Deploying Acoustic Detection Algorithms on Low-Cost, Open-Source Acoustic Sensors for Environmental Monitoring

High-sensitivity narrow‑band T-shaped cantilever Fabry-perot acoustic sensor for photoacoustic spectroscopy

Photoacoustic spectroscopy (PAS) has been rapidly developed and applied to different detection scenarios. The acoustic pressure detection is an important part in the PAS system. In this paper, an ultrahigh sensitivity Fabry-Perot acoustic sensor with a T-shaped cantilever was proposed. To achieve the best acoustic pressure effect, the dimension of the cantilever structure was designed and optimized by finite element analysis using COMSOL Multiphysics. Simulation results showed that the sensitivity of such T-shaped cantilever was 1.5 times higher than that based on a rectangular cantilever, and the resonance frequency of T-shaped cantilever were able to modulate from 800 Hz to 1500 Hz by adjusting the multi-parameter characteristics. Experimental sensing results showed that the resonance frequency of T-shaped Fabry-Perot acoustic sensor was 1080 Hz, yielding a high sensitivity of 1.428 μm/Pa, with a signal-to-noise ratio (SNR) of 84.8 dB and a detectable pressure limit of 1.9 μPa/Hz1/2@1 kHz. We successfully used such acoustic sensor to measure acetylene (C2H2) concentration in the PAS. The sensitivity of PAS for C2H2 gas was 3.22 pm/ppm with a concentration range of 50 ppm ∼100 ppm, and the minimum detection limit was 24.91ppb.

To Bag or Not to Bag? How AudioMoth-Based Passive Acoustic Monitoring Is Impacted by Protective Coverings

Bare board AudioMoth recorders offer a low-cost, open-source solution to passive acoustic monitoring (PAM) but need protecting in an enclosure. We were concerned that the choice of enclosure may alter the spectral characteristics of recordings. We focus on polythene bags as the simplest enclosure and assess how their use affects acoustic metrics. Using an anechoic chamber, a series of pure sinusoidal tones from 100 Hz to 20 kHz were recorded on 10 AudioMoth devices and a calibrated Class 1 sound level meter. The recordings were made on bare board AudioMoth devices, as well as after covering them with different bags. Linear phase finite impulse response filters were designed to replicate the frequency response functions between the incident pressure wave and the recorded signals. We applied these filters to ~1000 sound recordings to assess the effects of the AudioMoth and the bags on 19 acoustic metrics. While bare board AudioMoth showed very consistent spectral responses with accentuation in the higher frequencies, bag enclosures led to significant and erratic attenuation inconsistent between frequencies. Few acoustic metrics were insensitive to this uncertainty, rendering index comparisons unreliable. Biases due to enclosures on PAM devices may need to be considered when choosing appropriate acoustic indices for ecological studies. Archived recordings without adequate metadata may potentially produce biased acoustic index values and should be treated cautiously.

Applications and advances in acoustic monitoring for infectious disease epidemiology

Emerging infectious diseases continue to pose a significant burden on global public health, and there is a critical need to better understand transmission dynamics arising at the interface of human activity and wildlife habitats. Passive acoustic monitoring (PAM), more typically applied to questions of biodiversity and conservation, provides an opportunity to collect and analyse audio data in relative real time and at low cost. Acoustic methods are increasingly accessible, with the expansion of cloud-based computing, low-cost hardware, and machine learning approaches. Paired with purposeful experimental design, acoustic data can complement existing surveillance methods and provide a novel toolkit to investigate the key biological parameters and ecological interactions that underpin infectious disease epidemiology.

Development of an Artificial Neural Network Algorithm Embedded in an On-Site Sensor for Water Level Forecasting

Extreme weather events cause stream overflow and lead to urban inundation. In this study, a decentralized flood monitoring system is proposed to provide water level predictions in streams three hours ahead. The customized sensor in the system measures the water levels and implements edge computing to produce future water levels. It is very different from traditional centralized monitoring systems and considered an innovation in the field. In edge computing, traditional physics-based algorithms are not computationally efficient if microprocessors are used in sensors. A correlation analysis was performed to identify key factors that influence the variations in the water level forecasts. For example, the second-order difference in the water level is considered to represent the acceleration or deacceleration of a water level rise. According to different input factors, three artificial neural network (ANN) models were developed. Four streams or canals were selected to test and evaluate the performance of the models. One case was used for model training and testing, and the others were used for model validation. The results demonstrated that the ANN model with the second-order water level difference as an input factor outperformed the other ANN models in terms of RMSE. The customized microprocessor-based sensor with an embedded ANN algorithm can be adopted to improve edge computing capabilities and support emergency response and decision making.

Addressing Power Issues in Biologging: An Audio/Inertial Recorder Case Study

In the past decades, biologging, i.e., the development and deployment of animal-borne loggers, has revolutionized ecology. Despite recent advances, power consumption and battery size however remain central issues and limiting factors, constraining the quantity of data that can be collected and the size of the animals that can be studied. Here, we present strategies to achieve ultra-low power in biologging, using the design of a lightweight audio-inertial logger as an example. It is designed with low-power MEMS sensors, and a firmware based on a small embedded RTOS. Both methodologies for power reduction and experimental results are detailed. With an average power consumption reduced to 5.3 mW, combined with a battery of 1800 mAh, the logger provides 900 h of continuous 8 kHz audio, 50 Hz accelerometer and 10 Hz magnetometer data.

From Soundwave to Soundscape: A Guide to Acoustic Research in Captive Animal Environments

Sound is a complex feature of all environments, but captive animals' soundscapes (acoustic scenes) have been studied far less than those of wild animals. Furthermore, research across farms, laboratories, pet shelters, and zoos tends to focus on just one aspect of environmental sound measurement: its pressure level or intensity (in decibels). We review the state of the art of captive animal acoustic research and contrast this to the wild, highlighting new opportunities for the former to learn from the latter. We begin with a primer on sound, aimed at captive researchers and animal caregivers with an interest (rather than specific expertise) in acoustics. Then, we summarize animal acoustic research broadly split into measuring sound from animals, or their environment. We guide readers from soundwave to soundscape and through the burgeoning field of conservation technology, which offers new methods to capture multiple features of complex, gestalt soundscapes. Our review ends with suggestions for future research, and a practical guide to sound measurement in captive environments.

Self-Powered Gesture Recognition Wristband Enabled by Machine Learning for Full Keyboard and Multicommand Input

Virtual reality is a brand-new technology that can be applied extensively. To realize virtual reality, certain types of human-computer interaction equipment are necessary. Existing virtual reality technologies often rely on cameras, data gloves, game pads, and other equipment. These equipment are either bulky, inconvenient to carry and use, or expensive to popularize. Therefore, the development of a convenient and low-cost high-precision human-computer interaction device can contribute positively to the development of virtual reality technology. In this study, a gesture recognition wristband that can realize a full keyboard and multicommand input is developed. The wristband is convenient to wear, low in cost, and does not affect other daily operations of the hand. This wristband is based on physiological anatomy as well as aided by active sensor and machine learning technology; it can achieve a maximum accuracy of 92.6% in recognizing 26 letters. This wristband offers broad application prospects in the fields of gesture command recognition, assistive devices for the disabled, and wearable electronics.

Accessibility to Protected Areas Increases Primate Hunting Intensity in Bioko Island, Equatorial Guinea

Bioko is one of the most important sites for African primate conservation; yet it has seen a severe decline in its primate populations due to illegal hunting to supply a thriving wildmeat trade. The completion in 2015 of a new road bisecting the Gran Caldera Scientific Reserve (GCSR), where rugged terrain and lack of infrastructure once served as a natural barrier, further threatened this last stronghold for Bioko's primates. Here we used passive acoustic monitoring to study factors affecting hunting patterns within GCSR through the automatic detection of shotgun sounds. Ten acoustic sensors were placed in locations that varied in terrain heterogeneity, distance to the new road, human settlements, research camps (i.e., Moraka and Moaba) and elevation. Sensors recorded continuously between January 2018 and January 2020, collecting 2,671 site-days of audio. In total 596 gunshots were detected, including in the most remote areas. There were significant differences in hunting rate between areas (Kruskal-Wallis, χ2 = 102.71, df = 9, p < 0.001). We also found there were significantly fewer gunshots during 2019 than during 2018 (V = 55, p < 0.001). Occupancy modeling showed that hunting increased with decreasing terrain heterogeneity and decreasing distance to roads and villages; and decreased with increasing proximity to Research Camps. These results demonstrated that increasing accessibility increased primate hunting in GCSR, which was exacerbated by the opening of the new road. We also demonstrated that research presence was effective at reducing primate hunting. Unless strict conservation interventions are implemented, including road checkpoints, increasing biomonitoring and hunting patrols, and an island-wide, enforced ban on firearms, GCSR will see a significant decrease in primate density over the next decade, including the potential extinction of Critically Endangered Pennant's red colobus, whose entire population is restricted to GCSR and is a primary target of hunters.

Computational bioacoustics with deep learning: a review and roadmap

Animal vocalisations and natural soundscapes are fascinating objects of study, and contain valuable evidence about animal behaviours, populations and ecosystems. They are studied in bioacoustics and ecoacoustics, with signal processing and analysis an important component. Computational bioacoustics has accelerated in recent decades due to the growth of affordable digital sound recording devices, and to huge progress in informatics such as big data, signal processing and machine learning. Methods are inherited from the wider field of deep learning, including speech and image processing. However, the tasks, demands and data characteristics are often different from those addressed in speech or music analysis. There remain unsolved problems, and tasks for which evidence is surely present in many acoustic signals, but not yet realised. In this paper I perform a review of the state of the art in deep learning for computational bioacoustics, aiming to clarify key concepts and identify and analyse knowledge gaps. Based on this, I offer a subjective but principled roadmap for computational bioacoustics with deep learning: topics that the community should aim to address, in order to make the most of future developments in AI and informatics, and to use audio data in answering zoological and ecological questions.

RAP: A Software Framework of Developing Convolutional Neural Networks for Resource-constrained Devices Using Environmental Monitoring as a Case Study

Monitoring environmental conditions is an important application of cyber-physical systems. Typically, the monitoring is to perceive surrounding environments with battery-powered, tiny devices deployed in the field. While deep learning-based methods, especially the convolutional neural networks (CNNs), are promising approaches to enriching the functionalities offered by the tiny devices, they demand more computation and memory resources, which makes these methods difficult to be adopted on such devices. In this article, we develop a software framework, RAP , that permits the construction of the CNN designs by aggregating the existing, lightweight CNN layers, which are able to fit in the limited memory (e.g., several KBs of SRAM) on the resource-constrained devices satisfying application-specific timing constrains. RAP leverages the Python-based neural network framework Chainer to build the CNNs by mounting the C/C++ implementations of the lightweight layers, trains the built CNN models as the ordinary model-training procedure in Chainer, and generates the C version codes of the trained models. The generated programs are compiled into target machine executables for the on-device inferences. With the vigorous development of lightweight CNNs, such as binarized neural networks with binary weights and activations, RAP facilitates the model building process for the resource-constrained devices by allowing them to alter, debug, and evaluate the CNN designs over the C/C++ implementation of the lightweight CNN layers. We have prototyped the RAP framework and built two environmental monitoring applications for protecting endangered species using image- and acoustic-based monitoring methods. Our results show that the built model consumes less than 0.5 KB of SRAM for buffering the runtime data required by the model inference while achieving up to 93% of accuracy for the acoustic monitoring with less than one second of inference time on the TI 16-bit microcontroller platform.

MeLa: A Programming Language for a New Multidisciplinary Oceanographic Float

At 2000 m depth in the oceans, one can hear biological, seismological, meteorological, and anthropogenic activity. Acoustic monitoring of the oceans at a global scale and over long periods of time could bring important information for various sciences. The Argo project monitors the physical properties of the oceans with autonomous floats, some of which are also equipped with a hydrophone. These have a limited transmission bandwidth requiring acoustic data to be processed on board. However, developing signal processing algorithms for these instruments requires one to be an expert in embedded software. To reduce the need of such expertise, we have developed a programming language, called MeLa. The language hides several aspects of embedded software with specialized programming concepts. It uses models to compute energy consumption, processor usage, and data transmission costs early during the development of applications; this helps to choose a strategy of data processing that has a minimum impact on performances. Simulations on a computer allow for verifying the performance of the algorithms before their deployment on the instrument. We have implemented a seismic P wave detection and a blue whales D call detection algorithm with the MeLa language to show its capabilities. These are the first efforts toward multidisciplinary monitoring of the oceans, which can extend beyond acoustic applications.

Gunshot Airborne Surveillance with Rotary Wing UAV-Embedded Microphone Array

Unmanned aerial vehicles (UAV) are growing in popularity, and recent technological advances are fostering the development of new applications for these devices. This paper discusses the use of aerial drones as a platform for deploying a gunshot surveillance system based on an array of microphones. Notwithstanding the difficulties associated with the inherent additive noise from the rotating propellers, this application brings an important advantage: the possibility of estimating the shooter position solely based on the muzzle blast sound, with the support of a digital map of the terrain. This work focuses on direction-of-arrival (DoA) estimation methods applied to audio signals obtained from a microphone array aboard a flying drone. We investigate preprocessing and different DoA estimation techniques in order to obtain the setup that performs better for the application at hand. We use a combination of simulated and actual gunshot signals recorded using a microphone array mounted on a UAV. One of the key insights resulting from the field recordings is the importance of drone positioning, whereby all gunshots recorded in a region outside a cone open from the gun muzzle presented a hit rate close to 96%. Based on experimental results, we claim that reliable bearing estimates can be achieved using a microphone array mounted on a drone.

Acoustic Classification of Singing Insects Based on MFCC/LFCC Fusion

This work introduces a new approach for automatic identification of crickets, katydids and cicadas analyzing their acoustic signals. We propose the building of a tool to identify this biodiversity. The study proposes a sound parameterization technique designed specifically for identification and classification of acoustic signals of insects using Mel Frequency Cepstral Coefficients (MFCC) and Linear Frequency Cepstral Coefficients (LFCC). These two sets of coefficients are evaluated individually as has been done in previous studies and have been compared with the fusion proposed in this work, showing an outstanding increase in identification and classification at species level reaching a success rate of 98.07% on 343 insect species.

Heterogeneous LoRa-Based Wireless Multimedia Sensor Network Multiprocessor Platform for Environmental Monitoring

The acquisition of data in protected natural environments is subordinated to actions that do not stress the life-forms present in that environment. This is why researchers face two conflicting interests: autonomous and robust systems that minimize the physical interaction with sensors once installed, and complex enough ones to capture and process higher volumes of data. On the basis of this situation, this paper analyses the current state-of-the-art of wireless multimedia sensor networks, identifying the limitations and needs of these solutions. In this sense, in order to improve the trade-off between autonomous and computational capabilities, this paper proposes a heterogeneous multiprocessor sensor platform, consisting of an ultra-low power microcontroller and a high-performance processor, which transfers control between processors as needed. This architecture allows the shutdown of idle systems and fail-safe remote reprogramming. The sensor equipment can be adapted to the needs of the project. The deployed equipment incorporates, in addition to environmental meteorological variables, a microphone input and two cameras (visible and thermal) to capture multimedia data. In addition to the hardware description, the paper provides a brief description of how long-range (LoRa) can be used for sending large messages (such as an image or a new firmware), an economic analysis of the platform, and a study on energy consumption of the platform according to different use cases.

A Multispectral Backscattered Light Recorder of Insects’ Wingbeats

Most reported optical recorders of the wingbeat of insects are based on the so-called extinction light, which is the variation of light in the receiver due to the cast shadow of the insect’s wings and main body. In this type of recording devices, the emitter uses light and is placed opposite to the receiver, which is usually a single (or multiple) photodiode. In this work, we present a different kind of wingbeat sensor and its associated recorder that aims to extract a deeper representational signal of the wingbeat event and color characterization of the main body of the insect, namely: a) we record the backscattered light that is richer in harmonics than the extinction light, b) we use three different spectral bands, i.e., a multispectral approach that aims to grasp the melanization and microstructural and color features of the wing and body of the insects, and c) we average at the receiver’s level the backscattered signal from many LEDs that illuminate the wingbeating insect from multiple orientations and thus offer a smoother and more complete signal than one based on a single snapshot. We present all the necessary details to reproduce the device and we analyze many insects of interest like the bee Apis mellifera, the wasp Polistes gallicus, and some insects whose wingbeating characteristics are pending in the current literature, like Drosophila suzukii and Zaprionus, another member of the drosophilidae family.