Search Results (14,035)

Accidental crushing by sows is the primary cause of pre-weaning piglet mortality in intensive production, often due to the spatiotemporal lag of manual inspection. While Internet of Things (IoT) solutions exist, they frequently face challenges such as vision occlusion, high hardware costs, and latency. To address these, this study developed a low-cost multi-modal edge computing system based on TinyML. Using an ESP32-S3 microcontroller, the system employs a “Motion-Gated Acoustic Detection” strategy, activating a lightweight 1D-CNN model to identify piglet screams only when an IMU detects high-risk postural transitions of the sow. Results show the quantized model (5.1 KB) achieves 95.56% accuracy and 2 ms inference latency. The total end-to-end response latency is within 179 ms, ensuring intervention within the early “golden rescue window.” The low-power design enables the battery life to cover the entire lactation period. Field tests demonstrated that the system intercepted identified crushing risks within the monitored cohort, supporting its potential for significantly improving piglet survival probability. This research overcomes the limitations of single-modal monitoring and provides a scalable, cost-effective engineering intervention for enhancing animal welfare and achieving intelligent, unattended supervision in precision livestock farming. Full article

Background/Objectives: Multimodal depression detection research has traditionally relied on early or hybrid fusion strategies without systematically analyzing how dynamic fusion mechanisms interact with modality-specific pretraining. Although gated and attention-based architectures are increasingly adopted, their behavior is rarely examined within a structured fusion taxonomy framework. Methods: In this study, we conduct a controlled taxonomy-level evaluation of multimodal fusion strategies in a Japanese PHQ-9-annotated depression dataset. We compare four fusion paradigms (concatenation, summation, gated fusion, and cross-attention) across three integration stages, crossed with modality-specific affective pretraining configurations for visual (CMU-MOSI/MOSEI), acoustic (JTES), and textual (WRIME) encoders, yielding 512 experimental conditions. Results: The results reveal strong position-dependent effects of fusion strategy. Cross-attention fusion at the audio integration stage achieved the highest mean AUC (0.774) and PR-AUC (0.606), with statistically significant superiority over gated and concatenation-based fusion (Kruskal–Wallis $H=86.28$, $p<0.001$). In contrast, fusion effects at the text stage were non-significant in AUC but significant in PR-AUC, highlighting metric-sensitive behavior under class imbalance. Pretraining effects were modality-specific: SigLIP initialization produced significant positive transfer $(\Delta =+0.018,p<0.001)$, whereas audio pretraining on JTES resulted in negative transfer $(\Delta =-0.014,p=0.004)$, suggesting domain mismatch effects. Gate analysis further revealed condition-dependent modality dominance, including cases of semantic–geometric reversal under joint auxiliary augmentation. Conclusions: Our findings suggest that multimodal depression detection systems should not be interpreted through static fusion categories alone. Instead, modality contribution appears to be associated with structured interaction effects between fusion strategy, integration position, and affective pretraining. This work provides a controlled empirical bridge between fusion taxonomy and dynamic modality weighting in clinical multimodal modeling. Full article

This study presents a comprehensive multi-parameter analysis of seismo-ionospheric responses to the Mw 7.7 Myanmar earthquake on 28 March 2025, using GNSS-based Total Electron Content (TEC) data, seismic b-value trends, and acoustic gravity wave (AGW) signatures. A significant negative TEC anomaly (~30 TECU below the statistical threshold) was detected on 25 March, three days before the mainshock under geomagnetically quiet conditions, indicating a lithospheric origin. Concurrent variations in the Ionospheric Disturbance Index (IDI) and Rate of TEC Index (ROTI) indicate pronounced background departures and enhanced short-term variability during the preparation phase. Temporal b-value analysis shows a consistent decline from 1.12 to 0.58 across the 30-year to 6-month windows, with the lowest values clustering near the epicenter, indicating progressive stress accumulation. Spatial b-value mapping further reveals a low b-value zone overlapping the region of TEC depletion, while the Relative Seismic Hazard Index (RSHI) highlights high-hazard zones aligned with the epicentral area. Kernel density estimation (KDE) supports this coupling by showing a dominant low-b, low-vTEC cluster, consistent with linked lithospheric stress and ionospheric depletion. Overall, the integrated GNSS and seismic analyses demonstrate the value of multi-domain observations for characterizing earthquake preparation processes, highlighting a coherent physical linkage between crustal stress accumulation and ionospheric depletion that can enhance short-term seismic hazard assessment. Full article

This study presents a high-frequency ultrasound lens system that uses simply fabricated and low-cost acoustic lenses made from PMMA and PDMS materials. These lenses are designed for higher-frequency operation around 20 MHz, providing suitability for demanding high-frequency ultrasonic applications. They were designed and fabricated specifically for integration with a PMUT array, ensuring proper compatibility with array-based high-frequency ultrasonic imaging. Both Fresnel and convex lens designs were evaluated through axial and lateral beam measurements, along with pulse–echo testing in the focal region. The results show that the PMMA and PDMS lenses can produce a well-defined focus and a stable echo response despite their simple and low-cost fabrication. This demonstrates the feasibility of low-cost materials for high-frequency ultrasonic focusing in PMUT array applications. Full article

We investigated the effect of film thickness d on the acoustic response of titanium dioxide (TiO₂) layers deposited on Ti, SiO₂, Al₂O₃, and Si substrates. For each TiO₂ thickness–substrate pair, we computed reflection coefficients and acoustic signatures under normal operating conditions of a conventional scanning acoustic microscope, then deduced the Rayleigh-wave velocity V_R from spectral analysis of the oscillatory layer–substrate signatures. As d increased, V_R either rose or fell, depending on the layer/substrate pair, and eventually approached a saturation value. For TiO₂/SiO₂ and TiO₂/Ti, V_R increased from those of the bare substrates (SiO₂: 3415 m/s; Ti: 2965 m/s) toward 3830 m·s⁻¹, the bulk TiO₂ value. For TiO₂/Al₂O₃ and TiO₂/Si, V_R decreased from the substrate values (Al₂O₃: 5700 m/s; Si: 4712 m/s) toward the same TiO₂ saturation. These dispersion trends are consistent with stiffening (V_R (TiO₂) > V_R (Substrate)) or loading (V_R (TiO₂) < V_R (Substrate)) effects. The resulting V_R–d dispersion charts provide theoretical reference trends relating thickness and Rayleigh-wave velocity for the idealized TiO₂/substrate systems considered here. Full article

Against the global carbon neutrality target, predictive maintenance (PdM) of automotive engines represents a core technical strategy to advance the sustainable development of the automotive industry. Conventional single-modal diagnostic approaches for engine abnormal sound defects suffer from low accuracy and weak anti-interference capability. Existing multi-modal fusion methods fail to deeply mine the physical coupling between cross-modal features and often entail excessive model complexity, hindering deployment on resource-constrained on-board edge devices. To resolve these limitations, this study proposes a Physical Prior-Embedded Cross-Modal Attention (PPE-CMA) mechanism for lightweight multi-modal fusion diagnosis of engine abnormal sound defects. First, wavelet packet decomposition (WPD) and mel-frequency cepstral coefficients (MFCC) are integrated to extract time-frequency features from engine audio signals, while a channel-pruned ResNet18 is employed to extract spatial features from engine thermal imaging and vibration visualization images. Second, the PPE-CMA module is designed to adaptively assign attention weights to audio and image features by exploiting the physical coupling between engine fault acoustic and visual characteristics, enabling efficient cross-modal feature fusion with redundant information suppression. A rigorous theoretical derivation is provided to link cosine similarity with the physical correlation of engine fault acoustic-visual features, justifying the attention weight constraint (β = 1 − α) from the perspective of fault feature physical coupling. Third, an improved lightweight XGBoost classifier is constructed for fault classification, and a hybrid data augmentation strategy customized for engine multi-modal data is proposed to address the small-sample challenge in industrial applications. Ablation experiments on ResNet18 pruning ratios verify the optimal trade-off between diagnostic performance and computational efficiency, while feature distribution analysis validates the authenticity and effectiveness of the hybrid augmentation strategy. Experimental results on a self-constructed multi-modal dataset show that the proposed method achieves 98.7% diagnostic accuracy and a 98.2% F1-score, retaining 96.5% accuracy under 90 dB high-level environmental noise, with an end-to-end inference speed of 0.8 ms per sample (including preprocessing, feature extraction, and classification). Cross-engine and cross-domain validation on a 2.0T diesel engine small-sample dataset and the open-source SEMFault-2024 dataset yield average accuracies of 94.8% and 95.2%, respectively, demonstrating strong generalization. This method effectively enhances the accuracy and robustness of engine abnormal sound defect diagnosis, offering a lightweight technical solution for on-board real-time fault diagnosis and in-plant online quality inspection. By reducing engine fault-induced energy loss and spare parts waste, it further promotes energy conservation and emission reduction in the automotive industry. Quantified experimental data on fuel efficiency improvement and carbon emission reduction are provided to substantiate the ecological benefits of the proposed framework. Full article

Although high-frequency electromagnetic methods, such as Radio Magnetotellurics (RMT) and Controlled-Source Radio Magnetotellurics (CSRMT), are highly effective for shallow-to-medium depth exploration, deploying traditional transmitter–receiver setups remains labor-intensive and significantly slows down large-scale surveys. To overcome these logistical bottlenecks, we developed a mobile Ultra-Audio Frequency Electromagnetic (UAEM) measurement system. While the hardware is designed with dual-mode capabilities supporting conventional controlled-source operations, this paper specifically focuses on its application in a Signals of Opportunity (SOOP) mode. By utilizing pre-existing, stable anthropogenic signals, including Amplitude Modulation (AM) broadcasts and naval very low frequency communications, the system effectively functions as a broadband RMT receiver. Technical evaluations demonstrate that the instrument operates across a 1 Hz to 1000 kHz bandwidth with a high sampling rate of 2.5 MHz. Furthermore, it achieves a dynamic range of 143 dB and maintains an apparent resistivity measurement accuracy of better than 3%. Thanks to its modular, vehicle-towed design, the UAEM system enables continuous, on-the-move data acquisition wherever ambient field sources are available. This approach eliminates the need for dedicated transmitter deployment, fundamentally reducing exploration costs and boosting overall survey efficiency. Full article

Vertical docking of the autonomous underwater shuttle (AUS) for deep-sea data relay relies heavily on ultra-short baseline (USBL) acoustic positioning, whose measurements can be intermittently unavailable and contaminated by outliers in complex underwater environments. This paper proposes a neural network-enhanced robust navigation framework to improve AUS navigation reliability during acoustically guided vertical docking under USBL outages. First, a model-aided batch maximum a posteriori trajectory estimation method (MA-BMAP) is developed to generate learning quality supervision under sensor-limited conditions. Based on the estimated trajectories, a long short-term memory (LSTM)-based horizontal velocity predictor is integrated into a robust fusion filter with online ocean current estimation, enabling stable state estimation during USBL outages and robust rejection of abnormal USBL measurements. The proposed framework is validated through simulations and field trials in lake and sea environments. In sea trials, during two representative 200 s USBL outage intervals, the end-of-window horizontal position errors are 7.86 m and 4.14 m, respectively, corresponding to AUS-to-docking station distances of 244 m and 51 m. In addition, the introduced USBL outliers are successfully detected and rejected. The results indicate that the proposed method enables accurate and stable navigation during USBL unavailability and rapid recovery once USBL measurements resume, demonstrating its practicality for vertical docking missions. Full article

Access control systems rely increasingly on multimodal biometric and behavioral signals to enhance security and robustness against sophisticated attacks. However, when heterogeneous modalities provide conflicting evidence, such as valid biometric credentials accompanied by abnormal behavioral or acoustic patterns, traditional fusion strategies based on static thresholds or majority voting often fail, leading to false alarms or insecure authorization decisions. This paper addresses this critical limitation by proposing a contextual decision-making fusion framework designed to resolve conflicting multimodal evidence at the decision-making level. The proposed approach models access control as a decision-making problem in a context of uncertainty, where independent agents generate modality-specific evidence from authentication channels based on face, voice, and fingerprints. A centralized fusion mechanism integrates heterogeneous results using adaptive reliability weighting and contextual reasoning to resolve conflicts before operational decisions are made. Rather than treating each modality independently, the framework explicitly considers inconsistencies, uncertainties, and situational context when aggregating evidence. The framework is evaluated using public benchmarks, including VGGFace2, VoxCeleb2, and FVC2004, combined with controlled multimodal scenarios that induce conflicting evidence. Experimental results obtained under controlled contradiction scenarios show that the proposed fusion strategy reduces false alarms and improves decision consistency by approximately 18%. These results are interpreted within the scope of controlled multimodal simulations. Full article

Acoustic microactuation technology has emerged as an effective approach for fabrication of micro- and nanoscale objects, enabling precise processing and shaping control of microscale materials by efficiently transmitting ultrasonic vibration energy and focusing energy locally. In this work, the proposed platform is regarded as an acoustically driven micromachine, in which ultrasonic excitation acts as the primary microactuation mechanism. Micrometer-scale copper wires are widely used in microelectronics and precision manufacturing. However, their small dimensions and low rigidity make fixation and forming particularly challenging. To achieve controllable forming of fine copper wires, this study introduces an ultrasonic vibration energy-focusing principle and investigates an ultrasonic post-processing method tailored for such materials, with the aim of enhancing processing stability and forming accuracy. An ultrasonic processing experimental platform for copper wires was established, and multiple micro-tool designs—including glass fiber, 304 stainless steel wire with support, and elastic hard 304 stainless steel—were evaluated. Single-point and continuous processing experiments were conducted by varying micro-tool materials and support configurations, and the influence of feed speed on processing width and depth was systematically analyzed. The results indicate that a hard 304 stainless steel micro-tool supported by a hard plastic ring provides the best overall performance. Feed speed has a significant effect on processing depth, with a maximum average depth of approximately 0.95 μm achieved at a feed speed of 1 mm/min. These findings demonstrate the feasibility of ultrasonic processing for the effective forming of fine copper wires and confirm that appropriate micro-tool design and feed speed are critical for achieving stable and reliable processing results. The proposed system employs an ultrasonically actuated micro-tool to perform post-processing on micrometer-scale copper wires. The ultrasonic vibration serves as a microactuation mechanism that enhances local deformation and material response during micro-machining. Full article

Underwater acoustic sensor networks (UASNs) have emerged as a pivotal technology for ocean exploration, tactical surveillance, and environmental monitoring. However, the underwater acoustic channel poses severe challenges, including high propagation delay, limited bandwidth, and rapid time-varying multipath fading, which significantly degrade communication reliability. Cooperative communication, which exploits spatial diversity via relay nodes, offers a promising solution to these impairments. In this paper, we investigate the joint optimization of relay selection and power allocation in UASNs to maximize the long-term system energy efficiency and throughput. This problem is inherently complex due to the hybrid action space, which couples the discrete selection of relay nodes with the continuous allocation of transmission power, and the absence of real-time, perfect channel state information (CSI). To address these challenges, we propose a novel deep hybrid reinforcement learning (DHRL) framework utilizing a parameterized deep Q-Network (P-DQN) architecture. Unlike traditional approaches that discretize power levels or relax discrete constraints, our approach seamlessly integrates a deterministic policy network for continuous power control and a value-based network for discrete relay evaluation. Furthermore, we incorporate a prioritized experience replay (PER) mechanism to improve sample efficiency by focusing on rare but significant channel transition events. We provide a comprehensive theoretical analysis of the algorithm’s complexity and convergence properties. Extensive simulation results demonstrate that the proposed DHRL algorithm outperforms state-of-the-art combinatorial bandit algorithms and conventional deep reinforcement learning baselines in terms of system energy efficiency, and also exhibits superior robustness against channel estimation errors. Full article

Rock fracture behavior is strongly influenced by grain size and boundary effects, which complicate the determination of fracture parameters and the interpretation of size-dependent failure. This study investigates the fracture behavior of sandstone and diorite within the framework of the boundary effect model (BEM) using three-point bending tests, acoustic emission (AE), and digital image correlation (DIC). By varying the prefabricated crack length, different values of the structural geometric parameters a_e were obtained, and the fracture toughness K_IC and tensile strength f_t were identified by regression analysis. The results show that K_IC = 0.6841 MPa·m^0.5 and f_t = 4.5625 MPa for sandstone, whereas K_IC = 2.7233 MPa·m^0.5 and f_t = 21.8218 MPa for diorite. Increasing the prefabricated crack length reduces the peak load and prolongs the pre-peak damage evolution stage. Diorite, with a larger average grain size, exhibits higher AE energy release, a higher proportion of high-energy AE events, and a larger fracture process zone (FPZ) than sandstone. Moreover, the AE energy distribution along the crack propagation direction shows a distinct “three-stage” characteristic, consistent with the non-uniform distribution of local fracture energy g_f predicted by boundary effect theory. The results indicate that BEM can reasonably characterize the fracture behavior of rocks with different grain sizes, and the identified material parameters can be used to construct a BEM-based structural failure curve for estimating nominal failure stress over a wider range of structural geometric parameters. Full article

Urban wetlands are acoustic hotspots where vegetation structure, hydrological dynamics, and anthropogenic noise interact, yet multi-season assessments of how vegetation influences avian soundscapes are limited. This study explored bird soundscape dynamics across forest, open forest grassland, and meadow habitats in Nanjing Xinjizhou National Wetland Park, eastern China, using passive acoustic monitoring during spring and autumn 2023. Twelve sampling points (four per vegetation type) were established, and six acoustic indices were calculated, including the Acoustic Complexity Index (ACI), Acoustic Diversity Index (ADI), Acoustic Evenness Index (AEI), Bioacoustic Index (BIO), Normalized Difference Soundscape Index (NDSI), and Acoustic Entropy Index (H). were calculated from 48-h recordings each season. Random forest models and redundancy analysis assessed the relationships between acoustic indices, fine-scale vegetation parameters (e.g., crown width, tree height, species richness), and anthropogenic factors (e.g., distance to roads/trails, surface hardness). Vegetation structure, particularly crown width, was the primary driver of avian acoustic diversity, with broad-crowned forests consistently exhibiting the highest acoustic complexity. In spring, anthropogenic factors such as trail and road proximity dominated soundscape variation, suppressing biological sounds. In autumn, with reduced human presence, vegetation structure emerged as the dominant factor, while bioacoustic activity remained elevated despite reduced peaks in acoustic complexity. Proximity to roads increased low-frequency (1–2 kHz) noise and suppressed mid-frequency (4–8 kHz) bird vocalizations, but trees with crown widths ≥4 m maintained higher acoustic diversity even near disturbance sources. This study demonstrates that vegetation structure mediates both resource availability and sound propagation, buffering the effects of anthropogenic disturbance in frequency-specific ways. Multi-season sampling is crucial for understanding the dynamic interplay between vegetation phenology and human activity that shapes urban wetland soundscapes. Full article

To reduce the time and computational cost of vibro-acoustic simulations in gear reducer noise evaluation, this study develops a simulation-driven surrogate modeling framework for a three-stage helical gear reducer. A high-fidelity “vibration–acoustic radiation” simulation chain is established, where the housing vibration responses computed in Romax Designer are mapped into ACTRAN to obtain the radiated noise. Using Optimal Latin Hypercube Sampling, 300 designs are generated by varying the first-stage pinion micro-modification parameters (tooth drum, tooth slope, and tooth profile), and the average RMS sound pressure level over six field points is adopted as the noise metric. A BP neural network (BPNN) surrogate is then constructed, in which Bayesian Optimization (BOA) is used to tune hidden layer nodes and learning rate, and an improved Sparrow Search Algorithm (ISSA) is employed to optimize the initial weights and biases, forming the proposed BOA-ISSA-BPNN model. On the test set, the proposed model achieves R² = 0.97499, RMSE = 0.91385, and MAE = 0.6547, with an average prediction time of 32.35s. Meanwhile, comparisons with SVM, BPNN, BOA-BPNN, SSA-BPNN, and ISSA-BPNN demonstrate superior prediction accuracy; moreover, relative to the hour-level computational cost of high-fidelity simulations, the proposed surrogate enables rapid noise evaluation on the order of tens of seconds, enabling fast micro-modification design iteration and practical engineering decision-making. Full article

Model-aided navigation is a key approach for enhancing the positioning accuracy of autonomous underwater vehicles (AUVs). However, its precision is often degraded by model-based velocity errors arising from attitude-induced deviations and uncertainties in the mapping between propeller rotational speed and vehicle velocity. To overcome these limitations, this study proposes an attitude-compensated and acoustics-calibrated model-aided navigation framework for AUVs. The framework derives the vertical velocity from pressure sensor depth data to correct attitude-related model errors. It also dynamically refines the mapping between propeller speed and velocity using long-baseline (LBL) acoustic positioning data when LBL measurements are available. A sea trial was conducted in the South China Sea at a depth of 2000 m to verify the proposed method. The results showed that the system maintained a positional accuracy of 509 m over 5 h beyond LBL coverage. This outcome demonstrates its ability to achieve sustained high-precision navigation without external assistance. Full article