Narrow Results

The traditional fault detection methods for turntable bearings mainly rely on manual inspection and simple vibration signal analysis. Although these methods can detect faults to a certain extent, they have limitations such as low efficiency, low accuracy, and susceptibility to human factors. To overcome the challenges and limitations of traditional methods, we propose a fault detection method for engineering crane turntable bearings based on the adaptive fireworks algorithm (AFA). Fault detection of turntable bearing of engineering lifting machinery based on an AFA is an innovative method using the fireworks algorithm (FWA) for fault detection. FWA is a kind of optimization algorithm with global search and local search ability, which can effectively solve complex engineering problems. In the fault detection of turntable bearing of engineering lifting machinery, the FWA adaptively adjusts the radius and number of fireworks explosions, so that the algorithm can search in the global scope and detect the fault more accurately. At the same time, the FWA also has a local search ability, which can carry out fine search of the fault area and improve the accuracy of fault detection. By applying the FWA to the fault detection of turntable bearing of engineering lifting machinery, the efficiency and accuracy of fault detection can be effectively improved, the cost of fault detection can be reduced, and the safe operation of engineering lifting machinery can be guaranteed. The fault detection method of turntable bearing of engineering lifting machinery based on an AFA is an innovative method with broad application prospects and can provide an effective solution for the fault detection of engineering lifting machinery.

We proposed a gradient multi-Helmholtz cavities muffler for low-frequency broad bandgaps. The simulation and experiment results of our analysis claimed that this structure can reduce noise in resonance frequency, and the range of absorption frequency is enlarged with the number of cavities increase, almost 24.75 times that of one cavity. The transmission loss around the center frequency also increases from 45dB to 100dB. In addition, the relationship between noise attenuation and the distance of the cavities is also studied. Results show a deeper valley appears in the transmission loss curve with an increase of the distance, which greatly affects the sound absorption performance.

Speech enhancement methods differ depending on the degree of degradation and noise in the speech signal, so research in the field is still difficult, especially when dealing with residual and background noise, which is highly transient. Numerous deep learning networks have been developed that provide promising results for improving the perceptual quality and intelligibility of noisy speech. Innovation and research in speech enhancement have been opened up by the power of deep learning techniques with implications across a wide range of real time applications. By reviewing the important datasets, feature extraction methods, deep learning models, training algorithms and evaluation metrics for speech enhancement, this paper provides a comprehensive overview. We begin by tracing the evolution of speech enhancement research, from early approaches to recent advances in deep learning architectures. By analyzing and comparing the approaches to solving speech enhancement challenges, we categorize them according to their strengths and weaknesses. Moreover, we discuss the challenges and future directions of deep learning in speech enhancement, including the demand for parameter-efficient models for speech enhancement. The purpose of this paper is to examine the development of the field, compare and contrast different approaches, and highlight future directions as well as challenges for further research.

The Global Positioning System (GPS) is a network of satellites, whose original purpose was to provide accurate navigation, guidance, and time transfer to military users. The past decade has also seen rapid concurrent growth in civilian GPS applications, including farming, mining, surveying, marine, and outdoor recreation. One of the most significant of these civilian applications is commercial aviation. A stand-alone civilian user enjoys an accuracy of 100 meters and 300 nanoseconds, 25 meters and 200 nanoseconds, before and after Selective Availability (SA) was turned off. In some applications, high accuracy is required. In this paper, five Neural Networks (NNs) are proposed for acceptable noise reduction of GPS receivers timing data. The paper uses from an actual data collection for evaluating the performance of the methods. An experimental test setup is designed and implemented for this purpose. The obtained experimental results from a Coarse Acquisition (C/A)-code single-frequency GPS receiver strongly support the potential of methods to give high accurate timing. Quality of the obtained results is very good, so that GPS timing RMS error reduce to less than 120 and 40 nanoseconds, with and without SA.

To solve the problems of unit noise and vibration causing inconvenience to residents, this paper proposes a unit noise and vibration device and designs a unit noise and vibration control system. Adaptive active noise and vibration control is adopted, and DSP is used as the core of the entire system, which includes the acoustic sensor part, the peripheral signal conditioning part and the signal processing control part, so that it can achieve real-time control of unit noise and vibration. In addition, the improved independent component analysis method is used to achieve the noise reduction effect of unit noise and vibration. Finally, a unit noise and vibration detection system are designed, MEMS microphone detection is applied to achieve real-time detection of unit noise and vibration. Experiments show that the noise reduction effect of the system studied in this paper is relatively good. The vibration effect is better when the distance from the unit is 1m, and the noise value is reduced from 67dB to 48dB. Meanwhile, when the vibration distance from the unit is 22m, the noise drops to 37dB, and the noise value detected by the system in this paper is not much different from the actual noise value.

Web document ranking arises in many information retrieval (IR) applications, such as the search engine, recommendation system and online advertising. A challenging issue is how to select the representative query-document pairs and informative features as well for better learning and exploring new ranking models to produce an acceptable ranking list of candidate documents of each query. In this study, we propose an active sampling (AS) plus kernel principal component analysis (KPCA) based ranking model, viz. AS-KPCA Regression, to study the document ranking for a retrieval system, i.e. how to choose the representative query-document pairs and features for learning. More precisely, we fill those documents gradually into the training set by AS such that each of which will incur the highest expected DCG loss if unselected. Then, the KPCA is performed via projecting the selected query-document pairs onto p-principal components in the feature space to complete the regression. Hence, we can cut down the computational overhead and depress the impact incurred by noise simultaneously. To the best of our knowledge, we are the first to perform the document ranking via dimension reductions in two dimensions, namely, the number of documents and features simultaneously. Our experiments demonstrate that the performance of our approach is better than that of the baseline methods on the public LETOR 4.0 datasets. Our approach brings an improvement against RankBoost as well as other baselines near 20% in terms of MAP metric and less improvements using P@K and NDCG@K, respectively. Moreover, our approach is particularly suitable for document ranking on the noisy dataset in practice.

Spatial fluctuations in dissipative systems, such as rapid granular flows, behave very differently from those in elastic fluids. Fluctuations in the flow field drive the linear and nonlinear instability in the density field (clustering), while vortex structures appear and grow through the mechanism of noise reduction. The dynamics of the flow field on the largest space and time scales is described by diffusion equations with different diffusivities for the transverse and longitudinal flow fields. The results are obtained from analytic and simulation methods.

Semi-supervised community detection is an important research topic in the field of complex network, which incorporates prior knowledge and topology to guide the community detection process. However, most of the previous work ignores the impact of the noise from prior knowledge during the community detection process. This paper proposes a novel strategy to identify and remove the noise from prior knowledge based on harmonic function, so as to make use of prior knowledge more efficiently. Finally, this strategy is applied to three state-of-the-art semi-supervised community detection methods. A series of experiments on both real and artificial networks demonstrate that the accuracy of semi-supervised community detection approach can be further improved.

Quantum memory is an essential tool for quantum communications systems and quantum computers. An important category of quantum memory, called optically controlled quantum memory, uses a strong classical beam to control the storage and re-emission of a single-photon signal through an atomic ensemble. In this type of memory, the residual light from the strong classical control beam can cause severe noise and degrade the system performance significantly. Efficiently suppressing this noise is a requirement for the successful implementation of optically controlled quantum memories. In this paper, we briefly introduce the latest and most common approaches to quantum memory and review the various noise-reduction techniques used in implementing them.

The low-dose X-ray Computed Tomography (CT) is one of the most effective and indispensable imaging tools for clinical diagnosis. The reduced number of photons in low-dose X-ray CT imaging introduces the vulnerability towards Poisson and Gaussian noise. The majority of research till date focuses on reconstructing the images by reducing the effect of either Poisson or Gaussian noise. Thus, there is a need for a reconstruction framework that can counter the effects of both types of noises simultaneously. In this paper, an approach is proposed to handle the mixed noise (i.e. Poisson and Gaussian noises). Variational framework is utilized as energy minimization function. Minimizing the log likelihood gives data-fidelity term which portrays the distribution of noise in low-dose X-ray CT images. The problem of data-fidelity term as well as mixed noise issue in the sinogram data is resolved simultaneously by proposing a novel filter. The proposed filter modifies the Anisotropic Diffusion (AD) model based on Convolution Virtual Electric Field AD called as MADC. The modification in AD is achieved by applying fourth-order partial differential equations. To evaluate the effectiveness of the proposed MADC technique, both qualitative and quantitative evaluations are performed on three simulated test phantoms and one real standard thorax phantom of size $128\times 128$. Afterwards, the performance of the proposed technique is compared with competitive denoising techniques. The experimental results reveal that the proposed framework significantly preserves the edges of reconstructed images and introduces lesser number of gradient reversal artifacts.

Wavelet-based techniques are suitable for recovering a signal corrupted by noise. The time- and frequency-localization capabilities of wavelets provide better noise reduction and less signal distortion than conventional filtering methods. The noise reduction technique used in this paper is based on the hidden Markov model (HMM) structure, which can efficiently shape the statistical characteristics of practical data. As confirmed by numerical results, the HMM based approach provides a significant performance improvement over competing methods.

A noise reduction scheme on digitized mammographic phantom images is presented. This algorithm is based on a direct contrast modification method with an optimal function, obtained by using the mean squared error as a criterion. Computer simulated images containing objects similar to those observed in the phantom are built to evaluate the performance of the algorithm. Noise reduction results obtained on both simulated and real phantom images show that the developed method may be considered as a good preprocessing step from the point of view of automating phantom film evaluation by means of image processing.

The a priori signal-to-noise ratio (SNR) plays an essential role in many speech enhancement systems. Most of the existing approaches to estimate the a priori SNR only exploit the amplitude spectra while making the phase neglected. Considering the fact that incorporating phase information into a speech processing system can significantly improve the speech quality, this paper proposes a phase-sensitive decision-directed (DD) approach for the a priori SNR estimate. By representing the short-time discrete Fourier transform (STFT) signal spectra geometrically in a complex plane, the proposed approach estimates the a priori SNR using both the magnitude and phase information while making no assumptions about the phase difference between clean speech and noise spectra. Objective evaluations in terms of the spectrograms, segmental SNR, log-spectral distance (LSD) and short-time objective intelligibility (STOI) measures are presented to demonstrate the superiority of the proposed approach compared to several competitive methods at different noise conditions and input SNR levels.

In this paper, a new particle swarm optimization particle filter (NPSO-PF) algorithm is proposed, which is called particle cluster optimization particle filter algorithm with mutation operator, and is used for real-time filtering and noise reduction of nonlinear vibration signals. Because of its introduction of mutation operator, this algorithm overcomes the problem where by particle swarm optimization (PSO) algorithm easily falls into local optimal value, with a low calculation accuracy. At the same time, the distribution and diversity of particles in the sampling process are improved through the mutation operation. The defect of particle filter (PF) algorithm where the particles are poor and the utilization rate is not high is also solved. The mutation control function makes the particle set optimization process happen in the early and late stages, and improves the convergence speed of the particle set, which greatly reduces the running time of the whole algorithm. Simulation experiments show that compared with PF and PSO-PF algorithms, the proposed NPSO-PF algorithm has lower root mean square error, shorter running time, higher signal-to-noise ratio and more stable filtering performance. It is proved that the algorithm is suitable for real-time filtering and noise reduction processing of nonlinear signals.

Adversarial attacks can fool convolutional networks and make the systems vulnerable to fraud and deception. How to defend against malicious attacks is a critical challenge in practice. Adversarial attacks are often conducted by adding tiny perturbations on images to cause network misclassification. Noise reduction can defend the attacks; however, it is not suited for all the cases. Considering that different models have different tolerance abilities on adversarial attacks, we develop a novel detecting module to remove noise by adaptive process and detect adversarial attacks without modifying the models. Experimental results show that by comparing the classification results on adversarial samples of MNIST and two subclasses of ImageNet datasets, our models can successfully remove most of the noise and obtain detection accuracies of 97.71% and 92.96%, respectively. Furthermore, our adaptive module can be assembled into different networks to achieve detection accuracies of 70.83% and 71.96%, respectively, on the white-box adversarial attacks of ResNet18 and SCD01MLP images. The best accuracy of 62.5% is obtained for both networks when dealing with the black-box attacks.

A new shape descriptor, the high order statistical pattern spectrum (HSP), able to extract from real images a set of descriptive features which can be used to classify objects regardless of their positions, sizes, orientations and the presence of noise, has been developed. The HSP is an internal, noise-robust, noninformation-preserving operator which combines the properties of invariance of the high order pattern spectrum and the properties of noise robustness of the statistical pattern spectrum. A neural network trained by a back-propagation algorithm has been used to test the method on different classification problems. Experimental results are presented on both synthetic and real images corrupted by various levels of noise and containing an object in different positions. Comparisons with other existing shape descriptor operators have been also performed.

In multi-carrier differential chaos shift keying (MC-DCSK) system, channel noises pollute both the reference and data signals, resulting in deteriorated performance. To reduce noises in received signals in MC-DCSK, a novel noise reduction MC-DCSK (NR-MC-DCSK) system is proposed in this paper. The proposed system utilizes duplicated chaotic samples, rather than different ones, as the reference. At the receiver side, identical samples can be averaged before correlation detection, which helps decrease the noise interferences and thus brings performance improvement. Theoretical bit error rate (BER) expressions are derived and verified by simulation results for additive white Gaussian noise and multipath Rayleigh fading channels. Finally, comparisons to MC-DCSK and other DCSK-based systems are given to confirm the superiority of the proposed system in BER performance.

In this paper, a novel multi-user carrier index differential chaos shift keying (MU CI-DCSK) modulation scheme is proposed. For a better utilization of spectrum resources, each user is allocated a private subcarrier for reference signal transmission, while the remaining subcarriers are public and shared by all users to transmit their own data-bearing signals. To avoid user interferences in this design, users are distinguished in a code division multiple access (CDMA) way based on Walsh codes. By exploiting the redundancies in the transmitted signals, repeated segments of received signals are averaged, leading to greatly reduced noises and a noticeable improvement in bit error rate (BER) performance. BER expressions of this new system are derived over the additive white Gaussian noise (AWGN) and multi-path Rayleigh fading channels. Simulation results and comparisons are performed to verify the feasibility and advantages of this new scheme.

We propose a scheme to detect signals immersed in strong, externally imposed, undesirable noise (jamming) by making use of the principle of stochastic resonance. The strategy is to construct an array of simple nonlinear oscillators and to apply independent, modulating noise to each oscillator. We show that the collective effect of all oscillators and the interplay between nonlinearity and different noise sources can enhance the detectability of the original signal. For proof of principle we focus on periodic signals mixed with in-band, Gaussian jamming. In particular, we show by both extensive numerical computations and physical arguments that measures of the detectability such as the signal-to-noise ratio can be increased in our scheme. We suggest how the scheme can be implemented in laboratory experiments.

To suppress undesirable noise (jamming) associated with signals is important for many applications. Here we explore the idea of jamming suppression with realistic, aperiodic signals by stochastic resonance. In particular, we consider weak amplitude-modulated (AM), frequency-modulated (FM), and chaotic signals with strong, broad-band or narrow-band jamming, and show that aperiodic stochastic resonance occurring in an array of excitable dynamical systems can be effective to counter jamming. We provide formulas for quantitative measures characterizing the resonance. As excitability is ubiquitous in biological systems, our work suggests that aperiodic stochastic resonance may be a universal and effective mechanism for reducing noise associated with input signals for transmitting and processing information.