Search Results (1,187)

Radio spectrum is a limited national resource whose efficient utilization is of strategic importance. With the rapid advancement of wireless technologies, maintaining spectrum cleanliness and enabling fast and reliable anomaly detection have become critical challenges. Artificial intelligence (AI)-based approaches have recently shown great promise in addressing these issues; however, their effectiveness strongly depends on the availability of high-quality, representative, and annotated datasets. Generating such datasets is a complex task, further complicated by environmental conditions such as weather. Hungary’s nationwide spectrum monitoring network enables continuous observation of frequency bands, thereby providing the opportunity to construct large-scale and sustainable datasets. This study introduces a measurement methodology designed for the FM sound broadcasting in the VHF band (87.5–108 MHz), presents the resulting dataset, and details the annotation process. The published, openly accessible dataset is expected to serve not only as a valuable reference point but also as a benchmark for the international research community, facilitating the development, validation, and objective comparison of AI-driven spectrum monitoring solutions. Full article

Cities exhibit sound patterns that vary across locations and time, while transmitting raw audio introduces communication and privacy concerns. We present a federated TinyML architecture for real-time urban sound classification on microcontroller-class edge devices. A compact audio embedding network is deployed as a frozen feature extractor, while a lightweight classifier head is trained on-device and shared via MQTT, enabling communication-efficient collaborative learning. The system is evaluated on ESP32 (Espressif Systems, Shanghai, China) hardware under cross-dataset transfer from UrbanSound8K to SONYC. Domain shift reduces baseline accuracy from 90.39% to 78.27%, while local adaptation and federated aggregation improve accuracy to approximately 85%, recovering most of the performance loss. Repeated aggregation further improves macro-F1 and class balance across heterogeneous data. Embedded measurements confirm real-time inference (~250 ms per window) with negligible overhead, while each update exchanges only a compact classifier head (~1.2 kB). These results demonstrate that adaptive classification can be achieved on resource-constrained nodes in distributed smart-city networks. Full article

We report on a novel approach for the monitoring of tangential laser turning with ultrashort laser pulses. By using an ultra-sonic sensor consisting of a membrane-free optical microphone, the current state of the ablation process can be analyzed, potentially enabling a real-time automated regulation. With its high sensitivity, bandwidth, and sampling rate, it is an ideal tool for process monitoring. The material ablation caused by focused femtosecond laser pulses produces distinct sound waves, which can be detected by the optical microphone. The diameter reduction of a rotating cylindrical workpiece during the laser turning process with ultrashort laser pulses results in a variation in the acoustic emissions. From this, properties like the state of the machining progress can be inferred. Full article

Continuous monitoring of pig behavior is essential for timely health management and welfare assessment in commercial production systems. Although vision-based methods have been widely studied, their practical application in commercial barns is often limited by variable lighting, frequent occlusion, and high stocking density. Acoustic sensing offers a non-contact alternative that is independent of lighting conditions; however, reliable behavior classification from pig vocalizations remains challenging in commercial environments because of background noise and temporal variability in sound patterns. In this study, an attention-guided acoustic framework, termed ATF-Conformer, was developed for pig vocalization classification under farm conditions. A five-class vocalization dataset was collected from finishing Landrace pigs and multiparous sows on a commercial farm, including cough, scream, estrus, feeding, and normal behavior sounds. The proposed framework combined spectrogram denoising with interactive attention to enhance behavior-related acoustic information, while a time-frequency-decoupled Conformer encoder was introduced to improve feature representation under noisy conditions. Final classification was performed using mask-based temporal pooling with an additive angular margin Softmax objective. In five-fold grouped cross-validation, ATF-Conformer achieved an accuracy of 97.34% ± 0.42 and outperformed several existing acoustic models across multiple evaluation metrics. A similar accuracy of 97.38% was obtained on an independent test set, indicating stable performance across datasets. These results suggest that the proposed method can support continuous, non-invasive pig vocalization-based behavior monitoring and may assist farm owners or workers in pen-level screening of frequent cough or abnormal vocal events, thereby supporting targeted on-site inspection in precision livestock farming. Full article

With the increasing demand for intelligent fault monitoring, acoustic-based diagnosis has emerged as a promising solution for industrial applications such as pipeline leakage and electrical equipment fault detection. However, complex working conditions and domain shifts significantly degrade model performance, especially when unseen target domain data is unavailable. To address this, we propose an amplitude-phase collaborative augmentation network named AP-CANet tailored for acoustic fault diagnosis. Specifically, the network adaptively aligns amplitude and phase features across multiple source domains and performs label-consistent sample augmentation to enrich data diversity while preserving semantic consistency. A frequency–spatial interaction module further integrates global spectral information with local temporal details to improve feature discriminability. Moreover, we introduce a manifold triplet loss that scales shortest path distances in the feature manifold, encouraging the model to better capture subtle distinctions among hard samples and improving intra-class compactness and inter-class separability. We evaluate the proposed method on two publicly available datasets: the Pipeline Leak Acoustic Dataset (GPLA-12) and the Electrical Sound Dataset (MIMII-DG). Experimental results demonstrate superior performance under domain-shift scenarios, highlighting the method’s potential for scalable and low-cost acoustic fault diagnosis in real-world industrial environments. Full article

Continuous, non-invasive cardiopulmonary monitoring is receiving increasing attention as population aging and chronic diseases rise. Acoustic sensing provides diagnostically relevant information with relatively simple hardware. Yet, physiological body sounds span heterogeneous and partially overlapping spectra and are highly susceptible to environmental noise and motion artifacts, which limit conventional stethoscopes and fixed-frequency sensors. Frequency-Tunable Acoustic Sensors (FTAS) offer a promising route toward frequency-selective amplification and adaptive interference suppression by matching their resonance to target signals, thereby potentially supporting multi-site monitoring and personalized diagnostics on a single platform. This review starts with an overview of physiological sound generation and the evolution of auscultation, then surveys mainstream medical acoustic transducers (piezoelectric, capacitive microelectromechanical systems (MEMS), piezoresistive and triboelectric) and their limitations in frequency selectivity. Resonance-tuning strategies are classified into three paradigms: electrical tuning, material-based tuning, and geometric reconfiguration, and their tuning ranges, response characteristics, and representative implementations are comparatively discussed. Finally, this review discusses the potential translational value of FTAS in physiological acoustic signal monitoring, particularly in cardiovascular and respiratory assessment, and emphasizes the remaining challenges, including the trade-off between sensitivity and selectivity, as well as long-term biocompatibility. At the same time, this review highlights their development prospects in customizable acoustic sensing platforms. Full article

Tiny Machine Learning (TinyML) enables Machine Learning (ML) models to run on resource-constrained devices, which is critical for Industrial Internet of Things (IIoT) systems requiring low latency, energy efficiency, and local decision-making. Nevertheless, deploying TinyML in IIoT remains challenging due to diverse applications, hardware, frameworks, and deployment methodologies, highlighting the need for a structured and focused review. Existing review articles mainly address general IoT or edge AI, leaving a critical gap in a unified and systematic understanding of TinyML applications, system components, and methodologies within IIoT contexts. Consequently, this systematic literature review (SLR) addresses this gap by analyzing 35 peer-reviewed studies published between 2018 and 2026, offering a comprehensive and structured synthesis of TinyML-enabled IIoT systems. The selected works are synthesized across three major dimensions: applications, system components, and methodologies. In terms of applications, TinyML is primarily used for predictive maintenance, equipment monitoring, anomaly detection, energy management, and general-purpose applications. The general category captures cross-domain solutions that do not fit into a single industrial application. A comparative analysis of all application categories is conducted in terms of accuracy, latency, memory, and energy. For system components, a structured comparison shows how hardware, software, and sensing choices shape performance and applicability. Hardware platforms are grouped by microcontroller families, highlighting dominant types. Software frameworks are summarized, showing the widespread use of lightweight toolchains for on-device inference. Sensor types are categorized, with vibration sensing most common. They are supported by other sensing methods such as vision, sound (acoustic), and environmental sensors. Finally, the methodologies examined in this SLR provide a comprehensive view of the data foundations, model selection, and optimization strategies. In short, this SLR converges diverse TinyML–IIoT applications, microcontroller-based hardware, lightweight software frameworks, sensing modalities, varied datasets, and optimization strategies, while also identifying challenges and future research directions. Full article

Background: Early detection and monitoring of enamel changes during caries lesion formation are essential for preventive management. This study aimed to evaluate time-dependent enamel demineralization using micro-computed tomography (micro-CT) and to compare its diagnostic performance with laser fluorescence and digital colorimetric image analysis. Methods: Twelve sound human permanent teeth were subjected to a gel-based lactic acid demineralization for 14 days. Assessments were performed at baseline and after 3, 7, and 14 days. Enamel mineral density (MD) and demineralization depth (DD) were measured using micro-CT. Laser fluorescence was evaluated using DIAGNOdent, while colorimetric changes were analyzed through standardized digital imaging using the CIE Lab* system, including ΔE and Whiteness Index (WI). Statistical analysis included repeated measures ANOVA and Pearson correlation (p < 0.05). Results: A significant time-dependent progression of enamel demineralization was observed. Demineralization depth increased from 0.0828 mm (3 days) to 0.234 mm (14 days) (p < 0.001), while mineral density decreased significantly over time (p < 0.001). DIAGNOdent values showed significant increases after 7 and 14 days (p = 0.002). Colorimetric analysis revealed early detectable changes, with ΔE exceeding clinically perceptible thresholds as early as day 3. WI values increased progressively, indicating enhanced enamel opacity. A weak but significant negative correlation between MD and DD was found (p = 0.04). Conclusions: Enamel demineralization progresses in a time-dependent manner and can be effectively monitored using micro-CT, laser fluorescence, and colorimetric analysis. Digital colorimetric analysis may serve as a valuable adjunctive tool in caries diagnostics. Full article

Identifying noise sources in exceedance-triggered audio is essential for targeted source tracing and sustainable urban social noise governance. While accurate models require massive labeled data, the acoustic complexity, high redundancy, and imbalanced class distributions of real-world recordings incur prohibitive manual annotation costs, hindering their widespread application in IoT networks. To tackle this bottleneck, we present a label-efficient active learning framework designed to minimize annotation costs by dynamically selecting the most valuable audio samples. Specifically, rather than treating uncertainty, class balance, and diversity as separate query criteria, it encodes uncertainty and dynamic class-aware learning needs into a weighted acoustic feature space, so that diversity-based selection can be performed in a unified manner. Experiments on the UrbanSound8K benchmark and a realistic exceedance-triggered monitoring dataset demonstrate consistent label-efficiency advantages over mainstream methods. Notably, our approach reaches 98% of the fully supervised upper bound on the real-world dataset while reducing the training annotation workload by 85.0% compared to random sampling. On the real-world dataset, the proposed framework yields higher F1-scores for several challenging under-represented categories and reduces the misclassification of dominant sound events relevant to social noise source tracing. Furthermore, cross-site generalization experiments reveal rapid localized adaptation to new monitoring environments, reaching the fully supervised upper bound with only 13% of the target-domain training data. Overall, this study provides a scalable and cost-effective classification framework for urban noise monitoring, offering practical support for noise regulatory authorities and city managers in more targeted noise source tracing and governance. Full article

Noise in long highway tunnels and underground interchanges poses a significant environmental concern, affecting both drivers and nearby residents. This research develops an acoustic finite element model of a long tunnel in Leuven Measurement Systems (LMS) Virtual Lab to characterize the tunnel noise field, and the effectiveness of different noise mitigation measures was also evaluated and optimized accordingly. The model is validated against in situ monitoring data, with deviations controlled within 3 dB(A) and strong agreement confirmed by the Kappa consistency test. Both simulations and measurements show that sound pressure levels (SPLs) are generally highest near the tunnel center and lower toward the portal, exhibiting periodic fluctuations rather than a monotonic decrease. The dominant noise energy is concentrated between 125 Hz and 500 Hz. SPLs at 1.8 m above the road surface are noticeably higher than at 1.2 m and 1.5 m, indicating greater noise exposure for drivers of large vehicles compared with smaller vehicles. Noise reduction performance is further assessed for different lining materials and pavement types. Installing sound-absorbing panels in the tunnel midsection provides effective attenuation, with expanded perlite panels, single-layer metal micro-perforated panels, and FC quiet perforated panels (FC-PP) performing best, while porous asphalt shows superior noise reduction compared with conventional dense-graded asphalt pavements. Full article

Background and Objectives: Menopausal hormone therapy (MHT) is the most efficacious treatment for vasomotor symptoms and genitourinary conditions associated with menopause. Modern menopause care increasingly encompasses women with multimorbidity, renal or hepatic impairment, previous malignancies or thromboembolic disorders, advanced age, and polypharmacy—groups frequently underrepresented in randomized clinical trials. This evidence gap prompts significant inquiries about the relevance of trial-based recommendations to actual clinical practice. Materials and Methods: This narrative review offers a concentrated assessment of prominent worldwide clinical guidelines regarding menopausal hormone therapy through thematic synthesis. We examined position statements from the North American Menopause Society (NAMS), the European Menopause and Andropause Society (EMAS), NICE clinical guidelines, the ACOG Practice Bulletin on menopausal symptom management, the Endocrine Society clinical practice guideline, and pertinent UK guidance from RCOG, BMS, and BGCS. Data from systematic reviews, meta-analyses, and extensive observational studies were analyzed to contextualize guideline recommendations for populations often underrepresented in clinical trials, including women aged ≥65 years and individuals with multimorbidity or polypharmacy. Results: Only the NICE and EMAS recommendations expressly acknowledge clinical vulnerability or complexity (multimorbidity, frailty, and cancer survivorship) as foundational principles. NAMS and ACOG delineate risk categories but fail to offer a cohesive taxonomy of vulnerability. Polypharmacy and drug–drug interactions are inconsistently addressed across guidelines, and there is a deficiency of standardized prescribing algorithms. While routine safety monitoring is universally advocated, the intervals for follow-up and methods for risk categorization differ. Observational evidence consistently indicates route-dependent variations in cardiovascular and thromboembolic risk, with transdermal estrogen linked to a more advantageous safety profile in higher-risk individuals. Conclusions: Present menopausal therapy guidelines are methodologically sound; however, they insufficiently address the complexities of multimorbidity, polypharmacy, and organ dysfunction. A systematic conceptual framework that incorporates areas of clinical vulnerability may facilitate personalized benefit–risk evaluation in practical applications. Future guideline revisions should enhance clarity by incorporating polypharmacy concerns, monitoring strategies, and systematic risk stratification methods for clinically complicated patients. Full article

Suspended sediment plays a critical role in river ecosystem health, nutrient transport, and water quality, while also affecting navigation infrastructure and reservoir sedimentation in regulated rivers. A sound understanding of sediment dynamics in complex river systems consisting of natural lakes and engineered navigation structures remains a critical challenge for river management and water quality assessment. This study investigates the longitudinal patterns of suspended sediment concentration (SSC) along a ~500-km reach of the Upper Mississippi River containing Lake Pepin and multiple lock-and-dam structures. In this study, we analyze remotely sensed SSC estimates from the RivSED database (2001–2019). The SSC datasets were then integrated with in situ streamflow measurements and potential soil erosion to characterize sediment supply and transport dynamics and relate with upstream contributing watershed’s attributes. Results reveal distinct sediment behavior patterns: (1) Lake Pepin functions as a significant sediment trap, creating a clear discontinuity in SSC with mean concentrations decreasing from ~25 mg/L upstream to ~13 mg/L within the lake; (2) longitudinal SSC profiles show re-establishment patterns downstream of the lake, reaching ~23 mg/L approximately 100 km below the outlet; (3) strong positive correlation (r = 0.80, R² = 0.64, p < 0.001) exists between watershed sediment export and river-reach-scale sediment fluxes. Temporal analysis across these upstream monitoring stations shows sediment export rates ranging from 10,000 to 200,000 tons/year, with notable inter-annual variability driven by discharge patterns. This research demonstrates the utility of combining a spectrum of datasets for exploring sediment dynamics in complex riverine systems. Though the current study is a case study, the study results provide crucial insights for navigation management, ecosystem health assessment, and watershed management strategies in similar settings. Full article

Metastructures, waveguides composed of multiple unit cells (meta-atoms), have gained significant attention for controlling wave propagation in engineering applications, especially in the context of elastic and acoustic waves. However, existing metastructures often lack sufficient tunable functionality to dynamically control both elastic vibration and acoustic wave transmission using a single external parameter. This study introduces a phase-change material (PCM)-embedded meta-atom, where a core mass is connected to an outer shell by Archimedean spiral bridges. The solid–liquid phase transition of PCM induces a notable change in the effective shear modulus, enabling dynamic wave control. The mechanism for bandgap formation transitions from Bragg scattering in the solid PCM state to local resonance in the liquid state. Core rotation, driven by the phase transition, is key to generating flat bands and low-frequency locally resonant bandgaps at high temperatures. Temperature-dependent, mode-selective transmission behavior is observed, with transverse vibrations and acoustic waves exhibiting opposite blocking and transmission characteristics at the same frequency. This design provides a promising approach for decoupling sound and vibration management, using temperature control driven by the PCM phase transition. The work contributes to multifunctional metastructures with applications in adaptive noise control, structural health monitoring, and tunable vibration isolation systems. Full article

The Internet of Drones (IoD) has emerged as a critical extension of the Internet of Things, enabling unmanned aerial vehicles to support diverse applications, including precision agriculture, logistics, disaster monitoring, and security surveillance. Despite its rapid growth, securing IoD communications remains a significant challenge due to the open wireless environment, high drone mobility, and strict computational and energy constraints. Existing authentication mechanisms either rely on computationally expensive cryptographic operations or remain validated only at the protocol or simulation level, leaving a critical gap in practical, hardware-validated solutions suitable for resource-constrained drone platforms. This gap motivates the need for a lightweight, privacy-preserving authentication scheme that is both theoretically sound and experimentally deployable on real hardware. To address this, we propose a Physically Unclonable Functions (PUF)-assisted lightweight authentication scheme for IoD environments that binds cryptographic keys to each drone’s intrinsic hardware characteristics via PUFs. The scheme employs dynamically generated pseudo-identities to conceal permanent drone identities and prevent tracking, while authentication and key agreement are achieved using efficient symmetric cryptographic primitives, including SHA-256 for key derivation and updates, AES-256 for secure communication, and lightweight XOR operations to minimize overhead. Forward secrecy is ensured through rolling key updates, and periodic renewal of PUF challenges enhances resistance to replay and modeling attacks. To validate practicality, both software-based and hardware-based implementations were developed and evaluated. The software evaluation demonstrates a low communication overhead of 708.5 bytes and an average computation time of 18.87 ms. The hardware implementation on a Nexys A7-100T FPGA operates at 100 MHz with only 12.49% LUT utilization and low dynamic power consumption of approximately 182.5 mW. These results confirm that the proposed framework achieves an effective balance between security, privacy, and efficiency. The significance of this work lies in providing a fully hardware-validated, PUF-based authentication framework specifically tailored to the real-world constraints of IoD environments, offering a practical foundation for securing next-generation drone networks. Full article

Wind-driven surface processes are a major source of underwater ambient sound and are therefore an important component of coastal soundscapes. Yet their frequency-dependent expression in shallow nearshore reef environments remains insufficiently characterized from field observations. This study investigates low-to-mid-frequency (20–1000 Hz) ambient acoustic variability at Faro’s natural reef (southern Portugal) using short-term passive acoustic monitoring combined with concurrent sea state measurements. The results show evidence of a relationship between frequency-dependent acoustic response and wind-driven surface processes. At frequencies of 20–100 Hz, ambient sound levels exhibit a weak relationship with wind-driven surface conditions, with elevated variability under low agitation. This is attributed to persistent background anthropogenic noise, particularly vessel traffic. In contrast, above 100 Hz, the ambient sound level increases consistently with wind-driven agitation, indicating that wind-driven surface processes dominate ambient sound in the 100–1000 Hz frequency range. Transient high-energy peaks increase in frequency and intensity with surface agitation, consistent with breaking-wave events, even though elevated background sound levels persist after peak removal. These findings demonstrate that wind-related ambient sound variability at Faro’s natural reef is robustly expressed above approximately 100 Hz. This highlights the importance of frequency-dependent interpretation in passive acoustic monitoring as a necessary baseline for assessing the nearshore reef environment’s influence on ambient sound levels and acoustic propagation under variable sea state conditions. Full article