Similarity-sequenced multi-view discriminant feature extraction for image recognition

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

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.

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

Although the technical requirements for the feature extraction of ship radiated noise (SRN) in the fields of national defense and economy increase with each passing day, the complexity of the marine environment makes the feature extraction of SRN difficult. The traditional feature extraction method based on variational mode decomposition (VMD) is widely used in the feature extraction of SRN. Nevertheless, the use of VMD is greatly affected by parameters. In this paper, the butterfly optimization algorithm (BOA) is introduced to optimize VMD, which is called BOA-VMD algorithm, and realizes the optimal selection of VMD parameters K and α. To further improve the efficiency of feature extraction method, combined with slope entropy (SE), a feature extraction method of SRN based on BOA-VMD and SE is proposed. The experimental results of the simulated signal show that the BOA-VMD algorithm has a smaller envelope entropy value and better decomposition effect than the genetic algorithm (GA) and particle swarm optimization (PSO). The experimental results of feature extraction of SRN show that the highest recognition rate of the four entropy values improve with the increase of the number of extracted features, compared with the three entropy values of dispersion entropy (DE), fluctuation dispersion entropy (FDE) and permutation entropy (PE), the SRN feature extraction method based on BOA-VMD and SE has the highest recognition rate under different quantity features, and the recognition rate has reached 100% under three features.

This study describes a method for classifying electrocorticograms (ECoGs) based on motor imagery (MI) on the brain–computer interface (BCI) system. This method is different from the traditional feature extraction and classification method. In this paper, the proposed method employs the deep learning algorithm for extracting features and the traditional algorithm for classification. Specifically, we mainly use the convolution neural network (CNN) to extract the features from the training data and then classify those features by combing with the gradient boosting (GB) algorithm. The comprehensive study with CNN and GB algorithms will profoundly help us to obtain more feature information from brain activities, enabling us to obtain the classification results from human body actions. The performance of the proposed framework has been evaluated on the dataset I of BCI Competition III. Furthermore, the combination of deep learning and traditional algorithms provides some ideas for future research with the BCI systems.

The power system measurement data has high-dimensional features and strong noise, which is difficult to be directly used for intrusion detection. Traditional feature extraction and selection methods take the feature processing as a preprocessing step and perform separately from the model training, which makes the features not well adapted to the model. Therefore, we propose a novel wrapped feature selection framework based on the Las Vegas algorithm, which can improve the detection accuracy by strengthening the coupling between the feature selection and the model training. The Las Vegas algorithm can evaluate a feature subset through a specified model. In this paper, a heuristic thinking is integrated into the Las Vegas algorithm, which greatly improves the search performance of the original method. Finally, the proposed framework is examined on the IEEE 14-bus, 39-bus and 57-bus test systems for two attacks and the experimental results proves the effectiveness and stability of the proposed framework.

The edge feature extraction of image is one of the research fields of image processing theory and application. The traditional methods of image feature extraction are simple and proficient, but the accurate performance of the feature extracted is not even higher. As such, a new method for extracting image edge feature was proposed by using the two-dimensional Empirical Mode Decomposition (2-D EMD) and Riesz Transform. Firstly, the image was decomposed to multi-level Intrinsic) Mode Function (IMF) by 2-D EMD, and then the Riesz Transform with stronger local preserving ability was used for analyzing their local properties instead of the Hilbert Transform, by which the edge feature extraction with higher resolution was carried on. Finally, simulation shows that the proposed method is feasible and valid.

The detection of abnormal activities in deep learning is of great significance for preventing the occurrence of abnormal disasters in mine production. As the underground scenes of coal mines are characterized by much noise and uneven light, the traditional manual feature extraction method has little obvious effect in the underground and low accuracy of anomaly detection. To solve the above problems, a feature extraction method combining CNN+LSTM is proposed. Secondly, the obtained features are matched by graph structure. Finally, multiple classifiers are used to classify the features before and after matching. In this paper, experiments are carried out in coal mine dataset and UCSDped1 dataset respectively, and comparisons are made with some classical algorithms. Experimental show that the algorithm achieves high recognition accuracy in different abnormal event datasets.

In the field of the fault diagnosis of industrial processes, there are many problems in process data, such as missing critical fault data, high repeatability of normal state data, and poor representation of faults data, which may reduce the accuracy of fault diagnosis. In this paper, a novel K-medoids based synthetic minority over-sampling technique that combines locality preserving projections (KMS-LPP), is proposed for fault diagnosis. First, the synthetic minority sampling technology (SMOTE) is designed based on K-medoid to generate minority fault samples to address the imbalanced problem of data. Second, to extract the key fault-relevant features and reserve the local structure information at the same time, the manifold learning (ML) approach locality preserving projections (LPP) is performed to reduce the dimensionality of data. Finally, the Adaboost. M2, as an ensemble classifier, is conducted for fault classification. Simulations of the Tennessee Eastman process (TEP) are performed for validation of the performance of the presented KMS-LPP method. The obtained results show that KMS-LPP has enhanced the performance of fault diagnosis due to its higher accuracy compared with traditional oversampling and feature extraction methods, which indicates the effectiveness of KMS-LPP.

Improved prediction of protein-protein interactions using novel negative samples, features, and an ensemble classifier.

Face recognition based on depth images is widely studied due to its advantages of 3 dimensional information and environment illumination insensitivity. The traditional recognition methods in this field mainly focus on hand-crafted feature design, which cannot achieve satisfactory result. In addition, there is no fixed face feature extraction method. To achieve a better face recognition performance on depth images, this paper proposes a method based on Convolutional Neural Networks(CNN). The experiment performed on database IIITD Kinect suggests that the proposed CNN architecture has better recognition performance than some traditional manual feature extraction methods, such as HOG and LBP.

This research aims to study the deep learning applications in image recognition and classification tasks. The advantages and limitations of deep learning are explored by analysing existing deep learning algorithms and their applications on tasks such as using images to do classification, image segmentation, and target detection. In the experimental part, this paper evaluates the performance of deep learning in image recognition by using classical neural network models, including training and testing models on a large size of image datasets. The results show that neural network has good classification and detection capabilities in image recognition tasks and also achieves good results for image segmentation tasks. However, the model training process of shallow neural network models is time-consuming and performs poorly for small-scale datasets. Based on these situations, this paper proposes some optimization strategies to achieve high performance and efficiency of neural networks in image recognition and analyze the performance differences between different strategies .

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.

In the enterprise risk identification project, the data has the characteristics of the complex data sources and the diverse risks. The traditional feature extraction methods cannot cope with the multiple complex data sources at the same time. In this study, the risk feature extraction based on the single relationship of thein-depth learning and the feature coding technology of the risk atlas considering the time series can effectively extract the feature vectors of the risk atlas and avoid them at the same time. It avoids the complexity and blindness of the artificial feature extraction. And it is verified by a large-scale organization’s experiment on the enterprise’s overdue risk. Under the same model framework, the characteristics generated by using the risk feature coding technology are better than those given by the traditional experts under the model’s various indicators, which provide the strong support for the follow-up risk identification.