RESUMEN

Resting-state functional MRI (rs-fMRI) is increasingly employed in multi-site research to analyze neurological disorders, but there exists cross-site/domain data heterogeneity caused by site effects such as differences in scanners/protocols. Existing domain adaptation methods that reduce fMRI heterogeneity generally require accessing source domain data, which is challenging due to privacy concerns and/or data storage burdens. To this end, we propose a source-free collaborative domain adaptation (SCDA) framework using only a pretrained source model and unlabeled target data. Specifically, a multi-perspective feature enrichment method (MFE) is developed to dynamically exploit target fMRIs from multiple views. To facilitate efficient source-to-target knowledge transfer without accessing source data, we initialize MFE using parameters of a pretrained source model. We also introduce an unsupervised pretraining strategy using 3,806 unlabeled fMRIs from three large-scale auxiliary databases. Experimental results on three public and one private datasets show the efficacy of our method in cross-scanner and cross-study prediction.

RESUMEN

We aimed to assess the diagnostic performance of Cardiac Magnetic Resonance (CMR) strain parameters in ACM patients to evaluate their diagnostic role. We systematically searched MEDLINE, EMBASE, Scopus, and Web of Science. Of the 146 records, 16 were included. All Right Ventricle (RV) global strains were significantly reduced in ACM patients compared to controls (Standardized Mean Difference (SMD)[95 % Confidence Interval (CI)]: Longitudinal 1.31[0.79,1.83]; Circumferential 0.88[0.34,1.42]; Radial -1.14[-1.78,-0.51]). Similarly, all Left Ventricle (LV) global strains were significantly impaired in ACM compared to healthy controls (SDM [95 %CI]: Longitudinal 0.88[0.48,12.28], Circumferential 0.97[0.72,1.22], Radial -1.24[-1.49,-1.00]). Regarding regional RV strains, longitudinal and circumferential strains were significantly reduced in basal and mid-wall regions, while they were comparable to controls in the apical regions. The RV radial strain was reduced only within the basal region in the ACM group compared to controls. ACM patients exhibited significant impairment of regional LV strains in all regions-basal, mid-wall, and apical-compared to control subjects. Ultimately, despite the limitations of CMR-FT in terms of reproducibility, it is superior to qualitative assessment in detecting wall motion abnormalities. Thus, integrating CMR-FT with ACM diagnostic criteria seems to enhance its diagnostic yield.

RESUMEN

Primary endometrial squamous cell carcinoma (PESCC) is a rare malignant tumor. To investigate the clinical and pathological features of PESCC, two cases of PESCC in Fujian Maternal and Child Health Hospital were retrospectively studied and the literatures were reviewed. Both of the two cases were menopausal women aged 57-62 years, clinically presenting with "vaginal discharge". Case 1 was a non-keratinising squamous cell carcinoma with high-risk HPV infection. Tumor infiltrated in deep myometrium with multifocal intravascular thrombus and macro metastases to one pelvic lymph node (1/15) and abdominal aortic lymph node (1/1). Lung metastasis occurred 36 months after the surgery. After surgical resection and without postoperative supplemental therapy, the patient remained tumor-free for 110 months to date. Case 2 had a history of breast cancer for 5 years and long-term intake of aromatase inhibitor drugs without HPV infection. It was a keratinized squamous cell carcinoma. Tumor also infiltrated in deep myometrium with multifocal intravascular thrombus and one pelvic lymph node metastasis (1/18), However, no metastasis was seen elsewhere. To date, the patient survived for 16 months without tumor after surgery. Both of the two cases expressed squamous epithelial markers P40, P63, and CK5/6, but neither expressed PAX8 or PR. Case 1 had diffuse expression of P16, wild-type P53, and ER-negative. Case 2 had negative P16, mutant P53, and focal positive ER. PESCC is often associated with HPV infection and low estrogen levels. However, studies in the literatures have found that P16 expression is not always consistent with HPV infection, indicating that PESCC cannot be easily classified as HPV-associated or non-dependent like cervical cancer. There are two main patterns of P16 and P53 expression, P16-positive/P53 wild-type and P16-negative/P53-mutant, but no positive expression of both has been seen so far. It is worth noting that we reported the second case of PESCC with a history of breast cancer, where the patient had been taking the oral aromatase inhibitor drug (exemestane) for a long period of time to reduce the estrogen level, indicating the low estrogen level may be also a key factor in the pathogenesis of PESCC.

RESUMEN

A novel method for the rapid identification of hemp fibers is proposed in this paper, utilizing terahertz time-domain spectroscopy (THz-TDS) combined with the LargeVis (LV) dimensionality reduction technique. This approach takes advantage of the strengths of THz-TDS while enhancing classification accuracy through LV. To verify the efficacy of this method, terahertz absorption spectral data from three types of hemp fibers were processed. The THz absorption spectra were initially preprocessed using Hanning filtering. Following this, the filtered data underwent dimensionality reduction through three distinct methods: linear Principal Component Analysis (PCA), nonlinear t-Distributed Stochastic Neighbor Embedding (t-SNE), and the LV method. This sequence of steps resulted in a two-dimensional feature data matrix derived from the THz source spectral data. The resultant feature data matrices were then input into both K-Nearest Neighbors (KNN) and Decision Tree (DT) classifiers for analysis. The classification accuracies of six models were evaluated, revealing that the LV-KNN model achieved a 86.67% accuracy rate for the three hemp fiber types. Impressively, the LV-DT model achieved a perfect 100.00% accuracy rate for the same fibers. The LV-DT model, when integrated with THz spectroscopy technology, offers a quick and precise method for identifying various types of hemp fibers. This development introduces an innovative optical measurement scheme for the characterization of textile materials.

RESUMEN

BACKGROUND: Accurately modeling respiratory motion in medical images is crucial for various applications, including radiation therapy planning. However, existing registration methods often struggle to extract local features effectively, limiting their performance. OBJECTIVE: In this paper, we aimed to propose a new framework called CvTMorph, which utilizes a Convolutional vision Transformer (CvT) and Convolutional Neural Networks (CNN) to improve local feature extraction. METHODS: CvTMorph integrates CvT and CNN to construct a hybrid model that combines the strengths of both approaches. Additionally, scaling and square layers are added to enhance the registration performance. We have evaluated the performance of CvTMorph on the 4D-Lung and DIR-Lab datasets and compared it with state-of-the-art methods to demonstrate its effectiveness. RESULTS: The experimental results have demonstrated CvTMorph to outperform the existing methods in terms of accuracy and robustness for respiratory motion modeling in 4D images. The incorporation of the convolutional vision transformer has significantly improved the registration performance and enhanced the representation of local structures. CONCLUSION: CvTMorph offers a promising solution for accurately modeling respiratory motion in 4D medical images. The hybrid model, leveraging convolutional vision transformer and convolutional neural networks, has proven effective in extracting local features and improving registration performance. The results have highlighted the potential of CvTMorph for various applications, such as radiation therapy planning, and provided a basis for further research in this field.

RESUMEN

INTRODUCTION: Amomum fruit, also known as Sharen, serves as both a functional food and a traditional Chinese medicine with significant pharmacological activities. However, there are three botanical origins of Amomum fruit: Amomum villosum Lour. (AVL), Amomum villosum Lour. var. xanthioides T. L. (AVX), and Amomum longiligulare T. L. Wu (ALW). OBJECTIVE: Conducting a comprehensive chemical composition analysis of Amomum fruit from three botanical origins aims to identify potential differences in metabolic characteristics. METHODS: To annotate the metabolic characteristic ions of multi-origin Amomum fruit, we employed metabolomic techniques, including ultra-high-performance liquid chromatography (LC) coupled with linear ion trap-Orbitrap-tandem mass spectrometry (MS) and gas chromatography-MS, in conjunction with feature-based molecular networking technology. Additionally, chemometrics was utilized to examine the correlations between the various botanical origins. RESULTS: A total of 201 non-volatile and 151 volatile metabolites were annotated, and most of the proanthocyanidins and flavonoids were identified by feature-based molecular networking. Additionally, 61 non-volatile and 45 volatile feature ions were screened out for classification. Principal component analysis, orthogonal projection to latent structures discrimination analysis, and heat map analysis were employed to clearly distinguish the metabolite profiles of Amomum fruit from different origins. Hierarchical clustering analysis indicated that proanthocyanidins C1 and C2, as well as proanthocyanins oligomers, show significant differential expression between AVX and AVL, which could be the new quality markers for the classification. CONCLUSION: Classification of the botanical origin of Amomum fruit based on LC-MS characteristic ions proved to be more advantageous. This study introduces new strategies and technical support for the quality control of Amomum fruit and facilitates the identification of unknown compounds for future research.

RESUMEN

Alzheimer's Disease (AD) causes slow death in brain cells due to shrinkage of brain cells which is more prevalent in older people. In most cases, the symptoms of AD are mistaken as age-related stresses. The most widely utilized method to detect AD is Magnetic Resonance Imaging (MRI). Along with Artificial Intelligence (AI) techniques, the efficacy of identifying diseases related to the brain has become easier. But, the identical phenotype makes it challenging to identify the disease from the neuro-images. Hence, a deep learning method to detect AD at the beginning stage is suggested in this work. The newly implemented "Enhanced Residual Attention with Bi-directional Long Short-Term Memory (Bi-LSTM) (ERABi-LNet)" is used in the detection phase to identify the AD from the MRI images. This model is used for enhancing the performance of the Alzheimer's detection in scale of 2-5%, minimizing the error rates, increasing the balance of the model, so that the multi-class problems are supported. At first, MRI images are given to "Residual Attention Network (RAN)", which is specially developed with three convolutional layers, namely atrous, dilated and Depth-Wise Separable (DWS), to obtain the relevant attributes. The most appropriate attributes are determined by these layers, and subjected to target-based fusion. Then the fused attributes are fed into the "Attention-based Bi-LSTM". The final outcome is obtained from this unit. The detection efficiency based on median is 26.37% and accuracy is 97.367% obtained by tuning the parameters in the ERABi-LNet with the help of Modified Search and Rescue Operations (MCDMR-SRO). The obtained results are compared with ROA-ERABi-LNet, EOO-ERABi-LNet, GTBO-ERABi-LNet and SRO-ERABi-LNet respectively. The ERABi_LNet thus provides enhanced accuracy and other performance metrics compared to such deep learning models. The proposed method has the better sensitivity, specificity, F1-Score and False Positive Rate compared with all the above mentioned competing models with values such as 97.49%.97.84%,97.74% and 2.616 respective;y. This ensures that the model has better learning capabilities and provides lesser false positives with balanced prediction.

Asunto(s)

RESUMEN

OBJECTIVE: Optimized deep brain stimulation (DBS) is fast becoming a therapy of choice for the treatment of Parkinson's disease (PD). However, the post-operative optimization (aimed at maximizing patient clinical benefits and minimizing adverse effects) of all possible DBS parameter settings using the standard-of-care clinical protocol requires numerous clinical visits, which substantially increases the time to optimization per patient (TPP), patient cost burden and limit the number of patients who can undergo DBS treatment. The TPP is further elongated in electrodes with stimulation directionality or in diseases with latency in clinical feedback. In this work, we proposed a deep learning and fMRI-based pipeline for DBS optimization that can potentially reduce the TPP from ~1 year to a few hours during a single clinical visit. METHODS AND PROCEDURES: We developed an unsupervised autoencoder (AE)-based model to extract meaningful features from 122 previously acquired blood oxygenated level dependent (BOLD) fMRI datasets from 39 a priori clinically optimized PD patients undergoing DBS therapy. The extracted features are then fed into multilayer perceptron (MLP)-based parameter classification and prediction models for rapid DBS parameter optimization. RESULTS: The AE-extracted features of optimal and non-optimal DBS were disentangled. The AE-MLP classification model yielded accuracy, precision, recall, F1 score, and combined AUC of 0.96 ± 0.04, 0.95 ± 0.07, 0.92 ± 0.07, 0.93 ± 0.06, and 0.98 respectively. Accuracies of 0.79 ± 0.04, 0.85 ± 0.04, 0.82 ± 0.05, 0.83 ± 0.05, and 0.70 ± 0.07 were obtained in the prediction of voltage, frequency, and x-y-z contact locations, respectively. CONCLUSION: The proposed AE-MLP models yielded promising results for fMRI-based DBS parameter classification and prediction, potentially facilitating rapid semi-automated DBS parameter optimization. Clinical and Translational Impact Statement-A deep learning-based pipeline for semi-automated DBS parameter optimization is presented, with the potential to significantly decrease the optimization duration per patient and patients' financial burden while increasing patient throughput.

Asunto(s)

RESUMEN

BACKGROUND: Immune checkpoint inhibitor (ICI) has been widely used in the treatment of advanced cancers, but predicting their efficacy remains challenging. Traditional biomarkers are numerous but exhibit heterogeneity within populations. For comprehensively utilizing the ICI-related biomarkers, we aim to conduct multidimensional feature selection and deep learning model construction. METHODS: We used statistical and machine learning methods to map features of different levels to next-generation sequencing gene expression. We integrated genes from different sources into the feature input of a deep learning model, by means of self-attention mechanism. RESULTS: We performed feature selection at the single-cell sequencing level, PD-L1 (CD274) analysis level, tumor mutational burden (TMB)/mismatch repair (MMR) level, and somatic copy number alteration (SCNA) level, obtaining 96 feature genes. Based on the pan-cancer dataset, we trained a multi-task deep learning model. We tested the model in the bladder urothelial carcinoma testing set 1 (AUC = 0.62, n = 298), bladder urothelial carcinoma testing set 2 (AUC = 0.66, n = 89), non-small cell lung cancer testing set (AUC = 0.85, n = 27), and skin cutaneous melanoma testing set (AUC = 0.71, n = 27). CONCLUSION: Our study demonstrates the potential of the deep learning model for integrating multidimensional features in predicting the outcome of ICI. Our study also provides a potential methodological case for medical scenarios requiring the integration of multiple levels of features.

RESUMEN

Apoptotic proteins play a crucial role in the apoptosis process, ensuring a balance between cell proliferation and death. Thus, further elucidating the regulatory mechanisms of apoptosis will enhance our understanding of their functions. However, the development of computational methods to accurately identify positive and negative regulation of apoptosis remains a significant challenge. This work proposes a machine learning model based on multi-feature fusion to effectively identify the roles of positive and negative regulation of apoptosis. Initially, we constructed a reliable benchmark dataset containing 200 positive regulation of apoptosis and 241 negative regulation of apoptosis proteins. Subsequently, we developed a classifier that combines the support vector machine (SVM) with pseudo composition of k-spaced amino acid pairs (PseCKSAAP), composition transition distribution (CTD), dipeptide deviation from expected mean (DDE), and PSSM-composition to identify these proteins. Analysis of variance (ANOVA) was employed to select optimized features that could yield the maximum prediction performance. Evaluating the proposed model on independent data revealed and achieved an accuracy of 0.781 with an AUROC of 0.837, demonstrating our model's potent capabilities.

RESUMEN

Auditory spatial attention detection (ASAD) aims to decipher the spatial locus of a listener's selective auditory attention from electroencephalogram (EEG) signals. However, current models may exhibit deficiencies in EEG feature extraction, leading to overfitting on small datasets or a decline in EEG discriminability. Furthermore, they often neglect topological relationships between EEG channels and, consequently, brain connectivities. Although graph-based EEG modeling has been employed in ASAD, effectively incorporating both local and global connectivities remains a great challenge. To address these limitations, we propose a new ASAD model. First, time-frequency feature fusion provides a more precise and discriminative EEG representation. Second, EEG segments are treated as graphs, and the graph convolution and global attention mechanism are leveraged to capture local and global brain connections, respectively. A series of experiments are conducted in a leave-trials-out cross-validation manner. On the MAD-EEG and KUL datasets, the accuracies of the proposed model are more than 9% and 3% higher than those of the corresponding state-of-the-art models, respectively, while the accuracy of the proposed model on the SNHL dataset is roughly comparable to that of the state-of-the-art model. EEG time-frequency feature fusion proves to be indispensable in the proposed model. EEG electrodes over the frontal cortex are most important for ASAD tasks, followed by those over the temporal lobe. Additionally, the proposed model performs well even on small datasets. This study contributes to a deeper understanding of the neural encoding related to human hearing and attention, with potential applications in neuro-steered hearing devices.

RESUMEN

Interpreting intramuscular electromyography (iEMG) signals for diagnosing and quantifying the severity of lumbosacral radiculopathy is challenging due to the subjective evaluation of signals. To address this limitation, a clinical decision support system (CDSS) was developed for the diagnosis and quantification of the severity of lumbosacral radiculopathy based on intramuscular electromyography (iEMG) signals. The CDSS uses the EMG interference pattern method (QEMG IP) to directly extract features from the iEMG signal and provide a quantitative expression of injury severity for each muscle and overall radiculopathy severity. From 126 time and frequency domain features, a set of five features, including the crest factor, mean absolute value, peak frequency, zero crossing count, and intensity, were selected. These features were derived from raw iEMG signals, empirical mode decomposition, and discrete wavelet transform, and the wrapper method was utilized to determine the most significant features. The CDSS was trained and tested on a dataset of 75 patients, achieving an accuracy of 93.3%, sensitivity of 93.3%, and specificity of 96.6%. The system shows promise in assisting physicians in diagnosing lumbosacral radiculopathy with high accuracy and consistency using iEMG data. The CDSS's objective and standardized diagnostic process, along with its potential to reduce the time and effort required by physicians to interpret EMG signals, makes it a potentially valuable tool for clinicians in the diagnosis and management of lumbosacral radiculopathy. Future work should focus on validating the system's performance in diverse clinical settings and patient populations.

RESUMEN

Schizophrenia is a mental disorder characterized by neurophysiological dysfunctions that result in disturbances in thinking, perception, and behavior. Early identification of schizophrenia can help prevent potential complications and facilitate effective treatment and management of the condition. This paper proposes a computer aided diagnosis system for the early detection of schizophrenia using 19-channel Electroencephalography (EEG) signals from 28 subjects, leveraging statistical moments of Mel-frequency Cepstral Coefficients (MFCC) and ensemble learning. Initially, the EEG signals are passed through a high-pass filter to mitigate noise and remove extraneous data. The feature extraction technique is then employed to extract MFC coefficients from the filtered EEG signals. The dimensionality of these coefficients is reduced by computing their statistical moments, which include the mean, standard deviation, skewness, kurtosis, and energy. Subsequently, the Support Vector Machine based Recursive Feature Elimination (SVM-RFE) is applied to identify pertinent features from the statistical moments of the MFC coefficients. These SVM-RFE-based selected features serve as input for three base classifiers: Support Vector Machine, k-Nearest Neighbors, and Logistic Regression. Additionally, an ensemble learning approach, which combines the predictions of the three classifiers through majority voting, is introduced to enhance schizophrenia detection performance and generalize the results of the proposed approach. The study's findings demonstrate that the ensemble model, combined with SVM-RFE-based selected statistical moments of MFCC, achieves encouraging detection performance, highlighting the potential of machine learning techniques in advancing the diagnostic process of schizophrenia.

RESUMEN

ADHD is a prevalent childhood behavioral problem. Early ADHD identification is essential towards addressing the disorder and minimizing its negative impact on school, career, relationships, as well as general well-being. The present ADHD diagnosis relies primarily on an emotional assessment which can be readily influenced by clinical expertise and lacks a basis of objective markers. In this paper, an innovative IoT based ADHD detection is proposed using an EEG signal. To the input EEG signal, the min-max normalization technique is processed. Features are extracted as the subsequent step, where improved fuzzy feature, in which the entropy is estimated to increase the effectiveness of recognizing the vector along with, fractal dimension, wavelet transform and non-linear features are extracted. Also, proposes the new hybrid PUDMO algorithm to select the optimal features from the extracted feature set. Subsequently, the selected features are fed to the proposed hybrid detection system that including IDBN and LSTM classifier to detect whether it is ADHD or not. Further, the weights of both classifiers are tuned optimally as per the hybrid PUDMO algorithm to enhance the detection performance. The PUDMO achieved an accuracy of 0.9649 in the best statistical metric, compared to the SLO's 0.8266, SOA's 0.8201, SMA's 0.8060, BRO's 0.8563, DE's 0.8083, POA's 0.8537, and DMOA's 0.8647, respectively. Thus, the assessments and detection help the clinicians to take appropriate decision.

RESUMEN

Kidney diseases pose a significant global health challenge, requiring precise diagnostic tools to improve patient outcomes. This study addresses this need by investigating three main categories of renal diseases: kidney stones, cysts, and tumors. Utilizing a comprehensive dataset of 12,446 CT whole abdomen and urogram images, this study developed an advanced AI-driven diagnostic system specifically tailored for kidney disease classification. The innovative approach of this study combines the strengths of traditional convolutional neural network architecture (AlexNet) with modern advancements in ConvNeXt architectures. By integrating AlexNet's robust feature extraction capabilities with ConvNeXt's advanced attention mechanisms, the paper achieved an exceptional classification accuracy of 99.85%. A key advancement in this study's methodology lies in the strategic amalgamation of features from both networks. This paper concatenated hierarchical spatial information and incorporated self-attention mechanisms to enhance classification performance. Furthermore, the study introduced a custom optimization technique inspired by the Adam optimizer, which dynamically adjusts the step size based on gradient norms. This tailored optimizer facilitated faster convergence and more effective weight updates, imporving model performance. The model of this study demonstrated outstanding performance across various metrics, with an average precision of 99.89%, recall of 99.95%, and specificity of 99.83%. These results highlight the efficacy of the hybrid architecture and optimization strategy in accurately diagnosing kidney diseases. Additionally, the methodology of this paper emphasizes interpretability and explainability, which are crucial for the clinical deployment of deep learning models.

Asunto(s)

RESUMEN

Anxiety among pregnant women can significantly impact their overall well-being. However, the development of data-driven HCI interventions for this demographic is often hindered by data scarcity and collection challenges. In this study, we leverage the Empatica E4 wristband to gather physiological data from pregnant women in both resting and relaxed states. Additionally, we collect subjective reports on their anxiety levels. We integrate features from signals including Blood Volume Pulse (BVP), Skin Temperature (SKT), and Inter-Beat Interval (IBI). Employing a Support Vector Machine (SVM) algorithm, we construct a model capable of evaluating anxiety levels in pregnant women. Our model attains an emotion recognition accuracy of 69.3%, marking achievements in HCI technology tailored for this specific user group. Furthermore, we introduce conceptual ideas for biofeedback on maternal emotions and its interactive mechanism, shedding light on improved monitoring and timely intervention strategies to enhance the emotional health of pregnant women.

Asunto(s)

RESUMEN

Combining item feature information helps extract comprehensive sequential patterns, thereby improving the accuracy of sequential recommendations. However, existing methods usually combine features of each item using a vanilla attention mechanism. We argue that such a combination ignores the interactions between features and does not model integrated feature representations. In this study, we propose a novel Feature Interaction Dual Self-attention network (FIDS) model for sequential recommendation, which utilizes dual self-attention to capture both feature interactions and sequential transition patterns. Specifically, we first model the feature interactions for each item to form meaningful higher-order feature representations using a multi-head attention mechanism. Then, we adopt two independent self-attention networks to capture the transition patterns in both the item sequence and the integrated feature sequence, respectively. Moreover, we stack multiple self-attention blocks and add residual connections at each block for all self-attention networks. Finally, we combine the feature-wise and item-wise sequential patterns into a fully connected layer for the next item recommendation. We conduct experiments on two real-world datasets, and our experimental results show that the proposed FIDS method outperforms state-of-the-art recommendation models.

RESUMEN

As a common disease, cardiovascular and cerebrovascular diseases pose a great harm threat to human wellness. Even using advanced and comprehensive treatment methods, there is still a high mortality rate. Arteriosclerosis, as an important factor reflecting the severity of cardiovascular and cerebrovascular diseases, is imperative to detect the arteriosclerotic retinopathy. However, the detection of arteriosclerosis retinopathy requires expensive and time-consuming manual evaluation, while end-to-end deep learning detection methods also need interpretable design to high light task-related features. Considering the importance of automatic arteriosclerotic retinopathy grading, we propose a segmentation and classification interaction network (SCINet). We propose a segmentation and classification interaction architecture for grading arteriosclerotic retinopathy. After IterNet is used to segment retinal vessel from original fundus images, the backbone feature extractor roughly extracts features from the segmented and original fundus arteriosclerosis images and further enhances them through the vessel aware module. The last classifier module generates fundus arteriosclerosis grading results. Specifically, the vessel aware module is designed to highlight the important areal vessel features segmented from original images by attention mechanism, thereby achieving information interaction. The attention mechanism selectively learns the vessel features of segmentation region information under the proposed interactive architecture, which leads to reweighting the extracted features and enhances significant feature information. Extensive experiments have confirmed the effect of our model. SCINet has the best performance on the task of arteriosclerotic retinopathy grading. Additionally, the CNN method is scalable to similar tasks by incorporating segmented images as auxiliary information.

RESUMEN

Aiming at the problem that the feature extraction ability of forehead single-channel electroencephalography (EEG) signals is insufficient, which leads to decreased fatigue detection accuracy, a fatigue feature extraction and classification algorithm based on supervised contrastive learning is proposed. Firstly, the raw signals are filtered by empirical modal decomposition to improve the signal-to-noise ratio. Secondly, considering the limitation of the one-dimensional signal in information expression, overlapping sampling is used to transform the signal into a two-dimensional structure, and simultaneously express the short-term and long-term changes of the signal. The feature extraction network is constructed by depthwise separable convolution to accelerate model operation. Finally, the model is globally optimized by combining the supervised contrastive loss and the mean square error loss. Experiments show that the average accuracy of the algorithm for classifying three fatigue states can reach 75.80%, which is greatly improved compared with other advanced algorithms, and the accuracy and feasibility of fatigue detection by single-channel EEG signals are significantly improved. The results provide strong support for the application of single-channel EEG signals, and also provide a new idea for fatigue detection research.

Asunto(s)

RESUMEN

With the development of automated malware toolkits, cybersecurity faces evolving threats. Although visualization-based malware analysis has proven to be an effective method, existing approaches struggle with challenging malware samples due to alterations in the texture features of binary images during the visualization preprocessing stage, resulting in poor performance. Furthermore, to enhance classification accuracy, existing methods sacrifice prediction time by designing deeper neural network architectures. This paper proposes PAFE, a lightweight and visualization-based rapid malware classification method. It addresses the issue of texture feature variations in preprocessing through pixel-filling techniques and applies data augmentation to overcome the challenges of class imbalance in small sample datasets. PAFE combines multi-scale feature fusion and a channel attention mechanism, enhancing feature expression through modular design. Extensive experimental results demonstrate that PAFE outperforms the current state-of-the-art methods in both efficiency and effectiveness for malware variant classification, achieving an accuracy rate of 99.25 % with a prediction time of 10.04 ms.