Pattern Recognition Classification Research Articles

Few-shot learning for inference in medical imaging with subspace feature representations.

Unlike in the field of visual scene recognition, where tremendous advances have taken place due to the availability of very large datasets to train deep neural networks, inference from medical images is often hampered by the fact that only small amounts of data may be available. When working with very small dataset problems, of the order of a few hundred items of data, the power of deep learning may still be exploited by using a pre-trained model as a feature extractor and carrying out classic pattern recognition techniques in this feature space, the so-called few-shot learning problem. However, medical images are highly complex and variable, making it difficult for few-shot learning to fully capture and model these features. To address these issues, we focus on the intrinsic characteristics of the data. We find that, in regimes where the dimension of the feature space is comparable to or even larger than the number of images in the data, dimensionality reduction is a necessity and is often achieved by principal component analysis or singular value decomposition (PCA/SVD). In this paper, noting the inappropriateness of using SVD for this setting we explore two alternatives based on discriminant analysis (DA) and non-negative matrix factorization (NMF). Using 14 different datasets spanning 11 distinct disease types we demonstrate that at low dimensions, discriminant subspaces achieve significant improvements over SVD-based subspaces and the original feature space. We also show that at modest dimensions, NMF is a competitive alternative to SVD in this setting. The implementation of the proposed method is accessible via the following link.

Semi-supervised learning for gas insulated switchgear partial discharge pattern recognition in the case of limited labeled data

Semi-supervised learning has better and more efficient performance than supervised algorithms in the case of limited labeled data. Existing methods for diagnosing partial discharge (PD) insulation defects in gas-insulated switchgear (GIS) equipment can only be effective if there is sufficient labeled data. However, in the actual working conditions of GIS equipment, insulation defect data is very scarce, where labeled data is more expensive to obtain and most of the data is unlabeled. In the case of limited PD labeled data, it is still a serious challenge to achieve higher classification accuracy of GIS PD pattern recognition. Therefore, we propose a semi-supervised self-training algorithm based on density peaks of local neighbor Information. Firstly, an improved density peak clustering algorithm based on local neighbor information is proposed, which no longer depends on the truncation distance, and considers the local information to better reflect the local density. Secondly, using local neighbor Information of labeled data, the criterion of confidence of unlabeled data is improved. Then, the PD unlabeled data with pseudo-labels are used to build a strong classifier for GIS PD pattern recognition. The experimental results show that the proposed algorithm has higher classification accuracy than other semi-supervised algorithms. When the proportion of labeled data is 10 %, the recognition accuracy can reach 65.98 %, which is the highest in the comparison algorithm. The proposed algorithm provides a feasible solution for GIS PD pattern recognition in the case of limited labeled data.

Pattern recognition of control charts based on data feature enhancement and ensemble learning of classifiers for dimensional accuracy of products

Product quality in manufacturing is directly related to the reliability, durability and safety of the product. Product quality can be controlled by building a product control chart pattern recognition model. The complexity and temporal sequence of product quality data make it difficult to extract effective control chart features, and it is difficult for common classifiers to play an effective role for each control chart pattern category, thus affecting the accuracy of pattern recognition. Therefore, this paper proposes a data feature enhancement processing method that combines Smote algorithm and smooth shift processing. This method reveals data features by performing feature enhancement processing on raw data and extracts statistical and shape features for dimensionality reduction to improve recognition accuracy and efficiency. Based on this approach, this paper also proposes an ensemble learning model based on the Stacking method, which incorporates BP, ELM, PNN and SVM classifiers for control chart pattern recognition. Through extensive experimental validation, the data feature enhancement method improves the accuracy of the weak classifier normal pattern recognition by 30%, and effectively reduces the misclassification in the quality control process. The ensemble learning model is stronger than the weak classifier, and its recognition accuracy can reach 97.31%.

Measures of extended fractional Deng entropy and extropy with applications

Recently, Zhang and Shang introduced modifications to the concept of fractional entropy and proved some properties based on the inverse Mittag-Leffler function (MLF). The Deng entropy serves as a valuable measure in the Dempster-Shafer evidence theory (DST) to tackle uncertainty. In this study, we extend the fractional Deng entropy measure, introducing two distinct versions: E fd 1 α ( m ) and E fd 2 α ( m ) . We call this new measure the extended fractional Deng entropy, EFDEn. Additionally, we apply a similar approach to the fractional Deng extropy measure, resulting in E X fd 1 α ( m ) and E X fd 2 α ( m ) . We call this new measure the extended fractional Deng extropy, EFDEx. These two measures are complementary, leading to provide a deeper analysis of known and unknown information. Subsequently, we conduct a comparative analysis of these measures within the DST framework. We also propose the decomposable fractional Deng entropy, an extension of the decomposable entropy for Dempster–Shafer evidence theory, which effectively decomposes fractional Deng entropy. Finally, we delve into a pattern recognition classification problem to highlight the importance of these new measures.

Why consider quantum instead classical pattern recognition techniques?

This article delves into the evolving landscape of pattern recognition, transitioning from classical methodologies to quantum-based techniques. It underscores how quantum algorithms offer a new paradigm with the potential to overcome the limitations of classical techniques. Unlike conventional methods, which, while effective, often struggle with complex and high-dimensional datasets, quantum algorithms are poised to surpass these limitations. This study explores the applications, benefits, drawbacks, and open issues surrounding quantum pattern recognition methods and provides a comprehensive overview of the current state of quantum technology and outlines potential future directions, highlighting the intersection of quantum computing and pattern recognition for breakthroughs.

A feature extractor for temporal data of electronic nose based on parallel long short-term memory network in flavor discrimination of Chinese vinegars

Volatile flavor is a key indicator of food quality which can directly affect consumer preference and purchase intention. Electronic nose is considered as a promising intelligent sensory analysis tool for food flavor assessment, however, extracting effective features from the gas sensor array is still a major challenge, which largely determines the performance of subsequent classifiers. Here, a parallel long short-term memory (LSTM) network is proposed as a feature extractor for automatically extracting features from the whole time series of sensor responses in flavor discrimination of five Chinese vinegars. The network was trained by the temporal data from the sensor array and yielded different feature patterns corresponding to different vinegars, which were then fed to other conventional classifiers for pattern recognition. We also evaluated the influence of the extracted feature dimension that is related to the dimension of the hidden state of the LSTM layer on the classification performance. The results indicate that a larger dimension of extracted feature is unnecessary for promoting classification accuracy, instead, the optimum dimension 4 of the hidden state gives the highest accuracy of 95.8% in this application under the softmax evaluator. Moreover, much higher accuracies were obtained when combined with other sophisticated classifiers such as support vector machine. The results demonstrate that the proposed network is competent to extract features directly and automatically from the temporal data of the electronic nose.

Automated Determination of Music Genre and Linguistic Categorization

The main objective of the project is to build a system that allows users to predict genre as well as language out of some music . The Automated determination of musical genre and linguistic categorization is a machine learning based prediction model which is used to predict the genres and languages of an audio . Musical genres are categorical labels created by humans to characterize piece of music. A musical genre is characterized by common characteristics typically related to the instrumentation, rhythmic structure and harmonic content of the music. The performance and relative importance of the proposed features are investigated by training the statistical pattern recognition classifiers using real world audio collections and using machine learning algorithm.In this project, we built systems called music genre and language classification and the effects of different feature extraction methods and their various combinations were also investigated. This task is of great interest in music information retrieval and recommendation systems. In recent years, several machine learning algorithms have been developed to tackle this task, using features such spectral, temporal, and tonal characteristics of audio signals. Music genre prediction and language classification is a task that involves automatically predicting a piece of music into a specific genre category as well as language based on its audio features. Keywords-machine-learning,music,music genre and language classification

Molecular characterization of a short-chained pentraxin gene from kuruma shrimp Marsupenaeus japonicus hemocytes

Pentraxins (PTXs) are a family of pattern recognition proteins (PRPs) that play a role in pathogen recognition during infection via pathogen-associated molecular patterns (PAMPs). Here, we characterized a short-chained pentraxin isolated from kuruma shrimp (Marsupenaeus japonicus) hemocytes (MjPTX). MjPTX contains the pentraxin signature HxCxS/TWxS (where x can be any amino acid), although the second conserved residue of this signature differed slightly (L instead of C). In the phylogenetic analysis, MjPTX clustered closely with predicted sequences from crustaceans (shrimp, lobster, and crayfish) displaying high sequence identities exceeding 52.67 %. In contrast, MjPTX showed minimal sequence identity when compared to functionally similar proteins in other animals, with sequence identities ranging from 20.42 % (mouse) to 28.14 % (horseshoe crab). MjPTX mRNA transcript levels increased significantly after artificial infection with Vibrio parahaemolyticus (48 h), White Spot Syndrome Virus (72 h) and Yellow Head Virus (24 and 48 h). Assays done in vitro revealed that recombinant MjPTX (rMjPTX) has an ability to agglutinate Gram-negative and Gram-positive bacteria and to bind microbial polysaccharides and bacterial suspensions in the presence of Ca2+. Taken together, our results suggest that MjPTX functions as a classical pattern recognition protein in the presence of calcium ions, that is capable of binding to specific moieties present on the surface of microorganisms and facilitating their clearance.

Efficient water-related failure detection in PEM fuel cells: Combining a PEMFCs fractional order impedance model with FFT-PWM techniques and artificial neural network classification

Water management and early detection of faults in proton exchange membrane fuel cells (PEMFCs) are among the most critical constraints that limit the optimal spread of this type of energy. Consequently, it is necessary to enhance the reliability and durability of PEMFCs by developing an approach to diagnose and identify water failure modes. This paper proposes an effective and simple method to detect, diagnose, and classify various water failure modes in PEMFCs using a hybrid diagnostic approach. This approach combines the PEMFC fractional order impedance model (FOIM) with fast Fourier transform pulse width modulation (FFT-PWM) techniques and artificial neural network pattern recognition (ANN-PR) classification. The results show an accurate match between the electrochemical impedance spectroscopy (EIS) experimental data, the Nyquist impedance spectra of FOIM, and the FFT-PWM algorithm as a proposed alternative technique to EIS measurements. Learning of ANN-PR was performed using the frequency spectrum amplitude (FSA) database of the voltage and current signals produced by the PEMFCs FOIM DC/DC boost converter, which was generated using the FFT-PWM algorithm. The ANN-PR achieved low values for error accuracy, with the Low Square Error and Learning Error reaching 6.676 × 10−19 and 1.888 × 10−16, respectively. The elements inside the confusion matrix and the rest of the matrices confirm that the proposed model's accuracy, precision, recall, and high F1 score reached 100%. Furthermore, all predictions made by the ANN-PR model were consistently accurate across all areas of failure detection. Overall, the proposed method helps in analyzing, diagnosing, and classifying fuel cell failure modes such as flooding and drying, which may simplify the health assessment of PEMFC.

An automatic method for estimating insect defoliation with visual highlights of consumed leaf tissue regions

As an essential component of the architecture of a plant, leaves are crucial to sustaining decision-making in cultivars and effectively support agricultural processes. When the leaf area is constantly monitored, a plant’s health and productive capacity can be assessed to foment proactive and reactive strategies. Because of that, one of the most critical tasks in agricultural processes is estimating foliar damage. In this sense, we present an automatic method to estimate leaf stress caused by insect herbivory, including damage in border regions. As a novelty, we present a method with well-defined processing steps suitable for numerical analysis and visual inspection of defoliation severity. We describe the proposed method and evaluate its performance concerning 12 different plant species. Experimental results show high assertiveness in estimating leaf area loss with a concordance correlation coefficient of 0.98 for grape, soybean, potato, and strawberry leaves. A classic pattern recognition approach, named template matching, is at the core of the method whose performance is compared to cutting-edge techniques. Results demonstrated that the method achieves foliar damage quantification with precision comparable to deep learning models. The code prepared by the authors is publicly available.

The Role of the TLR4-MyD88 Signaling Pathway in the Immune Response of the Selected Scallop Strain “Hongmo No. 1” to Heat Stress

The innate immunity of marine bivalves is challenged upon exposure to heat stress, especially with increases in the frequency and intensity of heat waves. TLR4 serves a classical pattern recognition receptor in recognizing pathogenic microorganisms and activating immune responses. In this study, three genes, HMTLR4, HMMyD88 and HMTRAF6, were characterized as homologs of genes in the TLR4-MyD88 signaling pathway in the selected scallop strain “Hongmo No. 1”. According to RT-PCR, acute heat stress (32 °C) inhibited genes in the TLR4-MyD88 signaling pathway, and LPS stimulation-induced activation of TLR4-MyD88 signal transduction was also negatively affected at 32 °C. ELISA showed LPS-induced tumor necrosis factor alpha (TNF-α) or lysozyme (LZM) activity, but this was independent of temperature. RNA interference (RNAi) confirmed that HMTLR4 silencing suppressed the expression of its downstream gene, whether at 24 °C or at 32 °C. The level of TNF-α and the activity of LZM also decreased after injection with dsRNA, indicating a negative effect on the innate immunity of scallops. Additionally, acute heat stress affected the suppression of downstream gene expression when compared with that at 24 °C, which led us to the hypothesis that heat stress directly influences the downstream targets of HMTLR4. These results enrich the knowledge of scallop immunity under heat stress and can be beneficial for the genetic improvement of new scallop strains with higher thermotolerance.

Identification, characterization and the inflammatory regulating effect of NOD1/2 in sturgeon

As an ancient species with both conservation and commercial value, Sturgeon's inflammatory regulation mechanism is a research point. Nucleotide-binding and oligomerization domain-containing proteins 1 and 2 (NOD1/2) are classical intracellular pattern recognition receptors (PRRs) in immunity of anti-bacterial infection. However, the characterization and function of NOD1/2 in Sturgeon are still unclear. In this study, we analyzed the synteny relationship of NOD1/2 genes between Acipenser ruthenus and representative fishes at the genome-level. Results showed that the ArNOD2 collinear genes pair was present in all representative fishes. The duplicated ArNOD1/2 genes were under purifying selection during evolution as indicated by their Ka/Ks values. To explore the function of NOD1/2, we further investigated their expression patterns and the effects of pathogenic infection, PAMPs treatment, and siRNA interference in Acipenser baerii, the sibling species of A. ruthenus. Results showed that both AbNOD1/2 were expressed at early developmental stages and in different tissues. Pathogenic infection in vivo and PAMPs treatment in vitro demonstrated that AbNOD1/2 could respond to pathogen stimulation. siRNA interference with AbNOD1/2 inhibited expression levels of RIPK2 and inflammatory cytokines compared to the control group after iE-DAP or MDP treatment. This study hinted that the AbNOD1/2 could stimulate the inflammatory cytokines response during evolutionary processes.

Optimizing the performance of machine learning algorithms for the condition assessment of utility timber poles

ABSTRACT This study focuses on evaluating several machine learning algorithms for the condition assessment of utility timber poles. An efficient feature extraction technique combining Hilbert Huang transform (HHT) and wavelet packet transform (WPT) is adopted from the authors’ previous work and implemented to determine damage-sensitive features from vibration data related to five serviceable and eight unserviceable in-situ timber poles. Then, these features are pre-processed using correlation heat map analysis for feature selection. Principal component analysis (PCA) is adopted as the final step of pre-processing for reducing noise interference and enhancing classification accuracy. Afterwards, a feature matrix is formed, which is fed into the selected classifiers for pattern recognition. In addition, the information gain method is also implemented and compared against PCA to examine the effect of feature selection. Finally, selected classifiers are employed using those dominant features, and their performance is evaluated based on six parameters – accuracy, precision, recall, F1-score, confusion matrix and Receiver Operating Characteristic (ROC) curve. It was found that choosing the best feature set related to the health state helps to improve the performance of the pattern recognition algorithms to a great extent.

FPRnet: A lightweight multi-domain multi-stream network for complex horizontal oil-water two-phase flow pattern recognition

The complicated spatio-temporal structure of horizontal oil-water flows renders the identification of flow patterns exceedingly challenging, owing to the presence of interfacial waves and droplet entrainment. In this study, a multi-domain fusion feature (MFF) as flow pattern descriptors (FPD) and a lightweight multi-stream networks (LMN) as flow pattern classifier (FPC) are proposed to identify the flow patterns of horizontal oil-water two-phase flow. MFF can map time series into different domains and compactly encode them into higher dimensional expressions, thus displaying implicit flow pattern signals incorporating nonlinear, time-frequency, and probabilistic transition domain features. Finally, the comparison of LMN, variational and other networks is evaluated on the horizontal oil-water flows pattern identification task. Extensive comparison experiments show that the time-frequency feature exhibits optimal characterization for the D O/W flow pattern, the URP feature is most accurately characterized for the D W/O and D O/W flow patterns, and the MTF feature exhibits superior characterization for the remaining three flow patterns. The 98.40 % recognition accuracy demonstrates that MFF has a good representation of flow patterns and the proposed LMN outperforms existing classifiers in flow pattern recognition.

An automatic detection method for schizophrenia based on abnormal eye movements in reading tasks

Schizophrenia is a common mental disease worldwide. To assist doctors in diagnosing schizophrenia through objective biological indicators, an automatic detection method for schizophrenia is proposed in this work. The proposed automatic detection method, which is based on the abnormal eye movements of schizophrenic patients in reading tasks, includes three parts: valid reading state trajectory extraction, eye movement trajectory extraction, and model construction based on abnormal eye movements in schizophrenic patients. The valid reading state trajectory extraction algorithm is proposed to divide the reading process into a valid reading state and an invalid reading state based on the visual perception of the subjects in the reading process. For the eye movement trajectory extraction, an eye center positioning algorithm based on the double ring of the limbic boundary is proposed for the valid reading state. Based on the extracted eye movement trajectory, models from three aspects of abnormalities of schizophrenic patients during reading are built: the merged eye-head movement, relative eye movement, and comprehensive reading performance. The features extracted from the three models are combined with a pattern recognition classifier to realize the automatic diagnosis of schizophrenia (the support vector machine, random forest, and adaptive boosting are used in this work). The video dataset used in this experiment was recorded using 40 subjects (20 schizophrenic patients and 20 healthy controls) from the Psychiatry Department of the Mental Health Center. The experimental results show that the detection accuracy of the automatic detection method for schizophrenia can reach 96.25%, which indicates that the proposed method can be used as a computer-aided diagnosis method for schizophrenia.

WR-PTXF, a novel short pentraxin, protects gut mucosal barrier and enhances the antibacterial activity in Carassius cuvieri × Carassius auratus red var.

The pentraxin family is an evolutionarily conserved group that plays an important role in innate immunity. C-reactive protein (CRP) and serum amyloid P component (SAP) are classical members of the short pentraxins and are known to be the major acute phase proteins. In this work, we have cloned a novel pentraxin fusion protein, WR-PTXF, from Carassius cuvieri × Carassius auratus red var. In fish, the biological function of PTXF is essentially unknown. For this purpose, we report the identification and analysis of WR-PTXF and elucidate its role in the antibacterial innate immunity. WR-PTXF contains 224 amino acids and shares 79.8% and 23.0% sequence identities with crucian carp CRP and SAP, respectively. Blast analysis shows that WR-PTXF and goldfish PTXF had the highest similarity (97.3%). WR-PTXF is expressed in multiple tissues and is upregulated by Aeromonas hydrophila infection. WR-PTXF contains a short pentraxin domain and recombinant WR-PTXF protein (rWR-PTXF) can bind the A. hydrophila in a concentration-dependent manner. Further, rWR-PTXF displays apparent bacteriostatic activity against A. hydrophila in vitro by enhancing the uptake of the bound bacteria by host phagocytes. When introduced in vivo, rWR-PTXF not only protects the gut mucosa but also limits the colonization of A. hydrophila in systemic immune organs. Consistently, knockdown of WR-PTXF significantly promotes bacterial dissemination in the tissues of host. These results indicate that WR-PTXF is a classic pattern recognition molecule that exerts a protective effect against bacterial infection.

Rolling Bearing Fault Diagnosis Based on SVD-GST Combined with Vision Transformer

Aiming at rolling bearing fault diagnosis, the collected vibration signal contains complex noise interference, and one-dimensional information cannot be used to fully mine the data features of the problem. This paper proposes a rolling bearing fault diagnosis method based on SVD-GST combined with the Vision Transformer. Firstly, the one-dimensional vibration signal is preprocessed to reduce noise using singular value decomposition (SVD) to obtain a more accurate and useful signal. Then, the generalized S-transform (GST) is used to convert the processed one-dimensional vibration signal into a two-dimensional time–frequency image and make full use of the advantages of deep learning in image classification with higher recognition accuracy. In order to avoid the problem of limited sensory fields in CNN and the need for an RNN to compute step by step over time when processing sequence data, the use of a Vision Transformer model for pattern recognition classification is proposed. Finally, an experimental platform for the fault diagnosis of rolling bearings is built. The model is experimentally validated, achieving an average accuracy of 98.52% over multiple tests. Additionally, compared with the SVD-GST-2DCNN, STFT-CNN-LSTM, SVD-GST-LSTM, and GST-ViT fault diagnosis models, the proposed method has higher diagnostic accuracy and stability, providing a new method for rolling bearing fault diagnosis.

Neural network based pattern recognition for classification of the forced and natural oscillation

Forced Oscillation (FO) has emerged as a major concern in power system due to its unpredictable frequency range. When the frequency of FO lies in the vicinity of that of the inherent natural oscillation, it can lead to resonance, posing a serious risk to the system. Improper identification and dissociation of FO in a power system can imprint huge detrimental effects, including blackouts. To address this issue, a novel method based on pattern recognition using artificial neural networks (ANNs) is proposed in this paper to classify FO and electromechanical oscillation. Multivariate time series data are collected from phasor measurement units (PMUs) placed at different buses are used as input for a two-layer NN, which is optimized using the stochastic scaled conjugate gradient algorithm. The proposed algorithm is simulated on the standard IEEE 10 machine, 39 bus system for various cases. The accuracy of the proposed algorithm is evaluated using the F1 score, obtained from the confusion plot. The results demonstrate that the network achieves a training accuracy of 97.5% and a testing accuracy of 96.67% with an F1 score of 96.7%. Additionally, ROC curves shows the efficiency of the designed model to predict the FO.

Lightweight and intelligent model based on enhanced sparse filtering for rotating machine fault diagnosis

Rotating machine fault diagnosis plays a vital role in reducing maintenance costs and preventing accidents. Machine learning (ML) methods and Internet of things (IoT) technologies have been recently introduced into machine fault diagnosis and have generated inspiring results. An ML model with more trainable parameters can typically generate a higher fault diagnostic accuracy. However, the IoT nodes have limited computation and storage resources. How to design an ML model with high accuracy and computational efficiency is still a difficulty and challenge. This work develops an enhanced sparse filtering (ESF) method for mining and fusing the features of the machine signals for fault diagnosis. First, a dimension reduction algorithm is utilized for obtaining the principal components of the vibration signals that are hindered by noises. The distinct features of the principal components are then exploited by using sparse filtering (SF). To reduce the overfitting of the SF model, the L1/2 norm is applied to regularize the objective function. Finally, the obtained features are combined as the inputs of a softmax classifier for machine fault pattern recognition. The effectiveness, superiority, and robustness of the proposed ESF method are validated by the simulated signals and the practical bearing and motor fault signals compared with the other conventional methods. The lightweight and intelligent ESF algorithm is also deployed onto an edge computing node to realize online motor fault diagnosis. The designed model and the proposed method show great potential in highly accurate and efficient rotation machine fault diagnosis.

Open set classification of untranscribed handwritten text image documents

Content-based classification of manuscripts is an important task that is generally carried out by expert archivists. Nevertheless, many historical manuscript collections are so vast that in most cases this task is hardly feasible, even for large, well staffed archives. Nowadays, manuscripts are generally preserved in the form of sets of digital images. Therefore, the technical problem we are interested in is automatic classification of “‘image documents”, each consisting of a set of untranscribed handwritten text images, by the textual contents of the images. The traditional Pattern Recognition classification paradigm does provide the basic tools to deal with this problem. However, in practice, the set of relevant classes of a large documental series is seldom known in advance. Therefore, a classifier trained with a predefined set of classes will systematically fail when new image documents arrive which do not belong to any of the classes assumed in training. Here we adopt the “Open Set Classification” framework to extend and consolidate our previous work on image document classification in order to adequately handle new documents from unknown classes. The proposed approaches are based on a relatively novel technology for text image representation known as “probabilistic indexing”, which proves very effective to characterise the intrinsic word-level uncertainty exhibited by historical handwritten text images. We assess the performance of this approach on a moderately sized but representative dataset extracted from a huge series of complex notarial manuscripts from the Spanish Archivo Histórico Provincial de Cádiz, with good results.