Search Results (231)

Compressed air systems (CASs) represent a significant portion of energy consumption in large-scale built environments and manufacturing facilities, suffering from both micro-level physical pipeline leaks and macro-level operational inefficiencies. This paper proposes a unified, dual-action artificial intelligence framework aimed at advancing building decarbonization by systematically integrating acoustic-vision leak quantification with schedule-aware machine learning. Specifically, the framework targets pneumatic pipe connection leaks, fitting leaks, and joint degradation faults within compressed air distribution networks, which are the primary sources of micro-level volumetric energy losses in industrial building systems. First, a probabilistic multimodal fusion algorithm (MPSF) using an ultrasonic camera is developed to detect and geometrically quantify physical leaks, successfully translating pixel areas into physical facility energy loss metrics (estimating 11.0 kW of wasted power from detected severe leaks). Second, to optimize the compressor’s supply matching the actual facility demand without risking data leakage from internal flow sensors, an eXtreme Gradient Boosting (XGBoost) model is proposed. By utilizing only external building environmental conditions and the real-time operational schedules of 13 distinct zones, the model achieves highly accurate dynamic power prediction (R² = 0.9698). Finally, comprehensive simulations based on real-world digital monitoring data from a facility-scale built environment demonstrate that only the concurrent application of both modules ensures stable end-point pressure. The integrated framework achieves a substantial system-wide building energy reduction of over 20% to 40% compared to baseline constant-pressure operations, yielding an estimated annual reduction of 116 tons of CO₂ emissions, thereby providing a direct pathway toward carbon-neutral building operations. Full article

To investigate the mechanical bearing characteristics of the “excavation-backfill” composite after the excavation of coal pillars and backfill replacement with gangue-based cemented paste backfill, mechanical bearing characteristic experiments are conducted on a series of coal samples with rectangular “excavation-backfill” roadways under uniaxial loading, covering the full deformation and failure process. The MTS universal testing machine and DS5-type acoustic emission signal acquisition system are employed, and a high-speed camera is adopted to monitor and record the full failure process. The mechanical bearing characteristics and crack evolution mechanisms of unfilled coal pillar (U-C) and backfill coal pillar (B-C) samples are explored. The results show that with the increase in “excavation-backfill” width, the uniaxial compressive strength and elastic modulus of U-C samples decrease significantly, and the samples exhibit brittle–ductile failure. When the “excavation-backfill” width is 60 mm, the backfill can distinctly improve the strength and elastic modulus of B-C samples, showing a strong strength recovery effect. The temporal characteristics of AE signals indicate that both U-C and B-C samples experience four stages subjected to uniaxial compression: quiet period, rising period, active period, and post-peak rising period. In the quiet period and rising period, the b-value fluctuates upward with energy release; in the active period, the b-value decreases significantly with large energy release; in the post-peak rising period, crack propagation and frictional slip increase, leading to an enlarged fluctuation amplitude of the b-value. Based on the location of AE sources, the three-dimensional crack chain evolution is inverted. The crack chain evolution of the U-C is mainly distributed along the dip direction (75°~90°, 255°~270°) and vertical direction (165°~180°) of the coal bedding plane, while the B-C is more uniform, indicating that the backfill evidently affects the crack distribution. This study provides new insights for predicting the crack evolution and failure mode of coal–rock composites. Full article

As global aquaculture continues to expand, there is increasing interest in sustainable and non-invasive tools for monitoring fish growth. Nile tilapia (Oreochromis niloticus) is one of the most farmed species worldwide. Its biomass estimation often relies on manual sampling or stereo-camera systems limited by water turbidity. This study establishes a robust relationship between lateral target strength (TS) and the total length (TL) and weight (W) of Nile tilapia using a cost-effective 201 kHz single-beam echosounder. Measurements were conducted with free-swimming fish in a controlled pond environment (TL range, 13–44 cm). The results show a strong linear correlation between acoustic and biometric data. Specifically, the relationship for mean TS was defined as TS_mean = 20.4log(TL) − 68.8 (R² = 0.93) and TS_mean = 6.3log(W) − 55.4 (R² = 0.96), proving the system’s accuracy for biomass estimation. Furthermore, the Method of Fundamental Solutions (MFS) was employed for numerical validation based on X-ray morphometry of the swim bladder. Very good agreement was observed between experimental data and numerical simulations, reinforcing the validity of the acoustic models despite the inherent complexity of biological targets. These findings demonstrate that calibrated single-beam acoustic systems provide a viable, non-intrusive tool for real-time monitoring in aquaculture ponds. Full article

This paper presents a cover lens concept for camera modules based on surface acoustic waves (SAW) to mitigate the degradation of physical AI optical sensor field-of-view performance caused by surface contamination. The proposed approach utilizes a single-phase unidirectional transducer (SPUDT) that intentionally breaks left–right symmetry through a geometrically asymmetric electrode array to generate SAW, thereby removing droplet contamination. First, the acoustic streaming induced inside a single sessile droplet by the SAW was visualized, and the dynamic behavior of the droplet upon SAW actuation was observed using a high-speed camera. The internal flow developed into a recirculating vortex structure with directional deflection relative to the SAW propagation direction, indicating a symmetry-broken streaming pattern rather than a purely symmetric circulation. Upon the application of the SAW, the droplet was confirmed to move a total of 7.2 mm along the SAW propagation direction, accompanied by interfacial deformation and oscillation. Next, an analysis of transport trajectories for five sessile droplets dispensed at different y-coordinates ($y_1$–$y_5$) revealed that all droplets were transported along the x-axis regardless of their initial positions. Furthermore, the analysis of transport velocity as a function of droplet viscosity (1 $\mathrm{c}\mathrm{P}$ and 10 $\mathrm{c}\mathrm{P}$) and volume (2$\mathrm{\mu }\mathrm{L}$, 4$\mathrm{\mu }\mathrm{L}$, and 6 $\mathrm{\mu }\mathrm{L}$) demonstrated that the transport velocity gradually increased with driving voltage but decreased as viscosity increased under identical actuation conditions. Finally, the proposed cover lens was applied to an automotive front camera module to verify its effectiveness in improving object recognition performance by removing surface contamination. Based on its simple structure and driving principle, the proposed technology is deemed to be expandable as a surface contamination cleaning technology for various physical AI perception systems, including intelligent security cameras and drone camera lenses. Full article

Conventional acoustic time-of-arrival (TOA) estimation in complex indoor environments is highly susceptible to multipath reflections and occlusions, resulting in unstable measurements and limited physical interpretability. This paper presents a smartphone-based indoor localization method built on vision-assisted acoustic channel modeling, and develops a fusion anchor integrating a pan–tilt–zoom (PTZ) camera and a near-ultrasonic signal transmitter to explicitly perceive indoor geometry, surface materials, and occlusion patterns. First, vision-derived priors are constructed on the anchor side based on line-of-sight reachability, orientation consistency, and directional risk, and are converted into soft anchor weights to suppress the impact of occlusion and pointing mismatch. Second, planar geometry and material cues reconstructed from camera images are used to generate probabilistic room impulse response (RIR) priors that cover the direct path and first-order reflections, where environmental uncertainty is mapped into path-dependent arrival-time variances and prior probabilities. Finally, under the RIR prior constraints, a path-wise posterior distribution is built from matched-filter outputs, and an adaptive fusion strategy is applied to switch between maximum a posteriori (MAP) and minimum mean square error (MMSE) estimators, yielding debiased TOA measurements with calibratable variances for downstream localization filters. Experiments in representative complex indoor scenarios demonstrate mean localization errors of 0.096 m and 0.115 m in static and dynamic tests, respectively, indicating improved accuracy and robustness over conventional TOA estimation. Full article

Improving city crossroads safety is a critical problem for modern smart transportation systems (STS). This article presents the results of developing, upgrading, and comprehensively experimentally testing an acoustic monitoring system prototype designed for rapid accident detection. Unlike conventional camera- or lidar-based approaches, the proposed solution uses passive sound source localization to operate effectively with no direct visibility and in adverse weather conditions, addressing a key limitation of camera- or lidar-based systems. Generalized Cross-Correlation with Phase Transform (GCC-PHAT) algorithms were used to develop a hardware–software complex featuring four microphones, a multichannel audio interface, and a computation module. This study focuses on the gradual upgrading of the algorithm to reduce the mean localization error in real-life urban conditions. Laboratory and complex field tests were conducted on an open-air testing ground of a university campus. During these tests, the system demonstrated that it can accurately determine the coordinates of a sound source imitating accidents (sirens, collisions). The analysis confirmed that the system satisfies the V2X infrastructure integration response time requirement (<200 ms). The results suggest that the system can be used as part of smart transportation systems. Full article

This study presents an in-depth exploration of an innovative monitoring system that contributes to precision agriculture (PA) and supports sustainability and biodiversity. Amidst the challenges of global population growth and the need for sustainable, high-yield agricultural practices, PA, supported by modern technology and data-driven methodologies, emerges as a pivotal approach for optimizing crop yield and resource management. The proposed monitoring system integrates Wireless sensor networks (WSNs) into PA, enabling real-time acquisition of environmental data and multimodal observations through cameras and microphones, with data transmission via LTE and/or LoRaWAN for cloud-based analysis. Its main contribution is a physically modular, pole-mounted station architecture that simplifies sensor integration and reconfiguration across use cases, while remaining solar-powered for long-term off-grid operation. The system was evaluated in two field deployments, including a year-long wild-flora monitoring campaign (three stations; 365 days; 1870 images; 63–100% image-based operational availability), during which stations remained operational through a wildfire event. In the viticulture deployment, the acoustic module supported bat monitoring as a bio-indicator of ecosystem health, achieving bat call detection performance of 0.94 (AP Det) and species classification performance of 0.85 (mAP Class). Overall, the results support the use of modular, energy-aware monitoring stations to perform sustained agricultural and ecological data collection under practical field constraints. Full article

The recolonization of the wolf (Canis lupus italicus) in Italy represents conservation success, but it has led to increased conflicts with livestock farming. These conflicts may undermine traditional pastoral practices, which are important for maintaining rural landscapes and associated biodiversity. In 2023, the European wolf population exceeded 20,300 individuals, with an estimated 65,000 livestock losses reported annually across the EU. This study assesses the effectiveness of an acoustic anti-wolf collar to complement existing protective measures, including fencing, human surveillance, and guarding dogs. A field trial was conducted from June to August 2024 in the municipality of Bova Marina in the metropolitan city of Reggio Calabria, Italy, using three groups of 50 Aspromonte goats. The groups were managed by: (1) a shepherd only (SO), (2) a shepherd with guarding dogs (SGD), and (3) a shepherd with guarding dogs and the anti-wolf collar (SGDC). The collar emitting modulated frequency intervals based on natural harmonic sounds, intended to deter wolves, was mounted on goats. Monitoring, by camera traps, enabled a comparative analysis of predation events. Camera data indicated persistent wolf activity at the site (54 images at CT1, 42 at CT2), but outcomes diverged by treatment. Two camera traps positioned at corridor bottlenecks identified from terrain morphology confirmed wolf presence and provided continuous coverage of the three groups on the single property. SO had 72 attacks and 5 kills; SGD had 26.39% fewer attacks and 1 kill; SGDC had no predation events despite confirmed presence. The preliminary findings suggest that the use of the anti-wolf collar may contribute to a reduction in predation and be a useful addition to strategies aimed at promoting coexistence between wolves and pastoral activities. Full article

This paper presents Vaulted Harmonies, a 66-min animated feature film created as part of the scientific outreach effort of the Past Has Ears at Notre-Dame project (ANR-PHEND). The project investigates the historical acoustics of Notre-Dame de Paris and their influence on music over the centuries. The film is structured around eleven musical pieces spanning the 12th to 20th centuries, each chosen for its relevance to the cathedral’s history and musical heritage. Details include how each piece was recorded and auralised using a calibrated geometric acoustic model that reflects the acoustics of the corresponding historical period. Further details describe the creation of the CGI renderings of Notre-Dame, which feature animated musicians synchronised with the music they perform, enhancing the immersive quality of the experience. These musical performances are interwoven with short documentary-style segments that provide historical and musicological context. The film adopts a first-person perspective in which the acoustics and visuals dynamically follow the camera’s movement, offering a virtual reality-like experience in a cinematic format. Vaulted Harmonies thus functions both as an engaging archaeoacoustic outreach project and as a standalone virtual concert rooted in historically informed performance and production. Full article

As crucial transportation hubs and economic nodes, the underwater security and infrastructure maintenance of harbors are of paramount importance. Harbors are characterized by high vessel traffic and complex underwater environments, where traditional underwater inspection methods, such as diver operations, face challenges of low efficiency, high risk, and limited operational range. This paper introduces a collaborative survey and disposal system that integrates a deformable unmanned surface vehicle (USV) with a lightweight remotely operated vehicle (ROV). The USV is equipped with a side-scan sonar (SSS) and a multibeam echo sounder (MBES), enabling rapid, large-area searches and seabed topographic mapping. The ROV, equipped with an optical camera system, forward-looking sonar (FLS), and a manipulator, is tasked with conducting close-range, detailed observations to confirm and dispose of abnormal objects identified by the USV. Field trials were conducted at an island harbor in the South China Sea, where simulated underwater objects, including an iron drum, a plastic drum, and a rubber tire, were deployed. The results demonstrate that the USV-ROV collaborative system effectively meets the demands for underwater environmental measurement, object localization, identification, and disposal in complex harbor environments. The USV acquired high-resolution (0.5 m × 0.5 m) three-dimensional topographic data of the harbor, effectively revealing its topographical features. The SSS accurately localized and preliminarily identified all deployed simulated objects, revealing their acoustic characteristics. Repeated surveys revealed a maximum positioning deviation of 2.2 m. The lightweight ROV confirmed the status and location of the simulated objects using an optical camera and an underwater positioning system, with a maximum deviation of 3.2 m when compared to the SSS locations. The study highlights the limitations of using either vehicle alone. The USV survey could not precisely confirm the attributes of the objects, whereas a full-area search of 0.36 km² by the ROV alone would take approximately 20 h. In contrast, the USV-ROV collaborative model reduced the total time to detect all objects to 9 h, improving efficiency by 55%. This research offers an efficient, reliable, and economical practical solution for applications such as underwater security, topographic mapping, infrastructure inspection, and channel dredging in harbor environments. Full article

Real-time insect monitoring is essential for sustainable agriculture and biodiversity conservation. The traditional method of attracting insects to colored glue traps and manually counting the catch is time-intensive and requires specialized taxonomic expertise. Moreover, these traps are often lethal to pests and beneficial insects alike, raising both ecological and ethical concerns. Camera-based trap designs have recently emerged to lower the amount of manual labor involved in determining insect species, yet they are still deadly to the catch. This study presents the design and evaluation of a non-lethal acoustic monitoring system capable of detecting and classifying insect species based on their sound signatures. A first prototype was developed with a focus on low self-noise and suitability for autonomous field deployment. The system was initially validated through laboratory experiments, and subsequently tested in six rapeseed fields over a 25-day period. More than 3400 h of acoustic data were successfully collected without system failures. Key findings highlight the importance of carefully selecting each component to minimize self-noise, as insect sounds are extremely low in amplitude. The results also underscore the need for efficient data and energy management strategies in long-term field deployments. This paper aims to share the development process, design decisions, technical challenges, and practical lessons learned over the course of building our IoT sensor system. By outlining what worked, what did not, and what should be improved, this work contributes to the advancement of non-invasive insect monitoring technologies. Full article

The aims of the study were to evaluate the effectiveness of audio detection for identifying feeding sounds in free grazing sheep and to assess whether the recognition of these sounds could be influenced by pasture characteristics. Twelve Valle del Belice dry ewes were grazed on two mixed swards: on 10 May, grass-rich sward (G); on 13 May, legume-rich sward (L). Each ewe was fitted with a collar equipped with a point of view (POV) camera. All audio files (without viewing the videos) were listened to and sounds recognized as herbage prehension and rumination activity were highlighted. Time spent eating and ruminating was then calculated. To validate the audio file analysis, all video files were subjected to observation of the same behavioral aspects detected with audio. The regression between the prehensions number estimated using sound alone and the actual values recorded through video was significant (r² 0.743; p < 0.001). No differences were found in recognizing grazing behavior between data obtained by listening or watching the videos and between the two swards. The acoustic analysis of the single bites on grass and legume forages reveals significant differences between the two forage classes (p ≤ 0.001) particularly in terms of energy, temporal structure, and spectral features. Since sheep showed a strong selective activity towards legumes even in the grass-rich sward (selectivity index 3.1), this may have reduced acoustic differences between swards. Full article

Distributed Acoustic Sensing (DAS) is a new oceanographic measurement technology that exploits the physical sensitivities of fiber-optic communication cables to changes in pressure, allowing time series measurements of pressure at meter-scale spacing for ranges up to 150 km. The along-cable measurement locations, called channels, are evenly distributed, but the specific locations of each are initially unknown. In terrestrial applications, channel locations are often found by the “tap test” where acoustic transients are created at surveyed locations along the cable. For submarine installations, tap tests are inconvenient or logistically impossible. Here we describe a new method for submarine channel geolocation by comparing DAS signals to ambient ocean wave time series using a variety of cross-spectral methods. Ground truth data were derived from two remote sensing sources: marine radar (X-band) and shore-based cameras. The methods were developed and tested at two coastal locations and showed an ability to geolocate DAS channels to within 10 m at ranges of up to 3 km (radar) or within 1.0 m at ranges up to 600 m (optical). Full article

To investigate the failure mechanisms of surrounding rock in deep mine tunnels and its spatio-temporal evolution patterns, a true triaxial disturbance unloading rock testing system, the acoustic emission (AE) system, and the miniature camera monitoring system were employed to conduct true triaxial graded loading tests on sandstone containing circular holes at burial depths of 800 m, 1000 m, 1200 m, 1400 m, and 1600 m. The study investigated the patterns of mechanical properties and failure characteristics of porous sandstone at different burial depths. The results showed that the peak strength of the specimens increased quadratically with increasing burial depth; the failure process of porous sandstone could be divided into four stages: the calm period, the particle ejection period, the stable failure period, and the complete collapse period; as burial depth increases, the failure mode transitions from a composite tensile–shear crack type to a shear crack-dominated type, with the ratio of shear cracks to tensile cracks exhibiting quadratic growth and reduction, respectively; the particle ejection stage is characterised by low-frequency, low-amplitude signals, corresponding to the microcrack initiation stage, while the stable failure stage exhibits a sharp increase in low-frequency, high-amplitude signals, reflecting macrocrack propagation characteristics, with the spatial evolution of their locations ultimately forming a penetrating oblique shear failure zone; and peak stress analysis indicates that as burial depth increases, peak stress during the particle ejection phase first increases and then decreases, while peak stress during the stable failure phase first decreases and then stabilises. The duration of the pre-instability calm phase shows a significant negative correlation with burial depth. The research findings provide a theoretical basis for controlling tunnel rock mass stability and disaster warning. Full article

Urban unmanned aerial vehicle (UAV) surveillance faces significant obstacles due to visual obstructions, inadequate lighting, small target dimensions, and acoustic signal interference caused by environmental noise and multipath propagation. To address these issues, this study proposes a multimodal detection framework that integrates an efficient YOLOv11-based visual detection module—trained on a comprehensive dataset containing over 50,000 UAV images—with a Capon beamforming-based acoustic imaging system using a 144-element spiral-arm microphone array. Adaptive compensation strategies are implemented to improve the robustness of each sensing modality, while detections results are validated through intersection-over-union and angular deviation metrics. The angular validation is accomplished by mapping acoustic direction-of-arrival estimations onto the camera image plane using established calibration parameters. Experimental evaluation reveals that the fusion system achieves outstanding performance under optimal conditions, exceeding 99% accuracy. However, its principal advantage becomes evident in challenging environments where individual modalities exhibit considerable limitations. The fusion approach demonstrates substantial performance improvements across three critical scenarios. In low-light conditions, the fusion system achieves 78% accuracy, significantly outperforming vision-only methods which attain only 25% accuracy. Under occlusion scenarios, the fusion system maintains 99% accuracy while vision-only performance drops dramatically to 9.75%, though acoustic-only detection remains highly effective at 99%. In multi-target detection scenarios, the fusion system reaches 96.8% accuracy, bridging the performance gap between vision-only systems at 99% and acoustic-only systems at 54%, where acoustic intensity variations limit detection capability. These experimental findings validate the effectiveness of the complementary fusion strategy and establish the system’s practical value for urban airspace monitoring applications. Full article