Search

Clustering samples based on similarity remains a significant challenge, especially when the goal is to accurately capture the underlying data clusters of complex arbitrary shapes. Existing density-based clustering techniques are known to be best suited for capturing arbitrarily shaped clusters. However, a key limitation of these methods is the difficulty in automatically finding the optimal set of parameters adapted to dataset characteristics, which becomes even more challenging when the data contain inherent noise. In our recent work, we proposed a Differential Evolution-based DENsity CLUstEring (DE-DENCLUE) to optimise DENCLUE parameters. This study evaluates DE-DENCLUE for its robustness in finding accurate clusters in the presence of noise in the data. DE-DENCLUE performance is compared against three other density-based clustering algorithms—DPC based on weighted local density sequence and nearest neighbour assignment (DPCSA), Density-Based Spatial Clustering of Applications with Noise (DBSCAN), and Variable Kernel Density Estimation–based DENCLUE (VDENCLUE)—across several datasets (i.e., synthetic and real). The study has consistently shown superior results for DE-DENCLUE compared to other models for most datasets with different noise levels. Clustering quality metrics such as the Silhouette Index (SI), Davies–Bouldin Index (DBI), Adjusted Rand Index (ARI), and Adjusted Mutual Information (AMI) consistently show superior SI, ARI, and AMI values across most datasets at different noise levels. However, in some cases regarding DBI, the DPCSA performed better. In conclusion, the proposed method offers a reliable and noise-resilient clustering solution for complex datasets. [ABSTRACT FROM AUTHOR]

Relaxation time and frequency spectra are not directly available by measurement. To determine them, an ill-posed inverse problem must be solved based on relaxation stress or oscillatory shear relaxation data. Therefore, the quality of spectra models has only been assessed indirectly by examining the fit of the experiment data to the relaxation modulus or dynamic moduli models. As the measures of data fitting, the mean sum of the moduli square errors were usually used, the minimization of which was an essential step of the identification algorithms. The aim of this paper was to determine a relaxation spectrum model that best approximates the real unknown spectrum in a direct manner. It was assumed that discrete-time noise-corrupted measurements of a relaxation modulus obtained in the stress relaxation experiment are available for identification. A modified relaxation frequency spectrum was defined as a quotient of the real relaxation spectrum and relaxation frequency and expanded into a series of linearly independent exponential functions that are known to constitute a basis of the space of square-integrable functions. The spectrum model, given by a finite series of these basis functions, was assumed. An integral-square error between the real unknown modified spectrum and the spectrum model was taken as a measure of the model quality. This index was proved to be expressed in terms of the measurable relaxation modulus at uniquely defined sampling instants. Next, an empirical identification index was introduced in which the values of the real relaxation modulus are replaced by their noisy measurements. The identification consists of determining the spectrum model that minimizes this empirical index. Tikhonov regularization was applied to guarantee model smoothness and noise robustness. A simple analytical formula was derived to calculate the optimal model parameters and expressed in terms of the singular value decomposition. A complete identification algorithm was developed. The analysis of the model smoothness and model accuracy for noisy measurements was carried out. The equivalence of the direct identification of the relaxation frequency and time spectra has been demonstrated when the time spectrum is modeled by a series of functions given by the product of the relaxation frequency and its exponential function. The direct identification concept can be applied to both viscoelastic fluids and solids; however, some limitations to its applicability have been pointed out. Numerical studies have shown that the proposed identification algorithm can be successfully used to identify Gaussian-like and Kohlrausch–Williams–Watt relaxation spectra. The applicability of this approach to determining other commonly used classes of relaxation spectra was also examined. [ABSTRACT FROM AUTHOR]

Abstract In the field of intelligent fault diagnosis, particularly concerning rotating machinery, convolutional neural networks (CNNs) face significant challenges when applied to real industrial vibration data. These data are not only contaminated by various types of noise but also exhibit fault features that vary across different scales. Consequently, the effective suppression of extraneous noise and accurate extraction of multi-scale fault features are crucial issues. To address these challenges, this study proposes a novel deep neural network framework, termed the Multidimensional Fusion Residual Attention Network (MFRANet), for gearbox fault diagnosis. The MFRANet employs a multi-scale deep separable convolution module to thoroughly investigate the fundamental characteristics of the original vibration signals in both the time and time-frequency domains. To enhance the detailed analysis of diagnostic data and mitigate the risks of overfitting and noise interference, an efficient residual channel attention module is incorporated to weight and denoise the feature maps. Additionally, an external attention module is introduced to create implicit connections between the denoised multi-scale feature maps and to highlight potential correlations within the sample data, thereby improving the accuracy of fault diagnosis. Experimental evaluations on a gearbox fault dataset demonstrate that the proposed method surpasses several benchmark and state-of-the-art techniques in terms of diagnostic performance, exhibiting robust noise resilience across various noise levels. This indicates enhanced reliability and accuracy in gearbox fault diagnosis, providing an innovative and efficient solution for fault diagnosis in rotating machinery. The study underscores the contributions of artificial intelligence through the innovative structure of the method and the integration of advanced deep learning modules, while its engineering application is evidenced by addressing practical challenges in rotating machinery fault diagnosis. This work meets the urgent need for reliable diagnostic methods in industrial environments.

The relaxation spectrum is a fundamental viscoelastic characteristic from which other material functions used to describe the rheological properties of polymers can be determined. The spectrum is recovered from relaxation stress or oscillatory shear data. Since the problem of the relaxation spectrum identification is ill-posed, in the known methods, different mechanisms are built-in to obtain a smooth enough and noise-robust relaxation spectrum model. The regularization of the original problem and/or limit of the set of admissible solutions are the most commonly used remedies. Here, the problem of determining an optimally smoothed continuous relaxation time spectrum is directly stated and solved for the first time, assuming that discrete-time noise-corrupted measurements of a relaxation modulus obtained in the stress relaxation experiment are available for identification. The relaxation time spectrum model that reproduces the relaxation modulus measurements and is the best smoothed in the class of continuous square-integrable functions is sought. Based on the Hilbert projection theorem, the best-smoothed relaxation spectrum model is found to be described by a finite sum of specific exponential–hyperbolic basis functions. For noise-corrupted measurements, a quadratic with respect to the Lagrange multipliers term is introduced into the Lagrangian functional of the model's best smoothing problem. As a result, a small model error of the relaxation modulus model is obtained, which increases the model's robustness. The necessary and sufficient optimality conditions are derived whose unique solution yields a direct analytical formula of the best-smoothed relaxation spectrum model. The related model of the relaxation modulus is given. A computational identification algorithm using the singular value decomposition is presented, which can be easily implemented in any computing environment. The approximation error, model smoothness, noise robustness, and identifiability of the polymer real spectrum are studied analytically. It is demonstrated by numerical studies that the algorithm proposed can be successfully applied for the identification of one- and two-mode Gaussian-like relaxation spectra. The applicability of this approach to determining the Baumgaertel, Schausberger, and Winter spectrum is also examined, and it is shown that it is well approximated for higher frequencies and, in particular, in the neighborhood of the local maximum. However, the comparison of the asymptotic properties of the best-smoothed spectrum model and the BSW model a priori excludes a good approximation of the spectrum in the close neighborhood of zero-relaxation time. [ABSTRACT FROM AUTHOR]

Structural damage detection is crucial for maintaining the health and safety of buildings. However, achieving high accuracy in damage detection remains challenging, especially in noisy environments. To improve the accuracy and noise robustness of damage detection, this study proposes a novel method that combines the Conformer model and the dual-channel pseudo-supervised (DCPS) learning strategy for structural damage detection. The DCPS learning strategy improves the stability and accuracy of the model in noisy environments. It enables the model to input acceleration signals with different noise levels into each branch of the dual-channel network, thereby learning noise-robust features. The Conformer model, as the backbone network, integrates the advantages of convolutional neural networks (CNNs) and Transformers to effectively extract both local and global features from acceleration signals. The proposed method is validated using a four-story single-span steel-frame building model and the IASC-ASCE simulated benchmark structure. The results show that the proposed method achieves a higher classification accuracy than existing structural damage detection methods. Compared to the single Conformer-based method, this method improves the accuracy by 1.57% and 4.93% for the two validation structures, respectively. Moreover, the proposed method benefits from the DCPS learning strategy's ability to achieve superior noise robustness compared to other methods. The proposed method holds potential value for improving the accuracy of damage detection and noise robustness in scenarios such as maintenance and extreme events. [ABSTRACT FROM AUTHOR]

Structural damage detection is of significance for maintaining the structural health. Currently, data-driven deep learning approaches have emerged as a highly promising research field. However, little progress has been made in studying the relationship between the global and local information of structural response data. In this paper, we have presented an innovative Convolutional Enhancement and Graph Features Fusion in Transformer (CGsformer) network for structural damage detection. The proposed CGsformer network introduces an innovative approach for hierarchical learning from global to local information to extract acceleration response signal features for structural damage representation. The key advantage of this network is the integration of a graph convolutional network in the learning process, which enables the construction of a graph structure for global features. By incorporating node learning, the graph convolutional network filters out noise in the global features, thereby facilitating the extraction to more effective local features. In the verification based on the experimental data of four-story steel frame model experiment data and IASC-ASCE benchmark structure simulated data, the CGsformer network achieved damage identification accuracies of 92.44% and 96.71%, respectively. It surpassed the existing traditional damage detection methods based on deep learning. Notably, the model demonstrates good robustness under noisy conditions. [ABSTRACT FROM AUTHOR]

Purpose: This study introduces an algorithm specifically designed for processing unprocessed 12-lead electrocardiogram (ECG) data, with the primary aim of detecting cardiac abnormalities. Methods: The proposed model integrates Diagonal State Space Sequence (S4D) model into its architecture, leveraging its effectiveness in capturing dynamics within time-series data. The S4D model is designed with stacked S4D layers for processing raw input data and a simplified decoder using a dense layer for predicting abnormality types. Experimental optimization determines the optimal number of S4D layers, striking a balance between computational efficiency and predictive performance. This comprehensive approach ensures the model's suitability for real-time processing on hardware devices with limited capabilities, offering a streamlined yet effective solution for heart monitoring. Results: Among the notable features of this algorithm is its strong resilience to noise, enabling the algorithm to achieve an average F1-score of 81.2% and an AUROC of 95.5% in generalization. The model underwent testing specifically on the lead II ECG signal, exhibiting consistent performance with an F1-score of 79.5% and an AUROC of 95.7%. Conclusion: It is characterized by the elimination of pre-processing features and the availability of a low-complexity architecture that makes it suitable for implementation on numerous computing devices because it is easily implementable. Consequently, this algorithm exhibits considerable potential for practical applications in analyzing real-world ECG data. This model can be placed on the cloud for diagnosis. The model was also tested on lead II of the ECG alone and has demonstrated promising results, supporting its potential for on-device application. [ABSTRACT FROM AUTHOR]

We performed uncertainty analysis and further numerical studies on the data-enabled physics-informed neural network (DEPINN). The purpose of DEPINN is to accurately and efficiently use a small amount of prior data to solve the neutron diffusion eigenvalue equations based on the physics-informed neural network. However, in practical engineering experiments, these prior data are acquired through different kinds of sensors, which are inevitably polluted by noise. Numerical results of three typical benchmark problems show that the classical DEPINN is not so robust with respect to noise. To improve the noise robustness, we propose an interval loss function to deal with the noisy prior data term; the weight of the noisy prior data term is also set to be noise dependent. Numerical results show that the proposed framework effectively enhances the robustness of DEPINN and improves the efficiency of utilizing the noisy prior data and thus promotes the engineering application of DEPINN. [ABSTRACT FROM AUTHOR]

This article describes a novel Low Voltage Noise Immune Domino Logic (LVNIDL), which can be used to create CMOS domino using Si Nanomaterials. In 32 nm nano size silicon CMOS technology, wide fan-in input domino OR gate have been proposed and have already undergone HSPICE simulation. For the transient analysis of domino gates in the simulation, a D.C supply voltage of 0.9 V and a frequency of 100 MHz are utilized. The proposed technique consumes 76.07% less power than the preceding conditional stacked keeper domino logic. Furthermore, when compared to the existing CPVT technique, the designed LVNIDL technique reduces maximum delay by 56.25%. The decrease in power consumption and propagation delay increases the energy-efficiency and speed of operation of the proposed domino logic as compared to existing techniques. The LVNIDL technique boosts the power delay product by up to 88.54% and the EDP by up to 95.31% when compared to earlier domino. This decrease shows the decrease In terms of unity noise gain (UNG), the LVNIDL technique outperforms the earlier domino by 1.09 to 1.47 times due to reduction in leakage current. This increase in UNG will make circuit more noise immune to the unwanted signals or glitches which is a major issue in existing domino techniques. The stand-by power consumption in the proposed technique shows a maximum reduction of 98.29% as compared to existing techniques which indicates improvement in battery life under idle condition. [ABSTRACT FROM AUTHOR]

An Automatic Speech Recognition (ASR) System is a software tool that converts a speech audio waveform into its corresponding text transcription. ASR systems are usually built using Artificial Intelligence techniques, particularly Machine Learning algorithms like Deep Learning, to address the multi-faceted complexity and variability of human speech. This allows these systems to learn from extensive speech datasets, adapt to several languages and accents, and continuously improve their performance over time, making them each time more versatile and effective in their purpose of transcribing spoken language to text. Much in the same way, we argue that the noises commonly present in the different environments also need to be explicitly dealt with, and, when possible, modeled within specific datasets with proper training. Our motivation comes from the observation that noise removal techniques (commonly called denoising), are not always fully (and generically) efficient. For instance, noise degeneration due to communication interference, which is almost always present in radio transmissions, has peculiarities that a simple mathematical formulation cannot model. This work presents a modeling technique composed of an augmented dataset-building approach and a profile identifier that can be used to build ASRs for noisy environments that perform similarly to those used in noise-free environments. As a case study, we developed a specific ASR for the interference noise in radio transmissions with its specific dataset, while comparing our results with other state-of-the-art work. As a result, we report a Character Error Rate value of 0.3163 for the developed ASR under several different noise conditions.

This paper proposes a Multi-scale Dilated Variational Graph Convolutional Autoencoder (MG-VAE) model for gas turbine fault diagnosis. The model integrates a multi-scale dilated convolutional attention mechanism to extract features across different scales, enhancing its ability to represent complex data and improving robustness in noisy environments. Additionally, a graph convolution module captures correlations between sensors, further enhancing diagnostic accuracy. Experimental results demonstrate the model’s effectiveness, achieving high diagnostic accuracy in both gear fault simulation and real gas turbine fault datasets. Ablation experiments show that the integration of the graph convolutional network and the multi-scale dilated convolutional attention mechanism significantly improves accuracy, highlighting the model’s potential for practical industrial applications in gas turbine fault diagnosis.

Clustering samples based on similarity remains a significant challenge, especially when the goal is to accurately capture the underlying data clusters of complex arbitrary shapes. Existing density-based clustering techniques are known to be best suited for capturing arbitrarily shaped clusters. However, a key limitation of these methods is the difficulty in automatically finding the optimal set of parameters adapted to dataset characteristics, which becomes even more challenging when the data contain inherent noise. In our recent work, we proposed a Differential Evolution-based DENsity CLUstEring (DE-DENCLUE) to optimise DENCLUE parameters. This study evaluates DE-DENCLUE for its robustness in finding accurate clusters in the presence of noise in the data. DE-DENCLUE performance is compared against three other density-based clustering algorithms—DPC based on weighted local density sequence and nearest neighbour assignment (DPCSA), Density-Based Spatial Clustering of Applications with Noise (DBSCAN), and Variable Kernel Density Estimation–based DENCLUE (VDENCLUE)—across several datasets (i.e., synthetic and real). The study has consistently shown superior results for DE-DENCLUE compared to other models for most datasets with different noise levels. Clustering quality metrics such as the Silhouette Index (SI), Davies–Bouldin Index (DBI), Adjusted Rand Index (ARI), and Adjusted Mutual Information (AMI) consistently show superior SI, ARI, and AMI values across most datasets at different noise levels. However, in some cases regarding DBI, the DPCSA performed better. In conclusion, the proposed method offers a reliable and noise-resilient clustering solution for complex datasets.

Copyright of Proceedings of the YSU A: Physical & Mathematical Sciences is the property of Publishing House of Yerevan State University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Structural damage detection is crucial for maintaining the health and safety of buildings. However, achieving high accuracy in damage detection remains challenging, especially in noisy environments. To improve the accuracy and noise robustness of damage detection, this study proposes a novel method that combines the Conformer model and the dual-channel pseudo-supervised (DCPS) learning strategy for structural damage detection. The DCPS learning strategy improves the stability and accuracy of the model in noisy environments. It enables the model to input acceleration signals with different noise levels into each branch of the dual-channel network, thereby learning noise-robust features. The Conformer model, as the backbone network, integrates the advantages of convolutional neural networks (CNNs) and Transformers to effectively extract both local and global features from acceleration signals. The proposed method is validated using a four-story single-span steel-frame building model and the IASC-ASCE simulated benchmark structure. The results show that the proposed method achieves a higher classification accuracy than existing structural damage detection methods. Compared to the single Conformer-based method, this method improves the accuracy by 1.57% and 4.93% for the two validation structures, respectively. Moreover, the proposed method benefits from the DCPS learning strategy’s ability to achieve superior noise robustness compared to other methods. The proposed method holds potential value for improving the accuracy of damage detection and noise robustness in scenarios such as maintenance and extreme events.

Structural damage detection is of significance for maintaining the structural health. Currently, data-driven deep learning approaches have emerged as a highly promising research field. However, little progress has been made in studying the relationship between the global and local information of structural response data. In this paper, we have presented an innovative Convolutional Enhancement and Graph Features Fusion in Transformer (CGsformer) network for structural damage detection. The proposed CGsformer network introduces an innovative approach for hierarchical learning from global to local information to extract acceleration response signal features for structural damage representation. The key advantage of this network is the integration of a graph convolutional network in the learning process, which enables the construction of a graph structure for global features. By incorporating node learning, the graph convolutional network filters out noise in the global features, thereby facilitating the extraction to more effective local features. In the verification based on the experimental data of four-story steel frame model experiment data and IASC-ASCE benchmark structure simulated data, the CGsformer network achieved damage identification accuracies of 92.44% and 96.71%, respectively. It surpassed the existing traditional damage detection methods based on deep learning. Notably, the model demonstrates good robustness under noisy conditions.

This article addresses the challenges of selecting robust classifiers with increasing noise levels in real-world scenarios. We propose the WB Score methodology, which enables the identification of reliable classifiers for deployment in noisy environments. The methodology addresses four significant challenges that are commonly encountered: (i) Ensuring classifiers possess robustness to noise; (ii) Overcoming the difficulty of obtaining representative data that captures real-world noise; (iii) Addressing the complexity of detecting noise, making it challenging to differentiate it from natural variations in the data; and (iv) Meeting the requirement for classifiers capable of efficiently handling noise, allowing prompt responses for decision-making. WB Score provides a comprehensive approach for classifier assessment and selection to address these challenges. We analyze five classic datasets and one customized flooding dataset in São Paulo. The results demonstrate the practical effect of using the WB Score methodology is the enhanced ability to select robust classifiers for datasets in noisy real-world scenarios. Compared with similar techniques, the improvement centers around providing a visual and intuitive output, enhancing the understanding of classifier resilience against noise, and streamlining the decision-making process.

This paper proposes a noise-robust and accurate bearing fault diagnosis model based on time-frequency multi-domain 1D convolutional neural networks (CNNs) with attention modules. The proposed model, referred to as the TF-MDA model, is designed for an accurate bearing fault classification model based on vibration sensor signals that can be implemented at industry sites under a high-noise environment. Previous 1D CNN-based bearing diagnosis models are mostly based on either time domain vibration signals or frequency domain spectral signals. In contrast, our model has parallel 1D CNN modules that simultaneously extract features from both the time and frequency domains. These multi-domain features are then fused to capture comprehensive information on bearing fault signals. Additionally, physics-informed preprocessings are incorporated into the frequency-spectral signals to further improve the classification accuracy. Furthermore, a channel and spatial attention module is added to effectively enhance the noise-robustness by focusing more on the fault characteristic features. Experiments were conducted using public bearing datasets, and the results indicated that the proposed model outperformed similar diagnosis models on a range of noise levels ranging from −6 to 6 dB signal-to-noise ratio (SNR). [ABSTRACT FROM AUTHOR]

This article addresses the challenges of selecting robust classifiers with increasing noise levels in real-world scenarios. We propose the WB Score methodology, which enables the identification of reliable classifiers for deployment in noisy environments. The methodology addresses four significant challenges that are commonly encountered: (i) Ensuring classifiers possess robustness to noise; (ii) Overcoming the difficulty of obtaining representative data that captures real-world noise; (iii) Addressing the complexity of detecting noise, making it challenging to differentiate it from natural variations in the data; and (iv) Meeting the requirement for classifiers capable of efficiently handling noise, allowing prompt responses for decision-making. WB Score provides a comprehensive approach for classifier assessment and selection to address these challenges. We analyze five classic datasets and one customized flooding dataset in São Paulo. The results demonstrate the practical effect of using the WB Score methodology is the enhanced ability to select robust classifiers for datasets in noisy real-world scenarios. Compared with similar techniques, the improvement centers around providing a visual and intuitive output, enhancing the understanding of classifier resilience against noise, and streamlining the decision-making process. [ABSTRACT FROM AUTHOR]

Local binary pattern (LBP) is widely used in texture classification fields because of its low computational cost and invariance to environmental changes. There are two essential steps in LBP: the texture feature extraction step and the texture feature classification step. However, in the texture feature extraction step, all existing LBP-based methods with fixed sampling radius R cannot obtain multi-scale texture features. Furthermore, at present, the texture feature classification step cannot efficiently use multi-scale texture features as well. To overcome these two main drawbacks, we propose a novel adaptive two-stage selection strategy in local binary pattern. There are totally three steps in our proposed adaptive two-stage selection (ATSS) strategy: the preprocessing step, the adaptive first-stage selection step and the second-stage selection step. In the preprocessing step, the ATSS strategy uses Gaussian kernel to obtain down-sampled multi-scale texture images. In the adaptive first-stage selection step, the ATSS strategy uses the low-complexity original LBP to off-line extract a small number of large-scale texture features from down-sampled texture images. The top T training images which have more similar large-scale texture features with the testing image are adaptively selected to go to the next step. In the second-stage selection step, the ATSS strategy uses the original LBP and LBP-based variants separately to off-line extract a large number of small-scale texture features from the original testing images and the selected top T original training images. Hence, the finally selected top 1 training image has most similar both small-scale and large-scale texture features with the testing image. Comparing with original LBP-based methods, after introducing our adaptive two-stage selection (ATSS) strategy, the training images with only similar small-scale texture structures but different large-scale texture structures can be excluded after the adaptive first-stage selection step. Hence, the classification accuracy of LBP-based methods can be significantly improved. Furthermore, it is worth noting that our proposed adaptive two-stage selection (ATSS) strategy can be straightforwardly utilized in any other LBP-based variants to enhance their classification performance. Extensive experiments are conducted on four standard texture databases, Outex, UIUC, CUReT and XU_HR. The experimental results of seven representative LBP-based methods, LBP, LTP, CLBP, BRINT, CLBC, LNDP and CMPE show that our proposed ATSS strategy can significantly improve their classification accuracy and robustness against noise corruption. [ABSTRACT FROM AUTHOR]

In this paper, a noise-robust method is proposed for infrared small target detection. In the proposed method, according to the differences between the real targets and the noise, a suitable filter is provided to enhance the target. The proposed method is named Branch Local Contrast Measure (BLCM). This small target detection method is designed to ignore noisy pixels in IR images. In the experiment, 431 IR images with small dim targets containing various sources of false response have been used to evaluate the effectiveness of the proposed method. The results demonstrate that the BLCM method outperforms the other state of the arts for small target detection in the noisy image. [ABSTRACT FROM AUTHOR]

In recent years, significant progress has been made in deep model-based automatic speech recognition (ASR), leading to its widespread deployment in the real world. At the same time, adversarial attacks against deep ASR systems are highly successful. Various methods have been proposed to defend ASR systems from these attacks. However, existing classification based methods focus on the design of deep learning models while lacking exploration of domain specific features. This work leverages filter bank-based features to better capture the characteristics of attacks for improved detection. Furthermore, the paper analyses the potentials of using speech and non-speech parts separately in detecting adversarial attacks. In the end, considering adverse environments where ASR systems may be deployed, we study the impact of acoustic noise of various types and signal-to-noise ratios. Extensive experiments show that the inverse filter bank features generally perform better in both clean and noisy environments, the detection is effective using either speech or non-speech part, and the acoustic noise can largely degrade the detection performance.

Copyright of Journal of Computer-Aided Design & Computer Graphics / Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao is the property of Gai Kan Bian Wei Hui and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

For circuit-based quantum computation, experimental implementation of a universal set of quantum logic gates with high-fidelity and strong robustness is essential and central. Quantum gates induced by geometric phases, which depend only on global properties of the evolution paths, have built-in noise-resilience features. Here, we propose and experimentally demonstrate nonadiabatic holonomic single-qubit quantum gates on two dark paths in a trapped 171Yb+ ion based on four-level systems with resonant drives. We confirm the implementation with measured gate fidelity through both quantum process tomography and randomized benchmarking methods. Meanwhile, we find that nontrivial holonomic two-qubit quantum gates can also be realized within current experimental technologies. Compared with previous implementations, our experiments share both the advantages of fast nonadiabatic evolution and robustness against systematic errors. Therefore, our experiments confirm a promising method for fast and robust holonomic quantum computation.

Local binary pattern (LBP) plays a crucial part in texture classification. Although plenty of LBP-based methods for texture extraction have achieved good classification results, most LBP variants focus on the relationships between the neighboring pixels and its central pixel in an image patch whereas ignoring the information among neighboring pixels, making the extracted texture descriptors not robust enough to external changes (illumination, rotation, noise, etc.). In this paper, a new texture descriptor, the extended local grouped order and non-local binary pattern (ELGONBP) is introduced. Firstly, we propose a first-order difference coding scheme which is based on the sign difference to encode grouped neighborhood difference information. In this way, we can obtain a more complete representation among neighboring sampling points. To further promote the robustness of texture descriptor, we perform cross-image domain information fusion, which combines the texture information in the original image domain and the gradient domain since image gradients contain rich structural information. Comprehensive experiments are implemented on four public representative texture databases and the noise robustness of different descriptors is evaluated. The experimental results prove that the presented ELGONBP descriptor has better classification performance and noise robustness compared with other state-of-the-art LBP descriptors. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Guangdong University of Technology is the property of Journal of Guangdong University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Radar ground target recognition technology is an important technical base for intellectualization and informatization of radar seeker of air-to-ground missile. Recently, ground target recognition technology has been paid much attention by researchers. However, with the increasingly fierce offensive and defensive confrontation in modern war, the application of radar ground target recognition technology is facing many problems, which has become a bottleneck factor restricting the development of weapons for a long time. To ensure that relevant radar practitioners better understand the development and future trend of this field, this paper introduces the conception of radar target recognition technology, and summarizes the technical difficulties of radar ground target recognition for equipment application. Afterwards, the research status at home and abroad are reviewed. Finally, the development trend of this technology is prospected.

One persistent challenge in Speech Emotion Recognition (SER) is the ubiquitous environmental noise, which frequently results in deteriorating SER performance in practice. In this paper, we introduce a Two-level Refinement Network, dubbed TRNet, to address this challenge. Specifically, a pre-trained speech enhancement module is employed for front-end noise reduction and noise level estimation. Later, we utilize clean speech spectrograms and their corresponding deep representations as reference signals to refine the spectrogram distortion and representation shift of enhanced speech during model training. Experimental results validate that the proposed TRNet substantially promotes the robustness of the proposed system in both matched and unmatched noisy environments, without compromising its performance in noise-free environments. • We propose a novel speech recognition algorithm that leverages speech enhancement for noise level estimation. • We design both low-level feature compensation and high-level representation calibration to promote the noise robustness. • The proposed method can achieve superior performance in both noisy and noise-free environments. [ABSTRACT FROM AUTHOR]

Establishing the relationships among hierarchical visual attributes of objects in the visual world is crucial for human cognition. The classic convolution neural network (CNN) can successfully extract hierarchical features but ignore the relationships among features, resulting in shortcomings compared to humans in areas like interpretability and domain generalization. Recently, algorithms have introduced feature relationships by external prior knowledge and special auxiliary modules, which have been proven to bring multiple improvements in many computer vision tasks. However, prior knowledge is often difficult to obtain, and auxiliary modules bring additional consumption of computing and storage resources, which limits the flexibility and practicality of the algorithm. In this paper, we aim to drive the CNN model to learn the relationships among hierarchical deep features without prior knowledge and consumption increasing, while enhancing the fundamental performance of some aspects. Firstly, the task of learning the relationships among hierarchical features in CNN is defined and three key problems related to this task are pointed out, including the quantitative metric of connection intensity, the threshold of useless connections, and the updating strategy of relation graph. Secondly, Relational Embedding Convolution (RE-Conv) layer is proposed for the representation of feature relationships in convolution layer, followed by a scheme called use & disuse strategy which aims to address the three problems of feature relation learning. Finally, the improvements brought by the proposed feature relation learning scheme have been demonstrated through numerous experiments, including interpretability, domain generalization, noise robustness, and inference efficiency. In particular, the proposed scheme outperforms many state-of-the-art methods in the domain generalization community and can be seamlessly integrated with existing methods for further improvement. Meanwhile, it maintains comparable precision to the original CNN model while reducing floating point operations (FLOPs) by approximately 50%. [ABSTRACT FROM AUTHOR]

Inverse problems of contact heat conduction with an interfacial heat source are common in various fields of science, engineering and technology. In this study, an algorithm for their solution is developed based on an inverse parametric optimisation method with an impulse response function describing the heat partition and contact heat transfer. A first-order thermocouple model with a time constant parameter is embedded in the impulse response function. The specific power of the heat source is sought in the form of a polynomial from the condition of least-squares deviation of the simulated temperature from the temperature samples obtained by a thermocouple. Compared to the classical methods of simple inverse convolution and sequential function specification, the algorithm proves to be accurate in a substantially larger region of variation of the heating duration and time constant, covering slow-response thermocouple measurements. Additionally, the algorithm is significantly more robust against noise with a sufficient number of temperature samples. The applicability of the algorithm is demonstrated by solving inverse problems of contact heat conduction typical for sliding friction, laser and electric resistance welding at different thermal contact conditions and ratios of the time constant to the heating duration. • The proposed algorithm solves inverse problems of contact heat conduction. • The algorithm is accurate for slow-response thermocouple measurements. • The algorithm is noise robust with a sufficient number of temperature samples. [ABSTRACT FROM AUTHOR]

This paper proposes a noise-robust and accurate bearing fault diagnosis model based on time-frequency multi-domain 1D convolutional neural networks (CNNs) with attention modules. The proposed model, referred to as the TF-MDA model, is designed for an accurate bearing fault classification model based on vibration sensor signals that can be implemented at industry sites under a high-noise environment. Previous 1D CNN-based bearing diagnosis models are mostly based on either time domain vibration signals or frequency domain spectral signals. In contrast, our model has parallel 1D CNN modules that simultaneously extract features from both the time and frequency domains. These multi-domain features are then fused to capture comprehensive information on bearing fault signals. Additionally, physics-informed preprocessings are incorporated into the frequency-spectral signals to further improve the classification accuracy. Furthermore, a channel and spatial attention module is added to effectively enhance the noise-robustness by focusing more on the fault characteristic features. Experiments were conducted using public bearing datasets, and the results indicated that the proposed model outperformed similar diagnosis models on a range of noise levels ranging from −6 to 6 dB signal-to-noise ratio (SNR).

As a special imaging technique, one of the most important advantages of single-pixel imaging (SPI) than conventional imaging method is that it can recover the object image even through turbid medium. In these situations, the noises bring by the turbid medium usually obey special rules in statistics. While in some other applications, SPI is performed in the environment with complicate ambient light, in which no prior information of the environment noise is known. Aiming at this situation, in this work, the frame-by-frame subtraction-based compressive sensing SPI (FFS-CSPI) method with random 0/1 pattern is used to decrease the effect from the unknown ambient light. The noise robustness of the FFS-CSPI method is analyzed and compared with Hadamard CSPI. In simulation and experiment, two kinds of noises, from external light source and from background video, are considered. The results prove that FFS-CSPI with random 0/1 patterns can achieve higher image quality than conventional mean subtraction method and Hadamard CSPI with the same measurement number. Considering the high refresh rate of digital micromirror device when it loads the 0/1 binary patterns, the imaging speed is acceptable. This work will promote the practical applications of SPI in complicated environment.

Multiple damage detection using structural responses only is a problem unresolved that is in the field of structural health monitoring. To address this problem, a novel feature of mechanics-driven statistical moments of wavelet transform-processed dynamic responses is proposed for multi-damage identification in beam-type structures. This feature is referred to as a continuous wavelet transform (CWT)-second-order strain statistical moment (SSSM), with CWT-SSSM in the abbreviation. The mechanical connotation of CWT-SSSM lies in that the SSSM of each order principal vibration contains strain mode shapes, inducing greater sensitivity to local damage. With this method, the CWT is used to extract and amplify the singularities caused by damage in each order SSSM curve, following which the data fusion technology and three-sigma rule in statistics are adopted to construct the damage index. The presence of damage is characterized by the abrupt change in the damage index. The soundness and characteristics of the CWT-SSSM feature are verified by identifying multiple damages in a cantilever beam bearing two breathing cracks. The results show that the proposed feature can accurately designate multiple cracks free of baseline information on the intact counterpart; moreover, it has robustness against noise and applicability under excitations of approximately uniform spectra. [ABSTRACT FROM AUTHOR]

In this work, we focus on real-time 3D reconstruction or localization and mapping for outdoor scene using an aerial vehicle called quadcopter. Quadcopter provides the advantages of high flexibility and wide view field in spatial movement. However, existing feature-based and direct methods (using dense or semi-dense approach) are not suitable for outdoor environment, in which multiple challenging scenarios arise such as lighting variance, jittering views, high-speed and non-smooth flight trajectory. The main reason is that the existing methods rely on the assumption of brightness constancy across multiple images and only raw pixel intensities are employed for direct image alignment. In order to tackle these scenarios, a novel method called Feature-based Direct Tracking and Mapping (FDTAM) is proposed, which i) incorporates an efficient binary feature descriptor into direct image alignment module to tackle the challenging scenarios, such as drifting issue under lighting variance problem; ii) applies semi-dense approach to obtain high reconstruction quality; iii) provides a framework with low computational complexity for real-time reconstruction. Compared to other state-of-the-art feature-based and direct methods, our proposed method is shown to tackle the challenging scenarios and improve the accuracy and robustness even in CPU (rather than GPU) platform. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Remote Sensing is the property of Editorial Office of Journal of Remote Sensing & Science Publishing Co. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This manuscript discusses the robustness to noise of deep learning models for two audio classification tasks. The first task is a speaker recognition application, trying to identify five different speakers. The second one is a speech command identification where the goal is to classify ten voice commands. These two tasks are very important to make the communication between humans and smart devices as smooth and natural as possible. The emergence of smart home devices such as personal assistants and the deployment of audio based applications in noisy environments raise new challenges and reveal the weaknesses of existing speech recognition systems. Despite the advances of deep learning in audio tasks, most of the proposed architectures are computationally inefficient and very sensitive to noise. This research addresses these problems by proposing two neural architectures that incorporate a novel pooling operation, named entropy pooling. Entropy pooling is based on the principle of maximum entropy. A detailed ablation study is conducted to evaluate the performance of entropy pooling against the classic max and average pooling layers. The neural networks that are developed are based on two architectures, convolutional networks and residual ones. The study shows that entropy based feature pooling improves the robustness of these architectures in the presence of noise. [ABSTRACT FROM AUTHOR]

The concept of intuitionistic fuzzy set has been found to be highly useful to handle vagueness in data. Based on intuitionistic fuzzy set theory, intuitionistic fuzzy clustering algorithms are proposed and play an important role in image segmentation. However, due to the influence of initialization and the presence of noise in the image, intuitionistic fuzzy clustering algorithm cannot acquire the satisfying performance when applied to segment images corrupted by noise. In order to solve above problems, a robust intuitionistic fuzzy clustering with bias field estimation (RIFCB) is proposed for noisy image segmentation in this paper. Firstly, a noise robust intuitionistic fuzzy set is constructed to represent the image by using the neighboring information of pixels. Then, initial cluster centers in RIFCB are adaptively determined by utilizing the frequency statistics of gray level in the image. In addition, in order to offset the information loss of the image when constructing the intuitionistic fuzzy set of the image, a new objective function incorporating a bias field is designed in RIFCB. Based on the new initialization strategy, the intuitionistic fuzzy set representation, and the incorporation of bias field, the proposed method preserves the image details and is insensitive to noise. Experimental results on some Berkeley images show that the proposed method achieves satisfactory segmentation results on images corrupted by different kinds of noise in contrast to conventional fuzzy clustering algorithms. [ABSTRACT FROM AUTHOR]

As an important part of rotating machinery, gear is easy to appear some unexpected fault states, and its fault diagnosis is very important. Fourier decomposition method (FDM) is a common method for gear fault diagnosis, but the noise robustness, period recognition, and extraction capabilities of FDM are unsatisfactory. Based on this, in this article, Ramanujan Fourier mode decomposition (RFMD) method is proposed. The RFMD not only has a complete mathematical theory foundation but also has an excellent ability to identify and extract periodic components. Emulational and experimental results of planetary gearbox show that the RFMD method has good noise robustness and can accurately extract gear fault characteristic information. Thus, it is an effective gear fault diagnosis method. [ABSTRACT FROM AUTHOR]

Joint spectrum cartography and disaggregation from sparse spatial observations has been proven to be theoretically feasible based on block-term tensor decomposition (BTD) model. However, the existing BTD framework suffers from inherent drawbacks in terms of numerical stability, complexity and noise robustness. To combat with these drawbacks, we propose a new Constrained-BTD (CBTD) framework in this letter by fully utilizing practical traits of geographical power density spectrum (PSD) and spatial loss field (SLF). The cornerstone of CBTD framework is formulating the joint PSD and SLF estimation as a constrained matrix factorization problem, instead of addressing the factors of multi-linear rank-BTD. Further, a projection gradient-based (PG) algorithm, which has sublinear convergence, is proposed to handle the restrictions of PSD and SLF by projection on manifolds. Compared with the baseline methods, simulations verify that the proposed approach obtains better performances in terms of stability, complexity and noise robustness. [ABSTRACT FROM AUTHOR]

Real-world datasets commonly have noisy labels, which negatively affects the performance of deep neural networks (DNNs). In order to address this problem, we propose a label noise robust learning algorithm, in which the base classifier is trained on soft-labels that are produced according to a meta-objective. In each iteration, before conventional training, the meta-training loop updates soft-labels so that resulting gradients updates on the base classifier would yield minimum loss on meta-data. Soft-labels are generated from extracted features of data instances, and the mapping function is learned by a single layer perceptron (SLP) network, which is called MetaLabelNet. Following, base classifier is trained by using these generated soft-labels. These iterations are repeated for each batch of training data. Our algorithm uses a small amount of clean data as meta-data, which can be obtained effortlessly for many cases. We perform extensive experiments on benchmark datasets with both synthetic and real-world noises. Results show that our approach outperforms existing baselines. The source code of the proposed model is available at https://github.com/gorkemalgan/MetaLabelNet. [ABSTRACT FROM AUTHOR]