Feature Pattern Recognition Research Articles

A Real-Time Fault Diagnosis Method for Grid-Side Overcurrent in Train Traction System Using Signal Time Series Feature Pattern Recognition

Grid-side overcurrent (GSOC) is a common anomaly state in traction drive system (TDS). Once GSOC occurs, to protect the train, traction control units (TCU) will trip the main circuit breaker and stop the train in a short time. Since TCU cannot locate the source of the GSOC fault, troubleshooting can only be done by inspecting the components one by one after the train stops, which greatly affects the availability and maintenance efficiency of train. Therefore, this paper proposes a real-time fault diagnosis method based on time series feature pattern recognition of signals in TCU. Firstly, the time series pattern of GSOC caused by different fault sources are established. Secondly, the feature extraction method of time series pattern is carried out based on the fusion of engineering knowledge, variational mode decomposition and signal selection. Thirdly, the time series feature patterns of GSOC are identified to determine the most likely fault type of GSOC by Gaussians mixture model-Hidden Markov model (GMM-HMM). Finally, the proposed real-time fault diagnosis method is verified by the field test data. The results show that the proposed algorithm can realize real-time diagnosis of GSOC and trace the fault source effectively.

Second-order texton feature extraction and pattern recognition of building polygon cluster using CNN network

The cluster patterns of features in map space represent a comprehensive reflection of individual feature geometric attributes and their spatial adjacency relationships. These patterns also embody spatial cognition results under the Gestalt principle. Describing non-linear spatial cluster patterns as effective regular structures is one of the fundamental tasks in deep learning for recognizing feature cluster patterns. In this study, based on the concept of texture co-occurrence matrices from regular gray-scale images, we utilized Voronoi diagrams to construct the tessellation structure of building polygons. Built upon the foundation of first-order texton co-occurrence matrices, we established three-dimensional texton co-occurrence matrices for building polygons, considered five attributes of building size, shape, orientation, and density, and encompassed 64 different combinations of second-order neighboring directions. This matrix concretizes the latent Gestalt spatial characteristics of building polygon clusters into a three-dimensional sparse matrix. It is then used as an input vector to construct a deep convolutional neural network for recognizing building polygon cluster patterns. Through adjustments and optimizations of neural network structure and strategies, along with validation through practical case studies and comparisons with other models, we have demonstrated the effectiveness of the second-order texton co-occurrence matrix in describing the characteristics of building polygon clusters.

Advances and Challenges in Deep Learning-Based Change Detection for Remote Sensing Images: A Review through Various Learning Paradigms

Change detection (CD) in remote sensing (RS) imagery is a pivotal method for detecting changes in the Earth’s surface, finding wide applications in urban planning, disaster management, and national security. Recently, deep learning (DL) has experienced explosive growth and, with its superior capabilities in feature learning and pattern recognition, it has introduced innovative approaches to CD. This review explores the latest techniques, applications, and challenges in DL-based CD, examining them through the lens of various learning paradigms, including fully supervised, semi-supervised, weakly supervised, and unsupervised. Initially, the review introduces the basic network architectures for CD methods using DL. Then, it provides a comprehensive analysis of CD methods under different learning paradigms, summarizing commonly used frameworks. Additionally, an overview of publicly available datasets for CD is offered. Finally, the review addresses the opportunities and challenges in the field, including: (a) incomplete supervised CD, encompassing semi-supervised and weakly supervised methods, which is still in its infancy and requires further in-depth investigation; (b) the potential of self-supervised learning, offering significant opportunities for Few-shot and One-shot Learning of CD; (c) the development of Foundation Models, with their multi-task adaptability, providing new perspectives and tools for CD; and (d) the expansion of data sources, presenting both opportunities and challenges for multimodal CD. These areas suggest promising directions for future research in CD. In conclusion, this review aims to assist researchers in gaining a comprehensive understanding of the CD field.

Multimedia Identification and Analysis Algorithm of Piano Performance Music Based on Deep Learning

In the biometric biomedical applications, the study presents a pioneering research endeavor focused on the development of a multimedia identification and analysis algorithm tailored for piano performance music. With the power of deep learning techniques, this algorithm has been designed to address the intricate challenges posed by the convergence of musical data analysis and biometrics. The core objectives encompass the extraction, recognition, and interpretation of biometric information from piano performances, exploring the intricate patterns, nuances, and individualistic characteristics inherent to musicians. The study focuses on the development of advanced biometric authentication and identification systems capable of capturing and analyzing a user's unique behavioral patterns across diverse modalities. These biometric modalities offer the potential for highly secure and non-intrusive user identification. Hence, this paper developed an architecture of Marker Controlled Point (MCP) Estimation for the computation of the gesture in biometric-based applications. This architecture utilizes markers or reference points to precisely track and analyze user gestures, resulting in accurate and reliable biometric data. The research details the architecture's implementation, integrating advanced deep-learning techniques for feature extraction, pattern recognition, and authentication. This system finds versatile applications in various domains, from healthcare and cybersecurity to finance, where secure and user-friendly authentication is paramount. Experimental results underscore the system's effectiveness and robustness, demonstrating its potential for enhancing biometric authentication. The proposed model represents a significant stride in biometric technology, offering secure, non-intrusive user identification through the synergy of behavior biometrics and emerging modalities.

Feature extraction and pattern recognition of gas pipeline flow noise signals in a strong noisy background.

The purpose of this study is to put forward a feature extraction and pattern recognition method for the flow noise signal of natural gas pipelines in view of the complex situation brought by the rapid development and expansion of urban natural gas infrastructure in China, especially in the case that there are active and abandoned pipelines, metal and nonmetal pipelines, and natural gas, water and power pipelines coexist in the underground of the city. Because the underground situation is unknown, gas leakage incidents caused by natural gas pipeline rupture occur from time to time, posing a threat to personal safety. Therefore, the motivation of this study is to provide a feasible method to accelerate the aging, renewal and transformation of urban natural gas pipelines to ensure the safe operation of urban natural gas pipeline network and promote the high-quality development of urban economy. Through the combination of experimental test and numerical simulation, this study establishes a database of urban natural gas pipeline flow noise signals, and uses principal component analysis (PCA) to extract the characteristics of flow noise signals, and develops a mathematical model for feature extraction. Then, a classification and recognition model based on backpropagation neural network (BPNN) is constructed, which realizes the detection and recognition of convective noise signals. The research results show that the theoretical method based on acoustic feature analysis provides guidance for the orderly and safe construction of urban natural gas pipeline network and ensures its safe operation. The research conclusion shows that through the simulation analysis of 75 groups of gas pipeline flow noise under different working conditions. Combined with the experimental verification of ground flow noise signals, the feature extraction and pattern recognition method proposed in this study has a recognition accuracy of up to 97% under strong noise background, which confirms the accuracy of numerical simulation and provides theoretical basis and technical support for the detection and recognition of urban gas pipeline flow noise.

Deep learning for image-based diagnosis : Applications in medical imaging for drug development

This research delves into the application of Deep Learning (DL) to medical imaging for drug discovery, highlighting DL’s ability to enhance diagnostic precision and efficiency. The research looks into the use of DL methods like CNNs and RNNs for automating feature extraction, pattern recognition, and classification in large, complex medical datasets. Effective drug development relies on fast and accurate diagnosis of disease to determine treatment’s therapeutic efficacy and identify therapeutic targets. When applied to huge datasets, DL excels at uncovering subtle patterns and correlations that may be missed by more conventional methods. In addition to improving early disease identification and tailored medicinal therapies, the technology also helps in biomarker discovery. In this study, we discuss some of the obstacles of deploying DL ethically in medical imaging, such as protecting sensitive patient information, ensuring that models can be easily interpreted, and using a wide variety of data. The merger of DL and medical images offers great potential to promote image-based diagnosis in drug discovery, contributing to a more personalized and precise approach in healthcare, ultimately improving patient outcomes and changing the future of modern medicine.

Empirical Network Structure of Malicious Programs

A modern binary executable is a composition of various types of networks. Control flow graphs are a commonly used representation of an executable program used for classification tasks. Control flow and term frequency representations are widely adopted, but provide only a partial view of program semantics and present challenges to increases in resolution. By performing a quantitative analysis of program networks, we enable the identification of patterns within these features that are correlated to structure. This allows for increases in feature resolution and pattern recognition in classification tasks. These are necessary steps in order to obtain greater explainability in classification results. We demonstrate the presence of Scale-Free properties of network structure for program data dependency and control flow graphs, and show that data dependency graphs also have Small-World structural properties. We show that program data dependency graphs have a degree correlation that is structurally disassortative, and that control flow graphs have a neutral degree assortativity, indicating the use of random graphs to model the structural properties of program control flow graphs would show increased accuracy. An increase in feature resolution allows for the structural

NEURAL NETWORK-BASED ALGORITHM FOR ELECTROCARDIOSIGNAL PROCESSING: DEVELOPMENT AND ANALYSIS

This study focuses on the development and analysis of an algorithm utilizing neural network techniques for the processing of electrocardiograms. The proposed approach integrates advanced neural network models to enhance the processing and analysis of intricate electrocardiogram (ECG) data. The algorithm aims to accurately detect and interpret various cardiac patterns and abnormalities within ECG signals through neural network analysis, contributing to the efficient diagnosis and monitoring of cardiovascular conditions. The research involves the application of machine learning methodologies, particularly neural networks, to optimize signal processing, enabling robust feature extraction and pattern recognition from ECG data. The study's methodology involves training and validating the neural network algorithm with a diverse dataset of electro cardio signals, ensuring its effectiveness across varying cardiac conditions and patterns. The outcomes of this research aim to offer a sophisticated tool for clinicians and researchers, enhancing the accuracy and speed of ECG analysis, and ultimately contributing to improved clinical decision-making and patient care in cardiology.practitioners for the evolving educational landscape.

DETEKSI CACAT BANTALAN GELINDING BERBASIS ALGORITMA DECISION TREES DAN PARAMETER STATISTIK

Rolling bearings are a common machine element found in rotary machines. The components in the rolling bearing such as the inner race, outer race, rolling element, and cage are the parts that are often damaged. Traditionally spectrum analysis is used to diagnose bearing defects. However, spectrum analysis is not effectively applied to bearings with early defects because the vibration signal generated is dominated by frequency components from other machine elements, so the frequency of bearing defects cannot be observed. This study proposes an alternative method of detecting bearing defects based on vibration signals using machine learning with a decision tree algorithm. This method is more effective than the spectrum analysis method because machine learning is based on feature extraction and pattern recognition of vibration signal data, therefore, providing classification results directly without further analysis. Vibration signals were recorded using an accelerometer mounted on a bearing housing on a test rig. Nine-time domain statistical parameters and six frequency domain statistical parameters were extracted from the vibration signal and then used as input for decision trees. The results show that the decision trees algorithm gives an accuracy of 94.4% for classifying three rolling bearing conditions using the input of 6 selected frequency domain statistical parameters.

Suitability of curvature as a feature for image-based pattern recognition: a case study on leaf image classification based on machine learning

Suitability of curvature as a feature for image-based pattern recognition: a case study on leaf image classification based on machine learning

Fault diagnosis of rolling bearing using CNN and PCA fractal based feature extraction

A novel adaptive decomposition algorithm based on CEEMDAN and fractal dimension is proposed in this study to overcome limitations like redundancy and mode confusion in traditional EMD-based algorithms. An intelligent fault diagnosis model is developed using CNN and the proposed CEEMDAN to enhance rolling bearing state recognition. Sub-signals generated by CEEMDAN are selected and reconstructed using PCA and fractal dimension. In feature extraction and pattern recognition, the proposed Improve Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN), coupled with CNN, extracts advanced features from the reconstructed signal for intelligent diagnosis. The methodology is validated through empirical experiments involving rolling bearings, where its superiority and reliability are compared with approaches based on CNN. The accuracy of this method reaches 99.79%

Potato Malformation Identification and Classification Based on Improved YOLOv3 Algorithm

Potato malformation seriously affects commercial value, and its removal has become one of the core steps in the post-harvest and pre-sales process of potatoes. At present, this work mainly relies on manual visual inspection, which requires a lot of labor and incurs high investment costs. Therefore, precise and efficient automatic detection technology urgently needs to be developed. Due to the efficiency of deep learning based on image information in the field of complex object feature extraction and pattern recognition, this study proposes the use of the YOLOv3 algorithm to undertake potato malformation classification. However, the target box regression loss function MSE of this algorithm is prone to small errors being ignored, and the model code is relatively large, which limits its performance due to the high demand for computing hardware performance and storage space. Accordingly, in this study, CIOU loss is introduced to replace MSE, and thus the shortcoming of the inconsistent optimization direction of the original algorithm’s loss function is overcome, which also significantly reduces the storage space and computational complexity of the network model. Furthermore, deep separable convolution is used instead of traditional convolution. Deep separable convolution first convolves each channel, and then combines different channels point by point. With the introduction of an inverted residual structure and the use of the h-swish activation function, deep separable convolution based on the MobileNetv3 structure can learn more comprehensive feature representations, which can significantly reduce the computational load of the model while improving its accuracy. The test results showed that the model capacity was reduced by 66%, mAP was increased by 4.68%, and training time was shortened by 6.1 h. Specifically, the correctness rates of malformation recognition induced by local protrusion, local depression, proportional imbalance, and mechanical injury within the test set range were 94.13%, 91.00%, 95.52%, and 91.79%, respectively. Misjudgment mainly stemmed from the limitation of training samples and the original accuracy of the human judgment in type labeling. This study lays a solid foundation for the final establishment of an intelligent recognition and classification picking system for malformed potatoes in the next step.

State evaluation method for complex task network models

This paper focuses on the assessment of non-complete states in complex task networks and establishes an online capability boundary assessment model based on real-time feature parameters. By utilizing multivariate heterogeneous state features for data mining and pattern recognition, we delve into virtual sample generation technology using an overall diffusion trend approach. This starts by examining the validity of sample data and analyzing the relevance of data acquired within the feature space. Building on this foundation, the overall diffusion trend method is applied to generate virtual sample input that aligns with the sampling distribution characteristics of avionics system equipment. To address non-complete state evaluation in complex task networks, we design a comprehensive model. This model involves constructing a system signal flow block diagram and a structural diagram depicting the available capacity of subsystems and the overall system tasks. The establishment of unknown function relationships in signal connections is achieved through a fusion of neural network and fuzzy logic systems. Finally, an intelligent optimization algorithm is employed to determine system parameters. Utilizing this neuro-fuzzy system in simulation, we attain real-time system responses and evaluate the output regarding the available capacity of system tasks.

Efficient Skip Connections-Based Residual Network (ESRNet) for Brain Tumor Classification.

Brain tumors pose a complex and urgent challenge in medical diagnostics, requiring precise and timely classification due to their diverse characteristics and potentially life-threatening consequences. While existing deep learning (DL)-based brain tumor classification (BTC) models have shown significant progress, they encounter limitations like restricted depth, vanishing gradient issues, and difficulties in capturing intricate features. To address these challenges, this paper proposes an efficient skip connections-based residual network (ESRNet). leveraging the residual network (ResNet) with skip connections. ESRNet ensures smooth gradient flow during training, mitigating the vanishing gradient problem. Additionally, the ESRNet architecture includes multiple stages with increasing numbers of residual blocks for improved feature learning and pattern recognition. ESRNet utilizes residual blocks from the ResNet architecture, featuring skip connections that enable identity mapping. Through direct addition of the input tensor to the convolutional layer output within each block, skip connections preserve the gradient flow. This mechanism prevents vanishing gradients, ensuring effective information propagation across network layers during training. Furthermore, ESRNet integrates efficient downsampling techniques and stabilizing batch normalization layers, which collectively contribute to its robust and reliable performance. Extensive experimental results reveal that ESRNet significantly outperforms other approaches in terms of accuracy, sensitivity, specificity, F-score, and Kappa statistics, with median values of 99.62%, 99.68%, 99.89%, 99.47%, and 99.42%, respectively. Moreover, the achieved minimum performance metrics, including accuracy (99.34%), sensitivity (99.47%), specificity (99.79%), F-score (99.04%), and Kappa statistics (99.21%), underscore the exceptional effectiveness of ESRNet for BTC. Therefore, the proposed ESRNet showcases exceptional performance and efficiency in BTC, holding the potential to revolutionize clinical diagnosis and treatment planning.

ALADA: A lite automatic data augmentation framework for industrial defect detection

Industrial defect detection is a critical and challenging task in the quality control of manufacturing production. Competent in feature extraction and pattern recognition, deep learning shows great power for classifying and locating defects in industrial products. However, insufficient data records and diverse categories of defects restrict the detection accuracy of data-driven neural networks. One direction to solve such a problem is data augmentation, which aims at generating synthetic copies from existing data and improving the generalizability of detection models. However, confirming a suitable augmentation policy involves either human experience or substantial experiments for augmentation parameters. To address these challenges, in this work, a lite automatic data augmentation (ALADA) framework is proposed to jointly optimize the data augmentation policies and the neural network for industrial defect detection. First, a lite search space is formulated to efficiently sample augmentation policies and generate augmented images for joint optimization. To reduce the hyperparameter tuning efforts for retraining with searched policies, a three-step bi-level optimization scheme is proposed to replace the retraining strategy and update the model and augmentation parameter alternately. To solve the non-differentiable problem in the joint optimization scheme, policy gradient sampling is implemented to estimate the gradient flow efficiently. Experimental results on three industrial defect detection datasets, namely, Tianchi-TILE, GC10-DET, and NEU-DET, reveal that our proposed automatic augmentation framework outperforms the state-of-the-art augmentation methods and effectively improves the accuracy of the baseline defect detection model. The proposed ALADA scheme also alleviates the missed detection of defects in four practical industrial circumstances: textured background, uneven brightness, low contrast, and intraclass difference.

Usefulness of automated image analysis for recognition of the fragile X syndrome gestalt in Congolese subjects

BackgroundComputer-aided software such as the facial image diagnostic aid (FIDA) and Face2Gene has been developed to perform pattern recognition of facial features with promising clinical results. The aim of this pilot study was to test Face2Gene's recognition performance on Bantu Congolese subjects with Fragile X syndrome (FXS) as compared to Congolese subjects with intellectual disability but without FXS (non‐FXS). MethodFrontal facial photograph from 156 participants (14 patients with FXS and 142 controls) predominantly young-adults to adults, median age 18.9 age range 4–39yo, were uploaded. Automated face analysis was conducted by using the technology used in proprietary software tools called Face2Gene CLINIC and Face2Gene RESEARCH (version 17.6.2). To estimate the statistical power of the Face2Gene technology in distinguishing affected individuals from controls, a cross validation scheme was used. ResultsThe similarity seen in the upper facial region (of males and females) is greater than the similarity seen in other parts of the face. Binary comparison of subjects with FXS versus non-FXS and subjects with FXS versus subjects with Down syndrome reveal an area under the curve values of 0.955 (p = 0.002) and 0.986 (p = 0.003). ConclusionThe Face2Gene algorithm is separating well between FXS and Non-FXS subjects.

Empirical Myoelectric Feature Extraction and Pattern Recognition in Hemiplegic Distal Movement Decoding.

In myoelectrical pattern recognition (PR), the feature extraction methods for stroke-oriented applications are challenging and remain discordant due to a lack of hemiplegic data and limited knowledge of skeletomuscular function. Additionally, technical and clinical barriers create the need for robust, subject-independent feature generation while using supervised learning (SL). To the best of our knowledge, we are the first study to investigate the brute-force analysis of individual and combinational feature vectors for acute stroke gesture recognition using surface electromyography (EMG) of 19 patients. Moreover, post-brute-force singular vectors were concatenated via a Fibonacci-like spiral net ranking as a novel, broadly applicable concept for feature selection. This semi-brute-force navigated amalgamation in linkage (SNAiL) of EMG features revealed an explicit classification rate performance advantage of 10-17% compared to canonical feature sets, which can drastically extend PR capabilities in biosignal processing.

Identification of multiple symptoms of huanglongbing by electronic nose based on the variability of volatile organic compounds

AbstractHuanglongbing (HLB) is highly contagious and cannot be cured, resulting in a decrease in the commercial value of citrus. Timely detection and removal of diseased trees is an effective way to reduce losses. Complex symptoms of HLB, such as nutrient deficiencies often accompany HLB; as a result effective and accurate identification of HLB remains a challenge. In this study, 175 volatile organic compounds (VOCs) were detected in three categories (healthy, HLB, and Zn‐deficiency) of samples using headspace solid‐phase microextraction gas chromatography–mass spectrometry (HS‐SPME‐GC/MS), highlighting the variability of VOCs present in different categories of samples. In order to simplify the testing steps and reduce the cost in practical agricultural production, a method based on electronic nose technology to collect VOCs from citrus leaves for HLB detection was proposed. Among them, limiting value features and linear discriminant analysis were identified as the best combination of feature extraction and pattern recognition methods. Multiple sets of comparison experiments were set up and the collection conditions of VOCs were optimized. The results showed that the best classification performance was achieved for a 0.2 g sample at a collection time of 20 min when the collection temperature was 40°C and the headspace volume was 200 mL. Four types of samples (healthy, HLB‐positive, Zn‐deficiency, Zn‐deficiency and HLB‐positive) were used for model reliability validation, with an accuracy of 97.79% for HLB samples for multiple symptoms (including HLB‐positive and Zn‐deficiency and HLB‐positive) identification. In addition, the accuracy of samples with a combined effect of Zn‐deficiency and HLB was 96.43%. The results show that the E‐nose‐based HLB detection method is conducive to suppressing the spread of HLB, which can ensure the quality of citrus products and reduce the economic loss to horticulturists, and has good practical value.

Chess Engine Based on AI: A Survey

Researchers have been experimenting with several methods to create chess engines that can surpass human players, which has led to a lot of advancement in the field of chess AI in recent years. Neural networks, genetic algorithms, and machine learning are a few of the common methods. Chess engines that use self-play, automatic feature extraction, pattern recognition, and genetic player learning have been created using these methods. Researchers have also looked into various chess AI-related topics, like enhancing the game's visual appeal, creating multi-player engines, and even creating automated chess commentary. Although each strategy has its advantages and disadvantages, the area of chess AI is still developing as researchers work to create ever-more complex engines that can beat this game. Key Words: Chess, Chess AI, Chess Engine, Game ,Chess Algorithm, Negamax Algorithm, Player VS Player Game, Play with Computer,Play against AI, Play against Chess Engine.

PD Signal Detection Model Based on Multiscale Simulation of EM Generation and Transmission

Nowadays, the digital twin method has been gradually applied to power equipment condition monitoring. Since a main fundamental part of the digital twin is a simulation process with better fitting for the real one, this paper is devoted to building up a PD detection model to simulate the generation and transmission of electromagnetic (EM) wave signals caused by PDs, especially those inside the void defects. This model combines the micro discharge process with the transmission process inside certain geometry structures. Specifically, two commonly used methods are applied to simulate the processes correspondingly. The dielectric barrier discharge (DBD) model is used for the PD simulation inside void defects, while the finite-difference time-domain (FDTD) method is for the EM signal transmission process. The pulsed discharge current can be obtained during the simulation of DBD, which can function as the excitation source of the transmission process solved by FDTD. According to the PD detection model, the influences on the simulation results are discussed, including the impact on the discharge current caused by coefficient variation and the impact on the transmission process caused by the power equipment geometry structure and materials. As mentioned above, this paper is aimed at building a direct relationship between the observed EM signal and the micro discharge process, which reveals the physical process of PD signal measurement in virtual space that can provide more features for PD pattern recognition or noise elimination, and further the mechanism and theoretical analysis support for digital twin application.