The operation of cyber security has gradually become a significant part of informatization in the process of smart campus construction. However, universities rely too much on physical security devices in the current network security operation process, and lack of self-defined statistical analysis automation program. The current network logs have the following problems: difficult to gather data-sets of different application systems, difficult to unify attribute names of different data-sets, difficult to count the number of records with attacker and victim as the only items, and besieged to do repetitive work daily. In order to solve the above problems, this paper proposes an automatic statistical threatening IP algorithm, which can uniquely locate the attacker and victim and process other data through a programmatic way. Finally, it is used to report statistical data to departments related to cyber security. The results of experiment show that the proposed algorithm can effectively complete the statistical work of network attack threatening IP details.
{"title":"Statistical Analysis of threatening IP in Universities Based Automated Script","authors":"Zesheng Chen, Min Zhou, Lichun Feng, Binnan Li","doi":"10.1145/3548608.3559315","DOIUrl":"https://doi.org/10.1145/3548608.3559315","url":null,"abstract":"The operation of cyber security has gradually become a significant part of informatization in the process of smart campus construction. However, universities rely too much on physical security devices in the current network security operation process, and lack of self-defined statistical analysis automation program. The current network logs have the following problems: difficult to gather data-sets of different application systems, difficult to unify attribute names of different data-sets, difficult to count the number of records with attacker and victim as the only items, and besieged to do repetitive work daily. In order to solve the above problems, this paper proposes an automatic statistical threatening IP algorithm, which can uniquely locate the attacker and victim and process other data through a programmatic way. Finally, it is used to report statistical data to departments related to cyber security. The results of experiment show that the proposed algorithm can effectively complete the statistical work of network attack threatening IP details.","PeriodicalId":201434,"journal":{"name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126876101","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 recent years, machine learning has made remarkable achievements in many fields. The stock market forecast is a vital application scenario. However, stock market prediction in real situations usually has relatively little data available for machine learning model training. This paper focuses on establishing a stock prediction model based on a small data set. The experiment mainly focuses on three aspects: data set, regression algorithm, and feature selection. To solve the small data set problem, we chose interpolation to expand the data number, improving the model's accuracy remarkably. After comparing the different combinations, such as any set of 2 features or any set of 3 features, this model finally used all 15 features to predict. Its prediction result is very close to the accurate stock price. In this model, MSE (Mean Squad Error) is a suitable option to evaluate the model's accuracy. The result shows the four regressions: Linear Regression, Polynomial Regression, Decision Tree Regression, Random Forest Regression. The result shows that Linear Regression has better-predicted accuracy. Based on the small data set, the best solution is to use as many features as possible to train Linear Regression.
{"title":"Under-Resourced Machine Learning for Stock Market Prediction","authors":"Yutong Feng, Shengyu He, Jianguo Wu, Haofei Zhang","doi":"10.1145/3548608.3559328","DOIUrl":"https://doi.org/10.1145/3548608.3559328","url":null,"abstract":"In recent years, machine learning has made remarkable achievements in many fields. The stock market forecast is a vital application scenario. However, stock market prediction in real situations usually has relatively little data available for machine learning model training. This paper focuses on establishing a stock prediction model based on a small data set. The experiment mainly focuses on three aspects: data set, regression algorithm, and feature selection. To solve the small data set problem, we chose interpolation to expand the data number, improving the model's accuracy remarkably. After comparing the different combinations, such as any set of 2 features or any set of 3 features, this model finally used all 15 features to predict. Its prediction result is very close to the accurate stock price. In this model, MSE (Mean Squad Error) is a suitable option to evaluate the model's accuracy. The result shows the four regressions: Linear Regression, Polynomial Regression, Decision Tree Regression, Random Forest Regression. The result shows that Linear Regression has better-predicted accuracy. Based on the small data set, the best solution is to use as many features as possible to train Linear Regression.","PeriodicalId":201434,"journal":{"name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125676256","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}
The rise and development of edge computing technology have solved the problem of massive data in the era of big data, and provided a new direction for the development of intelligent security systems. Edge computing analyzes, calculates and stores the data at the edge near the data source, which reduces network transmission burden and the computing pressure of the cloud center and improves the efficiency of the whole system. In order to solve the problem of massive data in intelligent security system, a feasible architecture of intelligent security system based on edge computing is proposed, which is divided into four parts: perception layer, edge layer, transport layer and application layer. The intelligent security system based on edge computing can take full advantages of edge computing in terms of computing ability, real-time and security, and better meet the needs of real-time monitoring, risk assessment, early warning and intelligent decision-making services, so as to promote the comprehensive improvement of security level.
{"title":"Application of edge computing in intelligent security system","authors":"Jiqiang Zhang, Pengcheng Liu","doi":"10.1145/3548608.3559195","DOIUrl":"https://doi.org/10.1145/3548608.3559195","url":null,"abstract":"The rise and development of edge computing technology have solved the problem of massive data in the era of big data, and provided a new direction for the development of intelligent security systems. Edge computing analyzes, calculates and stores the data at the edge near the data source, which reduces network transmission burden and the computing pressure of the cloud center and improves the efficiency of the whole system. In order to solve the problem of massive data in intelligent security system, a feasible architecture of intelligent security system based on edge computing is proposed, which is divided into four parts: perception layer, edge layer, transport layer and application layer. The intelligent security system based on edge computing can take full advantages of edge computing in terms of computing ability, real-time and security, and better meet the needs of real-time monitoring, risk assessment, early warning and intelligent decision-making services, so as to promote the comprehensive improvement of security level.","PeriodicalId":201434,"journal":{"name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123731457","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}
Taking the cold chain logistics of agricultural products in Hefei as the research point, the distribution path of Zhougudui cold chain market is optimized. Based on the modeling analysis under the three elements of fuel consumption, stability and cost, the improved nearest insertion method is used for solution. Compared with the solution results of the original distribution path and mileage saving method, it is found that the improved insertion method is more suitable for the optimization of cold chain logistics distribution path in Hefei, which can effectively reduce the distribution logistics cost and improve the efficiency of cold chain logistics distribution.
{"title":"Study on Optimization of cold chain logistics distribution path of agricultural products in Hefei","authors":"Dong-Xu Liu","doi":"10.1145/3548608.3559224","DOIUrl":"https://doi.org/10.1145/3548608.3559224","url":null,"abstract":"Taking the cold chain logistics of agricultural products in Hefei as the research point, the distribution path of Zhougudui cold chain market is optimized. Based on the modeling analysis under the three elements of fuel consumption, stability and cost, the improved nearest insertion method is used for solution. Compared with the solution results of the original distribution path and mileage saving method, it is found that the improved insertion method is more suitable for the optimization of cold chain logistics distribution path in Hefei, which can effectively reduce the distribution logistics cost and improve the efficiency of cold chain logistics distribution.","PeriodicalId":201434,"journal":{"name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114073147","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 fast visual positioning of sheet metal parts based on electronic drawings is proposed in conjunction with CAD. The template of the edge contour of the sheet metal part is obtained based on the top view of CAD, and the sheet metal image pyramid is searched for template matching at the same time, thus improving the speed of template matching. For problems such as unclear edges or incomplete edges, the accurate value of the sheet metal part orientation is obtained by taking the inner contour as the template and finding the center point of the workpiece based on the relative position relationship of the inner contour. The final experiment verifies the accuracy and stability of the method, and the error is within 4mm, which meets the industrial production requirements.
{"title":"Rapid visual positioning of sheet metal parts based on electronic drawing templates","authors":"Yafeng Xiao, Zhiyong He","doi":"10.1145/3548608.3559257","DOIUrl":"https://doi.org/10.1145/3548608.3559257","url":null,"abstract":"A fast visual positioning of sheet metal parts based on electronic drawings is proposed in conjunction with CAD. The template of the edge contour of the sheet metal part is obtained based on the top view of CAD, and the sheet metal image pyramid is searched for template matching at the same time, thus improving the speed of template matching. For problems such as unclear edges or incomplete edges, the accurate value of the sheet metal part orientation is obtained by taking the inner contour as the template and finding the center point of the workpiece based on the relative position relationship of the inner contour. The final experiment verifies the accuracy and stability of the method, and the error is within 4mm, which meets the industrial production requirements.","PeriodicalId":201434,"journal":{"name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114372436","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}
Ma Qiu, Qian Wang, Wanzhen Wang, Jie Wang, Jian Huang
The correct four-wheel alignment parameters of the vehicle are an important prerequisite for ensuring the good handling stability, fuel economy, safety and other performance. It mainly analyzes the research status of four-wheel alignment parameters on handling stability at home and abroad, expounds the relationship between four-wheel alignment parameters and vehicle performance, analyzes the research progress of four-wheel alignment parameters based on different types of vehicles, and the influence of camber angle and kingpin inclination on steering reversal torque and wheel resistance torque. At the same time, the common optimization direction, optimization content and optimization method of four-wheel alignment parameters based on suspension structure are summarized,then analyzes the general detection method of four-wheel positioning parameters, and the change trend of positioning parameters and interval mileage is predicted by the method of regression equation.
{"title":"Research Status of Four-wheel Alignment Parameters on Handling Stability and Interval Mileage Prediction","authors":"Ma Qiu, Qian Wang, Wanzhen Wang, Jie Wang, Jian Huang","doi":"10.1145/3548608.3559204","DOIUrl":"https://doi.org/10.1145/3548608.3559204","url":null,"abstract":"The correct four-wheel alignment parameters of the vehicle are an important prerequisite for ensuring the good handling stability, fuel economy, safety and other performance. It mainly analyzes the research status of four-wheel alignment parameters on handling stability at home and abroad, expounds the relationship between four-wheel alignment parameters and vehicle performance, analyzes the research progress of four-wheel alignment parameters based on different types of vehicles, and the influence of camber angle and kingpin inclination on steering reversal torque and wheel resistance torque. At the same time, the common optimization direction, optimization content and optimization method of four-wheel alignment parameters based on suspension structure are summarized,then analyzes the general detection method of four-wheel positioning parameters, and the change trend of positioning parameters and interval mileage is predicted by the method of regression equation.","PeriodicalId":201434,"journal":{"name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124303711","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}
Aiming at the necessity of aircraft gust load alleviation control and fast response requirements, a design method of gust load alleviation control law based on L1 adaptive control is proposed. First, an aircraft-gust comprehensive dynamics model is established. Based on the gust response characteristics of the uncontrolled aircraft, the dynamic response of the target aircraft under gust disturbance is analyzed, and the corresponding L1 adaptive control architecture is constructed. Afterwards, the L1 adaptive control algorithm is used to design the gust load alleviation control system of the target aircraft, including a state observer, a low-pass filter and an adaptive law. Finally, the wing root bending moment and wing tip overload are used as control parameters, and the control system is simulated and evaluated under the influence of continuous gusts and random gusts. The results show that the control system can make the gust load alleviation rate of the flexible aircraft reach more than 15%.
{"title":"Gust Load Alleviation by L1 Adaptive Control","authors":"Ao He, Ban Wang, Shanshan Zhang, Z. Gao","doi":"10.1145/3548608.3559293","DOIUrl":"https://doi.org/10.1145/3548608.3559293","url":null,"abstract":"Aiming at the necessity of aircraft gust load alleviation control and fast response requirements, a design method of gust load alleviation control law based on L1 adaptive control is proposed. First, an aircraft-gust comprehensive dynamics model is established. Based on the gust response characteristics of the uncontrolled aircraft, the dynamic response of the target aircraft under gust disturbance is analyzed, and the corresponding L1 adaptive control architecture is constructed. Afterwards, the L1 adaptive control algorithm is used to design the gust load alleviation control system of the target aircraft, including a state observer, a low-pass filter and an adaptive law. Finally, the wing root bending moment and wing tip overload are used as control parameters, and the control system is simulated and evaluated under the influence of continuous gusts and random gusts. The results show that the control system can make the gust load alleviation rate of the flexible aircraft reach more than 15%.","PeriodicalId":201434,"journal":{"name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121749360","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 the field of robotics and autonomous driving, vision or laser-based map construction has always been the main direction for solving mobile vehicle's perception and localization. The stereo camera is widely used in robot map construction because it can perceive both color information and depth information. Based on the RGBD semantic segmentation network, this paper proposes a map construction algorithm based on deep semantic segmentation. By using the pixel information of deep semantic segmentation, the missing part of the 3D point cloud is filled to construct an octomap. After experiments, on the datasets, the algorithm has achieved better results than only using the depth information, and after actual deployment, the algorithm has completed the construction of real-time indoor semantic maps on the robot.
{"title":"Indoor map construction algorithm based on RGBD semantic segmentation","authors":"Jie-Ying He","doi":"10.1145/3548608.3559274","DOIUrl":"https://doi.org/10.1145/3548608.3559274","url":null,"abstract":"In the field of robotics and autonomous driving, vision or laser-based map construction has always been the main direction for solving mobile vehicle's perception and localization. The stereo camera is widely used in robot map construction because it can perceive both color information and depth information. Based on the RGBD semantic segmentation network, this paper proposes a map construction algorithm based on deep semantic segmentation. By using the pixel information of deep semantic segmentation, the missing part of the 3D point cloud is filled to construct an octomap. After experiments, on the datasets, the algorithm has achieved better results than only using the depth information, and after actual deployment, the algorithm has completed the construction of real-time indoor semantic maps on the robot.","PeriodicalId":201434,"journal":{"name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116955112","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}
Because of the long service life and slight corrosion of metal structure of a portal crane in an enterprise, in order to master the technical situation of the main stress components of the portal crane, this paper establishes the three-dimensional model of the main stress components of the equipment in ProE software, and then carries on the finite element analysis with the software, obtains the stress nephogram of the portal crane under rated load, and compares with the field stress test results to form an evaluation conclusion.
{"title":"Safety Evaluation of Portal Crane Based on Stress Test","authors":"Zhengqiu Huang, Lixin Ren, Weiping Ouyang, Yao-ting Tong","doi":"10.1145/3548608.3559285","DOIUrl":"https://doi.org/10.1145/3548608.3559285","url":null,"abstract":"Because of the long service life and slight corrosion of metal structure of a portal crane in an enterprise, in order to master the technical situation of the main stress components of the portal crane, this paper establishes the three-dimensional model of the main stress components of the equipment in ProE software, and then carries on the finite element analysis with the software, obtains the stress nephogram of the portal crane under rated load, and compares with the field stress test results to form an evaluation conclusion.","PeriodicalId":201434,"journal":{"name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123624250","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}
Video stabilization is widely used in various fields of life. After video stabilization, due to the offset of video frames, it often brings the problem of edge missing. Traditional electronic video stabilization algorithms deal with the problem of missing video edge information through cropping. The clipping amplitude is determined by the intensity of video jitter and video smoothing algorithm. To solve this problem, this paper proposes a method to repair the video edge based on panoramic stitching. Use the reciprocity of jitter to segment the video; combined with the video motion trajectory, the extraction range of feature points is reduced; perform homography transform on each frame in the segmented interval, and then stitch it into an image containing panoramic information; finally, using the panoramic image, each frame after offset is stitched to repair the video with missing edge information. The experimental results show that using the real scene information to restore the missing part of the video, the filling is natural, the effect is stable, and can be applied to a variety of complex environments.
{"title":"Edge Restoration of Video Stabilization Based on Panoramic Stitching","authors":"Yuanliang Li, Xianqiao Chen, Yihan Wen, Shuai Sun","doi":"10.1145/3548608.3559278","DOIUrl":"https://doi.org/10.1145/3548608.3559278","url":null,"abstract":"Video stabilization is widely used in various fields of life. After video stabilization, due to the offset of video frames, it often brings the problem of edge missing. Traditional electronic video stabilization algorithms deal with the problem of missing video edge information through cropping. The clipping amplitude is determined by the intensity of video jitter and video smoothing algorithm. To solve this problem, this paper proposes a method to repair the video edge based on panoramic stitching. Use the reciprocity of jitter to segment the video; combined with the video motion trajectory, the extraction range of feature points is reduced; perform homography transform on each frame in the segmented interval, and then stitch it into an image containing panoramic information; finally, using the panoramic image, each frame after offset is stitched to repair the video with missing edge information. The experimental results show that using the real scene information to restore the missing part of the video, the filling is natural, the effect is stable, and can be applied to a variety of complex environments.","PeriodicalId":201434,"journal":{"name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129579597","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：