An intelligent automatic vehicle traffic flow monitoring and control system
| dc.contributor.advisor | Gatsheni, B. N. | |
| dc.contributor.author | Marie, Theko Emmanuel | |
| dc.date.accessioned | 2017-05-23T00:16:54Z | |
| dc.date.available | 2017-05-23T00:16:54Z | |
| dc.date.issued | 2015-01 | |
| dc.description | M. Tech. (Information Technology, Faculty of Applied and Computer Sciences), Vaal University of Technology | en_US |
| dc.description.abstract | Traffic congestion is a concern within the main arteries that link Johannesburg to Pretoria. In this study Matlab function Randperm is used to generate random vehicle speeds on a simulated highway. Randperm is used to mimic vehicle speed sensors capturing vehicle traffic on the highway. Java sockets are used to send vehicle speed to the Road Traffic Control Centre (RTCC)-database server through a wireless medium. The RTCC-database server uses MySQL to store vehicle speed data. The domain controller with active directory together with a certificate server is used to manage and provide security access control to network resources. The wireless link used by speed sensors to transmit vehicle speed data is protected using PEAP with EAP-TLS which employs the use of digital certificates during authentication. A java database connectivity driver is used to retrieve data from MySQL and a multilayer perceptron (MLP) model is used to predict future traffic status on the highway being monitored i.e. next 5 minutes from previous 5 minutes captured data. A dataset of 402 instances was divided as follows: 66 percent training data was used to train the MLP model, 15 percent data used during validation and the remaining 19 percent was used to test the trained MLP model. An excel spreadsheet was used to introduce novel (19 percent data not used during training) data to the trained MLP model to predict. Assuming that the spreadsheet data represent captured highway vehicle data for the last 5 minutes, the model showed 100 percent accuracy in predicting the four classes: congested, out congested, into congested and normal traffic flow. Predicted traffic status is displayed for the motorist on the highway to know. Ability of the proposed model to continuously capture the traffic pattern on the highway (monitor) helps in redirecting (controlling) the highway traffic during periods of congestion. Implementation of this project will definitely decrease traffic congestion across main arteries of Johannesburg. Pollution normally experienced when cars idle for a long time during congestion will be reduced by free highway traffic flow. Frequent servicing of motor vehicles will no longer be required by the motorists. Furthermore the economy of Gauteng and South Africa as a whole will benefit due to increase in production. Consumers will also benefit in obtaining competitive prices from organizations that depend on haulage services. | en_US |
| dc.format.extent | xv, 119 leaves: illustrations | en_US |
| dc.identifier.uri | http://hdl.handle.net/10352/345 | |
| dc.language.iso | en | en_US |
| dc.subject | Traffic congestion | en_US |
| dc.subject | Randperm | en_US |
| dc.subject | Java sockets | en_US |
| dc.subject | Vehicle speed sensors | en_US |
| dc.subject | Road traffic control centre | en_US |
| dc.subject | Domain controller | en_US |
| dc.subject | Predicted traffic status | en_US |
| dc.subject | Security access control | en_US |
| dc.subject | Wireless link | en_US |
| dc.subject.ddc | 363.1256 | en_US |
| dc.subject.lcsh | Traffic congestion -- Management | en_US |
| dc.subject.lcsh | Vehicle detectors | en_US |
| dc.title | An intelligent automatic vehicle traffic flow monitoring and control system | en_US |
| dc.type | Thesis | en_US |