Dynamic fuzzy logis traffic light integrated system with accident detection and action /
The increase of vehicular traffic in the cities is a major concern for the Traffic Management Systems worldwide. The way traffic flow is regulated in the cities directly or indirectly affects the citizen's life. Thus there is need to optimize and regulate the flow of the traffic effectively to...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
Kuala Lumpur :
Kulliyyah of Information and Communication Technology, International Islamic University Malaysia,
2014
|
| Subjects: | |
| Online Access: | Click here to view 1st 24 pages of the thesis. Members can view fulltext at the specified PCs in the library. |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The increase of vehicular traffic in the cities is a major concern for the Traffic Management Systems worldwide. The way traffic flow is regulated in the cities directly or indirectly affects the citizen's life. Thus there is need to optimize and regulate the flow of the traffic effectively to meet the ever increasing demand. This research takes an innovative approach in solving the congestion related to the vehicular traffic, firstly by minimizing the wait time for the vehicles at traffic lights depending on the volume of the traffic and secondly by devising a solution to determine the exact location of the roadblock (caused by an accident or a vehicle breakdown). For the first part of the research, it is vital to study and compare the existing algorithms of the Traffic Control system and overcome their shortcomings. One of the key parameters on which the research is based on is the Cross Ratio (i.e. the number of cars that cross the signal per second). The cross ratio helps to decide the effectiveness of the algorithms so it can support in any case of vary on flow of traffic. The most significant result of the study is the proposed Dynamic Webster with Dynamic Cycle time method (DWDC), which resulted in the largest total Crossed Car. The second part of the research focuses on strategically placing the sensors and sending real time traffic flow data into the Traffic management system connected through an internal network. Our optimal algorithm supported by Fuzzy Logic to control and detect an accident on the traffic lights in real time. This research accomplishes an intelligent dynamic traffic light system for optimally controlling the traffic flow and accident detection in cities by its contributions in the proposed two-layer framework namely the architecture layer and the application layer. The highest result of the proposed algorithm (DWDC) showed a significant improvement of 98.28% of total crossed car ratio compared with previous methods, namely Dynamic Webster 93.23%, Webster 93.07%, Optimum equal intervals (Optimum Fixed Time) 92.64% and Equal Intervals (Fixed Time) 84.57% using iTraffic software. The location of the accident is also proved to be precise giving the exact lane (Section) and the block (Zone) of the affected car using FuzzyTech Program and the input of average traffic light cross ratio 2 sec was taken in real life scenarios from video recorded. The system also takes into account the possibility of false alarms. It respects the fact that algorithms, no matter how precise, might make mistakes. Testing the system resulted in a staggering 96% incident detection rate and only a 4% false alarm rate. The action system proposed has demonstrated a major rise of percentage total crossed car with 9.32% compared with DWDC, also intuitive to take an appropriate action to solve the congestion on the accident road compared with DWDC in accident scenarios that used iTraffic software. |
|---|---|
| Physical Description: | xvi, 250 leaves : ill. ; 30cm. |
| Bibliography: | Includes bibliographical references (leaves 206-211). |