Search

Marine mammal acoustic signal recognition is a key technology for species conservation and ecological environment monitoring. Aiming at the complex and changing marine environment, and because the traditional recognition method based on a single feature input has the problems of poor environmental adaptability and low recognition accuracy, this paper proposes a dual-feature fusion learning method. First, dual-domain feature extraction is performed on marine mammal acoustic signals to overcome the limitations of single feature input methods by interacting feature information between the time-frequency domain and the Delay-Doppler domain. Second, this paper constructs a dual-feature fusion learning target recognition model, which improves the generalization ability and robustness of mammal acoustic signal recognition in complex marine environments. Finally, the feasibility and effectiveness of the dual-feature fusion learning target recognition model are verified in this study by using the acoustic datasets of three marine mammals, namely, the Fraser's Dolphin, the Spinner Dolphin, and the Long-Finned Pilot Whale. The dual-feature fusion learning target recognition model improved the accuracy of the training set by 3% to 6% and 20% to 23%, and the accuracy of the test set by 1% to 3% and 25% to 38%, respectively, compared to the model that used the time-frequency domain features and the Delay-Doppler domain features alone for recognition. [ABSTRACT FROM AUTHOR]

Indoor localization is still nowadays a challenge with room to improve. Even though there are many different approaches that have evidenced as effective, most of them require specific hardware or infrastructure deployed along the building that can be discarded in many potential scenarios. Others that do not require such on-site infrastructure, like inertial navigation-based systems, entail certain accuracy problems due to the accumulation of errors. However, this error-accumulation can be mitigated using beacons that support the recalibration of the system. The more frequently beacons are detected, the smaller will be the accumulated error. In this work, we evaluate the use of the noise signature of the rooms of a building to pinpoint the current location of a low-cost Android device. Despite this strategy is not a complete indoor localization system (two rooms could share the same signature), it allows us to generate beacons automatically. The noise recorded by the device is preprocessed performing audio filtering, audio frame segmentation, and feature extraction. We evaluated binary (determining if the ambient sound recording belonged to a specific room) and multi-class (identifying which room an ambient noise recording belonged to by comparing it amongst the remaining 18 rooms from the original 19 rooms sampled) classification methods. Our results indicate that the two Stacking techniques and K-Nearest Neighbor (KNN) machine learning classifier are the most successful methods in binary classification with an average accuracy of 99.19%, 99,08%, and 99.04%. In multi-class classification the average accuracy for KNN is 90.77%, and 90.52% and 90.15% for both Voting techniques. [ABSTRACT FROM AUTHOR]

Several advantages of directed energy deposition-arc (DED-arc) have garnered considerable research attention including high deposition rates and low costs. However, defects such as discontinuity and pores may occur during the manufacturing process. Defect identification is the key to monitoring and quality assessments of the additive manufacturing process. This study proposes a novel acoustic signal-based defect identification method for DED-arc via wavelet time–frequency diagrams. With the continuous wavelet transform, one-dimensional (1D) acoustic signals acquired in situ during manufacturing are converted into two-dimensional (2D) time–frequency diagrams to train, validate, and test the convolutional neural network (CNN) models. In this study, several CNN models were examined and compared, including AlexNet, ResNet-18, VGG-16, and MobileNetV3. The accuracy of the models was 96.35%, 97.92%, 97.01%, and 98.31%, respectively. The findings demonstrate that the energy distribution of normal and abnormal acoustic signals has significant differences in both the time and frequency domains. The proposed method is verified to identify defects effectively in the manufacturing process and advance the identification time. [ABSTRACT FROM AUTHOR]

The purpose of this study is to put forward a feature extraction and pattern recognition method for the flow noise signal of natural gas pipelines in view of the complex situation brought by the rapid development and expansion of urban natural gas infrastructure in China, especially in the case that there are active and abandoned pipelines, metal and nonmetal pipelines, and natural gas, water and power pipelines coexist in the underground of the city. Because the underground situation is unknown, gas leakage incidents caused by natural gas pipeline rupture occur from time to time, posing a threat to personal safety. Therefore, the motivation of this study is to provide a feasible method to accelerate the aging, renewal and transformation of urban natural gas pipelines to ensure the safe operation of urban natural gas pipeline network and promote the high-quality development of urban economy. Through the combination of experimental test and numerical simulation, this study establishes a database of urban natural gas pipeline flow noise signals, and uses principal component analysis (PCA) to extract the characteristics of flow noise signals, and develops a mathematical model for feature extraction. Then, a classification and recognition model based on backpropagation neural network (BPNN) is constructed, which realizes the detection and recognition of convective noise signals. The research results show that the theoretical method based on acoustic feature analysis provides guidance for the orderly and safe construction of urban natural gas pipeline network and ensures its safe operation. The research conclusion shows that through the simulation analysis of 75 groups of gas pipeline flow noise under different working conditions. Combined with the experimental verification of ground flow noise signals, the feature extraction and pattern recognition method proposed in this study has a recognition accuracy of up to 97% under strong noise background, which confirms the accuracy of numerical simulation and provides theoretical basis and technical support for the detection and recognition of urban gas pipeline flow noise. [ABSTRACT FROM AUTHOR]

This paper studies the dynamics of the development of laser breakdown plasma in aqueous colloids of dysprosium nanoparticles by analyzing the time patterns of plasma images obtained using a high-speed streak camera. In addition, the distribution of plasma flashes in space and their luminosity were studied, and the amplitude of acoustic signals and the rate of generation of new chemical products were studied depending on the concentration of dysprosium nanoparticles in the colloid. Laser breakdown was initiated by pulsed radiation from a nanosecond Nd:YAG laser. It is shown that the size of the plasma flash, the speed of motion of the plasma–liquid interface, and the lifetime of the plasma flash decrease with an increasing concentration of nanoparticles in the colloid. In this case, the time delay between the beginning of the laser pulse and the moment the plasma flash reaches its maximum intensity increases with increasing concentrations of nanoparticles. Varying the laser fluence in the range from 67 J/cm2 to 134 J/cm2 does not lead to noticeable changes in these parameters, due to the transition of the breakdown plasma to the critical regime. For dysprosium nanoparticles during laser breakdown of colloids, a decrease in the yield of hydrogen peroxide and an increase in the rate of formation of hydroxyl radicals per water molecule, characteristic of nanoparticles of rare earth metals, are observed, which may be due to the participation of nanoparticles and hydrogen peroxide in reactions similar to the Fenton and Haber–Weiss reactions. [ABSTRACT FROM AUTHOR]

The paper presents the experimental results into the development of a multi-channel system for monitoring and quality assurance of the multi-wire submerged arc welding (SAW) process for the manufacture of large diameter pipes. Process signals such as welding current, arc voltage and the acoustic signal emitted from the weld zone are recorded and processed to provide information on the stability of the welding process. It was shown by the experiments that the acoustic pattern of the SAW process in a frequency range between 30 Hz and 2.5 kHz contains the most diagnostic information. The on-line quality assessment of the weld seam produced is carried out in combination with methods of artificial intelligence (AI). From the results obtained, it can be concluded that the use of the latest concepts in welding and automation technology, combined with the high potential of AI, can achieve a new level of quality assurance in pipe manufacturing. [ABSTRACT FROM AUTHOR]

A survey of recent taxonomic studies of birds that included acoustic trait analyses reveals that most studies have not archived the sound recordings that support their conclusions, despite the current availability of online, publicly available collections of bird sounds. In addition, bird sound recordings have often been cited without unique accession numbers that permit unambiguous sample identification and in considerably less detail than other types of samples, such as museum specimens or genetic samples. Both this lack of data openness and the way acoustic samples have been cited undermine the methodological rigor that otherwise characterizes many of these studies, and much invaluable biological data are likely to be lost over time if bird sound recordings are not archived in long-term collections. I suggest that these problems can be easily addressed by embracing the open data movement and adopting some best practices that are widely used in other fields. Just as study skins and DNA sequences are required to be deposited in publicly available collections such as natural history museums and the GenBank, respectively, sound recordings used in taxonomic studies with acoustic trait analyses should be archived in publicly available collections as a condition for publication of associated results. Authors of taxonomic studies involving sounds should archive their sound recordings and provide unique accession numbers for sound recordings examined, and journals and reviewers should ensure that authors have done so. By embracing the open data movement, research studying avian acoustic signals is expected to become more transparent, reproducible, and useful. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) enabled Underwater Wireless Sensor Networks (UWSNs) to emerge for applications like underwater imagining, underwater equipment monitoring, marine data collection, etc. These all applications relied on the routing method for data transmissions. However, a designing routing protocol for UWSNs using acoustic should address lower throughput, longer delay, high energy consumption, and collisions. We propose the novel Hybrid Optimization-based Cooperative Opportunistic Routing (HOCOR) for improving the performance of IoT-enabled UWSNs. As the Swarm Intelligence (SI) methods have already proven effective for routing and clustering problems of various wireless networks, we aim to design a hybrid SI technique using popular Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) methods. In this hybrid SI technique, we exploit the benefits of both GA and PSO for optimal forwarding relay selection. In HOCOR, hybrid optimization aims at forming a reliable opportunistic data transmission route from any underwater sensor node to the surface sink. The hybrid optimization solves the problem of maximizing the Quality of Service (QoS) and network lifetime using the novel fitness function while evaluating each sensor node. The fitness function of the hybrid optimization algorithm computes the four parameters of each underwater sensor node such as underwater distance, node connectivity, packet transmission ability, and residual energy. We select these parameters to avoid packet collisions and void communications in UWSNs. Simulation results show that the HOCOR protocol outperforms the state-of-art methods in terms of the average throughput, Packet Delivery Ratio (PDR), average energy consumption, and average delay. [ABSTRACT FROM AUTHOR]

Copyright of Informatics Control Measurement in Economy & Environment Protection / Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska is the property of Lublin University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The geomagnetic field (GMF) is a worldwide source of compass cues used by animals and humans alike. The inclination of GMF flux lines also provides information on geomagnetic latitude. A long-disputed question, however, is whether horizontal gradients in GMF intensity, in combination with changes in inclination, provide bicoordinate "map" information. Multiple sources contribute to the total GMF, the largest of which is the core field. The ubiquitous crustal field is much less intense, but in both land and marine settings is strong enough at low altitudes (< 700 m; sea level) to mask the core field's weak N–S intensity gradient (~ 3–5 nT/km) over 10 s to 100 s of km. Non-orthogonal geomagnetic gradients, the lack of consistent E–W gradients, and the local masking of core-field intensity gradients by the crustal field, therefore, are grounds for rejection of the bicoordinate geomagnetic "map" hypothesis. In addition, the alternative infrasound direction-finding hypothesis is briefly reviewed. The GMF's diurnal variation has long been suggested as a possible Zeitgeber (timekeeper) for circadian rhythms and could explain the GMF's non-compass role in the avian navigational system. Requirements for detection of this weaker diurnal signal (~ 20–50 nT) might explain the magnetic alignment of resting and grazing animals. [ABSTRACT FROM AUTHOR]

Geographical variation in animals’ acoustic signals has received much attention. However, few studies have compared the patterns and underlying selective forces driving geographical divergence of vocalizations with similar and different functions within the same species. Also, the social consequences of geographical divergence in acoustic signals are still rather poorly understood. Here we recorded three types of social calls of male great Himalayan leaf-nosed bats (Hipposideros armiger) across eight colonies in China. Two calls share similar functions and the third has a function distinct from the other two. We examined the patterns and causes of geographical variation of each of these calls. We found that all three calls had significant geographic variation with similar patterns of spatial variation. Only one of the two social calls with similar functions was found to be affected by genetic drift, while the other two calls were not affected by selection, drift, or morphological constraints. Furthermore, we found that bats could discriminate between vocalizations of their own colony and those of an allopatric colony. Overall, these results suggest that acoustic signals with similar functions may be shaped by different driving forces and acoustic signals with different functions may exhibit similar geographical patterns. This study expands our limited knowledge of the patterns of geographical variation of vocalizations emitted at different emotional states and highlights the importance of comparing simultaneously patterns and causes of geographical divergence of vocalizations with similar and different functions.Significance statement: This study provides the empirical evidence suggesting that calls with a similar function may fail to co-vary and alternatively calls with a different function may co-vary. Moreover, we show that bats can discriminate between calls of their own colony from those of a foreign colony. These results expand our limited knowledge of the patterns of geographical variation of vocalizations uttered under different emotional states and the nature of functional drivers that influence the evolution of communicative systems. [ABSTRACT FROM AUTHOR]

The purpose of this study is to put forward a feature extraction and pattern recognition method for the flow noise signal of natural gas pipelines in view of the complex situation brought by the rapid development and expansion of urban natural gas infrastructure in China, especially in the case that there are active and abandoned pipelines, metal and nonmetal pipelines, and natural gas, water and power pipelines coexist in the underground of the city. Because the underground situation is unknown, gas leakage incidents caused by natural gas pipeline rupture occur from time to time, posing a threat to personal safety. Therefore, the motivation of this study is to provide a feasible method to accelerate the aging, renewal and transformation of urban natural gas pipelines to ensure the safe operation of urban natural gas pipeline network and promote the high-quality development of urban economy. Through the combination of experimental test and numerical simulation, this study establishes a database of urban natural gas pipeline flow noise signals, and uses principal component analysis (PCA) to extract the characteristics of flow noise signals, and develops a mathematical model for feature extraction. Then, a classification and recognition model based on backpropagation neural network (BPNN) is constructed, which realizes the detection and recognition of convective noise signals. The research results show that the theoretical method based on acoustic feature analysis provides guidance for the orderly and safe construction of urban natural gas pipeline network and ensures its safe operation. The research conclusion shows that through the simulation analysis of 75 groups of gas pipeline flow noise under different working conditions. Combined with the experimental verification of ground flow noise signals, the feature extraction and pattern recognition method proposed in this study has a recognition accuracy of up to 97% under strong noise background, which confirms the accuracy of numerical simulation and provides theoretical basis and technical support for the detection and recognition of urban gas pipeline flow noise.

Cartilage degeneration is a serious health condition in modern society, leading to problems in mobility and significant reduction in the quality of life of patients of all ages. It is mainly caused by obesity, workload, sports or trauma to the joint. Proper diagnosis is crucial to implement appropriate treatment to stop the further degeneration of the tissue. Usually the assessment is performed by using magnetic resonance. This paper describes the design and application of an alternative measurement system for vibroartography of the knee joint. The use of such device allows for fast, safe, easy and cheap assessment of joint condition, which in turn can lead to proper treatment planning. Similar portable systems can be rapidly deployed and used by entry level medical staff in hospitals, clinics or at patient’s home. The system consists of an orthosis, set of three vibroacoustic sensors, encoder for reading knee position, microcontroller with galvanic barrier and battery power and a computer for data storage and processing. The system is light, simple and portable. Data is recorded in both closed and open kinematic chains. Results show over 90% diagnostic accuracy based on the data obtained in the process of testing this device. In the future, the system will be further miniaturized and completely placed on the orthosis, leading to more portability and diagnostic merit.

Unmanned aerial vehicles, also known as drones, have seen increasing interest in recent years. This surge of interest is based on technological advancements, enhanced performance, affordability, and their large array of applications. Despite their utility in various applications, drones could also be used for malicious intent. The increasing concern regarding malicious drones triggers the use of various technologies and countermeasures, including drone detection and counter-drone systems. In this paper, we raise concerns about the malicious use of drone systems by providing a brief description of the major security threats. We also present the architecture of unmanned aerial systems, drone types, and their communication methods. We provide an in-depth overview of various drone detection techniques including vision-based, radio-frequency-based, and audio-based techniques, and discuss recent studies that address this issue using machine learning and deep learning models. We highlight the importance of using a hybrid approach for more accurate results.

Marine mammal acoustic signal recognition is a key technology for species conservation and ecological environment monitoring. Aiming at the complex and changing marine environment, and because the traditional recognition method based on a single feature input has the problems of poor environmental adaptability and low recognition accuracy, this paper proposes a dual-feature fusion learning method. First, dual-domain feature extraction is performed on marine mammal acoustic signals to overcome the limitations of single feature input methods by interacting feature information between the time-frequency domain and the Delay-Doppler domain. Second, this paper constructs a dual-feature fusion learning target recognition model, which improves the generalization ability and robustness of mammal acoustic signal recognition in complex marine environments. Finally, the feasibility and effectiveness of the dual-feature fusion learning target recognition model are verified in this study by using the acoustic datasets of three marine mammals, namely, the Fraser’s Dolphin, the Spinner Dolphin, and the Long-Finned Pilot Whale. The dual-feature fusion learning target recognition model improved the accuracy of the training set by 3% to 6% and 20% to 23%, and the accuracy of the test set by 1% to 3% and 25% to 38%, respectively, compared to the model that used the time-frequency domain features and the Delay-Doppler domain features alone for recognition.

Flight calls are short vocalizations frequently associated with migratory behavior that may maintain group structure, signal individual identity, and facilitate intra- and interspecific communication. In this study, Magnolia Warbler (Setophaga magnolia) flight call characteristics varied significantly by season and recording location, but not age or sex, and an individual’s flight calls were significantly more similar to one another than to calls of other individuals. To determine if flight calls encode traits of the signaling individual during migration, we analyzed acoustic characteristics of the calls from the nocturnally migrating Magnolia Warbler. Specifically, we analyzed calls recorded from temporarily captured birds across the northeastern United States, including Appledore Island in Maine, Braddock Bay Bird Observatory in New York, and Powdermill Avian Research Center in Pennsylvania to quantify variation attributable to individual identity, sex, age, seasonality, and recording location. Overall, our findings suggest that Magnolia Warbler flight calls may show meaningful individual variation and exhibit previously undescribed spatiotemporal variation, providing a basis for future research. [ABSTRACT FROM AUTHOR]

Copyright of Caldasia is the property of Universidad Nacional de Colombia and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In water-water power reactors (VVERs), loose, weakly fixed, and foreign objects can appear in the main circulation circuit (MCC) and pose a threat to the integrity of the equipment and the safety of the reactor. In order to detect these items early, the reactor is equipped with a loose parts monitoring system (LPMS). In addition to the detection of loose/weakly fixed parts, the LPMS functions include the classification of reported events. The possibility of applying the classification algorithm is based on the fact that the signals from the triggering of standard equipment are characterized by a high degree of repeatability, even in the presence of noise, while a loose object is characterized by a large stochastic component, and its own deterministic class cannot be formed for it. Classification reduces false alarms and allows signals from routine operations to be detected; the signals from the same process should be assigned to the same class. The idea of the article is to train the LPMS on some archive of data characterizing routine reactor operation, to create a library of basic classes, and to set the boundaries of each class in order to, on one hand, take into account the possible variability of signal parameters due to noise. Having defined the basic classes, we can assert that, if a newly received signal falls into one of the classes, it reflects routine reactor operation, while signals that do not fall into any of the classes can be from the appearance of a loose/weakly fixed item. The article analyzes a set of events accumulated in the archive of one of the operating LPMS. Their clustering is performed, as a result of which classes of events corresponding to routine unit operations are singled out. For each class, the center of the class and permissible limits of deviations from the center are calculated. All obtained class centers are benchmarks by which the LPMS in real time either classifies a newly detected event or characterizes it as unclassified. [ABSTRACT FROM AUTHOR]

This paper aims to develop an effective AI-driven method to predict the maturity level of coconut (Cocos nucifera) fruits using acoustic signals. The proposed sound-based autonomous approach exploits various deep learning models, including customized CNN pretrained networks, i.e., the ResNet50, InceptionV3, and MobileNetV2, models for maturity level classification of the coconuts. The proposed study also demonstrates the effectiveness of various deep learning models to automatically predict the maturity of coconuts into three classes, i.e., premature, mature, and overmature coconuts, for inspecting the coconut fruits by using a small amount of input acoustic data. We use an open-access dataset containing a total of 122 raw acoustic signals, which is the result of knocking 122 coconut samples. The results achieved by the proposed method for coconut maturity prediction are found to be promising, which enables producers to accurately determine the yield and product quality. [ABSTRACT FROM AUTHOR]

Partial discharge (PD) is a common issue in power transformers that can lead to catastrophic failures if left undetected. Time reversal (TR) is a well-known technique in signal processing that can reconstruct signals by reversing the direction of time. The paper investigates the use of time reversal and the integration of time reversal with convolution neural networks (CNNs) for diagnosing PD in power transformers. We compare the performance of these techniques on a dataset of PD signals collected from power transformers. We propose a novel method of using time reversal as a pre-processing step to improve the accuracy of CNNs on noisy or distorted signals. Our experimental results demonstrate that this approach can significantly enhance the performance of CNNs on various datasets, including speech, audio, and image datasets. This paper provides a novel approach to signal processing and demonstrates the potential of time reversal as a pre-processing step in CNNs. [ABSTRACT FROM AUTHOR]

The calling songs and acoustic behavior features of male grasshoppers of the genus Eclipophleps Tarbinsky of the tribe Hypernephiini are described for the first time. New data on the distribution of Eclipophleps glacialis Bey-Bienko in Russia, as well as of E. kerzhneri Mistshenko and E. confinis Mistshenko in Mongolia are given. [ABSTRACT FROM AUTHOR]

Several advantages of directed energy deposition-arc (DED-arc) have garnered considerable research attention including high deposition rates and low costs. However, defects such as discontinuity and pores may occur during the manufacturing process. Defect identification is the key to monitoring and quality assessments of the additive manufacturing process. This study proposes a novel acoustic signal-based defect identification method for DED-arc via wavelet time–frequency diagrams. With the continuous wavelet transform, one-dimensional (1D) acoustic signals acquired in situ during manufacturing are converted into two-dimensional (2D) time–frequency diagrams to train, validate, and test the convolutional neural network (CNN) models. In this study, several CNN models were examined and compared, including AlexNet, ResNet-18, VGG-16, and MobileNetV3. The accuracy of the models was 96.35%, 97.92%, 97.01%, and 98.31%, respectively. The findings demonstrate that the energy distribution of normal and abnormal acoustic signals has significant differences in both the time and frequency domains. The proposed method is verified to identify defects effectively in the manufacturing process and advance the identification time.

Detecting and localizing leakages in underground water pipelines continue to be challenging in large-scale water distribution networks (WDNs) having a low density of acoustic sensors per unit pipeline. Many previous acoustic research analyses have been restricted to either (1) lab-scale WDN setups having simulated leakage conditions, or (2) field-scale WDNs with high densities of acoustic sensors. To address the current challenges, this study develops a generic and practical acoustic data analysis framework to analyze acoustics signals for leakage detection and localization in large-scale WDNs, where the proposed framework encompasses multi-stage systematic analyses, namely: (1) data quality assessment; (2) acoustic features generation and analysis; (3) leakage event detection; and (4) leakage event localization. In collaboration with Public Utility Board (PUB), Singapore's National Water Agency, our proposed framework has been verified in large-scale WDNs in Singapore having more than 1,100 km of underground water pipelines and 82 permanently installed monitoring stations, each of which is instrumented to measure acoustics, via hydrophone equipment, pressure, and water quality parameters, and by using historical data collected between August 1, 2019 and August 31, 2020, where numerous leakage events were reported to within 1,000 m, or less, connected pipelines from independent hydrophones. [ABSTRACT FROM AUTHOR]

Water scarcity as well as social and economic damages caused by the increasing amounts of non-revenue water in the water distribution networks (WDNs) have been prompting innovative solutions. A great deal of potable water is wasted due to leakage in the WDNs all over the world. Hence, various leak detection approaches have been explored, including the promising application of acoustic devices. Exploiting the benefits of technological advances in acoustic devices, signal processing, and machine learning (ML), this study aimed to develop a sophisticated system for leak detection in WDNs. Different from laboratory-based studies, this study was conducted on real WDNs in Hong Kong and lasted for about two years. Utilizing acoustic emissions acquired using wireless noise loggers, various ML algorithms were explored to develop inspection models for in-service and buried WDNs. ML classification algorithms can identify patterns in the acquired signals for leak and no-leak statuses. Thus, a combination of features describing acoustic signals in time and frequency domains was utilized to facilitate the development of ML models. Separately for metal and non-metal WDNs, ten well-known ML algorithms were used to develop leak detection models. The validation results demonstrate the promising application of noise loggers and ML for leak detection in real WDNs. Support Vector Machine (SVM), Artificial Neural Network (ANN), and Deep Learning (DL) leak detection models demonstrated a largely stable performance and a very good accuracy, particularly for new unlabelled cases. [ABSTRACT FROM AUTHOR]

Acoustic signalling plays a crucial role in mother–calf communication. Here, we describe the acoustic signalling of three free-living Antillean manatee mother and calf pairs and one trio. The mother–calf pairs/trio produced six call types. The call rate varied between the pairs. The pair that experienced human interaction during the recording period had the highest call rate. Additionally, the Squeak vocalisations produced by each mother–calf pair differed structurally. Our results indicate that age and human interaction may affect call rate and suggest the potential production of signature vocalisations by manatee mothers and calves. Our findings add to the current knowledge of manatee acoustic communication. [ABSTRACT FROM AUTHOR]

Condition monitoring in a centrifugal pump is a significant field of study in industry. The acoustic method offers a robust approach to detect cavitations in different pumps. As a result, an acoustic-based technique is used in this experiment to predict cavitation. By using an acoustic technique, detailed information on outcomes can be obtained for cavitation detection under a variety of conditions. In addition, various features are used in this work to analyze signals in the time domain using the acoustic technique. A signal in the frequency domain is also investigated using the fast Fourier method. This method has shown to be an effective tool for predicting future events. In addition, this experimental investigation attempts to establish a good correlation between noise characteristics and cavitation detection in a pump by using an acoustic approach. Likewise, it aims to find a good method for estimating cavitation levels in a pump based on comparing and evaluating different systems.

Acoustic sensors are widely deployed to detect hidden leakages in water distribution networks (WDNs). However, few studies have been conducted to quantitatively understand the dominant leakage acoustic characteristics, which are usually mixed with unknown environmental noises, coupled with the constraint of sparse deployment of acoustic sensors. In this paper, a comprehensive approach, that performs acoustic data feature analysis, is developed to detect pipe leakages in near real-time via a series of systematic analyses, namely: (1) data quality assessment; (2) features identifications; (3) outlier detection and event classification; and finally (4) near real-time leakage detection. The proposed solution has been tested on two major WDNs in Singapore having around 1,000 km of water pipelines installed with 74 permanently installed hydrophone sensors. The leakage detection results obtained from our case study demonstrate that the dominant leakage acoustic characteristics can be captured in lower intrinsic mode functions (IMFs), to within the frequency range of 100–750 Hz approximately, by decomposing the original acoustic signal. Systemwide leakage event detection and classification models are subsequently trained and tested on acoustic datasets collected over 13 historical months, where more than 70% F1-scores can be obtained from the emulated near real-time leakage detection analysis. HIGHLIGHTS Developed acoustic feature-based methodology for near real-time leakage event detection and classification.; Verified methodology with 74 permanently installed hydrophones in two water supply zones having 1,000 km water pipelines in Singapore.; Achieved F1-score of >70% for leakage event detection and classification analyses on imbalanced acoustic datasets collected over 13 months.;

This paper aims to develop an effective AI-driven method to predict the maturity level of coconut (Cocos nucifera) fruits using acoustic signals. The proposed sound-based autonomous approach exploits various deep learning models, including customized CNN pretrained networks, i.e., the ResNet50, InceptionV3, and MobileNetV2, models for maturity level classification of the coconuts. The proposed study also demonstrates the effectiveness of various deep learning models to automatically predict the maturity of coconuts into three classes, i.e., premature, mature, and overmature coconuts, for inspecting the coconut fruits by using a small amount of input acoustic data. We use an open-access dataset containing a total of 122 raw acoustic signals, which is the result of knocking 122 coconut samples. The results achieved by the proposed method for coconut maturity prediction are found to be promising, which enables producers to accurately determine the yield and product quality.

Acoustic communication is vital to the survival and fitness of many vertebrates. While successful communication is reliant on acoustic signals reaching an intended receiver and maintaining content fidelity, propagating signals are attenuated by environmental factors such as habitat type. The acoustic adaptation hypothesis (AAH) predicts that the acoustic properties of signals are selected for optimal transmission in the habitats in which they propagate. To date, consistent evidence to support the theory is lacking, but studies have typically been primarily based on localized datasets with small sample sizes. Citizen science is emerging as a potential means to overcome the challenges associated with broad‐scale sampling, allowing us to assess the validity of the AAH in frogs on a continental scale. We analysed the male advertisement calls of 674 individual banjo frogs (Limnodynastes dorsalis, L. dumerilii, L. interioris and L. terraereginae) from across their range, pairing these citizen science data with remotely sensed measures of habitat complexity. While we detected considerable variation in acoustic structure within and among banjo frog species, this was not strongly correlated with habitat complexity. Thus, we found no support for the AAH. However, with our study spanning an area of over 1.7 million km2, we conducted the largest‐scale test of the AAH in frogs to date, contributing to the global understanding of acoustic signal evolution. [ABSTRACT FROM AUTHOR]

Material identification is playing an increasingly important role in various sectors such as industry, petrochemical, mining, and in our daily lives. In recent years, material identification has been utilized for security checks, waste sorting, etc. However, current methods for identifying materials require direct contact with the target and specialized equipment that can be costly, bulky, and not easily portable. Past proposals for addressing this limitation relied on non-contact material identification methods, such as Wi-Fi-based and radar-based material identification methods, which can identify materials with high accuracy without physical contact; however, they are not easily integrated into portable devices. This paper introduces a novel non-contact material identification based on acoustic signals. Different from previous work, our design leverages the built-in microphone and speaker of smartphones as the transceiver to identify target materials. The fundamental idea of our design is that acoustic signals, when propagated through different materials, reach the receiver via multiple paths, producing distinct multipath profiles. These profiles can serve as fingerprints for material identification. We captured and extracted them using acoustic signals, calculated channel impulse response (CIR) measurements, and then extracted image features from the time–frequency domain feature graphs, including histogram of oriented gradient (HOG) and gray-level co-occurrence matrix (GLCM) image features. Furthermore, we adopted the error-correcting output code (ECOC) learning method combined with the majority voting method to identify target materials. We built a prototype for this paper using three mobile phones based on the Android platform. The results from three different solid and liquid materials in varied multipath environments reveal that our design can achieve average identification accuracies of 90% and 97%. [ABSTRACT FROM AUTHOR]

Many bird species vary their alarm calls according to the level of risk they face and this information can be used by receivers to respond to the mobbing event. Recent studies have also found that the number of callers can play an important role in the decision of subsequent individuals to join a mobbing event. We conducted a playback experiment to assess if differences in calling rate and number of callers elicit different behavioural responses in the house wren (Troglodytes aedon chilensis). We broadcast the alarm call of either one or two individuals, at different calling rates along the breeding season. We found that house wrens responded more frequently during playback of alarm calls at higher rates than during playback of calls at lower rates. However, focal individuals moved closer to the speaker when calls were played back at lower rates. There were no differences in the response of house wrens when we broadcast the calls of one or two individuals. These results suggest that call rates are an important element in the communication of danger in the house wren, rather than caller number. Significance statement: Mobbing is an anti-predator strategy observed in many species, and often involves the use of calls that can communicate to conspecifics and heterospecifics about the threat of the predator. Understanding the factors and cues that receivers use to respond is an important element in understanding communication between individuals. We studied the role of call rate and number of callers in the behavioural response to mobbing calls of individuals in the house wren during the breeding season. Using a playback experiment, we show that individuals respond more often to calls played at a high rate, regardless of the number of callers. House wrens' call rates vary according to the level of perceived risk, so our results show that receivers use this information to respond to mobbing calls. [ABSTRACT FROM AUTHOR]

The paper investigates the physicochemical processes that occur during laser-induced breakdown in colloids of gadolinium oxide nanoparticles of different concentrations. A monotonic change in the number of optical breakdowns, the average distance between the nearest breakdowns in the track of a single laser pulse, the average plasma size of a single optical breakdown, the integral luminosity of an optical breakdown plasma flash, the intensity of acoustic signals, and the rate of formation of dissociation products—O2, H2, OH•, and H2O2—is demonstrated. It is shown that the rate of formation of chemical products of the decomposition of H2O molecules under the action of breakdown when using nanoparticles of rare earth metals, in particular, gadolinium oxide, is the highest compared to other materials. Based on one laser pulse, the rates of formation of chemical products formed during the dissociation of water during laser-induced breakdown of a colloid of gadolinium oxide nanoparticles are 13.13 nmol/pulse for H2, 5.41 nmol/pulse for O2, and 6.98 nmol/pulse for hydrogen peroxide. [ABSTRACT FROM AUTHOR]

Water pollution has drawn worldwide attention, which is a serious environmental problem. In time water pollution detection has great significance on the earth's environment. However, existing research methods rely on specialized devices, which are expensive and time-consuming. This paper introduces a novel water pollution detection method based on acoustic signals and a long short-term neural network. Unlike past work, our method relies on commercial devices, which is convenient. The intuition is that when the acoustic signals propagate through the detected target, the acoustic signals arrive at the receiver through multi-paths, and different polluted waters will cause different multi-path propagation, which can be seen as fingerprints, and can be used for water pollution detection. We use the microphone and speaker equipped in the smartphones to capture the acoustic signals of detected water, and then calculate CIR measurements, perform data segmentation and feature extraction, and apply LSTM for pollution detection and pollutant detection. The experimental results show that the method can obtain high accuracy and strong robustness. [ABSTRACT FROM AUTHOR]

Oligoglena sirintaylan sp. n. is defined from Saklıkent in Mediterranean Turkey, which are part of the Taurus Mountains. Taurus Mountains are known for their high diversity and endemism rate of both plants and animals. The new species has a characteristic morphology and is distinguished from all other species of the genus Oligoglena Horváth also by its behavioural character. It prefers the subalpine zone and lives in gramineous vegetation. [ABSTRACT FROM AUTHOR]

In this paper, we develop a tractable mathematical model and an emulation framework for communicating information through water using acoustic signals. Water is considered one of the most complex media to model due to its vastness and variety of characteristics, which depend on the scenario, the type of water body (lakes, rivers, tanks, sea, etc.), and the geographical location of the water body being considered. Our proposed mathematical model involves the concept of damped harmonic oscillators to represent the medium (water); Milne's oscillator technique is used to map the interaction between the acoustic signal and water. Wave equations formulated for acoustic pressure and acoustic wave velocity are employed to characterise the travelling acoustic signal. The signal strength, phase shift, and time delay generated from the mathematical model are then inputted into a Simulink-based emulator framework to generate channel samples and channel impulse responses. The emulator utilises the wide sense stationary uncorrelated scattering (WSSUS) assumption and a finite sum-of-sinusoids (SOS) approach with a uniformly distributed phase to generate the channel samples. By utilising this emulator platform, it becomes feasible to generate profiles for amplitude variation, the Doppler shift, and spread experienced by any travelling signal in various underwater communication scenarios. Such a platform can be employed to simulate different communication scenarios, underwater network topologies, and data for training various learning models. Additionally, it can predict the performance of different modulation, multiplexing, error correction, and multi-access techniques for underwater acoustic communication (UWAC) systems. [ABSTRACT FROM AUTHOR]

Condition monitoring in a centrifugal pump is a significant field of study in industry. The acoustic method offers a robust approach to detect cavitations in different pumps. As a result, an acoustic-based technique is used in this experiment to predict cavitation. By using an acoustic technique, detailed information on outcomes can be obtained for cavitation detection under a variety of conditions. In addition, various features are used in this work to analyze signals in the time domain using the acoustic technique. A signal in the frequency domain is also investigated using the fast Fourier method. This method has shown to be an effective tool for predicting future events. In addition, this experimental investigation attempts to establish a good correlation between noise characteristics and cavitation detection in a pump by using an acoustic approach. Likewise, it aims to find a good method for estimating cavitation levels in a pump based on comparing and evaluating different systems. [ABSTRACT FROM AUTHOR]

For indoor sensor systems, it is essential to implement an extra supporting area notification part. To inform the real-time coordinates, the time difference of arrival (TDOA) algorithm can be introduced. For these indoor localization systems, their main processes are often built based on the line of sight (LOS) scenario. However, obstacles make the off-the-shelf localization system unable to play its due role in the flexible non-line of sight (NLOS) scenario. So, it is necessary to adjust the signals according to the NLOS identification results. However, the NLOS identification methods before were not effective enough. To address these challenges, on the one hand, this paper proposes an adaptive strategy for a dual-receiving signal processing method. On the other hand, the system is matched with the homologous NLOS identification method based on a novel artificial fish school algorithm (AFSA) and the decision tree model. According to our experiments, our novel AFSA optimization method can obtain a better effect and take less time. The NLOS acoustic signal identification accuracy can be improved significantly in flexible scenarios compared with other methods. Based on these processes, the system will achieve more accurate localization results in flexible NLOS situations. [ABSTRACT FROM AUTHOR]

Vocal complexity can be expressed through variations in repertoire size, structure, and individual manatee repertoires. Here we aimed to assess the complexity of the vocal behaviour of Antillean manatees living in captivity (i.e., artificial pools) and in reintroduction enclosures (i.e., natural enclosures placed in an estuarine area). Specifically, we evaluated: (i) the structure of vocalisations to assess whether they had variants; (ii) the variation in call production (rate and pattern) between groups with different configurations; (iii) whether individuality occurred in vocalisation structure. We found four categories of vocalisations, of which two had different variants. Not all study groups produced all call categories and variants. Older and younger males in the reintroduction enclosures had the highest call rates compared to captive females and captive males. The vocal and behavioural patterns differed between groups. Squeak call structure differed between individuals. Such vocal complexity may aid manatees in adapting to their dynamic social and structural environment, facilitating communication. [ABSTRACT FROM AUTHOR]

Vehicle tracking is one of the important applications of wireless sensor networks. We consider an aspect of tracking: the classification of targets based on the acoustic signals produced by vehicles. In this paper, we present a naıve classifier and simple distributed schemes for vehicle classification based on the features extracted from the acoustic signals. We demonstrate a novel way of using Aura matrices to create a new feature derived from the power spectral density (PSD) of a signal, which performs at par with other existing features. To benefit from the distributed environment of the sensor networks we also propose efficient dynamic acoustic features that are low on dimension, yet effective for classification. An experimental study has been conducted using real acoustic signals of different vehicles in an urban setting. Our proposed schemes using a na¨ıve classifier achieved highly accurate results in classifying different vehicles into two classes. Communication and computational costs were also computed to capture their trade-off with the classification quality.

Partial discharge (PD) is a common issue in power transformers that can lead to catastrophic failures if left undetected. Time reversal (TR) is a well-known technique in signal processing that can reconstruct signals by reversing the direction of time. The paper investigates the use of time reversal and the integration of time reversal with convolution neural networks (CNNs) for diagnosing PD in power transformers. We compare the performance of these techniques on a dataset of PD signals collected from power transformers. We propose a novel method of using time reversal as a pre-processing step to improve the accuracy of CNNs on noisy or distorted signals. Our experimental results demonstrate that this approach can significantly enhance the performance of CNNs on various datasets, including speech, audio, and image datasets. This paper provides a novel approach to signal processing and demonstrates the potential of time reversal as a pre-processing step in CNNs.

Divergence in acoustic signals may have a crucial role in the speciation process of animals that rely on sound for intra‐specific recognition and mate attraction. The acoustic adaptation hypothesis (AAH) postulates that signals should diverge according to the physical properties of the signalling environment. To be efficient, signals should maximize transmission and decrease degradation. To test which drivers of divergence exert the most influence in a speciose group of insects, we used a phylogenetic approach to the evolution of acoustic signals in the cicada genus Tettigettalna, investigating the relationship between acoustic traits (and their mode of evolution) and body size, climate and micro‐/macro‐habitat usage. Different traits showed different evolutionary paths. While acoustic divergence was generally independent of phylogenetic history, some temporal variables' divergence was associated with genetic drift. We found support for ecological adaptation at the temporal but not the spectral level. Temporal patterns are correlated with micro‐ and macro‐habitat usage and temperature stochasticity in ways that run against the AAH predictions, degrading signals more easily. These traits are likely to have evolved as an anti‐predator strategy in conspicuous environments and low‐density populations. Our results support a role of ecological selection, not excluding a likely role of sexual selection in the evolution of Tettigettalna calling songs, which should be further investigated in an integrative approach. [ABSTRACT FROM AUTHOR]

The study analyzed the spectra of acoustic signals obtained during uniaxial compression of artificial sandstone samples under continuous loading through the postultimate state up to failure. The authors attempt to reveal a shift towards lower values in the characteristic acoustic signal frequency as the load approaches the critical load state. The experiments were performed on a lever press in two modes: simple continuous loading and continuous loading with periodic impact on the sample by direct current. This was done in order to indicate the effect of electric current on the acoustic emission parameters. In both cases, when a load reached close-to-ultimate and postultimate states, the amplitude of the signals in the 10–20 kHz frequency range begins to significantly exceed the amplitude of the signals in frequency ranges above 20 kHz. At the final stage, immediately before the onset of an avalanche-like rise in acoustic emission activity, an increase in signals with frequencies in the 5–10 kHz range is also noted. Based on the identical behavior of the samples, the authors have concluded that the electric impact did not significantly affect the spectral acoustic signal characteristics. The shift of the frequency interval, which is accounted for the maximum RMS amplitudes of the acoustic signal, towards low frequencies may indicate either the formation of larger cracks or the appearance of additional cracks of a different mode than at lower loads (e.g., shear cracks). By itself, this phenomenon may indicate impending macrofailure. [ABSTRACT FROM AUTHOR]