ROUTE OPTIMIZATION USING HYBRID CLUSTERING AND OPTIMIZED LEVY FRUIT FLY ALGORITHM

Abstract

            Best route finding plays a crucial role in modern transportation systems for efficient traffic management. This study proposes a novel approach for best route finding and route optimization using a hybrid clustering and optimization method. The first step involves applying Hierarchical Clustering with K-Means Clustering to the traffic data, followed by applying the Deepwalk method for signal processing. Deepwalk generates random walks on a graph and uses a Skip-gram model to capture collocations within a specified window, aiding in traffic pattern recognition. The second step utilizes an optimized Levy fruit fly algorithm for route optimization. This optimization algorithm is inspired by the gathering good behavior of fruit flies and aims to find the best route considering best route and other factors. The algorithm iteratively refines routes based on real-time traffic data, leading to improved route recommendations. Lastly, a comparative analysis is conducted to evaluate the performance of the proposed method against existing techniques. Metrics such as travel time, traffic flow, and route efficiency are used to assess the effectiveness of the hybrid clustering and optimization approach. The results demonstrate the potential of the proposed method in achieving efficient traffic management and route planning in urban environments.