Complex Noisy Environment Research Articles

Vein visualization enhancement by dual-wavelength phase-locked denoising technology

Visual near-infrared imaging equipment has broad applications in various fields such as venipuncture, facial injections, and safety verification due to its noncontact, compact, and portable design. Currently, most studies utilize near-infrared single-wavelength for image acquisition of veins. However, many substances in the skin, including water, protein, and melanin can create significant background noise, which hinders accurate detection. In this paper, we developed a dual-wavelength imaging system with phase-locked denoising technology to acquire vein image. The signals in the effective region are compared by using the absorption valley and peak of hemoglobin at 700[Formula: see text]nm and 940[Formula: see text]nm, respectively. The phase-locked denoising algorithm is applied to decrease the noise and interference of complex surroundings from the images. The imaging results of the vein are successfully extracted in complex noise environment. It is demonstrated that the denoising effect on hand veins imaging can be improved with 57.3% by using our dual-wavelength phase-locked denoising technology. Consequently, this work proposes a novel approach for venous imaging with dual-wavelengths and phase-locked denoising algorithm to extract venous imaging results in complex noisy environment better.

Fault Diagnosis Methods for an Artillery Loading System Driving Motor in Complex Noisy Environments

With the development of modern military technology, electrical drive technology has become a power source for modern artillery. In fault monitoring of a driving motor mounted on a piece of artillery, various sensors are susceptible to interference from the complex environment, both inside and outside the artillery itself. In this study, we creatively propose a fault diagnosis model based on an attention mechanism, the AdaBoost method and a wavelet noise reduction network to address the difficulty in obtaining high-quality motor signals in complex noisy interference environments. First, multiple fusion wavelet basis, soft thresholding, and index soft filter optimization were used to train multiple wavelet noise reduction networks that could recover sample signals under different noise conditions. Second, a convolutional neural network (CNN) classification module was added to construct end-to-end classification models that could correctly identify faults. The above basis classification models were then integrated into the AdaBoost method with an improved attention mechanism to develop a fault diagnosis model suitable for complex noisy environments. Finally, two experiments were conducted to validate the proposed method. Under motor signals with varying signal-to-noise ratios (SNRs) noises, the proposed method achieved an average accuracy of 92%, surpassing the conventional method by over 8.5%.

A vibration correction system for cold atom gravimeter

Cold atom gravimeters are used to measure the absolute value of the gravitational acceleration. To mitigate the influence of seismic noise on the mirror, a vibration correction system is used. A commercial seismometer CMG-3ESPC is employed to measure the mirror vibration. The transfer function between the mirror vibration and the output of the seismometer is regarded as a proportional element with a time delay. The best proportional element and the best time delay are obtained by minimizing the standard deviation of the fitting residuals of the interference fringe with vibration correction. This system not only exhibits excellent environmental adaptability but also eliminates the need for rough estimation of local gravitational acceleration during the vibration correction process. The system was built on the homemade cold atom gravimeter to carry out experiments in the laboratory. Compared with the measurement results without vibration correction, the standard deviation of the gravity measurement results was reduced from Gal to Gal, resulting in a significant reduction by a factor of 28.7. Meanwhile, its sensitivity was significantly improved from 330.8 to 18.0 by performing vibration correction. In the future, this system is expected to carry out comprehensive verification experiments in more complex noisy environments.

Toward a general model for the evolution of the auditory sensitivity under variable ambient noise conditionsa).

Ambient noise constrains the evolution of acoustic signals and hearing. An earlier fitness model showed that the trade-off between sound detection and recognition helps predict the best level of auditory sensitivity for acoustic communication in noise. Here, the early model is improved to investigate the effects of different noise masking conditions and signal-to-noise ratios (SNRs). It is revealed that low sensitivity is expected for acoustic communication over short distances in complex noisy environments provided missed sound recognition is costly. By contrast, high sensitivity is expected for acoustic communication over long distances in quieter habitats or when sounds are received with good SNRs under unfavorable noise conditions. High sensitivity is also expected in noisy environments characterized by one dominant source of noise with a fairly constant spectrum (running-water noise) or when sounds are processed using anti-masking strategies favoring the detection and recognition of sound embedded in noise. These predictions help explain unexpected findings that do not fit with the current view on the effects of environmental selection on signal and sensitivity. Model predictions are compared with those of models of signal detection in noisy conditions and results of empirical studies.

Objective Signal Analysis for Investigating Feasibility of Active Noise Cancellation in Hearing Screening.

With the development of active noise cancellation (ANC) technology, ANC has been used to mitigate the effects of environmental noise on audiometric results. However, objective evaluation methods supporting the accuracy of audiometry for ANC exposure to different levels of noise have not been reported. Accordingly, the audio characteristics of three different ANC headphone models were quantified under different noise conditions and the feasibility of ANC in noisy environments was investigated. Steady (pink noise) and non-steady noise (cafeteria babble noise) were used to simulate noisy environments. We compared the integrity of pure-tone signals obtained from three different ANC headphone models after processing under different noise scenarios and analyzed the degree of ANC signal correlation based on the Pearson correlation coefficient compared to pure-tone signals in quiet. The objective signal correlation results were compared with audiometric screening results to confirm the correspondence. Results revealed that ANC helped mitigate the effects of environmental noise on the measured signal and the combined ANC headset model retained the highest signal integrity. The degree of signal correlation was used as a confidence indicator for the accuracy of hearing screening in noise results. It was found that the ANC technique can be further improved for more complex noisy environments.

Low-Rank Enforced Fault Feature Extraction of Rolling Bearings in a Complex Noisy Environment: A Perspective of Statistical Modeling of Noises

The fault feature extraction of rolling element bearings is of critical interest for fault diagnosis. The fault impulses are always buried in strong and complex background noise, which makes it hard to detect the fault characteristics and further diagnose the bearing. Many feature extraction techniques have been developed, which assumed that the noise obeys a single and straightforward Gaussian distribution. However, the noise is usually non-Gaussian and cannot be characterized by a single distribution in practical industrial scenarios. A fault feature extraction model for rolling bearings within complex noise is proposed in this article, where the complex noise is modeled by the Gaussian mixture model (GMM), thus highlighting the fault characteristics. The 2-D representation of the measurement is obtained by exploiting cyclic spectral analysis. Then, the measurement is further modeled as a low-rank faulty component and a complex noise component, where the noise is characterized by the GMM. Therefore, the model is named the GMM enable low-rank (GMM-LR) model. The variational Bayes inference method is employed to estimate the posterior of the proposed model, which can obtain the optimal solution to characterize the fault characteristics. Finally, the bearing fault features are detected by the enhanced envelope spectrum (EES). Both the synthetic and experimental signals are studied to demonstrate the efficacy of the proposed technique. The superiority is also validated by comparisons with envelope spectrum (ES), cyclic spectral analysis, spectral kurtosis (SK), and robust principal component analysis (RPCA).

Low-rank Gaussian mixture modeling of space-snapshot representation of microphone array measurements for acoustic imaging in a complex noisy environment

The microphone array can simultaneously obtain the multi-dimensional information (space-time-frequency) of sound sources, which is recognized as a fundamental and powerful tool in acoustic imaging. Acoustic Beamforming is one of the widely used methods in acoustic imaging. However, most of the applications of beamforming are based on the Gaussian noise assumption, which is not always accurate in on-site measurements. For example, shock noise with a skewed probability density function (PDF) may appear on the signal record when the turbulent eddies are not controlled. Thus, in this paper, the conventional Gaussian noise model is extended to a Gaussian mixture noise model, which can approximate any probability distribution of the noise in theory. The space-snapshot representation of microphone array measurements is further modeled as a combination of the low-rank matrix part (measurements from the sound sources) and a Gaussian mixture matrix part (measurement noise). The signal from the sources of interest is finally recovered by the Expectation–maximization algorithm, which iterates between the low-rank approximation of the sound sources and the estimation of the parameter of the Gaussian mixture model. The proposed method is further investigated with simulations and compared with robust principal component analysis (RPCA) and Gaussian-based probabilistic factor analysis (PFA). It is concluded that the proposed method outperforms the state-of-the-art denoising methods.

A novel BNMF-DNN based speech reconstruction method for speech quality evaluation under complex environments

Speech quality evaluation (SQE) under complex noisy environment is important for audio processing systems and quality of service. Recently, the non-intrusive SQE is getting more and more attentive due to its efficient and ease of use. However, non-intrusive SQEs are expected to be underperformed the intrusive ones since it has no prior knowledge of the clean speech. In this paper, a novel quasi-clean speech reconstruction method for non-intrusive SQE is proposed. The method incorporates Bayesian NMF (BNMF) with deep neural network (DNN), which takes the advantages of both NMF and DNN. BNMF is utilized to calculate the basic spectro-temporal matrixes of target speech, and the obtained matrices are integrated into the DNN model as an individual layer. Then DNN is trained to learn the complex mapping between the target source and the mixture signal, and reconstruct the magnitude spectrograms of the quasi-clean speech. Finally, the reconstructed speech is regarded as the reference of the perceptual model to estimate the Mean opinion score of the tested noisy sample. The experiment results show that the proposed method outperforms the comparative non-intrusive SQE algorithms under challenging conditions in terms of objective measurement.

Deep Neural Networks for Speech Enhancement in Complex-Noisy Environments

Deep Neural Networks for Speech Enhancement in Complex-Noisy Environments

Research on the Method of De-noising the Short-wave Time Signal at Low SNR

A voice enhancement algorithm based on the Empirical Mode Decomposition (EMD) and the improved spectral subtraction is proposed for the low-SNR (Signal Noise Ratio) shortwave time signal. This method is proposed to solve the problem that the shortwave time signal cannot be used for timing in complex noisy environments. The core idea of this method is to use the Hilbert-Huang Transform (HHT) algorithm to make the empirical mode decomposition on the noisy shortwave signal, and to select the intrinsic mode functions containing the shortwave signal information for the signal reconstruction by through the maximum correlation. Then, to make the spectral subtraction on the reconstructed signal to achieve the purpose of noise reduction. The experimental result shows that this method has a better noise reduction than the traditional methods.

Collective gradient sensing in fish schools

Throughout the animal kingdom, animals frequently benefit from living in groups. Models of collective behaviour show that simple local interactions are sufficient to generate group morphologies found in nature (swarms, flocks and mills). However, individuals also interact with the complex noisy environment in which they live. In this work, we experimentally investigate the group performance in navigating a noisy light gradient of two unrelated freshwater species: golden shiners (Notemigonuscrysoleucas) and rummy nose tetra (Hemigrammus bleheri). We find that tetras outperform shiners due to their innate individual ability to sense the environmental gradient. Using numerical simulations, we examine how group performance depends on the relative weight of social and environmental information. Our results highlight the importance of balancing of social and environmental information to promote optimal group morphologies and performance.

Speech Recognition Algorithm in Complex Noisy Environments Based on Multi-Space Compensation

Speech recognition rate drops significantly when interfered by noise in complex environment. In order to improve the accuracy and the robustness of the speech recognition in adverse acoustical environments, this paper reviewed the main problems of noise robust speech recognition, proposed a multi-space compensation algorithm which from signal-space, feature-space and model-space based on wiener filter, histogram equalization and vector Taylor series. Theory analyses and experiment results show that the proposed method can overcome the defect of the sharp descent of speech recognition rate of existing speech recognition algorithm interfered by environmental noise and improve the accuracy and the robustness in adverse acoustical environments. The algorithm provides the theoretical support for the speech recognition in airport, station, wharf and other complex noise environment.

Biological edge detection for UCAV via improved artificial bee colony and visual attention

Purpose – The purpose of this paper is to propose a biological edge detection approach for aircraft such as unmanned combat air vehicle (UCAV), with the objective of making the UCAV recognize targets, especially in complex noisy environment. Design/methodology/approach – The hybrid model of saliency-based visual attention and artificial bee colony (ABC) algorithm is established for edge detection of UCAV. Visual attention can extract the region of interesting objects, and this approach can narrow the searching region for object segmentation, which can reduce the computational complexity. An improved ABC algorithm is applied in edge detection of the salient region. Findings – This work improved ABC algorithm by modifying the search strategy and adding some limits, so that it can be applied to edge detection problem. A hybrid model of saliency-based visual attention and ABC algorithm is developed. Experimental results demonstrated the feasibility and effectiveness of the proposed method: it can guarantee ef...

Robust Speech Feature Extraction Using the Hilbert Transform Spectrum Estimation Method

The performance of traditional mel-frequency cepstral coefficients (MFCC) speech feature extraction method decreases drastically in the complex noisy environment. To improve the performance and robustness of speech recognition system, which is based on spectral envelope estimation method, the minimum distortionless response spectrum MVDR-MFCC (Minimum Variance Distortionless Response-MFCC) feature extraction method was proposed. However, the computational complexity of MVDR-MFCC is very high. In this paper, we proposed MHCC (Hilbert-MFCC) feature extraction method for speech, which introduced the Hilbert transform to MFCC process. The experiments, under 8 different noisy environments, indicate that, compared with MVDR-MFCC feature extraction method, the proposed method not only reduces the algorithm’s complexity significantly, but also is less affected by noises, achieving significant improvement in the robustness—the average recognition rate across different noise types and SNRs increases by 12%.

Speech Performance and Sound Localization in a Complex Noisy Environment in Bilaterally Implanted Adult Patients

Objective: To evaluate speech performance, in quiet and noise, and localization ability in adult patients who had undergone bilateral and simultaneous implantation. Study Design: Prospective multi-center study. Methods: Twenty-seven adult patients with profound or total hearing loss were bilaterally implanted in a single-stage procedure, and simultaneously activated (Med-El, Combi 40/40+). Subjects were assessed before implantation and at 3, 6 and 12 months after switch-on. Speech perception tests in monaural and binaural conditions were performed in quiet and in noise using disyllabic words, with speech coming from the front and a cocktail party background noise coming from 5 loudspeakers. Sound localization measurements were also performed in background noise coming from 5 loudspeakers positioned from –90° to +90° azimuth in the horizontal plane, and using a speech stimulus. Results: There was a bilateral advantage at 12 months in quiet (77 ± 5.0% in bilateral condition, 67 ± 5.3% for the better ear, p < 0.005) and in noise (signal-to-noise ratio +15 dB: 63 ± 5.9% in bilateral condition, 55 ± 6.9% for the better ear, p < 0.05). Considering unilateral speech scores recorded in quiet at 12 months, subjects were categorized as ‘good performers’ (speech comprehension score ≥60% for the better ear, n = 19) and ‘poor performers’ (n = 8). Subjects were also categorized as ‘asymmetrical’ (difference between their 2 unilateral speech scores ≥20%, n = 11) or ‘symmetrical’ (n = 16). The largest advantage (bilateral compared to the better ear) was obtained in poor performers: +19% compared to +7% in good performers (p < 0.05). In the group of good performers, there was a bilateral advantage only in cases of symmetrical results between the 2 ears (n = 10). In the group of poor performers, the bilateral advantage was shown in both patients with symmetrical (n = 6) and asymmetrical results (n = 2). In bilateral conditions, the sound localization ability in noise was improved compared to monaural conditions in patients with symmetrical and asymmetrical performance between the 2 ears. No preoperative factor (age, duration of deafness, use of hearing aids, etiology, etc.) could predict the asymmetrical performance, nor which ear would be the best. Conclusion: This study demonstrates a bilateral advantage (at 12 months after the implantation) in speech intelligibility and sound localization in a complex noisy environment. In quiet, this bilateral advantage is shown in cases of poor performance of both ears, and in cases of good performance with symmetrical results between the 2 ears. No preoperative factor can predict the best candidates for a simultaneous bilateral implantation.

Interactive perception for amplification of intended behavior in complex noisy environments

The detection of a human’s intended behavior is one of the most important skills that a social robot should have in order to become acceptable as a part of human society, because humans are used to understand the actions of other humans in a goal-directed manner and they will expect the social robot to behave similarly. A breakthrough in this area can advance several research branches related to social intelligence such as learning by imitation and mutual adaptation. To achieve this goal the robot needs to integrate all possible evidence of intention and neglect the unintended behavior, and a complete solution should use low-level signal processing and high-level reasoning. This work explores the low-level signal processing part of the solution by proposing an interactive adaptive perception scheme that uses four important features of human behavior to amplify the signals originating from intended behavior with respect to signals originating from unintended behavior and other noise sources such as instrumental noise. This work follows the vision that intelligence is not only a function of a centralized sophisticated artificial brain, but can be presented in different forms in the entire robot including its perception and motion systems (the mind is not contained in the brain, but distributed in every cell in the body). A simple example of using the proposed scheme was implemented and the results of two experiments with it are also presented.