Face Recognition Using Local PCA Filters

Feature extraction in electronic nose (E-nose) signals is the first signal processing step in machine olfactory systems. Traditional feature extraction methods are often cumbersome and depend greatly on the experience of the researcher. The failure of feature extraction seriously deteriorates the performance of subsequent pattern recognition algorithms. In addition, inherent sensor signal shifts among sensing systems with identical configurations affect E-nose performance. Therefore, due to the unfavorable performance of empirical feature extraction and poor reproducibility, the odor detection ability of E-nose systems has deteriorated. In this paper, a bionic olfactory signal processing (BOSP) network based on a spiking neural network (SNN) is proposed to address these issues. Inspired by the structure of the olfactory bulb in mammals, the system has two components: a virtual olfactory receptor (VOR) layer and a bionic olfactory bulb (BOB) layer. The VORs convert the sensor response signals into spike sequences through two spike coding strategies. The BOBs, consisting of mitral cells and granule cells, extract spatiotemporal features from the spike sequences. The proposed BOSP network is a feature-level model that automatically extracts useful features from the sensor array outputs without applying traditional and tedious feature extraction steps, which can subsequently cascade various classifiers. The results of extensive experiments demonstrate that the BOSP network not only shows better feature extraction capability than several state-of-the-art methods but also exhibits promising shift suppression ability.

Detection of fabric defects with intertwined frame vector feature extraction

Modular multilevel converters (MMCs) have a complex structure and a large number of submodules (SMs). If there is a fault in one of the SMs, it will affect the reliable operation of the system. Therefore, rapid fault diagnosis and accurate fault positioning are crucial to ensuring the continuous operation of the system. However, the IGBT open-circuit faults in different submodules of MMCs have similar fault features, and the traditional fault feature extraction method cannot effectively extract the key features of the fault so as to accurately locate the faulty submodules. In response to this problem, this paper proposes a fault diagnosis method based on weighted-amplitude permutation entropy (WAPE) and DS evidence fusion theory. The simulation results show that WAPE has better feature extraction ability than basic permutation entropy, and the fused multiscale feature decision output has better diagnostic accuracy than the single-scale feature. Compared with traditional fault diagnosis methods, this method achieves the diagnosis of multiple fault types by collecting a single signal, which greatly reduces the number of samples and leads to higher diagnostic accuracy and faster diagnostic speed.

Signa1 modulation recognition (SMR) is an essential and challenging topic in orthogonal frequency-division multiplexing (OFDM) systems, and also it is the fundamental technique for signal detection and recovery. However, traditional feature extraction based SMR methods cannot effectively acquire the characteristics of the OFDM signals. Hence, the modulated OFD-M signal cannot be reliably identified. In this paper, we propose a deep learning (DL) based SMR method for recognizing OFDM signals, which is combined with a convolutional neural network (CNN) trained on in-phase and quadrature (IQ) samples. In the network model, the batch normalization (BN) layer and dropout layer are used to speed up model training and prevent overfitting, respectively. Three convolution layers with different convolution kernels perform well than traditional feature extraction methods in obtaining intrinsic properties of OFDM signals. The same number of multiple modulated signals are mixed and sent to the trained model for identification. Experiments are conducted to show that the method we proposed performs better than the traditional methods, mainly reflected in a higher probability of correct classification (PCC) and better consistency.

Research on feature extraction algorithm of rolling bearing fatigue evolution stage based on acoustic emission

Cardiovascular diseases represent a leading cause of mortality worldwide, necessitating accurate and early diagnosis for improved patient outcomes. Current diagnostic approaches for cardiac abnormalities often present challenges in clinical settings due to their complexity, cost, or limited accessibility. This study develops two deep learning architectures that offer fast, accurate, and cost-effective methods for automatic diagnosis of cardiac diseases, focusing specifically on addressing the critical challenge of limited labeled datasets in medical contexts. We propose two methodologies: first, a Multi-Branch Deep Convolutional Neural Network (MBDCN) that emulates human auditory processing by utilizing diverse convolutional filter sizes and power spectrum input for enhanced feature extraction; second, a Long Short-Term Memory-Convolutional Neural (LSCN) model that integrates LSTM blocks with MBDCN to improve time-domain feature extraction. The synergistic integration of multiple parallel convolutional branches with LSTM units enables superior performance in heart sound analysis. Experimental validation demonstrates that LSCN achieves multiclass classification accuracy of 89.65% and binary classification accuracy of 93.93%, significantly outperforming state-of-the-art techniques and traditional feature extraction methods such as Mel Frequency Cepstral Coefficients (MFCC) and wavelet transforms. A comprehensive fivefold cross-validation confirms robustness of our approach across varying data partitions. These findings establish the efficacy of our proposed architectures for automated heart sound analysis, offering clinically viable and computationally efficient solutions for early detection of cardiovascular diseases in diverse healthcare environments.

The traditional matrix-based feature extraction methods that have been widely used in face recognition essentially work on the facial image matrixes only in one or two directions. For example, 2DPCA can be seen as the row-based PCA and only reflects the information in each row, and some structure information cannot be uncovered by it. In this paper, we propose the directional 2DPCA that can extract features from the matrixes in any direction. To effectively use all the features extracted by the D2DPCA, we combine a bank of D2DPCA performed in different directions to develop a matching score level fusion method named multi-directional 2DPCA for face recognition. The results of experiments on AR and FERET datasets show that the proposed method can obtain a higher accuracy than the previous matrix-based feature extraction methods.

Due to the lack of expert experience and the shortcomings of high blindness, the traditional partial discharge feature extraction method of gas insulated switchgear (GIS) has an impact on the accuracy of pattern recognition; convolutional neural network emerged in recent years has the ability to adaptively extract features, but training a network with better performance needs to increase the network depth on the one hand, and more supportive data on the other. Therefore, this paper propose a GIS partial discharge pattern recognition method based on transfer learning of three pre-trained network models (VGG, InceptionV3, and Resnet50) under the small data set. And the feature extracted by the network are applied to SVM classifier which performs well on a small data set. Realizing the combination of deep learning and traditional machine learning. Experimental result shows that this method can effectively improve the accuracy of GIS partial discharge pattern recognition.

The increasing global population has escalated the demand for fish products. This calls for a stable supply which can only be met through improved aquaculture practices. The automatic recognition of fish diseases from diseased underwater images is one of such practices that aims to control disease, improve fish production and optimize profits. However, due to lack of public fish disease dataset, there has been limited research towards fish disease recognition. Moreover, due to low quality of underwater images and complex underwater environments, traditional hand-designed feature extraction methods or convolutional neural networks (CNNs)-based classifiers cannot adequately recognize fish diseases in real underwater scenes. Therefore, this paper proposes a novel hybrid approach based on multilayer fusion, attention mechanism and online sequential extreme learning machine (OSELM) to recognize fish diseases in aquaculture. We further compare the classification performance of the proposed model with baseline, attention-based, ConvNeXt and Swin transformer models. Feature extraction is enhanced by integrating same level features and focusing on salient features for fish disease recognition. The characteristic information of fish disease is refined by using strongly discriminative features of the infected fish regions and weakening regions of low interest using convolutional block attention module (CBAM). The module is added to the multilayer fusion network to sequentially infer attention maps along the channel and spatial dimensions for every intermediate feature map. Fish disease recognition is then done using OSELM for faster learning and improved classification performance. The models are trained, validated and tested on a custom dataset with image samples collected from various internet sources. The proposed method achieves 94.28% of accuracy, precision of 92.67%, recall of 92.17% and 92.42% of F1- score on dataset with background elimination. The proposed method can be used for fish disease identification in complex underwater environments in aquaculture.

Shock signal features must be extracted for use in pattern recognition or fault diagnosis. In this work, we proposed a method for the feature extraction of shock signals, which are vibration signals that change faster and have larger amplitude ranges than general signals. First, we proposed the concepts of amplitude density for monotonic functions and piecewise monotonic functions. On the basis of these concepts, we then proposed the concept of the upper limit of density integral (ULDI), which was adopted to obtain signal features. Then, we introduced two types of serious fault cracks to the latch sheet of an automatic gun mechanism that is used on warships. Next, we applied the proposed method to extract the features of shock signals from data acquired when the automatic gun mechanism fired with normal and two fault patterns. Finally, we verified the effectiveness of our proposed method by applying the features that it extracted to a support vector machine (SVM). Our proposed method provided good results and was superior to the traditional statistics-based feature extraction method when applied to a SVM for classification. In addition, the former method demonstrated better generalisation than the latter. Thus, our method is an efficient approach for extracting shock signal features in pattern recognition and fault diagnosis.

Traditional multi-view feature extraction methods based on manifold learning frequently overlook the similarity sequence between samples, failing to capture the intrinsic manifold structure of raw nonlinear samples and restricting the recognition performance of multi-view learning. In this paper, we propose a novel similarity-sequenced multi-view discriminant feature extraction method, called Similarity -sequenced Multi-view Discriminant Correlation Analysis (SMDCA), which explicitly considers the sample sequences based on similarity. The method constructs similarity-sequenced discriminant scatters for preserving the sequence structure of within-class samples and develops between-class correlations with the similarity-sequence structure information for further constraining intrinsic manifold structure of cross-view samples. SMDCA can also simultaneously extract low-dimensional sequence features with well-discriminative power from multiple views. Extensive experiments exhibit that SMDCA can provide higher recognition accuracy and stronger robustness in image recognition tasks.

Point cloud completion aims to reconstruct the complete 3D shape from incomplete point clouds, and it is crucial for tasks such as 3D object detection and segmentation. Despite the continuous advances in point cloud analysis techniques, feature extraction methods are still confronted with apparent limitations. The sparse sampling of point clouds, used as inputs in most methods, often results in a certain loss of global structure information. Meanwhile, traditional local feature extraction methods usually struggle to capture the intricate geometric details. To overcome these drawbacks, we introduce PointCFormer, a transformer framework optimized for robust global retention and precise local detail capture in point cloud completion. This framework embraces several key advantages. First, we propose a relation-based local feature extraction method to perceive local delicate geometry characteristics. This approach establishes a fine-grained relationship metric between the target point and its k-nearest neighbors, quantifying each neighboring point's contribution to the target point's local features. Secondly, we introduce a progressive feature extractor that integrates our local feature perception method with self-attention. Starting with a denser sampling of points as input, it iteratively queries long-distance global dependencies and local neighborhood relationships. This extractor maintains enhanced global structure and refined local details, without generating substantial computational overhead. Additionally, we develop a correction module after generating point proxies in the latent space to reintroduce denser information from the input points, enhancing the representation capability of the point proxies. PointCFormer demonstrates state-of-the-art performance on several widely used benchmarks.

In this paper, we investigate the speech feature extraction problem in the noisy environment. A novel approach based on Gabor filtering and tensor factorization is proposed. From recent physiological and psychoacoustic experimental results, localized spectro-temporal features are essential for auditory perception. We employ 2D-Gabor functions with different scales and directions to analyze the localized patches of power spectrogram, by which speech signal can be encoded as a general higher order tensor. Then Nonnegative Tensor PCA with sparse constraint is used to learn the projection matrices from multiple interrelated feature subspaces and extract the robust features. Experimental results confirm that our proposed method can improve the speech recognition performance, especially in noisy environment, compared with traditional speech feature extraction methods.

Recent advances in the brain-computer interfaces (BCIs) have demonstrated the inference of movement related activity using non-invasive EEG. However, most of the sensorspace approaches that study sensorimotor rhythms using EEG do not reveal the underlying neurophysiological phenomenon while executing or imagining the movement with finer control. Therefore, there is a need to examine feature extraction techniques in the cortical source space which can provide more information about the task compared to sensor-space. In this study, we extend the traditional sensor-space feature extraction method, Common Spatial Pattern (CSP), to the source space, using various regularization approaches. We use Weighted Minimum Norm Estimate (wMNE) as a source localization technique. We show that for a multi-direction hand movement classification problem, the source space features can result in an increase of over 10% accuracy compared to sensor space features. Fisher's Linear Discriminant (FLD) classifier with the One-versus-rest approach is used for the classification.

Palmprint identification has emerged as one of the popular and promising biométrie modalities for forensic and commercial applications. In recent years the contactless system emerges as a viable option to address hygienic issues and improve the user acceptance. The presence of significant scale, rotation, occlusion and translation variations in the contactless palmprint images requires the feature extraction approaches which are tolerant to such changes. Therefore the usage of traditional palmprint feature extraction methods on contactless imaging schemes remains questionable and hence all/popular palmprint feature extraction methods may not be useful in contactless frameworks. This paper we systematically examine the issues related to the contactless palmprint authentication and presents performance evaluation on the two public databases. Our experimental results on more than 4300 images from two contactless databases suggests that the Scale Invariant Feature Transform (SIFT) features perform significantly better for the contactless palmprint images than the (most) promising Orthogonal Line Ordinal Features (OLOF) approach employed earlier on the more conventional palmprint imaging. Our experimental results further suggests that the combination of robust SIFT matching scores along with those from OLOF can be employed to achieve more reliable performance improvement. The achieved error rates show a good performance of these features in controlled and uncontrolled environments conditions with the error rates similar to other contact based approaches.