K-nearest Neighbor Classifier Research Articles

Evaluating Dimensionality Reduction Techniques in Bitcoin Ransomware Detection: Comparative Analysis of Incremental PCA and UMAP

ABSTRACTThis study investigates the classification performance of various machine learning algorithms on the Bitcoin Heist ransomware dataset, focusing on the effects of dimensionality reduction techniques. The primary objective was to evaluate the classifiers' effectiveness in distinguishing between malicious and benign transactions under three experimental scenarios: without dimensionality reduction, utilizing Incremental Principal Component Analysis (IPCA), and applying Uniform Manifold Approximation and Projection (UMAP). The methodology involved rigorous experimentation with four classifiers: K‐Nearest Neighbors (KNN), XGBoost, Decision Tree, and Multi‐Layer Perceptron (MLP). The results demonstrated that dimensionality reduction techniques, particularly UMAP, improved the performance of KNN and Decision Tree classifiers while adversely affecting the performance of XGBoost and MLP. Notably, KNN consistently outperformed the other classifiers across different scenarios, indicating its robustness in handling reduced feature spaces. This study concludes that the effectiveness of dimensionality reduction is contingent upon the specific characteristics of the classifiers employed.

Comparison of Machine Learning Algorithms and Hybrid Computational Intelligence Algorithms for Rehabilitation Classification and Prognosis in Reverse Total Shoulder Arthroplasty

Despite the increasing application of machine learning and computational intelligence algorithms in medicine and physiotherapy, accurate classification and prognosis algorithms for postoperative patients in the rehabilitation phase are still lacking. The present study was carried out in two phases. In Phase I, classification performance of simple machine learning algorithms applied on data of patients suffering of reverse total shoulder arthroplasty (RTSA), examining algorithms’ classification accuracy and patients’ rehabilitation prognosis. In Phase II, hybrid computational intelligence algorithms were developed and applied in order to search for the minimum possible training set that achieves the maximum classification and prognostic performance. The data included features like age and gender, passive range of available motion of all movements (preoperative and postoperative), visual analog pain scale (preoperative and postoperative), and total rehabilitation time. In Phase I, K-nearest neighbors (ΚΝΝ) classification algorithm and K-means clustering algorithm (GAKmeans) were applied. Also, a genetic algorithm (GA)-based clustering algorithm (GAClust) was also applied. To achieve 100% performance on the test set, KNN used 80% of the data in the training set, whereas K-means and GAClust used 90% and 53.3%, respectively. In Phase II, additional computational intelligence algorithms were developed, namely, GAKNN (Genetic Algorithm K-nearest neighbors), GAKmeans, and GA2Clust (genetic algorithm-based clustering algorithm 2), for genetic algorithm optimization of the training set. Genetic algorithm optimization of the training set using hybrid algorithms in Phase II resulted in 100% performance on the test set by using only 35% of the available data for training. The proposed hybrid algorithms can reliably be used for patients’ rehabilitation prognosis.

CubicPat: Investigations on the Mental Performance and Stress Detection Using EEG Signals

Background\Objectives: Solving the secrets of the brain is a significant challenge for researchers. This work aims to contribute to this area by presenting a new explainable feature engineering (XFE) architecture designed to obtain explainable results related to stress and mental performance using electroencephalography (EEG) signals. Materials and Methods: Two EEG datasets were collected to detect mental performance and stress. To achieve classification and explainable results, a new XFE model was developed, incorporating a novel feature extraction function called Cubic Pattern (CubicPat), which generates a three-dimensional feature vector by coding channels. Classification results were obtained using the cumulative weighted iterative neighborhood component analysis (CWINCA) feature selector and the t-algorithm-based k-nearest neighbors (tkNN) classifier. Additionally, explainable results were generated using the CWINCA selector and Directed Lobish (DLob). Results: The CubicPat-based model demonstrated both classification and interpretability. Using 10-fold cross-validation (CV) and leave-one-subject-out (LOSO) CV, the introduced CubicPat-driven model achieved over 95% and 75% classification accuracies, respectively, for both datasets. Conclusions: The interpretable results were obtained by deploying DLob and statistical analysis.

Fixed-focus laser triangulation simultaneously measures the morphology and color of object

Abstract Simultaneously measuring the surface morphology and color of a sample is crucial for full-color 3D printing and digitization of cultural artifacts. However, traditional methods are susceptible to the variations in the measurement angle and illumination condition, making it difficult to balance the color fidelity and spatial accuracy. Here, we propose a laser triangulation method that is implemented with a fixed focus, dark-field illumination, and data-driven spectral classification. With a fixed focus, this method measures the height of surface by analyzing the shape of reflected light spot. The dark-field illumination diminishes the background contributed by the specular reflection of white light, enabling an accurate spectral measurement. The data-driven spectral classification algorithm establishes color dataset for each sample, and ensures a precise color recognition through Principal component analysis (PCA) dimensionality reduction and K-nearest neighbor (KNN) classification. In our experiment, this method achieved an axial resolution of 5.1μm. The color classification accuracy was as high as 99.79% on ColorChecker cards and 96.03% on Pantone color match cards. Two samples were reconstructed and evaluated to validate this method, the Mean
Absolute Error (MAE) of the morphology measurements did not exceed 25μm, and the color difference (CIE2000) does not exceed 1.0, confirming its ability to accurately measure the surface morphology and color simultaneously.surface morphology and color simultaneously.

Improving detection of Parkinson’s disease with acoustic feature optimization using particle swarm optimization and machine learning

Abstract Parkinson’s disease (PD), characterized by motor impairments and tremors, also presents early-stage vocal abnormalities that hold diagnostic potential. Leveraging voice analysis and classification techniques, numerous studies explore the feasibility of early PD detection through automated systems. While several databases offer acoustic features for this purpose, their effectiveness largely depends on the classification methodology employed. This study aims to refine PD detection systems by introducing customized weighting to acoustic features, adjusting their significance based on their correlation with the disease and the classification algorithm utilized. The particle swarm optimization algorithm is employed for this purpose, with the Oxford PD dataset serving as the source data for training and validation. Performance evaluation encompasses four classification algorithms: support vector machine, Gradient Boosting (GB), k-nearest neighbors (KNN), and Naïve Bayes. A 5-fold cross-validation technique was adopted to evaluate the effectiveness of our method for PD detection. The results show that our approach significantly improves performance regardless of the classifier used, demonstrating its generalization capability. The KNN classifier surpasses state-of-the-art results, achieving an accuracy of 97.44% and a sensitivity of 98.02%.

Quantum-inspired K-nearest neighbors classifier for enhanced printer source identification in forensic document analysis

Document source identification in printer forensics focuses on determining the source printer of a document by analyzing characteristics such as printer model, serial number, defects, or unique artifacts. This is crucial in forensic investigations involving counterfeit documents or anonymous threats. However, identifying consistent patterns across different printers remains challenging, especially when perpetrators attempt to obscure these artifacts. Machine learning models in this field must identify discriminative features that differentiate printers while minimizing noise. In particular, choosing an appropriate distance metric for K-Nearest Neighbors (KNN) classifiers is critical and requires experimentation. This study proposes a quantum-inspired approach to improve KNN’s performance in printer source identification. By exploring alternative number of neighbors (K), quantum-inspired computing can optimize feature space calculations, even in noisy conditions. This allows the system to iteratively refine and select the optimal K value based on classification performance, ensuring that the best K is identified for the specific dataset and task. The system utilizes the Grey Level Co-occurrence Matrix (GLCM) for feature extraction, which is robust to changes in rotation and scale. Experimental results demonstrate that the Quantum-inspired KNN (QKNN) classifier outperforms classical KNN, achieving higher accuracy in identifying subtle printing artifacts, even under variable conditions.

Qualitative analysis of terpenoid esters based on near-infrared spectroscopy and machine learning.

This study delves into the method of qualitative analysis of terpenoid esters using near-infrared spectroscopy technology. Terpenoid esters are bioactive compounds widely used in the pharmaceutical and cosmetics industries. Near-infrared spectroscopy technology enables rapid and accurate component analysis without compromising the integrity of the sample, which is particularly important for valuable samples that need to be preserved intact or require subsequent analysis. This research combines machine learning techniques, such as K-Nearest Neighbors (K-NN) classifier, Random Forests algorithm, and Back Propagation Neural Networks (BPNN), to analyze terpenoid ester samples extracted from different concentrations of eluents, and compares and evaluates these algorithms. This study results show that in the test set, the prediction accuracy of the K-NN classifier is 96.154% and BPNN is 94.231%, and the Random Forest algorithm performs the best with a prediction accuracy of 100%. Additionally, this study utilizes the Random Forest algorithm to predict the characteristic spectra of terpenoid esters, demonstrating the effectiveness of feature spectrum extraction by ensuring a prediction accuracy of 100% while reducing the number of spectral features.

Identification of clonally expanded T-cell receptor sequences in giant cell arteritis.

Arterial wall inflammation in giant cell arteritis (GCA) is characterized by T-cell infiltration and granuloma formation. There have been limited studies investigating the diversity of the T-cell receptor (TCR) repertoire in GCA patients. Here we aim to identify disease-relevant TCRs. We sequenced the TCRβ repertoires in peripheral blood and biopsies from 72 GCA patients and compared them to repertoires of 60 age-matched controls. Applying K-nearest neighbours classification based on tcrdist3, an established TCR similarity measure, we identified GCA-associated TCRs across multiple model hyperparameters and experimental replicates. We observed that species richness and Shannon diversity were significantly lower (P=0.0003 and P=0.004, respectively) in GCA peripheral blood TCR repertoires compared with age-matched controls. 1526 TCRs were identified that were consistently associated with GCA, 63 TCRs were also detected in TAB repertoires. Identical GCA-associated TCRs were observed in paired blood and tissue samples from 21/30 GCA cases. 57% of GCA-associated TCRs were fitted into 10 clusters, which displayed distinct TCR sequences and TCR V and J segment usage. TRBV20-1∗01, TRBV4-3∗01, TRBV4-2∗01 and TRBV4-1∗01 segments were over-represented and occurred at least 10% more often among GCA patients than age-matched controls. Only 27/1526 TCR sequences had matches reported in public databases, reducing the likelihood that these targeted common infectious agents. Our data provide evidence of circulating T-cell clonal expansions in GCA patients. Certain TCR sequence patterns were over-represented in GCA subjects. As more TCR sequences directed at human antigens become available, further analysis may ultimately reveal whether these TCRs bind a common target antigen.

Cardiac sound classification using a hybrid approach: MFCC-based feature fusion and CNN deep features

The detection of cardiovascular diseases through the analysis of phonocardiograms (PCGs), which are digital recordings of heartbeat sounds, is crucial for early diagnosis. Conventional feature extraction methods often face challenges in distinguishing non-stationary signals like healthy and pathological PCG signals. Our research addresses these challenges by adopting a hybrid feature extraction scheme that leverages deep learning and handcrafted techniques. This approach allows for a more effective analysis and classification of PCG signals. This paper presents a novel approach to PCG signal classification, leveraging a fusion of deep learning features and handcrafted features based on mutual information measurements. High-level features are obtained through a pretrained deep network applied to time-frequency representations of PCG signals. Additionally, Mel-Frequency Cepstral Coefficients of empirical wavelet subbands serve as handcrafted features. Canonical correlation analysis is employed for feature fusion, effectively combining crucial information from both feature types. Classification is performed using support vector machines, k-nearest neighbor, and multilayer perceptron (MLP) classifiers with a fivefold cross-validation approach. Evaluation using the Physionet Challenge 2016 database demonstrates the superior performance of our proposed approach compared to existing state-of-the-art studies, showcasing its efficacy in PCG signal classification.

Aircraft Sensor Fault Diagnosis Based on GraphSage and Attention Mechanism

Aircraft sensors are crucial for ensuring the safe and efficient operation of aircraft. However, these sensors are vulnerable to external factors that can lead to malfunctions, making fault diagnosis essential. Traditional deep learning-based fault diagnosis methods often face challenges, such as limited data representation and insufficient feature extraction. To address these problems, this paper proposes an enhanced GraphSage-based fault diagnosis method that incorporates attention mechanisms. First, signal data representing the coupling characteristics of various sensors are constructed through data stacking. These signals are then transformed into graph data with a specific topology reflecting the overall sensor status of the aircraft using K-nearest neighbor and Radius classification algorithms. This approach helps fully leverage the correlations between data points. Next, node and neighbor information is aggregated through graph sampling and attention-based aggregation methods, strengthening the extraction of fault features. Finally, fault diagnosis is performed using multi-layer aggregation and transformation within fully connected layers. Experiments demonstrate that the proposed method outperforms baseline approaches, achieving better detection performance and faster computational speed. The method has been validated on both simulated and real-flight data.

Short-Wave Infrared Spectroscopy for On-Site Discrimination of Hazardous Mineral Fibers Using Machine Learning Techniques

Asbestos fibers are well-known carcinogens, and their rapid detection is critical for ensuring safety, protecting public health, and promoting environmental sustainability. In this work, short-wave infrared (SWIR) spectroscopy, combined with machine learning (ML), was evaluated as an environmentally friendly analytical approach for simultaneously distinguishing the asbestos type, asbestos-containing materials in various forms, asbestos-contaminated/-uncontaminated soil, and asbestos-contaminated/-uncontaminated cement, simultaneously. This approach offers a noninvasive and efficient alternative to traditional laboratory methods, aligning with sustainable practices by reducing hazardous waste generation and enabling in situ testing. Different chemometrics techniques were applied to discriminate the material classes. In more detail, partial least squares discriminant analysis (PLS-DA), principal component analysis-based discriminant analysis (PCA-DA), principal component analysis-based K-nearest neighbors classification (PCA-KNN), classification and regression trees (CART), and error-correcting output-coding support vector machine (ECOC SVM) classifiers were tested. The tested classifiers showed different performances in discriminating between the analyzed samples. CART and ECOC SVM performed best (RecallM and AccuracyM equal to 1.00), followed by PCA-KNN (RecallM of 0.98–1.00 and AccuracyM equal to 1.00). Poorer performances were obtained by PLS-DA (RecallM of 0.68–0.72 and AccuracyM equal to 0.95) and PCA-DA (RecallM of 0.66–0.70 and AccuracyM equal to 0.95). This research aligns with the United Nations’ Sustainable Development Goals (SDGs), particularly SDG 3 (Good Health and Well-Being), by enhancing human health protection through advanced asbestos detection methods, and SDG 12 (Responsible Consumption and Production), by promoting sustainable, low-waste testing methodologies.

Integrating Retinal Segmentation Metrics with Machine Learning for Predictions from Mouse SD-OCT Scans

Purpose This study aimed to initially test whether machine learning approaches could categorically predict two simple biological features, mouse age and mouse species, using the retinal segmentation metrics. Methods The retinal layer thickness data obtained from C57BL/6 and DBA/2J mice were processed for machine learning after segmenting mouse retinal SD-OCT scans. Twenty-two models were trained to predict the mouse groups. The best neural network model was optimized for better outcomes. Prediction accuracy, the area under the curve, sensitivity, specificity, precision, and F-1 score values were obtained. Results The Wilcoxon Signed-Rank test provided significantly higher validation accuracy for neural networks than decision trees, discriminant analysis, support vector machines, and k-nearest neighbor classifiers (p = 0.005 for all). For C57BL/6-DBA/2J classification, a mean validation accuracy of 88.11 ± 3.92% (95% CI: 86.99-89.22) was achieved for the neural network when the optimized neural network had 92.31% final test accuracy with an area under the curve value of 0.9762, 94.44% sensitivity, 90.48% specificity, 89.47% precision, and 0.92 F-1 score. The optimized neural network model for age group differentiation had a final test accuracy of 82.05% with a 0.9064 area under the curve value, 77.27% sensitivity, 88.24% specificity, 89.47% precision, and 0.83 F-1 score. Conclusions These findings validate that machine learning, using segmentation metrics instead of images, can effectively analyze retinal OCT scans in mice for categorical predictions in experimental models. Expanding this approach with additional features, including histopathological and functional correlations, is expected to improve the prediction power further, promising valuable applications to predict more complex outcomes in experimental and clinical studies.

MSIMRS: Multi-Scale Superpixel Segmentation Integrating Multi-Source Remote Sensing Data for Lithology Identification in Semi-Arid Area

Lithology classification stands as a pivotal research domain within geological Remote Sensing (RS). In recent years, extracting lithology information from multi-source RS data has become an inevitable trend. Various classification image primitives yield distinct outcomes in lithology classification. The current research on lithology classification utilizing RS data has predominantly concentrated on pixel-level classification, which suffers from a long classification time and high sensitivity to noise. In order to explore the application potential of superpixel segmentation in lithology classification, this study proposed the Multi-scale superpixel Segmentation Integrating Multi-source RS data (MSIMRS), and conducted a lithology classification study in Duolun County, Inner Mongolia Autonomous Region, China combining MSIMRS and the Support Vector Machine (MSIMRS-SVM). In addition, pixel-level K-Nearest Neighbor (KNN), Random Forest (RF) and SVM classification algorithms, as well as deep-learning models including Resnet50 (Res50), Efficientnet_B8 (Effi_B8), and Vision Transformer (ViT) were chosen for a comparative analysis. Among these methods, our proposed MSIMRS-SVM achieved the highest accuracy in lithology classification in a typical semi-arid area, Duolun County, with an overall accuracy and Kappa coefficient of 92.9% and 0.92. Moreover, the findings indicate that incorporating superpixel segmentation into lithology classification resulted in notably fewer fragmented patches and significantly improved the visualization effect. The results showcase the application potential of superpixel primitives in lithology information extraction within semi-arid areas.

Monkeypox diagnosis based on probabilistic K-nearest neighbors (PKNN) algorithm.

Although it is not a new illness and has been around since the previous century, monkeypox later resurgence is fraught with difficulties. This study presents a novel approach of diagnosing monkeypox using artificial intelligence, which is called Effective Monkeypox Diagnosis Strategy (EMDS). The proposed EMDS is established through two sequential stages, namely; (i) Pre-Processing Phase (PP) and (ii) Monkeypox Diagnosing phase (MDP). During PP the input image dataset is prepared through three processes, which are; feature extraction, feature selection, and anomaly rejection, while the actual diagnosis performed in the MDP. Features are extracted from input images using GoogleNet as an effective pre-trained deep learning model, while Leopard Seal Optimization (LSO) is employed to select the most instructive features. The major contribution of this paper is focused in two issues, which are; (i) introducing a new methodology for rejecting anomalies from the input image dataset based on interquartile range (IQR), and (ii) proposing a new instance of K-Nearest Neighbor classifier for monkeypox diagnosis, which is called; Probabilistic K-Nearest Neighbors (PKNN) Algorithm. The proposed PKNN combines evidence from distance based traditional KNN as well as the Naïve probabilistic theorem used by Naïve Bayes (NB) algorithm in an integrated way. Numerous experiments have been conducted considering the proposed EMDS as well as recent competitive strategies on two public monkeypox datasets, which are; the Monkeypox Skin Image and Lesion Datasets (MSID and MSLD, respectively). Initially, the performance of the basic contributions of the proposed EMDS, which are the outlier rejection methodology (ORM) and PKNN, are evaluated individually. Then, EMSD as a whole is evaluated. Moreover, an ablation study has also been conducted to evaluate the effect of ORM and PKNN on the performance of EMSD. Based on the experimental results, it is shown that EMDS outperforms recent monkeypox identification strategies as it achieves 99% diagnosis accuracy. Moreover, it indicates the maximum precision and recall with the minimum diagnosis time.

Modified kernel global-local marginal fisher analysis for rolling bearing feature extraction

Abstract The vibration signals of rolling bearings usually exhibit high-dimensional, nonlinear, and non-Gaussian distribution characteristics due to long-term operation under complex working conditions. Therefore, we proposed a novel algorithm named Modified Kernel Global-Local Marginal Fisher Analysis (MKGLMFA) for bearing feature extraction and dimensionality reduction. The proposed MKGLMFA algorithm introduces the kernel function to map data into a high-dimensional space to represent data nonlinearly first. It enhances the within-class compactness and between-class dispersibility by considering spatial relationships and label information when constructing adjacency graphs and simultaneously exploits the local and global geometry of data. Furthermore, a bearing fault diagnosis approach is presented based on MKGLMFA. It first processes the original vibration signals through MKGLMFA to obtain low-dimensional manifold features. Then these characteristics were input into the K-nearest neighbor (KNN) classifier to achieve fault pattern recognition. The superiority of the proposed MKGLMFA algorithm in feature extraction is verified in comparison with some existing state-of-the-art machine learning methods on three rolling bearings datasets. And the subsequent classification diagnosis experiments indicate the effectiveness and high efficiency of the newly raised MKGLMFA algorithm. In comparison with the representative diagnosis methods, the proposed method can extract more sensitive discriminant features, and the classification accuracy of diagnosis is significantly improved in consequence.

Using Inertial Measurement Units and Machine Learning to Classify Body Positions of Adults in a Hospital Bed.

In hospitals, timely interventions can prevent avoidable clinical deterioration. Early recognition of deterioration is vital to stopping further decline. Measuring the way patients position themselves in bed and change their positions may signal when further assessment is necessary. While inertial measurement units (IMUs) have been used in health research, their use inside hospitals has been limited. This study explores the use of IMUs with machine learning to continuously capture, classify and visualise patient positions in hospital beds. The participants attended a data collection session in a simulated hospital bedspace and were asked to adopt nine positions. Movement data were captured using five IMU Xsens DOTs attached to the forehead, wrists and ankles. Support Vector Machine (SVM) and K-Nearest Neighbours classifiers were trained using five different combinations of sensors (e.g., right wrist only, right and left wrist) to determine body positions. Data from 30 participants were analysed. The highest accuracy (87.7%) was achieved by SVM using forehead and wrist sensors. Adding data from ankle sensors reduced the accuracy. To preserve patient privacy in a hospital setting, a 3D visualisation was developed in Unity, offering a non-identifiable representation of patient positions. This system could help clinicians monitor changes in position which may signal clinical deterioration.

EEG-based neural activity for decoding situation awareness at different levels.

Situation awareness (SA) is the ability to perceive, comprehend and project environmental information. Neural activity is closely associated with SA. However, it remains unclear how neural activity represents SA at different levels. Here, three tasks were used to assess SA at three levels, behavioural and electroencephalogram data were collected. Relationships between SA and neural activity were explored through comparisons of EEG power between high and low SA. For each SA level, EEG power significantly differed between high and low SA. Brain region-based analyses further revealed neural activities originating from distinct brain regions were recruited to represent SA at different levels. These EEG pattern features differed between high and low SA could be used to decode SA with the KNN (k-nearest neighbour) classifier. The present study marked a significant step in augmenting our understanding of the neural mechanism that characterise SA.

Zipper Pattern: An Investigation into Psychotic Criminal Detection Using EEG Signals.

Background: Electroencephalography (EEG) signal-based machine learning models are among the most cost-effective methods for information retrieval. In this context, we aimed to investigate the cortical activities of psychotic criminal subjects by deploying an explainable feature engineering (XFE) model using an EEG psychotic criminal dataset. Methods: In this study, a new EEG psychotic criminal dataset was curated, containing EEG signals from psychotic criminal and control groups. To extract meaningful findings from this dataset, we presented a new channel-based feature extraction function named Zipper Pattern (ZPat). The proposed ZPat extracts features by analyzing the relationships between channels. In the feature selection phase of the proposed XFE model, an iterative neighborhood component analysis (INCA) feature selector was used to choose the most distinctive features. In the classification phase, we employed an ensemble and iterative distance-based classifier to achieve high classification performance. Therefore, a t-algorithm-based k-nearest neighbors (tkNN) classifier was used to obtain classification results. The Directed Lobish (DLob) symbolic language was used to derive interpretable results from the identities of the selected feature vectors in the final phase of the proposed ZPat-based XFE model. Results: To obtain the classification results from the ZPat-based XFE model, leave-one-record-out (LORO) and 10-fold cross-validation (CV) methods were used. The proposed ZPat-based model achieved over 95% classification accuracy on the curated EEG psychotic criminal dataset. Moreover, a cortical connectome diagram related to psychotic criminal detection was created using a DLob-based explainable artificial intelligence (XAI) method. Conclusions: In this regard, the proposed ZPat-based XFE model achieved both high classification performance and interpretability. Thus, the model contributes to feature engineering, psychiatry, neuroscience, and forensic sciences. Moreover, the presented ZPat-based XFE model is one of the pioneering XAI models for investigating psychotic criminal/criminal individuals.

Classification of wool and cashmere fiber based on LBP and DWT features: performance comparison of random forest, AdaBoost, and KNN classifiers

The automatic identification of cashmere and wool fibers presents a significant challenge due to their substantial structural and textural similarities. An image-based method is proposed in this article, which combines local binary pattern (LBP), discrete wavelet transform (DWT), and several classification algorithms – including random forest (RF), adaptive boosting (AdaBoost), and K-nearest neighbors (KNN) – to achieve rapid and accurate differentiation between wool and cashmere fibers. Primarily, 300 images each of cashmere and wool fibers were captured using optical microscopy, and the original images were pre-processed to prepare input data for feature extraction. Texture features were then extracted using LBP, and energy entropy was extracted using DWT. Fiber diameters were measured through geometric morphological analysis, using the maximum inscribed circle method to determine fiber diameter from segmented images. In conclusion, these features were input into RF, AdaBoost, and KNN classifiers for model training and classification. Experimental results indicate that the RF classifier achieved superior performance, with a classification accuracy of 94.88%, outperforming both AdaBoost and KNN, and demonstrating high recall, and F1 scores. Overall, the proposed method exhibits exceptional accuracy, robustness, and generalization capability in fiber classification tasks, with significant potential for application to the classification of other natural fibers.

An EEG-based framework for automated discrimination of conversion to Alzheimer's disease in patients with amnestic mild cognitive impairment: an 18-month longitudinal study.

As a clinical precursor to Alzheimer's disease (AD), amnestic mild cognitive impairment (aMCI) bears a considerably heightened risk of transitioning to AD compared to cognitively normal elders. Early prediction of whether aMCI will progress to AD is of paramount importance, as it can provide pivotal guidance for subsequent clinical interventions in an early and effective manner. A total of 107 aMCI cases were enrolled and their electroencephalogram (EEG) data were collected at the time of the initial diagnosis. During 18-month follow-up period, 42 individuals progressed to AD (PMCI), while 65 remained in the aMCI stage (SMCI). Spectral, nonlinear, and functional connectivity features were extracted from the EEG data, subjected to feature selection and dimensionality reduction, and then fed into various machine learning classifiers for discrimination. The performance of each model was assessed using 10-fold cross-validation and evaluated in terms of accuracy (ACC), area under the curve (AUC), sensitivity (SEN), specificity (SPE), positive predictive value (PPV), and F1-score. Compared to SMCI patients, PMCI patients exhibit a trend of "high to low" frequency shift, decreased complexity, and a disconnection phenomenon in EEG signals. An epoch-based classification procedure, utilizing the extracted EEG features and k-nearest neighbor (KNN) classifier, achieved the ACC of 99.96%, AUC of 99.97%, SEN of 99.98%, SPE of 99.95%, PPV of 99.93%, and F1-score of 99.96%. Meanwhile, the subject-based classification procedure also demonstrated commendable performance, achieving an ACC of 78.37%, an AUC of 83.89%, SEN of 77.68%, SPE of 76.24%, PPV of 82.55%, and F1-score of 78.47%. Aiming to explore the EEG biomarkers with predictive value for AD in the early stages of aMCI, the proposed discriminant framework provided robust longitudinal evidence for the trajectory of the aMCI cases, aiding in the achievement of early diagnosis and proactive intervention.