Heart disease is one of the most common diseases all over the world. The primary objective of this investigation is to diagnosis heart disease using hybrid classification based on NaN prediction and ANOVA test (NAN-ANOVA). The anticipated system comprises of two subsets: hybrid accelerated artificial bee colony and chicken swarm optimization algorithm (AABC-CSO) for effectual feature selection, followed by a classification technique with genetic algorithm based naive bayes classifier (GA-NBC). The first system in co-operates three stages: (i) loading the numerical value from the dataset (ii) evaluating the NaN value (iii) performing ANOVA test for efficient selection using AABC-CSO optimization algorithm. In second method, GA-NBC is proposed. The heart data set obtained from UCI machine repository, and was utilized for performing the computation. An accuracy of 61.0777%, sensitivity of 31.5868%, specificity of 67.8467%, precision of 17.9505, F-measure of 23.4050, G-mean of 46.6928 and loss of about 0.4480 was achieved according to the validation scheme.

Background: Cardiac Disease is the predominant cause of global death mainly due to its hidden symptoms and late diagnosis. People with CVD along with other diseases like hypertension, hyperlipidemia require very early detection for appropriate treatment. Hence this research proposed a hybrid technique for heart disease diagnosis. Objective The main contribution of the study is to overcome the existing limitations of Antlion, Crow search, and improved genetic algorithm and to hybridize the algorithm for the effective feature selection thereby improving the classification performance of the LSTM classifier. The motivation of this research is to improve the feature selection method with the optimization of features for effective heart disease prediction. Methodology: The proposed architecture uses the Ant lion algorithm with the effective determination of the elite position. The crow search Algorithm utilizes the phenomenon of position and memory of each crow for the evaluation of objective function. The inputs were processed by the improved genetic algorithm for effective feature selection. Now the hybridized proposed system successfully extracts the optimized features. These features are classified by the LSTM classifier. Results: The performance analysis was performed with two datasets. The dataset 1 had been used for the determination of the efficiency of the proposed system and the dataset 2 is utilized for the estimation of the proposed system followed by a detailed comparative analysis with the existing system. Further cross-validation of the sample with a varied range of testing percentage has also been accomplished. Apart from the intercombination performance of feature selection among the three utilized algorithms was also compared. From this comparative analysis, the proposed method had the highest accuracy of 99.7% compared to existing methods.

Emotion recognition based on biological signals from the brain necessitates sophisticated signal processing and feature extraction techniques. The major purpose of this research is to use the enhanced BiLSTM (E-BiLSTM) approach to improve the effectiveness of emotion identification utilizing brain signals. The approach detects brain activity that has distinct characteristics that vary from person to person. This experiment uses an emotional EEG dataset that is publicly available on Kaggle. The data was collected using an EEG headband with four sensors (AF7, AF8, TP9, TP10), and three possible states were identified, including neutral, positive, and negative, based on cognitive behavioral studies. A big dataset is generated using statistical brainwave extraction of alpha, beta, theta, delta, and gamma, which is then scaled down to smaller datasets using the PCA feature selection technique. Overall accuracy was around 98.12%, which is higher than the present state of the art.