Abstract Detecting tumors using gene analysis in microarray data is a critical area of research in artificial intelligence and bioinformatics. However, due to the large number of genes compared to observations, feature selection is a central process in microarray analysis. While various gene selection methods have been developed to select the most relevant genes, these methods’ efficiency and reliability can be improved. This paper proposes a new two-phase gene selection method that combines the ReliefF filter method with a novel version of the spider wasp optimizer (SWO) called RSWO-MPA. In the first phase, the ReliefF filter method is utilized to reduce the number of genes to a reasonable number. In the second phase, RSWO-MPA applies a recursive spider wasp optimizer guided by the marine predators algorithm (MPA) to select the most informative genes from the previously selected ones. The MPA is used in the initialization step of recursive SWO to narrow down the search space to the most relevant and accurate genes. The proposed RSWO-MPA has been implemented and validated through extensive experimentation using eight microarray gene expression datasets. The enhanced RSWO-MPA is compared with seven widely used and recently developed meta-heuristic algorithms, including Kepler optimization algorithm (KOA), marine predators algorithm (MPA), social ski-driver optimization (SSD), whale optimization algorithm (WOA), Harris hawks optimization (HHO), artificial bee colony (ABC) algorithm, and original SWO. The experimental results demonstrate that the developed method yields the highest accuracy, selects fewer features, and exhibits more stability than other compared algorithms and cutting-edge methods for all the datasets used. Specifically, it achieved an accuracy of 100.00%, 94.51%, 98.13%, 95.63%, 100.00%, 100.00%, 92.97%, and 100.00% for Yeoh, West, Chiaretti, Burcyznski, leukemia, ovarian cancer, central nervous system, and SRBCT datasets, respectively.

Feature selection (FS) is one of the basic data preprocessing steps in data mining and machine learning. It is used to reduce feature size and increase model generalization. In addition to minimizing feature dimensionality, it also enhances classification accuracy and reduces model complexity, which are essential in several applications. Traditional methods for feature selection often fail in the optimal global solution due to the large search space. Many hybrid techniques have been proposed depending on merging several search strategies which have been used individually as a solution to the FS problem. This study proposes a modified hunger games search algorithm (mHGS), for solving optimization and FS problems. The main advantages of the proposed mHGS are to resolve the following drawbacks that have been raised in the original HGS; (1) avoiding the local search, (2) solving the problem of premature convergence, and (3) balancing between the exploitation and exploration phases. The mHGS has been evaluated by using the IEEE Congress on Evolutionary Computation 2020 (CEC'20) for optimization test and ten medical and chemical datasets. The data have dimensions up to 20000 features or more. The results of the proposed algorithm have been compared to a variety of well-known optimization methods, including improved multi-operator differential evolution algorithm (IMODE), gravitational search algorithm, grey wolf optimization, Harris Hawks optimization, whale optimization algorithm, slime mould algorithm and hunger search games search. The experimental results suggest that the proposed mHGS can generate effective search results without increasing the computational cost and improving the convergence speed. It has also improved the SVM classification performance.

Breast cancer is the second leading cause of death in women; therefore, effective early detection of this cancer can reduce its mortality rate. Breast cancer detection and classification in the early phases of development may allow for optimal therapy. Convolutional neural networks (CNNs) have enhanced tumor detection and classification efficiency in medical imaging compared to traditional approaches. This paper proposes a novel classification model for breast cancer diagnosis based on a hybridized CNN and an improved optimization algorithm, along with transfer learning, to help radiologists detect abnormalities efficiently. The marine predators algorithm (MPA) is the optimization algorithm we used, and we improve it using the opposition-based learning strategy to cope with the implied weaknesses of the original MPA. The improved marine predators algorithm (IMPA) is used to find the best values for the hyperparameters of the CNN architecture. The proposed method uses a pretrained CNN model called ResNet50 (residual network). This model is hybridized with the IMPA algorithm, resulting in an architecture called IMPA-ResNet50. Our evaluation is performed on two mammographic datasets, the mammographic image analysis society (MIAS) and curated breast imaging subset of DDSM (CBIS-DDSM) datasets. The proposed model was compared with other state-of-the-art approaches. The obtained results showed that the proposed model outperforms the compared state-of-the-art approaches, which are beneficial to classification performance, achieving 98.32% accuracy, 98.56% sensitivity, and 98.68% specificity on the CBIS-DDSM dataset and 98.88% accuracy, 97.61% sensitivity, and 98.40% specificity on the MIAS dataset. To evaluate the performance of IMPA in finding the optimal values for the hyperparameters of ResNet50 architecture, it compared to four other optimization algorithms including gravitational search algorithm (GSA), Harris hawks optimization (HHO), whale optimization algorithm (WOA), and the original MPA algorithm. The counterparts algorithms are also hybrid with the ResNet50 architecture produce models named GSA-ResNet50, HHO-ResNet50, WOA-ResNet50, and MPA-ResNet50, respectively. The results indicated that the proposed IMPA-ResNet50 is achieved a better performance than other counterparts.

Abstract Affective computing, a subcategory of artificial intelligence, detects, processes, interprets, and mimics human emotions. Thanks to the continued advancement of portable non-invasive human sensor technologies, like brain–computer interfaces (BCI), emotion recognition has piqued the interest of academics from a variety of domains. Facial expressions, speech, behavior (gesture/posture), and physiological signals can all be used to identify human emotions. However, the first three may be ineffectual because people may hide their true emotions consciously or unconsciously (so-called social masking). Physiological signals can provide more accurate and objective emotion recognition. Electroencephalogram (EEG) signals respond in real time and are more sensitive to changes in affective states than peripheral neurophysiological signals. Thus, EEG signals can reveal important features of emotional states. Recently, several EEG-based BCI emotion recognition techniques have been developed. In addition, rapid advances in machine and deep learning have enabled machines or computers to understand, recognize, and analyze emotions. This study reviews emotion recognition methods that rely on multi-channel EEG signal-based BCIs and provides an overview of what has been accomplished in this area. It also provides an overview of the datasets and methods used to elicit emotional states. According to the usual emotional recognition pathway, we review various EEG feature extraction, feature selection/reduction, machine learning methods (e.g., k-nearest neighbor), support vector machine, decision tree, artificial neural network, random forest, and naive Bayes) and deep learning methods (e.g., convolutional and recurrent neural networks with long short term memory). In addition, EEG rhythms that are strongly linked to emotions as well as the relationship between distinct brain areas and emotions are discussed. We also discuss several human emotion recognition studies, published between 2015 and 2021, that use EEG data and compare different machine and deep learning algorithms. Finally, this review suggests several challenges and future research directions in the recognition and classification of human emotional states using EEG.

Evolution of the Internet of Things (IoT) makes a revolution in connecting, monitoring, controlling, and managing things, objects, and almost surroundings through the Internet. To reveal the potential of IoT, rich knowledge has to be extracted, indexed, and shared securely in real time. Recent comprehensive researches on IoT spot the light on main correlative challenges, such as security, scalability, heterogeneity, and big data. Due to the heterogeneity of IoT applications that produce a large volume of a variety of data streams in real time, mining, securing, and analyzing IoT data become tedious and challenging tasks. Indexing sensory data is one of data mining techniques, which ease information retrieval. But ordinary indexing methods are not fit with such massive and dynamic data; where indexes become out-of-date once they are built. Clustering, data reduction, and summarization present promising solutions for enabling low-power security and balanced indexing. This article presents a novel method for dynamic data reduction and summarization using dynamic time warping (DTW), which also presents a balanced architecture for enabling balanced indexing based on similarity data fusion. Data reduction-based prediction models enable real-time search and secure discovery for Smart Things (SThs). The results of the proposed model were proved using real examples and data sets. Using the Szeged-weather data set similar SThs data is reduced by 95%. Thus, indexes sizes could be reduced, and using smart scheduling, crawling cycle length could be expanded.