This paper investigates pressure regulation for multi-level gas tank by variable universe fuzzy PID control. Pressure vessel is one of important equipments in process industry. Conventional PID controllers in gas tanks must set initial parameters in advance according to engineers' knowledge, which will be unchanged during regulation. To remove these restrictions, variable universe fuzzy logic is applied to PID controller for parameters self-turning in this paper. By introducing the contraction and expansion factor of variable universe, both fuzzy universes and parameters of PID controller are on-line tuned, which improve the performance of controller. Finally, numerical simulation results showed the effectiveness of the proposed method.
{"title":"Variable Universe Fuzzy PID Control for Multi-level Gas Tank Pressure","authors":"Jian Zhang, Song Zhang, Zhihong Dan, Chufan Jiang","doi":"10.1109/CSE.2014.348","DOIUrl":"https://doi.org/10.1109/CSE.2014.348","url":null,"abstract":"This paper investigates pressure regulation for multi-level gas tank by variable universe fuzzy PID control. Pressure vessel is one of important equipments in process industry. Conventional PID controllers in gas tanks must set initial parameters in advance according to engineers' knowledge, which will be unchanged during regulation. To remove these restrictions, variable universe fuzzy logic is applied to PID controller for parameters self-turning in this paper. By introducing the contraction and expansion factor of variable universe, both fuzzy universes and parameters of PID controller are on-line tuned, which improve the performance of controller. Finally, numerical simulation results showed the effectiveness of the proposed method.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123277498","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}
Various malicious applications trend to access the user's files to achieve their functionalities. Such unauthorized file accesses may bring on the user data leakage or other threats. In this paper, we propose a novel light-weight hardware-assisted hyper visor, namely FVisor, to thwart such unauthorized file accesses. FVisor has three distinct advantages over existing hyper visor/host-based approaches: preinstalled commodity OS compatibility, non-by passable interception of files accesses and block level file-ware. Unlike typical hyper visors, deploying FVisor does not require OS reinstallation. FVisor intercepts the instruction-level interactions between the OS and the underlying hardware, instead of traditional API hooks. FVisor thus can manipulate the file accesses at the hyper visor layer instead of the OS layer, which is subvert able for the privileged malware. Besides, FVisor reconstructs the file system structures within the hyper visor at the block level without depending on the OS APIs. Our functionality evaluation shows FVisor is a feasible way to impede unauthorized file accesses while the performance evaluation shows desktop-oriented workloads achieve 93.57% of native speed on average.
{"title":"FVisor: Towards Thwarting Unauthorized File Accesses with a Light-Weight Hypervisor","authors":"Yan Wen, Jinjing Zhao, Shuanghui Yi, Xiang Li","doi":"10.1109/CSE.2014.136","DOIUrl":"https://doi.org/10.1109/CSE.2014.136","url":null,"abstract":"Various malicious applications trend to access the user's files to achieve their functionalities. Such unauthorized file accesses may bring on the user data leakage or other threats. In this paper, we propose a novel light-weight hardware-assisted hyper visor, namely FVisor, to thwart such unauthorized file accesses. FVisor has three distinct advantages over existing hyper visor/host-based approaches: preinstalled commodity OS compatibility, non-by passable interception of files accesses and block level file-ware. Unlike typical hyper visors, deploying FVisor does not require OS reinstallation. FVisor intercepts the instruction-level interactions between the OS and the underlying hardware, instead of traditional API hooks. FVisor thus can manipulate the file accesses at the hyper visor layer instead of the OS layer, which is subvert able for the privileged malware. Besides, FVisor reconstructs the file system structures within the hyper visor at the block level without depending on the OS APIs. Our functionality evaluation shows FVisor is a feasible way to impede unauthorized file accesses while the performance evaluation shows desktop-oriented workloads achieve 93.57% of native speed on average.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123281797","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}
Retrieving the wanted contents within large amount of video quickly is one of the key technologies of advertisement recognition. This paper analyzed the principle of AdaBoost algorithm and SURF matching algorithm, and designed a system of target face retrieving. The Adaboost algorithm was used to detect the faces from video key flames, and SURF matching algorithm was used to match the targeted face in a video. This system especially solved the matching problem for the changed targeted face brought by the different angle of view and scale in the video. This work was programmed by C# language in the environment of Visual Studio 2010 and EmguCV. The experimental results showed that the system could retrieve the appearing time of the target face accurately, and it was easy to be operated and was with a certain robustness and practicability.
快速提取海量视频中的通缉内容是广告识别的关键技术之一。分析了AdaBoost算法和SURF匹配算法的原理，设计了目标人脸检索系统。采用Adaboost算法对视频键焰中的人脸进行检测，采用SURF匹配算法对视频中的目标人脸进行匹配。该系统特别解决了视频中不同视角和比例所带来的目标人脸变化的匹配问题。本工作是在Visual Studio 2010和EmguCV环境下用c#语言编写的。实验结果表明，该系统能够准确地检索出目标人脸的出现时间，操作简单，具有一定的鲁棒性和实用性。
{"title":"Study of Target Face Search Algorithm for Video Advertisement","authors":"Jihong Liu, Yutao Fu, Qi Zhang, Yuting Geng","doi":"10.1109/CSE.2014.304","DOIUrl":"https://doi.org/10.1109/CSE.2014.304","url":null,"abstract":"Retrieving the wanted contents within large amount of video quickly is one of the key technologies of advertisement recognition. This paper analyzed the principle of AdaBoost algorithm and SURF matching algorithm, and designed a system of target face retrieving. The Adaboost algorithm was used to detect the faces from video key flames, and SURF matching algorithm was used to match the targeted face in a video. This system especially solved the matching problem for the changed targeted face brought by the different angle of view and scale in the video. This work was programmed by C# language in the environment of Visual Studio 2010 and EmguCV. The experimental results showed that the system could retrieve the appearing time of the target face accurately, and it was easy to be operated and was with a certain robustness and practicability.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122575128","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 vehicle state is of significant to examine and control vehicle performance. But some vehicle states such as vehicle velocity and side slip angle which are vital to active safety application of vehicle can not be measured directly and must be estimated instead. In this paper, a Cubature Kalman Filter (CKF) based algorithm for estimation vehicle velocity, yaw rate and side slip angle using steering wheel angle, longitudinal acceleration and lateral sensors is proposed. The estimator is designed based on a three-degree-of-freedom (3DOF) vehicle model. Effectiveness of the estimation is examined by comparing the outputs of the estimator with the responses of the vehicle model in Car Sim under double lane change and slalom conditions.
{"title":"Vehicle State Estimation Using Cubature Kalman Filter","authors":"Xiaoshuai Xin, Jinxi Chen, Jianxiao Zou","doi":"10.1109/CSE.2014.42","DOIUrl":"https://doi.org/10.1109/CSE.2014.42","url":null,"abstract":"The vehicle state is of significant to examine and control vehicle performance. But some vehicle states such as vehicle velocity and side slip angle which are vital to active safety application of vehicle can not be measured directly and must be estimated instead. In this paper, a Cubature Kalman Filter (CKF) based algorithm for estimation vehicle velocity, yaw rate and side slip angle using steering wheel angle, longitudinal acceleration and lateral sensors is proposed. The estimator is designed based on a three-degree-of-freedom (3DOF) vehicle model. Effectiveness of the estimation is examined by comparing the outputs of the estimator with the responses of the vehicle model in Car Sim under double lane change and slalom conditions.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"174 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122997522","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}
Android system has been widely utilized in smartphones, but it also has many security threats. Android uses the permission system to notice the user during installation about what permissions it will receive. However, according to related research, most users have poor understanding of permissions, and will accept the prompt directly. Over privileged applications will expose users to unnecessary permission warnings and increase the impact of a bug or vulnerability. In order to reduce user's trouble and avoid application over privilege, we focus on permissions for a given application and examine whether the application description provide any indication for why the application needs a permission. We propose an android semantic permission generator (ASPG) to understand what permissions an application needs from user's perspective. Our ASPG can get the semantic permissions based on the application description. Besides, ASPG will further tailor the semantically unrelated permissions. We analyze ten popular applications using the ASPG, finding that they all contain semantically unrelated permissions. After tailoring the semantically unrelated permissions, most of applications can run normally. Experimental results show ASPG is feasible. In addition, we provide a specification to support our ASPG better when an application runs abnormally.
{"title":"ASPG: Generating Android Semantic Permissions","authors":"Jiayu Wang, Qigeng Chen","doi":"10.1109/CSE.2014.132","DOIUrl":"https://doi.org/10.1109/CSE.2014.132","url":null,"abstract":"Android system has been widely utilized in smartphones, but it also has many security threats. Android uses the permission system to notice the user during installation about what permissions it will receive. However, according to related research, most users have poor understanding of permissions, and will accept the prompt directly. Over privileged applications will expose users to unnecessary permission warnings and increase the impact of a bug or vulnerability. In order to reduce user's trouble and avoid application over privilege, we focus on permissions for a given application and examine whether the application description provide any indication for why the application needs a permission. We propose an android semantic permission generator (ASPG) to understand what permissions an application needs from user's perspective. Our ASPG can get the semantic permissions based on the application description. Besides, ASPG will further tailor the semantically unrelated permissions. We analyze ten popular applications using the ASPG, finding that they all contain semantically unrelated permissions. After tailoring the semantically unrelated permissions, most of applications can run normally. Experimental results show ASPG is feasible. In addition, we provide a specification to support our ASPG better when an application runs abnormally.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122299489","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 Magneto-Rheological Fluid, MRF is a reversible material, this material would be an idea semi-active control device due to its reversible and easy-control properties. In this research, Solid Works 3D drawing software is used as the structural design and Max Well magnetic field analysis software is used to simulate the lines of magnetic force toward the innovation design "semi-active spiral flow channel magneto rheological damper" to improve the heat dissipation and the problem of precipitation. The Performance test of semi-active spiral flow channel magneto rheological damper uses ball screw and AC Servo Motor as actuator, the servo control system's function of displacement recorder and load cell as recorder of damping force. The syringe-type MR damper is an innovative design, the spiral flow can not only increase the length of the flow channel in a fixed distance, but also changes the excitating paramagnetic particles direction to be vertical with the direction of flow, and thus increases the ultimate shear strength of MRF. Without applying magnetic field, the syringe-type MR damper can generate the maximum damping force of 153N. When the current is 0.5A, the maximum damping force is about 301N, when the damping force adjustment coefficient is 1.97(=301/153), the damper is with high range of adjustable damping force. Most importantly, this design establishes a simple structure with lower cost.
{"title":"Design and Development of Sypinge-Type Magnetorheological Damper","authors":"Jinglong Tong, Kuangyuh Huang","doi":"10.1109/CSE.2014.44","DOIUrl":"https://doi.org/10.1109/CSE.2014.44","url":null,"abstract":"The Magneto-Rheological Fluid, MRF is a reversible material, this material would be an idea semi-active control device due to its reversible and easy-control properties. In this research, Solid Works 3D drawing software is used as the structural design and Max Well magnetic field analysis software is used to simulate the lines of magnetic force toward the innovation design \"semi-active spiral flow channel magneto rheological damper\" to improve the heat dissipation and the problem of precipitation. The Performance test of semi-active spiral flow channel magneto rheological damper uses ball screw and AC Servo Motor as actuator, the servo control system's function of displacement recorder and load cell as recorder of damping force. The syringe-type MR damper is an innovative design, the spiral flow can not only increase the length of the flow channel in a fixed distance, but also changes the excitating paramagnetic particles direction to be vertical with the direction of flow, and thus increases the ultimate shear strength of MRF. Without applying magnetic field, the syringe-type MR damper can generate the maximum damping force of 153N. When the current is 0.5A, the maximum damping force is about 301N, when the damping force adjustment coefficient is 1.97(=301/153), the damper is with high range of adjustable damping force. Most importantly, this design establishes a simple structure with lower cost.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126077131","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}
Software-Defined Networking (SDN) supports programmability by refactoring the network control plane. An SDN logically centralizes the control plane of network entities at the controller level. To achieve scalability, reliability, and availability, it is inevitable for the control plane to be configured as physically distributed. However, current deployments adopt a single SDN controller mainly due to problems of management complexity and costly maintenance. In this paper, we present a novel SDN architecture called a Wireless Proxy Controller (WiPCon) in order to increase the control plane efficiency of wireless networks. WiPCon involves a proxied control plane for wireless access points (APs) supporting SDN. It has a hybrid architecture in that the proxy SDN controller within the AP performs some of the main SDN controller roles, such as responding to specific network events, collecting wireless information, and local cooperation, although the control plane of the APs moves to the main SDN controller. Even though a single main SDN controller is used, WiPCon has robustness when it comes to network partitions or control bottlenecks, and flexibly copes with scalability issues that originate from dense deployment of APs. We analyzed various network factors through a preliminary implementation of WiPCon. Consequently, we verified that the proposed architecture efficiently supports control scalability and considerably reduces control overhead of the main SDN controller.
{"title":"WiPCon: A Proxied Control Plane for Wireless Access Points in Software Defined Networks","authors":"Won-Suk Kim, Sang-Hwa Chung, Jiameng Shi","doi":"10.1109/CSE.2014.186","DOIUrl":"https://doi.org/10.1109/CSE.2014.186","url":null,"abstract":"Software-Defined Networking (SDN) supports programmability by refactoring the network control plane. An SDN logically centralizes the control plane of network entities at the controller level. To achieve scalability, reliability, and availability, it is inevitable for the control plane to be configured as physically distributed. However, current deployments adopt a single SDN controller mainly due to problems of management complexity and costly maintenance. In this paper, we present a novel SDN architecture called a Wireless Proxy Controller (WiPCon) in order to increase the control plane efficiency of wireless networks. WiPCon involves a proxied control plane for wireless access points (APs) supporting SDN. It has a hybrid architecture in that the proxy SDN controller within the AP performs some of the main SDN controller roles, such as responding to specific network events, collecting wireless information, and local cooperation, although the control plane of the APs moves to the main SDN controller. Even though a single main SDN controller is used, WiPCon has robustness when it comes to network partitions or control bottlenecks, and flexibly copes with scalability issues that originate from dense deployment of APs. We analyzed various network factors through a preliminary implementation of WiPCon. Consequently, we verified that the proposed architecture efficiently supports control scalability and considerably reduces control overhead of the main SDN controller.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114192805","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}
Erasure code is an efficient redundancy solution to avoid permanent data losses in distributed storage system. By using erasure code, the original data is encoded into blocks which are stored on different nodes. When one node fails, the lost data block needs to be recovered by transmitting a large number of data from helper nodes, which is called repair. Intersecting zigzag sets codes (IZS codes) and hierarchical code are two kinds of codes which reduce the bandwidth overhead in repair. IZS codes reduce the amount of data uploaded by each helper node, while hierarchical codes reduce the number of nodes participating in repair. In this paper, we propose a class of code called intersecting zigzag sets-hierarchical code (IZ2SHC code) to unify them together. IZ2SHC code decreases repair degree as hierarchical code and reduces repair overhead compared with the latter. Besides, it realizes exact regeneration of the failed data, and need not encode in helper node during the repair, which reduces disk read cost for helper node when transferring data in repair.
{"title":"Reducing Repair Traffic with Exact and Uncoded Repair in Distributed Storage Systems: Intersecting Zigzag Sets Codes on Hierarchical Codes","authors":"Pengfei You, Zhen Huang, Changjian Wang, Yuxing Peng","doi":"10.1109/CSE.2014.150","DOIUrl":"https://doi.org/10.1109/CSE.2014.150","url":null,"abstract":"Erasure code is an efficient redundancy solution to avoid permanent data losses in distributed storage system. By using erasure code, the original data is encoded into blocks which are stored on different nodes. When one node fails, the lost data block needs to be recovered by transmitting a large number of data from helper nodes, which is called repair. Intersecting zigzag sets codes (IZS codes) and hierarchical code are two kinds of codes which reduce the bandwidth overhead in repair. IZS codes reduce the amount of data uploaded by each helper node, while hierarchical codes reduce the number of nodes participating in repair. In this paper, we propose a class of code called intersecting zigzag sets-hierarchical code (IZ2SHC code) to unify them together. IZ2SHC code decreases repair degree as hierarchical code and reduces repair overhead compared with the latter. Besides, it realizes exact regeneration of the failed data, and need not encode in helper node during the repair, which reduces disk read cost for helper node when transferring data in repair.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116246405","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 radix-4 Booth encoding or Modified Booth encoding (MBE) has been widely adopted in partial products generator to design high-speed redundant binary (RB) multipliers. Due to the existence of an error-correcting word (ECW) generated by MBE and RB encoding, the RB multiplier generates an additional RB partial product rows. An extra RB partial product accumulator (RBPPA) stage is needed for 2n-b RB MBE multiplier. The higher radix Booth algorithm than radix-4 can be adopted to reduce the number of partial products. However, the Booth encoding is not efficient because of the difficulty in generating hard multiples. The hard multiples problem in RB multiplier can be resolved by difference of two simple power-of-two multiples. This paper presents a new radix-16 RB Booth Encoding (RBBE-4) to avoid the hard multiple of high-radix Booth encoding without incurring any ECW. The proposed method leads to make high-speed and low-power RB multipliers. The experimental results show that the proposed RBBE-4 multiplier achieves significant improvement in delay and power consumption compared with the RB MBE multiplier and the current reported best RBBE-4 multipliers.
{"title":"A New Redundant Binary Partial Product Generator for Fast 2n-Bit Multiplier Design","authors":"Xiaoping Cui, Hu Wei, Chen Xin, Shumin Wang","doi":"10.1109/CSE.2014.171","DOIUrl":"https://doi.org/10.1109/CSE.2014.171","url":null,"abstract":"The radix-4 Booth encoding or Modified Booth encoding (MBE) has been widely adopted in partial products generator to design high-speed redundant binary (RB) multipliers. Due to the existence of an error-correcting word (ECW) generated by MBE and RB encoding, the RB multiplier generates an additional RB partial product rows. An extra RB partial product accumulator (RBPPA) stage is needed for 2n-b RB MBE multiplier. The higher radix Booth algorithm than radix-4 can be adopted to reduce the number of partial products. However, the Booth encoding is not efficient because of the difficulty in generating hard multiples. The hard multiples problem in RB multiplier can be resolved by difference of two simple power-of-two multiples. This paper presents a new radix-16 RB Booth Encoding (RBBE-4) to avoid the hard multiple of high-radix Booth encoding without incurring any ECW. The proposed method leads to make high-speed and low-power RB multipliers. The experimental results show that the proposed RBBE-4 multiplier achieves significant improvement in delay and power consumption compared with the RB MBE multiplier and the current reported best RBBE-4 multipliers.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"178 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116743957","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}
Yunong Zhang, Jianxi Liu, Dongsheng Guo, Sitong Ding, Hongzhou Tan
In recent years, the serious situation of Russian population causes concerns of the government, which also attracts great attentions of researchers from all over the world. The research on Russian population can help the government to make positive policies for solving the crisis and boosting economic growth. In this paper, implicitly considering almost all factors that influence population development, we present a 3-layer feed forward power-activated neuronet (PAN) equipped with the weights-and-structure-determination (WASD) algorithm for the estimation, correction and prediction of Russian population. Many numerical tests are conducted via WASD-PAN using past 2013-year Russian population data. We estimate the Russian population from 1000AD to 1800AD, correct it around 1897AD, and further indicate several possibilities of Russian population in the future. With the most possibility, Russian population is predicted to decrease steadily in next decade, while it is still possible that Russian population will (finally) increase.
{"title":"Power-Activated WASD Neuronet Based Russian Population Estimation, Correction, and Prediction","authors":"Yunong Zhang, Jianxi Liu, Dongsheng Guo, Sitong Ding, Hongzhou Tan","doi":"10.1109/CSE.2014.238","DOIUrl":"https://doi.org/10.1109/CSE.2014.238","url":null,"abstract":"In recent years, the serious situation of Russian population causes concerns of the government, which also attracts great attentions of researchers from all over the world. The research on Russian population can help the government to make positive policies for solving the crisis and boosting economic growth. In this paper, implicitly considering almost all factors that influence population development, we present a 3-layer feed forward power-activated neuronet (PAN) equipped with the weights-and-structure-determination (WASD) algorithm for the estimation, correction and prediction of Russian population. Many numerical tests are conducted via WASD-PAN using past 2013-year Russian population data. We estimate the Russian population from 1000AD to 1800AD, correct it around 1897AD, and further indicate several possibilities of Russian population in the future. With the most possibility, Russian population is predicted to decrease steadily in next decade, while it is still possible that Russian population will (finally) increase.","PeriodicalId":258990,"journal":{"name":"2014 IEEE 17th International Conference on Computational Science and Engineering","volume":"161 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123747377","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：