Feature Recognition Research Articles

AGWO-PSO-VMD-TEFCG-AlexNet bearing fault diagnosis method under strong noise

To solve the difficult problem of early bearing fault diagnosis under strong- background-noise, an AGWO-PSO-VMD-TEFCG-Alexnet bearing fault diagnosis method based on Augmented Grey Wolf Optimizer (AGWO), Particle Swarm Optimization (PSO), Variational Mode Decomposition (VMD) and TEFCG-AlexNet convolutional neural network deep learning algorithm is proposed. The comprehensive evaluation index of VMD is designed by using the envelope entropy (EE), and the optimal modulus and penalty factor of VMD are found adaptively by using the AGWO-PSO. Using the feature index and time–frequency characteristics of screened IMF, the time–frequency enhancement feature map is established. The bearing fault diagnosis method is constructed by TEFCG-AlexNet. The early bearing fault data set with strong-background-noise is tested and the decomposition effect is compared with the same type VMD algorithm,the results show that the proposed method has the best diagnosis effect. It’s proved that this method has better characteristics of fault feature recognition and diagnosis.

TF-BAPred: A Universal Bioactive Peptide Predictor Integrating Multiple Feature Representations

Bioactive peptides play essential roles in various biological processes and hold significant therapeutic potential. However, predicting the functions of these peptides is challenging due to their diversity and complexity. Here, we develop TF-BAPred, a framework for universal peptide prediction incorporating multiple feature representations. TF-BAPred feeds original peptide sequences into three parallel modules: a novel feature proposed in this study called FVG extracts the global features of each peptide sequence; an automatic feature recognition module based on a temporal convolutional network extracts the temporal features; and a module integrates multiple widely used features such as AAC, DPC, BPF, RSM, and CKSAAGP. In particular, FVG constructs a fixed-size vector graph to represent the global pattern by capturing the topological structure between amino acids. We evaluated the performance of TF-BAPred and other peptide predictors on different types of peptides, including anticancer peptides, antimicrobial peptides, and cell-penetrating peptides. The benchmarking tests demonstrate that TF-BAPred displays strong generalization and robustness in predicting various types of peptide sequences, highlighting its potential for applications in biomedical engineering.

Method for rail surface defect detection based on neural network architecture search

Abstract This study addresses the inherent limitations of implementing neural network architecture search algorithms for rail surface defect detection, including low search efficiency and the oversight of edge features on the rail surface. A sophisticated multi-level neural network architecture search framework is proposed that integrates and emphasizes rail surface edge features. The framework utilizes the Z-Score normalization method to quantify the edge concern of rail surface defect samples, combined with an Edge-Loss function to enhance edge feature recognition capabilities. Furthermore, acknowledging the sensitivity of defect features to spatial resolution changes, a multi-level neural network architecture search space is meticulously designed. In the cell-level search space, a method combining partial channel sampling with operation pruning is employed to enhance model search efficiency and regularization. In the network-level search space, optimal paths for resolution change are established, allowing for the screening and aggregation of defect features at various levels to facilitate the adaptive extraction of multi-scale edge defect features. Experimental outcomes indicate that this method significantly reduces computational resource usage by approximately 75% and increases mIOU by 2.6% relative to traditional architecture search methods. Moreover, it demonstrates robust capability in accurately recognizing defective edges on rail surfaces, thereby substantiating the method’s effectiveness.

Joint Classification of Hyperspectral and LiDAR Data via Multiprobability Decision Fusion Method

With the development of sensor technology, the sources of remotely sensed image data for the same region are becoming increasingly diverse. Unlike single-source remote sensing image data, multisource remote sensing image data can provide complementary information for the same feature, promoting its recognition. The effective utilization of remote sensing image data from various sources can enhance the extraction of image features and improve the accuracy of feature recognition. Hyperspectral remote sensing (HSI) data and light detection and ranging (LiDAR) data can provide complementary information from different perspectives and are frequently combined in feature identification tasks. However, the process of joint use suffers from data redundancy, low classification accuracy and high time complexity. To address the aforementioned issues and improve feature recognition in classification tasks, this paper introduces a multiprobability decision fusion (PRDRMF) method for the combined classification of HSI and LiDAR data. First, the original HSI data and LiDAR data are downscaled via the principal component–relative total variation (PRTV) method to remove redundant information. In the multifeature extraction module, the local texture features and spatial features of the image are extracted to consider the local texture and spatial structure of the image data. This is achieved by utilizing the local binary pattern (LBP) and extended multiattribute profile (EMAP) for the two types of data after dimensionality reduction. The four extracted features are subsequently input into the corresponding kernel–extreme learning machine (KELM), which has a simple structure and good classification performance, to obtain four classification probability matrices (CPMs). Finally, the four CPMs are fused via a multiprobability decision fusion method to obtain the optimal classification results. Comparison experiments on four classical HSI and LiDAR datasets demonstrate that the method proposed in this paper achieves high classification performance while reducing the overall time complexity of the method.

Kernelized support vector machines for modified Gabor features facial recognition

The Gabor-filter approach has been extensively used in the recognition of patterns most especially in the extraction of features during image processing. Gabor filters usefulness explored in face recognition is traceable to its computational properties and biological relevance. Despite all the distinct characteristics of Gabor filters, it suffers from high feature dimensionality. This has led majorly to computational problems in any Gabor-based facial recognition model. The paper presents modified Gabor features for face recognition by introducing a meta-heuristics optimization algorithm using the Ant Colony Optimization Algorithm (ACO) to obtain relevant and optimal features from huge Gabor features. Kernels of Support Vector Machines (SVM); Linear SVM Kernel (LSVMK), Polynomial SVM Kernel (PSVMK), Sigmoid SVM (SSVMK) and Gaussian SVM Kernel (GSVMK) were employed for the classification of face images to either matched or mismatched. Two datasets were used for the evaluation of the system, they include: the Olivetti Research Laboratory (ORL) database and the acquired Africa face image database (ABFI). All the Kernelized SVMs produced an effective output in terms of training time, classification accuracy and error rate. Experimental results showed the lowest training time of 7.3195s was obtained in GSVMK for ABFI face image dataset, non-optimized Gabor feature gave the best accuracy of 90.88% in PSVMK of image size 75x75 for ABFI dataset, the optimized Gabor features recorded the best accuracy of 96.93% in GSVMK of image size 125x125 for ORL image dataset, the lowest error rate of 08.18% was obtained in LSVMK with image size of 150x150 for ORL image dataset

Machine learning approach in canine mammary tumour classification using rapid evaporative ionization mass spectrometry.

Rapid evaporative ionization mass spectrometry (REIMS) coupled with a monopolar handpiece used for surgical resection and combined with chemometrics has been previously explored by our research group (Mangraviti et al. in Int J Mol Sci 23(18):10562, 2022) to identify several mammary gland pathologies. Here, the increased sample size allowed the construction of three statistical models to distinguish between benign and malignant canine mammary tumours (CMTs), facilitating a more in-depth investigation of changes in cellular metabolic phenotype during neoplastic transformation and biological behaviour. The results demonstrate that REIMS is effective in identifying neoplastic tissues with an accuracy of 97%, with differences in MS spectra characterized by the relative abundance of phospholipids compared to triglycerides more commonly identified in normal mammary glands. The increased rate of phospholipid synthesis represents an informative feature for tumour recognition, with phosphatidylcholine and phosphatidylethanolamine, the two major phospholipid species identified here together with sphingolipids, playing a crucial role in carcinogenesis. REIMS technology allowed the classification of different histotypes of benign CMTs with an accuracy score of 95%, distinguishing them from normal glands based on the increase in sphingolipids, glycolipids, phospholipids, and arachidonic acid, demonstrating the close association between cancer and inflammation. Finally, dysregulation of fatty acid metabolism with increased signalling for saturated, mono- and polyunsaturated fatty acids characterized the metabolic phenotype of neoplastic cells and their malignant transformation, supporting the increased formation of new organelles for cell division. Further investigations on a more significant number of tumour histotypes will allow for the creation of a more extensive database and lay the basis for how understanding metabolic alterations in the tumour microenvironment can improve surgical precision.

Advanced Artificial Intelligence Drivers and IoT Network Systems for Data Collection and Network Transmission in the Industry 5.0 Era

The primary bases of Industry 5.0, the Internet of Things (IoT), artificial intelligence (AI), and big data (BD) may serve as a basis for applying the concepts of smart manufacturing, innovative goods and services, and predictive maintenance (PDM) into practice. Assessing the remaining useful life of components using failure data and state monitoring information constitutes the AI techniques for predictive maintenance (PDM), which are critical in Industry 5.0. However, it is sometimes challenging to identify the annotation of component usage, creating an open problem for obtaining accurately labeled information and understanding it. This problem needs to be rectified if Industry 5.0 progress is proceeded with. In order to solve the PDM job, this study presents a new data-driven decision system (DDS) based on AI that overcomes the earlier issue. It does by concentrating on an actual industrial use scenario that involves modern processing and monitoring machines. Specifically, the most fundamental components of the recommended DDS include cloud-based storage, data interpretation, predictive modeling, recognition of features using Principal Component Analysis (PCA), and data collecting. An efficient prediction model called the unique moth flame search-tuned light gradient boosting machine (MFS-LGBM) technique is presented in this work. By enabling the ongoing gathering of identified samples and offering a data analysis environment to assist the maintainer/operator, the suggested approach resolves the PDM task. The research findings showed that when compared to the previous approaches, the suggested approach accomplishes the greatest conceivable balance between comprehension, computational effort, and forecasting accuracy in terms of quality estimation. Based on the suggested methodology, the performance is examined in terms of RMSE (600.10), MAE (390.60), [Formula: see text] (0.790) and MAPE (25.70) measures. By incorporating it into the cloud structure, the suggested technique minimizes maintenance expenses and enhances production efficiency by improving machining processes, assisting maintainers, and delivering current operating risk alerts.

An integrated deep learning model for intelligent recognition of long-distance natural gas pipeline features

Pipeline feature recognition is crucial for the reliability and safety of long-distance natural gas pipelines. Utilizing manual or machine learning methods to recognize pipeline features is not only inefficient, but also has problems such as high misjudgment rate and poor robustness. To overcome the above problems, this paper proposes a pipeline feature recognition method based on Multi-scale Attention Convolutional Neural Network (MACNN) and Gated_Twins_Transformer. MACNN is used to extract multi-scale information of pipeline features, and then the attention mechanism in it to focus on the more important feature information and suppress the less important feature information. It is then transmitted to the Gated_Twins_Transformer model, which uses the gated mechanism and the twins encoder module to determine the importance of the data length and input dimensions, focusing on the feature information of both with different weights, and the Transformer enhances the extraction of global features. Finally, the measured pipeline bending strain data are used as model input, trained and tested, and compared with other advanced models, the superiority of the proposed model in this paper is verified by comparing the metrics of Accuracy, Precision, Recall and F1-score.

Caricature-visual face recognition based on jigsaw solving and modal decoupling

In recent years, face recognition technology has made significant progress in the field of real visual images, yet face recognition involving caricature-visual images remains a challenge due to the exaggerated and unrealistic features of caricature faces. To tackle this issue, this paper introduces the Caricature-visual Face Recognition Model Based on Jigsaw Solving and Modal Decoupling (CVF-JSM). The CVF-JSM consists of two modules: feature extraction and decoupling. The feature extraction module incorporates a graph attention network at the intermediate stage of the backbone network, which constructs and solves jigsaw puzzles to enable the network to extract shape features. The feature decoupling module features a three-branch structure that divides the features into modal and identity features. The real and caricature face recognition branches separate identity features for recognition through parameter sharing and orthogonality constraints. The feature common subspace alignment branch maps the anchor image, as well as the positive and negative sample images, into a common subspace to isolate identity features. Subsequently, by aligning the features, it further refines the effective identity features. The experimental results conducted on multiple datasets demonstrate that the CVF-JSM model outperforms existing technologies in the realm of caricature-visual face recognition.

BEV-TinySpotter: A novel BEV perception method considering multi-dimensional feature fusion of small target

The BEV perceptual integrity depends on the ability to accurately capture multi-scale targets. However, the detection of multi-scale targets, especially small targets, is often affected by perceptual noise, information sparsity, and target occlusion, which subsequently affecting the accuracy of BEV perception and causing certain hidden danger to driving safety. To address these issues, we propose a novel BEV perception method BEV-TinySpotter (BEV-TS), which introduced two feature detection enhancement modules and one analytical causal reasoning module to highlighting small object features and improving the accuracy and robustness of small object detection. Specifically, we first enhance the feature recognition of small targets using the multi-scale spatial information acquisition module, and introduce the distribution and migration weights of small targets reflected in the time-series information. Then, we jointly employ global pooling and local pooling to differentiate the acquisition paths of the information to improve the sensitivity of capturing information for small targets. Additionally, we design causal inference graphs to post-fuse the recognition results of BEV, which utilizes causal reasoning to construct a state description mechanism for small targets, further enhancing the accuracy of BEV perception from a logical reasoning perspective. Compared with other SOTA BEV methods, the proposed method effectively enhances the ability to capture and infer the status of small targets during BEV perception, thus significantly improves the completeness of driving environment sensing.

Methodology for Object-Level Change Detection in Post-Earthquake Building Damage Assessment Based on Remote Sensing Images: OCD-BDA

Remote sensing and computer vision technologies are increasingly leveraged for rapid post-disaster building damage assessment, becoming a crucial and practical approach. In this context, the accuracy of employing various AI models in pixel-level change detection methods is significantly dependent on the consistency between pre- and post-disaster building images, particularly regarding variations in resolution, viewing angle, and lighting conditions; in object-level feature recognition methods, the low richness of semantic details of damaged buildings in images leads to a poor detection accuracy. This paper proposes a novel method, OCD-BDA (Object-Level Change Detection for Post-Disaster Building Damage Assessment), as an alternative to pixel-level change detection and object-level feature recognition methods. Inspired by human cognitive processes, this method incorporates three key steps: an efficient sample acquisition for object localization, labeling via HGC (Hierarchical and Gaussian Clustering), and model training and prediction for classification. Furthermore, this study establishes a change detection dataset based on Google Earth imagery of regions in Hatay Province before and after the Turkish earthquake. This dataset is characterized by pixel inconsistency and significant differences in photographic angles and lighting conditions between pre- and post-disaster images, making it a valuable test dataset for other studies. As a result, in the experiments of comparative generalization capabilities, OCD-BDA demonstrated a significant improvement, achieving an accuracy of 71%, which is twice that of the second-ranking method. Moreover, OCD-BDA exhibits superior performance in tasks with small sample amounts and rapid training time. With only 1% of the training samples, it achieves a prediction accuracy exceeding that of traditional transfer learning methods with 60% of samples. Additionally, it completes assessments across a large disaster area (450 km²) with 93% accuracy in under 23 min.

Enhancing Vibration Detection in ϕ-OTDR Through Image Coding and Deep Learning-Driven Feature Recognition

Enhancing Vibration Detection in ϕ-OTDR Through Image Coding and Deep Learning-Driven Feature Recognition

Algorithm for simulating calligrapher’s stroke features using neural networks

In the field of calligraphy art, simulating the stroke features of calligraphers has always been a challenging task. Traditional methods often rely on manually designed rules or feature extraction algorithms, which are difficult to accurately capture calligraphy details and time-consuming. This article aimed to explore a more effective method to simulate the stroke features of calligraphers using neural network technology. This article mainly explored the simulation algorithm of calligrapher stroke features based on neural networks, including calligrapher stroke feature statistics, calligrapher stroke feature abstraction, and calligrapher stroke feature extraction. By using Convolutional Neural Network (CNN) to learn and analyze calligraphy works, a better performance neural network model was established to achieve automatic recognition and classification of calligrapher stroke features. By continuously optimizing model parameters, the accuracy of calligrapher stroke feature simulation can be improved. The average similarity rates for imitating stroke features of five calligraphers (regular script, cursive script, clerical script, seal script, and running script) using Artificial Neural Network (ANN) were 0.72, 0.62, 0.40, 0.33, and 0.53, respectively. The average similarity rates for imitating stroke features of 5 calligraphers (regular script, cursive script, clerical script, seal script, and running script) using CNN were 0.93, 0.78, 0.87, 0.67, and 0.80, respectively. The research results of this article promoted the inheritance and innovation of calligraphy art, and expanded the expression forms and application fields of calligraphy art.

Fixed frequency range empirical wavelet transform based acoustic and entropy features for speech emotion recognition

The primary goal of automated speech emotion recognition (SER) is to accurately and effectively identify each specific emotion conveyed in a speech signal utilizing machines such as computers and mobile devices. The widespread recognition of the popularity of SER among academics for three decades is mainly attributed to its broad application in practical scenarios. The utilization of SER has proven to be beneficial in various fields, such as medical intervention, bolstering safety strategies, conducting vigil functions, enhancing online search engines, enhancing road safety, managing customer relationships, strengthening the connection between machines and humans, and numerous other domains. Many researchers have used diverse methodologies, such as the integration of different attributes, the use of different feature selection techniques, and designed a hybrid or complex model using more than one classifier, to augment the effectiveness of emotion classification. In our study, we used a novel technique called the fixed frequency range empirical wavelet transform (FFREWT) filter bank decomposition method to extract the features, and then used those features to accurately identify each and every emotion in the speech signal. The FFREWT filter bank method segments the speech signal frame (SSF) into many sub-signals or modes. We used each FFREWT-based decomposed mode to get features like the mel frequency cepstral coefficient (MFCC), approximate entropy (ApEn), permutation entropy (PrEn), and increment entropy (IrEn). We then used the different combinations of the proposed FFREWT-based feature sets and the deep neural network (DNN) classifier to classify the speech emotion. Our proposed method helps to achieve an emotion classification accuracy of 89.35%, 84.69%, and 100% using the combinations of the proposed FFREWT-based feature (MFCC + ApEn + PrEn + IrEn) for the EMO-DB, EMOVO, and TESS datasets, respectively. Our experimental results were compared with the other methods, and we found that the proposed FFREWT-based feature combinations with a DNN classifier performed better than the state-of-the-art methods in SER.

Pedestrian safety alarm system based on binocular distance measurement for trucks using recognition feature analysis

As an essential part of modern smart manufacturing, road transport with large and heavy trucks has in-creased dramatically. Due to the inside wheel difference in the process of turning, there is a considerable safety hazard in the blind area of the inside wheel difference. In this paper, multiple cameras combined with deep learning algorithms are introduced to detect pedestrians in the blind area of wheel error. A scheme of vehicle-pedestrian safety alarm detection system is developed via the integration of YOLOv5 and an improved binocular distance measurement method. The system accurately measures the distance between the truck and nearby pedestrians by utilizing multiple cameras and PP Human recognition, providing real-time safety alerts. The experimental results show that this method significantly reduces distance measurement errors, improves the reliability of pedestrian detection, achieves high accuracy and real-time performance, and thus enhances the safety of trucks in complex traffic environments.

Intelligent gear decision method for vehicle automatic transmission system based on data mining

The gear decision logic of automatic transmission directly affects the vehicle's dynamic, fuel economic, and comfort performance. This study employs data mining techniques to address the issues of low adaptability and low recognition rate in the intelligent gear decision of vehicle automatic transmission systems. The research further proposes the utilization of Kalman filter, Hidden Markov Models, and Long Short-Term Memory networks for condition feature recognition and time series classification. Subsequently, dynamic programming algorithms are employed to optimize intelligent gear decisions. Combining driver intent and driving environment, an intelligent gear decision method is formulated. The results indicate that, during a 430 s driving segment, the intelligent gear decision method consumes only 464 mL of fuel, closely resembling the economic strategy's 457 mL, with a gear shift frequency of 53, significantly better than the 79 shifts in the economic strategy. Moreover, the error rate for slope condition recognition is only 0.062 %. In a 200 s coupled condition, the intelligent gear decision results in fuel consumption of 207 mL, approximating the actual vehicle's 219 mL, while power-shifting consumes 316 mL, and economic shifting only 202mL. This study not only improves the accuracy of gear decisions but also effectively enhances vehicle operational efficiency, providing valuable insights for future automatic transmission systems with significant practical value.

Dendritic Molecular Baskets for Selective Binding of Toxic Methotrexate.

We describe the preparation, assembly, recognition characteristics, and bioactivity of dendritic basket 612-. This novel cavitand has a deep aromatic pocket with three (S)-glutamic acid dendrons at the rim to amplify water solubility and prevent self-association. 1H NMR spectroscopy, calorimetry (ITC), and mass spectrometry (ESI-MS) measurements validate the formation of an inclusion complex between 612- and anticancer drug methotrexate (MTX2-) in water (Kd=9.2 μM). To identify the docking pose, a comparison of computed (DFT and MM) and experimental 1H NMR chemical shifts suggests that MTX2- folds inside 612- (π⋅⋅⋅π), forming HBs with the peptidic dendrons while anchoring (C-H⋅⋅⋅π) to the aromatic pocket through its N-methyl group. In consequence, 612- selectively binds MTX2- in competition with structurally similar folic acid and leucovorin (reversal poisoning agent). While the host is biocompatible (HEK293; IC50>150 μM) and produces inclusion complex [MTX⊂6]14- in cell media, it experiences limitation in pharmacokinetic sequestration of MTX2- as dihydrofolate reductase's affinity to the drug is suggested to prevail over that of 612-. Nonetheless, considering the basket's biocompatibility, tunability, and chemoselectivity, it stands as the leading candidate in the pursuit of an effective abiotic antidote for methotrexate poisoning.

Dendritic Molecular Baskets for Selective Binding of Toxic Methotrexate

We describe the preparation, assembly, recognition characteristics, and bioactivity of dendritic basket 612‐. This novel cavitand has a deep aromatic pocket with three (S)‐glutamic acid dendrons at the rim to amplify water solubility and prevent self‐association. 1H NMR spectroscopy, calorimetry (ITC), and mass spectrometry (ESI‐MS) measurements validate the formation of an inclusion complex between 612‐ and anticancer drug methotrexate (MTX2‐) in water (Kd = 9.2 μM). To identify the docking pose, a comparison of computed (DFT and MM) and experimental 1H NMR chemical shifts suggests that MTX2‐ folds inside 612‐ (π···π), forming HBs with the peptidic dendrons while anchoring (C−H···π) to the aromatic pocket through its N‐methyl group. In consequence, 612‐ selectively binds MTX2‐ in competition with structurally similar folic acid and leucovorin (reversal poisoning agent). While the host is biocompatible (HEK293; IC50 > 150 μM) and produces inclusion complex [MTX⊂6]14‐ in cell media, it experiences limitation in pharmacokinetic sequestration of MTX2‐ as dihydrofolate reductase’s affinity to the drug is suggested to prevail over that of 612‐. Nonetheless, considering the basket’s biocompatibility, tunability, and chemoselectivity, it stands as the leading candidate in the pursuit of an effective abiotic antidote for methotrexate poisoning.

Employing Evolutionary Computing and Hybrid Artificial Neural Networks to Improve Drug Discovery

An ultimate relevant translational scientific endeavour that contributes to human vulnerability and happiness might be the creation and advancement of medications. Fast drug discovery procedures necessitate using contemporary computational approaches to tackle pharma data's complexities and high complexity. By combining Evolutionary Computing with Hybrid Artificial Neural Networks (EC-HANNs), this research introduces a novel strategy for optimizing and speeding up the drug development process. To handle various drug-target relations, predict the efficacy of compounds, and discover more accurate potential medications, the proposed model employs EC to evolve the computational construction and hyperparameters of HANNs in real-time. This innovation makes the model a flexible framework. Through repeated refinement of EC- HANN designs, the EC Module uses Particle Swarm Optimization (PSO) to choose the best configuration for individual drug discovery tasks. The model's distinctive feature is that it dynamically adjusts the network configuration to match the details of each drug discovery activity by using PSO to optimize the HANN's architecture and hyperparameters. Regarding sequential biological data, the HANN Module employs Convolutional Neural Networks (CNNs) to glean features for pattern recognition over time. By extracting high-level spatial information from genetic data, CNN can better identify prospective medication candidates. When tested on several benchmark datasets, the proposed framework demonstrates superior performance over traditional neural networks across the board regarding prediction accuracy, convergence speed, and model durability. As a powerful tool, this hybrid approach can simplify drug discovery, leading to more efficient drug development.

Research on Violin Audio Feature Recognition Based on Mel-frequency Cepstral Coefficient-based Feature Parameter Extraction

Research on Violin Audio Feature Recognition Based on Mel-frequency Cepstral Coefficient-based Feature Parameter Extraction