Facial Expression Recognition using Conspicuous Features Selection and Comparison of the Performance of Different Classifiers

Objective. The quantitative assessment of Parkinsonian tremor, e.g. (0, 1, 2, 3, 4) according to the Movement Disorder Society-Unified Parkinson’s Disease Rating Scale, is crucial for treating Parkinson’s disease. However, the tremor amplitude constantly fluctuates due to environmental and psychological effects on the patient. In clinical practice, clinicians assess the tremor severity for a short duration, whereas manual tremor labeling relies on the clinician’s physician experience. Therefore, automatic tremor quantification based on wearable inertial sensors and machine learning algorithms is affected by the manual labels of clinicians. In this study, an automatic modification method for the labels judged by clinicians is presented to improve Parkinsonian tremor quantitation. Approach. For the severe overlapping of dynamic feature range between different severities, an outlier modification algorithm (PCA-IQR) based on the combination of principal component analysis and interquartile range statistic rule is proposed to learn the blurred borders between different severity scores, thereby optimizing the labels. Afterward, according to the modified feature vectors, a support vector machine (SVM) with a radial basis function (RBF) kernel is proposed to classify the tremor severity. The classifier models of SVM with RBF kernel, k-nearest neighbors, and SVM with the linear kernel are compared. Main results. Experimental results show that the proposed method has high classification performance and excellent model generalization ability for tremor quantitation (accuracy: 97.93%, precision: 97.96%, sensitivity: 97.93%, F1-score: 97.94%). Significance. The proposed method may not only provide valuable assistance for clinicians to assess the tremor severity accurately, but also provides self-monitoring for patients at home and improve the assessment skills of clinicians.

Indonesia holds vast tourism potential, including Nusa Penida, Bali, renowned for its natural beauty. However, the adoption of modern technology to support tourism promotion and management remains limited. This study aims to compare the performance of Support Vector Machine (SVM) with Radial Basis Function (RBF) kernel and Random Forest algorithms in classifying images of three main tourist attractions in Nusa Penida: Angel’s Billabong, Broken Beach, and Kelingking Beach. The dataset consists of 450 images processed using the Histogram of Oriented Gradients (HOG) method for feature extraction. Two data split scenarios (80:20 and 70:30) were applied to evaluate the algorithms based on accuracy, precision, recall, and F1-score metrics. The experimental results revealed that SVM with RBF kernel outperformed Random Forest in all scenarios, achieving the best results in the 70% training and 30% testing data split with an accuracy of 0.967, precision of 0.969, recall of 0.967, and F1-score of 0.967. While Random Forest demonstrated stable performance, it remained inferior to SVM with RBF kernel. This study concludes that SVM with RBF kernel is superior for image classification tasks, offering opportunities for implementing artificial intelligence technologies to advance the tourism sector in Indonesia.

The depths, which have been used to detect outliers or to extract a representative subset, can be applied to classification. We propose a resampling-based classification method based on the fact that resampling techniques yield a consistent estimator of the distribution of a statistic. The performance of this method was evaluated with eight contaminated models in terms of Correct Classification Rates (CCRs), and the results were compared with other known methods. The proposed method consistently showed higher average CCRs and 4% higher CCR at the maximum compared to other methods. In addition, this method was applied to Berkeley data. The average CCRs were between 0.79 and 0.85.

Children with autism spectrum disorder (ASD) are deficit in communication, social skills, empathy, emotional responsiveness and have significant behavioral pattern. They have difficulty in understanding other feelings and their own emotions. This leads to the sudden emotional outburst and aggressive behavior in these children. Parents, caretakers and doctors find it very difficult to prevent such extreme behaviors. Learning the positive and negative valence leads in determining the early indications before the onset of emotional outbursts in children with ASD. The present study measures the psycho physiological electrocardiogram (ECG) signal from the typically developed (TD) children and children with ASD in the age group of 5–11 years. Personalized protocol was developed for every child with ASD to induce positive and negative valence and ECG data was collected using wearable Shimmer ECG device. The heart rate variability (HRV) and the QRS amplitude were derived from ECG signal using Pan–Tompkins algorithm and eleven features were extracted using DWT (db2, db4 and db8) mother wavelet. The significant features of ECG, HRV and QRS amplitude were classified using the K nearest neighbor (KNN), support vector machine (SVM) and ensemble classifier. Ensemble and KNN classifier achieved maximum accuracy of 81% and 76.2% for children with ASD and Ensemble and SVM classifiers obtained maximum accuracy of 87.4% and 83.8% for TD children using HRV data.

Objective: Delirium is an important syndrome found in patients in the intensive care unit (ICU), however, it is usually under-recognized during treatment. This study was performed to investigate whether delirious patients can be successfully distinguished from non-delirious patients by using heart rate variability (HRV) and machine learning. Approach: Electrocardiography data of 140 patients was acquired during daily ICU care, and HRV data were analyzed. Delirium, including its type, severity, and etiologies, was evaluated daily by trained psychiatrists. HRV data and various machine learning algorithms including linear support vector machine (SVM), SVM with radial basis function (RBF) kernels, linear extreme learning machine (ELM), ELM with RBF kernels, linear discriminant analysis, and quadratic discriminant analysis were utilized to distinguish delirium patients from non-delirium patients. Main results: HRV data of 4797 ECGs were included, and 39 patients had delirium at least once during their ICU stay. The maximum classification accuracy was acquired using SVM with RBF kernels. Our prediction method based on HRV with machine learning was comparable to previous delirium prediction models using massive amounts of clinical information. Significance: Our results show that autonomic alterations could be a significant feature of patients with delirium in the ICU, suggesting the potential for the automatic prediction and early detection of delirium based on HRV with machine learning.

In order to improve the accuracy in classification of electroencephalographic (EEG) signals of different brain functions, the research of how to select the suitable classifier is carried out in the paper. Some experiments have been performed to select the suitable kernel function of support vector machine (SVM). Four different kernel functions are put into the comparison and the results show that the radial basis function (RBF) has the highest rate of correct classification (RCC). On the other hand, the EEG signals from different electrodes will lead different classification results. The study of selecting the suitable electrode has been done. It shows that the RCC of the signal which from the electrode near by the area where EEG signal of a certain brain function is generated is much higher than those far from. We increase the dimension of SVM through combine the signal of different channels, which the RCC is very low, to improve the RCC of the signal which far from the area of the certain brain function. The results of our experiments are satisfied. The RCC of the EEG signal can reached to 99%.

Kernel functions are used in support vector machines (SVM) to compute inner product in a higher dimensional feature space. SVM classification performance depends on the chosen kernel. The radial basis function (RBF) kernel is a distance-based kernel that has been successfully applied in many tasks. This paper focuses on improving the accuracy of SVM by proposing a non-linear combination of multiple RBF kernels to obtain more flexible kernel functions. Multi-scale RBF kernels are weighted and combined. The proposed kernel allows better discrimination in the feature space. This new kernel is proved to be a Mercer’s kernel. Furthermore, evolutionary strategies (ESs) are used for adjusting the hyperparameters of SVM. Training accuracy, the bound of generalization error, and subset cross-validation on training accuracy are considered to be objective functions in the evolutionary process. The experimental results show that the accuracy of multi-scale RBF kernels is better than that of a single RBF kernel. Moreover, the subset cross-validation on training accuracy is more suitable and it yields the good results on benchmark datasets.

An expert system based on least square support vector machines for diagnosis of the valvular heart disease

The quality of fresh apple fruits is a major concern for consumers and manufacturers. Classification of these fruits according to their ripening stage is one of the most decisive factors in determining their quality. In this regard, the aim of this work is to develop a new method for non-destructive classification of the ripening state of Fuji apples using hyperspectral information in the visible and near-infrared (Vis/NIR) regions. Spectra of 172 apple samples in the range from 450 to 1000 nm were studied, which were selected from four different ripening stages. A convolutional neural network (CNN) model was proposed to perform the classification of the samples. The proposed method was compared with three alternative methods based on artificial neural networks (ANN), support vector machines (SVM), and k-nearest neighbors (KNN). The results revealed that the CNN method outperformed the alternative methods, achieving a correct classification rate (CCR) of 96.5%, compared with an average of 89.5%, 95.93%, and 91.68% for ANN, SVM, and KNN, respectively. These results will help in the development of a new device for fast and accurate estimation of the quality of apples.

Accurate estimation of forest aboveground biomass is essential for the assessment of regional carbon cycle and the climate change in the terrestrial ecosystem. Currently, ensemble learning algorithms and cross-validation methods have been widely applied to estimate regional forest Above Ground Biomass (AGB). However, the effects of ensemble learning algorithms, validation methods, and their interactions on forest AGB estimation were rarely investigated. Based on Landsat 8 Operational Land Imager (OLI) imagery, Airborne Laser Scanning (ALS) data and China’s National Forest Continuous Inventory data, this study explored the effects of five ensemble learning algorithms, including Simple Averaging (SA), Weighted Averaging (WA), Stacked Generalization (SG), Random Forest (RF) and Extreme Gradient Boosting (XGBoost), and two validation approaches (i.e. 10-fold and leave-one-out cross-validation) on the AGB estimation of the Natural Secondary Forests (NSFs) in northeast China. The results revealed that the ensemble learning algorithms that combine heterogenous-based models (i.e. SA, WA, SG) generally produced higher accuracy than the base models (i.e. Decision Tree (DT), K-Nearest Neighbor (KNN), Support Vector Regression (SVR), Convolutional Neural Network (CNN)). Among all ensemble learning algorithms, the SG algorithm has the highest accuracy whereas the XGBoost algorithm has the lowest accuracy. Although prediction models considerably impact the accuracy of AGB estimation, the validation approach also plays a non-negligible role in AGB estimation. The leave-one-out cross-validation produced much higher accuracy than the 10-fold cross-validation using the same prediction model and tends to generate over-optimistic AGB estimates compared to 10-fold cross-validation, especially for the averaging and stacking ensemble learning algorithms (i.e. SA, WA, SG). This study highlights the potential challenges of applying a leave-one-out cross-validation approach and provides a scientific foundation for the feasibility of different ensemble learning algorithms and cross-validation approaches for accurate AGB estimation.

Palm tree detection using remote sensing images has received increasing attention in recent years, concerning the issues of sustainability, productivity and profitability. There has been significant progress in the research of using machine learning techniques, especially convolutional neural networks (CNNs) for automatic palm tree detection. However, whether CNNs can actually outperform traditional human-engineered approaches in terms of classification accuracy and detection speed is yet unknown. In the present study, we have compared human-engineered features namely histogram of oriented gradients (HOG), local binary pattern (LBP) and scale-invariant feature transform (SIFT) with features extracted using pre-trained AlexNet model for detecting palm trees in high resolution images obtained via unmanned aerial vehicle (UAV). Support vector machines (SVM) with linear and non-linear kernels were used to classify feature vectors obtained by different feature extractors. Haar-like features used in Viola-Jones framework was also tested in the study. Results showed that features extracted from the fifth convolutional layer of AlexNet achieved the highest accuracy of 96.1% using SVM with RBF kernel as classifier, which surpassed the accuracy obtained by fully-connected CNN, namely 95.6%. The results also suggest that SVM classifier with radial basis function (RBF) kernel using LBP as features is the optimal combination as it achieved comparable accuracy but higher detection speed than CNN approaches.

Predictive fish distribution models have utility in planning conservation measures for rare fish species. However, species rarity creates sampling and modeling difficulties that require an understanding of model accuracy. We evaluated existing distribution models for 10 rare fishes based on 2,026 community fish samples and associated riverine habitat. Our fieldwork provided an independent fish species inventory for 143 sample sites. This inventory was used to quantify species detectability for use as a weighting factor with which to correct false-negative modeling errors. Presence/absence data were compared with predictions to evaluate model accuracy as determined by Cohen's kappa and correct classification rates. Detection probabilities were generally small but ranged from 0 to 0.68. The models predicted species occurrence with relatively high success (average kappa = 45.6% and average correct classification rate = 74.1%). The habitat variables for predicting species occurrence varied among species; however, stream size and streamflow were the most influential. All distribution models had adequate predictive abilities and improved our understanding of fish distributions and the factors determining those distributions. Model accuracy statistics can provide managers with a measure of confidence when they are directing conservation activities.

As knowledge of genetics and genome elements increases, the demand for the development of bioinformatics tools for analyzing these data is raised. Riboswitches are genetic components, usually located in the untranslated regions of mRNAs, that regulate gene expression. Additionally, their interaction with antibiotics has been recently suggested, implying a role in antibiotic effects and resistance. Following a previously published sequential block finding algorithm, herein, we report the development of a new block location-based feature extraction strategy (BLBFE). This procedure utilizes the locations of family-specific sequential blocks on riboswitch sequences as features. Furthermore, the performance of other feature extraction strategies, including mono- and dinucleotide frequencies, k-mer, DAC, DCC, DACC, PC-PseDNC-General and SC-PseDNC-General methods, was investigated. KNN, LDA, naïve Bayes, PNN and decision tree classifiers accompanied by V-fold cross-validation were applied for all methods of feature extraction, and their performances based on the defined feature extraction strategies were compared. Performance measures of accuracy, sensitivity, specificity and F-score for each method of feature extraction were studied. The proposed feature extraction strategy resulted in classification of riboswitches with an average correct classification rate (CCR) of 90.8%. Furthermore, the obtained data confirmed the performance of the developed feature extraction method with an average accuracy of 96.1%, an average sensitivity of 90.8%, an average specificity of 97.52% and an average F-score of 90.69%. Our results implied that the proposed feature extraction (BLBFE) method can classify and discriminate riboswitch families with high CCR, accuracy, sensitivity, specificity and F-score values.

Initial neural net construction for the detection of cervical intraepithelial neoplasia by fluorescence imaging

In the evolving field of cybersecurity, detecting malicious activity in high-dimensional network data remains a persistent challenge for traditional machine learning (ML) techniques. This study investigates the use of convolutional variational autoencoders (VAEs) to generate latent features that enhance the performance of various ML classifiers on the 2015 NSL-KDD dataset. Classifiers, including Gaussian Naïve Bayes (GNB), support vector machines (SVMs) with Radial Basis Function (RBF) kernel, decision trees, and dense neural networks, were evaluated using metrics such as accuracy, precision, recall, F1 score, and the Matthews Correlation Coefficient (MCC). To assess the effectiveness of VAEs, Principal Component Analysis (PCA) was used as a baseline dimensionality reduction method, and performance comparisons were made. The best-performing model was an SVM with an RBF kernel, a PCA (threshold = 0.92), and a VAE with six latent features, achieving an accuracy of 82.8%, an F1 score of 0.830, and an MCC of 0.682. The results indicate that VAEs can significantly enhance classifier performance, particularly in GNB and SVM models, suggesting their value in developing more effective intrusion detection systems. Received: 23 August 2024 | Revised: 3 June 2025 | Accepted: 15 July 2025 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in NSL-KDD Dataset at https://github.com/t-taylor/cvaes-research/tree/main/results. Author Contribution Statement Thomas Taylor: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Data curation, Writing – original draft, Writing – review & editing, Visualization. Amna Eleyan: Conceptualization, Methodology, Writing – original draft, Writing – review & editing, Supervision, Project administration. Mohammed Al-Khalidi: Validation, Resources, Writing – original draft, Writing – review & editing, Visualization, Supervision.