What are the three most widely used classifiers for water quality prediction in the study?
Click to see answer
ANN, LR, and KNN.
Click to see question
What are the three most widely used classifiers for water quality prediction in the study?
ANN, LR, and KNN.
What does the MWW test reveal about the parameters in water quality prediction?
Five parameters including Fe, Cr, Na, Ca, and Mg are statistically significant.
What is the highest classification accuracy obtained with all 17 parameters using the ANN model?
66.67%.
Which parameter is identified as the most significant for water quality prediction?
Cr.
What was the classification accuracy with the second experimental setup that included only five statistically significant parameters using the ANN model?
83.33%.
What is the classification accuracy achieved using the single parameter 'Cr' with ANN?
91.67%.
What is the proposed methodology for predicting water quality?
Pre-processing, identifying crucial parameters, classifying into drinkable and non-drinkable, evaluating system performance.
What was the classification accuracy with the last experimental setup that evaluated the performance of the statistically significant parameter 'Cr' using the ANN model?
91.67%.
What is the limitation of the proposed method according to the study?
The small size of the experimental dataset.
What is the primary goal of the present study?
To identify the most effective parameters for WQI prediction.
What is K-nearest neighbour (KNN) in the context of machine learning?
A non-parametric and lazy learning algorithm that measures similarity between new data points and training samples.
How did the performance of the second experimental setup compare to the first experimental setup?
It led to an impressive increase in classification accuracy.
How many physicochemical parameters were measured in the study?
Nineteen parameters.
What are some distance metrics used in K-nearest neighbour (KNN)?
Euclidean distance, Manhattan distance, and Minkowski distance.
What is the focus of the study by Asadollah, S.B.H.S. et al.?
River water quality index prediction and uncertainty analysis using machine learning models.
What was the highest recorded accuracy achieved by the deep neural network (DNN) proposed by U?
93%.
Which statistical test revealed strong significance in distinguishing between drinkable and non-drinkable water?
Mann—Whitney—Wilcoxon (MWW) test.
What is the purpose of the Standard Scaler (SS) in the pre-processing phase?
To normalize the data.
What is the main topic of the study by Uddin, M.G. et al.?
Review of water quality index models and their use for assessing surface water quality.
What is the significance level used to identify relevant parameters for water quality prediction?
p < 0.005
What makes the proposed method a highly practical solution for real-time water quality prediction from multiple sources?
It requires only one parameter.
What is the water quality index (WQI) used for?
To classify water into different categories based on its quality.
What machine learning techniques were used to validate the efficiency of the statistically significant parameters?
Artificial Neural Networks (ANN) and Logistic Regression (LR).
What is the significance of the mean values of parameters in drinkable and non-drinkable water?
They help in understanding the differences between the two categories.
What is the main focus of the study by Singha, S. et al.?
Effectiveness of groundwater heavy metal pollution indices studies using deep-learning.
Which test was used to identify the relevant parameters and discard irrelevant parameters?
MWW test (Wilcoxon Rank Sum test)
How many categories are used to classify water based on WQI?
Five categories: excellent, good, poor, very poor, and unsuitable for drinking.
What parameter achieved remarkably high classification accuracy using artificial neural networks?
Parameter 'Cr'.
What is the approach used by Agrawal, P. et al. in their study?
Geospatial analysis coupled with logarithmic method for water quality assessment.
How many parameters are found to be statistically significant in discriminating drinkable water from non-drinkable water?
Five parameters: Fe, Cr, Na, Ca, and Mg.
How is the experimental dataset categorized based on WQI?
Into two classes: drinkable (WQI < 100) and non-drinkable (WQI > 100).
What percentage of accuracy was achieved using parameter 'Cr' in artificial neural networks?
91.67%.
What is the focus of the study by Bui, D.T. et al.?
Improving prediction of water quality indices using novel hybrid machine-learning algorithms.
What is the null hypothesis in the context of the MWW test?
Ho: The median of the non-drinkable water is less than the median of the drinkable water.
What are the three ML algorithms used for evaluation?
ANN, LR, and KNN.
What is the ratio of the training set to the testing set in the experimental dataset?
8:2 (29 for training and 8 for testing).
What is the significance of maintaining the quality of groundwater?
It is crucial for human as well as plant health.
What is the applicability of the study by Khalil, A. et al.?
Statistical learning algorithms in groundwater quality modeling.
What is the alternative hypothesis in the context of the MWW test?
Ha: The median of the non-drinkable water is greater than the median of the drinkable water.
How many neurons were used in the first and second hidden layers of the ANN model?
6 neurons in both the first and second hidden layers.
What machine learning algorithms were used for water quality identification?
ANN, logistic regression, and K-nearest neighbour (KNN).
What proportion of Indians rely on groundwater for drinking?
A significant proportion.
What is the focus of the study by Lingjun, H. et al.?
Random forest as a predictive analytics alternative to regression in institutional research.
How many ML algorithms were used to evaluate the efficiency of the statistically significant parameters?
Three ML algorithms: ANN, LR, and KNN.
What activation function was used in the output layer of the ANN model?
SoftMax activation function.
What is the architecture of an Artificial Neural Network (ANN)?
Input layer, hidden layer, and output layer.
What is the Water Quality Index (WQI) defined as?
A rating reflecting the composite influence of different water quality parameters.
What is the main concept discussed in the study by Sperandei, S.?
Understanding logistic regression analysis.
How many layers does the ANN model comprise?
Four layers: 1 input layer, 2 hidden layers, and 1 output layer.
What parameters were used to achieve the highest accuracy in the LR model?
C = 1.0, penalty = 'l2', tolerance = 0.0001.
How is the activation at the jth neuron in an ANN calculated?
Yj = ∑(Xi * Wij) + bj.
What is the purpose of the Entropy Weight-based Groundwater Quality Index (EWQI)?
To accurately anticipate the quality of groundwater using thirteen physicochemical parameters.
What is the main topic of the study by Zhang, Z.?
Introduction to machine learning: K-nearest neighbors.
What activation function was used in the output layer of the ANN model?
‘SoftMax’ activation function.
What is the focus of the study by Ahmed, U. et al.?
Efficient water quality prediction using supervised machine learning.
How was the highest accuracy of KNN achieved?
With k = 7 and Minkowski distance metric.
What is logistic regression used for?
Binary classification.
How did Kord et al. (2022) model the Water Quality Index (WQI)?
They used neural networks with precipitation and water-table fluctuation as inputs.
What was the highest classification accuracy obtained for the LR model?
Not provided in the text.
What is the topic of the study by Singha, S. et al.?
Prediction of groundwater quality using efficient machine learning technique.
What parameters are used to predict contamination levels in groundwater?
pH, temperature, turbidity, dissolved oxygen, hardness, chlorides, alkalinity, and chemical oxygen demand.
What are the four commonly used metrics to assess classification algorithms' performance?
Accuracy (ACC), recall (RC) or sensitivity (SN), specificity (SP), and precision (PR).
What method does K-nearest neighbour (KNN) use to make predictions?
By measuring the similarity of new datapoints with the training samples.
What methods were used by Gaagai et al. to study groundwater quality in the Sahara aquifer in Algeria?
Irrigation water quality indices (IWQIs), ANN models, and Gradient Boosting Regression (GBR).
What is the main focus of the study by Tong, S.T. and Chen, W.?
Modeling the relationship between land use and surface water quality.
What is the mathematical formula for recall (RC) or sensitivity (SN)?
RC/SN = TP/(TP + FN) × 100
Why is K-nearest neighbour (KNN) considered a lazy learning algorithm?
It does not explicitly learn a model during the training phase.
How many groundwater samples were analyzed by Gaagai et al. in their study?
27 groundwater samples.
What is the main focus of the study by Babiker, I.S. et al.?
Assessing groundwater quality using GIS.
What ML algorithms were employed by Singha et al. (2021) to predict the Water Quality Index (WQI)?
Naive Bayes classifier (NBC) and support vector machine (SVM).
What is the mathematical formula for specificity (SP)?
SP = TN/(TN + FP) × 100
What did the study by Asadollah et al. in 2021 examine?
The monthly water quality of the Lam Tsuen River in Hong Kong.
What is the main focus of the study by Lenat, D.R.?
Water quality assessment of streams using a qualitative collection method for benthic macroinvertebrates.
What method did Gupta et al. (2019) introduce to predict groundwater quality?
An innovative cascade forward approach based on advanced ANN.
What is the mathematical formula for accuracy (ACC)?
ACC = (TP + TN)/(TP + TN + FP + FN) × 100
What is the main focus of the study by Tyagi, S. et al.?
Water quality assessment in terms of water quality index.
What techniques were used to identify water quality in different papers?
Knowledge-driven and machine learning decision tree-based approach, ANN, and deep learning.
How did Sakizadeh make highly accurate forecasts of Water Quality Index (WQI)?
By employing Bayesian regularization in an ANN model.
What is the mathematical formula for precision (PR)?
PR = TP/(TP + FP) × 100
What is the main focus of the study by Yan, T. et al.?
Indices and models of surface water quality assessment: Review and perspectives.
Why is it important to analyze multiple parameters to predict the quality of groundwater?
To make accurate predictions.
What ML models were utilized to predict the hardness of groundwater?
Boosted regression trees (BRT) and random forest (RF).
What is the main focus of the study by Sarker, B. et al.?
Surface and ground water pollution: Causes and effects of urbanization and industrialization in South Asia.
What statistical test was used to find discriminative parameters for water quality estimation?
The Mann—Whitney—Wilcoxon test.
What was the purpose of the ML algorithm developed for producing an artificial groundwater recharge site suitability map (AGRSSM)?
To determine the ideal site for an agricultural groundwater recharge (AGR) project.
What is the main focus of the study by Kord, M. and Arshadi, B.?
Applying the water quality index with fuzzy logic as a way to analyze multiple long-term groundwater quality data.
How many samples were considered for the experimental purpose in the study?
37 samples.
What were the selected optimal parameters used to identify the most impactful parameters for analyzing water quality?
Nineteen significant parameters including pH, Cond, TDS, and others.
What is the main focus of the study by Agbasi, J.C. and Egbueri, J.C.?
Assessment of PTEs in water resources by integrating HHRISK code, water quality indices, multivariate statistics, and ANNs.
What does the experimental dataset comprise in the study?
37 samples collected from the Pindrawan tank command area of Raipur district, Chhattisgarh, India.
