A comprehensive comparative analysis of deep learning tools for modeling failures in smart water taps

Predicting early-stage failure in smart water taps (SWT) and selecting the most efficient tools to build failure prediction models are many challenges that water institutions face. In this study, three Deep Learning (DL) algorithms, i.e., the Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN) and Bi-directional Long Short-Term Memory (BiLSTM), were selected to analyse and determine the most appropriate among them for failure prediction in SWTs. This study uses a historical dataset acquired from smart water withdrawal taps to determine the most efficient DL neural network architecture for failure prediction in the SWT, leading to a hybrid model's development. After a comprehensive evaluation of the three ML models, findings show that a hybrid combination of the CNN and Bi-LSTM (CNN-BiLSTM) models is a better solution for investigating failures in the SWT.

[1]  Xu Zhe,et al.  Pressure prediction and abnormal working conditions detection of water supply network based on LSTM , 2020 .

[2]  Fan Xiong,et al.  Auto-detection of epileptic seizure events using deep neural network with different feature scaling techniques , 2019, Pattern Recognit. Lett..

[3]  B. Choubin,et al.  Susceptibility Mapping of Soil Water Erosion Using Machine Learning Models , 2020, Water.

[4]  Bahram Choubin,et al.  Ensemble Boosting and Bagging Based Machine Learning Models for Groundwater Potential Prediction , 2020, Water Resources Management.

[5]  Yang-Ping Yao,et al.  Machine learning for pore-water pressure time-series prediction: Application of recurrent neural networks , 2021 .

[6]  Min Zuo,et al.  Comparative analysis of surface water quality prediction performance and identification of key water parameters using different machine learning models based on big data. , 2019, Water research.

[7]  M. N. Sulaiman,et al.  A Review On Evaluation Metrics For Data Classification Evaluations , 2015 .

[8]  I. Ray,et al.  From intermittent to continuous service: Costs, benefits, equity and sustainability of water system reforms in Hubli-Dharwad, India , 2018, World Development.

[9]  Denis A. Hughes,et al.  Facing a future water resources management crisis in sub-Saharan Africa , 2019, Journal of Hydrology: Regional Studies.

[10]  A. Azapagic,et al.  Environmental assessment of domestic water supply options for remote communities. , 2020, Water research.

[11]  Marcus Liwicki,et al.  Scene labeling with LSTM recurrent neural networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Md. Ashad Alam,et al.  Prediction of Algal Chlorophyll-a and Water Clarity in Monsoon-Region Reservoir Using Machine Learning Approaches , 2019, Water.

[13]  Jürgen Schmidhuber,et al.  Bidirectional LSTM Networks for Improved Phoneme Classification and Recognition , 2005, ICANN.

[14]  E. Dungumaro.  Socioeconomic differentials and availability of domestic water in South Africa , 2007 .

[15]  Fitore Muharemi,et al.  Machine learning approaches for anomaly detection of water quality on a real-world data set* , 2019, J. Inf. Telecommun..

[16]  Mohammad Khubeb Siddiqui,et al.  Application of Receiver Operating Characteristics (ROC) on the Prediction of Obesity , 2020, Brazilian Archives of Biology and Technology.

[17]  Francisco Herrera,et al.  Incremental learning model inspired in Rehearsal for deep convolutional networks , 2020, Knowl. Based Syst..

[18]  Rasu Eeswaran,et al.  Forecast of short-term daily reference evapotranspiration under limited meteorological variables using a hybrid bi-directional long short-term memory model (Bi-LSTM) , 2020 .

[19]  Akbar Siami Namin,et al.  A Comparison of ARIMA and LSTM in Forecasting Time Series , 2018, 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA).

[20]  Kaizhi Wang,et al.  Prediction of Satellite Time Series Data Based on Long Short Term Memory-Autoregressive Integrated Moving Average Model (LSTM-ARIMA) , 2019, 2019 IEEE 4th International Conference on Signal and Image Processing (ICSIP).

[21]  Sarah L. Smiley.  Complexities of water access in Dar es Salaam, Tanzania , 2013 .

[22]  Minho Lee,et al.  Continuous Timescale Long-Short Term Memory Neural Network for Human Intent Understanding , 2017, Front. Neurorobot..

[23]  Francisco Herrera,et al.  Big data preprocessing: methods and prospects , 2016 .