Final Feature Research Articles

Two-Stream Modality-Based Deep Learning Approach for Enhanced Two-Person Human Interaction Recognition in Videos

Human interaction recognition (HIR) between two people in videos is a critical field in computer vision and pattern recognition, aimed at identifying and understanding human interaction and actions for applications such as healthcare, surveillance, and human–computer interaction. Despite its significance, video-based HIR faces challenges in achieving satisfactory performance due to the complexity of human actions, variations in motion, different viewpoints, and environmental factors. In the study, we proposed a two-stream deep learning-based HIR system to address these challenges and improve the accuracy and reliability of HIR systems. In the process, two streams extract hierarchical features based on the skeleton and RGB information, respectively. In the first stream, we utilised YOLOv8-Pose for human pose extraction, then extracted features with three stacked LSM modules and enhanced them with a dense layer that is considered the final feature of the first stream. In the second stream, we utilised SAM on the input videos, and after filtering the Segment Anything Model (SAM) feature, we employed integrated LSTM and GRU to extract the long-range dependency feature and then enhanced them with a dense layer that was considered the final feature for the second stream module. Here, SAM was utilised for segmented mesh generation, and ImageNet was used for feature extraction from images or meshes, focusing on extracting relevant features from sequential image data. Moreover, we newly created a custom filter function to enhance computational efficiency and eliminate irrelevant keypoints and mesh components from the dataset. We concatenated the two stream features and produced the final feature that fed into the classification module. The extensive experiment with the two benchmark datasets of the proposed model achieved 96.56% and 96.16% accuracy, respectively. The high-performance accuracy of the proposed model proved its superiority.

Predicting atrial fibrillation within 7 years follow-up using machine learning models

Abstract Background The prevalence of atrial fibrillation (AF), the most common type of cardiac arrhythmia, has increased globally. AF is also the leading cardiac factor for several cardiovascular and cerebrovascular events. Early prediction and treatment of AF prevents major cardiovascular and cerebrovascular events. Purpose Our objective is to predict AF risk within 7-years follow-up using only twelve basic factors and applying machine learning (ML) models. Methods Data from the German epidemiological trial on ankle brachial index (getABI) were utilized in this work. GetABI includes 6,457 patients with mean age of 72.53 years. 3,985 individuals were assessed for AF of which 393 patients suffered from AF at 7-years follow-up. The feature selection was initially done manually, ending up in 45 features. The 10 best features were extracted from this dataset according to the SHAP (SHapley Additive exPlanations) values. The final features were body mass index, sensitive CRP, cholesterol, LDL-cholesterol, troponin I, NT-pro-BNP, glomerular filtration rate, ratio of triglycerides and HDL-cholesterol, gamma-GT, heart rate, including age and sex as major factors. The handling of missing values was achieved by SimpleImputer, estimating the mean values. XGBoost and Random Forest predicted AF. Logistic Regression was also used as a baseline model. The data were split into training and test set and ML models were applied for 100 iterative runs, extracting results with mean values. Results XGBoost was the most accurate model, predicting the AF with 71.19 % mean accuracy, 66.37 % mean sensitivity and 75.61 % mean specificity. Figure 1 depicts the performance of all models. Additionally, Receiver Operating Characteristic Curve (ROC) and Area Under Curve (AUC) for each model are presented in Figure 2. XGBoost also outperformed all the others models, achieving the highest mean AUC value, equal to 70.99 %. Contrariwise, logistic regression had the lowest overall performance. Conclusion ML models, specifically XGBoost, achieved accurate AF prediction in 3,985 individuals utilizing only twelve clinical-routine data.Evaluation results of each used model.ROC curve and AUC value of each model.

Estimating Winter Canola Aboveground Biomass from Hyperspectral Images Using Narrowband Spectra-Texture Features and Machine Learning

Aboveground biomass (AGB) is a critical indicator for monitoring the crop growth status and predicting yields. UAV remote sensing technology offers an efficient and non-destructive method for collecting crop information in small-scale agricultural fields. High-resolution hyperspectral images provide abundant spectral-textural information, but whether they can enhance the accuracy of crop biomass estimations remains subject to further investigation. This study evaluates the predictability of winter canola AGB by integrating the narrowband spectra and texture features from UAV hyperspectral images. Specifically, narrowband spectra and vegetation indices were extracted from the hyperspectral images. The Gray Level Co-occurrence Matrix (GLCM) method was employed to compute texture indices. Correlation analysis and autocorrelation analysis were utilized to determine the final spectral feature scheme, texture feature scheme, and spectral-texture feature scheme. Subsequently, machine learning algorithms were applied to develop estimation models for winter canola biomass. The results indicate: (1) For spectra features, narrow-bands at 450~510 nm, 680~738 nm, 910~940 nm wavelength, as well as vegetation indices containing red-edge narrow-bands, showed outstanding performance with correlation coefficients ranging from 0.49 to 0.65; For texture features, narrow-band texture parameters CON, DIS, ENT, ASM, and vegetation index texture parameter COR demonstrated significant performance, with correlation coefficients between 0.65 and 0.72; (2) The Adaboost model using the spectra-texture feature scheme exhibited the best performance in estimating winter canola biomass (R2 = 0.91; RMSE = 1710.79 kg/ha; NRMSE = 19.88%); (3) The combined use of narrowband spectra and texture feature significantly improved the estimation accuracy of winter canola biomass. Compared to the spectra feature scheme, the model’s R2 increased by 11.2%, RMSE decreased by 29%, and NRMSE reduced by 17%. These findings provide a reference for studies on UAV hyperspectral remote sensing monitoring of crop growth status.

Construction of a prediction model for induction of labor based on a small sample of clinical indicator data

Because of the diversity and complexity of clinical indicators, it is difficult to establish a comprehensive and reliable prediction model for induction of labor (IOL) outcomes with existing methods. This study aims to analyze the clinical indicators related to IOL and to develop and evaluate a prediction model based on a small-sample of data. The study population consisted of a total of 90 pregnant women who underwent IOL between February 2023 and January 2024 at the Shanghai First Maternity and Infant Healthcare Hospital, and a total of 52 clinical indicators were recorded. Maximal information coefficient (MIC) was used to select features for clinical indicators to reduce the risk of overfitting caused by high-dimensional features. Then, based on the features selected by MIC, the support vector machine (SVM) model based on small samples was compared and analyzed with the fully connected neural network (FCNN) model based on large samples in deep learning, and the receiver operating characteristic (ROC) curve was given. By calculating the MIC score, the final feature dimension was reduced from 55 to 15, and the area under curve (AUC) of the SVM model was improved from 0.872 before feature selection to 0.923. Model comparison results showed that SVM had better prediction performance than FCNN. This study demonstrates that SVM successfully predicted IOL outcomes, and the MIC feature selection effectively improves the model's generalization ability, making the prediction results more stable. This study provides a reliable method for predicting the outcome of induced labor with potential clinical applications.

An efficient state-of-health estimation method for lithium-ion batteries based on feature-importance ranking strategy and hybrid kernel extreme learning machine algorithm

The safe and reliable operation of battery systems depends critically on accurately and dependably estimating the state of health (SOH) of lithium-ion batteries (LIBs). However, accurate prediction of SOH still needs improvement due to the complex battery aging mechanism. This paper introduces a hybrid kernel extremum learning machine (HKELM) for estimating battery SOH. To improve estimation accuracy, we enhance the standard dung beetle optimization algorithm (DBO) with a new initialized population, adaptive weights method, and improved population diversification. We then use the enhanced IDBO algorithm to optimize the parameters of HKELM. This study examines two distinct anode types of LIBs from NASA and Oxford datasets. Fifty significant features are extracted from charging voltage, current, temperature, and incremental capacity (IC) curves. The importance indices of these features are then computed using statistical analyses, including Pearson's correlation coefficient and Spearman's rank correlation coefficient, followed by optimal ranking. The optimal number of final features is determined by comparing various combinations of high-level features, thus reducing model complexity and improving estimation accuracy. This paper proposes the IDBO-HKELM algorithm for SOH estimation. Compared to other methods, the algorithm shows superior estimation performance and anti-interference capability. Both B0007 and Cell8 estimate SOH with MAE < 0.15, RMSE <0.2, and R2 > 99.9 %. Experimental results demonstrate the robustness of the proposed method, achieving accurate and noise-immune SOH estimation.

Enhancing nursing care through technology and standardized nursing language: The TEC-MED multilingual platform.

This study describes the design, integration, and semantic interoperability process of a minimum data set using standardized nursing language in the caring module of the TEC-MED care platform. The caring module was developed in three phases (2020-2022): platform concept, functional design and construction, and testing and evaluation. Phases involved collaboration among academics, information technology developers, and social/healthcare professionals. Nursing taxonomies (NANDA-I, NOC, NIC) were integrated to support the nursing process. The platform was piloted in six Mediterranean countries. The final platform features an assessment module with eight dimensions for data collection on older adults and their caregivers. A clinical decision support system links assessment data with nursing diagnoses, outcomes, and interventions. The platform is available in six languages (English, Spanish, French, Italian, Greek, and Arabic). Usability testing identified the need for improved Arabic language support. The TEC-MED platform is a pioneering tool using standardized nursing language to improve care for older adults in the Mediterranean. The platform's multilingualism promotes accessibility. Limitations include offline use and mobile app functionality. Pilot testing is underway to evaluate effectiveness and facilitate cross-cultural validation of nursing taxonomies. The TEC-MED platform offers standardized nursing care for older adults across the Mediterranean, promoting consistent communication and evidence-based practice. This approach has the potential to improve care quality and accessibility for a vulnerable population.

LDAGM: prediction lncRNA-disease asociations by graph convolutional auto-encoder and multilayer perceptron based on multi-view heterogeneous networks

BackgroundLong non-coding RNAs (lncRNAs) can prevent, diagnose, and treat a variety of complex human diseases, and it is crucial to establish a method to efficiently predict lncRNA-disease associations.ResultsIn this paper, we propose a prediction method for the lncRNA-disease association relationship, named LDAGM, which is based on the Graph Convolutional Autoencoder and Multilayer Perceptron model. The method first extracts the functional similarity and Gaussian interaction profile kernel similarity of lncRNAs and miRNAs, as well as the semantic similarity and Gaussian interaction profile kernel similarity of diseases. It then constructs six homogeneous networks and deeply fuses them using a deep topology feature extraction method. The fused networks facilitate feature complementation and deep mining of the original association relationships, capturing the deep connections between nodes. Next, by combining the obtained deep topological features with the similarity network of lncRNA, disease, and miRNA interactions, we construct a multi-view heterogeneous network model. The Graph Convolutional Autoencoder is employed for nonlinear feature extraction. Finally, the extracted nonlinear features are combined with the deep topological features of the multi-view heterogeneous network to obtain the final feature representation of the lncRNA-disease pair. Prediction of the lncRNA-disease association relationship is performed using the Multilayer Perceptron model. To enhance the performance and stability of the Multilayer Perceptron model, we introduce a hidden layer called the aggregation layer in the Multilayer Perceptron model. Through a gate mechanism, it controls the flow of information between each hidden layer in the Multilayer Perceptron model, aiming to achieve optimal feature extraction from each hidden layer.ConclusionsParameter analysis, ablation studies, and comparison experiments verified the effectiveness of this method, and case studies verified the accuracy of this method in predicting lncRNA-disease association relationships.

Improving Text Classification in Agricultural Expert Systems with a Bidirectional Encoder Recurrent Convolutional Neural Network

With the rapid development of internet and AI technologies, Agricultural Expert Systems (AESs) have become crucial for delivering technical support and decision-making in agricultural management. However, traditional natural language processing methods often struggle with specialized terminology and context, and they lack the adaptability to handle complex text classifications. The diversity and evolving nature of agricultural texts make deep semantic understanding and integration of contextual knowledge especially challenging. To tackle these challenges, this paper introduces a Bidirectional Encoder Recurrent Convolutional Neural Network (AES-BERCNN) tailored for short-text classification in agricultural expert systems. We designed an Agricultural Text Encoder (ATE) with a six-layer transformer architecture to capture both preceding and following word information. A recursive convolutional neural network based on Gated Recurrent Units (GRUs) was also developed to merge contextual information and learn complex semantic features, which are then combined with the ATE output and refined through max-pooling to form the final feature representation. The AES-BERCNN model was tested on a self-constructed agricultural dataset, achieving an accuracy of 99.63% in text classification. Its generalization ability was further verified on the Tsinghua News dataset. Compared to other models such as TextCNN, DPCNN, BiLSTM, and BERT-based models, the AES-BERCNN shows clear advantages in agricultural text classification. This work provides precise and timely technical support for intelligent agricultural expert systems.

Met4DX: A Unified and Versatile Data Processing Tool for Multidimensional Untargeted Metabolomics Data.

Liquid chromatography-mass spectrometry (LC-MS) is a powerful tool in untargeted metabolomics, enabling the high-sensitivity and high-specificity characterization of metabolites. The integration of ion mobility (IM) with LC-MS, known as LC-IM-MS, enhances the analytical depth, facilitating more comprehensive metabolite profiling. However, the complexity of data generated by these technologies presents significant challenges in data processing. Addressing these challenges, we developed Met4DX, a unified and versatile software tool for processing both 3D and 4D untargeted metabolomics data. Met4DX incorporates a new MS1-oriented peak detection approach coupled with our bottom-up assembly algorithm, enabling highly sensitive and comprehensive peak detection in untargeted metabolomics data. Additionally, Met4DX employs a uniform quantification strategy to enhance the precision of peak integration across different samples. The software provides a user-friendly interface that simplifies data processing with default parameter sets, consolidating peak detection, alignment, quantification, and other procedures into a single streamlined workflow. Together, Met4DX offers a comprehensive solution for multidimensional metabolomics data processing, transforming raw data from diverse MS instruments into a final feature table containing quantification and identification results. We postulate Met4DX facilitates metabolite discovery in biological samples by deciphering the complex untargeted metabolomics data. Met4DX is freely available on the Internet (https://met4dx.zhulab.cn/).

TAG-fusion: Two-stage attention guided multi-modal fusion network for semantic segmentation

In the current research, leveraging auxiliary modalities, such as depth information or point cloud information, to improve RGB semantic segmentation has shown significant potential. However, existing methods mainly use convolutional modules for aggregating features from auxiliary modalities, thereby lacking sufficient exploitation of long-range dependencies. Moreover, fusion strategies are typically limited to singular approaches. In this paper, we propose a transformer-based multimodal fusion framework to better utilize auxiliary modalities for enhancing semantic segmentation results. Specifically, we employ a dual-stream architecture for extracting features from RGB and auxiliary modalities, respectively. We incorporate both early fusion and deep feature fusion techniques. At each layer, we introduce mixed attention mechanisms to leverage features from other modalities, guiding and enhancing the current modality's features before propagating them to the subsequent stage of feature extraction. After the extraction of features from different modalities, we employ an enhanced cross-attention mechanism for feature interaction, followed by channel fusion to obtain the final semantic features. Subsequently, we provide separate supervision to the network on the RGB stream, auxiliary stream, and fusion stream to facilitate the learning of representations for different modalities. The experimental results demonstrate that our framework exhibits superior performance across diverse modalities. Specifically, our approach achieves state-of-the-art results on the NYU Depth V2, SUN-RGBD, DELIVER and MFNet datasets.

Multiple myeloma segmentation net (MMNet): an encoder-decoder-based deep multiscale feature fusion model for multiple myeloma segmentation in magnetic resonance imaging.

Patients with multiple myeloma (MM), a malignant disease involving bone marrow plasma cells, shows significant susceptibility to bone degradation, impairing normal hematopoietic function. The accurate and effective segmentation of MM lesion areas is crucial for the early detection and diagnosis of myeloma. However, the presence of complex shape variations, boundary ambiguities, and multiscale lesion areas, ranging from punctate lesions to extensive bone damage, presents a formidable challenge in achieving precise segmentation. This study thus aimed to develop a more accurate and robust segmentation method for MM lesions by extracting rich multiscale features. In this paper, we propose a novel, multiscale feature fusion encoding-decoding model architecture specifically designed for MM segmentation. In the encoding stage, our proposed multiscale feature extraction module, dilated dense connected net (DCNet), is employed to systematically extract multiscale features, thereby augmenting the model's sensing field. In the decoding stage, we propose the CBAM-atrous spatial pyramid pooling (CASPP) module to enhance the extraction of multiscale features, enabling the model to dynamically prioritize both channel and spatial information. Subsequently, these features are concatenated with the final output feature map to optimize segmentation outcomes. At the feature fusion bottleneck layer, we incorporate the dynamic feature fusion (DyCat) module into the skip connection to dynamically adjust feature extraction parameters and fusion processes. We assessed the efficacy of our approach using a proprietary dataset of MM, yielding notable advancements. Our dataset comprised 753 magnetic resonance imaging (MRI) two-dimensional (2D) slice images of the spinal regions from 45 patients with MM, along with their corresponding ground truth labels. These images were primarily obtained from three sequences: T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), and short tau inversion recovery (STIR). Using image augmentation techniques, we expanded the dataset to 3,000 images, which were employed for both model training and prediction. Among these, 2,400 images were allocated for training purposes, while 600 images were reserved for validation and testing. Our method showed increase in the intersection over union (IoU) and Dice coefficients by 7.9 and 6.7 percentage points, respectively, as compared to the baseline model. Furthermore, we performed comparisons with alternative image segmentation methodologies, which confirmed the sophistication and efficacy of our proposed model. Our proposed multiple myeloma segmentation net (MMNet), can effectively extract multiscale features from images and enhance the correlation between channel and spatial information. Furthermore, a systematic evaluation of the proposed network architecture was conducted on a self-constructed, limited dataset. This endeavor holds promise for offering valuable insights into the development of algorithms for future clinical applications.

Enhancing brain tumor classification through ensemble attention mechanism.

Brain tumors pose a serious threat to public health, impacting thousands of individuals directly or indirectly worldwide. Timely and accurate detection of these tumors is crucial for effective treatment and enhancing the quality of patients' lives. The widely used brain imaging technique is magnetic resonance imaging, the precise identification of brain tumors in MRI images is challenging due to the diverse anatomical structures. This paper introduces an innovative approach known as the ensemble attention mechanism to address this challenge. Initially, the approach uses two networks to extract intermediate- and final-level feature maps from MobileNetV3 and EfficientNetB7. This assists in gathering the relevant feature maps from the different models at different levels. Then, the technique incorporates a co-attention mechanism into the intermediate and final feature map levels on both networks and ensembles them. This directs attention to certain regions to extract global-level features at different levels. Ensemble of attentive feature maps enabling the precise detection of various feature patterns within brain tumor images at both model, local, and global levels. This leads to an improvement in the classification process. The proposed system was evaluated on the Figshare dataset and achieved an accuracy of 98.94%, and 98.48% for the BraTS 2019 dataset which is superior to other methods. Thus, it is robust and suitable for brain tumor detection in healthcare systems.

Human–object interaction detection algorithm based on graph structure and improved cascade pyramid network

Aiming at the problem of insufficient use of human–object interaction (HOI) information and spatial location information in images, we propose a human–object​ interaction detection network based on graph structure and improved cascade pyramid. This network is composed of three branches, namely, graph branch, human–object branch and human pose branch. In graph branch, we propose a Graph-based Interactive Feature Generation Algorithm (GIFGA) to address the inadequate utilization of interaction information. GIFGA constructs an initial dense graph model by taking humans and objects as nodes and their interaction relationships as edges. Then, by traversing each node, the graph model is updated to generate the final interaction features. In human pose branch, we propose an Improved Cascade Pyramid Network (ICPN) to tackle the underutilization of spatial location information. ICPN extracts human pose features and maps both the object bounding boxes and extracted human pose maps onto the global feature map to capture the most discriminative interaction-related region features within the global context. Finally, the features from the three branches are fed into a Multi-Layer Perceptron (MLP) for fusion and then classified for recognition. Experimental results demonstrate that our network achieves mAP of 54.93% and 28.69% on the V-COCO and HICO-DET datasets, respectively.

Construction of a machine learning-based prediction model for unfavorable discharge outcomes in patients with ischemic stroke

BackgroundIschemic stroke is a common and serious disease with economic and healthcare burdens. Predicting the unfavorable discharge outcome of patients is essential for formulating appropriate treatment strategies and providing personalized care. Therefore, this study aims to establish and validate a prediction model based on machine learning methods to accurately predict the discharge outcome of ischemic stroke patients, providing valuable information for clinical decision making. MethodsThe derivation data consisted of 964 patients from Guangdong Provincial People's Hospital and was used for training and internal validation. A favourable discharge outcome was defined as a National Institutes of Health Stroke Scale score of ≤1 or a decrease of ≥8 points compared to the admission score. A predictive model was created based on 88 medical characteristics gathered during the patient's initial admission, using nine machine learning algorithms. The model's predictive performance was compared using various evaluation metrics. The final model's feature importance was ranked and explained using the Shapley additive explanation method. FindingsThe random forest model demonstrated the greatest discriminative ability among the nine machine learning models. We created an interpretable random forest model by ranking and reducing the features based on their importance, which included eight features. In internal validations, the final model accurately predicted the discharge outcomes of ischemic stroke with AUC values of 0.903 and has been translated into a convenient tool to facilitate its utility in clinical settings. ConclusionsOur explainable ML model was not only successfully developed to accurately predict discharge outcomes in patients with ischemic stroke and it mitigated the concern of the “black-box” issue with an undirect interpretation of the ML technique.

A lightweight color and geometry feature extraction and fusion module for end-to-end 6D pose estimation

Although advancements in red–green–blue-depth (RGB-D)-based six degree-of-freedom (6D) pose estimation methods, severe occlusion remains challenging. Addressing this issue, we propose a novel feature fusion module that can efficiently leverage the color and geometry information in RGB-D images. Unlike prior fusion methods, our method employs a two-stage fusion process. Initially, we extract color features from RGB images and integrate them into a point cloud. Subsequently, an anisotropic separable set abstraction network-like network is utilized to process the fused point cloud, extracting both local and global features, which are then combined to generate the final fusion features. Furthermore, we introduce a lightweight color feature extraction network to reduce model complexity. Extensive experiments conducted on the LineMOD, Occlusion LineMOD, and YCB-Video datasets conclusively demonstrate that our method significantly enhances prediction accuracy, reduces training time, and exhibits robustness to occlusion. Further experiments show that our model is significantly smaller than the latest popular 6D pose estimation models, which indicates that our model is easier to deploy on mobile platforms.

Radiomics machine learning algorithm facilitates detection of small pancreatic neuroendocrine tumors on CT

PurposeThe purpose of this study was to develop a radiomics-based algorithm to identify small pancreatic neuroendocrine tumors (PanNETs) on CT and evaluate its robustness across manual and automated segmentations, exploring the feasibility of automated screening. Materials and methodsPatients with pathologically confirmed T1 stage PanNETs and healthy controls undergoing dual-phase CT imaging were retrospectively identified. Manual segmentation of pancreas and tumors was performed, then automated pancreatic segmentations were generated using a pretrained neural network. A total of 1223 radiomics features were independently extracted from both segmentation volumes, in the arterial and venous phases separately. Ten final features were selected to train classifiers to identify PanNETs and controls. The cohort was divided into training and testing sets, and performance of classifiers was assessed using area under the receiver operator characteristic curve (AUC), specificity and sensitivity, and compared against two radiologists blinded to the diagnoses. ResultsA total of 135 patients with 142 PanNETs, and 135 healthy controls were included. There were 168 women and 102 men, with a mean age of 55.4 ± 11.6 (standard deviation) years (range: 20–85 years). Median PanNET size was 1.3 cm (Q1, 1.0; Q3, 1.5; range: 0.5–1.9). The arterial phase LightGBM model achieved the best performance in the test set, with 90 % sensitivity (95 % confidence interval [CI]: 80–98), 76 % specificity (95 % CI: 62–88) and an AUC of 0.87 (95 % CI: 0.79–0.94). Using features from the automated segmentations, this model achieved an AUC of 0.86 (95 % CI: 0.79–0.93). In comparison, the two radiologists achieved a mean 50 % sensitivity and 100 % specificity using arterial phase CT images. ConclusionRadiomics features identify small PanNETs, with stable performance when extracted using automated segmentations. These models demonstrate high sensitivity, complementing the high specificity of radiologists, and could serve as opportunistic screeners.

Deep hybrid approach with sequential feature extraction and classification for robust malware detection

Malware attacks have escalated significantly with an increase in the number of internet users and connected devices. With the increasingly different types of malware released by hackers, designing new and competitive techniques to detect advanced malware is essential. In the proposed research, we have developed a multi-level feature extraction technique using deep learning architectures and a classification model to classify malware families. The essential features from the malware images are extracted using the Gated Recurrent Unit in the first step, which are further fed to a Convolutional Neural Network model for extracting the final feature vector. The multi-level feature selection is followed by classification into various malware families using Cost-sensitive Boot Strapped Weighted Random Forest (CSBW-RF). The proposed approach gave promising results of 99.58 % accuracy in distinguishing the 25 different malware families on the Mallmg dataset. This hybrid model gave significantly better performance scores for classifying visually similar malware families. The generalizability of the proposed model is benchmarked with the popular Microsoft Big 2015 dataset and has achieved comparatively higher performance scores than many existing models. This benchmarking demonstrates the robustness and scalability of our approach. The use of cost-sensitive learning and bootstrapping techniques also contributed to the model’s ability to generalize well to new and unseen data. These enhancements ensure that our model can be effectively applied in diverse real-world scenarios, maintaining high performance across different environments and malware types. This research can contribute to detecting malware attacks and can be integrated in threat monitoring systems. The successful application of this hybrid model indicates its potential for deployment in real-world cybersecurity environments, providing a strong defense against evolving malware threats.

A detection method of oil content for maize kernels based on CARS feature selection and deep sparse autoencoder feature extraction

To achieve accurate, rapid, and non-destructive oil content determination in maize, a neural fitting model that combines feature selection and feature extraction is proposed. Competitive adaptive re-weighted sampling (CARS) is used to choose features, while the deep sparse autoencoder (DSAE) network is utilized to extract features. The 160 spectral data from the near-infrared spectra public datasets of maize served as experimental samples. Several preprocessing approaches were tested, and the first-order derivatives fared the best. To capture the various degrees of abstract features in spectral data, SSAE networks with two or three hidden layers are developed. The number of nodes in the network's hidden layer (30, 50, 70, 100, 200, 300, respectively) and the network's sparsity parameter (0.001, 0.004, 0.007, 0.01, 0.04, 0.07, 0.1, 0.2, …, 1) are tuned to generate partial least squares regression (PLSR) models for testing the feature learning effect. The highest performance comes from a three-layer network with 200 hidden layer nodes and a sparsity parameter of 0.04. This network extracts three levels of features from the preprocessed spectral data: F1, F2, and F3. Full_cars, F1_cars, F2_cars, and F3_cars are obtained using the CARS algorithm for variable selection on the preprocessed spectral data, F1, F2, and F3, respectively. They are then integrated into a final feature set to build a neural-fitting network (FNN). After training and testing, the test set has a correlation coefficient of 0.964205 and an mean square error (MSE) of 0.00636809. Comparing this model to support vector machine regression (SVR), PLSR, and gaussian process regression (GPR), the findings demonstrate that the model described in this study outperforms the others in terms of fitting accuracy and generalization performance. To summarize, this paper introduces a new regression analysis method based on near-infrared spectra.

A Hierarchical Matrix Factorization-Based Method for Intelligent Industrial Fault Diagnosis.

Data-driven fault diagnosis, identifying abnormality causes using collected industrial data, is one of the challenging tasks for intelligent industry safety management. It is worth noting that practical industrial data are usually related to a mixture of several physical attributes, such as the operating environment, product quality and working conditions. However, the traditional models may not be sufficient to leverage the coherent information for diagnostic performance enhancement, due to their shallow architecture. This paper presents a hierarchical matrix factorization (HMF) that relies on a succession of matrix factoring to find an efficient representation of industrial data for fault diagnosis. Specifically, HMF consecutively decomposes data into several hierarchies. The intermediate hierarchies play the role of analysis operators which automatically learn implicit characteristics of industrial data; the final hierarchy outputs high-level and discriminative features. Furthermore, HMF is also extended in a nonlinear manner by introducing activation functions, referred as NHMF, to deal with nonlinearities in practical industrial processes. The applications of HMF and NHMF to fault diagnosis are evaluated by the multiple-phase flow process. The experimental results show that our models achieve competitive performance against the considered shallow and deep models, consuming less computing time than deep models.

Swin transformer-based fork architecture for automated breast tumor classification

Breast cancer constitutes a prevalent and escalating health concern globally. Additionally, the significance of early diagnosis for effective treatment cannot be overstated. Ultrasound imaging (UI) emerges as a cost-effective means for early diagnosis. However, the interpretation of user interface images can be challenging, leading to the development of computer-aided diagnostic systems. In this article, a network architecture named Swin Transformer-based Fork Network (SW-ForkNet) is developed for breast tumor classification. Utilizing the DenseNet121 backbone, SW-ForkNet amalgamates spatial, semantic, and long-context features. The inclusion of the spatial Squeeze-and-Excitation (sSE) block is instrumental for spatial details, while the Swin Transformer structure is employed for capturing global long-context features. Moreover, to optimize the acquisition of these features, a connection is established in the middle layer of the DenseNet121 architecture, feeding both sSE and Swin Transformers. In the network architecture’s output, three distinct feature groups are vectorized, combined, and processed to obtain the final feature map. Finally, a prediction is generated by applying the softmax classifier to this concluding feature map. Experimental evaluations conducted on three datasets (BUSI, GDPH, and SYSUCC) demonstrate the superior performance of SW-ForkNet, showcasing high accuracy (Acc) and F1-Scores (F1S) compared to existing methods and state-of-the-art models. Notable achievements include 93.12 % Acc and 92.27 % F1s for BUSI, 96.15 % Acc and 96.04 % F1S for GDPH, and 94.88 % Acc and 94.03 % F1S for SYSUCC. Consequently, the proposed SW-ForkNet model seems to present itself as a novel and effective structure in breast tumor classification.