Multi-feature Integration Research Articles

Classification of coastal wetlands in the Liaohe Delta with multi-source and multi-feature integration.

Coastal wetlands, situated at the interface of land and sea, are the most productive ecosystems on the planet, boasting the richest biodiversity and the highest value in ecological services. The primary goal of this study is to analyze the spatial distribution of land use within the Liaohe Delta wetlands and to introduce a wetland classification system that integrates multiple sources and features, utilizing Google Earth Engine (GEE) for the Liaohe Delta wetlands. Firstly, the Sentinel 2 data were downloaded by median synthesis on GEE, after which random sample points were selected on QGIS, and secondly, the multi-source feature set was created by integrating data from Sentinel 1, Sentinel 2, and a Digital Elevation Model (DEM), utilizing the Recursive Feature Elimination (RFE) algorithm within a Random Forest (RF) framework to optimize feature selection. Various feature combination schemes were constructed to evaluate the impact of multi-source feature optimization on wetland classification performance. Ultimately, the Random Forest (RF) algorithm was employed to classify and extract wetlands in the study area. The findings indicate that the overall accuracy of the classification of the study area is 88.56%, and the Kappa coefficient is 0.8472. Compared with the results of using all the features for classification, the overall accuracy of the optimized features is improved by 3.83%, and the Kappa coefficient is improved by 0.0525. Compared with other machine learning methods, the overall accuracy and kappa of RF classification results improved by 1.06 to 22.77% and 0.0165 to 0.3248, respectively.

MFP-MFL: Leveraging Graph Attention and Multi-Feature Integration for Superior Multifunctional Bioactive Peptide Prediction

Bioactive peptides, composed of amino acid chains, are fundamental to a wide range of biological functions. Their inherent multifunctionality, however, complicates accurate classification and prediction. To address these challenges, we present MFP-MFL, an advanced multi-feature, multi-label learning framework that integrates Graph Attention Networks (GAT) with leading protein language models, including ESM-2, ProtT5, and RoBERTa. By employing an ensemble learning strategy, MFP-MFL effectively utilizes deep sequence features and complex functional dependencies, ensuring highly accurate and robust predictions of multifunctional peptides. Comparative experiments demonstrate that MFP-MFL achieves precision, coverage, and accuracy scores of 0.799, 0.821, and 0.786, respectively. Additionally, it attains an Absolute true of 0.737 while maintaining a low Absolute false of 0.086. A comprehensive case study involving 86,970 mutations further highlights the model’s ability to predict functional changes resulting from sequence variations. These results establish MFP-MFL as a powerful tool for the discovery and application of multifunctional peptides, offering significant potential to advance research and biomedical applications.

A robust framework for Alzheimer’s disease detection and staging: incorporating multi-feature integration, MRMR feature selection, and Random Forest classification

A robust framework for Alzheimer’s disease detection and staging: incorporating multi-feature integration, MRMR feature selection, and Random Forest classification

Vae-Clip: Unveiling Deception through Cross-Modal Models and Multi-Feature Integration in Multi-Modal Fake News Detection

With the development of internet technology, fake news has become a multi-modal collection. The current news detection methods cannot fully extract semantic information between modalities and ignore the rumor properties of fake news, making it difficult to achieve good results. To address the problem of the accurate identification of multi-modal fake news, we propose the Vae-Clip multi-modal fake news detection model. The model uses the Clip pre-trained model to jointly extract semantic features of image and text information using text information as the supervisory signal, solving the problem of semantic interaction across modalities. Moreover, considering the rumor attributes of fake news, we propose to fuse semantic features with rumor style features using multi-feature fusion to improve the generalization performance of the model. We use a variational autoencoder to extract rumor style features and combine semantic features and rumor features using an attention mechanism to detect fake news. Numerous experiments were conducted on four datasets primarily composed of Weibo and Twitter, and the results show that the proposed model can accurately identify fake news and is suitable for news detection in complex scenarios, with the highest accuracy reaching 96.3%.

Learning a Context-Aware Environmental Residual Correlation Filter via Deep Convolution Features for Visual Object Tracking

Visual tracking has become widespread in swarm robots for intelligent video surveillance, navigation, and autonomous vehicles due to the development of machine learning algorithms. Discriminative correlation filter (DCF)-based trackers have gained increasing attention owing to their efficiency. This study proposes “context-aware environmental residual correlation filter tracking via deep convolution features (CAERDCF)” to enhance the performance of the tracker under ambiguous environmental changes. The objective is to address the challenges posed by intensive environment variations that confound DCF-based trackers, resulting in undesirable tracking drift. We present a selective spatial regularizer in the DCF to suppress boundary effects and use the target’s context information to improve tracking performance. Specifically, a regularization term comprehends the environmental residual among video sequences, enhancing the filter’s discrimination and robustness in unpredictable tracking conditions. Additionally, we propose an efficient method for acquiring environmental data using the current observation without additional computation. A multi-feature integration method is also introduced to enhance the target’s presence by combining multiple metrics. We demonstrate the efficiency and feasibility of our proposed CAERDCF approach by comparing it with existing methods using the OTB2015, TempleColor128, UAV123, LASOT, and GOT10K benchmark datasets. Specifically, our method increased the precision score by 12.9% in OTB2015 and 16.1% in TempleColor128 compared to BACF.

Urban Perception Assessment from Street View Images Based on a Multifeature Integration Encompassing Human Visual Attention

Urban perception is a multifaceted process, spanning from vision to cognitive interpretation. Earlier studies on urban perception assessment have primarily concentrated on the analysis of graphic features of street view images such as color or semantic elements, neglecting the vital human sensory fixation features in cognitive processes. This study leveraged eye-tracking technology to accumulate human visual attention data during emotion scoring of street view images. Additionally, a deep learning network model was proposed to forecast human visual attention areas by assimilating environmental features such as image color, depth, and semantic elements, and subsequently amalgamating the aforementioned environmental features and visual attention to establish a perception prediction model, capable of predicting urban perception on a larger scale. Finally, the reliability and superiority of the urban perception prediction method were confirmed through ablation experiments and bias analysis. On the one hand, the method enhances the prediction accuracy of urban perception; on the other, it investigates the comprehensive influence of multiple features on human subjective emotions from the external environment perspective and individual perspective. This approach transcends the former limited reliance on single-image features, providing a novel and scientific approach for assessing urban perception.

基于多特征融合及背景建模的微表情Apex帧检测

基于多特征融合及背景建模的微表情Apex帧检测

Lung Sound Classification With Multi-Feature Integration Utilizing Lightweight CNN Model

Lung Sound Classification With Multi-Feature Integration Utilizing Lightweight CNN Model

Combined two-level guided wave structural health monitoring strategy using multifeature integration and machine learning: application to early-age grouted sleeves

Structural health monitoring of grouted sleeves is one of the assembly industry’s huge challenges. In this study, a combined two-level damage detection was introduced. It comprises defect classification (healthy, rebar eccentricity, and grout leakage) and severity evaluation for early-age grouted sleeves using guided waves. Multiple features (MF) from time-, frequency-, and time-frequency domains were extracted and defined according to the diverse defects and ages of grouted sleeves to represent complex damage characteristics. Moreover, the egret swarm algorithm optimization–extreme learning machine (ESAO-ELM) models were proposed to avoid the influence of subjective experience and judgment from experts. ESAO optimized the initial random parameters (input weights and hidden layer bias) of ELM. Then, two MF-ESAO-ELM models were trained for two-level damage detection on the experimental dataset. The performance of the proposed models was comprehensively evaluated using accuracy, recall, precision, and confusion matrix. MF-ESAO-ELM performs better than ELM and PSO-ELM in accuracy. In this strategy, the defect classification model works in the outer layer to distinguish the state and types of defects of grouted sleeves (healthy, eccentric, or leakage). In comparison, the inner layer starts predicting the severity only if the defect type is leakage. MF-ESAO-ELM offers advantages in terms of accuracy, strategy, and calculation time.

Deep learning-based multifeature integration robustly predicts central lymph node metastasis in papillary thyroid cancer

BackgroundFew highly accurate tests can diagnose central lymph node metastasis (CLNM) of papillary thyroid cancer (PTC). Genetic sequencing of tumor tissue has allowed the targeting of certain genetic variants for personalized cancer therapy development.MethodsThis study included 488 patients diagnosed with PTC by ultrasound-guided fine-needle aspiration biopsy, collected clinicopathological data, analyzed the correlation between CLNM and clinicopathological features using univariate analysis and binary logistic regression, and constructed prediction models.ResultsBinary logistic regression analysis showed that age, maximum diameter of thyroid nodules, capsular invasion, and BRAF V600E gene mutation were independent risk factors for CLNM, and statistically significant indicators were included to construct a nomogram prediction model, which had an area under the curve (AUC) of 0.778. A convolutional neural network (CNN) prediction model built with an artificial intelligence (AI) deep learning algorithm achieved AUCs of 0.89 in the training set and 0.78 in the test set, which indicated a high prediction efficacy for CLNM. In addition, the prediction models were validated in the subclinical metastasis and clinical metastasis groups with high sensitivity and specificity, suggesting the broad applicability of the models. Furthermore, CNN prediction models were constructed for patients with nodule diameters less than 1 cm. The AUCs in the training set and test set were 0.87 and 0.76, respectively, indicating high prediction efficacy.ConclusionsThe deep learning-based multifeature integration prediction model provides a reference for the clinical diagnosis and treatment of PTC.

Wetlands mapping in typical regions of South America with multi-source and multi-feature integration

Wetlands mapping in typical regions of South America with multi-source and multi-feature integration

FHENet: Lightweight Feature Hierarchical Exploration Network for Real-Time Rail Surface Defect Inspection in RGB-D Images

In recent years, computer vision systems have been increasingly applied to rail defect inspection. Rail defects should be identified quickly and accurately to ensure safe, stable, and fast train operations and thereby reduce the incidence of accidents and economic losses. As most existing methods focus on accuracy, they cannot be deployed on mobile devices with limited computational resources. To solve this problem, we propose a lightweight feature hierarchical exploration network (FHENet) for real-time rail surface defect inspection. First, boundary textures of rail defects are acquired based on the maximum function and maximum pooling in a novel boundary extraction module (BEM), which improves boundary prediction while avoiding heavy computations. Second, a novel cross-modality exploration module (CEM) complements prominent regions through basic operations to avoid complex inference while providing high detection performance. Third, a novel multifeature integration module (MIM) optimizes representative feature regions by using simple operations to avoid complex computations. Results from extensive experiments demonstrate the superiority of the proposed FHENet to 14 state-of-the-art methods. Regarding efficiency, FHENet outperforms the state-of-the-art methods with only 5.26 M parameters and a processing speed of 60.33 frames/s. The FHENet code and results are available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/hjklearn/Rail-Defect-Detection</uri> .

Detecting dynamic visual attention in augmented reality aided navigation environment based on a multi-feature integration fully convolutional network

ABSTRACT Visual attention detection, as an important concept for human visual behavior research, has been widely studied. However, previous studies seldom considered the feature integration mechanism to detect visual attention and rarely considered the differences due to different geographical scenes. In this paper, we use an augmented reality aided (AR-aided) navigation experimental dataset to study human visual behavior in a dynamic AR-aided environment. Then, we propose a multi-feature integration fully convolutional network (M-FCN) based on a self-adaptive environment weight (SEW) to integrate RGB-D, semantic, optical flow and spatial neighborhood features to detect human visual attention. The result shows that the M-FCN performs better than other state-of-the-art saliency models. In addition, the introduction of feature integration mechanism and the SEW can improve the accuracy and robustness of visual attention detection. Meanwhile, we find that RGB-D and semantic features perform best in different road routes and road types, but with the increase in road type complexity, the expressiveness of these two features weakens, and the expressiveness of optical flow and spatial neighborhood features increases. The research is helpful for AR-device navigation tool design and urban spatial planning.

Swin-MFINet: Swin transformer based multi-feature integration network for detection of pixel-level surface defects

Automatic surface defect detection is critical for manufacturing industries, such as steel, fabric, and marble industries. This study proposes a Swin transformer-based model called Multi-Feature Integration Network (Swin-MFINet) for pixel-level surface defect detection. The proposed model consists of an encoder, a Swin transformer-based decoder, and Multi-Feature Integration (MFI) modules. In the encoder module of the proposed model, a pre-trained Inception network is used to extract key features from small-size datasets. In the decoder section, global semantic features are obtained from the initial features by using the Swin-transformer block, which is the newest transformer technology of today. In addition, the convolution layer is used in the last step of the decoder, since transformers are limited in acquiring small spatial details such as edges, colors, and textures, which are important in detecting some small defects. In the last module called MFI, feature maps from different decoder stages are combined, and the channel squeeze-spatial excitation block is applied to reveal important features. Finally, a prediction map is obtained by applying a convolution layer and sigmoid activation function to the MFI module output, respectively. The performance of proposed model is analyzed over MT and MVTec datasets containing surface defect images. The proposed model obtained mIoU scores of 81.37%, and 77.07% respectively, for these two datasets These results outperform the state-of-the-art for the surface defect detection problem.

Feature Integration and Feature Augmentation for Predicting GPCR-Drug Interaction

Accurately predicting the interaction between G-protein-coupled receptors (GPCR) and drugs is of great significance for understanding protein functions and drug discovery and has become a hot spot in current research. To improve the accuracy of GPCR-drug interaction prediction, this paper proposes a new GPCR-Drug interaction prediction method based on multi-feature integration and feature augmentation from deep random forest: First, the sequence features of GPCR from amino acid composition and protein evolution are extracted respectively, and the characteristics of the drug molecule from the molecular fingerprint perspective are formulated; then, the extracted multiple features are combined to obtain the feature representation of the GPCR-Drug pair; finally, based on the proposed GPCR-Drug feature representation method, we use deep random forest to generate augmented features and construct cascaded predictions model. The cross-validation and independent test results on the standard data set verify the effectiveness and greater explainability of the proposed method.

Multi-feature integration and machine learning for guided wave structural health monitoring: Application to switch rail foot

Switch rails are weak but essential components of high-speed railway systems that have urgent nondestructive testing requirements owing to aging and the associated potential for fatigue damage accumulation. This study presents a multi-feature integration and automatic classification algorithm for switch rail damage using guided wave monitoring signals. A combination of piezoelectric transducers and magnetostrictive patch transducers is adopted to improve the monitoring performance and meet actual monitoring requirements. Furthermore, multiple features extracted from various signal processing domains—such as the time domain, power spectrum domain, and time–frequency domain—are proposed and defined according to the structure and characteristics of the switch rail and guided wave to represent the complex nature of the damage. A damage index is defined to eliminate the influence of various environmental and operational conditions, signal power, and other factors. In addition, a feature selection method based on binary particle swarm optimization with a new fitness function is proposed to select the most damage-sensitive features and eliminate irrelevant and redundant features to improve the classification performance. Moreover, considering that the results are easily influenced by experts’ subjective judgment and experience, the least-squares support-vector machine is used to construct automatic classification models to reduce the probability of artificial incorrect diagnosis and improve the generalization ability to unknown environments. Finally, three types of experiments on the foot of a switch rail are presented to evaluate the proposed method. The results indicate that the proposed method is capable of identifying damage in challenging cases and is superior to conventional methods.

Multi-Feature Tensor Neighborhood Preserving Embedding for 3D Facial Expression Recognition

To investigate an effective representation model for 3D facial expression recognition, this paper proposes a multi-feature tensor neighborhood preserving embedding (MFTNPE) method, which seeks various attribute features from raw textured shape scan models of 3D facial expression to construct a multi-feature tensor model. With MFTNPE method, we can project the model into a tensor subspace, explore the interactions and correlations among multimodal data and then extract discriminative low-dimensional tensor features for 3D facial expression recognition. In the study, we first introduce a tensor model based on multi-feature integration for 3D facial expression recognition. Via exploring the textural and geometric features of 3D facial expression data, an original multi-feature tensor model is constructed by stacking various attribute maps orderly. Second, we utilize the tensor completion approach as the scheme of data preprocessing to correct the original multi-feature tensor model. Due to the presence of imperfect data in the projected attribute maps, the tensor completion can predict the missing data in tensor by the trace norm of multi-feature tensor model along each mode. Third, we redefine a weighted matrix for use in the orthogonal-based tensor neighborhood preserving embedding algorithm. In the weighted matrix, the class information is used to guarantee the correct neighborhood relationships for multi-feature tensor samples. This effectively avoids the disturbances and confusions between similar samples while preserving spatial structure and inter-class information. Finally, we conduct extensive experiments on two 3D facial expression recognition datasets. The experimental results show that the proposed method has much better efficiency and performance compared with the state-of-the-art methods.

LigMate: A Multifeature Integration Algorithm for Ligand-Similarity-Based Virtual Screening.

Ligand-similarity-based virtual screening is one of the most applicable computer-aided drug design techniques. The current methodology relies heavily on several descriptors of molecular features, including atoms (zero-dimensional, 0D), the presence or absence of structural features (one-dimensional, 1D), topological descriptors (two-dimensional, 2D), geometry and volume (three-dimensional, 3D), or stereoelectronic and stereodynamic properties (four-dimensional, 4D). These descriptors have been frequently used in virtual screening; however, they are usually used independently without integration, which may hinder effective and precise virtual screening. In this study, we developed a multifeature integration algorithm named LigMate, which employs a Hungarian algorithm-based matching and a machine learning-based nonlinear combination of various descriptors, including the new relevant descriptors focusing on the maximum common substructures (maximum common substructure score, MCSS), the relative distance of atoms from the ligand mass center (intraligand distance score, ILDS), as well as the ring differences (ring score, RS). In the benchmark tests, LigMate achieved an overall enrichment factor of the first percent (EF1) of 36.14 and an area under the curve (AUC) value of 0.81 on the DUD-E data set, as well as an EF1 of 15.44 and an AUC of 0.69 on the maximum unbiased validation (MUV) data set, outperforming the control methods that are based on single descriptors. Thus, our study provides a new framework for multiple feature integration, which can benefit ligand-similarity-based virtual screening. LigMate is freely available for noncommercial users at http://cao.labshare.cn/ligmate/.

MDFI: Multi-CNN Decision Feature Integration for Diagnosis of Cervical Precancerous Lesions

Colposcopy is an essential medical examination that mainly through visual inspection for cervical epithelial tissue to preventing cervical cancer. However, screening by artificial vision has the problems of missed diagnosis, low efficiency, and diversity. This paper proposes a deep learning-based method using multi-CNN decision feature integration for classification and diagnosis of cervical lesions. The proposed method first uses the k-means algorithm to aggregate training data into specific classes in data preprocessing and then trained in cross-validation to improve the generalization ability of the model. Subsequently, two kinds of CNN are separately fine-tuned based on the transfer learning, and then XGBoost algorithm is used to integrate the different CNN decision results for optimizing the final prediction. Two integration ways for decision features (named inner-model integration and outer-model integration) are proposed to embody multi-feature integration from the data level and the model structural level. Simultaneously, two specific integration strategies (inner-to-outer and outer-to-inner) are designed for as the final output based on the combination of the two ways. Experimental results show that the K-means data preprocessing method can improve the training of neural networks, and the proposed multi-decision feature fusion strategy can better obtain the results of computer-aided diagnosis that meet the needs of clinical diagnosis.

Independent component analysis with reference multifeature integration for visual object tracking via adaptive update

Tracking methods based on correlation filter have been showing great advantages and huge potential. However, it will lead to tracking drift when the target is disturbed, such as occlusion, illumination variation, deformation, and others. In the pursuit of tracking accuracy and robustness, a feature integration model and an adaptive update method for robust tracking are proposed. First, the fine-tuned convolutional neural networks medium is employed to obtain the deep features. The deep features are integrated with traditional manual features by combining with the independent component analysis with reference method to obtain more discriminative features. Second, in the model update phase, an adaptive updating strategy based on the center shift Euclidean distance of image patch is proposed to reduce the unnecessary calculation in model training so as to speed up the tracking speed. Finally, the tracker proposed is evaluated on online tracking benchmark (OTB-2015) and visual object tracking benchmark (VOT-2016). The experimental results show that the method that integrates deep features with traditional manual features can distinguish background and target better. Thus the proposed VOT algorithm performs better robustness and accuracy against state-of-the-art methods when dealing with challenging environments.