Optimal Feature Set Research Articles

Detection of attention deficit hyperactivity disorder based on EEG signals using Least Square Support Vector Machine (LS-SVM)

ABSTRACT Attention Deficit Hyperactivity Disorder (ADHD) is a mental disorder affecting children in their early stages. Detection of ADHD is considered a challenging task for experts because there is no accurate test to determine whether a child has ADHD or not. Mainly, most of previous studies are used electroencephalography (EEG) signals to detect ADHD. In this study, a robust model for ADHD detection-integrated discrete wavelet transform (DWT), statistical features, and a least square support vector machine (LS-SVM) is proposed to detect ADHD from EEG signals. The EEG signals are decomposed into five bands and then, a set of statistical features are tested to find the optimal feature sets using K-means model. A public dataset is used to evaluate the proposed model. A total of 45 ADHD patients and 45 healthy are involved to evaluate the proposed model. Several metrics are used to evaluate the proposed model including 10-fold cross-validation precision, sensitivity, and specificity metrics. A channel selection is also investigated, and we found that the channels ‘P3, P7, Pz’ are more important and gave better prediction results than other channels. The proposed model obtained an average accuracy of 98.06% with LS-SVM, and 95.46% with the KNN classifier.

FDF-HybridFS: Towards design of a failure detection framework using hybrid feature selection method for IP core networks that connect 5G core in NFV-based test environment

With the advancement of recent technologies, high-speed and secure internet connectivity is required for 5th-generation mobile networks. A massive number of smart devices connected to the networks generate a large amount of data. Consequently, increasing traffic has generated more strain on networks and devices. Therefore, to handle the huge amount of data generated by the various devices and to detect network and device failures, automation is expected to play an important role. Hence, these requirements have accelerated the necessity of automation. This study presents a novel hybrid feature-selection technique for detecting network and device failure in IP core networks that connect 5 G core networks for internet connectivity. This approach first performs feature ranking using the MI (Mutual information), CC (Correlation coefficient), and GI (Gini index) to get the three different feature sets. Subsequently, in order to acquire a single optimized feature set, features are combined using a union operation. This optimized feature set is fed to the wrapper-based Boruta feature selection algorithm. In addition, to handle the data imbalance problem, we have applied the SMOTETomek method. Finally, obtained optimized feature set is fed to the three most popular ensemble approaches, Random forest, LGBM (Light gradient boosting machine), and xGBoost for the detection of failure. The proposed detection system's performance is evaluated using the KDDI dataset provided by KDDI Corporation. The effectiveness of the proposed FDF-HybridFS is tested and compared with several recent state-of-the-art methods cited in the related work in terms of detection rate, precision, accuracy, and F1 score. An analysis of the proposed failure detection framework's performance on the KDDI dataset shows that it outperforms state-of-the-art methods in terms of both detection rate and detection accuracy.

Spam review detection with Metapath-aggregated graph convolution network

The large flux of online products in today’s world makes business reviews a valuable source for consumers for making sound decisions before making online purchases. Reviews are useful for readers in learning more about the product and gauge its quality. Fake reviews and reviewers form the bulk of the review corpus, making review spamming an open research challenge. These spam reviews require detection to nullify their contribution to product recommendations. In the past, researchers and communities have taken spam detection problems as a matter of serious concern. Yet, for all that, there is space for the performance of exploration on large-scale complex datasets. The work contributes towards robust feature selection with derived features that provide more details on malicious reviews and spammers. Ensemble and other standard machine learning techniques are trained and evaluated over optimal feature sets. In addition, the Metapath-based Graph Convolution Network (M-GCN) framework is proposed, which is an implicit knowledge extraction method to automatically capture the complex semantic meaning of reviews from the heterogeneous network. It makes analysis of triplet (users, reviews, and products) relationships in e-commerce sites through examination of Top-n feature sets in a mutually reinforcing manner. The proposed model is demonstrated on Yelp and Amazon benchmark datasets for evaluation of efficacy and it is shown outperforming state-of-the-art techniques with and without graph-utilization, providing an accuracy of 96% in the prediction task.

Automatic Life Detection Based on Efficient Features of Ground-Penetrating Rescue Radar Signals.

Good feature engineering is a prerequisite for accurate classification, especially in challenging scenarios such as detecting the breathing of living persons trapped under building rubble using bioradar. Unlike monitoring patients' breathing through the air, the measuring conditions of a rescue bioradar are very complex. The ultimate goal of search and rescue is to determine the presence of a living person, which requires extracting representative features that can distinguish measurements with the presence of a person and without. To address this challenge, we conducted a bioradar test scenario under laboratory conditions and decomposed the radar signal into different range intervals to derive multiple virtual scenes from the real one. We then extracted physical and statistical quantitative features that represent a measurement, aiming to find those features that are robust to the complexity of rescue-radar measuring conditions, including different rubble sites, breathing rates, signal strengths, and short-duration disturbances. To this end, we utilized two methods, Analysis of Variance (ANOVA), and Minimum Redundancy Maximum Relevance (MRMR), to analyze the significance of the extracted features. We then trained the classification model using a linear kernel support vector machine (SVM). As the main result of this work, we identified an optimal feature set of four features based on the feature ranking and the improvement in the classification accuracy of the SVM model. These four features are related to four different physical quantities and independent from different rubble sites.

Identification of psychological stress states based on joint analysis of multidomain features of skin conductance

Background and ObjectivePsychological stress identification generally uses a questionnaire with strong subjectivity. In contrast, skin conductance (SC) is not controlled by self-consciousness. Due to its correlation with psychological stress, SC has become the object of analysis for identifying psychological stress states. This study aimed to determine the effective features of SC and to establish an assessment model for psychological stress. MethodsIn this study, SC in resting and stress states was measured in 27 healthy subjects. Time-domain features (including general-time-domain and rise-and-fall-time features), frequency-domain features, and nonlinear features of the SC were extracted after pre-processing. Statistical differences in the features were analysed. Feature selection for the four feature types in the three domains was performed using the recursive feature elimination method. The optimal feature set was fed into support vector machine for classification. ResultsStatistical analysis results showed that all three feature domains contained features with significant statistical differences. When analysing single-domain features, the rise-and-fall-time features obtained the best classification results, with an accuracy of 86.73 %. In the joint analysis of two-domain features, combination of the frequency-domain and nonlinear features produced a maximum classification accuracy of 90.73 %. When three domain features were jointly analysed, a maximum classification accuracy of 94.36 % was achieved with the combination of the rise-and-fall-time, frequency-domain, and nonlinear features. ConclusionsThis study confirms the feasibility of joint analysis of the multidomain features of SC for identification of psychological stress states and provides methodological support for the real-time, objective, and quantitative evaluation of psychological stress.

Fortified-Chain 2.0: Intelligent Blockchain for Decentralized Smart Healthcare System

The Internet of Medical Things (IoMT) technology’s fast advancements aided smart healthcare systems to a larger extent. IoMT devices, on the other hand, rely on centralized processing and storage systems because of their limited computational and storage capacity. The reliance is susceptible to a single point of failure (SPoF) and erodes the user control over their medical data. In addition, Cloud models result in communication delays, which slow down the system’s overall reaction time. To overcome these issues a decentralized distributed smart healthcare system is proposed that eliminates the SPoF and third-party control over healthcare data. Additionally, the proposed Fortified-Chain 2.0 uses a blockchain-based selective sharing mechanism with a mutual authentication technique to solve the issues such as data privacy, security and trust management in decentralized peer-to-peer healthcare systems. Also, we suggested a hybrid computing paradigm to deal with latency, computational and storage constraints. A novel distributed Machine Learning (ML) module named Random Forest Support Vector Machine (RFSVM) also embedded into the Fortified-Chain 2.0 system to automate patient health monitoring. In the RFSVM module, Random Forest (RF) is used to select an optimal set of features from patients data in real time environment and also Support Vector Machine (SVM) is used to perform the decision making tasks. The proposed Fortified-Chain 2.0 works on a private blockchain-based Distributed Data Storage System (DDSS) that improves the system-level transparency, integrity, and traceability. Fortified-Chain 2.0 outperformed the existing Fortified-Chain in terms of low latency, high throughput, and availability with the help of a mutual authentication method.

A Generalized Classification Framework with Simultaneous Feature Weighting and Selection Using Antlion Optimization Algorithm

ABSTRACT The use of machine-learning based algorithms on a large-scale nondestructive evaluation (NDE) data considerably advances the NDE techniques toward complete industrial automation. In this article, simultaneous feature selection and feature weighting are carried out on the magnetic Barkhausen emission (MBE) dataset to demonstrate the significance of optimization in NDE data. Antlion optimization is employed as a searching method to determine the optimum feature set that will maximize the classification performance. The proposed framework is validated for different magnetization frequencies separately and found to be frequency independent. The framework resulted in the selection of four significant features extracted from the MBE response thereby reducing the computational effort and improving the accuracy to 98.4% for AdaBoost classifier. The developed machine learning methodology is a potential strategy for processing industrial sensory data since material testing, property prediction, and categorization are frequent tasks in manufacturing and production engineering industries. Further, this research demonstrated the necessity of embedded intelligence in automation of NDE toward Industrial Revolution 4.0.

Online Failure Prediction for Complex Systems: Methodology and Case Studies

Online Failure Prediction (OFP) allows proactively taking countermeasures before a failure occurs, such as saving data or restarting a system. However, despite its potential contribution to improving dependability, OFP still presents key limitations. Besides the problem of choosing the optimal set of features, assessing predictive models is complex and common procedures for supporting comparison are not available. There is, in fact, little work on developing and assessing failure predictors for complex systems. In this paper, we present two extensive case studies on distinct Operating Systems (OSs), Linux and Windows, showing that it is possible to create models that can predict different types of incoming failures, highlighting various important considerations such as the operational requirements of the target system. To drive the case studies, we define a well-structured framework for a fair and sound assessment and comparison of alternative predictive solutions. It includes scenarios for choosing the most adequate metrics for the assessment, comparing alternative models, and selecting the best predictor, while considering the need to tolerate perturbations in the data. In practice, we show that, by following a well-defined process, it is possible to develop accurate failure predictors and establish a ranking of the models under evaluation in different scenarios and OSs.

A novel interpretable feature set optimization method in blood pressure estimation using photoplethysmography signals

Blood pressure (BP) estimation based on photoplethysmography (PPG) signals enables continuous and comfortable BP measurement, which is important for the clinical management of hypertension. The purpose of this study is to propose a novel and interpretable feature optimization method to improve the performance of the PPG-based model for BP estimation. The PPG signals of 152 subjects were selected from a public database. Feature detection was performed on the signals after FIR band-pass filtering. A total of 172 features extracted from ten feature dimensions were used to construct a feature set, including features from the raw PPG signals, PPG derivative signals, and statistical information. Light Gradient Boosting Machine (LightGBM) was used as this work's prediction model. To further improve the performance of the LightGBM model, Shapley Additive Explanations (SHAP) were utilized for feature optimization to achieve the purpose. The number of features corresponding to the lowest model error was defined as the optimal feature set, and this was utilized for training the model to obtain BP estimation. Compared to the validated BP, the mean and standard deviation (SD) of the estimation errors for systolic blood pressure (SBP) and diastolic blood pressure (DBP) were −0.73 ± 6.50 mmHg and 0.37 ± 3.83 mmHg, respectively. According to the British Hypertension Society (BHS) criteria, SBP and DBP are within the range of B and A grades, respectively. We propose a novel feature optimization method to reduce the feature dimension for BP estimation. The algorithm can effectively prevent overfitting and improve the model's performance.

Abnormal Diagnosis Method of Self-Powered Power Supply System Based on Improved GWO-SVM

In order to solve the problem of low abnormal diagnosis rate of self-powered power supply system, an improved grey wolf optimization-support vector machine (GWO-SVM) algorithm combined with maximal information coefficient (MIC) are proposed. First, the feature sets of 11 kinds of monitoring data are optimized and selected based on MIC for self-powered power supply system. By eliminating redundant variables and insensitive variables, feature variable sets with great influence on abnormal diagnosis are selected. Second, by upgrading the selection method of control parameter σ from linear to nonlinear, an improved GWO-SVM algorithm that can take into account both global and local search capabilities is proposed. Furthermore, the optimal feature set which has great influence on abnormal diagnosis is selected as the input of the proposed algorithm, and then the abnormal diagnosis method combining the improved GWO-SVM with MIC is constructed for self-powered power supply system. The specific algorithm flow and step are given. Finally, compared with other algorithm, the simulation experiments show that the GWO-SVM method has a higher accuracy and a higher recall rate for the abnormal diagnosis in the self-powered power supply system.

Automatic risk prediction of intracranial aneurysm on CTA image with convolutional neural networks and radiomics analysis.

Intracranial aneurysm (IA) is a nodular protrusion of the arterial wall caused by the localized abnormal enlargement of the lumen of a brain artery, which is the primary cause of subarachnoid hemorrhage. Accurate rupture risk prediction can effectively aid treatment planning, but conventional rupture risk estimation based on clinical information is subjective and time-consuming. We propose a novel classification method based on the CTA images for differentiating aneurysms that are prone to rupture. The main contribution of this study is that the learning-based method proposed in this study leverages deep learning and radiomics features and integrates clinical information for a more accurate prediction of the risk of rupture. Specifically, we first extracted the provided aneurysm regions from the CTA images as 3D patches with the lesions located at their centers. Then, we employed an encoder using a 3D convolutional neural network (CNN) to extract complex latent features automatically. These features were then combined with radiomics features and clinical information. We further applied the LASSO regression method to find optimal features that are highly relevant to the rupture risk information, which is fed into a support vector machine (SVM) for final rupture risk prediction. The experimental results demonstrate that our classification method can achieve accuracy and AUC scores of 89.78% and 89.09%, respectively, outperforming all the alternative methods. Our study indicates that the incorporation of CNN and radiomics analysis can improve the prediction performance, and the selected optimal feature set can provide essential biomarkers for the determination of rupture risk, which is also of great clinical importance for individualized treatment planning and patient care of IA.

Multi-view radiomics and deep learning modeling for prostate cancer detection based on multi-parametric MRI.

This study aims to develop an imaging model based on multi-parametric MR images for distinguishing between prostate cancer (PCa) and prostate hyperplasia. A total of 236 subjects were enrolled and divided into training and test sets for model construction. Firstly, a multi-view radiomics modeling strategy was designed in which different combinations of radiomics feature categories (original, LoG, and wavelet) were compared to obtain the optimal input feature sets. Minimum-redundancy maximum-relevance (mRMR) selection and least absolute shrinkage selection operator (LASSO) were used for feature reduction, and the next logistic regression method was used for model construction. Then, a Swin Transformer architecture was designed and trained using transfer learning techniques to construct the deep learning models (DL). Finally, the constructed multi-view radiomics and DL models were combined and compared for model selection and nomogram construction. The prediction accuracy, consistency, and clinical benefit were comprehensively evaluated in the model comparison. The optimal input feature set was found when LoG and wavelet features were combined, while 22 and 17 radiomic features in this set were selected to construct the ADC and T2 multi-view radiomic models, respectively. ADC and T2 DL models were built by transferring learning from a large number of natural images to a relatively small sample of prostate images. All individual and combined models showed good predictive accuracy, consistency, and clinical benefit. Compared with using only an ADC-based model, adding a T2-based model to the combined model would reduce the model's predictive performance. The ADCCombinedScore model showed the best predictive performance among all and was transformed into a nomogram for better use in clinics. The constructed models in our study can be used as a predictor in differentiating PCa and BPH, thus helping clinicians make better clinical treatment decisions and reducing unnecessary prostate biopsies.

Prediction of stock price movement using an improved NSGA-II-RF algorithm with a three-stage feature engineering process.

Prediction of stock price has been a hot topic in artificial intelligence field. Computational intelligent methods such as machine learning or deep learning are explored in the prediction system in recent years. However, making accurate predictions of stock price direction is still a big challenge because stock prices are affected by nonlinear, nonstationary, and high dimensional features. In previous works, feature engineering was overlooked. How to select the optimal feature sets that affect stock price is a prominent solution. Hence, our motivation for this article is to propose an improved many-objective optimization algorithm integrating random forest (I-NSGA-II-RF) algorithm with a three-stage feature engineering process in order to decrease the computational complexity and improve the accuracy of prediction system. Maximizing accuracy and minimizing the optimal solution set are the optimization directions of the model in this study. The integrated information initialization population of two filtered feature selection methods is used to optimize the I-NSGA-II algorithm, using multiple chromosome hybrid coding to synchronously select features and optimize model parameters. Finally, the selected feature subset and parameters are input to the RF for training, prediction, and iterative optimization. Experimental results show that the I-NSGA-II-RF algorithm has the highest average accuracy, the smallest optimal solution set, and the shortest running time compared to the unmodified multi-objective feature selection algorithm and the single target feature selection algorithm. Compared to the deep learning model, this model has interpretability, higher accuracy, and less running time.

Apis-Prime: A deep learning model to optimize beehive monitoring system for the task of daily weight estimation

This work presents Apis-Prime,22This study extends the work in Anwar et al. (2022).a hybrid deep learning model for soft sensing and time series forecasting, to estimate the daily weight variations of honeybee hives. Apis-Prime improves the state-of-the-art of earlier proposed WE-Bee (Anwar et al., 2022), and also helps optimize the beehive monitoring systems for the task of daily weight variation estimation. Weight variations of a honeybee hive are the most important indicator of hive productivity, and the health and strength of a bee colony. Currently, precise measurement of the weight of a hive requires an expensive weighing scale under each hive. On the other hand, sensors deployed inside the hive are cheaper than a weighing scale, and are shielded from the extreme weather variations outside the hive. In this work, honeybee activity is monitored using data from sensors inside the hive, along with monitoring the information related to the seasons, time of the day, weather, and the size of the hive. Apis-Prime’s deep learning algorithm is based on two self-attention encoders, which collectively transform the sensor data into daily weight variations of the hive. Two parallel encoders simultaneously pay attention to time-based relationships and feature-based relationships within the daily sensor data and generate daily hive weight estimates with better accuracy. The comparison shows an average error of 19.7 grams/frame for Apis-Prime, compared to 21.05 grams/frame for the earlier proposed model WE-Bee. For system optimization, this work uses the attention weights of trained encoders of Apis-Prime to evaluate the sensor features collected by the monitoring system. This evaluation is used to identify and remove the unnecessary sensors/features from the dataset, reducing the number of features from 36 to 23, hence providing a significant optimization of cost, power, and data bandwidth. We provide a performance analysis of beehive weight estimations by Apis-Prime using the complete, as well as the optimized dataset on 2,170 days of beehive sensor recordings. Equally good results of daily weight estimations using the optimized feature set demonstrate the efficacy of the proposed model for the optimization of the beehive monitoring system for the task of hive weight estimation.

Affective state estimation based on Russell’s model and physiological measurements

Affective states are psycho-physiological constructs connecting mental and physiological processes. They can be represented in terms of arousal and valence according to the Russel’s model and can be extracted from physiological changes in human body. However, a well-established optimal feature set and a classification method effective in terms of accuracy and estimation time are not present in the literature. This paper aims at defining a reliable and efficient approach for real-time affective state estimation. To obtain this, the optimal physiological feature set and the most effective machine learning algorithm, to cope with binary as well as multi-class classification problems, were identified. ReliefF feature selection algorithm was implemented to define a reduced optimal feature set. Supervised learning algorithms, such as K-Nearest Neighbors (KNN), cubic and gaussian Support Vector Machine, and Linear Discriminant Analysis, were implemented to compare their effectiveness in affective state estimation. The developed approach was tested on physiological signals acquired on 20 healthy volunteers during the administration of images, belonging to the International Affective Picture System, conceived for inducing different affective states. ReliefF algorithm reduced the number of physiological features from 23 to 13. The performances of machine learning algorithms were compared and the experimental results showed that both accuracy and estimation time benefited from the optimal feature set use. Furthermore, the KNN algorithm resulted to be the most suitable for affective state estimation. The results of the assessment of arousal and valence states on 20 participants indicate that KNN classifier, adopted with the 13 identified optimal features, is the most effective approach for real-time affective state estimation.

Development and comparative evaluation of various fault detection algorithms for a drum brake using artificial neural networks and a physics-based model

Drum brakes are among the essential safety components in automobiles; hence, it is critical to detect any fault in the system that might hinder its performance. A fault detection framework based on artificial intelligence and a rigid-body model of a system (as a digital experiment) is proposed to detect four of the most common faults in automotive drum brakes. First, a contact mechanics-based nonlinear model of a drum brake (incorporating conformal contact between the brake shoes and the brake drum) is developed to estimate the dynamic response accurately. The predictions from this model are compared with the data available in the literature. The responses estimated from the model with a known level of faults form the input data set for various fault quantification algorithms. Sensitivity-based pruning technique in conjunction with an artificial neural network is used to select the optimal set of features for which the physical interpretations are deduced. The developed fault detection methodologies are quantitatively compared, and the most applicable among them is determined based on the detection accuracy and the computational cost. Finally, the robustness of the selected methodology is tested under the presence of white Gaussian noise in the measured signals. The proposed framework and the selected methodology will help design an accurate health monitoring tool to diagnose faults in automotive drum brakes. Though the current study focuses on drum brakes, the possible generalization of its framework to other systems is discussed.

Quantitative analysis of pulse arrival time and PPG morphological features based cuffless blood pressure estimation: a comparative study between diabetic and non-diabetic groups.

Pulse arrival time (PAT) and PPG morphological features have attracted much interest in cuffless blood pressure (BP) estimation, but their effects are not clearly understood when vascular characteristics are affected by diseases such as diabetes. This work quantitatively analyzes the effect of diabetic disease on the PAT and PPG morphological features-based BP estimation. We selected 112 diabetic patients and 308 non-diabetic subjects from VitalDB, and extracted 16 features including PAT, PPG morphological features, and heart rate. BP estimation performance was statistically compared between groups using linear regression models with several feature sets, and the relative importance of each feature in the optimal feature set was extracted. As a result, the standard deviation of the error and mean absolute error of PAT-based BP estimation were significantly higher in the diabetic group than in the non-diabetic group (p < 0.01). A feature set containing PAT and PPG morphological features achieved the best performance in both groups. However, the relative importance of each feature for BP estimation differed notably between groups. The results indicate that different features are important depending on the vascular characteristics, which could help to construct different models to accommodate specific diseases.

An improved hybrid chameleon swarm algorithm for feature selection in medical diagnosis

Feature selection (FS) is generally associated with the process of using a probabilistic method to select optimal feature combinations during pre-processing steps in data mining. This technique can optimize the datasets’ features that need to be considered to heighten the performance of classification on the grounds of the selected optimal feature set. In this paper, a hybridization model is evolved and applied to select the optimal feature subset based on a binary version of the Hybrid Memory Improved Chameleon Swarm Algorithm (CSA) (HMICSA) and the k-Nearest Neighbor (k-NN) classifier. In this FS model, the following are proposed and applied: (1) Four kinds of transfer functions, (2) Amendments to the velocity of the CSA’s individuals, (3) Addition of internal memory to the CSA’s individuals, and (4) Hybridization of CSA with Ali baba and the Forty Thieves (AFT) algorithm. These actions are aimed to strike an adequate equipoise between global exploration and local exploitation conducts of the search space of the basic CSA. This is to mitigate the problem of early convergence, and to sidestep trapping into a local optima in CSA. The efficacy of the proposed FS algorithm was evaluated on 24 medical diagnosis benchmark datasets collected from different specialized repositories and compared with other k-NN-based FS methods. The all-inclusive outcomes using various evaluation methods disclose the competence of the proposed method in augmenting the classification performance compared to other methods, ensuring its potential in scouting the feature space and designating the most useful features for classification tasks.

Gaussian Coordinate Feature Set Optimisation (GCFSO) Model for Analysing the Impact of Urbanisation on Cultural Identities and City Images

Urbanization, characterized by the rapid growth of cities and the associated changes in social, economic, and physical landscapes, has been a significant global phenomenon in recent decades. As cities expand and transform, they play a crucial role in shaping cultural identity and projecting a distinct city image. The constructed framework process comprises the multi-modal image processing with the Gaussian Coordinate estimation with the Optimization model. The proposed model comprises the estimation of the feature sets associated with the feature set for the classification of cultural identity. The model comprises the Gaussian Coordinate Feature Set Optimization (GcFSO). The GcFSO model estimates the feature sets in the data related to the cultural identity for the shaping of images to analyze the urbanization process. The GcFSO model computes the feature set based on the Mandami Fuzzy set model for the classification of cultural identity in China. The fuzzy set rules are computed for the estimation of the features in the process of Urbanization. The performance of the GcFSO model is examined with the deep learning model for classification. The simulation analysis stated that GcFSO model achieves a higher classification accuracy of 0.99 with a minimal error rate.

Leopard seal optimization (LSO): A natural inspired meta-heuristic algorithm

The main objective of this paper is to introduce a new NIO algorithm inspired from the hunting strategy of the leopard seals called Leopard Seal Optimization (LSO)to provide a simple swarm intelligence algorithm that have a high flexibility to solve real-time engineering problems in a fast and more accurate manner without falling into local optima problem. LSO is compared against recent NIO algorithms considering feature selection for disease diagnosing as the underlying optimization problem. In experimental results, LSO has been statistically tested against a recent six swarm intelligence algorithms using Wilcoxon test and t-test with significance level equals 0.05 based on the common five benchmark functions. These recent algorithms are called Tuna Swarm Optimization (TSO), Pelican Optimization Algorithm (POA), Cat and Mouse-Based Optimization (CMBO), Aphid–Ant Mutualism (AAM), White Shark Optimizer (WSO), and Red Piranha Optimization (RPO). The statistical analysis proved that LSO outperforms other recent techniques in most cases where the most tested results are less than 0.05. Then, LSO has been tested against the same algorithms in binary version as feature selection algorithms using two metrics called accuracy and execution time. It is noted that LSO is faster and more accurate than other algorithms to determine the optimal set of features at all numbers of search agents. Finally, it is concluded that LSO outperforms other techniques using accuracy, execution time, Wilcoxon test, and t-test metrics. Compared to the recent techniques using the maximum iteration number=400, LSO provided the maximum accuracy value that equals 97.62% at the search agents number=120 and the minimum execution time that equals 1314 at the search agents number= 40.