Outlier Detection and Smoothing Process for Water Level Data Measured by Ultrasonic Sensor in Stream Flows

Bae, Inhyeok; Ji, Un

doi:10.3390/w11050951

Cited by 32 publications

(29 citation statements)

References 21 publications

(28 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Missing values in the data were estimated by linear interpolation. Outliers were checked using the modified z-score method [ 42 , 43 , 44 ] and removed from the data. This method is expressed by the following equation:

where

is the modified z-score, and

and

are the i th ordinate and median of a feature vector, respectively.…”

Section: Methodsmentioning

confidence: 99%

Spectrophotometric Online Detection of Drinking Water Disinfectant: A Machine Learning Approach

Hossain

Chow

Hewa

et al. 2020

Sensors

View full text Add to dashboard Cite

The spectra fingerprint of drinking water from a water treatment plant (WTP) is characterised by a number of light-absorbing substances, including organic, nitrate, disinfectant, and particle or turbidity. Detection of disinfectant (monochloramine) can be better achieved by separating its spectra from the combined spectra. In this paper, two major focuses are (i) the separation of monochloramine spectra from the combined spectra and (ii) assessment of the application of the machine learning algorithm in real-time detection of monochloramine. The support vector regression (SVR) model was developed using multi-wavelength ultraviolet-visible (UV-Vis) absorbance spectra and online amperometric monochloramine residual measurement data. The performance of the SVR model was evaluated by using four different kernel functions. Results show that (i) particles or turbidity in water have a significant effect on UV-Vis spectral measurement and improved modelling accuracy is achieved by using particle compensated spectra; (ii) modelling performance is further improved by compensating the spectra for natural organic matter (NOM) and nitrate (NO3) and (iii) the choice of kernel functions greatly affected the SVR performance, especially the radial basis function (RBF) appears to be the highest performing kernel function. The outcomes of this research suggest that disinfectant residual (monochloramine) can be measured in real time using the SVR algorithm with a precision level of ± 0.1 mg L−1.

show abstract

where

is the modified z-score, and

and

are the i th ordinate and median of a feature vector, respectively.…”

Section: Methodsmentioning

confidence: 99%

Spectrophotometric Online Detection of Drinking Water Disinfectant: A Machine Learning Approach

Hossain

Chow

Hewa

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…A recent work has also shown that water level measurements from an ultrasonic sensor can be improved if an algorithm scans the time-series data for removing outliers and random errors such as the ones caused by small waves [ 36 ]. From the experience with the Pikrodafni urban stream in the case study of our paper and the relatively short time-series that is already available though, no significant outliers are observed, while errors due to random factors are not expected to be high.…”

Section: Discussionmentioning

confidence: 99%

“…From the experience with the Pikrodafni urban stream in the case study of our paper and the relatively short time-series that is already available though, no significant outliers are observed, while errors due to random factors are not expected to be high. However, such an automatic algorithmic process for smoothing the data [ 36 ] may exclude the majority of abnormal values in the future when longer ultrasonic time-series data are expected.…”

Section: Discussionmentioning

confidence: 99%

Assessment of an Ultrasonic Water Stage Monitoring Sensor Operating in an Urban Stream

Panagopoulos

Παπαδόπουλος

Poulis

et al. 2021

Sensors

View full text Add to dashboard Cite

The monitoring of the water stage in streams and rivers is essential for the sustainable management of water resources, particularly for the estimation of river discharges, the protection against floods and the design of hydraulic works. The Institute of Marine Biological Resources and Inland Waters of the Hellenic Centre for Marine Research (HCMR) has developed and operates automatic stations in rivers of Greece, which, apart from their monitoring role, offer opportunities for testing new monitoring equipment. This paper compares the performance of a new ultrasonic sensor, a non-contact water stage monitoring instrument, against a pressure transducer, both installed at the same location in an urban stream of the metropolitan area of Athens. The statistical and graph analysis of the almost one-year concurrent measurements from the two sensors revealed that stage differences never exceeded 7%, while the ultrasonic measurements were most of the time higher than the respective pressure transducer ones during the low flow conditions of the dry period and lower during the wet period of the year, when high flow events occurred. It is also remarkable that diurnal air temperature variations under stable hydrologic conditions had an impact on the measured stage from the ultrasonic sensor, which varied its stage measurements within a small but non-negligible range, while the pressure transducer did not practically fluctuate. Despite a slightly increased sensitivity of the ultrasonic sensor to meteorological conditions, the paper concludes that non-contact sensors for the monitoring of the water stage in rivers can be useful, especially where danger for possible damage of submersible instruments is increased.

show abstract

“…The sensor used in this study is an ultrasonic sensor. Ultrasonic sensors work using a trigger and echo system to determine the distance from the center of the signal transmitter to the object being measured [1][2] [3]. To process sensor data from a flood detection system requires a microcontroller such as an ATMEGA238 microcontroller.…”

Section: Literature Surveymentioning

confidence: 99%

Implementation of GSM Communication on Flood Monitoring Systems Based on Multiple Locations Visualization

Satria¹,

Yana²,

Yusibani³

et al. 2019

IJRTE

View full text Add to dashboard Cite

Flooding is one of the national disaster tragedies that currently often occurs in various countries. Therefore the government encourages various government, private and community institutions to develop disaster mitigation systems. Disaster mitigation systems are short-term programs aimed at reducing disaster victims. Therefore, this paper aims to describe the results of research in building flood monitoring information systems by developing flood data visualization systems in many locations. The system as a whole consists of two systems namely a flood detection system as a client and a flood monitoring information system as a server. the two systems communicate in sending flood data using GSM services, namely SMS. Flood detection systems are designed using ultrasonic sensors, temperature sensors, rain sensors, Arduino Uno microcontrollers and GSM modules. While the flood monitoring information system server was designed using a GSM modem, web server application, mySQL database, PHP engine and Gammu. The results showed that the flood detection system can send flood data consisting of flood locations, water levels, temperatures and rain conditions to the flood monitoring information system using SMS. SMS data received can already be converted by a flood monitoring information system server to a flood visualization-based interface for many locations in real time.

show abstract

Outlier Detection and Smoothing Process for Water Level Data Measured by Ultrasonic Sensor in Stream Flows

Cited by 32 publications

References 21 publications

Spectrophotometric Online Detection of Drinking Water Disinfectant: A Machine Learning Approach

Spectrophotometric Online Detection of Drinking Water Disinfectant: A Machine Learning Approach

Assessment of an Ultrasonic Water Stage Monitoring Sensor Operating in an Urban Stream

Implementation of GSM Communication on Flood Monitoring Systems Based on Multiple Locations Visualization

Contact Info

Product

Resources

About