Water management using genetic algorithm-based machine learning

Sophia, S.; Sharmila, V. Ceronmani; Suchitra, S.; SudalaiMuthu, T; Pavithra, B.

doi:10.1007/s00500-020-05009-0

Cited by 16 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Genetic algorithm (GA) [ 20 ], particle swarm optimization (PSO) [ 21 ], spider swarm optimization (SSO) [ 21 ], and grey wolf optimization algorithm (GWO) [ 22 ], which are among the intelligent optimization algorithms, are applied to solve the Panjiakou Reservoir Group's joint flood control optimal operation model, and the efficiency and optimal operation results of each algorithm are compared and analyzed.…”

Section: Methodsmentioning

confidence: 99%

Optimization of Reservoir Flood Control Operation Based on Multialgorithm Deep Learning

Xue

Xie

Liu

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

With the rapid development of China’s social economy, it is the most important task for the water conservancy industry to make use of the existing water conservancy engineering measures to carry out the research on river basin flood control dispatching. Large-scale joint operation of river basins usually needs to consider meteorological and hydrological conditions, historical flood data, multireservoir engineering conditions, and multiple flood control targets, which is a complex decision-making problem. Therefore, electing the optimal operation model of reservoir flood control optimization is very important. In this paper, Luanhe River Basin is taken as the research area, and three kinds of constraints, namely, water balance constraint, reservoir flood control capacity constraint, and water release decision constraint, are set to construct the flood control optimization model. Taking the minimum square of the sum of reservoir discharge and interval flood discharge as the objective function, genetic algorithm (GA), particle swarm optimization (PSO), Spider swarm optimization (SSO), and grey wolf optimization (GWO) are introduced into flood control optimal operation to seek the minimum value of objective function, and the results are compared and analyzed. Through the analysis of optimization results, the optimization ability and convergence effect of grey wolf optimization algorithm are better than those of genetic algorithm and particle algorithm, and the results are more stable than those of spider swarm algorithm. It has a good model structure and can make full use of the results of three wolf groups for optimization. Through the analysis of scheduling results, the results of genetic algorithm and particle swarm optimization algorithm are similar, while those of spider swarm optimization algorithm and grey wolf optimization algorithm are similar and slightly better than those of the first two. Moreover, the search range of grey wolf optimization algorithm for solving long sequence problems is wider and the calculation time is shorter. Therefore, the grey wolf optimization algorithm can be applied to solve the flood control operation optimization model of Panjiakou Reservoir Group.

show abstract

Section: Methodsmentioning

confidence: 99%

Optimization of Reservoir Flood Control Operation Based on Multialgorithm Deep Learning

Xue

Xie

Liu

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Again applying the standard neural network which would be equal to a CNN, because the unit of factors will be seriously greater, the training period will also be increment simultaneously. In a CNN, since the unit of factors is extremely decreasing, training period is simultaneously reducing [30]. Also, supposing excellent training, we can make a standard neural network whose characteristics will be similar to a CNN.…”

Section: Classification and Labellingmentioning

confidence: 99%

Design of Intelligent Insect Monitoring System Using Deep Learning Techniques

Sharmila¹,

Chauhan²,

Kumar³

et al. 2021

Proceedings of the First International Conference on Computing, Communication and Control System, I3CAC 2021, 7-8 June 2021, Bh

View full text Add to dashboard Cite

The agriculture field is growing up its potential to better the demand of food and delivers healthy and nutritious foodstuff. This project presents an insect or pest detection and classification for the plant using machine learning. It's a challenging part for the farmers to the crops which are acquiring defective and the degree or grade of excellence is also getting reduced day by day due to various pest or insect attacks. Earlier insect identification has been a big issue due to not well-skilled taxonomists to name the insects based on surface structure construction features accurately. Here, the proposed system will be a research tool for the study of early insects on the plants and leaves which will classify it using CNN and K-Means Clustering algorithm in machine learning. The detection analysis of insects was executed with shorter computational point in time for wang dataset using insect image Median Filter. The final classification results of accuracy were utilized to identify the pest and insects in the earliest period and increased the period to grow the harvest fertility and crop degree of excellence in the field of agriculture.

show abstract

“…For solving both, constrained and unconstrained optimization problems to generate high quality solutions, Gino Sophia et al [3] describes the approach of a proposed intelligent regressor system using Genetic operations and ANN. As Genetic algorithms look for optimal combination of solutions for brute force search problems, objective functions such as Crossover, Mutation, Fitness scaling, Selection and migration were used for increasing optimization performance of system developed and a Regression accuracy of about 98% was achieved by the model.…”

Section: Related Workmentioning

confidence: 99%

A Hybrid Approach for Heart Disease Prediction

Angappan¹,

Meenakshi²,

E³

et al. 2021

Proceedings of the First International Conference on Computing, Communication and Control System, I3CAC 2021, 7-8 June 2021, Bh

View full text Add to dashboard Cite

An estimated count of 17900000people, i.e., 31% of deaths is related to cardiac diseases every year. This number is projected to rise to 22million by the end of this decade, making cardiac diseases among the most common global sources of death. The only effective method is ECG tests among various other limited methods for the detection of heart diseases. With regard to cardiac diseases, early diagnosis has the potential to produce better treatment outcomes. Hence, this paper discusses a Machine Learning methodology to detect heart diseases using the Data Set for Heart Disease by the repository of UCI Machine learning. This system is developed based on classification algorithms such as Support Vector Machines, K-Nearest Neighbour, Naïve Bayes, Decision Trees and Random forest classifiers. We define a hybrid stacking method and genetic algorithm which increases the accuracy achieved by the basic individual data mining techniques of classification.

show abstract

Water management using genetic algorithm-based machine learning

Cited by 16 publications

References 11 publications

Optimization of Reservoir Flood Control Operation Based on Multialgorithm Deep Learning

Optimization of Reservoir Flood Control Operation Based on Multialgorithm Deep Learning

Design of Intelligent Insect Monitoring System Using Deep Learning Techniques

A Hybrid Approach for Heart Disease Prediction

Contact Info

Product

Resources

About