Use Of Acoustic Sensors Research Articles

Living Together, Singing Together: Revealing Similar Patterns of Vocal Activity in Two Tropical Songbirds Applying BirdNET.

In recent years, several automated and noninvasive methods for wildlife monitoring, such as passive acoustic monitoring (PAM), have emerged. PAM consists of the use of acoustic sensors followed by sound interpretation to obtain ecological information about certain species. One challenge associated with PAM is the generation of a significant amount of data, which often requires the use of machine learning tools for automated recognition. Here, we couple PAM with BirdNET, a free-to-use sound algorithm to assess, for the first time, the precision of BirdNET in predicting three tropical songbirds and to describe their patterns of vocal activity over a year in the Brazilian Pantanal. The precision of the BirdNET method was high for all three species (ranging from 72 to 84%). We were able to describe the vocal activity patterns of two of the species, the Buff-breasted Wren (Cantorchilus leucotis) and Thrush-like Wren (Campylorhynchus turdinus). Both species presented very similar vocal activity patterns during the day, with a maximum around sunrise, and throughout the year, with peak vocal activity occurring between April and June, when food availability for insectivorous species may be high. Further research should improve our knowledge regarding the ability of coupling PAM with BirdNET for monitoring a wider range of tropical species.

Use Brain-Like Audio Features to Improve Speech Recognition Performance

Speech recognition plays an important role in the field of human-computer interaction through the use of acoustic sensors, but speech recognition is technically difficult, has complex overall logic, relies heavily on neural network algorithms, and has extremely high technical requirements. In speech recognition, feature extraction is the first step in speech recognition for recovering and extracting speech features. Existing methods, such as Meier spectral coefficients (MFCC) and spectrograms, lose a large amount of acoustic information and lack biological interpretability. Then, for example, existing speech self-supervised representation learning methods based on contrast prediction need to construct a large number of negative samples during training, and their learning effects depend on large batches of training, which requires a large amount of computational resources for the problem. Therefore, in this paper, we propose a new feature extraction method, called SHH (spike-H), that resembles the human brain and achieves higher speech recognition rates than previous methods. The features extracted using the proposed model are subsequently fed into the classification model. We propose a novel parallel CRNN model with an attention mechanism that considers both temporal and spatial features. Experimental results show that the proposed CRNN achieves an accuracy of 94.8% on the Aurora dataset. In addition, audio similarity experiments show that SHH can better distinguish audio features. In addition, the ablation experiments show that SHH is applicable to digital speech recognition.

Fault Classification in Vehicle Power Transmission using Machine Learning

The work describes the application of machine learning (ML) to the categorization and diagnosis of vehicle faults in the power transmission system. For each failure characteristic condition, a machine learning algorithm may be employed to categorize their separate diagnostic elements. The use of acoustic sensors can be used to create a real-time detection approach for vehicle engines and transmission systems. Previously, it was contacting drivers or obscuring services based on vehicle maintenance and driving safety degree under internet of vehicle (IoV) needs. The car's variable acoustic signals are captured and categorised utilising fuzzy logic controllers through the data acquisition device (DAQ) in this manner (FLC). Further, the results are optimized using Particle Swarm Optimization (PSO) technique. While previous systems used 15 fault conditions, we have just used 8 conditions to obtain results.

A PORTABLE OPTO-ACOUSTIC SURVEY SOLUTION FOR MAPPING OF UNDERWATER TARGETS

Abstract. During underwater investigations, whatever the mission objective and the type of vehicle, obstacles detection and avoidance are essential tasks. They can either represent a target of interest that is the object of the mission or, on the contrary, represent obstacles that can hinder or affect the navigation of the vehicle. The underwater optical cameras that are usually fitted to underwater vehicles only offer a narrow field of view. The absorption of electromagnetic waves in the first few meters and the diffusion of light by the particles limit the use of these sensors to only a few meters range. The use of acoustic sensors, such as the forward looking sonar (FLS), is then necessary to enlarge the volume in which a target can be detected during the progression of the vehicle. Traditionally, sonars featured mechanical rotating parts, but lately bidirectional forward looking sonar, which directly produces a 2D image of the area, are becoming more and more common. Although these sonars can operate at frequency higher than 1MHz, their spatial resolution remains much lower if compared to current optical sensors and can be insufficient to identify and characterize a target. The combination of these two sensors in an operational scenario is essential to take advantage of each technology. In this paper we describe a low cost, multi-sensor, underwater survey solution for the identification, tracking, and 3D mapping of targets. After a description of the architecture of the opto-acoustics data acquisition and processing platform, we will focus on the calibration of the rigid transformation between the two sensors.

Application of acoustic intelligent leak detection in an urban water supply pipe network

Abstract Different leakage detection technologies present different efficiency and precision of leakage detection in water distribution systems due to their own properties. This study aimed to investigate the use of acoustic sensors to locate the exact position of leaks, which work 24 hours per day in different modes, i.e. fixed installation and mobile exploration. The results showed that the maximum distance between the acoustic sensors installed on the pipeline was 380 m. Field application results indicated that detecting threshold of the distance was 300 m and the intensity ratio of leaking state noise (LSN) to background noise was 1.9 respectively. The pipeline length by manual hunting area (MHA) is 1.3 times longer than the acoustic logger tested area (ALTA), but the detected leakage points in MHA is 20% less than in ALTA. Furthermore, the cost of leakage detection in MHA was about 6,000 yuan/detected leakage point. That in ALTA was about 2,500 yuan/detected leakage point. The case study also indicates that the acoustic logger is a promising tool with the advantage of lower cost and faster detection, compared to manual ground listening with a sound stick. The acoustic leakage detection method can detect the leakage in different sized pipelines, whereas the manual detection was concentrated in small-sized pipelines.

Acoustic Sensor Data Flow for Cultural Heritage Monitoring and Safeguarding.

Cultural heritage sites, apart from being the tangible link to a country’s history and culture, actively contribute to the national economy, offering a foundation upon which cultural tourism can develop. This importance at the cultural and economic level, advocates for the need for preservation of cultural heritage sites for the future generations. To this end, advanced monitoring systems harnessing the power of sensors are deployed near the sites to collect data which can fuel systems and processes aimed at protection and preservation. In this paper we present the use of acoustic sensors for safeguarding cultural sites located in rural or urban areas, based on a novel data flow framework. We developed and deployed Wireless Acoustic Sensors Networks that record audio signals, which are transferred to a modular cloud platform to be processed using an efficient deep learning algorithm (f1-score: 0.838) to identify audio sources of interest for each site, taking into account the materials the assets are made of. The extracted information is presented exploiting the designed STORM Audio Signal ontology and then fused with spatiotemporal information using semantic rules. The results of this work give valuable insight to the cultural experts and are publicly available using the Linked Open Data format.

Detection and estimation of population density of bean weevils (Coleoptera: Bruchidae) in stored pulses via bioacoustic analysis: Poster

Stored product insects, produce acoustic emissions by moving, feeding or ovipositing inside the grain mass. These sounds can be used not only for detection purposes, but also for population density estimation. Acoustic emissions of adults of Acanthoscelides obtectus (Coleoptera: Bruchidae) and Callosobruchus maculatus (Coleoptera: Chrysomelidae) were recorded infesting various pulses in varying population densities from 1 to 500 adults/kg product. The acoustic analysis system is being described. Population density, type of grain and pest species had significant influence on the number of sounds. The system was 100% precise in negative predictions and considerably successful in positive predictions. The system was very accurate (80-100%) in detecting insect presence even in the “critical” density of 1 adult/kg product, the most common threshold for classifying a stored mass as “infested” or “not infested”. Our study suggests that automatic monitoring of the infestation state in bulk grain is feasible in small containers. This kind of service can assist reliable decision making if it can be transferred to larger storage establishments (eg. silos). Our results are discussed on the basis of enhancing the use of acoustic sensors as a decision support system in stored product IPM.

Estimation of population density of stored grain pests via bioacoustic detection

The potential of bioacoustics in estimating the population density of insect pests inside the stored grain mass was evaluated in the laboratory. We used a piezoelectric sensor and a portable acoustic emission amplifier connected to a computer for recording acoustic emissions of insects. The software analyses the vibration recordings of the piezoelectric sensor, performs signal parameterization and eventually classification of the infestation severity inside the grain mass in four classes, namely: Class A (densities ≤1 adult/kgr), Class B (densities 1–2 adults/kgr), Class C (densities 2–10 adults/kgr) and Class D (densities >10 adults/kgr). Adults of the most important beetle pests of stored cereals and pulses, in various population densities (1, 2, 10, 20, 50, 100, 200 & 500 beetle adults/kgr grain) were used during the present study. The linear model was very effective in describing the relationship between population density and number of sounds. Multiple classifiers were used to evaluate the accuracy of bioacoustics on predicting the pest density given per minute counts of vibration pulses. Based on our results, our system's performance was very satisfactory in most cases (∼68%) given that probabilities for successful prediction typically exceeding 70%. Our study suggests that automatic monitoring of infestations in bulk grain is feasible in small containers. This kind of service can assist with reliable decision making if it can be transferred to larger storage establishments (e.g. silos). Our results are discussed on the basis of enhancing the use of acoustic sensors as a decision support system in stored product IPM.

Recent Developments in the use of Acoustic Sensors and Signal Processing Tools to Target Early Infestations of Red Palm Weevil in Agricultural Environments1

ABSTRACT Much of the damage caused by red palm weevil larvae to date palms, ornamental palms, and palm offshoots could be mitigated by early detection and treatment of infestations. Acoustic technology has potential to enable early detection, but the short, high-frequency sound impulses produced by red palm weevil larvae can be difficult to distinguish from certain similar sounds produced by other insects or small animals, or by wind-induced tapping noises. Considerable research has been conducted to develop instruments and signal processing software that selectively amplify insect-produced sounds and identify signal features that distinguish sounds produced by a particular target insect from those produced by other causes. Progress has been made in identifying unique spectral and temporal patterns in the sounds produced by larvae during movement and feeding activities. This report describes some of the new instrumentation and signal analyses available for early, reliable detection of red palm weevil larv...

Acoustic-based modal filtering of orthogonal radiating functions for global error sensing: Part I theory and simulation

This is the first of two companion papers which summarise the theoretical and experimental work aimed at developing a generalised, acoustic-based sensing strategy for free and semi free field problems. The aim of the work is the design of practical acoustic sensing systems for active noise control of large complex noise sources, based on data fusion of a large number of sensor signals. A wide breath of literature illustrates several practical advantages to pursuing a sensing system which measures orthogonal functions with respect to a global error, and how a large number of point sensors are required in the filtering process. For this reason we examine modal filtering of orthogonal functions for two-dimensional noise sources and highlight the practicalities of sensing systems which measure the associated constituents. We compare three variations of orthogonally radiating shapes based on structural modes, structural elements and combinations of in-/out-of-phase acoustic monopoles. Comparisons are made based on the number of constituents required to estimate 90% of radiated power; the modal filtering weights frequency dependence; and simulated decompositions of a sound pressure field to radiated power. Of the sensing strategies which are structural specific, we extend them to facilitate the use of acoustic sensors to measure the orthogonal “structural” patterns.

Passive sensing with acoustics on the battlefield

This paper reports military uses of passive acoustic sensing. Physical phenomema and boundary conditions governing the use of acoustic sensors in military systems are discussed. Based on field work, realistic limits for various parameters are given. This enables the reader to understand design characteristics for acoustic sensor systems and to predict their performance under given conditions. A selection of advanced acoustic sensor systems for military use is presented along with the necessary background information. Since cost effectiveness and ease of operation are important advantages for military systems, acoustic sensing offers a considerable potential. No other sensing method can rival acoustic sensing in its unique capability to detect targets beyond line of sight while being passive and easily camouflaged.

音響センサを用いた配管の形状および長さ計測

音響センサを用いた配管の形状および長さ計測

Tasks for a sensor-controlled robot

Several advanced applications of industrial robots in the areas of material handling, welding, and assembly were described. Emphasis was placed on potential improvements that could be made in these application areas through the use of acoustic sensors to gain additional information about the processes and working environment of the industrial robot. The objective of this paper was to stimulate future innovative work in the application of acoustic sensors and sensing systems to industrial robots.