With the development of large-scale power systems, wind power has become the mainstream. Wind power is clean energy, but its uncertainty will bring risks to the economic dispatch of the power system. This paper adopts an adjustable robust optimization method to deal with the uncertainty of wind power output, so that the power system can achieve an acceptable balance between economy and safety. In addition, this paper also proposes a novel evolutionary algorithm (NEA) to solve the large-scale dynamic economic dispatch problem with wind power. The case contains 10 generators, 4 wind farms and 96 time periods in a day are used as scheduling cycles, and there are 960 decision variables in total. The experimental results verify the effectiveness and efficiency of the robust optimization method and the NEA.
{"title":"A novel evolutionary algorithm for solving large-scale dynamic economic dispatch problem integrated with wind power","authors":"Qun Niu, Likun Wang, Litao Yu","doi":"10.1145/3556677.3556699","DOIUrl":"https://doi.org/10.1145/3556677.3556699","url":null,"abstract":"With the development of large-scale power systems, wind power has become the mainstream. Wind power is clean energy, but its uncertainty will bring risks to the economic dispatch of the power system. This paper adopts an adjustable robust optimization method to deal with the uncertainty of wind power output, so that the power system can achieve an acceptable balance between economy and safety. In addition, this paper also proposes a novel evolutionary algorithm (NEA) to solve the large-scale dynamic economic dispatch problem with wind power. The case contains 10 generators, 4 wind farms and 96 time periods in a day are used as scheduling cycles, and there are 960 decision variables in total. The experimental results verify the effectiveness and efficiency of the robust optimization method and the NEA.","PeriodicalId":350340,"journal":{"name":"Proceedings of the 2022 6th International Conference on Deep Learning Technologies","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126650669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Brain disorders such as autism spectrum disorder (ASD) is still difficult to diagnose. In the recent years, different novel deep learning algorithms have been applied to detect ASD. Most studies use the functional connectivity (FC) pattern to represent the brain activities. However, it has been investigated that dynamic functional connectivity (dFC) which represent more features than FC can characterize the intrinsic brain organization changes over time. The goal of this paper is to determine that dFC features are more successful than FC features in the classification of ASD using deep learning. In this paper, we propose a classification model using dFC and deep neural network. Firstly, we used windowed k-means (WKM) approach to compute the sub-state of the brain and extract the main features of the functional magnetic resonance imaging(fMRI). Then, two stacked denoising autoencoders were applied to extract the features and reduce the dimension. At last, the MLP was utilized to complete the classification task and do fine-tuning based on the autoencoder encoders weights. The experiments were carried out on the Autism Brain Imaging Data Exchange (ABIDE) datasets. Result shows that we acquired a mean accuracy of 68.51%. Overall, our proposed classification is effective and provide evidence that dFC contains more brain states features.
像自闭症谱系障碍(ASD)这样的脑部疾病仍然很难诊断。近年来，不同的新型深度学习算法被应用于ASD检测。大多数研究使用功能连接(FC)模式来表征大脑活动。然而，动态功能连通性(dynamic functional connectivity, dFC)的研究表明，动态功能连通性比动态功能连通性更能表征大脑内在组织随时间的变化。本文的目标是确定dFC特征在使用深度学习对ASD进行分类时比FC特征更成功。本文提出了一种基于dFC和深度神经网络的分类模型。首先，采用窗口k-均值(WKM)方法计算脑的子状态，提取功能磁共振成像(fMRI)的主要特征;然后，采用两个叠置去噪自编码器进行特征提取和降维;最后，利用MLP完成分类任务，并根据自编码器的编码器权值进行微调。实验在自闭症脑成像数据交换(Autism Brain Imaging Data Exchange，简称ABIDE)数据集上进行。结果表明，平均准确率为68.51%。总的来说，我们提出的分类是有效的，并提供证据表明dFC包含更多的大脑状态特征。
{"title":"An Improved dynamic functional connectivity and deep neural network model for Autism Spectrum Disorder Classification","authors":"Ming Li, Shanshan Tu, S. Rehman, Yong Jie Yang","doi":"10.1145/3556677.3556694","DOIUrl":"https://doi.org/10.1145/3556677.3556694","url":null,"abstract":"Brain disorders such as autism spectrum disorder (ASD) is still difficult to diagnose. In the recent years, different novel deep learning algorithms have been applied to detect ASD. Most studies use the functional connectivity (FC) pattern to represent the brain activities. However, it has been investigated that dynamic functional connectivity (dFC) which represent more features than FC can characterize the intrinsic brain organization changes over time. The goal of this paper is to determine that dFC features are more successful than FC features in the classification of ASD using deep learning. In this paper, we propose a classification model using dFC and deep neural network. Firstly, we used windowed k-means (WKM) approach to compute the sub-state of the brain and extract the main features of the functional magnetic resonance imaging(fMRI). Then, two stacked denoising autoencoders were applied to extract the features and reduce the dimension. At last, the MLP was utilized to complete the classification task and do fine-tuning based on the autoencoder encoders weights. The experiments were carried out on the Autism Brain Imaging Data Exchange (ABIDE) datasets. Result shows that we acquired a mean accuracy of 68.51%. Overall, our proposed classification is effective and provide evidence that dFC contains more brain states features.","PeriodicalId":350340,"journal":{"name":"Proceedings of the 2022 6th International Conference on Deep Learning Technologies","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126535834","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yiwen Long, Mengyan Xiao, Xiaoqiang Wang, Bin Wang, Jun Luo, Shuo Diao
Defect detection of ultrasonic scanning images of plastic packaging components is mainly rely on manpower and not suitable for traditional feature extraction methods, to solve this problem, this paper put forward an optimized FCOS deep learning network to identify its delaminated defects. We redesign the backbone IResNeSt that consists of new bottleneck and data transmission path as the feature extraction module to enhance the information expression ability, furthermore, we introduce a feature pyramid network TF-FPN to improve the feature utilization. Finally, the complete proposed structure FCOS-ITN realizes the identification of various defects and retains more feature details. The experimental results show that compared with the typical object detection method, our FCOS-ITN applied on ultrasonic scan data set locates the delaminated region more accurately. As a matter of fact, the average accuracy (mAP) achieved 90.27% on all defect types, which is 6.58% higher than that of the original frame, indicating that our approach is feasible for non-destructive defect detection.
{"title":"Ultrasonic scanning image defect detection of plastic packaging components based on FCOS","authors":"Yiwen Long, Mengyan Xiao, Xiaoqiang Wang, Bin Wang, Jun Luo, Shuo Diao","doi":"10.1145/3556677.3556686","DOIUrl":"https://doi.org/10.1145/3556677.3556686","url":null,"abstract":"Defect detection of ultrasonic scanning images of plastic packaging components is mainly rely on manpower and not suitable for traditional feature extraction methods, to solve this problem, this paper put forward an optimized FCOS deep learning network to identify its delaminated defects. We redesign the backbone IResNeSt that consists of new bottleneck and data transmission path as the feature extraction module to enhance the information expression ability, furthermore, we introduce a feature pyramid network TF-FPN to improve the feature utilization. Finally, the complete proposed structure FCOS-ITN realizes the identification of various defects and retains more feature details. The experimental results show that compared with the typical object detection method, our FCOS-ITN applied on ultrasonic scan data set locates the delaminated region more accurately. As a matter of fact, the average accuracy (mAP) achieved 90.27% on all defect types, which is 6.58% higher than that of the original frame, indicating that our approach is feasible for non-destructive defect detection.","PeriodicalId":350340,"journal":{"name":"Proceedings of the 2022 6th International Conference on Deep Learning Technologies","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120911697","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Proceedings of the 2022 6th International Conference on Deep Learning Technologies","authors":"","doi":"10.1145/3556677","DOIUrl":"https://doi.org/10.1145/3556677","url":null,"abstract":"","PeriodicalId":350340,"journal":{"name":"Proceedings of the 2022 6th International Conference on Deep Learning Technologies","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124219002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：