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 significance level used to identify relevant parameters for water quality prediction?

p < 0.005

1/90

p.8

ANN Model

91.67%.

p.6

Statistical Significance

p < 0.005

p.4

ANN Model

Yj = ∑(Xi * Wij) + bj.

p.4

Logistic Regression

Binary classification.

p.7

Statistical Significance

ACC = (TP + TN)/(TP + TN + FP + FN) × 100

p.10

Water Quality Index

Applying the water quality index with fuzzy logic as a way to analyze multiple long-term groundwater quality data.

p.9

Machine Learning Algorithms

ANN, LR, and KNN.

p.8

ANN Model

83.33%.

p.5

Physicochemical Parameters

To normalize the data.

p.5

Statistical Significance

They help in understanding the differences between the two categories.

p.11

Machine Learning Algorithms

Improving prediction of water quality indices using novel hybrid machine-learning algorithms.

p.7

ANN Model

6 neurons in both the first and second hidden layers.

p.2

ANN Model

An innovative cascade forward approach based on advanced ANN.

p.1

Physicochemical Parameters

Nineteen parameters.

p.11

Physicochemical Parameters

Geospatial analysis coupled with logarithmic method for water quality assessment.

p.1

Water Quality Prediction

It is crucial for human as well as plant health.

p.11

ANN Model

Random forest as a predictive analytics alternative to regression in institutional research.

p.2

Water Quality Prediction

A rating reflecting the composite influence of different water quality parameters.

p.8

Comparative Performance Analysis

93%.

p.6

ANN Model

Four layers: 1 input layer, 2 hidden layers, and 1 output layer.

p.4

K-nearest Neighbour

It does not explicitly learn a model during the training phase.

p.2

Water Quality Prediction

To determine the ideal site for an agricultural groundwater recharge (AGR) project.

p.9

Statistical Significance

Five parameters including Fe, Cr, Na, Ca, and Mg are statistically significant.

p.5

Machine Learning Algorithms

Euclidean distance, Manhattan distance, and Minkowski distance.

p.6

Water Quality Prediction

Five parameters: Fe, Cr, Na, Ca, and Mg.

p.11

K-nearest Neighbour

Introduction to machine learning: K-nearest neighbors.

p.9

Physicochemical Parameters

Cr.

p.1

Statistical Significance

Mann—Whitney—Wilcoxon (MWW) test.

p.1

Machine Learning Algorithms

Artificial Neural Networks (ANN) and Logistic Regression (LR).

p.11

Logistic Regression

Understanding logistic regression analysis.

p.7

Statistical Significance

RC/SN = TP/(TP + FN) × 100

p.5

Water Quality Prediction

Pre-processing, identifying crucial parameters, classifying into drinkable and non-drinkable, evaluating system performance.

p.4

Machine Learning Algorithms

ANN, logistic regression, and K-nearest neighbour (KNN).

p.7

Logistic Regression

C = 1.0, penalty = 'l2', tolerance = 0.0001.

p.7

K-nearest Neighbour

With k = 7 and Minkowski distance metric.

p.7

Statistical Significance

Accuracy (ACC), recall (RC) or sensitivity (SN), specificity (SP), and precision (PR).

p.3

Water Quality Prediction

37 samples.

p.1

Water Quality Prediction

To identify the most effective parameters for WQI prediction.

p.1

ANN Model

Parameter 'Cr'.

p.7

Statistical Significance

PR = TP/(TP + FP) × 100

p.5

K-nearest Neighbour

A non-parametric and lazy learning algorithm that measures similarity between new data points and training samples.

p.4

Water Quality Prediction

Five categories: excellent, good, poor, very poor, and unsuitable for drinking.

p.4

Water Quality Prediction

8:2 (29 for training and 8 for testing).

p.4

ANN Model

Input layer, hidden layer, and output layer.

p.2

Water Quality Prediction

To accurately anticipate the quality of groundwater using thirteen physicochemical parameters.

p.7

Statistical Significance

SP = TN/(TN + FP) × 100

p.10

Water Quality Assessment

Indices and models of surface water quality assessment: Review and perspectives.

p.8

ANN Model

66.67%.

p.1

Comparative Performance Analysis

91.67%.

p.6

Statistical Significance

Ha: The median of the non-drinkable water is greater than the median of the drinkable water.

p.6

ANN Model

‘SoftMax’ activation function.

p.10

Water Quality Prediction

Prediction of groundwater quality using efficient machine learning technique.

p.10

Physicochemical Parameters

Modeling the relationship between land use and surface water quality.

p.2

Machine Learning Algorithms

Boosted regression trees (BRT) and random forest (RF).

p.9

Future Research Directions

The small size of the experimental dataset.

p.6

Statistical Significance

MWW test (Wilcoxon Rank Sum test)

p.7

Machine Learning Algorithms

ANN, LR, and KNN.

p.1

Water Quality Prediction

A significant proportion.

p.7

ANN Model

SoftMax activation function.

p.3

Comparative Performance Analysis

27 groundwater samples.

p.3

Machine Learning Algorithms

Knowledge-driven and machine learning decision tree-based approach, ANN, and deep learning.

p.10

Groundwater Quality Index

Assessment of PTEs in water resources by integrating HHRISK code, water quality indices, multivariate statistics, and ANNs.

p.11

Water Quality Prediction

River water quality index prediction and uncertainty analysis using machine learning models.

p.4

Water Quality Prediction

To classify water into different categories based on its quality.

p.4

Water Quality Prediction

Into two classes: drinkable (WQI < 100) and non-drinkable (WQI > 100).

p.11

Statistical Significance

Statistical learning algorithms in groundwater quality modeling.

p.6

Machine Learning Algorithms

Three ML algorithms: ANN, LR, and KNN.

p.10

Water Quality Prediction

Efficient water quality prediction using supervised machine learning.

p.3

Water Quality Prediction

pH, temperature, turbidity, dissolved oxygen, hardness, chlorides, alkalinity, and chemical oxygen demand.

p.3

Water Quality Prediction

The monthly water quality of the Lam Tsuen River in Hong Kong.

p.8

Comparative Performance Analysis

It led to an impressive increase in classification accuracy.

p.8

Future Research Directions

It requires only one parameter.

p.10

Groundwater Quality Index

Assessing groundwater quality using GIS.

p.2

ANN Model

By employing Bayesian regularization in an ANN model.

p.9

ANN Model

91.67%.

p.11

Comparative Performance Analysis

Review of water quality index models and their use for assessing surface water quality.

p.11

Groundwater Quality Index

Effectiveness of groundwater heavy metal pollution indices studies using deep-learning.

p.6

Statistical Significance

Ho: The median of the non-drinkable water is less than the median of the drinkable water.

p.2

ANN Model

They used neural networks with precipitation and water-table fluctuation as inputs.

p.4

K-nearest Neighbour

By measuring the similarity of new datapoints with the training samples.

p.10

Water Quality Index

Water quality assessment in terms of water quality index.

p.3

Physicochemical Parameters

Nineteen significant parameters including pH, Cond, TDS, and others.

p.6

Logistic Regression

Not provided in the text.

p.2

Machine Learning Algorithms

Naive Bayes classifier (NBC) and support vector machine (SVM).

p.3

Water Quality Prediction

37 samples collected from the Pindrawan tank command area of Raipur district, Chhattisgarh, India.

p.3

Groundwater Quality Index

Irrigation water quality indices (IWQIs), ANN models, and Gradient Boosting Regression (GBR).

p.3

Water Quality Prediction

To make accurate predictions.

p.10

Water Quality Assessment

Water quality assessment of streams using a qualitative collection method for benthic macroinvertebrates.

p.10

Water Quality Assessment

Surface and ground water pollution: Causes and effects of urbanization and industrialization in South Asia.

p.3

Statistical Significance

The Mann—Whitney—Wilcoxon test.

Study Smarter, Not Harder

Study Smarter, Not Harder