In order to increase the classification accuracy, the paper presents a novel feature grouping method, which is based on random forest variable importance measures. We applied the method to the classification of growing areas of tobacco and also compared it with other methods. The results showed that our proposed method efficiently got the optimal feature subset and can be used to identify the growing areas of tobacco. The feature grouping divided all features into different groups according to feature importance scores measured by random forest variable importance measures. The optimal feature subset was generated by continuous groups with important features, while the groups with irrelevant features were eliminated, which degraded the difficulty of feature selection. The experimental results demonstrated that our proposed method successfully eliminated the irrelevant features and got the optimal feature subset, leading to a significant improvement on the classification accuracy.
{"title":"Application of High Dimensional Feature Grouping Method in Near-Infrared Spectra of Identification of Tobacco Growing Areas","authors":"Cheng Zhu, Huili Gong, Zhongren Li, Chunxia Yu","doi":"10.1109/ICISCE.2016.58","DOIUrl":"https://doi.org/10.1109/ICISCE.2016.58","url":null,"abstract":"In order to increase the classification accuracy, the paper presents a novel feature grouping method, which is based on random forest variable importance measures. We applied the method to the classification of growing areas of tobacco and also compared it with other methods. The results showed that our proposed method efficiently got the optimal feature subset and can be used to identify the growing areas of tobacco. The feature grouping divided all features into different groups according to feature importance scores measured by random forest variable importance measures. The optimal feature subset was generated by continuous groups with important features, while the groups with irrelevant features were eliminated, which degraded the difficulty of feature selection. The experimental results demonstrated that our proposed method successfully eliminated the irrelevant features and got the optimal feature subset, leading to a significant improvement on the classification accuracy.","PeriodicalId":6882,"journal":{"name":"2016 3rd International Conference on Information Science and Control Engineering (ICISCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90589147","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}
To solve the peak-to-average power ratio (PAPR) problem of the artificial noise (AN) aided secure communication system, we propose a PAPR reduction algorithm based on the rotation invariant of AN subspaces in this paper. High peaks of the transmit signal caused by in-phase superposition between information subspace and AN subspaces is cancelled by rotating AN subspaces appropriately. Furthermore, the differential evolution (DE) algorithm is also employed to search the optimum rotation angle of each AN subspace. Simulation results show that the proposed algorithm reduces the transmit signal PAPR property effectively on the premise of keeping the security capacity of this AN aided secure communication system.
{"title":"Peak-to-Average Power Ratio Reduction for an Artificial Noise Aided Secure Communication System","authors":"Tao Hong, Zhi-peng Li","doi":"10.1109/ICISCE.2016.292","DOIUrl":"https://doi.org/10.1109/ICISCE.2016.292","url":null,"abstract":"To solve the peak-to-average power ratio (PAPR) problem of the artificial noise (AN) aided secure communication system, we propose a PAPR reduction algorithm based on the rotation invariant of AN subspaces in this paper. High peaks of the transmit signal caused by in-phase superposition between information subspace and AN subspaces is cancelled by rotating AN subspaces appropriately. Furthermore, the differential evolution (DE) algorithm is also employed to search the optimum rotation angle of each AN subspace. Simulation results show that the proposed algorithm reduces the transmit signal PAPR property effectively on the premise of keeping the security capacity of this AN aided secure communication system.","PeriodicalId":6882,"journal":{"name":"2016 3rd International Conference on Information Science and Control Engineering (ICISCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74432887","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 B to C E-commerce Enterprise (B2CEE) has produced extensive and profound influence on the economic structure. To study the structural factors of stock price of B2CEE which will influence the market pricing of them, we have introduced fractal method and made an empirical analysis on the typical case of listed B2CEE. Furthermore, to reveal the true value of B2CEE, it must separate the trend factor and the cyclical factor. Based on the fractal analysis of a typical B2CEE company: AMAZON, our study has provided a new method to separate the trend factor from the cyclical factor and has found that the stock price volatility of B2CEE appears as a trend with cyclical fluctuations.
{"title":"Research of the Volatility of Stock Price of B to C Electronic Commerce Enterprise by Fractal Method","authors":"Ming Chen","doi":"10.1109/ICISCE.2016.226","DOIUrl":"https://doi.org/10.1109/ICISCE.2016.226","url":null,"abstract":"The B to C E-commerce Enterprise (B2CEE) has produced extensive and profound influence on the economic structure. To study the structural factors of stock price of B2CEE which will influence the market pricing of them, we have introduced fractal method and made an empirical analysis on the typical case of listed B2CEE. Furthermore, to reveal the true value of B2CEE, it must separate the trend factor and the cyclical factor. Based on the fractal analysis of a typical B2CEE company: AMAZON, our study has provided a new method to separate the trend factor from the cyclical factor and has found that the stock price volatility of B2CEE appears as a trend with cyclical fluctuations.","PeriodicalId":6882,"journal":{"name":"2016 3rd International Conference on Information Science and Control Engineering (ICISCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77048066","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}
E-Learning is widely accepted to be the next generation of learning approach with extended features, while technology and theory step forward. However, the current model of e-Learning system lacks the scalable and sustainable infrastructure to support extended features. In this paper, we discuss the technical challenges faced in e-Learning and some common problems concerned by content providers. After that, we propose a framework of e-Learning education cloud with some featured characters. The main contribution is not only to introduce Cloud Computing into an e-Learning system to extend its scalability but also to design some featured modules for improved using experiences.
{"title":"A Framework of e-Learning Education Clouds to Efficiency and Personalization","authors":"S. Johnson, Yong Jin, Xubin Liu, Qin Wei, Hui Miao, Zhao Xu, Jiajin Yuan","doi":"10.1109/ICISCE.2016.17","DOIUrl":"https://doi.org/10.1109/ICISCE.2016.17","url":null,"abstract":"E-Learning is widely accepted to be the next generation of learning approach with extended features, while technology and theory step forward. However, the current model of e-Learning system lacks the scalable and sustainable infrastructure to support extended features. In this paper, we discuss the technical challenges faced in e-Learning and some common problems concerned by content providers. After that, we propose a framework of e-Learning education cloud with some featured characters. The main contribution is not only to introduce Cloud Computing into an e-Learning system to extend its scalability but also to design some featured modules for improved using experiences.","PeriodicalId":6882,"journal":{"name":"2016 3rd International Conference on Information Science and Control Engineering (ICISCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86875132","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}
Mingmin Liu, Fang Xu, Kai Jia, Qifeng Yang, Chong Tang
For a quadruped robot to implement steady moving on horizontal planes, avoiding the impact against the ground, a foot trajectory planning method underling low contact impact was presented. At first, kinematic model of the quadruped robot though D-H algorithm have been established. Then, the foot trajectories, which are continuous not only in displacements and velocities but also in accelerations, was scheduled based on the walking gait. Lastly, the steering and straight line movements of the robot were simulated, simulation experiments show that the quadruped robot motion stably on horizontal planes without impact and sliding.
{"title":"A Stable Walking Strategy of Quadruped Robot Based on Foot Trajectory Planning","authors":"Mingmin Liu, Fang Xu, Kai Jia, Qifeng Yang, Chong Tang","doi":"10.1109/ICISCE.2016.175","DOIUrl":"https://doi.org/10.1109/ICISCE.2016.175","url":null,"abstract":"For a quadruped robot to implement steady moving on horizontal planes, avoiding the impact against the ground, a foot trajectory planning method underling low contact impact was presented. At first, kinematic model of the quadruped robot though D-H algorithm have been established. Then, the foot trajectories, which are continuous not only in displacements and velocities but also in accelerations, was scheduled based on the walking gait. Lastly, the steering and straight line movements of the robot were simulated, simulation experiments show that the quadruped robot motion stably on horizontal planes without impact and sliding.","PeriodicalId":6882,"journal":{"name":"2016 3rd International Conference on Information Science and Control Engineering (ICISCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82804700","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}
To solve the problems of demand forecasting, the case-based reasoning (CBR) is used to create samples, and the least squares support vector machines (LSSVM) model is used as forecasting model, then the anti-air ammo demand forecasting in island offensive operation is taken as an empirical analysis. The result indicates that the samples created by case-based reasoning are available, and the forecasting results of different models are consilient but more accurate, this method can solve the problem of the lack of samples, so it is applicable to the combat supplies demand forecasting.
针对需求预测问题，采用基于案例推理(case-based reasoning, CBR)方法生成样本，采用最小二乘支持向量机(least squares support vector machines, LSSVM)模型作为预测模型，对海岛进攻作战防空弹药需求预测进行实证分析。结果表明，基于案例推理生成的样本是可用的，不同模型的预测结果一致且更准确，该方法解决了样本不足的问题，适用于作战物资需求预测。
{"title":"Study on Transportation and Replenishment Demand Forecasting Problem of Naval Warship","authors":"Peng Dong, Peng Yu, Furong Qin","doi":"10.1109/ICISCE.2016.148","DOIUrl":"https://doi.org/10.1109/ICISCE.2016.148","url":null,"abstract":"To solve the problems of demand forecasting, the case-based reasoning (CBR) is used to create samples, and the least squares support vector machines (LSSVM) model is used as forecasting model, then the anti-air ammo demand forecasting in island offensive operation is taken as an empirical analysis. The result indicates that the samples created by case-based reasoning are available, and the forecasting results of different models are consilient but more accurate, this method can solve the problem of the lack of samples, so it is applicable to the combat supplies demand forecasting.","PeriodicalId":6882,"journal":{"name":"2016 3rd International Conference on Information Science and Control Engineering (ICISCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91516404","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 tungsten carbide burs (TCBS) and diamond burs (DBS) are two mainly tools in clinical dentistry, while the TCBS possess many advantages over the DBS. The main goals of this paper were to parametrically design and manufacture a series of spherical tungsten carbide burs (STCBS) with 0.5mm to 3mm diameter, and the burs have an "S" shape cutting edges with six or eight flutes. The major cutting edges are modeled based on the mathematical model of the "S" shape curve, and the transition cutting edges are formed by 3-D interpolation between two points located at the spherical surface. A modular design flow is used to establish a series of 3-D models with different parameters of diameter, edge number and geometric angles. As an application, the manufacture of a spherical tungsten carbide bur (STCB) with 2.3mm diameter and 8 flutes is presented. An automated technique is developed to determine G-Code generated by tool path through the UG post process unit according to an available 5-aixs CNC grinding machine tool. The simulation is carried out using a commercial software package VERICUT, which shows the tool path meets the machining precision and is no overcut as well as interference between the bur and the process system of the machine tool.
{"title":"Research on the Parametric Design and Manufacture of Spherical Tungsten Carbide Burs Using a Five-Axis CNC Grinding Machine","authors":"Kai Wang, Jianfei Sun, Wuyi Chen","doi":"10.1109/ICISCE.2016.233","DOIUrl":"https://doi.org/10.1109/ICISCE.2016.233","url":null,"abstract":"The tungsten carbide burs (TCBS) and diamond burs (DBS) are two mainly tools in clinical dentistry, while the TCBS possess many advantages over the DBS. The main goals of this paper were to parametrically design and manufacture a series of spherical tungsten carbide burs (STCBS) with 0.5mm to 3mm diameter, and the burs have an \"S\" shape cutting edges with six or eight flutes. The major cutting edges are modeled based on the mathematical model of the \"S\" shape curve, and the transition cutting edges are formed by 3-D interpolation between two points located at the spherical surface. A modular design flow is used to establish a series of 3-D models with different parameters of diameter, edge number and geometric angles. As an application, the manufacture of a spherical tungsten carbide bur (STCB) with 2.3mm diameter and 8 flutes is presented. An automated technique is developed to determine G-Code generated by tool path through the UG post process unit according to an available 5-aixs CNC grinding machine tool. The simulation is carried out using a commercial software package VERICUT, which shows the tool path meets the machining precision and is no overcut as well as interference between the bur and the process system of the machine tool.","PeriodicalId":6882,"journal":{"name":"2016 3rd International Conference on Information Science and Control Engineering (ICISCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84791662","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}
Extensive economic development and traditional industrial production processes had caused great waste on human resources and natural energy. In the view of this situation, the paper establishes a coupling information system based on the internet of things and decision support system, expanding the research on the overall framework and design level of the integration system. First, from the macro level, the coupling system is built with the perception layer and decision-making layer as a whole, secondly, starting with complex network theory, the paper makes use of small-world network model to optimize perception layer topology network, finally, as the manufacturing is the core part of perception layer of the industrial enterprises, the technical framework of the active perception of critical events in IOMT based manufacturing process is established, which contributes to providing dynamic monitoring and decision-making to optimize the production process with a new model of support real-time information. Hence, the visual decision knowledge as well as realization of real-time intelligent management can be obtained by the coupling system.
{"title":"A Coupling System Design Based on the Internet of Things and Intelligent Decision Support System in Industrial Enterprises","authors":"Hui Wan, Liankai Liao","doi":"10.1109/ICISCE.2016.166","DOIUrl":"https://doi.org/10.1109/ICISCE.2016.166","url":null,"abstract":"Extensive economic development and traditional industrial production processes had caused great waste on human resources and natural energy. In the view of this situation, the paper establishes a coupling information system based on the internet of things and decision support system, expanding the research on the overall framework and design level of the integration system. First, from the macro level, the coupling system is built with the perception layer and decision-making layer as a whole, secondly, starting with complex network theory, the paper makes use of small-world network model to optimize perception layer topology network, finally, as the manufacturing is the core part of perception layer of the industrial enterprises, the technical framework of the active perception of critical events in IOMT based manufacturing process is established, which contributes to providing dynamic monitoring and decision-making to optimize the production process with a new model of support real-time information. Hence, the visual decision knowledge as well as realization of real-time intelligent management can be obtained by the coupling system.","PeriodicalId":6882,"journal":{"name":"2016 3rd International Conference on Information Science and Control Engineering (ICISCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82670554","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 presents a new robust adaptive filter based on the state dependent Riccati equation (SDRE) technique for SINS/SAR (strap-down inertial navigation system/synthetic aperture radar) integrated navigation. This method adopts the state dependent coefficient (SDC) form to convert nonlinear system model into linear system for avoiding the errors caused by the traditional numerical linearization process. It also adopts the concepts of robust estimation and adaptive factor to construct reasonably the discriminant statistics and adaptive factor for resisting the disturbances of singular observations and kinematic model error. Experiment results and comparison analysis demonstrate that the proposed filtering method can not only effectively resist disturbances from nonlinear system state noise and observation noise, but it also can achieve higher accuracy than the extended Kalman filter and SDRE filter.
{"title":"Robust Adaptive SDRE Filter and Its Application to SINS/SAR Integration","authors":"Zhaohui Gao, Bingbing Gao, Dejun Mu, Shesheng Gao","doi":"10.1109/ICISCE.2016.300","DOIUrl":"https://doi.org/10.1109/ICISCE.2016.300","url":null,"abstract":"This paper presents a new robust adaptive filter based on the state dependent Riccati equation (SDRE) technique for SINS/SAR (strap-down inertial navigation system/synthetic aperture radar) integrated navigation. This method adopts the state dependent coefficient (SDC) form to convert nonlinear system model into linear system for avoiding the errors caused by the traditional numerical linearization process. It also adopts the concepts of robust estimation and adaptive factor to construct reasonably the discriminant statistics and adaptive factor for resisting the disturbances of singular observations and kinematic model error. Experiment results and comparison analysis demonstrate that the proposed filtering method can not only effectively resist disturbances from nonlinear system state noise and observation noise, but it also can achieve higher accuracy than the extended Kalman filter and SDRE filter.","PeriodicalId":6882,"journal":{"name":"2016 3rd International Conference on Information Science and Control Engineering (ICISCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84194066","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 investigates the problem of trustworthy cloud service selection based on collaborative filtering in open network environment. First, it searches a set of Cloud services with same or similar functions according to the user's requirement, then computes the collection of users that have similar preferences for the target user based on their common evaluations, and obtains the recommendable user set for each candidate service, computes the recommendation degree for each service using it's similarity, and sorts the candidate services according to the recommendation degree to the target user. The experimental results show that the referral effect increases with the increase in the number of user evaluations, and with the increase of malicious user evaluations in the system, compared to other service recommendation methods, it only has a slight impact on the referral result of this method.
{"title":"A Collaborative Filtering Method for Trustworthy Cloud Service Selection","authors":"Guojun Sheng, Y. Cao, Yanxia Lu, Yao Li","doi":"10.1109/ICISCE.2016.14","DOIUrl":"https://doi.org/10.1109/ICISCE.2016.14","url":null,"abstract":"This paper investigates the problem of trustworthy cloud service selection based on collaborative filtering in open network environment. First, it searches a set of Cloud services with same or similar functions according to the user's requirement, then computes the collection of users that have similar preferences for the target user based on their common evaluations, and obtains the recommendable user set for each candidate service, computes the recommendation degree for each service using it's similarity, and sorts the candidate services according to the recommendation degree to the target user. The experimental results show that the referral effect increases with the increase in the number of user evaluations, and with the increase of malicious user evaluations in the system, compared to other service recommendation methods, it only has a slight impact on the referral result of this method.","PeriodicalId":6882,"journal":{"name":"2016 3rd International Conference on Information Science and Control Engineering (ICISCE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84330503","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：