Abstract
Wireless acoustic sensor networks represent an attractive solution that can be deployed for animal detection and recognition in a monitored area. A typical configuration for this application would be to transmit the whole acquired audio signal through multi-hop communication to a remote server for recognition. However, continuous data streaming can cause a severe decline in the energy of the sensors, which consequently reduces the network lifetime and questions the viability of the application. An efficient solution to reduce the sensor's radio activity would be to perform the recognition task at the source sensor then to communicate the result to the remote server. This approach is intended to save the energy of the acoustic source sensor and to unload the network from carrying, probably, useless data. However, the validity of this solution depends on the energy efficiency of performing on-sensor detection of a new acoustic event and accurate recognition. In this context, this paper proposes a new scheme for on-sensor energy-efficient acoustic animal recognition based on low-complexity methods for feature extraction using the Haar wavelet transform. This scheme achieves more than 86% in recognition accuracy while saving 71.59% of the sensor energy compared with the transmission of the raw signal.
Highlights
Many animal species face habitat loss in a rapidly changing world due to global warming, harmful human activities, etc. [1]
4 Results and discussion we describe the set of experiments conducted to assess the proposed scheme performances in terms of recognition accuracy and energy efficiency
5 Conclusions This paper presented a lightweight scheme for acoustic-based animal recognition designed for sharply limited-resources systems (i.e., MICAz motes) seeking to extend their lifetime
Summary
Many animal species face habitat loss in a rapidly changing world due to global warming, harmful human activities, etc. [1]. Monitoring the endangered species in the ecosystems becomes an urgent worldwide concern In this context, the automatic animal surveillance system presents an effective substitute for the ecologists’ manual observations since they require costly and time-consuming on-site monitoring that can be infeasible depending on the monitored area’s size. The rapid progress in micro-electro-mechanical systems (MEMSs) has allowed the integration of low-cost micro-acoustic sensing components within network nodes, enabling the development of wireless acoustic sensor networks (WASNs). This technology enables a wide variety of unassisted acoustic-based monitoring applications for both. Al‐Quayed et al J Wireless Com Network (2020) 2020:256 indoor and outdoor environments Examples of these applications are endangered animal tracking [2], vehicle monitoring [3], speech localizing [4]. Despite that the compressed sensing can be an effective solution for data reduction during signal acquisition [8]; it produces characteristics that are only useful for signal regeneration but not recognition using complex algorithms, which is infeasible at WASN due to the limited resources [9]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: EURASIP Journal on Wireless Communications and Networking
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
