BUMPSTER: A Mobile Cloud Computing System for Speed Breakers and Ditches
Arhum Savera, Ahmed Zia, Muhammad Salman Edhi, Muhammad Tauseen, Jawwad Ahmed Shamsi · 2016
Road accidents are one of the universal problems faced by people all around the world. A major reason is reckless driving on speed breakers and ditches causing high causalities due to no warning signs, lack of street lights, substandard construction etc. There has been some research related to finding a Computer Science oriented solution but no substance in terms of a product. We present an Android application to solve this and have collected data from different parts of Karachi to detect upcoming speed breakers and ditches within a 10-12 meter radius. The application will be able to accurately warn users ahead of time and prevent hazards using a Support Vector Machine which has been trained with data from multiple devices. Speed breaker and ditch locations are loaded on the Cloud and filtered using a defined threshold. The model predicted speed breakers and ditches up to 85% accuracy with minimal power consumption.