Pub Date : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9697032
Zhen Cheng, Huang Lin, Wei Liang, Lan Zhu, Y. Zheng
In order to solve the problems of discontinuous process and low efficiency of traditional aerator by dissolved and released gas method, a new structure of micro-nano aerator with double dissolved gas tank was designed. After this design by getting water, oxygen, divided into hypoxia under the condition of the start-up mode and the remote control of the mobile phone app, can produce efficiently and large specific surface area is big, slow pressurization dissolved itself, the problem of high rate of gas dissolved, micro-nano bubbles, water, increasing oxygen in water environmental governance is important aspects of research and application value.
{"title":"Design of New Micro-Nano Aerator","authors":"Zhen Cheng, Huang Lin, Wei Liang, Lan Zhu, Y. Zheng","doi":"10.1109/ICESIT53460.2021.9697032","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9697032","url":null,"abstract":"In order to solve the problems of discontinuous process and low efficiency of traditional aerator by dissolved and released gas method, a new structure of micro-nano aerator with double dissolved gas tank was designed. After this design by getting water, oxygen, divided into hypoxia under the condition of the start-up mode and the remote control of the mobile phone app, can produce efficiently and large specific surface area is big, slow pressurization dissolved itself, the problem of high rate of gas dissolved, micro-nano bubbles, water, increasing oxygen in water environmental governance is important aspects of research and application value.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116542672","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696462
Shengjie Zhu
As the light reflection problem keeps bothering students around the world, we thought of a novel approach to solve the problem through a blackboard that can rotate itself. In this project, mechanical design and embedded technology are used. And used 3D printing to process some parts. Verified the performance of the equipment through experiments. This can prevent the light reflections from interrupting the students.
{"title":"A Novel Approach for Solving Light Reflections on the Blackboard by Machine Vision Algorithm","authors":"Shengjie Zhu","doi":"10.1109/ICESIT53460.2021.9696462","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696462","url":null,"abstract":"As the light reflection problem keeps bothering students around the world, we thought of a novel approach to solve the problem through a blackboard that can rotate itself. In this project, mechanical design and embedded technology are used. And used 3D printing to process some parts. Verified the performance of the equipment through experiments. This can prevent the light reflections from interrupting the students.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115046589","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696685
J. Ling
In recent years, the in-depth development of the Internet has given birth to the learning mode of knowledge payment. Since 2016 to date, knowledge payment has gone through the process of fumbling to maturity from its infancy to emergence, and its market scale has expanded, and is expected to reach $50 billion after 2020, with college students expected to account for up to $10 billion in the interim. In this explosion of the knowledge payment industry, countless platforms have emerged and grown. However, among the existing platforms, most of them target at the whole society, and the products are many and miscellaneous, with insufficient quality control ability and low product repurchase rate. Today, with the rapid development of distributed ledger and big data mining technologies, this situation can be precisely solved.
{"title":"Design of Uimprove Knowledge Payment Platform Using Artificial Intelligence and Big Data Analysis","authors":"J. Ling","doi":"10.1109/ICESIT53460.2021.9696685","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696685","url":null,"abstract":"In recent years, the in-depth development of the Internet has given birth to the learning mode of knowledge payment. Since 2016 to date, knowledge payment has gone through the process of fumbling to maturity from its infancy to emergence, and its market scale has expanded, and is expected to reach $50 billion after 2020, with college students expected to account for up to $10 billion in the interim. In this explosion of the knowledge payment industry, countless platforms have emerged and grown. However, among the existing platforms, most of them target at the whole society, and the products are many and miscellaneous, with insufficient quality control ability and low product repurchase rate. Today, with the rapid development of distributed ledger and big data mining technologies, this situation can be precisely solved.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134015181","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696503
Jingqi Ma, Kai Huang, Zeyu Jiao, Chentong Li, Liangsheng Wu
With the diverse development of human-computer interaction. The gesture recognition-based interaction has a large-scale application prospect in collaborative robotics and smart home control. However, due to the similarity of gestures and occlusion, the previous methods have problems with the poor accuracy and shift of detection box. Aiming at the above issues, a gesture recognition method based on the Yolov4 deep learning algorithm is proposed. Firstly, gesture images were collected and annotated, and the data was processed by the GridMask and scale adjustment of data augmentation in order to improve the generalization performance of the network. Then K-means clustering algorithm was used to cluster the annotation boxes in the annotation dataset, by this way, the anchor box of YOLOV4 was optimized to improve the IOU accuracy. Finally, during the training process, focal loss and Consine warmup were adopted to improve the unbalanced sample number of classes and overfitting of the network. The experimental results shows that the proposed algorithm outperforms the main target detection models which include Yolov4, Yolov3 and Faster RCNN, the average recognition accuracy of this method reaches 99.4% and the FPS is 33fps. The proposed algorithm has good real-time performance.
{"title":"A Gesture Recognition Method Based on Yolov4 Network","authors":"Jingqi Ma, Kai Huang, Zeyu Jiao, Chentong Li, Liangsheng Wu","doi":"10.1109/ICESIT53460.2021.9696503","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696503","url":null,"abstract":"With the diverse development of human-computer interaction. The gesture recognition-based interaction has a large-scale application prospect in collaborative robotics and smart home control. However, due to the similarity of gestures and occlusion, the previous methods have problems with the poor accuracy and shift of detection box. Aiming at the above issues, a gesture recognition method based on the Yolov4 deep learning algorithm is proposed. Firstly, gesture images were collected and annotated, and the data was processed by the GridMask and scale adjustment of data augmentation in order to improve the generalization performance of the network. Then K-means clustering algorithm was used to cluster the annotation boxes in the annotation dataset, by this way, the anchor box of YOLOV4 was optimized to improve the IOU accuracy. Finally, during the training process, focal loss and Consine warmup were adopted to improve the unbalanced sample number of classes and overfitting of the network. The experimental results shows that the proposed algorithm outperforms the main target detection models which include Yolov4, Yolov3 and Faster RCNN, the average recognition accuracy of this method reaches 99.4% and the FPS is 33fps. The proposed algorithm has good real-time performance.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133892341","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696465
Qin Fengyan, Zhang Guangsheng
Metro section tunnels are constructed by undercutting method. Different section excavation methods and excavation sequences will cause different section deformation, vault subsidence and ground surface settlement. Therefore, how to excavate sections reasonably and what support methods are adopted, And the reinforcement measures of the surrounding rock masses will become the key factors for controlling surface settlement. Aiming at the characteristics of tight construction period, district filling of different materials, and high material transportation intensity in subway section tunnel construction, the functions and design principles of the subway section tunnel construction scheduling and simulation adopted, system are analyzed, and the construction information management and The design idea of optimizing the combination of deployment, information management and visualization technology, systematically discussed the main content and implementation methods of each function, and designed and developed practical software for related projects. Finally, the paper uses actual cases to carry out finite element numerical simulation calculations. A more reasonable excavation and support method is obtained through comparison and selection, which can be used as a reference for similar projects.
{"title":"Research on Mechanics System in Civil Engineering through Computer Big Data Technology and Visual Simulation","authors":"Qin Fengyan, Zhang Guangsheng","doi":"10.1109/ICESIT53460.2021.9696465","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696465","url":null,"abstract":"Metro section tunnels are constructed by undercutting method. Different section excavation methods and excavation sequences will cause different section deformation, vault subsidence and ground surface settlement. Therefore, how to excavate sections reasonably and what support methods are adopted, And the reinforcement measures of the surrounding rock masses will become the key factors for controlling surface settlement. Aiming at the characteristics of tight construction period, district filling of different materials, and high material transportation intensity in subway section tunnel construction, the functions and design principles of the subway section tunnel construction scheduling and simulation adopted, system are analyzed, and the construction information management and The design idea of optimizing the combination of deployment, information management and visualization technology, systematically discussed the main content and implementation methods of each function, and designed and developed practical software for related projects. Finally, the paper uses actual cases to carry out finite element numerical simulation calculations. A more reasonable excavation and support method is obtained through comparison and selection, which can be used as a reference for similar projects.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133245836","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696599
Cong Xiong, Anning Yu, L. Rong, Jiaming Huang, Bocheng Wang, Hai-nan Liu
Because of the low cost, strong mobility, and wide aerial view, the UAV is more and more widely used in the field of inspection and emergency rescue. Most of the traditional fire detection methods are based on the RGB color model, and their detection speed and accuracy are inadequate. In this paper, a fire detection method based on an autonomous drone platform is proposed. The drone flies on a designated route and carries an Ultra96-V2 development board with YOLOv3 fire detection algorithms deployed, which acts as an edge computing device to transmit the detection results back to the ground station in real time. Experimental results show that the recognition rate of the algorithm is 80%, the model memory compression is more than 75%, and the real-time detection frame rate is more than 3 FPS.
{"title":"Fire detection system based on unmanned aerial vehicle","authors":"Cong Xiong, Anning Yu, L. Rong, Jiaming Huang, Bocheng Wang, Hai-nan Liu","doi":"10.1109/ICESIT53460.2021.9696599","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696599","url":null,"abstract":"Because of the low cost, strong mobility, and wide aerial view, the UAV is more and more widely used in the field of inspection and emergency rescue. Most of the traditional fire detection methods are based on the RGB color model, and their detection speed and accuracy are inadequate. In this paper, a fire detection method based on an autonomous drone platform is proposed. The drone flies on a designated route and carries an Ultra96-V2 development board with YOLOv3 fire detection algorithms deployed, which acts as an edge computing device to transmit the detection results back to the ground station in real time. Experimental results show that the recognition rate of the algorithm is 80%, the model memory compression is more than 75%, and the real-time detection frame rate is more than 3 FPS.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"170 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116322169","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696525
W. Junlong, Kangwei Wei, Z. Wei, Huang Fengbiao, Tao Xuefeng, Wu Qiong
To solve the problems of low recognition accuracy and undetectable helmet of small targets in helmet detection in complex scenes, a helmet detection algorithm based on improved YOLOv5 and dynamic anchor box matching is proposed to improve the detection efficiency of small helmets in complex scenes. Firstly, by adding a small target detection layer in the YOLOv5 network, the detection accuracy of small targets is preliminarily improved; Secondly, convolution block attention model (CBAM) is added to the feature extraction network to enhance the information transmission between feature layers and the recognition of foreground and background by the neural network; Finally, to further improve the detection rate of small target helmet, the accuracy of a priori frame matching is enhanced by dynamic topK anchor frame matching. The weight of pre-training on the COCO data set is fused for detection and recognition to improve the generalization and accuracy of detection. The experimental results show that in the helmet data set constructed in this paper, the detection accuracy of helmets is 98.2%, and the helmet detection of small targets is realized.
{"title":"Helmet Detection Algorithm Based on the Improved YOLOv5 and Dynamic Anchor Box Matching","authors":"W. Junlong, Kangwei Wei, Z. Wei, Huang Fengbiao, Tao Xuefeng, Wu Qiong","doi":"10.1109/ICESIT53460.2021.9696525","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696525","url":null,"abstract":"To solve the problems of low recognition accuracy and undetectable helmet of small targets in helmet detection in complex scenes, a helmet detection algorithm based on improved YOLOv5 and dynamic anchor box matching is proposed to improve the detection efficiency of small helmets in complex scenes. Firstly, by adding a small target detection layer in the YOLOv5 network, the detection accuracy of small targets is preliminarily improved; Secondly, convolution block attention model (CBAM) is added to the feature extraction network to enhance the information transmission between feature layers and the recognition of foreground and background by the neural network; Finally, to further improve the detection rate of small target helmet, the accuracy of a priori frame matching is enhanced by dynamic topK anchor frame matching. The weight of pre-training on the COCO data set is fused for detection and recognition to improve the generalization and accuracy of detection. The experimental results show that in the helmet data set constructed in this paper, the detection accuracy of helmets is 98.2%, and the helmet detection of small targets is realized.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116830417","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696839
Chuyang Jin
This paper aims to build a model to predict used cars' reasonable prices based on multiple aspects, including vehicle mileage, year of manufacturing, fuel consumption, transmission, road tax, fuel type, and engine size. This model can benefit sellers, buyers, and car manufacturers in the used cars market. Upon completion, it can output a relatively accurate price prediction based on the information that users input. The model building process involves machine learning and data science. The dataset used was scraped from listings of used cars. Various regression methods, including linear regression, polynomial regression, support vector regression, decision tree regression, and random forest regression, were applied in the research to achieve the highest accuracy. Before the actual start of model-building, this project visualized the data to understand the dataset better. The dataset was divided and modified to fit the regression, thus ensure the performance of the regression. To evaluate the performance of each regression, R-square was calculated. Among all regressions in this project, random forest achieved the highest R-square of 0.90416. Compared to previous research, the resulting model includes more aspects of used cars while also having a higher prediction accuracy.
{"title":"Price Prediction of Used Cars Using Machine Learning","authors":"Chuyang Jin","doi":"10.1109/ICESIT53460.2021.9696839","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696839","url":null,"abstract":"This paper aims to build a model to predict used cars' reasonable prices based on multiple aspects, including vehicle mileage, year of manufacturing, fuel consumption, transmission, road tax, fuel type, and engine size. This model can benefit sellers, buyers, and car manufacturers in the used cars market. Upon completion, it can output a relatively accurate price prediction based on the information that users input. The model building process involves machine learning and data science. The dataset used was scraped from listings of used cars. Various regression methods, including linear regression, polynomial regression, support vector regression, decision tree regression, and random forest regression, were applied in the research to achieve the highest accuracy. Before the actual start of model-building, this project visualized the data to understand the dataset better. The dataset was divided and modified to fit the regression, thus ensure the performance of the regression. To evaluate the performance of each regression, R-square was calculated. Among all regressions in this project, random forest achieved the highest R-square of 0.90416. Compared to previous research, the resulting model includes more aspects of used cars while also having a higher prediction accuracy.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114499958","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696492
T. Deng
At present, the school has strong comprehensiveness, complete disciplines and specialties, advanced instruments and equipment, greatly developed the scale of various laboratories, and a large number of teachers and students participated in experimental activities. With the popularization of computer application technology and the gradual increase of public computer laboratories' external business. Man-made and popular network viruses are increasingly threatening the safety of laboratories, and laboratories are often unable to use because of the destruction of software, hardware and network systems. But at the same time, computer laboratory management, maintenance, especially security and other aspects of the problem followed. These accidents have exposed the safety loopholes and problems in the management of laboratories again and again, and aroused the great concern of the whole society. Therefore, we must find the causes and solutions fundamentally, and bring higher guarantee to the safety of laboratories. This paper mainly discusses the problems of laboratory safety management. It is of great significance to reduce the occurrence of safety accidents and improve the safety management level of computer laboratory.
{"title":"Strengthening and Upgrading of Laboratory Safety Management Based on Computer Risk Identification","authors":"T. Deng","doi":"10.1109/ICESIT53460.2021.9696492","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696492","url":null,"abstract":"At present, the school has strong comprehensiveness, complete disciplines and specialties, advanced instruments and equipment, greatly developed the scale of various laboratories, and a large number of teachers and students participated in experimental activities. With the popularization of computer application technology and the gradual increase of public computer laboratories' external business. Man-made and popular network viruses are increasingly threatening the safety of laboratories, and laboratories are often unable to use because of the destruction of software, hardware and network systems. But at the same time, computer laboratory management, maintenance, especially security and other aspects of the problem followed. These accidents have exposed the safety loopholes and problems in the management of laboratories again and again, and aroused the great concern of the whole society. Therefore, we must find the causes and solutions fundamentally, and bring higher guarantee to the safety of laboratories. This paper mainly discusses the problems of laboratory safety management. It is of great significance to reduce the occurrence of safety accidents and improve the safety management level of computer laboratory.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114659879","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 : 2021-11-22DOI: 10.1109/ICESIT53460.2021.9696788
Wenyan Yan, Degang Yang
In the background of “Internet+”, the use of advanced information technology and Internet of Things technology to create brand-new “smart venues” has become the main trend now. However, due to the large number of people, complex personnel types and frequent emergencies, it is a challenging task to manage the venue intelligently. This paper introduces a multidimensional feature fusion trajectory clustering algorithm, and designs a visual analysis system. The system can monitor the movement track of the venue personnel in real time, analyze the type of personnel, dig the movement rule of personnel, find abnormal situations in time, prevent and deal with emergencies, and well meet the demand of “smart venue”. By contrast with the existing trajectory clustering methods, the clustering algorithm logic more closely, clustering richer, more realistic value, provides strong technical support for emergency management of venues.
{"title":"Application of Multidimensional Feature Visualization in Emergency Management of Venues","authors":"Wenyan Yan, Degang Yang","doi":"10.1109/ICESIT53460.2021.9696788","DOIUrl":"https://doi.org/10.1109/ICESIT53460.2021.9696788","url":null,"abstract":"In the background of “Internet+”, the use of advanced information technology and Internet of Things technology to create brand-new “smart venues” has become the main trend now. However, due to the large number of people, complex personnel types and frequent emergencies, it is a challenging task to manage the venue intelligently. This paper introduces a multidimensional feature fusion trajectory clustering algorithm, and designs a visual analysis system. The system can monitor the movement track of the venue personnel in real time, analyze the type of personnel, dig the movement rule of personnel, find abnormal situations in time, prevent and deal with emergencies, and well meet the demand of “smart venue”. By contrast with the existing trajectory clustering methods, the clustering algorithm logic more closely, clustering richer, more realistic value, provides strong technical support for emergency management of venues.","PeriodicalId":164745,"journal":{"name":"2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128437348","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：