Noise Interference Problem Research Articles

Feature Extraction Method Based on Filter Banks and Riemannian Tangent Space in Motor-Imagery BCI.

Optimal feature extraction for multi-category motor imagery brain-computer interfaces (MI-BCIs) is a research hotspot. The common spatial pattern (CSP) algorithm is one of the most widely used methods in MI-BCIs. However, its performance is adversely affected by variance in the operational frequency band and noise interference. Furthermore, the performance of CSP is not satisfactory when addressing multi-category classification problems. In this work, we propose a fusion method combining Filter Banks and Riemannian Tangent Space (FBRTS) in multiple time windows. FBRTS uses multiple filter banks to overcome the problem of variance in the operational frequency band. It also applies the Riemannian method to the covariance matrix extracted by the spatial filter to obtain more robust features in order to overcome the problem of noise interference. In addition, we use a One-Versus-Rest support vector machine (OVR-SVM) model to classify multi-category features. We evaluate our FBRTS method using BCI competition IV dataset 2a and 2b. The experimental results show that the average classification accuracy of our FBRTS method is 77.7% and 86.9% in datasets 2a and 2b respectively. By analyzing the influence of the different numbers of filter banks and time windows on the performance of our FBRTS method, we can identify the optimal number of filter banks and time windows. Additionally, our FBRTS method can obtain more distinctive features than the filter banks common spatial pattern (FBCSP) method in two-dimensional embedding space. These results show that our proposed method can improve the performance of MI-BCIs.

Automatic Expansion of Voltage Signals Using Empirical Mode Decomposition for Voltage Sag Detection

Voltage sag is one of the most harmful power quality issues. In practical engineering, harmonic interference and noise interference problems will bring big challenges to the analysis of voltage signals. These disturbances can easily lead to a delay or even false detection of the voltage signal. To address this problem, adaptive processing and diagnosis methods of the voltage signal, such as the Empirical Mode Decomposition (EMD) and the Variational Mode Decomposition (VMD), have become a research hotspot. In order to overcome the interference of voltage harmonic and achieve rapid voltage sag detection, this paper first analyzes the performance of EMD and VMD in decomposing voltage sag signals. Then, a tailored EMD-based adaptive voltage signal expansion method for real-time voltage sag detection is proposed. The sampling voltage signal is automatically expanded using the real-time voltage signal to achieve the rapid detection of voltage sag under complex operational environments. Numerical results illustrate the effectiveness of the proposed method.

The Application of Machine Learning ICA-VMD in an Intelligent Diagnosis System in a Low SNR Environment.

This paper proposes a new method called independent component analysis–variational mode decomposition (ICA-VMD), which combines ICA and VMD. The purpose is to study the application of ICA-VMD in low signal-to-noise ratio (SNR) signal processing and data analysis. ICA is a very important method in the field of machine learning. It is an unsupervised learning algorithm that can dig out the independent factors hidden in the observation signal. The VMD method estimates each signal component by solving the frequency domain variational optimization problem, and it is very suitable for mechanical fault diagnosis. The advantage of ICA-VMD is that it requires two sensory cues to distinguish the original source from the unwanted noise. In the three cases studied here, the original source was first contaminated by white Gaussian noise. The three cases in this study are under different SNR conditions. The SNR in the first case is –6.46 dB, the SNR in the second case is –21.3728, and the SNR in the third case is –46.8177. The simulation results show that the ICA-VMD method can effectively recover the original source from the contaminated data. It is hoped that, in the future, there will be new discoveries and advances in science and technology to solve the noise interference problem through this method.

Power quality disturbance classification under noisy conditions using adaptive wavelet threshold and DBN-ELM hybrid model

To solve the problems of noise interference and artificial feature extraction in power quality disturbance (PQD) classification, a new method combining adaptive wavelet threshold denoising and deep belief network fusion extreme learning machine (DBN-ELM) is proposed. Firstly, the noise content of the layer is determined by calculating the energy ratio of the wavelet coefficients of each layer, and an adaptive wavelet threshold is constructed based on the energy ratio to denoise the PQD signals. Secondly, the feature extraction capability of DBN is used to extract the feature from the PQD signals after denoising. Finally, a novel PQD classifier called DBN-ELM is constructed by integrating an ELM into a DBN, which avoids global fine-tuning of DBN and improves PQD classification efficiency. The simulation result and experimental verification show that the proposed method can effectively suppress PQD noise and performs well on DBN-ELM classification.

An estimation model for cross temperature measuring in blast furnace ironmaking

ABSTRACT The cross temperature measuring device is applied to monitor the top temperature and gas flow distribution in the blast furnace (BF) during the ironmaking process. However, the temperature of the BF roof is relatively high, which causes damage to the cross temperature measuring device. Therefore, this paper proposes an efficient estimation method. First of all, the data filtering method are used to solve the problems of noise interference. Moreover, as the fact that BF cross temperature measurement is affected by interference factors, it is easy to cause information redundancy. Aiming at this, the maximum information coefficient (MIC) correlation analysis and sequence dislocation method are used to determine the input variables and its action time of the model. Finally, an estimation model based three-layer long and short-term memory network (LSTM3) is established. The experimental results show that the LSTM3 can estimate the centre temperature of cross temperature measuring device.

Research on the method of underwater image enhancement

A multi-angle image enhancement method based on underwater imaging was proposed to solve the problems of color bias, geometric distortion and low contrast of the observed object in the complex and changeable underwater environment. Firstly, the gray world algorithm is used to preprocess the underwater image. Then an image optimization denoising algorithm based on K-SVD dictionary learning is used to keep the structure and texture information of the original image. Finally, combining with the underwater optical imaging model, the blue-green channel enhancement algorithm is used to realize the underwater imaging defog processing, which makes the restored image closer to the reality. The results show that this method can solve the problems of noise interference, fuzzy underwater image and low contrast.

Iris Localization Algorithm based on Effective Area

Iris localization is the most crucial part of the iris processing because its accuracy can directly affect the accuracy of biometric identification in subsequent steps. Yet, the quality of iris images may be sharply degraded due to interference from eyelashes and reflections during image acquisition, which can affect the localization accuracy adversely. To solve the problem, an iris localization algorithm based on effective area is proposed. First, YOLOv4 is used to crop the image to obtain the effective iris area, which is beneficial in improving the accuracy of subsequent localization. Furthermore, a method to remove reflective noise is proposed, which can effectively avoid the problem of noise interference in the process of inner boundary determination. Finally, aiming at the edge deviation caused by eyelashes, an outer boundary adjustment method is proposed. The experimental results show that the proposed method achieves good performance in the localization of iris images of both good quality and noise interference and outperforms other state-of-the-art methods.

Females and males respond differently to calls impaired by noise in a tree frog.

Both human and nonhuman animals communicating acoustically face the problem of noise interference, especially anurans during mating activities. Previous studies concentrated on the effect of continuous noise on signal recognition, but it is still unknown whether different notes in advertisement calls impaired by noise affect female choice and male–male competition or not. In this study, we tested female preferences and male‐evoked vocal responses in serrate‐legged small tree frog (Kurixalus odontotarsus), by broadcasting the five‐note advertisement call and the advertisement call with the second, third, or fourth note replaced by noise, respectively. In phonotaxis experiments, females significantly discriminated against the advertisement call with the fourth note impaired by noise, although they did not discriminate against other two calls impaired by noise, which indicates that the negative effect of noise on female preference is related to the order of impaired notes in the advertisement call. In playback experiments, males increased the total number of notes in response to noise‐impaired calls compared with spontaneous calls. More interestingly, the vocal responses evoked by noise‐impaired calls were generally similar to those evoked by complete advertisement calls, suggesting that males may recognize the noise‐impaired calls as complete advertisement calls. Taken together, our study shows that different notes in advertisement calls replaced by noise have distinct effects on female choice and male–male competition.

Research on the Application of Visual Maps Based on CiteSpace in Speech Technology

In recent years, deep learning has been widely used in the field of speech technology, and provides people with an efficient and convenient way of obtaining information and communicating in most application scenarios. This paper uses CiteSpace information visualization software to visually analyze the speech technology research literature based on nearly 10,000 papers in the field of speech technology research and application from 2013 to 2021. From the perspective of bibliometrics, this paper analyzes the distribution of hotspots and research frontiers in speech technology research in countries, institutions, disciplines and other information visualization maps, and compares and analyzes the literature information in the field of speech technology research and application at home and abroad in recent years. The research results show that the main disadvantages of speech technology at home and abroad are: the inability to completely avoid noise interference; the inability to correctly identify ambiguous and generalized sentences; and the inability to idealize the radio remotely. Aiming at the problem of noise interference, this paper proposes a deep learning-based noise reduction algorithm and increases the number of convolutions of the neural network to improve the model; then, for the ambiguity and generalization in the recognition process, this paper proposes a deep learning-based unsupervised training method; Finally, for the problems of sound reception and echo, this paper proposes a far-field sound pickup technology based on multi-channel signal microphone collection.

A new method of power quality disturbance classification based on deep belief network

In view of the low accuracy of single disturbances under the problem of noise interference, a new method of power quality disturbance classification based on deep belief network was proposed. A smooth wavelet multiscale transform is performed on the power quality disturbance signal, and then the soft threshold function is used to process the estimated wavelet coefficients for reconstructing the original signal. Further, it is proposed to use deep confidence network to classify and recognize the reconstructed single disturbance signal. The simulation results demonstrate that the recognition rate of this method for seven typical single disturbances is high. Even under 20dB noise interference, the classification accuracy rate is as high as 93% or more, which proves that the method has a strong ability to resist noise interference.

3D Virtual Animation Instant Network Communication System Design

This project uses Openfire to implement a virtual 3D animation instant messaging system, which is easier to use and more expandable. The main work of the client is to implement the Extensible Messaging and Presence Protocol (XMPP) and use XMPP to transmit data to the server side and receive data from the server side, while Openfire is built by the server side to use. To address the problem that the current mainstream face key point localization model is less robust to complex environments, this project adopts a deep learning‐based approach to design and implement the face key point localization model, through data preprocessing, model design, and model training, to achieve a robust model that can locate 68 face key points and complete the migration of the model to mobile. The current video communication often suffers from delay and lag, so this project uses face key point data instead of video stream data transmission to reduce the pressure on the network. This topic also uses voice coding and decoding, noise reduction, echo cancellation, and other processing to solve the problems of noise interference and echo interference in voice transmission. This paper also introduces the creation, import, and loading of 3D virtual models, and explains how to use face key point association to drive 3D animation models, how to make the drive smoother and more natural, and using individual face key points as an example.

Recognition for Human Gestures Based on Convolutional Neural Network Using the Off‐the‐Shelf Wi‐Fi Routers

Human gestures have been considered as one of the important human‐computer interaction modes. With the fast development of wireless technology in urban Internet of Things (IoT) environment, Wi‐Fi can not only provide the function of high‐speed network communication but also has great development potential in the field of environmental perception. This paper proposes a gesture recognition system based on the channel state information (CSI) within the physical layer of Wi‐Fi transmission. To solve the problems of noise interference and phase offset in the CSI, we adopt a model based on CSI quotient. Then, the amplitude and phase curves of CSI are smoothed using Savitzky‐Golay filter, and the one‐dimensional convolutional neural network (1D‐CNN) is used to extract the gesture features. Then, the support vector machine (SVM) classifier is adopted to recognize the gestures. The experimental results have shown that our system can achieve a recognition rate of about 90% for three common gestures, including pushing forward, left stroke, and waving. Meanwhile, the effects of different human orientation and model parameters on the recognition results are analyzed as well.

Development status, problems and solutions of speech recognition technology

The purpose of automatic speech recognition technology is to enable the machine to “understand” human voice, and convert human voice into text information, which is the key technology to realize human-computer interaction. This paper briefly introduces the development of speech recognition technology and the acoustic model involved, analyzes the problems of noise interference in the environment, the low recognition rate of dialect speech, and the need to improve the speech recognition effect in the far-field environment, and puts forward solutions such as optimizing the acoustic model, building dialect corpus, accurately modeling the sound transmission environment, the future development is prospected.

Electromagnetic Noise Suppression of Magnetic Resonance Sounding Combined with Data Acquisition and Multi-Frame Spectral Subtraction in the Frequency Domain

As an advanced groundwater detection method, magnetic resonance sounding (MRS) has received more and more attention. However, the biggest challenge is that MRS measurements always suffer with a bad signal-to-noise ratio (SNR). Aiming at the problem of noise interference in MRS measurement, we propose a novel noise-suppression approach based on the combination of data acquisition and multi-frame spectral subtraction (DA-MFSS). The pure ambient noise from the measurement area is first collected by the receiving coil, and then the noisy MRS signal is recorded following the pulse moments transmitting. The procedure of the pure noise and the noisy MRS signal acquisition will be repeated several times. Then, the pure noise and the noisy signal are averaged to preliminarily suppress the noise. Secondly, the averaged pure noise and the noisy signal are divided into multiple frames. The framed signal is transformed into the frequency domain and the spectral subtraction method is applied to further suppress the electromagnetic noise embedded in the noisy MRS signal. Finally, the de-noised signal is recovered by the overlap-add method and inverse Fourier transformation. The approach was examined by numerical simulation and field measurements. After applying the proposed approach, the SNR of the MRS data was improved by 16.89 dB and both the random noise and the harmonic noise were well suppressed.

Measurement of sound velocity in oil wells based on fast adaptive median filtering

Measurement of sound velocity in oil wells has long been a challenging industrial issue due to the difficulty in obtaining clear oil pipe coupling waves in strong noise. In this paper, a novel sound velocity measurement method is developed for the dynamic liquid level of oil wells based on fast adaptive median filtering. First, to solve the noise interference problem in the reflected oil pipe coupling wave, a fast adaptive median filtering algorithm is proposed to obtain an accurate oil pipe coupling wave. Then a curve fitting method based on range discrete coefficient is developed to estimate the sound velocity in the tubing-casing annular space of oil wells. The fitting sound velocity can reflect the propagation rule of the real sound velocity. In particular, the sound velocity at any position within the tubing-casing annular space can be accurately calculated by the fitting function. Finally, the proposed method is applied to the dynamic liquid level of an oil well. Experimental results show the effectiveness and favorable accuracy in estimating the sound velocity distribution.

Improved Classification Method Based on the Diverse Density and Sparse Representation Model for a Hyperspectral Image.

To solve the small sample size (SSS) problem in the classification of hyperspectral image, a novel classification method based on diverse density and sparse representation (NCM_DDSR) is proposed. In the proposed method, the dictionary atoms, which learned from the diverse density model, are used to solve the noise interference problems of spectral features, and an improved matching pursuit model is presented to obtain the sparse coefficients. Airborne hyperspectral data collected by the push-broom hyperspectral imager (PHI) and the airborne visible/infrared imaging spectrometer (AVIRIS) are applied to evaluate the performance of the proposed classification method. Results illuminate that the overall accuracies of the proposed model for classification of PHI and AVIRIS images are up to 91.59% and 92.83% respectively. In addition, the kappa coefficients are up to 0.897 and 0.91.

A weak fault feature extraction of rolling element bearing based on attenuated cosine dictionaries and sparse feature sign search

The time domain signal of bearing pitting/spalling fault always presents shock and modulation, and it is often submerged by strong noises, especially in the early stage. the conventional fault feature extraction method may have insufficient feature extraction accuracy, and even in some extreme cases, the fault feature frequency cannot be extracted because of the strong noise interference. Aiming at overcoming the noise interference problem encountered in this kind of weak fault feature extraction, a novel weak fault feature extraction algorithm termed as ACFSS of rolling bearing is proposed. The ACFSS is based on an overcomplete dictionary (or overcomplete atomic library) of Attenuated Cosines(AC) basis, which is highly matched to the bearing fault waveforms, and an improved Basis Pursuit algorithm with Feature Sign Search(FSS) is introduced into the ACFSS to improve the calculating speed. In order to select the suitable parameters of the attenuated cosine dictionary, some methods such as peak resonance frequency (PRF), power variation peak (PVK), time shift parameter (TSP), etc. are introduced. These parameters span the sparse overcomplete dictionary. Finally, the bearing fault data of Case-Western University and full life accelerated IMS bearing data are utilized to verify the validation of ACFSS. Compared with the ordinary envelope spectrum analysis(ESA) method /the ordinary Basis Pursuit Denoising(BPDN) method/ Wavelet package transform(WPT) Kurtogram method and Empirical Mode Decomposition(EMD) combining Singular Value Decomposition(SVD) method, The experiment show that the proposed method are more redundant and robust when facing strong noise interference, and it can be used to extract the weak fault feature frequency efficiently and accurately.

Research on power quality disturbance identification and classification technology in high noise background

In order to solve the problem of noise interference in power quality disturbance identification, a new method of multiresolution hyperbolic S-transform for noise abatement based on energy density is proposed. First, multiresolution hyperbolic S-transform is performed on the power quality disturbance signal. This method combines suitable time-frequency resolution with good noise suppression performances. Second, the transient disturbance time-frequency domain is determined according to the fluctuation energy density. By using a mean time-frequency filter, the interference of the noise in the non-transient disturbance time-frequency domain with signals is eliminated, and the noise in the non-signal time-frequency domain is suppressed. Then, the signal time-frequency domain is determined according to the energy density, and the noise in the non-signal time-frequency domain is further suppressed by the denoising time-frequency filter. The characteristic curve is extracted from the complex matrix module after the noise abatement. Finally, a time-frequency database of tree structure is established. The dynamic time warping distance query classification method is used for quick classification according to the relationship of membership degree, which reduces the number of queries and improves the recognition accuracy. The classification result shows the effectiveness of the algorithm in high noise background and the applicability in actual fields.

Dynamic liquid level detection method based on resonant frequency difference for oil wells

The dynamic liquid level of an oil well can be used to determine the oil production strategies and analyze the reservoir performance. Therefore, it is important to measure the dynamic liquid level in an oil field. This paper proposes a novel dynamic liquid level measurement method for oil wells, where the resonant frequency difference (RFD) of the resonant acoustic signal in annular is used to calculate the dynamic liquid level. To solve the noise interference problem in the resonant acoustic signal, a spectral fast Fourier transform (FFT) method based on Welch power spectrum is proposed to obtain the RFD. First, the Welch power spectrum approach is employed to process the resonant acoustic signal, and a high-pass filter is designed to filter the inherent envelope of low frequency in the power spectrum. In particular, a clear and smooth power spectrum can be obtained by choosing a suitable window and a sectional length. Furthermore, the short-time Fourier transform method is used to extract the strongest energy spectrum of the power spectrum. Finally, the RFD of two adjacent resonant harmonics can be accurately obtained by using FFT for the strongest energy spectrum. Experimental results show the effectiveness of the proposed approach.

Flow Watermarking for Antinoise and Multistream Tracing in Anonymous Networks

To solve the problems of noise interference and multistream tracing in anonymous network tracing, this article proposes an interval packet-size-based spread spectrum (IPS3) network flow watermarking technology, which adopts a new watermarking carrier based on the original direct sequence spread spectrum (DSSS) technology. On one hand, IPS3 solves the problem of multistream tracing through the operation of DSSS for original watermarking. On the other hand, taking the average packet size in a time interval as the watermarking carrier, it solves the problem of network flow watermarking technology being subjected to the network stability by adjusting the carrier size in the process of watermarking modulation. Experimental results show that the proposed IPS3 scheme outperforms the traditional network flow watermarking technology in the above-mentioned two issues: noise filtering and multistream tracing, which can achieve higher accuracy when it is used in anonymous network tracing. This article is part of a special issue on cybersecurity.