Pub Date : 2014-12-01DOI: 10.1109/ICVES.2014.7063725
Sohel Ahmed, Q. Sultana, K. D. Rao
Differential Global Positioning System (DGPS) is a technique to improve the accuracy of the GPS positioning. In DGPS, error correction signal is transmitted to the surrounding rovers. Any correction loss during transmission may lead to navigation inaccuracy. This problem can be minimized by incorporating Dynamic Neural Networks (DNNs) at the rovers. DNNs can be used to predict the present and future DGPS correction values by utilizing the past correction values. This paper presents the prediction of error correction values using DNNs such as Focused Time Delay Neural Network (FTDNN), Distributed Time Delay Neural Network (DTDNN), Nonlinear Auto Regressive with eXogenous input Neural Network (NARXNN), Nonlinear Auto Regressive Neural Network (NARNN) and Layer Recurrent Neural Network (LRNN). The results show that the Mean Square Error (MSE) in predicted correction values due to third order LRNN is the least (2.5316e- 05 m).
{"title":"Comparative analysis of DGPS predicted corrections using dynamic neural networks","authors":"Sohel Ahmed, Q. Sultana, K. D. Rao","doi":"10.1109/ICVES.2014.7063725","DOIUrl":"https://doi.org/10.1109/ICVES.2014.7063725","url":null,"abstract":"Differential Global Positioning System (DGPS) is a technique to improve the accuracy of the GPS positioning. In DGPS, error correction signal is transmitted to the surrounding rovers. Any correction loss during transmission may lead to navigation inaccuracy. This problem can be minimized by incorporating Dynamic Neural Networks (DNNs) at the rovers. DNNs can be used to predict the present and future DGPS correction values by utilizing the past correction values. This paper presents the prediction of error correction values using DNNs such as Focused Time Delay Neural Network (FTDNN), Distributed Time Delay Neural Network (DTDNN), Nonlinear Auto Regressive with eXogenous input Neural Network (NARXNN), Nonlinear Auto Regressive Neural Network (NARNN) and Layer Recurrent Neural Network (LRNN). The results show that the Mean Square Error (MSE) in predicted correction values due to third order LRNN is the least (2.5316e- 05 m).","PeriodicalId":248904,"journal":{"name":"2014 IEEE International Conference on Vehicular Electronics and Safety","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114704114","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 : 2014-12-01DOI: 10.1109/ICVES.2014.7063739
Swapnil A. Umre, Komal P. Mehta, L. Malik
The Vehicular Ad-hoc Networks (VANETs) is the most promising technology that can provide solution for vehicular traffic and safety. VANET establishes vehicle to vehicle communication, which can be implemented for the safety of the vehicles and for other services. The optimal utilization of VANET technology can be achieved with specially designed Routing Protocols. The enhancement in the technology asks for more efficient Routing Algorithms to be developed to meet the desired system requirements. The proposed system enables us to make maximum utilization of the VANET technology when used with Bio-Inspired computing for communication between nodes within a zone. The genetic algorithm proposed in this system can help to find out the most optimal path from source to destination. It can also help to reduce the energy consumption and delay with lesser data lost during transmission. The proposed system provides us a way to make the most utilization of the VANET technology.
{"title":"Performance improvement of communication in zone based routing that uses cluster formation and bio-inspired computing in VANET","authors":"Swapnil A. Umre, Komal P. Mehta, L. Malik","doi":"10.1109/ICVES.2014.7063739","DOIUrl":"https://doi.org/10.1109/ICVES.2014.7063739","url":null,"abstract":"The Vehicular Ad-hoc Networks (VANETs) is the most promising technology that can provide solution for vehicular traffic and safety. VANET establishes vehicle to vehicle communication, which can be implemented for the safety of the vehicles and for other services. The optimal utilization of VANET technology can be achieved with specially designed Routing Protocols. The enhancement in the technology asks for more efficient Routing Algorithms to be developed to meet the desired system requirements. The proposed system enables us to make maximum utilization of the VANET technology when used with Bio-Inspired computing for communication between nodes within a zone. The genetic algorithm proposed in this system can help to find out the most optimal path from source to destination. It can also help to reduce the energy consumption and delay with lesser data lost during transmission. The proposed system provides us a way to make the most utilization of the VANET technology.","PeriodicalId":248904,"journal":{"name":"2014 IEEE International Conference on Vehicular Electronics and Safety","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127290609","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 : 2014-12-01DOI: 10.1109/ICVES.2014.7063724
Spandana Mounica. U, Praveen Mande, Swathi Mugada
Human lives are being greatly menaced by road accidents. Accidents due to overtaking pose an even greater threat. Disciplined behavioral mechanisms of animal groups have promoted development in various technological fields including crowd simulation. On this basis, the proposed work develops Overtaking Possibility Check Algorithm (OPC) and the Overtaking Algorithm (OT) which operates on the front and the rear vehicles respectively. The algorithms provide a new mechanism for avoiding accidents due to overtaking by mutual communication between them. The various components of the proposed system work in collaboration to indicate the possibilities to overtake with detailed review of the recommended speed, trajectories. In other scenarios where immediate overtaking is not possible a suggested deceleration of the front vehicle is recommended. It is ensured that the safe distances are maintained throughout the process thus avoiding tailgating as well. The safe range space around the vehicle is considered to be delimited by an ellipse shaped boundary. The algorithm refrains to allow overtaking if the safe distances cannot be maintained i.e. if there is a significant amount of overlap between the ellipse regions of the vehicles. After the simulation of the above model it is inferred that algorithm's dynamic implementation in real time scenario could potentially reduce the number of accidents occurring due to overtaking.
{"title":"The intelligent overtaking model for reducing road accidents based on animal group behavior","authors":"Spandana Mounica. U, Praveen Mande, Swathi Mugada","doi":"10.1109/ICVES.2014.7063724","DOIUrl":"https://doi.org/10.1109/ICVES.2014.7063724","url":null,"abstract":"Human lives are being greatly menaced by road accidents. Accidents due to overtaking pose an even greater threat. Disciplined behavioral mechanisms of animal groups have promoted development in various technological fields including crowd simulation. On this basis, the proposed work develops Overtaking Possibility Check Algorithm (OPC) and the Overtaking Algorithm (OT) which operates on the front and the rear vehicles respectively. The algorithms provide a new mechanism for avoiding accidents due to overtaking by mutual communication between them. The various components of the proposed system work in collaboration to indicate the possibilities to overtake with detailed review of the recommended speed, trajectories. In other scenarios where immediate overtaking is not possible a suggested deceleration of the front vehicle is recommended. It is ensured that the safe distances are maintained throughout the process thus avoiding tailgating as well. The safe range space around the vehicle is considered to be delimited by an ellipse shaped boundary. The algorithm refrains to allow overtaking if the safe distances cannot be maintained i.e. if there is a significant amount of overlap between the ellipse regions of the vehicles. After the simulation of the above model it is inferred that algorithm's dynamic implementation in real time scenario could potentially reduce the number of accidents occurring due to overtaking.","PeriodicalId":248904,"journal":{"name":"2014 IEEE International Conference on Vehicular Electronics and Safety","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126518175","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：