Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.supervisorBaliyan, Niyati-
dc.contributor.authorVerma, Niharika-
dc.descriptionMaster of Engineering -CSEen_US
dc.description.abstractA huge amount of spatio-temporal data is generated by millions of cabs in metro cities all around the world. This data, if analyzed correctly, can provide a better understanding of the taxi demand. With the increasing preference of customers to have a hassle-free experience, cabs are becoming the ultimate choice for all due to their point to point service. The inability of the taxi companies to meet ever increasing demand of cabs leads to high unavailability of cabs during peak hours and low usage during non peak hours. This taxi imbalance problem can be resolved by analyzing the spatial data and predicting the demand hotspots to identify areas with potential passengers. Moreover, with the increasing demand of cabs around the city, the cabs need to be dispatched in such a way that the average waiting time of the cabs and the cancellation rate is reduced at the same time. This can be achieved by selecting appropriate places in the city for the cab bases to be setup. The knowledge about the base setup can help map the nearest cab of the taxi base to a pickup location. Hence, this thesis aims at filtering the data on various parameters such as day of the week, time of the day, nearest taxi base etc. to segregate the data for further useful insights. In this thesis, a multi-layer clustering approach is implemented for hotspot detection and selection of taxi base setup location. Any new incoming request is first mapped to the nearest taxi base for allocation of cab and then it is identified in which hotspot region, the area falls. Using this approach, a region specific allocation of cabs is enhanced. Clustering techniques are used on the filtered dataset to provide the popularity of regions in the city at different timings. K-means, k-medians and CLARA clustering techniques are used and the results from these clustering techniques are compared. The clustering technique that provides the best results for spatial data is chosen for hotspot detection and taxi base setup based on the day and time. This date and time based hotspot detection helps the taxi companies to dispatch the cabs at locations predicted to have higher number of passengers in future resulting in better service for customers and increased revenue for the shareholders.en_US
dc.subjectMachine Learningen_US
dc.titleAn Improved Multi-Layer Clustering Approach for Enhancing Informed Taxi Drivingen_US
Appears in Collections:Masters Theses@CSED

Files in This Item:
File Description SizeFormat 
Thesis File - 801532036 (1).pdf2.34 MBAdobe PDFThumbnail

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.