Pub Date : 2020-03-01DOI: 10.1109/CTISC49998.2020.00033
Kaibei Peng, W. Bai, Liuyi Wu
To solve the problem that the traditional neural network model lacks the ability to predict the complex nonlinear data, this paper constructed a short-term passenger flow prediction model based on the improved LSTM. Taking the AFC data of Beijing West Railway Station as the research object, the neural network model is trained by using the deep learning framework Keras. The prediction results of the improved LSTM network model is compared with BP network model and the standard LSTM network model. The results show that the improved LSTM model has better prediction results. In different periods of weekdays and weekends, the mean absolute percentage error (MAPE) of passenger flow prediction is lower than other models.
{"title":"Passenger flow forecast of railway station based on improved LSTM","authors":"Kaibei Peng, W. Bai, Liuyi Wu","doi":"10.1109/CTISC49998.2020.00033","DOIUrl":"https://doi.org/10.1109/CTISC49998.2020.00033","url":null,"abstract":"To solve the problem that the traditional neural network model lacks the ability to predict the complex nonlinear data, this paper constructed a short-term passenger flow prediction model based on the improved LSTM. Taking the AFC data of Beijing West Railway Station as the research object, the neural network model is trained by using the deep learning framework Keras. The prediction results of the improved LSTM network model is compared with BP network model and the standard LSTM network model. The results show that the improved LSTM model has better prediction results. In different periods of weekdays and weekends, the mean absolute percentage error (MAPE) of passenger flow prediction is lower than other models.","PeriodicalId":266384,"journal":{"name":"2020 2nd International Conference on Advances in Computer Technology, Information Science and Communications (CTISC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121419764","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}
Pub Date : 2020-03-01DOI: 10.1109/ctisc49998.2020.00002
{"title":"CTISC 2020 Commentary","authors":"","doi":"10.1109/ctisc49998.2020.00002","DOIUrl":"https://doi.org/10.1109/ctisc49998.2020.00002","url":null,"abstract":"","PeriodicalId":266384,"journal":{"name":"2020 2nd International Conference on Advances in Computer Technology, Information Science and Communications (CTISC)","volume":"34 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114111851","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}
Pub Date : 2020-03-01DOI: 10.1109/ctisc49998.2020.00004
Shi-Hong Shao
Research on Spectrum Sensing System Based on Composite Neural Network 22 Long Zhang (The Spectrum Division of China Electronic Equipment System Engineering Company), Min Zhao (The Spectrum Division of China Electronic Equipment System Engineering Company), Cheng Tan (The Spectrum Division of China Electronic Equipment System Engineering Company), Gang Li (The Spectrum Division of China Electronic Equipment System Engineering Company), and Chunying Lv (The Spectrum Division of China Electronic Equipment System Engineering Company)
{"title":"CTISC 2020 TOC","authors":"Shi-Hong Shao","doi":"10.1109/ctisc49998.2020.00004","DOIUrl":"https://doi.org/10.1109/ctisc49998.2020.00004","url":null,"abstract":"Research on Spectrum Sensing System Based on Composite Neural Network 22 Long Zhang (The Spectrum Division of China Electronic Equipment System Engineering Company), Min Zhao (The Spectrum Division of China Electronic Equipment System Engineering Company), Cheng Tan (The Spectrum Division of China Electronic Equipment System Engineering Company), Gang Li (The Spectrum Division of China Electronic Equipment System Engineering Company), and Chunying Lv (The Spectrum Division of China Electronic Equipment System Engineering Company)","PeriodicalId":266384,"journal":{"name":"2020 2nd International Conference on Advances in Computer Technology, Information Science and Communications (CTISC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115880826","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}
Pub Date : 2020-03-01DOI: 10.1109/CTISC49998.2020.00032
Xuemin Lu, Yuchen Peng, W. Quan, N. Zhou, Dong Zou, Jim X. Chen
The outdoors insulator is an important component of the high-speed railway traction substation, which is of great significance to maintain the stability of transmission line and ensure the normal operation of transmission network. Once there is a fault for the insulator, it will cause serious transmission failure and economic loss. Therefore, a method is proposed to detect the abnormal areas of outdoors insulator in high-speed railway traction substation based on object detection and generative adversarial networks. First, we employ Faster RCNN to locate the area of insulator from the input image of traction substation. Then, the image of insulator obtained from the first step is fed into our designed generative adversarial networks to generate fake image, which is a normal image of insulator. Finally, multi-scale structural similarity algorithm is used to realize the anomaly detection of insulator and visualize anomalous areas. Experiments results on Heishan traction substation show that the proposed method is effective.
{"title":"An Anomaly Detection Method for Outdoors Insulator in High-Speed Railway Traction Substation","authors":"Xuemin Lu, Yuchen Peng, W. Quan, N. Zhou, Dong Zou, Jim X. Chen","doi":"10.1109/CTISC49998.2020.00032","DOIUrl":"https://doi.org/10.1109/CTISC49998.2020.00032","url":null,"abstract":"The outdoors insulator is an important component of the high-speed railway traction substation, which is of great significance to maintain the stability of transmission line and ensure the normal operation of transmission network. Once there is a fault for the insulator, it will cause serious transmission failure and economic loss. Therefore, a method is proposed to detect the abnormal areas of outdoors insulator in high-speed railway traction substation based on object detection and generative adversarial networks. First, we employ Faster RCNN to locate the area of insulator from the input image of traction substation. Then, the image of insulator obtained from the first step is fed into our designed generative adversarial networks to generate fake image, which is a normal image of insulator. Finally, multi-scale structural similarity algorithm is used to realize the anomaly detection of insulator and visualize anomalous areas. Experiments results on Heishan traction substation show that the proposed method is effective.","PeriodicalId":266384,"journal":{"name":"2020 2nd International Conference on Advances in Computer Technology, Information Science and Communications (CTISC)","volume":"185 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132869045","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}
In this paper, a template matching method based on local stable pixels is proposed. First, gradient magnitude and orientation difference are utilized to evaluate the local pixel information for local stable pixel detection. Second, an updated strategy based on gradient magnitude standard deviation is designed to detect local stable pixels. Finally, a coarse-to-fine search approach based on the detected stable pixels is employed to acquire rotation angle. Experimental results demonstrate that the proposed method is robust to arbitrary rotation, occlusion, complex background clutter, blur, noise and it is able to meet the demand of real-time processing for visual positioning project.
{"title":"Real-Time Template Matching Based on Local Stable Pixels","authors":"Xicheng Zhu, Xiao Hu, Changhong Liu, Shao-Hu Peng, Chang Zhang","doi":"10.1109/CTISC49998.2020.00028","DOIUrl":"https://doi.org/10.1109/CTISC49998.2020.00028","url":null,"abstract":"In this paper, a template matching method based on local stable pixels is proposed. First, gradient magnitude and orientation difference are utilized to evaluate the local pixel information for local stable pixel detection. Second, an updated strategy based on gradient magnitude standard deviation is designed to detect local stable pixels. Finally, a coarse-to-fine search approach based on the detected stable pixels is employed to acquire rotation angle. Experimental results demonstrate that the proposed method is robust to arbitrary rotation, occlusion, complex background clutter, blur, noise and it is able to meet the demand of real-time processing for visual positioning project.","PeriodicalId":266384,"journal":{"name":"2020 2nd International Conference on Advances in Computer Technology, Information Science and Communications (CTISC)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121688926","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}
Pub Date : 2020-03-01DOI: 10.1109/CTISC49998.2020.00023
Guo Yan, Mao Shao-jie
Cloud based simulation system architecture concentrates a lot of simulation resources in the Datacenter for unified management, which has the advantages of efficiency and cost, but also faces problems such as collaborative interaction. A novel simulation system architecture called is proposed. In this architecture, edge computing is introduced. It employed resource virtualization and service technical to get through the integration and interaction of various simulation resources of cloud, edge, and end. It is the further development of cloud architecture-based simulation system architecture, which is conducive to the transfer of simulation ability to application edge frontier.
{"title":"Cloud-Edge-End Simulation System Architecture Study","authors":"Guo Yan, Mao Shao-jie","doi":"10.1109/CTISC49998.2020.00023","DOIUrl":"https://doi.org/10.1109/CTISC49998.2020.00023","url":null,"abstract":"Cloud based simulation system architecture concentrates a lot of simulation resources in the Datacenter for unified management, which has the advantages of efficiency and cost, but also faces problems such as collaborative interaction. A novel simulation system architecture called is proposed. In this architecture, edge computing is introduced. It employed resource virtualization and service technical to get through the integration and interaction of various simulation resources of cloud, edge, and end. It is the further development of cloud architecture-based simulation system architecture, which is conducive to the transfer of simulation ability to application edge frontier.","PeriodicalId":266384,"journal":{"name":"2020 2nd International Conference on Advances in Computer Technology, Information Science and Communications (CTISC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121601092","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}
Pub Date : 2020-03-01DOI: 10.1109/CTISC49998.2020.00029
Yubing Ma, Kaifeng Shang, Qionghai Dai, Jingtao Fan
Tracking neurons by analyzing their calcium imaging data has enabled biological scientists to better understand the structure and working principle of the nervous system. Several algorithms have been proposed for neurons identification, but most of them become less effective when processing data recorded by single-photon wide-field fluorescence microscopes due to low signal-to-noise ratio (SNR). Moreover, defocus blur, which is common in in vivo imaging, and interference of other biological structures near the neurons have brought greater challenges. In the face of these issues, we have presented an improved method based on the extended constrained nonnegative matrix factorization (CNMF-E) framework to better identify the spatial locations and temporal activities of the neurons. To obtain more appropriate spatial components, we have introduced regularizations into the optimization problem and applied more morphological processing. For more precise temporal components, we have performed a piecewise baseline adjustment on the neurons’ fluorescence traces and suppressed the overestimated signals caused by the estimation error of background fluctuations. Our approach has been tested on the mouse brain cortex recorded by the Real-time, Ultra-large-Scale imaging at High-resolution (RUSH) macroscope. Due to the lack of existing datasets similar to the current imaging conditions, we have manually labeled some neurons and compared the results qualitatively, which show that our method has identified the neurons more accurately compared with the original CNMF-E method.
{"title":"Neurons identification of single-photon wide-field calcium fluorescent imaging data","authors":"Yubing Ma, Kaifeng Shang, Qionghai Dai, Jingtao Fan","doi":"10.1109/CTISC49998.2020.00029","DOIUrl":"https://doi.org/10.1109/CTISC49998.2020.00029","url":null,"abstract":"Tracking neurons by analyzing their calcium imaging data has enabled biological scientists to better understand the structure and working principle of the nervous system. Several algorithms have been proposed for neurons identification, but most of them become less effective when processing data recorded by single-photon wide-field fluorescence microscopes due to low signal-to-noise ratio (SNR). Moreover, defocus blur, which is common in in vivo imaging, and interference of other biological structures near the neurons have brought greater challenges. In the face of these issues, we have presented an improved method based on the extended constrained nonnegative matrix factorization (CNMF-E) framework to better identify the spatial locations and temporal activities of the neurons. To obtain more appropriate spatial components, we have introduced regularizations into the optimization problem and applied more morphological processing. For more precise temporal components, we have performed a piecewise baseline adjustment on the neurons’ fluorescence traces and suppressed the overestimated signals caused by the estimation error of background fluctuations. Our approach has been tested on the mouse brain cortex recorded by the Real-time, Ultra-large-Scale imaging at High-resolution (RUSH) macroscope. Due to the lack of existing datasets similar to the current imaging conditions, we have manually labeled some neurons and compared the results qualitatively, which show that our method has identified the neurons more accurately compared with the original CNMF-E method.","PeriodicalId":266384,"journal":{"name":"2020 2nd International Conference on Advances in Computer Technology, Information Science and Communications (CTISC)","volume":"69 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114037674","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}
Pub Date : 2020-03-01DOI: 10.1109/CTISC49998.2020.00018
Mingxing Shao, Xiangqing Li
In the era of big data, where cloud computing proves to be an essential technology, its ability to align itself with enterprise is the key to facilitate business process reengineering and innovation and enhance enterprise value. In order to identify the key factors influencing the alignment of cloud computing and enterprises in Zhongguancun Technology Park, this paper, based on the dynamic capability theory and taking into account the ever-changing business environment in the Zhongguancun Technology Park, focused on three factors of an enterprise, namely Enterprise Dynamic Capability, Organization Flexibility and IT Flexibility, and built a theoretical model to study how these three factors influence the alignment of cloud computing. The paper measured the impact by two dimensions, Alignment Depth and Alignment Breadth. The results were tested by data collected in questionnaires and the Structural Equation Model (SEM) empirically. The findings showed that enterprise dynamic capability and IT flexibility both have a positive impact on the alignment depth and alignment breadth of cloud computing.
{"title":"An Empirical Study of Impact Factors on the Alignment of Cloud Computing and Enterprise","authors":"Mingxing Shao, Xiangqing Li","doi":"10.1109/CTISC49998.2020.00018","DOIUrl":"https://doi.org/10.1109/CTISC49998.2020.00018","url":null,"abstract":"In the era of big data, where cloud computing proves to be an essential technology, its ability to align itself with enterprise is the key to facilitate business process reengineering and innovation and enhance enterprise value. In order to identify the key factors influencing the alignment of cloud computing and enterprises in Zhongguancun Technology Park, this paper, based on the dynamic capability theory and taking into account the ever-changing business environment in the Zhongguancun Technology Park, focused on three factors of an enterprise, namely Enterprise Dynamic Capability, Organization Flexibility and IT Flexibility, and built a theoretical model to study how these three factors influence the alignment of cloud computing. The paper measured the impact by two dimensions, Alignment Depth and Alignment Breadth. The results were tested by data collected in questionnaires and the Structural Equation Model (SEM) empirically. The findings showed that enterprise dynamic capability and IT flexibility both have a positive impact on the alignment depth and alignment breadth of cloud computing.","PeriodicalId":266384,"journal":{"name":"2020 2nd International Conference on Advances in Computer Technology, Information Science and Communications (CTISC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132755360","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}
Pub Date : 2020-03-01DOI: 10.1109/ctisc49998.2020.00008
{"title":"Sponsors and Supporters: CTISC 2020","authors":"","doi":"10.1109/ctisc49998.2020.00008","DOIUrl":"https://doi.org/10.1109/ctisc49998.2020.00008","url":null,"abstract":"","PeriodicalId":266384,"journal":{"name":"2020 2nd International Conference on Advances in Computer Technology, Information Science and Communications (CTISC)","volume":"467 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115368436","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}
Pub Date : 2020-03-01DOI: 10.1109/CTISC49998.2020.00027
Yun Jiang, Shengxin Tao, Hai Zhang, Simin Cao
Deep neural networks usually contain tens to hundreds of millions of orders of learning parameters that provide the necessary representation to solve various visual tasks. But with the increase of the representational ability, the possibility of over-fitting also increase, which bring about poor generalization. In this paper, we propose MA (Maximum Activation point processing) algorithm, a new image data augmentation method which is designed to improve the generalization ability of the model and reduce the risk of overfitting. During the training process, the most discriminative part of the input image is searched for, and the model is driven to search for the supplementary information of the most important feature information by erasing the maximum attention image block. During this process, training images with different occlusion levels are generated as new inputs to the network and the model continues to be trained. The image erasure method based on the maximum activation point guidance only needs to modify the input image, which can effectively improve the robustness of the model to occluded image recognition, and can be integrated with various network structures. The effectiveness of our method is verified on the Cifar10, Cifar100 and Fashion-MNIST datasets.
深度神经网络通常包含数千万到数亿阶的学习参数，这些参数为解决各种视觉任务提供了必要的表示。但随着表征能力的提高，过度拟合的可能性也随之增加，导致泛化效果较差。本文提出了一种新的图像数据增强方法MA (Maximum Activation point processing，最大激活点处理)算法，该算法旨在提高模型的泛化能力，降低过拟合的风险。在训练过程中，搜索输入图像中最具判别性的部分，并通过擦除最大关注图像块来驱动模型搜索最重要特征信息的补充信息。在此过程中，生成不同遮挡水平的训练图像作为网络的新输入，并继续训练模型。基于最大激活点制导的图像擦除方法只需要修改输入图像，可以有效提高模型对遮挡图像识别的鲁棒性，并且可以与各种网络结构集成。在Cifar10、Cifar100和Fashion-MNIST数据集上验证了该方法的有效性。
{"title":"Image data augmentation method based on maximum activation point guided erasure","authors":"Yun Jiang, Shengxin Tao, Hai Zhang, Simin Cao","doi":"10.1109/CTISC49998.2020.00027","DOIUrl":"https://doi.org/10.1109/CTISC49998.2020.00027","url":null,"abstract":"Deep neural networks usually contain tens to hundreds of millions of orders of learning parameters that provide the necessary representation to solve various visual tasks. But with the increase of the representational ability, the possibility of over-fitting also increase, which bring about poor generalization. In this paper, we propose MA (Maximum Activation point processing) algorithm, a new image data augmentation method which is designed to improve the generalization ability of the model and reduce the risk of overfitting. During the training process, the most discriminative part of the input image is searched for, and the model is driven to search for the supplementary information of the most important feature information by erasing the maximum attention image block. During this process, training images with different occlusion levels are generated as new inputs to the network and the model continues to be trained. The image erasure method based on the maximum activation point guidance only needs to modify the input image, which can effectively improve the robustness of the model to occluded image recognition, and can be integrated with various network structures. The effectiveness of our method is verified on the Cifar10, Cifar100 and Fashion-MNIST datasets.","PeriodicalId":266384,"journal":{"name":"2020 2nd International Conference on Advances in Computer Technology, Information Science and Communications (CTISC)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115293182","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：