With the continuous development of railway informatization, railway operation and maintenance system also needs to be more intelligent. Starting from the basic concepts of operation and maintenance, intelligent operation and maintenance and railway intelligent operation and maintenance, according to the current operation and maintenance situation of some systems in the railway industry, this paper studies the overall architecture and workflow of the railway intelligent operation and maintenance system. Intelligent operation and maintenance technology can provide technical means for ensuring railway transportation safety, improving maintenance efficiency and reducing operation and maintenance cost. The implementation of railway intelligent operation and maintenance system will make railway operation and maintenance move forward from traditional decentralized mode to centralized and unified mode, so as to make railway operation and maintenance work more scientific and efficient and improve the overall operation and maintenance level of railway.
{"title":"Research on Railway Intelligent Operation and Maintenance and Its System Architecture","authors":"Mengqi He, Honghui Li, Yuhang Duan","doi":"10.1109/DSA.2019.00079","DOIUrl":"https://doi.org/10.1109/DSA.2019.00079","url":null,"abstract":"With the continuous development of railway informatization, railway operation and maintenance system also needs to be more intelligent. Starting from the basic concepts of operation and maintenance, intelligent operation and maintenance and railway intelligent operation and maintenance, according to the current operation and maintenance situation of some systems in the railway industry, this paper studies the overall architecture and workflow of the railway intelligent operation and maintenance system. Intelligent operation and maintenance technology can provide technical means for ensuring railway transportation safety, improving maintenance efficiency and reducing operation and maintenance cost. The implementation of railway intelligent operation and maintenance system will make railway operation and maintenance move forward from traditional decentralized mode to centralized and unified mode, so as to make railway operation and maintenance work more scientific and efficient and improve the overall operation and maintenance level of railway.","PeriodicalId":342719,"journal":{"name":"2019 6th International Conference on Dependable Systems and Their Applications (DSA)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114615235","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":"[DSA 2019 Keynote Speech I - III - 3 abstracts]","authors":"","doi":"10.1109/dsa.2019.00010","DOIUrl":"https://doi.org/10.1109/dsa.2019.00010","url":null,"abstract":"","PeriodicalId":342719,"journal":{"name":"2019 6th International Conference on Dependable Systems and Their Applications (DSA)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126318909","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}
A traditional color recognition sensor cannot track and move at the same time. In order to overcome this problem, OpenMV based cradle head mount tracking system is proposed in this paper. After the camera captures an image, a series of basic digital image processing is performed, which is controlled by two servo motors. The pan-tilt movement causes the cradle head to track the target color and if the pixel value of the target color is within the target threshold range, the recognition is successful and is displayed in a rectangular frame. The system is mounted on the cradle head to optimize the traditional color recognition, which increases the flexibility of recognition by facilitating angular movement. The experimental results prove that the cradle head can accurately and effectively identify and track the target color.
{"title":"OpenMV Based Cradle Head Mount Tracking System","authors":"Shiwei Zhou, Jiayuan Gong, Haiying Zhou, Zhengze Zhu, Chao He, Kui Zhou","doi":"10.1109/DSA.2019.00085","DOIUrl":"https://doi.org/10.1109/DSA.2019.00085","url":null,"abstract":"A traditional color recognition sensor cannot track and move at the same time. In order to overcome this problem, OpenMV based cradle head mount tracking system is proposed in this paper. After the camera captures an image, a series of basic digital image processing is performed, which is controlled by two servo motors. The pan-tilt movement causes the cradle head to track the target color and if the pixel value of the target color is within the target threshold range, the recognition is successful and is displayed in a rectangular frame. The system is mounted on the cradle head to optimize the traditional color recognition, which increases the flexibility of recognition by facilitating angular movement. The experimental results prove that the cradle head can accurately and effectively identify and track the target color.","PeriodicalId":342719,"journal":{"name":"2019 6th International Conference on Dependable Systems and Their Applications (DSA)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128491260","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}
With the continuous development of deep learning, research on the conversion of singing voice has gradually enriched. The study of singing voice conversion comes from voice conversion. The singing voice conversion is to sing the voice of the target singer without changing the sound content of the source singer. In this paper, we use WORLD vocoder and speech signal processing toolkit (SPTK) to extract the acoustic characteristics of songs and use two mirrored generative adversarial Nets complete the conversion of acoustic features. The experiment realizes the singing conversion of non-parallel corpus. Subjective evaluations show that the songs after the conversion have a good performance in the quality and similarity of the songs.
{"title":"Singing Voice Conversion Based on Non-Parallel Corpus","authors":"Wenyao Deng, Wei Zhao, Lin Qi, Cong Jin","doi":"10.1109/DSA.2019.00081","DOIUrl":"https://doi.org/10.1109/DSA.2019.00081","url":null,"abstract":"With the continuous development of deep learning, research on the conversion of singing voice has gradually enriched. The study of singing voice conversion comes from voice conversion. The singing voice conversion is to sing the voice of the target singer without changing the sound content of the source singer. In this paper, we use WORLD vocoder and speech signal processing toolkit (SPTK) to extract the acoustic characteristics of songs and use two mirrored generative adversarial Nets complete the conversion of acoustic features. The experiment realizes the singing conversion of non-parallel corpus. Subjective evaluations show that the songs after the conversion have a good performance in the quality and similarity of the songs.","PeriodicalId":342719,"journal":{"name":"2019 6th International Conference on Dependable Systems and Their Applications (DSA)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127583267","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}
This paper studies a network security situation assessment model based on D-S evidence theory for the problems that the assessment information source is too single and the accuracy deviation is too large in the situation awareness system. First, the model uses PCA to pre-process the alarm data to shorten the alarm processing time; secondly, it uses the improved DS evidence theory to combine the credibility of multi-source attack data and improve the alarm recognition rate; thirdly, by constructing three kinds of situation assessment indicators of vulnerability, threat and assets, it quantifies the situation component and improves the accuracy of the perception; fourthly, it also uses the weighted average method to synthesize the situation component; finally, the model and algorithm are verified by using network instance data and the results show the correctness of the method.
{"title":"Quantitative Evaluation Model of Network Security Situation Based on D-S Evidence Theory","authors":"Zhongwei Zhao, Tingting Zhou, Huan Wang","doi":"10.1109/DSA.2019.00057","DOIUrl":"https://doi.org/10.1109/DSA.2019.00057","url":null,"abstract":"This paper studies a network security situation assessment model based on D-S evidence theory for the problems that the assessment information source is too single and the accuracy deviation is too large in the situation awareness system. First, the model uses PCA to pre-process the alarm data to shorten the alarm processing time; secondly, it uses the improved DS evidence theory to combine the credibility of multi-source attack data and improve the alarm recognition rate; thirdly, by constructing three kinds of situation assessment indicators of vulnerability, threat and assets, it quantifies the situation component and improves the accuracy of the perception; fourthly, it also uses the weighted average method to synthesize the situation component; finally, the model and algorithm are verified by using network instance data and the results show the correctness of the method.","PeriodicalId":342719,"journal":{"name":"2019 6th International Conference on Dependable Systems and Their Applications (DSA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133245551","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}
It is known that the topological structure of an interconnection network can be modelled by a connected graph whose vertices represent sites of the network and whose edges represent the communication links. So many problems about networks can be converted to the study of graphs. The domination number of graphs is an important parameter and it has been used to measure the robustness of an interconnection network. But it has been proved that calculating the domination number of graph is a NP-complete problem, and it is also difficult to give the better boundary domination number of the graph, we only can calculate some special graphs which have some special structure. In this paper we consider the domination number of two special networks.
{"title":"Research on the Stability of Two Special Networks","authors":"Jianxiang Cao, Wenqian Shang, Weiguo Lin","doi":"10.1109/DSA.2019.00088","DOIUrl":"https://doi.org/10.1109/DSA.2019.00088","url":null,"abstract":"It is known that the topological structure of an interconnection network can be modelled by a connected graph whose vertices represent sites of the network and whose edges represent the communication links. So many problems about networks can be converted to the study of graphs. The domination number of graphs is an important parameter and it has been used to measure the robustness of an interconnection network. But it has been proved that calculating the domination number of graph is a NP-complete problem, and it is also difficult to give the better boundary domination number of the graph, we only can calculate some special graphs which have some special structure. In this paper we consider the domination number of two special networks.","PeriodicalId":342719,"journal":{"name":"2019 6th International Conference on Dependable Systems and Their Applications (DSA)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133454814","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 view of the existing problems in data sharing and equipment universality in the control technology of power transmission and transformation equipment, the interconnection and mutual control technology of power transmission and transformation equipment is studied in combination with the technology of Internet of things. According to the information communication structure of the power transmission and transformation equipment Internet of things, this paper analyzes the interconnection and mutual control technology. Under the structure of single and double star aggregation network, its reliability is calculated to ensure the safety of data resource sharing. Under the topology structure of ring convergence network, the average network delay is calculated to ensure that the equipment can be used in general, thus the overall design scheme of interconnection and mutual control technology is completed. According to the experimental results, the highest control effect of the technology can reach 98%, which provides an effective means for transmission line control in remote areas.
{"title":"Research on Interconnection and Mutual Control Technology of Power Transmission and Transformation Equipment Based on Internet of Things","authors":"Caiyun Di, Mingxing Li, Zhi Zhao","doi":"10.1109/DSA.2019.00044","DOIUrl":"https://doi.org/10.1109/DSA.2019.00044","url":null,"abstract":"In view of the existing problems in data sharing and equipment universality in the control technology of power transmission and transformation equipment, the interconnection and mutual control technology of power transmission and transformation equipment is studied in combination with the technology of Internet of things. According to the information communication structure of the power transmission and transformation equipment Internet of things, this paper analyzes the interconnection and mutual control technology. Under the structure of single and double star aggregation network, its reliability is calculated to ensure the safety of data resource sharing. Under the topology structure of ring convergence network, the average network delay is calculated to ensure that the equipment can be used in general, thus the overall design scheme of interconnection and mutual control technology is completed. According to the experimental results, the highest control effect of the technology can reach 98%, which provides an effective means for transmission line control in remote areas.","PeriodicalId":342719,"journal":{"name":"2019 6th International Conference on Dependable Systems and Their Applications (DSA)","volume":"2013 14","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134481983","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}
Intelligent robot Q & A is a new focus in the field of natural language understanding and processing. In recent years, with the gradual maturity of deep learning technology, more and more research has begun to model deep neural networks for text semantics. Deep neural networks are computational models abstracted from human brain cognitive processes, closer to humans. In this paper, we use GRU deep neural network to study the generative dialogue, and implement a seq2seq model manmachine conversation system. Experiments show that the confidence of the system can reach the range of human acceptance.
{"title":"Research on Man-Machine Conversation System Based on GRU seq2seq Model","authors":"Wei Huang, Xiaoyu Dong, Wenqian Shang, Weiguo Lin","doi":"10.1109/DSA.2019.00064","DOIUrl":"https://doi.org/10.1109/DSA.2019.00064","url":null,"abstract":"Intelligent robot Q & A is a new focus in the field of natural language understanding and processing. In recent years, with the gradual maturity of deep learning technology, more and more research has begun to model deep neural networks for text semantics. Deep neural networks are computational models abstracted from human brain cognitive processes, closer to humans. In this paper, we use GRU deep neural network to study the generative dialogue, and implement a seq2seq model manmachine conversation system. Experiments show that the confidence of the system can reach the range of human acceptance.","PeriodicalId":342719,"journal":{"name":"2019 6th International Conference on Dependable Systems and Their Applications (DSA)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134339487","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}
From the perspective of reliability research, the anti-noise performance of chaotic criterion is a kind of difficult problems. We proposed one new metric for chaos detection under noise-dying challenge. To build three dimensional compression entropy variable-space, measuring geometric selfsimilarity without tunable parameters, our new chaos criterion can easily find the periodic windows during chaos equation evolution, and the anti-noise ability keeps strong, since the golden partition rate embedded threshold activation function is applied. Four key chaos equations are as test cases. The results under MATLAB tool show that our new chaos criterion touches the anti-noise ability near 15% additive composition.
{"title":"Research on Anti-Noise Performance of New Chaos Criterion","authors":"Jinwei Cai, Yilin Ning, Wenshi Li, Linhong Yao","doi":"10.1109/DSA.2019.00086","DOIUrl":"https://doi.org/10.1109/DSA.2019.00086","url":null,"abstract":"From the perspective of reliability research, the anti-noise performance of chaotic criterion is a kind of difficult problems. We proposed one new metric for chaos detection under noise-dying challenge. To build three dimensional compression entropy variable-space, measuring geometric selfsimilarity without tunable parameters, our new chaos criterion can easily find the periodic windows during chaos equation evolution, and the anti-noise ability keeps strong, since the golden partition rate embedded threshold activation function is applied. Four key chaos equations are as test cases. The results under MATLAB tool show that our new chaos criterion touches the anti-noise ability near 15% additive composition.","PeriodicalId":342719,"journal":{"name":"2019 6th International Conference on Dependable Systems and Their Applications (DSA)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114581736","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}
This paper proposes a cone detection algorithm based on HSV color and the least-squares method. The algorithm first converts the RGB image of the cone into HSV format and then binarizes it. Next, filter the binarized image by methods of floodfill and morphology. The contour of the cone is detected, and then the slope is determined by the least-squares method for the final determination. This article also describes the principle of camera calibration and the perspective transformation method to extract the position of the identified cone. Finally, it is verified by experiments that cone recognition is effective and the location information is highly reliable.
{"title":"Cone Detection and Location for Formula Student Driverless Race","authors":"Leipeng Qie, Jiayuan Gong, Haiying Zhou, Sishan Wang, Shiwei Zhou, Nandan Bangalore Chetan","doi":"10.1109/DSA.2019.00069","DOIUrl":"https://doi.org/10.1109/DSA.2019.00069","url":null,"abstract":"This paper proposes a cone detection algorithm based on HSV color and the least-squares method. The algorithm first converts the RGB image of the cone into HSV format and then binarizes it. Next, filter the binarized image by methods of floodfill and morphology. The contour of the cone is detected, and then the slope is determined by the least-squares method for the final determination. This article also describes the principle of camera calibration and the perspective transformation method to extract the position of the identified cone. Finally, it is verified by experiments that cone recognition is effective and the location information is highly reliable.","PeriodicalId":342719,"journal":{"name":"2019 6th International Conference on Dependable Systems and Their Applications (DSA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124384828","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：