Flooding Level Classification by Gait Analysis of Smartphone Sensor Data

Abstract

Urban flooding is a common problem across the world. In India, it leads to casualties every year, and financial loss to the tune of tens of billions of rupees. The damage done due to flooding can be mitigated if the locations deserving attention are known. This will enable an effective emergency response, and provide enough information for the construction of appropriate storm water drains to mitigate the effect of floods. In this work, a new technique to detect flooding level is introduced, which requires no additional equipment, and consequent installation and maintenance costs. The gait characteristics in different flooding levels have been captured by smartphone sensors, which are then used to classify flooding levels. In order to accomplish this, smartphone sensor readings have been taken by 12 volunteers in pools of different depths, and have been used to train machine learning models in a supervised manner. Support vector machines, random forests and naïve bayes models have been attempted, of which, support vector machines perform best with a classification accuracy of 99.45%. Further analysis of the most relevant features for classification agrees with our intuition of gait characteristics in different depths.

A systematic review of municipal smart water for climate adaptation and mitigation

“…With an intent of identifying new infrastructure needs, one study uses crowd-sourced data to map street-level flooding (Panchal et al, 2019).…”

“…Zhang et al (2018) test the accuracy of different neural network models for simulating and predicting water levels in a combined sewer system. Panchal et al (2019) create an algorithm to detect floods from gait analysis of smartphone data, with the suggestion results can inform the construction of appropriate stormwater drains. Liu et al (2019) predict the quality of drinking water using a LSTM deep neural network.…”

IoT-Enabled Flood Severity Prediction via Ensemble Machine Learning Models

“…Sun and Scanlon [7] indicate that the use of machine learning has significantly improved the detection of early flood warning using powerful deep learning algorithms. Panchal et al [8] show that gait characteristics can be utilised to capture flood levels and used machine learning algorithms including support vector machine and random forest for the analysis of the data. While Furquim et al [9] propose a flood detection system based on IoT, machine learning and Wireless Sensor Networks (WSNs) in which fault-tolerance was embedded in their system to anticipate any risk of communication breakdown.…”