Sakthivel Selvaraj's starred repositories
Genetic-Algorithm-RNN
Using Genetic Algorithms to optimize Recurrent Neural Network's Configuration
HeartHealthPrediction
The major reason for the death in worldwide is the heart disease in high and low developed countries. The data scientist uses distinctive machine learning techniques for modeling health diseases by using authentic dataset efficiently and accurately. The medical analysts are needy for the models or systems to predict the disease in patients before the strike. High cholesterol, unhealthy diet, harmful use of alcohol, high sugar levels, high blood pressure, and smoking are the main symptoms of chances of the heart attack in humans. Data Science is an advanced and enhanced method for the analysis and encapsulation of useful information. The attributes and variable in the dataset discover an unknown and future state of the model using prediction in machine learning. Chest pain, blood pressure, cholesterol, blood sugar, family history of heart disease, obesity, and physical inactivity are the chances that influence the possibility of heart diseases. This project emphasizes to evaluate different algorithms for the diagnosis of heart disease with better accuracies by using the patient’s data set because predictions and descriptions are fundamental objectives of machine learning. Each procedure has unique perspective for the modeling objectives. Algorithms have been implemented for the prediction of heart disease with our Heart patient data set
Weather-Prediction-Time-Series-Forecasting
Predicting Weather using CNN-LSTM
Portfolio-Optimization-using-Genetic-Algorithm
Portfolio optimization using Genetic algorithm.
epistatic-net
Epistatic Net is an algorithm which allows for spectral regularization of deep neural networks to predict biological fitness functions (e.g., protein functions).
house-price-prediction
Using Genetic Algorithm and Neural Networks to predict housing price
intel-
A variety of conditions that affect your heart are referred to as heart disease. According to World Health Organization reports, cardiovascular diseases are now the leading cause of death worldwide, with 17.9 million deaths per year. Artificial intelligence and machine learning are now widely acknowledged to play an important role in the medical field, where they are used to diagnose diseases, classify or forecast outcomes using a variety of machine learning and deep learning models. Machine learning algorithms can quickly adapt to a thorough analysis of genetic data. For accurate estimation, medical records can be changed and studied more thoroughly, and better models can be identified for accurate prediction. Using a different algorithm, several researchers have reported on the prediction of heart problems.The aim of this study is to diagnose heart disease using machine learning algorithms. Machine Learning can help predict the presence or absence of locomotor disorders, heart diseases, and other conditions. Artificial intelligence (AI) has the potential to solve this problem right now. To improve the classification accuracy of a heart disease data set, we propose combining KNN, logistics regression, SVM, Random Forest algorithm, and decision tree algorithm. The proposed approach was applied to the dataset, which included first a thorough analysis of the data, followed by the use of various machine learning algorithms, including linear model selection and Logistic Regression. KNeighborsClassifier was used to focus on neighbour selection, followed by a tree-based technique like DecisionTreeClassifier, and finally a very popular and most popular ensemble method RandomForestClassifier. Support Vector Machine was also used to check and handle the data's high dimensionality.
PredictBusinessSuccess
Predicting business success and how to optimize for it using machine learning
Prediction-Of-Disease-Classes-Using-Genetic-DNA-Microarray-Data
The purpose of this project is to develop a method that uses genetic data for disease classification. Data is extracted from a DNA microarray which measures the expression levels of large numbers of genes simultaneously. Samples in the datasets represent patients. For each patient 7070 genes expressions (values) are measured in order to classify the patient’s disease into one of the following cases: EPD, JPA, MED, MGL, RHB.
Clustering-features-in-texts-using-Genetic-Algorithm
Use the Genetic Algorithm to select features in texts and reduce the number of features by clustering them. The fitness function calculates the information loss using the information theory formula and picks the cluster with less information loss as the best chromosome. After optimization, the KNN classifier is implemented on reduced data to see the performance of this feature selection method. The Reuters-21578 dataset was used in this program.
Genetic-Programming-Predictive
Prediction of Children's alcohol behaviors using Python and Genetic Programming algorithms
Liver-Disease-Prediction-Using-ML-Models
This is a Machine Learning project in which I have taken dataset form UCLA of Indian patients for predicting Liver Disease using Machine Learning Models. In this I have used models like Random Forest, Naive Bayes, MLP Neural Networks, SVM, PSO-SVM. I have applied these models on the dataset and find out which model gives best accuracy. Best accuracy was shown by PSO-SVM. After applying Genetic Algorithm for feature selection on Random Forest, Naive Bayes and SVM, the best accuracy was shown by Random Forest.
Corporate-Bankruptcy-modeling-and-prediction-using-Genetic-Algorithms-
Final_code_for_NN_training_with_GA
GA-Based-Neural-Architecture-Prediction
Predicts neural network architecture for MNIST dataset using genetic algorithm
Stochastic-Optimization
Simulated Annealing -Simulated Annealing + Mean Field Annealing
Link-Prediction-using-Genetic-Algorithm
Improving Link Prediction in Social Network using Genetic Algorithm.
GA-IHK-Predictions
IHK Predictions using genetic algorithm
titanic-survival-prediction
Genetic program using Titanic dataset from Kaggle competition to predict survival people.
Particle-Swarm-optimization
Particle Swarm Optimization For Various Fitness Function
Travel-Time-Optimization-using-Machine-Learning
Optimize travel routes for a delivery vehicle by using machine learning model predictions
AI-Project-Comparison-of-3-algo-s
In this project I had to compare 3 algorithm's on the bases of there execution time. There are 3 AI algorithm's which were assign to me in these algorithm's two are uninform and one is inform. And the names of the algorithm's are: 1-DFS, 2-UCS, and A*