Feature Extraction Method Research Articles

MAR-YOLOv9: A multi-dataset object detection method for agricultural fields based on YOLOv9

With the development of deep learning technology, object detection has been widely applied in various fields. However, in cross-dataset object detection, conventional deep learning models often face performance degradation issues. This is particularly true in the agricultural field, where there is a multitude of crop types and a complex and variable environment. Existing technologies still face performance bottlenecks when dealing with diverse scenarios. To address these issues, this study proposes a lightweight, cross-dataset enhanced object detection method for the agricultural domain based on YOLOv9, named Multi-Adapt Recognition-YOLOv9 (MAR-YOLOv9). The traditional 32x downsampling Backbone network has been optimized, and a 16x downsampling Backbone network has been innovatively designed. A more streamlined and lightweight Main Neck structure has been introduced, along with innovative methods for feature extraction, up-sampling, and Concat connection. The hybrid connection strategy allows the model to flexibly utilize features from different levels. This solves the issues of increased training time and redundant weights caused by the detection neck and auxiliary branch structures in traditional YOLOv9, enabling MAR-YOLOv9 to maintain high performance while reducing the model’s computational complexity and improving detection speed, making it more suitable for real-time detection tasks. In comparative experiments on four plant datasets, MAR-YOLOv9 improved the mAP@0.5 accuracy by 39.18% compared to seven mainstream object detection algorithms, and by 1.28% compared to the YOLOv9 model. At the same time, the model size was reduced by 9.3%, and the number of model layers was decreased, reducing computational costs and storage requirements. Additionally, MAR-YOLOv9 demonstrated significant advantages in detecting complex agricultural images, providing an efficient, lightweight, and adaptable solution for object detection tasks in the agricultural field. The curated data and code can be accessed at the following link: https://github.com/YangxuWangamI/MAR-YOLOv9.

A Robust Hybrid Approach for Malware Detection: Leveraging CNN and LSTM for Encrypted Traffic Analysis

The rapid growth in Internet usage and advancements in network technologies have escalated the risk of network attacks. As the adoption of encryption protocols increases, so does the difficulty in identifying malware within encrypted traffic. Malware represents a significant danger in cyberspace, as it compromises personal data and harms computer systems. Network attacks involve unauthorized access to networks, often aiming to disrupt or damage them, with potentially severe consequences. To counter these threats, researchers, developers, and security experts are constantly innovating new malware detection techniques. Recently, deep learning has gained traction in network security and intrusion detection systems (IDSs), with models such as Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) showing promise in detecting malicious traffic. Despite these advancements, extracting relevant features from diverse malware types remains a challenge. Current solutions demand substantial computational resources and are often inefficient for large datasets. Additionally, existing image-based feature extraction methods consume significant resources. This study tackles these issues by employing a 1D CNN alongside LSTM for the detection and classification of encrypted malicious traffic. Using the Malware Analysis benchmark dataset, which consists of 42,797 malware and 1,079 goodware API call sequences, the proposed model achieved an accuracy of 99.2%, surpassing other state-of-the-art models

A robust deep learning approach for identification of RNA 5-methyluridine sites

RNA 5-methyluridine (m5U) sites play a significant role in understanding RNA modifications, which influence numerous biological processes such as gene expression and cellular functioning. Consequently, the identification of m5U sites can play a vital role in the integrity, structure, and function of RNA molecules. Therefore, this study introduces GRUpred-m5U, a novel deep learning-based framework based on a gated recurrent unit in mature RNA and full transcript RNA datasets. We used three descriptor groups: nucleic acid composition, pseudo nucleic acid composition, and physicochemical properties, which include five feature extraction methods ENAC, Kmer, DPCP, DPCP type 2, and PseDNC. Initially, we aggregated all the feature extraction methods and created a new merged set. Three hybrid models were developed employing deep-learning methods and evaluated through 10-fold cross-validation with seven evaluation metrics. After a comprehensive evaluation, the GRUpred-m5U model outperformed the other applied models, obtaining 98.41% and 96.70% accuracy on the two datasets, respectively. To our knowledge, the proposed model outperformed all the existing state-of-the-art technology. The proposed supervised machine learning model was evaluated using unsupervised machine learning techniques such as principal component analysis (PCA), and it was observed that the proposed method provided a valid performance for identifying m5U. Considering its multi-layered construction, the GRUpred-m5U model has tremendous potential for future applications in the biological industry. The model, which consisted of neurons processing complicated input, excelled at pattern recognition and produced reliable results. Despite its greater size, the model obtained accurate results, essential in detecting m5U.

Automatic categorization of medical documents in Afaan Oromo using ensemble machine learning techniques

Automatic medical document classification using machine learning techniques can enhance the productivity of healthcare services by reducing processing time and cost. This work proposes an ensemble learning approach to develop a model that classifies electronic medical documents in Afaan Oromo. The main tasks in this work are preparing the corpus, pre-processing, training the models, and the classification process. We used the term frequency-inverse document frequency (TF-IDF) and bag of words (BOW) feature extraction methods. An ensemble technique in this work is that it creates multiple individual classifier predictions from naïve Bayes, random forest, SVM, and logistic regression and then combines them to advance a reliable and more accurate classifier. Evaluation measures were employed using accuracy, F1-score, recall, and precision for performance comparison. The efficiency of the proposed method is compared with the two existing boosting approaches, namely gradient boosting and adaboost. The experimental result shows the efficiency of BOW feature extraction over TF-IDF in this work on our dataset. These results also illustrated the effectiveness of the proposed model by scoring 94.81% accuracy and 94.84% F1-score. This work significantly contributes to the technological enhancement of service delivery, managing documents through classification methods, and advancing the data processing systems in healthcare sectors.

Anchoring temporal convolutional networks for epileptic seizure prediction.

Accurate and timely prediction of epileptic seizures is crucial for empowering patients to mitigate their impact or prevent them altogether. Current studies predominantly focus on short-term seizure predictions, which causes the prediction time to be shorter than the onset of antiepileptic, thus failing to prevent seizures. However, longer epilepsy prediction faces the problem that as the preictal period lengthens, it increasingly resembles the interictal period, complicating differentiation. To address these issues, we employ the sample entropy method for feature extraction from electroencephalography (EEG) signals. Subsequently, we introduce the Anchoring Temporal Convolutional Networks (ATCN) model for longer-term, patient-specific epilepsy prediction. ATCN utilizes dilated causal convolutional networks to learn time-dependent features from previous data, capturing temporal causal correlations within and between samples. Additionally, the model also incorporates anchoring data to enhance the performance of epilepsy prediction further. Finally, we proposed a multilayer sliding window prediction algorithm for seizure alarms. Evaluation on the Freiburg intracranial EEG dataset shows our approach achieves 100% sensitivity, a false prediction rate (FPR) of 0.08 per hour and an average prediction time (APT) of 99.98 minutes. Using the CHB-MIT scalp EEG dataset, we a achieve 97.44% sensitivity, an FPR of 0.11 per hour, and an APT of 92.99 minutes. These results demonstrate that our approach is adequate for seizure prediction over a more extended prediction range on intracranial and scalp EEG datasets. The average prediction time of our approach exceeds the typical onset time of antiepileptic. This approach is particularly beneficial for patients who need to take medication at regular intervals, as they may only need to take their medication when our method issues an alarm. This capability has the potential to prevent seizures, which will greatly improving patients' quality of life.

A novel multi-model feature generation technique for suicide detection

Automated expert systems (AES) analyzing depression-related content on social media have piqued the interest of researchers. Depression, often linked to suicide, requires early prediction for potential life-saving interventions. In the conventional approach, psychologists conduct patient interviews or administer questionnaires to assess depression levels. However, this traditional method is plagued by limitations. Patients might not feel comfortable disclosing their true feelings to psychologists, and counselors may struggle to accurately predict situations due to limited data. In this context, social media emerges as a potentially valuable resource. Given the widespread use of social media in daily life, individuals often express their nature and mental state through their online posts. AES can efficiently analyze vast amounts of social media content to predict depression levels in individuals at an early stage. This study contributes to this endeavor by proposing an innovative approach for predicting suicide risks using social media content and machine learning techniques. A novel multi-model feature generation technique is employed to enhance the performance of machine learning models. This technique involves the use of a feature extraction method known as term frequency-inverse document frequency (TF-IDF), combined with two machine learning models: logistic regression (LR) and support vector machine (SVM). The proposed technique calculates probabilities for each sample in the dataset, resulting in a new feature set referred to as the probability-based feature set (ProBFS). This ProBFS is compact yet highly correlated with the target classes in the dataset. The utilization of concise and correlated features yields significant outcomes. The SVM model achieves an impressive accuracy score of 0.96 using ProBFS while maintaining a low computational time of 5.63 seconds even when dealing with extensive datasets. Furthermore, a comparison with state-of-the-art approaches is conducted to demonstrate the significance of the proposed method.

Autism Identification Based on the Intelligent Analysis of Facial Behaviors: An Approach Combining Coarse- and Fine-Grained Analysis

Background: Facial behavior has emerged as a crucial biomarker for autism identification. However, heterogeneity among individuals with autism poses a significant obstacle to traditional feature extraction methods, which often lack the necessary discriminative power. While deep-learning methods hold promise, they are often criticized for their lack of interpretability. Methods: To address these challenges, we developed an innovative facial behavior characterization model that integrates coarse- and fine-grained analyses for intelligent autism identification. The coarse-grained analysis provides a holistic view by computing statistical measures related to facial behavior characteristics. In contrast, the fine-grained component uncovers subtle temporal fluctuations by employing a long short-term memory (LSTM) model to capture the temporal dynamics of head pose, facial expression intensity, and expression types. To fully harness the strengths of both analyses, we implemented a feature-level attention mechanism. This not only enhances the model’s interpretability but also provides valuable insights by highlighting the most influential features through attention weights. Results: Upon evaluation using three-fold cross-validation on a self-constructed autism dataset, our integrated approach achieved an average recognition accuracy of 88.74%, surpassing the standalone coarse-grained analysis by 8.49%. Conclusions: This experimental result underscores the improved generalizability of facial behavior features and effectively mitigates the complexities stemming from the pronounced intragroup variability of those with autism, thereby contributing to more accurate and interpretable autism identification.

Estimation of CO 2 saturation maps from synthetic seismic data using a deep-learning method with a multi-scale approach

In the context of Carbon Capture and Storage (CCS), monitoring the behaviour of CO 2 within subsurface reservoirs is pivotal for efficient and safe storage operations. This study proposes a new approach to enhance the accuracy of predicting CO 2 saturation maps directly from shot gathers, using a combination of deep learning (DL) and feature extraction methods. We employ a U-Net model, specifically tailored to solve regression tasks, and two-dimensional continuous wavelet transform (2D-CWT) to analyse shot gathers at different scales. We introduce a novel approach using multi-channel input data for the DL model, combining shot gathers and CWT images. The DL model was trained and tested using both single channel and multichannel input. The single channel datasets included shot gathers and CWT images at the first scale, while the multi-channel datasets integrated shot gathers with either two or four scales of CWT. We conducted a sensitivity analysis on the number of training epochs to compare the performance of the model with multichannel and single channel input. Additionally, a Transfer Learning approach was implemented to improve performance in noisy conditions by leveraging knowledge from a pre-trained model on noise-free images. Monte Carlo dropout was used to predict pixel-scale variability and provided a prediction variability with a standard deviation ranging from 0.019 to 0.194, enhancing the robustness of CO 2 saturation estimates. Our results suggest that combining feature extraction using 2D-CWT with the U-Net architecture improves the prediction performance of CO 2 saturation in a synthetic CCS model. Additionally, using multi-channel input instead of single channel is more efficient as it requires less training and prediction time to achieve comparable results. This confirms the effectiveness of 2D-CWT as a pre-processing technique, contributing valuable insights and advances in the field of data-driven geophysical inversion problems.

Jamming Attacks Detection Based on IGWO for Optimization of Fast Correlation-Based Feature extraction in Wireless Communication

Background: Wireless networks are essential communication technologies that prevent cable installation prices and burdens. Because of this technology's pervasive usage, wireless network safety is a significant problem. Owing to distributed and open wireless medium aspects, attackers might use different jamming methods to exploit physical and MAC layer protocol vulnerabilities. In addition, jamming attacks require to be accurately grouped so that suitable countermeasures can be considered. Given the potential severity of such attacks, precisely identifying and classifying them is critical for implementing effective responses. The motivation for this paper is the need to improve the detection and categorization of jamming signals using modern machine learning algorithms, consequently enhancing wireless network security and reliability. Objective: In this paper, we compare some machine learning models' efficiency for diagnosing jamming signals. Methods: Such algorithms refer to support vector machine (SVM) and k-nearest neighbors (KNN). We checked the signal features that recognize jamming signals. After the jamming attack model, the developed grey wolf optimizer version known as IGWO (improved grey wolf optimizer) has been discussed for feature extraction of software usability. Four separate metrics were employed as features to detect jamming attacks in order to evaluate the machine learning models. This novel feature extraction method is crucial for improving the accuracy of jamming detection. Results: The measurements of these parameters were gathered through a simulation of a real setting. And generated a large dataset using these parameters. Conclusion: The simulation results illustrate that the KNN algorithm based on jamming detection could diagnose jammers having a minimal likelihood of false alarms and a high level of accuracy.

Heart sound classification algorithm based on bispectral feature extraction and convolutional neural networks

Cardiovascular disease (CVD) is one of the leading causes of death worldwide. Heart sound classification plays a key role in the early detection of CVD. The difference between normal and abnormal heart sounds is not obvious. In this paper, in order to improve the accuracy of the heart sound classification model, we propose a heart sound feature extraction method based on bispectral analysis and combine it with convolutional neural network (CNN) to classify heart sounds. The model can effectively suppress Gaussian noise by using bispectral analysis and can effectively extract the features of heart sound signals without relying on the accurate segmentation of heart sound signals. At the same time, the model combines with the strong classification performance of convolutional neural network and finally achieves the accurate classification of heart sound. According to the experimental results, the proposed algorithm achieves 0.910, 0.884 and 0.940 in terms of accuracy, sensitivity and specificity under the same data and experimental conditions, respectively. Compared with other heart sound classification algorithms, the proposed algorithm shows a significant improvement and strong robustness and generalization ability, so it is expected to be applied to the auxiliary detection of congenital heart disease.

Enhancement algorithm for surface electromyographic-based gesture recognition based on real-time fusion of muscle fatigue features

This study aims to optimize surface electromyography-based gesture recognition technique, focusing on the impact of muscle fatigue on the recognition performance. An innovative real-time analysis algorithm is proposed in the paper, which can extract muscle fatigue features in real time and fuse them into the hand gesture recognition process. Based on self-collected data, this paper applies algorithms such as convolutional neural networks and long short-term memory networks to provide an in-depth analysis of the feature extraction method of muscle fatigue, and compares the impact of muscle fatigue features on the performance of surface electromyography-based gesture recognition tasks. The results show that by fusing the muscle fatigue features in real time, the algorithm proposed in this paper improves the accuracy of hand gesture recognition at different fatigue levels, and the average recognition accuracy for different subjects is also improved. In summary, the algorithm in this paper not only improves the adaptability and robustness of the hand gesture recognition system, but its research process can also provide new insights into the development of gesture recognition technology in the field of biomedical engineering.

Machine Learning For Risk Prediction After Heart Failure Emergency Department Visit or Hospital Admission Using Administrative Health Data.

Patients visiting the emergency department (ED) or hospitalized for heart failure (HF) are at increased risk for subsequent adverse outcomes, however effective risk stratification remains challenging. We utilized a machine-learning (ML)-based approach to identify HF patients at risk of adverse outcomes after an ED visit or hospitalization using a large regional administrative healthcare data system. Patients visiting the ED or hospitalized with HF between 2002-2016 in Alberta, Canada were included. Outcomes of interest were 30-day and 1-year HF-related ED visits, HF hospital readmission or all-cause mortality. We applied a feature extraction method using deep feature synthesis from multiple sources of health data and compared performance of a gradient boosting algorithm (CatBoost) with logistic regression modelling. The area under receiver operating characteristic curve (AUC-ROC) was used to assess model performance. We included 50,630 patients with 93,552 HF ED visits/hospitalizations. At 30-day follow-up in the holdout validation cohort, the AUC-ROC for the combined endpoint of HF ED visit, HF hospital readmission or death for the Catboost and logistic regression models was 74.16 (73.18-75.11) versus 62.25 (61.25-63.18), respectively. At 1-year follow-up corresponding values were 76.80 (76.1-77.47) versus 69.52 (68.77-70.26), respectively. AUC-ROC values for the endpoint of all-cause death alone at 30-days and 1-year follow-up were 83.21 (81.83-84.41) versus 69.53 (67.98-71.18), and 85.73 (85.14-86.29) versus 69.40 (68.57-70.26), for the CatBoost and logistic regression models, respectively. ML-based modelling with deep feature synthesis provided superior risk stratification for HF patients at 30-days and 1-year follow-up after an ED visit or hospitalization using data from a large administrative regional healthcare system.

Decoding the brain: EEG applications in sensory processing, emotion recognition, and pain assessment

This work explores the diverse applications of electroencephalography (EEG) across sensory processing, emotion recognition, and pain assessment. It analyzes recent studies employing EEG to investigate auditory perception, visual processing, emotional states, and pain experiences, highlighting common methodological approaches such as preprocessing techniques, feature extraction methods, and classification algorithms. Key findings reveal EEG’s potential in decoding complex brain states, from identifying neural correlates of music perception to detecting pain signals, and discuss the advancement of machine learning techniques, particularly deep learning, in enhancing the accuracy and real-time capabilities of EEG-based systems. The paper also addresses challenges in EEG research, such as limited spatial resolution and the need for larger, more diverse datasets, and proposes future directions emphasizing multimodal integration, standardization of protocols, and the development of user-friendly tools for clinical applications. This paper underscores EEG’s significant role in advancing our understanding of brain function and its potential to revolutionize neurological diagnostics and treatments.

Utilizing Attention-Enhanced Deep Neural Networks for Large-Scale Preliminary Diabetes Screening in Population Health Data

Early screening for diabetes can promptly identify potential early stage patients, possibly delaying complications and reducing mortality rates. This paper presents a novel technique for early diabetes screening and prediction, called the Attention-Enhanced Deep Neural Network (AEDNN). The proposed AEDNN model incorporates an Attention-based Feature Weighting Layer combined with deep neural network layers to achieve precise diabetes prediction. In this study, we utilized the Diabetes-NHANES dataset and the Pima Indians Diabetes dataset. To handle significant missing values and outliers, group median imputation was applied. Oversampling techniques were used to balance the diabetes and non-diabetes groups. The data were processed through an Attention-based Feature Weighting Layer for feature extraction, producing a feature matrix. This matrix was subjected to Hadamard product operations with the raw data to obtain weighted data, which were subsequently input into deep neural network layers for training. The parameters were fine-tuned and the L2 regularization and dropout layers were added to enhance the generalization performance of the model. The model’s reliability was thoroughly assessed through various metrics, including the accuracy, precision, recall, F1 score, mean squared error (MSE), and R2 score, as well as the ROC and AUC curves. The proposed model achieved a prediction accuracy of 98.4% in the Pima Indians Diabetes dataset. When the test dataset was expanded to the large-scale Diabetes-NHANES dataset, which contains 52,390 samples, the test precision of the model improved further to 99.82%, with an AUC of 0.9995. A comparative analysis was conducted using multiple models, including logistic regression with L1 regularization, support vector machine (SVM), random forest, K-nearest neighbors (KNNs), AdaBoost, XGBoost, and the latest semi-supervised XGBoost. The feature extraction method using attention mechanisms was compared with the classical feature selection methods, Lasso and Ridge. The experiments were performed on the same dataset, and the conclusion was that the Attention-based Ensemble Deep Neural Network (AEDNN) outperformed all the aforementioned methods. These results indicate that the model not only performs well on smaller datasets but also fully leverages its advantages on larger datasets, demonstrating strong generalization ability and robustness. The proposed model can effectively assist clinicians in the early screening of diabetes patients. This is particularly beneficial for the preliminary screening of high-risk individuals in large-scale, extensive healthcare datasets, followed by detailed examination and diagnosis. Compared to the existing methods, our AEDNN model showed an overall performance improvement of 1.75%.

Advances in Gas Detection of Pattern Recognition Algorithms for Chemiresistive Gas Sensor

Gas detection and monitoring are critical to protect human health and safeguard the environment and ecosystems. Chemiresistive sensors are widely used in gas monitoring due to their ease of fabrication, high customizability, mechanical flexibility, and fast response time. However, with the rapid development of industrialization and technology, the main challenges faced by chemiresistive gas sensors are poor selectivity and insufficient anti-interference stability in complex application environments. In order to overcome these shortcomings of chemiresistive gas sensors, the pattern recognition method is emerging and is having a great impact in the field of sensing. In this review, we focus systematically on the advancements in the field of data processing methods for feature extraction, such as the methods of determining the characteristics of the original response curve, the curve fitting parameters, and the transform domain. Additionally, we emphasized the developments of traditional recognition algorithms and neural network algorithm in gas discrimination and analyzed the advantages through an extensive literature review. Lastly, we summarized the research on chemiresistive gas sensors and provided prospects for future development.

Phase-based video vibration measurement and fault feature extraction method for compound faults of rolling bearings

Vibration characterization of rotating machinery is crucial for determining rotational and failure frequencies. Traditional contact measurement methods have limitations, while high-speed cameras offer a non-contact alternative for measuring target vibrations, spatial phase-based techniques have recently been widely used in detecting subtle vibrations and show good robustness to imaging noise. In this paper, a vision-based vibration extraction method for rotating machinery is proposed, aiming at extracting minor vibrations of bearings from them and further analyzing their fault frequencies. To address the challenge of separating a single fault frequency from the extracted compound faulty vibration signals, kurtosis is employed to analyze the inverse convolution period of multiple periodic components, and the MOMEDA filter length is optimized using the golden section algorithm. MOMEDA is then used to enhance each periodic pulse separately, and fault frequency is obtained through envelope spectrum demodulation. In the experimental part, a phase-based method is used to extract minor vibration displacements from rotor vibration video, which is subsequently compared with eddy current sensors in both time and frequency domains to verify the accuracy of the proposed method in extracting vibration displacements based on vision. Finally, vibration signals are extracted from the bearing compound fault video, and the single fault frequency characteristics of the bearing are successfully separated using the adaptive MOMEDA method, which provides an efficient and reliable method in the field of rotating machinery fault diagnosis.

A mode shape sensitivity-based wavelet feature extraction method for interface debonding detection in concrete-filled steel tubes

A mode shape sensitivity-based wavelet feature extraction method for interface debonding detection in concrete-filled steel tubes

DMFGAN: a multifeature data augmentation method for grape leaf disease identification.

The use of deep learning techniques to identify grape leaf diseases relies on large, high-quality datasets. However, a large number of images occupy more computing resources and are prone to pattern collapse during training. In this paper, a depth-separable multifeature generative adversarial network (DMFGAN) was proposed to enhance grape leaf disease data. First, a multifeature extraction block (MFEB) based on the four-channel feature fusion strategy is designed to improve the quality of the generated image and avoid the problem of poor feature learning ability of the adversarial generation network caused by the single-channel feature extraction method. Second, a depth-based D-discriminator is designed to improve the discriminator capability and reduce the number of model parameters. Third, SeLU activation function was substituted for DCGAN activation function to overcome the problem that DCGAN activation function was not enough to fit grape leaf disease image data. Finally, an MFLoss function with a gradient penalty term is proposed to reduce the mode collapse during the training of generative adversarial networks. By comparing the visual indicators and evaluation indicators of the images generated by different models, and using the recognition network to verify the enhanced grape disease data, the results show that the method is effective in enhancing grape leaf disease data. Under the same experimental conditions, DMFGAN generates higher quality and more diverse images with fewer parameters than other generative adversarial networks. The mode breakdown times of generative adversarial networks in training process are reduced, which is more effective in practical application.

High-order brain network feature extraction and classification method of first-episode schizophrenia: an EEG study.

A multimodal persistent topological feature extraction and classification method is proposed to enhance the recognition accuracy of first-episode schizophrenia patients. This approach addresses the limitations of traditional higher-order brain network analyses that rely on single persistent features (e.g., persistent images). The study utilized resting-state EEG data from 198 subjects recruited at Huilongguan Hospital in Beijing, comprising 102 males and 96 females, with a mean age of 30 years and mean education of 14 years. Persistent topological features were extracted using adaptive thresholding during persistent homology (PH) filtrations. The distribution of these features was visualized through heatmaps and persistence entropies, while the generation process was elucidated using Betti curves and persistence landscapes. The classification performance of the multimodal persistent topological features was assessed using various machine learning classifiers. The classifier yielding the highest performance was selected for comparison with traditional brain network features derived from graph theory and single persistent topological features. The results revealed significant topological changes in first-episode schizophrenia patients throughout the persistent homology filtering compared to healthy subjects. The univariate feature selection algorithm achieved a classification accuracy of 94.6% with a combination of attributes meeting the criterion of AC ≥ 0.6. The proposed method demonstrates clinical significance for the early identification and diagnosis of first-episode schizophrenia patients, offering a new research perspective for constructing higher-order functional connectivity networks and extracting topological structure features.

High performance method for COPD features extraction using complex network.

Objectives. The paper proposes a novel methodology for the classification of Chronic Obstructive Pulmonary Disease (COPD) utilizing respiratory sound attributes.Methods. The approach involves segmenting respiratory sounds into individual breaths and conducting extensive studies on this dataset. Spectral Transforms, various Wavelet Transforms are applied to capture distinct signal features. Complex Network is also employed to extract characteristic elements, generating novel representations of spectrogram data based on graph factors, including entropy, density, and position. The normalized and enriched data is then used to develop COPD classifiers using six machine learning algorithms, fine-tuning with appropriate training details and hyperparameter tuning.Results. Our results demonstrate robust performance, with ROC curves consistently exhibiting an Area Under the Curve (AUC) > 96% across different time-frequency transformations. Notably, the Random Forest algorithm achieves an AUC of 99.67%, outperforming other algorithms. Moreover, the Wavelet Daubechies 2 (Db2) consistently approaches 98% accuracy, particularly noteworthy in conjunction with the Naive Bayes algorithm.Conclusion. This study diagnosis patients through spectrogram images extracted from lung sounds. The application of Inverse Transforms, Complex Network, and Optimized Classification Algorithms yielded results beyond expectations. This methodology provides a promising approach for accurate COPD diagnosis, leveraging Machine Learning techniques applied to respiratory sound analysis.