Search Results (14)

Unsupervised learning is a type of machine learning that learns from data without human supervision. Unsupervised feature selection (UFS) is crucial in data analytics, which plays a vital role in enhancing the quality of results and reducing computational complexity in huge feature spaces. The UFS problem has been addressed in several research efforts. Recent studies have witnessed a surge in innovative techniques like nature-inspired algorithms for clustering and UFS problems. However, very few studies consider the UFS problem as a multi-objective problem to find the optimal trade-off between the number of selected features and model accuracy. This paper proposes a multi-objective symbiotic organism search algorithm for unsupervised feature selection (SOSUFS) and a symbiotic organism search-based clustering (SOSC) algorithm to generate the optimal feature subset for more accurate clustering. The efficiency and robustness of the proposed algorithm are investigated on benchmark datasets. The SOSUFS method, combined with SOSC, demonstrated the highest f-measure, whereas the KHCluster method resulted in the lowest f-measure. SOSFS effectively reduced the number of features by more than half. The proposed symbiotic organisms search-based optimal unsupervised feature-selection (SOSUFS) method, along with search-based optimal clustering (SOSC), was identified as the top-performing clustering approach. Following this, the SOSUFS method demonstrated strong performance. In summary, this empirical study indicates that the proposed algorithm significantly surpasses state-of-the-art algorithms in both efficiency and effectiveness. Unsupervised learning in artificial intelligence involves machine-learning techniques that learn from data without human supervision. Unlike supervised learning, unsupervised machine-learning models work with unlabeled data to uncover patterns and insights independently, without explicit guidance or instruction. Full article

Stroke is a major cause of mortality worldwide, disrupts cerebral blood flow, leading to severe brain damage. Hemiplegia, a common consequence, results in motor task loss on one side of the body. Many stroke survivors face long-term motor impairments and require great rehabilitation. Electroencephalograms (EEGs) provide a non-invasive method to monitor brain activity and have been used in brain–computer interfaces (BCIs) to help in rehabilitation. Motor imagery (MI) tasks, detected through EEG, are pivotal for developing BCIs that assist patients in regaining motor purpose. However, interpreting EEG signals for MI tasks remains challenging due to their complexity and low signal-to-noise ratio. The main aim of this study is to focus on optimizing channel selection in EEG-based BCIs specifically for stroke rehabilitation. Determining the most informative EEG channels is crucial for capturing the neural signals related to motor impairments in stroke patients. In this paper, a binary bat algorithm (BA)-based optimization method is proposed to select the most relevant channels tailored to the unique neurophysiological changes in stroke patients. This approach is able to enhance the BCI performance by improving classification accuracy and reducing data dimensionality. We use time–entropy–frequency (TEF) attributes, processed through automated independent component analysis with wavelet transform (AICA-WT) denoising, to enhance signal clarity. The selected channels and features are proved through a k-nearest neighbor (KNN) classifier using public BCI datasets, demonstrating improved classification of MI tasks and the potential for better rehabilitation outcomes. Full article

The pressing need for sustainable development solutions necessitates innovative data-driven tools. Machine learning (ML) offers significant potential, but faces challenges in centralized approaches, particularly concerning data privacy and resource constraints in geographically dispersed settings. Federated learning (FL) emerges as a transformative paradigm for sustainable development by decentralizing ML training to edge devices. However, communication bottlenecks hinder its scalability and sustainability. This paper introduces an innovative FL framework that enhances communication efficiency. The proposed framework addresses the communication bottleneck by harnessing the power of the Lemurs optimizer (LO), a nature-inspired metaheuristic algorithm. Inspired by the cooperative foraging behavior of lemurs, the LO strategically selects the most relevant model updates for communication, significantly reducing communication overhead. The framework was rigorously evaluated on CIFAR-10, MNIST, rice leaf disease, and waste recycling plant datasets representing various areas of sustainable development. Experimental results demonstrate that the proposed framework reduces communication overhead by over 15% on average compared to baseline FL approaches, while maintaining high model accuracy. This breakthrough extends the applicability of FL to resource-constrained environments, paving the way for more scalable and sustainable solutions for real-world initiatives. Full article

Recently, signature verification systems have been widely adopted for verifying individuals based on their handwritten signatures, especially in forensic and commercial transactions. Generally, feature extraction and classification tremendously impact the accuracy of system authentication. Feature extraction is challenging for signature verification systems due to the diverse forms of signatures and sample circumstances. Current signature verification techniques demonstrate promising results in identifying genuine and forged signatures. However, the overall performance of skilled forgery detection remains rigid to deliver high contentment. Furthermore, most of the current signature verification techniques demand a large number of learning samples to increase verification accuracy. This is the primary disadvantage of using deep learning, as the figure of signature samples is mainly restricted to the functional application of the signature verification system. In addition, the system inputs are scanned signatures that comprise noisy pixels, a complicated background, blurriness, and contrast decay. The main challenge has been attaining a balance between noise and data loss, since some essential information is lost during preprocessing, probably influencing the subsequent stages of the system. This paper tackles the aforementioned issues by presenting four main steps: preprocessing, multifeature fusion, discriminant feature selection using a genetic algorithm based on one class support vector machine (OCSVM-GA), and a one-class learning strategy to address imbalanced signature data in the practical application of a signature verification system. The suggested method employs three databases of signatures: SID-Arabic handwritten signatures, CEDAR, and UTSIG. Experimental results depict that the proposed approach outperforms current systems in terms of false acceptance rate (FAR), false rejection rate (FRR), and equal error rate (EER). Full article

Tire defects are crucial for safe driving. Specialized experts or expensive tools such as stereo depth cameras and depth gages are usually used to investigate these defects. In image processing, feature extraction, reduction, and classification are presented as three challenging and symmetric ways to affect the performance of machine learning models. This paper proposes a hybrid system for cracked tire detection based on the adaptive selection of correlation features and deep belief neural networks. The proposed system has three steps: feature extraction, selection, and classification. First, the oriented gradient histogram extracts features from the tire images. Second, the proposed adaptive correlation feature selection selects important features with a threshold value adapted to the nature of the images. The last step of the system is to predict the image category based on the deep belief neural networks technique. The proposed model is tested and evaluated using real images of cracked and normal tires. The experimental results show that the proposed solution performs better than the current studies in effectively classifying tire defect images. The proposed hybrid cracked tire detection system based on adaptive correlation feature selection and Deep Belief Neural Networks’ performance provided better classification accuracy (88.90%) than that of Belief Neural Networks (81.6%) and Convolution Neural Networks (85.59%). Full article

Malware is one of the most frequent cyberattacks, with its prevalence growing daily across the network. Malware traffic is always asymmetrical compared to benign traffic, which is always symmetrical. Fortunately, there are many artificial intelligence techniques that can be used to detect malware and distinguish it from normal activities. However, the problem of dealing with large and high-dimensional data has not been addressed enough. In this paper, a high-performance malware detection system using deep learning and feature selection methodologies is introduced. Two different malware datasets are used to detect malware and differentiate it from benign activities. The datasets are preprocessed, and then correlation-based feature selection is applied to produce different feature-selected datasets. The dense and LSTM-based deep learning models are then trained using these different versions of feature-selected datasets. The trained models are then evaluated using many performance metrics (accuracy, precision, recall, and F1-score). The results indicate that some feature-selected scenarios preserve almost the same original dataset performance. The different nature of the used datasets shows different levels of performance changes. For the first dataset, the feature reduction ratios range from 18.18% to 42.42%, with performance degradation of 0.07% to 5.84%, respectively. The second dataset reduction rate is between 81.77% and 93.5%, with performance degradation of 3.79% and 9.44%, respectively. Full article

Machine learning models have recently provided great promise in diagnosis of several ophthalmic disorders, including keratoconus (KCN). Keratoconus, a noninflammatory ectatic corneal disorder characterized by progressive cornea thinning, is challenging to detect as signs may be subtle. Several machine learning models have been proposed to detect KCN, however most of the models are supervised and thus require large well-annotated data. This paper proposes a new unsupervised model to detect KCN, based on adapted flower pollination algorithm (FPA) and the k-means algorithm. We will evaluate the proposed models using corneal data collected from 5430 eyes at different stages of KCN severity (1520 healthy, 331 KCN1, 1319 KCN2, 1699 KCN3 and 579 KCN4) from Department of Ophthalmology and Visual Sciences, Paulista Medical School, Federal University of São Paulo, São Paulo in Brazil and 1531 eyes (Healthy = 400, KCN1 = 378, KCN2 = 285, KCN3 = 200, KCN4 = 88) from Department of Ophthalmology, Jichi Medical University, Tochigi in Japan and used several accuracy metrics including Precision, Recall, F-Score, and Purity. We compared the proposed method with three other standard unsupervised algorithms including k-means, Kmedoids, and Spectral cluster. Based on two independent datasets, the proposed model outperformed the other algorithms, and thus could provide improved identification of the corneal status of the patients with keratoconus. Full article

Migraine is a periodic disorder in which a patient experiences changes in the morphological and functional brain, leading to the abnormal processing of repeated external stimuli in the inter-ictal phase, known as the habituation deficit. This is a significant feature clinically of migraine in both two types with aura or without aura and plays an essential role in studying pathophysiological differences between these two groups. Several studies indicated that the reason for migraine aura is cortical spreading depression (CSD) but did not clarify its impact on migraine without aura and lack of habituation. In this study, 22 migraine patients (MWA, N = 13), (MWoA, N = 9), and healthy controls (HC, N = 19) were the participants. Participants were exposed to the steady state of visual evoked potentials also known as (SSVEP), which are the signals for a natural response to the visual motivation at four Hz or six Hz for 2 s followed by the inter-stimulus interval that varies between 1 and 1.5 s. The order of the temporal frequencies was randomized, and each temporal frequency was shown 100 times. We recorded from 128 customized electrode locations using high-density electroencephalography (HD-EEG) and measured amplitude and habituation for the N1–P1 and P1–N2 from the first to the sixth blocks of 100 sweep features in patients and healthy controls. Using the entropy, a decrease in amplitude and SSVEP N1-P1 habituation between the first and the sixth block appeared in both MWA and MWoA (p = 0.0001, Slope = −0.4643), (p = 0.065, Slope = 0.1483), respectively, compared to HC. For SSVEP P1–N2 between the first and sixth block, it is varied in both MWA (p = 0.0029, Slope = −0.3597) and MWoA (p = 0.027, Slope = 0.2010) compared to HC. Therefore, migraine patients appear amplitude decrease and habituation deficit but with different rates between MWA, and MWoA compared to HCs. Our findings suggest this disparity between MWoA and MWA in the lack of habituation and amplitude decrease in the inter-ictal phase has a close relationship with CSD. In light of the fact that CSD manifests during the inter-ictal phase of migraine with aura, which is when migraine seizures are most likely to occur, multiple researchers have lately reached this conclusion. This investigation led us to the conclusion that CSD during the inter-ictal phase and migraine without aura are associated. In other words, even if previous research has not demonstrated it, CSD is the main contributor to both types of migraine (those with and without aura). Full article

Skin cancer is one of the major types of cancer with an increasing incidence in recent decades. The source of skin cancer arises in various dermatologic disorders. Skin cancer is classified into various types based on texture, color, morphological features, and structure. The conventional approach for skin cancer identification needs time and money for the predicted results. Currently, medical science is utilizing various tools based on digital technology for the classification of skin cancer. The machine learning-based classification approach is the robust and dominant approach for automatic methods of classifying skin cancer. The various existing and proposed methods of deep neural network, support vector machine (SVM), neural network (NN), random forest (RF), and K-nearest neighbor are used for malignant and benign skin cancer identification. In this study, a method was proposed based on the stacking of classifiers with three folds towards the classification of melanoma and benign skin cancers. The system was trained with 1000 skin images with the categories of melanoma and benign. The training and testing were performed using 70 and 30 percent of the overall data set, respectively. The primary feature extraction was conducted using the Resnet50, Xception, and VGG16 methods. The accuracy, F1 scores, AUC, and sensitivity metrics were used for the overall performance evaluation. In the proposed Stacked CV method, the system was trained in three levels by deep learning, SVM, RF, NN, KNN, and logistic regression methods. The proposed method for Xception techniques of feature extraction achieved 90.9% accuracy and was stronger compared to ResNet50 and VGG 16 methods. The improvement and optimization of the proposed method with a large training dataset could provide a reliable and robust skin cancer classification system. Full article

The Lemur Optimizer (LO) is a novel nature-inspired algorithm we propose in this paper. This algorithm’s primary inspirations are based on two pillars of lemur behavior: leap up and dance hub. These two principles are mathematically modeled in the optimization context to handle local search, exploitation, and exploration search concepts. The LO is first benchmarked on twenty-three standard optimization functions. Additionally, the LO is used to solve three real-world problems to evaluate its performance and effectiveness. In this direction, LO is compared to six well-known algorithms: Salp Swarm Algorithm (SSA), Artificial Bee Colony (ABC), Sine Cosine Algorithm (SCA), Bat Algorithm (BA), Flower Pollination Algorithm (FPA), and JAYA algorithm. The findings show that the proposed algorithm outperforms these algorithms in fourteen standard optimization functions and proves the LO’s robust performance in managing its exploration and exploitation capabilities, which significantly leads LO towards the global optimum. The real-world experimental findings demonstrate how LO may tackle such challenges competitively. Full article

The electroencephalogram (EEG) introduced a massive potential for user identification. Several studies have shown that EEG provides unique features in addition to typical strength for spoofing attacks. EEG provides a graphic recording of the brain’s electrical activity that electrodes can capture on the scalp at different places. However, selecting which electrodes should be used is a challenging task. Such a subject is formulated as an electrode selection task that is tackled by optimization methods. In this work, a new approach to select the most representative electrodes is introduced. The proposed algorithm is a hybrid version of the Flower Pollination Algorithm and $\beta$-Hill Climbing optimizer called FPA$\beta$-hc. The performance of the FPA$\beta$-hc algorithm is evaluated using a standard EEG motor imagery dataset. The experimental results show that the FPA$\beta$-hc can utilize less than half of the electrode numbers, achieving more accurate results than seven other methods. Full article

The Coronavirus herd immunity optimizer (CHIO) is a new human-based optimization algorithm that imitates the herd immunity strategy to eliminate of the COVID-19 disease. In this paper, the coronavirus herd immunity optimizer (CHIO) is modified to tackle a discrete power scheduling problem in a smart home (PSPSH). PSPSH is a combinatorial optimization problem with NP-hard features. It is a highly constrained discrete scheduling problem concerned with assigning the operation time for smart home appliances based on a dynamic pricing scheme(s) and several other constraints. The primary objective when solving PSPSH is to maintain the stability of the power system by reducing the ratio between average and highest power demand (peak-to-average ratio (PAR)) and reducing electricity bill (EB) with considering the comfort level of users (UC). This paper modifies and adapts the CHIO algorithm to deal with such discrete optimization problems, particularly PSPSH. The adaptation and modification include embedding PSPSH problem-specific operators to CHIO operations to meet the discrete search space requirements. PSPSH is modeled as a multi-objective problem considering all objectives, including PAR, EB, and UC. The proposed method is examined using a dataset that contains 36 home appliances and seven consumption scenarios. The main CHIO parameters are tuned to find their best values. These best values are used to evaluate the proposed method by comparing its results with comparative five metaheuristic algorithms. The proposed method shows encouraging results and almost obtains the best results in all consumption scenarios. Full article

This review describes a cloud-based intelligent power management system that uses analytics as a control signal and processes balance achievement pointer, and describes operator acknowledgments that must be shared quickly, accurately, and safely. The current study aims to introduce a conceptual and systematic structure with three main components: demand power (direct current (DC)-device), power mix between renewable energy (RE) and other power sources, and a cloud-based power optimization intelligent system. These methods and techniques monitor demand power (DC-device), load, and power mix between RE and other power sources. Cloud-based power optimization intelligent systems lead to an optimal power distribution solution that reduces power consumption or costs. Data has been collected from reliable sources such as Science Direct, IEEE Xplore, Scopus, Web of Science, Google Scholar, and PubMed. The overall findings of these studies are visually explained in the proposed conceptual framework through the literature that are considered to be cloud computing based on storing and running the intelligent systems of power management and mixing. Full article

The power scheduling problem in a smart home (PSPSH) refers to the timely scheduling operations of smart home appliances under a set of restrictions and a dynamic pricing scheme(s) produced by a power supplier company (PSC). The primary objectives of PSPSH are: (I) minimizing the cost of the power consumed by home appliances, which refers to electricity bills, (II) balance the power consumed during a time horizon, particularly at peak periods, which is known as the peak-to-average ratio, and (III) maximizing the satisfaction level of users. Several approaches have been proposed to address PSPSH optimally, including optimization and non-optimization based approaches. However, the set of restrictions inhibit the approach used to obtain the optimal solutions. In this paper, a new formulation for smart home battery (SHB) is proposed for PSPSH that reduces the effect of restrictions in obtaining the optimal/near-optimal solutions. SHB can enhance the scheduling of smart home appliances by storing power at unsuitable periods and use the stored power at suitable periods for PSPSH objectives. PSPSH is formulated as a multi-objective optimization problem to achieve all objectives simultaneously. A robust swarm-based optimization algorithm inspired by the grey wolf lifestyle called grey wolf optimizer (GWO) is adapted to address PSPSH. GWO has powerful operations managed by its dynamic parameters that maintain exploration and exploitation behavior in search space. Seven scenarios of power consumption and dynamic pricing schemes are considered in the simulation results to evaluate the proposed multi-objective PSPSH using SHB (BMO-PSPSH) approach. The proposed BMO-PSPSH approach’s performance is compared with that of other 17 state-of-the-art algorithms using their recommended datasets and four algorithms using the proposed datasets. The proposed BMO-PSPSH approach exhibits and yields better performance than the other compared algorithms in almost all scenarios. Full article