Detecting and Alerting Damaged Roads Using Smart Street System

Abstract

Develop an infrastructure-free approach for anomaly detection and identification based on data collected through a smartphone application (SMART STREET). The approach is capable of effectively finding the damaged roads and effectively classifying roadway obstacles and knowing its type using machine learning algorithms, and accelerometer in smartphone ,as well as prioritizing actionable ones in need of immediate attention based on a proposed “anomaly index.” We explore some algorithms that combine clustering with classification and introduce appropriate regularization in order to concentrate on a sparse set of most relevant features, which has the effect of reducing over fitting.I introduce, combines novel metrics of obstacle irregularity computed based on the data captured and alerting system by the smartphone application (Smart Street). It Results by capturing the location of damaged road and transferring it to the corporation by an alert message .The data collector in corporation will receive the alert message and instruct the corporation to take necessary action for repairing the road.