Simulation Research of Applying Two-dimensional Empirical Mode Decomposition on Image Feature Extraction

The distribution of heavy metals in agricultural soils is affected by various anthropogenic activities and environmental factors occurring at different spatial scales. This paper introduced the two-dimensional empirical mode decomposition (2D-EMD) to separate the spatial variability in soil heavy metals into different scales. Geostatistics and multivariate analysis were also utilized to quantify their spatial structure and identify their potential influencing factors. The study was conducted in an arable land in southeastern China where 260 surface soil samples were collected and measured for total contents of cadmium (Cdtotal), mercury (Hgtotal), and sulfur (TS); pH; and soil organic carbon content (SOC). The results showed that both Cdtotal and Hgtotal had high coefficients of variation. The overall variation in all five soil variables was separated into three intrinsic mode functions (IMFs) and spatial residues. All three IMFs had short-range spatial correlations (1-8km), while the spatial residues had moderate-large spatial ranges (13-39km). IMF1 of Cdtotal was strongly correlated with IMF1 of SOC and TS, which was consistent with the principal component analysis. This indicated that IMF1 of Cdtotal represented local variations which were influenced by agricultural activities. IMFs of Hgtotal showed clustered distributions in the study area, with IMF1 and IMF2 of Hgtotal correlated in one principal component, and IMF3 of Hgtotal and IMF3 of soil pH in another component. This indicated that all three IMFs of Hgtotal might be influenced by different industrial activities or different pathways of the same industrial activities. The residues of Cdtotal and Hgtotal, representing the regional trends, only accounted for 26% of the total variance, whereas IMF1 contributed about half of the total variance. It can be concluded that agricultural activities and industrial activities were the dominant contributors of the overall variations in Cdtotal and Hgtotal in the study area, respectively.

With the increasing intelligent demand of substations, more and more machine vision technologies are applied in smart substations. This paper deals with the power cabinet door-opening state recognition based on edge feature extraction. Firstly, the substation patrol robot with machine vision is introduced, and the image acquirement and main processing flowchart including image line segment fitting of the power cabinet door-opening state is presented. Secondly, main algorithms, such as grey scale, image denoising, edge feature detection and Hough transform, used in the image feature extraction are provided. Finally, the proposed power cabinet door state recognition is implemented with real image of typical terminal box state, and the experimental results show that the proposed technology can identify the power cabinet door-opening state with accuracy as high as 99%.

Traditional two-dimensional empirical mode decomposition (2D-EMD) algorithms generate multiple subband signals, each having the same size of the original signal. Thus, huge amounts of data to be stored may be generated. Moreover, the computational load is massive as the decomposition levels increase. This paper introduces a method to reduce the data generated (i.e. reduce storage requirement) by incorporating decimation into the 2D-EMD, while maintaining perfect reconstruction. Furthermore, it is well established that traditional EMDs can be thought as having the structure of a single dyadic filter bank. The proposed algorithm is applicable into any arbitrary tree structures including octave filter banks, 2D-EMD packets when applied to a full binary tree, etc. The methodology hereby presented builds on the algorithm introduced by the authors in [8].

Pattern recognition is a key issue in the field of textile computer aided analysis and design. Focusing on the non-stationarity of the fabric texture structure, a hybrid method combining two-dimensional mode decomposition with mean shift segmentation is proposed in this paper. Two-dimensional empirical mode decomposition is an adaptive image analysing technique, which uses intrinsic spatial scales instead of predefined basis functions to decompose a given image into a number of intrinsic modes. The first intrinsic mode preserves multiple patterns for an underlying fabric image, which is subsequently submitted to the mean shift clustering process in this paper. Simulation results have proved that the proposed mean shift algorithm in empirical mode domain is in accordance with human visual effect, and possesses the capability of clustering diverse patterns inherent in the textile in a fully unsupervised way.

Partial Discharge (PD) detection in High Voltage (HV) equipment is an essential technique for assessing the insulation condition in the power system apparatus. The presence of PD is one of the critical indications for the defect and deterioration of the insulating material. Effective signal processing techniques are required to acquire, analyse, and classify PD signals into a specific fault type. The PD measurement device is prone to be affected by various noise sources, which leads to misinterpretation of the PD signal. This research focuses on developing a suitable algorithm for denoising PD signals and proposes a novel feature extraction process for classifying PD signals. The signal decomposition-based denoising algorithms in various engineering disciplines have become popular, and such techniques are being applied to PD signals. A novel PD signal denoising using adaptive decomposition, optimized by entropy and statistical parameters is proposed. Furthermore, a novel entropy-driven PD signal classification method is proposed. Initially, the PD signal is decomposed using various adaptive decomposition methods to get Intrinsic Mode Functions (IMFs). Then, IMFs are analysed using statistical or information theory measures such as Kurtosis, Mutual Information (MI) and Dispersion Entropy (DE). The IMFs are classified as noise, noise–dominant and signal IMFs, based on Kurtosis and MI values. The DE value of IMFs is used to select the regularisation parameter of Group-Sparse Total Variation (GSTV). The noise–dominant IMFs are subjected to the GSTV method, and the signal IMFs are added to the output vector to reconstruct the denoised output. The noisy IMFs are discarded for further processing. The proposed methods are applied under different input signal-noise ratios, lengths, and noise sources. The proposed denoising methods with the results and findings are presented and discussed, along with the performance metrics related to the filters. In addition, Tsallis entropy and a novel Generalized Gaussian Distribution – Refined Composite Multiscale Dispersion Entropy (GGD–RCMDE) based features are proposed for the time series signal. The suggested feature extraction methods are applied to the PD dataset to extract the features from various PD signals such as ‘corona’, ‘surface’ and ‘void’. A novel preprocessing method followed by the min-redundancy max-relevance (mRMR) feature selection method is applied to select sensitive features. A multiclass classifier model is trained using the most sensitive features to classify PD faults. The robust experimental analysis of the feature extraction method was carried out and reported. The performance metrics are computed using the results obtained through the experiments. The effectiveness of the proposed denoising and classification methods was presented with a suitable discussion and conclusion.

This paper considers the accident images and develops a deep learning method for feature extraction together with a mixture of experts for classification. For the first task, the outputs of the last max-pooling layer of a Convolution Neural Network (CNN) are used to extract the hidden features automatically. For the second task, a mixture of advanced variations of Extreme Learning Machine (ELM) including basic ELM, constraint ELM (CELM), On-Line Sequential ELM (OSELM) and Kernel ELM (KELM), is developed. This ensemble classifier combines the advantages of different ELMs using a gating network and its accuracy is very high while the processing time is close to real-time. To show the efficiency, the different combinations of the traditional feature extraction and feature selection methods and the various classifiers are examined on two kinds of benchmarks including accident images’ data set and some general data sets. It is shown that the proposed system detects the accidents with 99.31% precision, recall and F-measure. Besides, the precisions of accident-severity classification and involved-vehicle classification are 90.27% and 92.73%, respectively. This system is suitable for on-line processing on the accident images that will be captured by Unmanned Aerial Vehicles (UAV) or other surveillance systems.

To realize accurate fault diagnosis of rolling bearing under random noise, a novel fault diagnosis method based on random forest (RF) - principal component analysis (PCA) and long short-term memory (LSTM) neural network is proposed in this paper. The vibration signal is decomposed into several intrinsic mode functions (IMFs) with ensemble empirical mode decomposition (EEMD) to eliminate the random noise interference from the original vibration signal. It is vital to choose sensitive features from both the time and frequency domain of IMF components with importance rank by using RF. Then PCA is conducted to eliminate the correlation among sensitive features. On this basis, this paper utilizes LSTM neural network to get better diagnosis performance in complicated working conditions and hybrid faults. Comparing with the traditional feature extraction method, RF-PCA can get fewer but more representative characteristics. At the same time, the introduction of the LSTM neural network can provide a simple and practical resolution for rolling bearing fault diagnosis.

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.

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.

Detection of fabric defects with intertwined frame vector feature extraction

基于二维经验模态分解的五步非等步在线三维检测

Objective. The aim of this work was to study the cerebral protective effect of craniotomy hematoma removal under propofol anesthesia based on the artificial intelligence algorithm analysis of the changes in imaging characteristics of chronic subdural hematoma (CSDH) patients. Methods. A total of 60 CSDH patients who were treated in hospital were recruited and were randomly rolled into an experimental group and a control group, with 30 people in each group. Patients in the experimental group were treated with propofol anesthesia + craniotomy hematoma removal, while those in the control group were treated with conventional anesthesia + craniotomy hematoma removal. Head CT examinations were performed on the next day, one week, one month, three months, and six months after the operation. A two-dimensional empirical mode decomposition (BEMD) algorithm was used for edge detection and denoising of brain CT images of CSDH patients. Then, the amount of hematoma was calculated, and the Markwalder grading was performed to evaluate the neurological function. The number of recurrence and reoperation cases within six months of follow-up was collected. Results. 1. The quality of CT images was remarkably improved after processing with artificial intelligence algorithms. 2. The amount of hematoma in the experimental group was remarkably lower than that in the control group at January, March, and June after surgery (12.89 ± 2.12 VS 20.32 ± 16.41; 7.55 ± 4.13 VS 15.88 ± 14.22; 3.39 ± 3.79 VS 6.55 ± 3.69, P < 0.05 ). 3. The experimental group was remarkably better than the control group in Markwalder grading three months and six months after the operation ( P < 0.05 ). Conclusion. Artificial intelligence algorithm had good effect on the brain CT image processing of CSDH patients, and craniotomy hematoma removal under propofol anesthesia had an ideal brain protection effect.

Aimed at applying the sound recognition technology on the vehicle categories identification in border surveillance system, a new method of feature extraction is proposed based on the Empirical Mode Decomposition (EMD). The sound signals produced by different vehicles are important information source in the recognition system. These sound signals are decomposed by EMD, and a series of Intrinsic Mode Function (IMF) are obtained. Then the IMFs are analyzed by Fast Fourier Transform (FFT). According to the obtained amplitude spectrum of each IMF, the corresponding energy are calculated and normalized, which are regarded as feature vectors. After that, neural network is designed to recognize different types of vehicle in border surveillance. The simulation results indicate that the identification ratio grows up to 89.7% using this feature extraction method, which improves 11.7% and 1.8% by comparing with the methods based on Short Time Fourier Transform (STFT) and Wavelet Transform (WT), respectively.

Tail rotor bearing is the key components of Unmanned Aerial Vehicle (UAV) tail rotor to help the tail rotor blade to keep the balance and control the course. The previous researches about tail rotor bearing diagnosis are based on vibration, acoustic, temperature and others. However, the existing monitoring signals are easily contaminated by environment or measurement noises and fail to detect early fault with high accuracy. To overcome this challenge, this paper utilizes the ultrasound signal to monitor health condition of tail rotor bearing, and proposes an automatic feature extraction and fusion method. In our proposed method, Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) is first used decompose the ultrasound signal into several intrinsic mode functions (IMFs) containing different fault-related information. Then, we design an attention-based weight module to dynamically assign different weights to each IMFs. Finally, the weighted IMFs are fed to a CNN-based feature extraction module to perform feature learning and classification. A Unmanned Aerial vehicle (UAV) rotor simulation bench has been setup to validate the performance of our proposed method. Experimental results illustrate that the proposed approach can effectively decompose and extract the discriminative fault features of Unmanned Aerial vehicle (UAV) tail rotor bearing and achieved superior diagnosis performance.