Pub Date : 2023-07-01DOI: 10.1109/CSCloud-EdgeCom58631.2023.00059
Shuai Zhang, Xiang Chen, Li Peng
Single-cell sequencing techniques are often impacted by technical noise, leading to the generation of very sparse expression matrices. This technical noise is referred to as dropouts and poses as a major challenge for downstream analysis. In this study, we introduce scIAMC (single-cell imputation via adaptive parameter matrix completion), which is based on matrix completion theory to recover missing values in expression matrices. To expedite the algorithm's running time and avoid any parameter tuning on data, we formulated an optimization problem. Our approach led to an enhanced cell population identification and minimal errors, while also restoring biological landscapes that were damaged by these dropouts.
单细胞测序技术经常受到技术噪声的影响，导致产生非常稀疏的表达矩阵。这种技术噪声被称为遗漏，是下游分析的主要挑战。在本研究中，我们引入scIAMC (single-cell imputation via adaptive parameter matrix补全)，它基于矩阵补全理论来恢复表达矩阵中的缺失值。为了加快算法的运行速度，避免对数据进行任何参数调整，我们制定了一个优化问题。我们的方法增强了细胞群的识别和最小的错误，同时也恢复了被这些辍学破坏的生物景观。
{"title":"scIAMC:Single-Cell Imputation via adaptive matrix completion","authors":"Shuai Zhang, Xiang Chen, Li Peng","doi":"10.1109/CSCloud-EdgeCom58631.2023.00059","DOIUrl":"https://doi.org/10.1109/CSCloud-EdgeCom58631.2023.00059","url":null,"abstract":"Single-cell sequencing techniques are often impacted by technical noise, leading to the generation of very sparse expression matrices. This technical noise is referred to as dropouts and poses as a major challenge for downstream analysis. In this study, we introduce scIAMC (single-cell imputation via adaptive parameter matrix completion), which is based on matrix completion theory to recover missing values in expression matrices. To expedite the algorithm's running time and avoid any parameter tuning on data, we formulated an optimization problem. Our approach led to an enhanced cell population identification and minimal errors, while also restoring biological landscapes that were damaged by these dropouts.","PeriodicalId":56007,"journal":{"name":"Journal of Cloud Computing-Advances Systems and Applications","volume":"23 1","pages":"305-310"},"PeriodicalIF":4.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81656829","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-01DOI: 10.1109/CSCloud-EdgeCom58631.2023.00032
Shao-Jie Sun, Linshu Chen, Benshan Mei, Tao Li, Xue-Qi Ye, Min Shi
Because of the problems that the fast k-Medoids clustering algorithm does not consider the weight of each attribute and the initial clustering center may be in the same cluster, this paper proposes a weighted $boldsymbol{k}$-Medoids clustering algorithm based on granular computing. Firstly, the hierarchical structure in the fuzzy quotient space theory is introduced to define the decision attribute of the sample under each granularity, and the computing method of sample attribute weight is defined by the attributes of the sample set itself and the definition of attribute importance in the rough set model. Secondly, the sample similarity function is defined by the attribute weight coefficient, and the attribute weight is integrated into the similarity of the fast k-Medoids clustering algorithm to quantitatively define the importance of each sample's attribute. Finally, from the prospective view of granular computing, the samples are clustered according to the above similarity function, and the original clustering centers are initialized by K cluster centers with long distance. The experimental results on machine learning datasets UCI show that the proposed weighted k-Medoids clustering algorithm based on granular computing greatly improves the accuracy of clustering.
{"title":"A Weighted k-Medoids Clustering Algorithm Based on Granular Computing","authors":"Shao-Jie Sun, Linshu Chen, Benshan Mei, Tao Li, Xue-Qi Ye, Min Shi","doi":"10.1109/CSCloud-EdgeCom58631.2023.00032","DOIUrl":"https://doi.org/10.1109/CSCloud-EdgeCom58631.2023.00032","url":null,"abstract":"Because of the problems that the fast k-Medoids clustering algorithm does not consider the weight of each attribute and the initial clustering center may be in the same cluster, this paper proposes a weighted $boldsymbol{k}$-Medoids clustering algorithm based on granular computing. Firstly, the hierarchical structure in the fuzzy quotient space theory is introduced to define the decision attribute of the sample under each granularity, and the computing method of sample attribute weight is defined by the attributes of the sample set itself and the definition of attribute importance in the rough set model. Secondly, the sample similarity function is defined by the attribute weight coefficient, and the attribute weight is integrated into the similarity of the fast k-Medoids clustering algorithm to quantitatively define the importance of each sample's attribute. Finally, from the prospective view of granular computing, the samples are clustered according to the above similarity function, and the original clustering centers are initialized by K cluster centers with long distance. The experimental results on machine learning datasets UCI show that the proposed weighted k-Medoids clustering algorithm based on granular computing greatly improves the accuracy of clustering.","PeriodicalId":56007,"journal":{"name":"Journal of Cloud Computing-Advances Systems and Applications","volume":"64 1","pages":"138-143"},"PeriodicalIF":4.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78574398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-01DOI: 10.1109/CSCloud-EdgeCom58631.2023.00083
Weihong Huang, Kuan Jiang, Jing Huang, Lisi F. Lisi, Yufeng Xiao, Zihao Deng
Energy saving has become a key issue for heterogeneous embedded systems. Previous energy-saving methods attempt to minimize the energy consumption of applications in heterogeneous embedded systems subject to deadline constraints by reducing the processor frequency. However, good scheduling strategy can also minimize energy consumption to some extent. This paper proposes a novel energy-saving scheduling algorithm, called the Energy-saving Processors Two-phases Frequency Reduction (EPTFR) Algorithm. In the first stage, within the deadline constraints, the maximum working frequency of each processor is reasonably and synchronously reduced; in the second phase, when running sub-applications on the processor, under the constraints of the earliest start time and latest end time of sub-applications, the actual operating frequency of the processor is reasonably reduced. Finally, the effectiveness of the EPTFR algorithm is verified through numerical experiments, and the results show that the proposed EPTFR algorithm can achieve a significant energy-saving effect.
{"title":"Energy-saving Processors Two-phases Frequency Reduction Algorithm on Heterogeneous Embedded Systems","authors":"Weihong Huang, Kuan Jiang, Jing Huang, Lisi F. Lisi, Yufeng Xiao, Zihao Deng","doi":"10.1109/CSCloud-EdgeCom58631.2023.00083","DOIUrl":"https://doi.org/10.1109/CSCloud-EdgeCom58631.2023.00083","url":null,"abstract":"Energy saving has become a key issue for heterogeneous embedded systems. Previous energy-saving methods attempt to minimize the energy consumption of applications in heterogeneous embedded systems subject to deadline constraints by reducing the processor frequency. However, good scheduling strategy can also minimize energy consumption to some extent. This paper proposes a novel energy-saving scheduling algorithm, called the Energy-saving Processors Two-phases Frequency Reduction (EPTFR) Algorithm. In the first stage, within the deadline constraints, the maximum working frequency of each processor is reasonably and synchronously reduced; in the second phase, when running sub-applications on the processor, under the constraints of the earliest start time and latest end time of sub-applications, the actual operating frequency of the processor is reasonably reduced. Finally, the effectiveness of the EPTFR algorithm is verified through numerical experiments, and the results show that the proposed EPTFR algorithm can achieve a significant energy-saving effect.","PeriodicalId":56007,"journal":{"name":"Journal of Cloud Computing-Advances Systems and Applications","volume":"98 1","pages":"452-457"},"PeriodicalIF":4.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84119976","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-01DOI: 10.1109/CSCloud-EdgeCom58631.2023.00057
Zhenzhen Wang, Jia Zhang, Zhihuan Liu, Shaomiao Chen, Danqing Lu
In many computer-aided spinal imaging and disease diagnosis, automating the segmentation of the spine and cones from CT images is a challenging problem. Therefore, in this paper, we propose a triple channel expansion attention segmentation network based on U-Net for spinal CT images. We design a triple channel expansion attention to solve the problem of low accuracy caused by the loss of important feature information in the downsampling process of ordinary convolution, which uses different sizes of convolution set kernels to extract different features. Then through this attention, we output a feature image for each layer of the down-sampling, and finally skip connection with it during the up-sampling. Finally, many experimental results on VerSe 2019 and VerSe 2020 datasets show that our proposed network is superior to other prior art segmentation networks.
{"title":"An improved U-Net network for medical image segmentation","authors":"Zhenzhen Wang, Jia Zhang, Zhihuan Liu, Shaomiao Chen, Danqing Lu","doi":"10.1109/CSCloud-EdgeCom58631.2023.00057","DOIUrl":"https://doi.org/10.1109/CSCloud-EdgeCom58631.2023.00057","url":null,"abstract":"In many computer-aided spinal imaging and disease diagnosis, automating the segmentation of the spine and cones from CT images is a challenging problem. Therefore, in this paper, we propose a triple channel expansion attention segmentation network based on U-Net for spinal CT images. We design a triple channel expansion attention to solve the problem of low accuracy caused by the loss of important feature information in the downsampling process of ordinary convolution, which uses different sizes of convolution set kernels to extract different features. Then through this attention, we output a feature image for each layer of the down-sampling, and finally skip connection with it during the up-sampling. Finally, many experimental results on VerSe 2019 and VerSe 2020 datasets show that our proposed network is superior to other prior art segmentation networks.","PeriodicalId":56007,"journal":{"name":"Journal of Cloud Computing-Advances Systems and Applications","volume":"27 1","pages":"292-297"},"PeriodicalIF":4.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77924302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-01DOI: 10.1109/CSCloud-EdgeCom58631.2023.00047
Shuping Wang, Chongze Lin, Yitong Zheng
As an indispensable technique in the field of information filtering, recommendation systems (RSs) have been well studied and developed both in academia and in industry recently. In this paper, we propose the intimacy among users to obtain a user-item objective rating matrix, which can reflect user’s real interest. For the sake of better predicting ratings, a user-item sub-block is presented to cluster a group of intimate users and a subset of items. Then, the sub-block can be detected through intimacy among users and similarity between items. In order to improve recommendation accuracy, we propose a social contribution degree and social similarity based matrix factorization method to predict scores in sub-block. The final predicted ratings are obtained by combining all sub-blocks. Top- N items with highest predicted scores are recommended to each user. Systematic simulations on real world data set have demonstrated the effectiveness of our proposed approach.
{"title":"Using User-Item Sub-Block to Improve Recommendation Systems","authors":"Shuping Wang, Chongze Lin, Yitong Zheng","doi":"10.1109/CSCloud-EdgeCom58631.2023.00047","DOIUrl":"https://doi.org/10.1109/CSCloud-EdgeCom58631.2023.00047","url":null,"abstract":"As an indispensable technique in the field of information filtering, recommendation systems (RSs) have been well studied and developed both in academia and in industry recently. In this paper, we propose the intimacy among users to obtain a user-item objective rating matrix, which can reflect user’s real interest. For the sake of better predicting ratings, a user-item sub-block is presented to cluster a group of intimate users and a subset of items. Then, the sub-block can be detected through intimacy among users and similarity between items. In order to improve recommendation accuracy, we propose a social contribution degree and social similarity based matrix factorization method to predict scores in sub-block. The final predicted ratings are obtained by combining all sub-blocks. Top- N items with highest predicted scores are recommended to each user. Systematic simulations on real world data set have demonstrated the effectiveness of our proposed approach.","PeriodicalId":56007,"journal":{"name":"Journal of Cloud Computing-Advances Systems and Applications","volume":"54 1","pages":"229-234"},"PeriodicalIF":4.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91155255","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In recent years, with the wide application of CNN in the field of deep learning, the related model of CNN, the Deep Pyramid Convolutional Neural Networks for Text Categorization (DPCNN) model, has emerged, and by the idea of deepening the depth of the network to obtain the best accuracy, DPCNN has made breakthroughs in related fields, especially in the field of text categorization, and its concrete applications in solving practical problems have achieved good results. This paper first introduces the text classification system, then introduces the mainstream model CNN for text classification, after that this paper focuses on the analysis of the DPCNN model, introduces its background and its principle analysis, and introduces the application of DPCNN in specific examples, and finally summarizes and outlooks on DPCNN, emphasizes its application advantages and builds suitable application scenarios.
近年来，随着CNN在深度学习领域的广泛应用，CNN的相关模型——文本分类的深度金字塔卷积神经网络(deep Pyramid Convolutional Neural Networks for Text Categorization, DPCNN)模型应运而生，并通过深化网络深度以获得最佳准确率的思路，DPCNN在相关领域，特别是在文本分类领域取得了突破，其在解决实际问题中的具体应用取得了良好的效果。本文首先介绍了文本分类系统，然后介绍了用于文本分类的主流模型CNN，然后重点分析了DPCNN模型，介绍了其背景和原理分析，并通过具体实例介绍了DPCNN的应用，最后对DPCNN进行了总结和展望，强调了其应用优势，构建了适合的应用场景。
{"title":"DPCNN-based Models for Text Classification","authors":"Meijiao Zhang, Jiacheng Pang, Jiahong Cai, Yingzi Huo, Ce Yang, Huixuan Xiong","doi":"10.1109/CSCloud-EdgeCom58631.2023.00068","DOIUrl":"https://doi.org/10.1109/CSCloud-EdgeCom58631.2023.00068","url":null,"abstract":"In recent years, with the wide application of CNN in the field of deep learning, the related model of CNN, the Deep Pyramid Convolutional Neural Networks for Text Categorization (DPCNN) model, has emerged, and by the idea of deepening the depth of the network to obtain the best accuracy, DPCNN has made breakthroughs in related fields, especially in the field of text categorization, and its concrete applications in solving practical problems have achieved good results. This paper first introduces the text classification system, then introduces the mainstream model CNN for text classification, after that this paper focuses on the analysis of the DPCNN model, introduces its background and its principle analysis, and introduces the application of DPCNN in specific examples, and finally summarizes and outlooks on DPCNN, emphasizes its application advantages and builds suitable application scenarios.","PeriodicalId":56007,"journal":{"name":"Journal of Cloud Computing-Advances Systems and Applications","volume":"103 1","pages":"363-368"},"PeriodicalIF":4.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88139020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-01DOI: 10.1109/CSCloud-EdgeCom58631.2023.00039
Rui-Ding Gao, Lei Jiang, Ziwei Zou, Yuan Li, Yu-Rong Hu
The task of aspect-level sentiment analysis is to identify the sentiment polarity of sentences when expressed in different aspects. The attention mechanism-based approach allows for attentional interaction between the target and context, but it only combines sentences from a semantic perspective, overlooking the syntactic information present in the sentences. Although graph convolutional networks are capable of handling syntactic information well, they are still unable to effectively combine semantic and syntactic information. This paper proposes a sentiment-supported graph convolutional network (SSGCN), which first extracts the semantic information of words using aspect-aware attention and self-attention. Then, the grammar mask matrix and graph convolutional network are used to combine semantic and grammatical information. The features are then split into two parts - one part extracts semantic and syntactic information related to aspect words, and the other part extracts features related to sentiment-supportive words. Finally, the results from the two parts are concatenated to effectively combine semantic and syntactic information. Experimental results show that the proposed model outperforms the benchmark models in terms of accuracy and macro F1 values on three public datasets.
{"title":"A Sentiment-Support Graph Convolutional Network for Aspect-Level Sentiment Analysis","authors":"Rui-Ding Gao, Lei Jiang, Ziwei Zou, Yuan Li, Yu-Rong Hu","doi":"10.1109/CSCloud-EdgeCom58631.2023.00039","DOIUrl":"https://doi.org/10.1109/CSCloud-EdgeCom58631.2023.00039","url":null,"abstract":"The task of aspect-level sentiment analysis is to identify the sentiment polarity of sentences when expressed in different aspects. The attention mechanism-based approach allows for attentional interaction between the target and context, but it only combines sentences from a semantic perspective, overlooking the syntactic information present in the sentences. Although graph convolutional networks are capable of handling syntactic information well, they are still unable to effectively combine semantic and syntactic information. This paper proposes a sentiment-supported graph convolutional network (SSGCN), which first extracts the semantic information of words using aspect-aware attention and self-attention. Then, the grammar mask matrix and graph convolutional network are used to combine semantic and grammatical information. The features are then split into two parts - one part extracts semantic and syntactic information related to aspect words, and the other part extracts features related to sentiment-supportive words. Finally, the results from the two parts are concatenated to effectively combine semantic and syntactic information. Experimental results show that the proposed model outperforms the benchmark models in terms of accuracy and macro F1 values on three public datasets.","PeriodicalId":56007,"journal":{"name":"Journal of Cloud Computing-Advances Systems and Applications","volume":"24 1","pages":"181-185"},"PeriodicalIF":4.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90105173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Blockchain applications have grown tremendously recently, especially in the Decentralized Finance (DeFi) and Non-fungible Token (NFT) markets. The DeFi and NFT markets generate massive transactions and research-worthy data. However, few studies have systematically processed and analyzed them, preventing users from understanding the ecosystem. The main challenge of analyzing the DeFi & NFT markets is the heterogeneity of data that different markets have heterogeneous businesses and data. To address this problem, in this paper, we propose a framework to explore the heterogeneous decentralized markets in DeFi and NFT on the Ethereum blockchain. Based on this framework, we analyze the data of 21 exchange/lending markets in DeFi/NFT, with 184,173,656 records in total. We investigate the activity, profitability, and security of these markets. We obtain several findings to help market users through quantitative analysis. Datasets and codes are released.
{"title":"Exploring Heterogeneous Decentralized Markets in DeFi and NFT on Ethereum Blockchain","authors":"Peilin Zheng, Bowei Su, Zigui Jiang, Chan-Ming Yang, Jiachi Chen, Jiajing Wu","doi":"10.1109/CSCloud-EdgeCom58631.2023.00052","DOIUrl":"https://doi.org/10.1109/CSCloud-EdgeCom58631.2023.00052","url":null,"abstract":"Blockchain applications have grown tremendously recently, especially in the Decentralized Finance (DeFi) and Non-fungible Token (NFT) markets. The DeFi and NFT markets generate massive transactions and research-worthy data. However, few studies have systematically processed and analyzed them, preventing users from understanding the ecosystem. The main challenge of analyzing the DeFi & NFT markets is the heterogeneity of data that different markets have heterogeneous businesses and data. To address this problem, in this paper, we propose a framework to explore the heterogeneous decentralized markets in DeFi and NFT on the Ethereum blockchain. Based on this framework, we analyze the data of 21 exchange/lending markets in DeFi/NFT, with 184,173,656 records in total. We investigate the activity, profitability, and security of these markets. We obtain several findings to help market users through quantitative analysis. Datasets and codes are released.","PeriodicalId":56007,"journal":{"name":"Journal of Cloud Computing-Advances Systems and Applications","volume":"1 1","pages":"259-267"},"PeriodicalIF":4.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79413109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-01DOI: 10.1109/cscloud-edgecom58631.2023.00006
{"title":"Message from the Program Chairs - CSCloud 2023","authors":"","doi":"10.1109/cscloud-edgecom58631.2023.00006","DOIUrl":"https://doi.org/10.1109/cscloud-edgecom58631.2023.00006","url":null,"abstract":"","PeriodicalId":56007,"journal":{"name":"Journal of Cloud Computing-Advances Systems and Applications","volume":"13 1","pages":""},"PeriodicalIF":4.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86577307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Silk cocoon is one of the critical textile raw materials, and its quality has a significant impact on production and processing. In view of the problems such as time-consuming, labor-intensive, and low efficiency in the existing silk cocoon quality inspection methods, this paper proposes a machine vision-based silk cocoon quality inspection system. For different types of silk cocoons, multiple machine vision techniques are used for image processing and feature extraction. The quality characteristics of silk cocoons are discriminated and analyzed by machine learning algorithms to achieve automatic detection of the cocoon quality. Experimental results show that the proposed system has high accuracy and fast detection speed and can meet the requirements of automated detection in the silk cocoon production process.
{"title":"Research and design of a machine vision-based silk cocoon quality inspection system","authors":"Chengjun Yang, Jansheng Peng, Jiahong Cai, Yun Tang, Ling Zhou, YaoSheng Yang","doi":"10.1109/CSCloud-EdgeCom58631.2023.00069","DOIUrl":"https://doi.org/10.1109/CSCloud-EdgeCom58631.2023.00069","url":null,"abstract":"Silk cocoon is one of the critical textile raw materials, and its quality has a significant impact on production and processing. In view of the problems such as time-consuming, labor-intensive, and low efficiency in the existing silk cocoon quality inspection methods, this paper proposes a machine vision-based silk cocoon quality inspection system. For different types of silk cocoons, multiple machine vision techniques are used for image processing and feature extraction. The quality characteristics of silk cocoons are discriminated and analyzed by machine learning algorithms to achieve automatic detection of the cocoon quality. Experimental results show that the proposed system has high accuracy and fast detection speed and can meet the requirements of automated detection in the silk cocoon production process.","PeriodicalId":56007,"journal":{"name":"Journal of Cloud Computing-Advances Systems and Applications","volume":"61 1","pages":"369-374"},"PeriodicalIF":4.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79491152","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：