Explore the vast range of titles available.

The classification accuracy of a multi-layer perceptron (MLP) depends on the selection of relevant features from the data set, its architecture, connection weights and the transfer functions. Generating an optimal value of all these parameters together is a complex task. Metaheuristic algorithms are popular choice among researchers to solve complex optimization problems. This paper presents a hybrid metaheuristic algorithm simple matching-grasshopper new cat swarm optimization algorithm (SM-GNCSOA) that optimizes all the four components simultaneously. SM-GNCSOA uses grasshopper optimization algorithm, a new variant of binary grasshopper optimization algorithm called simple matching-binary grasshopper optimization algorithm and a new variant of cat swarm optimization algorithm called new cat swarm optimization algorithm to generate an optimal MLP. Features play a vital role in determining the classification accuracy of a classifier. Here, we propose a new feature penalty function and use it in SM-GNCSOA to prevent underfitting or overfitting due to the selected number of features. To evaluate the performance of SM-GNCSOA, different variants of SM-GNCSOA are proposed and their classification accuracies are compared with SM-GNCSOA on ten classification data sets. The results show that SM-GNCSOA gives better results on most of the data sets due to its capability to balance exploration and exploitation and to avoid local minima.

“Brain–Computer Interface” (BCI)—a real-life support system provides a way for epileptic patients to improve their quality of life. In general, epileptic seizure detection using Electroencephalogram (EEG) signals provide a significant solution in preventing seizures through medication. Thus, the design of efficient machine learning-based seizure detection model is highly acclaimed by various academic and health professionals. In a motive to address the challenges posed by the state-of-the-art techniques in terms of noise, non-stationarity, and transient nature of EEG signals, this paper presents a novel Deep Learning model for epileptic seizure detection which hybridizes Adaptive Haar Wavelet-based Binary Grasshopper Optimization Algorithm and Deep Neural Network (AHW-BGOA-DNN). The experimental analysis was carried out using three benchmark EEG datasets obtained from the University of Bonn, the University of Bern and CHB-MIT EEG database which confirm the proposed technique to be reliable and accurate over the existing state-of-the-art techniques in terms of stability analysis, classification accuracy, AUC–ROC Curve (Area Under Curve–Receiver Operating Characteristics), sensitivity, and specificity.

Feature selection aims to select crucial features to improve classification accuracy in machine learning and data mining. In this paper, a new binary grasshopper optimization algorithm using time-varying Gaussian transfer functions (BGOA-TVG) is proposed for feature selection. Compared with the traditional S-shaped and V-shaped transfer functions, the proposed Gaussian time-varying transfer functions have the characteristics of a fast convergence speed and a strong global search capability to convert a continuous search space to a binary one. The BGOA-TVG is tested and compared to S-shaped and V-shaped binary grasshopper optimization algorithms and five state-of-the-art swarm intelligence algorithms for feature selection. The experimental results show that the BGOA-TVG has better performance in UCI, DEAP, and EPILEPSY datasets for feature selection.

The application of machine learning (ML) methods and predictive analytics in disaster management has made a drastic change in this field over the past few years. With their unparalleled ability to forecast, prepare, and respond, these advanced technologies are transforming the complete paradigm of disaster and emergency management. Much of this work is reinforced by machine learning models, an artificial intelligence domain that analyses huge amounts of data to establish patterns and forecast future disasters. This research proposes novel techniques in disaster management-based healthcare system utilizing machine learning model for sustainable environment. The study utilizes a dataset Centre for Research on Epidemiology of Disasters (CRED) launched Emergency Events Database (EM-DAT) in 1988. Data on frequency as well as effects of about 15,700 incidents since 1900 can be found in International Disaster Database, or EM-DA, which is preprocessed for noise removal and normalization. The processed data features have been extracted utilizing deep adversarial gaussian multilayer perceptron and the features has been optimized using firefly swarm binary grasshopper optimization. Experimental analysis is carried out in terms of random accuracy, precision, recall, AUC, F-1 score. Proposed technique random accuracy 98%, precision 95%, F-1 score 94%, AUC 96%, Recall 97%.

The migration and predation of grasshoppers inspire the grasshopper optimization algorithm (GOA). It can be applied to practical problems. The binary grasshopper optimization algorithm (BGOA) is used for binary problems. To improve the algorithm’s exploration capability and the solution’s quality, this paper modifies the step size in BGOA. The step size is expanded and three new transfer functions are proposed based on the improvement. To demonstrate the availability of the algorithm, a comparative experiment with BGOA, particle swarm optimization (PSO), and binary gray wolf optimizer (BGWO) is conducted. The improved algorithm is tested on 23 benchmark test functions. Wilcoxon rank-sum and Friedman tests are used to verify the algorithm’s validity. The results indicate that the optimized algorithm is significantly more excellent than others in most functions. In the aspect of the application, this paper selects 23 datasets of UCI for feature selection implementation. The improved algorithm yields higher accuracy and fewer features.