Search

Terminal neurological conditions can affect millions of people worldwide and hinder them from doing their daily tasks and movements normally. Brain computer interface (BCI) is the best hope for many individuals with motor deficiencies. It will help many patients interact with the outside world and handle their daily tasks without assistance. Therefore, machine learning-based BCI systems have emerged as non-invasive techniques for reading out signals from the brain and interpreting them into commands to help those people to perform diverse limb motor tasks. This paper proposes an innovative and improved machine learning-based BCI system that analyzes EEG signals obtained from motor imagery to distinguish among various limb motor tasks based on BCI competition III dataset IVa. The proposed framework pipeline for EEG signal processing performs the following major steps. The first step uses a meta-heuristic optimization technique, called the whale optimization algorithm (WOA), to select the optimal features for discriminating between neural activity patterns. The pipeline then uses machine learning models such as LDA, k-NN, DT, RF, and LR to analyze the chosen features to enhance the precision of EEG signal analysis. The proposed BCI system, which merges the WOA as a feature selection method and the optimized k-NN classification model, demonstrated an overall accuracy of 98.6%, outperforming other machine learning models and previous techniques on the BCI competition III dataset IVa. Additionally, the EEG feature contribution in the ML classification model is reported using Explainable AI (XAI) tools, which provide insights into the individual contributions of the features in the predictions made by the model. By incorporating XAI techniques, the results of this study offer greater transparency and understanding of the relationship between the EEG features and the model's predictions. The proposed method shows potential levels for better use in controlling diverse limb motor tasks to help people with limb impairments and support them while enhancing their quality of life. [ABSTRACT FROM AUTHOR]

This paper proposes a hybrid Modified Coronavirus Herd Immunity Aquila Optimization Algorithm (MCHIAO) that compiles the Enhanced Coronavirus Herd Immunity Optimizer (ECHIO) algorithm and Aquila Optimizer (AO). As one of the competitive human-based optimization algorithms, the Coronavirus Herd Immunity Optimizer (CHIO) exceeds some other biological-inspired algorithms. Compared to other optimization algorithms, CHIO showed good results. However, CHIO gets confined to local optima, and the accuracy of large-scale global optimization problems is decreased. On the other hand, although AO has significant local exploitation capabilities, its global exploration capabilities are insufficient. Subsequently, a novel metaheuristic optimizer, Modified Coronavirus Herd Immunity Aquila Optimizer (MCHIAO), is presented to overcome these restrictions and adapt it to solve feature selection challenges. In this paper, MCHIAO is proposed with three main enhancements to overcome these issues and reach higher optimal results which are cases categorizing, enhancing the new genes’ value equation using the chaotic system as inspired by the chaotic behavior of the coronavirus and generating a new formula to switch between expanded and narrowed exploitation. MCHIAO demonstrates it’s worth contra ten well-known state-of-the-art optimization algorithms (GOA, MFO, MPA, GWO, HHO, SSA, WOA, IAO, NOA, NGO) in addition to AO and CHIO. Friedman average rank and Wilcoxon statistical analysis (p-value) are conducted on all state-of-the-art algorithms testing 23 benchmark functions. Wilcoxon test and Friedman are conducted as well on the 29 CEC2017 functions. Moreover, some statistical tests are conducted on the 10 CEC2019 benchmark functions. Six real-world problems are used to validate the proposed MCHIAO against the same twelve state-of-the-art algorithms. On classical functions, including 24 unimodal and 44 multimodal functions, respectively, the exploitative and explorative behavior of the hybrid algorithm MCHIAO is evaluated. The statistical significance of the proposed technique for all functions is demonstrated by the p-values calculated using the Wilcoxon rank-sum test, as these p-values are found to be less than 0.05. [ABSTRACT FROM AUTHOR]

Nowadays, big data plays a substantial part in information knowledge analysis, manipulation, and forecasting. Analyzing and extracting knowledge from such big datasets are a very challenging task due to the imbalance of data distribution, which could lead to a biased classification results and wrong decisions. The standard classifiers are not capable of handling such datasets. Hence, a new technique for dealing with such datasets is required. This paper proposes a novel classification framework for big data that consists of three developed phases. The first phase is the feature selection phase, which uses the Whale optimization algorithm (WOA) for finding the best set of features. The second phase is the preprocessing phase, which uses the SMOTE algorithm and the LSH-SMOTE algorithm for solving the class imbalance problem. Lastly, the third phase is WOA + BRNN algorithm, which is using the Whale optimization algorithm for training a deep learning approach called bidirectional recurrent neural network for the first time. Our proposed algorithm WOA-BRNN has been tested against nine highly imbalanced datasets one of them is big dataset in terms of area under curve (AUC) against four of the most common use machine learning algorithms (Naïve Bayes, AdaBoostM1, decision table, random tree), in addition to GWO-MLP (training multilayer perceptron using Gray Wolf Optimizer), then we test our algorithm over four well-known datasets against GWO-MLP and particle swarm optimization (PSO-MLP), genetic algorithm (GA-MLP), ant colony optimization (ACO-MLP), evolution strategy (ES-MLP), and population-based incremental learning (PBIL-MLP) in terms of classification accuracy. Experimental results proved that our proposed algorithm WOA + BRNN has achieved promising accuracy and high local optima avoidance, and outperformed four of the most common use machine learning algorithms, and GWO-MLP in terms of AUC. [ABSTRACT FROM AUTHOR]

Classification of gene expression data is a pivotal research area that plays a substantial role in diagnosis and prediction of diseases. Generally, feature selection is one of the extensively used techniques in data mining approaches, especially in classification. Gene expression data are usually composed of dozens of samples characterized by thousands of genes. This increases the dimensionality coupled with the existence of irrelevant and redundant features. Accordingly, the selection of informative genes (features) becomes difficult, which badly affects the gene classification accuracy. In this paper, we consider the feature selection for classifying gene expression microarray datasets. The goal is to detect the most possibly cancer-related genes in a distributed manner, which helps in effectively classifying the samples. Initially, the available huge amount of considered features are subdivided and distributed among several processors. Then, a new filter selection method based on a fuzzy inference system is applied to each subset of the dataset. Finally, all the resulted features are ranked, then a wrapper-based selection method is applied. Experimental results showed that our proposed feature selection technique performs better than other techniques since it produces lower time latency and improves classification performance. [ABSTRACT FROM AUTHOR]

Abstract Gene expression microarray classification is a crucial research field as it has been employed in cancer prediction and diagnosis systems. Gene expression data are composed of dozens of samples characterized by thousands of genes. Hence, an accurate and effective classification of such samples is a challenge. Machine learning techniques have been broadly utilized to build substantial and precise classification models. This paper proposes a new classification technique for gene expression data, which is called Modified k-nearest neighbor (MKNN). MKNN is applied in two scenarios namely; smallest modified KNN (SMKNN) and largest modified KNN (LMKNN). Both implementations are undertaken to enhance the performance of KNN. The key idea is to employ robust neighbors from training data by using a new weighting strategy. Several experiments have been performed on six different gene expression datasets. Experiments have shown that MKNN in its both scenarios outperforms traditional as well as recent ones. MKNN has been compared against (i) KNN, (ii) weighted KNN, (iii) support vector machine (SVM), (iv) fuzzy support vector machine, (v) brain emotional learning (BEL) in terms of classification accuracy, precision, and recall. On the other hand, results show that MKNN introduces smaller testing time than both KNN and weighted KNN. [ABSTRACT FROM AUTHOR]

IP traceback techniques are used to defend against DDoS attacks, and two of the most preferred techniques are packet marking and packet logging. Marking techniques differentiate between attacks and legitimate packets incur little computation overhead while requiring a large flow of packets to build the entire attack path. Logging techniques trace even a single packet; routers record the packet digests locally, so it is considered as a more powerful technique. However, routers require a high storage space for storing packet digests that represents a vital problem in deploying it practically. In this paper, a new hybrid IP traceback framework is presented. This framework is based on both marking and logging techniques. In the marking algorithm, every router is assigned a 12-bit-length ID number; it helps in deploying pushback method to permit legitimate traffic flow smoothly. In the packet logging technique, a logging ratio is managed by changing a value k specified in the traceback system. According to the mathematical analysis and experimental results, >50% of the storage space of routers could be saved as a result of choosing a proper k value. [ABSTRACT FROM AUTHOR]

Prostate cancer, which is also known as prostatic adenocarcinoma, is an unconstrained growth of epithelial cells in the prostate and has become one of the leading causes of cancer-related death worldwide. The survival of patients with prostate cancer relies on detection at an early, treatable stage. In this paper, we introduce a new comprehensive framework to precisely differentiate between malignant and benign prostate cancer. This framework proposes a noninvasive computer-aided diagnosis system that integrates two imaging modalities of MR (diffusion-weighted (DW) and T2-weighted (T2W)). For the first time, it utilizes the combination of functional features represented by apparent diffusion coefficient (ADC) maps estimated from DW-MRI for the whole prostate in combination with texture features with its first- and second-order representations, extracted from T2W-MRIs of the whole prostate, and shape features represented by spherical harmonics constructed for the lesion inside the prostate and integrated with PSA screening results. The dataset presented in the paper includes 80 biopsy confirmed patients, with a mean age of 65.7 years (43 benign prostatic hyperplasia, 37 prostatic carcinomas). Experiments were conducted using different well-known machine learning approaches including support vector machines (SVM), random forests (RF), decision trees (DT), and linear discriminant analysis (LDA) classification models to study the impact of different feature sets that lead to better identification of prostatic adenocarcinoma. Using a leave-one-out cross-validation approach, the diagnostic results obtained using the SVM classification model along with the combined feature set after applying feature selection (88.75% accuracy, 81.08% sensitivity, 95.35% specificity, and 0.8821 AUC) indicated that the system's performance, after integrating and reducing different types of feature sets, obtained an enhanced diagnostic performance compared with each individual feature set and other machine learning classifiers. In addition, the developed diagnostic system provided consistent diagnostic performance using 10-fold and 5-fold cross-validation approaches, which confirms the reliability, generalization ability, and robustness of the developed system. [ABSTRACT FROM AUTHOR]

Prostate cancer is one of the most identified cancers and second most prevalent among cancer-related deaths of men worldwide. Early diagnosis and treatment are substantial to stop or handle the increase and spread of cancer cells in the body. Histopathological image diagnosis is a gold standard for detecting prostate cancer as it has different visual characteristics but interpreting those type of images needs a high level of expertise and takes too much time. One of the ways to accelerate such an analysis is by employing artificial intelligence (AI) through the use of computer-aided diagnosis (CAD) systems. The recent developments in artificial intelligence along with its sub-fields of conventional machine learning and deep learning provide new insights to clinicians and researchers, and an abundance of research is presented specifically for histopathology images tailored for prostate cancer. However, there is a lack of comprehensive surveys that focus on prostate cancer using histopathology images. In this paper, we provide a very comprehensive review of most, if not all, studies that handled the prostate cancer diagnosis using histopathological images. The survey begins with an overview of histopathological image preparation and its challenges. We also briefly review the computing techniques that are commonly applied in image processing, segmentation, feature selection, and classification that can help in detecting prostate malignancies in histopathological images. [ABSTRACT FROM AUTHOR]