foundation for future developments in efficient data processing techniques. © 2024 Sichuan University. All rights reserved.
Keyword ：
Adaptive algorithms Adaptive algorithms Adaptive boosting Adaptive boosting Convergence of numerical methods Convergence of numerical methods Decision trees Decision trees Flow visualization Flow visualization Image segmentation Image segmentation Nearest neighbor search Nearest neighbor search
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Ting , Wang, Zongkai , Lin, Zhenhuan et al. Improved Kd-tree Particle Nearest Neighbor Search Based on Automatic Termination Criterion [J]. | Advanced Engineering Sciences , 2024 , 56 (6) : 217-229 . |
| MLA | Zhang, Ting et al. "Improved Kd-tree Particle Nearest Neighbor Search Based on Automatic Termination Criterion" . | Advanced Engineering Sciences 56 . 6 (2024) : 217-229 . |
| APA | Zhang, Ting , Wang, Zongkai , Lin, Zhenhuan , Zheng, Xianghan . Improved Kd-tree Particle Nearest Neighbor Search Based on Automatic Termination Criterion . | Advanced Engineering Sciences , 2024 , 56 (6) , 217-229 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
对于大规模运动模拟问题而言,近邻点的搜索效率将对整体的运算效率产生显著影响.本文基于关联性分析建立kd-tree的最大深度dmax与粒子总数N的自适应关系式,提出了kd-tree自动终止准则,即ATC-kd-tree,同时还考虑了叶子节点大小阈值no对近邻搜索效率的影响.试验表明,ATC-kd-tree具有更高的近邻搜索效率,相较于不使用自动终止准则的kd-tree搜索效率最高提升46％,且适用性更强,可求解不同N值的近邻搜索问题,解决了粒子总数N发生改变时需要再次率定最大深度dmax的问题.同时,本文还提出了网格搜索法组合坐标下降法的两步参数优化算法GSCD法.通过2维阿米巴虫形状的参数优化试验发现,GSCD法可更为快速地率定ATC-kd-tree的可变参数,其优化效率比网格搜索法最高提升了205％,相较于改进网格搜索法最高提升了90％.研究结果表明,ATC-kd-tree和GSCD法不仅提高了近邻搜索的效率,也为复杂运动中近邻粒子搜索问题提供了一种更为高效的解决方案,能够显著降低计算资源的消耗,进一步提升模拟的精度和效率.
Keyword ：
kd-tree kd-tree 坐标下降法 坐标下降法 粒子近邻搜索 粒子近邻搜索 网格搜索法 网格搜索法 自适应 自适应
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 张挺 , 王宗锴 , 林震寰 et al. 基于自动终止准则改进的kd-tree粒子近邻搜索研究 [J]. | 工程科学与技术 , 2024 , 56 (6) : 217-229 . |
| MLA | 张挺 et al. "基于自动终止准则改进的kd-tree粒子近邻搜索研究" . | 工程科学与技术 56 . 6 (2024) : 217-229 . |
| APA | 张挺 , 王宗锴 , 林震寰 , 郑相涵 . 基于自动终止准则改进的kd-tree粒子近邻搜索研究 . | 工程科学与技术 , 2024 , 56 (6) , 217-229 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Face recognition technology is widely used in various fields, such as law enforcement, payment systems, transportation, and access control. Traditional face authentication systems typically establish a facial feature template database for identity verification. However, this approach poses various security risks, such as the risk of plaintext feature data stored in cloud databases being leaked or stolen. To address these issues, in recent years, a face recognition technology based on homomorphic encryption has gained attention. Based on homomorphic encryption, face recognition can encrypt facial feature values and achieve feature matching without exposing the feature information. However, due to the encryption, face recognition in the ciphertext domain often requires considerable time. In this paper, we introduce the big data stream processing engine Flink to achieve parallel computation of face recognition in the ciphertext domain based on homomorphic encryption. We analyze the security, accuracy, and acceleration of this approach. Ultimately, we verify that this approach achieves recognition accuracy close to plaintext and significant efficiency improvement. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.
Keyword ：
Access control Access control Face recognition Face recognition Privacy-preserving techniques Privacy-preserving techniques
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wang, Gong , Zheng, Xianghan , Zeng, Lingjing et al. A Privacy-Preserving Face Recognition Scheme Combining Homomorphic Encryption and Parallel Computing [C] . 2024 : 38-52 . |
| MLA | Wang, Gong et al. "A Privacy-Preserving Face Recognition Scheme Combining Homomorphic Encryption and Parallel Computing" . (2024) : 38-52 . |
| APA | Wang, Gong , Zheng, Xianghan , Zeng, Lingjing , Xie, Weipeng . A Privacy-Preserving Face Recognition Scheme Combining Homomorphic Encryption and Parallel Computing . (2024) : 38-52 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Sorting is an important construction waste management tool to increase recycling rates and reduce pollution. Previous studies have used robots to improve the efficiency of construction waste recycling. However, in large construction sites, it is difficult for a single robot to accomplish the task quickly, and multiple robots working together are a better option. Most construction waste recycling robotic systems are developed based on a client-server framework, which means that all robots need to be continuously connected to their respective cloud servers. Such systems are low in robustness in complex environments and waste a lot of computational resources. Therefore, in this paper, we propose a pixel-level automatic construction waste recognition platform with high robustness and low computational resource requirements by combining multiple computer vision technologies with edge computing and cloud computing platforms. Experiments show that the computing platform proposed in this study can achieve a recognition speed of 23.3 fps and a recognition accuracy of 90.81% at the edge computing platform without the help of network and cloud servers. This is 23 times faster than the algorithm used in previous research. Meanwhile, the computing platform proposed in this study achieves 93.2% instance segmentation accuracy on the cloud server side. Notably, this system allows multiple robots to operate simultaneously at the same construction site using only a single server without compromising efficiency, which significantly reduces costs and promotes the adoption of automated construction waste recycling robots.
Keyword ：
cloud computing cloud computing computer vision computer vision construction waste management construction waste management edge computing edge computing multi-robot multi-robot waste recycling waste recycling
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wang, Zeli , Yang, Xincong , Zheng, Xianghan et al. Computer Vision System for Multi-Robot Construction Waste Management: Integrating Cloud and Edge Computing [J]. | BUILDINGS , 2024 , 14 (12) . |
| MLA | Wang, Zeli et al. "Computer Vision System for Multi-Robot Construction Waste Management: Integrating Cloud and Edge Computing" . | BUILDINGS 14 . 12 (2024) . |
| APA | Wang, Zeli , Yang, Xincong , Zheng, Xianghan , Huang, Daoyin , Jiang, Binfei . Computer Vision System for Multi-Robot Construction Waste Management: Integrating Cloud and Edge Computing . | BUILDINGS , 2024 , 14 (12) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
