The main objective of this study was to assess the applicability of IoT (Internet of Things)-based flood management under climate change by developing intelligent water level monitoring platform based on IoT. In this study, Arduino Uno was selected as the development board, which is an open-source electronic platform. Arduino Uno was designed to connect the ultrasonic sensor, temperature sensor, and data logger shield for implementing IoT. Arduino IDE (Integrated Development Environment) was selected as the Arduino software and used to develop the intelligent algorithm to measure and calibrate the real-time water level automatically. The intelligent water level monitoring platform consists of water level measurement, temperature calibration, data calibration, stage-discharge relationship, and data logger algorithms. Water level measurement and temperature calibration algorithm corrected the bias inherent in the ultrasonic sensor. Data calibration algorithm analyzed and corrected the outliers during the measurement process. The verification of the intelligent water level measurement algorithm was performed by comparing water levels using the tape and ultrasonic sensor, which was generated by measuring water levels at regular intervals up to the maximum level. The statistics of the slope of the regression line and were 1.00 and 0.99, respectively which were considered acceptable. The error was 0.0575 cm. The verification of data calibration algorithm was performed by analyzing water levels containing all error codes in a time series graph. The intelligent platform developed in this study may contribute to the public IoT service, which is applicable to intelligent flood management under climate change.
[1]
Ge Guo,et al.
Nonlinear platoon control of Arduino cars with range-limited sensors
,
2015,
Int. J. Control.
[2]
C.-L. Cheng,et al.
Coefficient of determination for multiple measurement error models
,
2014,
J. Multivar. Anal..
[3]
Hyun Suk Park,et al.
Combined Filtering Model Using Voting Rule and Median Absolute Deviation for Travel Time Estimation
,
2013
.
[4]
Stratis Kanarachos,et al.
Intelligent road adaptive suspension system design using an experts' based hybrid genetic algorithm
,
2015,
Expert Syst. Appl..
[5]
Andry Rakotonirainy,et al.
Driver's behavioural changes with new intelligent transport system interventions at railway level crossings--A driving simulator study.
,
2015,
Accident; analysis and prevention.
[6]
Richard A. Russell,et al.
The coefficient of determination: what determines a useful R² statistic?
,
2012,
Investigative ophthalmology & visual science.
[7]
Xinrong Li,et al.
Wireless Sensor Network System Design Using Raspberry Pi and Arduino for Environmental Monitoring Applications
,
2014,
FNC/MobiSPC.
[8]
Jeffrey G. Arnold,et al.
Model Evaluation Guidelines for Systematic Quantification of Accuracy in Watershed Simulations
,
2007
.