Volume - 6 | Issue - 1 | march 2024
Published
13 February, 2024
In many urban areas, traffic congestion has become one of the most challenging issues of modern life, resulting in detrimental effects on the environment, productivity loss, fuel wastage, and longer travel times. As a solution, people are increasingly turning to shared transportation modes due to the convenience of multi-modal journeys facilitated by smart transportation systems. The last mile problem refers to the fact that, in large cities, buses and trains deliver passengers to transit stations close to retail and job areas, leaving them needing another form of transportation to reach their final destination. By promoting the use of public transportation and addressing this issue, a smart bike-sharing system can contribute to reducing traffic congestion. The study presents a review of various methods that are associated with the designing of the bike sharing system and suggests a model incorporating various methods to derive solutions, with a focus on utilizing clustering algorithms for the analysis of the provided time series dataset. The study reveals that the application of algorithms such as the K-Means algorithm, Fuzzy C-means, etc. would be very effective in visualizing the resulting clusters and improve the forecasting accuracy.
KeywordsDemand Forecasting Collaborative Computing Bike Sharing System Machine Learning