Search Results (286)

Underwater acoustic source localization is formulated as a feature learning problem within a machine learning framework, where a data-driven approach directly extracts source distance features from hydroacoustic signals. This study systematically compares the localization performance of four machine learning models—decision tree (DT), random forest (RF), support vector machine (SVM), and feedforward neural network (FNN) models—in both classification and regression tasks. Experimental results demonstrate that, in classification tasks, all algorithms achieve effective localization under high signal-to-noise ratio (SNR) conditions, while the DT model exhibits significant noise sensitivity in low-SNR scenarios; regression tasks show reduced model convergence overall, with only the SVM and RF models maintaining basic localization capabilities at a high SNR. For two-dimensional localization, machine learning classification algorithms are employed, revealing systematic accuracy degradation compared to one-dimensional scenarios, where only the RF and SVM models demonstrate practical value under high-SNR conditions. Validation using measured data from the SWellEx-96 experiment’s S5 event confirms that when constructing datasets with frequency-domain acoustic pressure features from the final 35 min segment, the classification task-driven DT, RF, and SVM models all demonstrate reliable localization performance, benefiting from the inherent high-SNR characteristics of the data. Full article

This paper proposes a rolling bearing fault diagnosis method based on HFMD and a dual-branch parallel network, aiming to address the issue of diagnostic accuracy being compromised by the disparity in data quality across different source domains due to sparse feature separation in rolling bearing acoustic signals. Traditional methods face challenges in feature extraction, sensitivity to noise, and difficulties in handling coupled multi-fault conditions in rolling bearing fault diagnosis. To overcome these challenges, this study first employs the HawkFish Optimization Algorithm to optimize Feature Mode Decomposition (HFMD) parameters, thereby improving modal decomposition accuracy. The optimal modal components are selected based on the minimum Residual Energy Index (REI) criterion, with their time-domain graphs and Continuous Wavelet Transform (CWT) time-frequency diagrams extracted as network inputs. Then, a dual-branch parallel network model is constructed, where the multi-scale residual structure (Res2Net) incorporating the Efficient Channel Attention (ECA) mechanism serves as the temporal branch to extract key features and suppress noise interference, while the Swin Transformer integrating multi-stage cross-scale attention (MSCSA) acts as the time-frequency branch to break through local perception bottlenecks and enhance classification performance under limited resources. Finally, the time-domain graphs and time-frequency graphs are, respectively, input into Res2Net and Swin Transformer, and the features from both branches are fused through a fully connected layer to obtain comprehensive fault diagnosis results. The research results demonstrate that the proposed method achieves 100% accuracy in open-source datasets. In the experimental data, the diagnostic accuracy of this study demonstrates significant advantages over other diagnostic models, achieving an accuracy rate of 98.5%. Under few-shot conditions, this study maintains an accuracy rate no lower than 95%, with only a 2.34% variation in accuracy. HFMD and the dual-branch parallel network exhibit remarkable stability and superiority in the field of rolling bearing fault diagnosis. Full article

This paper proposes a robust blind algorithm for direction of arrival (DOA) estimation in challenging acoustic environments. The method introduces a novel Time Difference of Arrival (TDOA) consensus framework that effectively identifies and filters outliers using Median and Median Absolute Deviation (MAD) statistics. By combining this consensus approach with whitening transformation and Lawson norm optimization, the algorithm achieves superior performance in noisy and reverberant conditions. Comprehensive simulations demonstrate that the proposed method significantly outperforms traditional approaches and modern alternatives such as SRP-PHAT and robust MUSIC, particularly in environments with high reverberation times and low signal-to-noise ratios. The algorithm’s robustness to impulsive noise and varying microphone array configurations is also evaluated. Results show consistent improvements in DOA estimation accuracy across diverse acoustic scenarios, with root mean square error (RMSE) reductions of up to 30% compared to standard methods. The computational complexity analysis confirms the algorithm’s feasibility for real-time applications with appropriate implementation optimizations, showing significant improvements in estimation accuracy compared to conventional approaches, particularly in highly reverberant conditions and under impulsive noise. The proposed algorithm maintains consistent performance without requiring prior knowledge of the acoustic environment, making it suitable for real-world applications. Full article

Sound source localization (SSL) adds a spatial dimension to auditory perception, allowing a system to pinpoint the origin of speech, machinery noise, warning tones, or other acoustic events, capabilities that facilitate robot navigation, human–machine dialogue, and condition monitoring. While existing surveys provide valuable historical context, they typically address general audio applications and do not fully account for robotic constraints or the latest advancements in deep learning. This review addresses these gaps by offering a robotics-focused synthesis, emphasizing recent progress in deep learning methodologies. We start by reviewing classical methods such as time difference of arrival (TDOA), beamforming, steered-response power (SRP), and subspace analysis. Subsequently, we delve into modern machine learning (ML) and deep learning (DL) approaches, discussing traditional ML and neural networks (NNs), convolutional neural networks (CNNs), convolutional recurrent neural networks (CRNNs), and emerging attention-based architectures. The data and training strategy that are the two cornerstones of DL-based SSL are explored. Studies are further categorized by robot types and application domains to facilitate researchers in identifying relevant work for their specific contexts. Finally, we highlight the current challenges in SSL works in general, regarding environmental robustness, sound source multiplicity, and specific implementation constraints in robotics, as well as data and learning strategies in DL-based SSL. Also, we sketch promising directions to offer an actionable roadmap toward robust, adaptable, efficient, and explainable DL-based SSL for next-generation robots. Full article

Acoustic Emission tomography (AET) has the potential to visualize damage in existing structures, contributing to structural health monitoring. Further, AET requires only the arrival times of elastic waves at sensors to identify velocity distributions, as source localization based on ray-tracing is integrated into its algorithm. Thus, AET offers the advantage of easy acquisition of measurement data. However, accurate source localization requires a large number of elastic wave source candidate points, and increasing these candidates significantly raises the computational resource demand. Lagrange Interpolation has the potential to reduce the number of candidate points, optimizing computational resources, and this potential has been validated numerically. In this study, AET incorporating Lagrange Interpolation is applied to identify the velocity distribution in a defective concrete plate, validating its effectiveness using measured wave data. The validation results show that the defect location in the concrete plate is successfully identified using only 36 source candidates, compared to the 121 candidates required in conventional AET. Furthermore, when using 36 source candidates, the percentage error in applying Lagrange Interpolation is 8.4%, which is significantly more accurate than the 25% error observed in conventional AET. Therefore, it is confirmed that AET with Lagrange Interpolation has the potential to identify velocity distributions in existing structures using optimized resources, thereby contributing to the structural health monitoring of concrete infrastructure. Full article

Distributed acoustic sensing shows great potential for pipeline monitoring. However, internally deployed and unfixed sensing cables are highly susceptible to disturbances from water flow noise, severely challenging impact source localization. This study proposes a novel two-step method to address this. The first step employs Variational Mode Decomposition (VMD) combined with Short-Time Energy Entropy (STEE) for the adaptive extraction of impact signal from noisy data. STEE is introduced as a stable metric to quantify signal impulsiveness and guides the selection of the relevant intrinsic mode function. The second step utilizes the Pruned Exact Linear Time (PELT) algorithm for accurate signal segmentation, followed by an unsupervised learning method combining Dynamic Time Warping (DTW) and clustering to identify the impact segment and precisely pick the arrival time based on shape similarity, overcoming the limitations of traditional pickers under conditions of complex noise. Field tests on an operational water pipeline validated the method, demonstrating the consistent localization of manual impacts with standard deviations typically between 1.4 m and 2.0 m, proving its efficacy under realistic noisy conditions. This approach offers a reliable framework for pipeline safety assessments under operational conditions. Full article

Accurate localization plays a critical role in enabling underwater vehicle autonomy. In this work, we develop a robust infrastructure-based localization framework that estimates the position and orientation of underwater vehicles using only range measurements from long baseline (LBL) acoustic beacons to multiple on-board receivers. The proposed framework integrates three key components, each formulated as a convex optimization problem. First, we introduce a robust calibration function that unifies multiple sources of measurement error—such as range-dependent degradation, variable sound speed, and latency—by modeling them through a monotonic function. This function bounds the true distance and defines a convex feasible set for each receiver location. Next, we estimate the receiver positions as the center of this feasible region, using two notions of centrality: the Chebyshev center and the maximum volume inscribed ellipsoid (MVE), both formulated as convex programs. Finally, we recover the vehicle’s full 6-DOF pose by enforcing rigid-body constraints on the estimated receiver positions. To do this, we leverage the known geometric configuration of the receivers in the vehicle and solve the Orthogonal Procrustes Problem to compute the rotation matrix that best aligns the estimated and known configurations, thereby correcting the position estimates and determining the vehicle orientation. We evaluate the proposed method through both numerical simulations and field experiments. To further enhance robustness under real-world conditions, we model beacon-location uncertainty—due to mooring slack and water currents—as bounded spherical regions around nominal beacon positions. We then mitigate the uncertainty by integrating the modified range constraints into the MVE position estimation formulation, ensuring reliable localization even under infrastructure drift. Full article

Data over sound (DoS) is an established technique that has experienced a resurgence in recent years, finding applications in areas such as contactless payments, device pairing, authentication, presence detection, toys, and offline data transfer. This study introduces CardiaWhisper, a system that extends the DoS concept to the medical domain by using a medical data-over-sound (MDoS) framework. CardiaWhisper integrates wearable biomedical sensors with home care systems, edge or IoT gateways, and telemedical networks or cloud platforms. Using a transmitter device, vital signs such as ECG (electrocardiogram) signals, PPG (photoplethysmogram) signals, RR (respiratory rate), and ACC (acceleration/movement) are sensed, conditioned, encoded, and acoustically transmitted to a nearby receiver—typically a smartphone, tablet, or other gadget—and can be further relayed to edge and cloud infrastructures. As a case study, this paper presents the real-time transmission and processing of ECG signals. The transmitter integrates an ECG sensing module, an encoder (either a PLL-based FM modulator chip or a microcontroller), and a sound emitter in the form of a standard piezoelectric speaker. The receiver, in the form of a mobile phone, tablet, or desktop computer, captures the acoustic signal via its built-in microphone and executes software routines to decode the data. It then enables a range of control and visualization functions for both local and remote users. Emphasis is placed on describing the system architecture and its key components, as well as the software methodologies used for signal decoding on the receiver side, where several algorithms are implemented using open-source, platform-independent technologies, such as JavaScript, HTML, and CSS. While the main focus is on the transmission of analog data, digital data transmission is also illustrated. The CardiaWhisper system is evaluated across several performance parameters, including functionality, complexity, speed, noise immunity, power consumption, range, and cost-efficiency. Quantitative measurements of the signal-to-noise ratio (SNR) were performed in various realistic indoor scenarios, including different distances, obstacles, and noise environments. Preliminary results are presented, along with a discussion of design challenges, limitations, and feasible applications. Our experience demonstrates that CardiaWhisper provides a low-power, eco-friendly alternative to traditional RF or Bluetooth-based medical wearables in various applications. Full article

This study introduces an algorithm for quantifying oceanic wind speed and identifying sound sources in the local underwater soundscape. Utilizing low-complexity metrics like one-minute spectral kurtosis and power spectral density levels, the algorithm categorizes different soundscapes and estimates wind speed. It detects rain, vessels, fin and blue whales, as well as clicks and whistles from dolphins. Positioned as a foundational tool for implementing the Ocean Sound Essential Ocean Variable (EOV), it contributes to understanding long-term trends in climate change for sustainable ocean health and predicting threats through forecasts. The proposed soundscape classification algorithm, validated using extensive acoustic recordings (≥32 kHz) collected at various depths and latitudes, demonstrates high performance, achieving an average precision of $89\%$ and an average recall of $86.59\%$ through optimized parameter tuning via a genetic algorithm. Here, wind speed is determined using a cubic function with power spectral density (PSD) at 6 kHz and the MASLUW method, exhibiting strong agreement with satellite data below 15 m/s. Designed for compatibility with low-power electronics, the algorithm can be applied to both archival datasets and real-time data streams. It provides a straightforward metric for ocean monitoring and sound source identification. Full article

The wind turbine blade is subject to multi-source impacts, such as bird strikes, lightning strikes, and hail, throughout its extended service. Accurate localization of those impact sources is a key technical link in structural health monitoring of the wind turbine blade. In this paper, a single-sensor impact source localization method is proposed. Capitalizing on deep learning frameworks, this method innovatively transforms the impact source localization problem into a classification task, thereby eliminating the need for anisotropy compensation and correction required by conventional localization algorithms. Furthermore, it leverages the inherent coding effects of the blade’s material and geometric anisotropy on impact sources originating from different positions, enabling localization using only a single sensor. Experimental results show that the method has a high localization accuracy of 96.9% under single-sensor conditions, which significantly reduces the cost compared to the traditional multi-sensor array scheme. This study provides a cost-effective solution for real-time detection of wind turbine blade impact events. Full article

To address the difficulty of locating small-hole leaks in buried natural gas pipelines, this study conducted a comprehensive theoretical and numerical analysis of the acoustic characteristics associated with such leakage events. A coupled flow–acoustic simulation framework was developed, integrating gas compressibility via the realizable k-ε and Large Eddy Simulation (LES) turbulence models, the Peng–Robinson equation of state, a broadband noise source model, and the Ffowcs Williams–Hawkings (FW-H) acoustic analogy. The effects of pipeline operating pressure (2–10 MPa), leakage hole diameter (1–6 mm), soil type (sandy, loam, and clay), and leakage orientation on the flow field, acoustic source behavior, and sound field distribution were systematically investigated. The results indicate that the leakage hole size and soil medium exert significant influence on both flow dynamics and acoustic propagation, while the pipeline pressure mainly affects the strength of the acoustic source. The leakage direction was found to have only a minor impact on the overall results. The leakage noise is primarily composed of dipole sources arising from gas–solid interactions and quadrupole sources generated by turbulent flow, with the frequency spectrum concentrated in the low-frequency range of 0–500 Hz. This research elucidates the acoustic characteristics of pipeline leakage under various conditions and provides a theoretical foundation for optimal sensor deployment and accurate localization in buried pipeline leak detection systems. Full article

It is vital to stabilize pillar dams in underground reservoirs in coal mine goafs to protect groundwater resources and quarry safety, practice green mining, and protect the ecological environment. Considering the actual occurrence of coal pillar dams in underground reservoirs, acoustic emission (AE) mechanical tests were performed on dry, naturally absorbed, and soaked coal samples. According to the mechanical analysis, Quantitative analysis revealed that dry samples exhibited the highest mechanical parameters (peak strength: 12.3 ± 0.8 MPa; elastic modulus: 1.45 ± 0.12 GPa), followed by natural absorption (peak strength: 9.7 ± 0.6 MPa; elastic modulus: 1.02 ± 0.09 GPa), and soaked absorption showed the lowest values (peak strength: 7.2 ± 0.5 MPa; elastic modulus: 0.78 ± 0.07 GPa). The rate of mechanical deterioration increased by ~25% per 1% increase in moisture content. It was identified that the internal crack development presented a macrofracture surface initiating at the sample center and expanding radially outward, and gradually expanding to the edges by adopting AE seismic source localization and the K-means clustering algorithm. Soaked absorption was easier to produce shear cracks than natural absorption, and a higher water content increased the likelihood. The b-value of the AE damage evaluation index based on crack development was negatively correlated with the rock damage state, and the S-value was positively correlated, and both effectively characterized it. The research results can offer reference and guidance for the support design, monitoring, and warning of coal pillar dams in underground reservoirs. (The samples were tested under two moisture conditions: (1) ‘Soaked absorption’—samples fully saturated by immersion in water for 24 h, and (2) ‘Natural absorption’—samples equilibrated at 50% relative humidity and 25 °C for 7 days). Full article

Underwater acoustic target recognition (UATR) is challenged by complex marine noise, scarce labeled data, and inadequate multi-scale feature extraction in conventional methods. This study proposes DART-MT, a semi-supervised framework that integrates a Dual Attention Parallel Residual Network Transformer with a mean teacher paradigm, enhanced by domain-specific prior knowledge. The architecture employs a Convolutional Block Attention Module (CBAM) for localized feature refinement, a lightweight New Transformer Encoder for global context modeling, and a novel TriFusion Block to synergize spectral–temporal–spatial features through parallel multi-branch fusion, addressing the limitations of single-modality extraction. Leveraging the mean teacher framework, DART-MT optimizes consistency regularization to exploit unlabeled data, effectively mitigating class imbalance and annotation scarcity. Evaluations on the DeepShip and ShipsEar datasets demonstrate state-of-the-art accuracy: with 10% labeled data, DART-MT achieves 96.20% (DeepShip) and 94.86% (ShipsEar), surpassing baseline models by 7.2–9.8% in low-data regimes, while reaching 98.80% (DeepShip) and 98.85% (ShipsEar) with 90% labeled data. Under varying noise conditions (−20 dB to 20 dB), the model maintained a robust performance (F1-score: 92.4–97.1%) with 40% lower variance than its competitors, and ablation studies validated each module’s contribution (TriFusion Block alone improved accuracy by 6.9%). This research advances UATR by (1) resolving multi-scale feature fusion bottlenecks, (2) demonstrating the efficacy of semi-supervised learning in marine acoustics, and (3) providing an open-source implementation for reproducibility. In future work, we will extend cross-domain adaptation to diverse oceanic environments. Full article

This study investigates pre-seismic ionospheric anomalies preceding the 2023 Jishishan Ms6.2 earthquake using total electron content (TEC) data derived from BDS geostationary orbit (GEO) satellites. Multi-scale analysis integrating Butterworth filtering and wavelet transforms resolved TEC disturbances into three distinct frequency regimes: (1) high-frequency perturbations (0.56–3.33 mHz) showed localized disturbances (amplitude ≤ 4 TECU, range < 300 km), potentially associated with near-field acoustic waves from crustal stress adjustments; (2) mid-frequency signals (0.28–0.56 mHz) exhibited anisotropic propagation (>1200 km) with azimuth-dependent N-shaped waveforms, consistent with the characteristics of acoustic–gravity waves (AGWs); and (3) low-frequency components (0.18–0.28 mHz) demonstrated phase reversal and power-law amplitude attenuation, suggesting possible lithosphere–atmosphere–ionosphere (LAI) coupling oscillations. The stark contrast between near-field residuals and far-field weak fluctuations highlighted the dominance of large-scale atmospheric gravity waves over localized acoustic disturbances. Geometry-based velocity inversion revealed incoherent high-frequency dynamics (5–30 min) versus anisotropic mid/low-frequency traveling ionospheric disturbance (TID) propagation (30–90 min) at 175–270 m/s, aligning with theoretical AGW behavior. During concurrent G1-class geomagnetic storm activity, spatial attenuation gradients and velocity anisotropy appear primarily consistent with seismogenic sources, providing insights for precursor discrimination and contributing to understanding multi-scale coupling in seismo-ionospheric systems. Full article

Sound source localization represents one of the major challenges for soundscapes due to the dynamicity of a large variety of signals. Many applications are found related to ecosystems to study the migration process of birds and animals other than other terrestrial environments to survey wildlife. Other applications on sound recording are supported by sensors to detect animal movement. This paper deals with the immersive 3D soundscape by using a multi-channel spherical microphone probe, in combination with a 360° camera. The soundscape has been carried out in three Italian squares across the city of Parma. The acoustic maps obtained from the data processing detect the directivity of dynamic sound sources as typical of an urban environment. The analysis of the objective environmental parameters (like loudness, roughness, sharpness, and prominence) was conducted alongside the investigations on the historical importance of Italian squares as places for social inclusivity. A dedicated listening playback is provided by the AGORA project with a portable listening room characterized by modular unit of soundbars. Full article