当前位置: X-MOL 学术EURASIP J. Wirel. Commun. Netw. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Lightweight feature extraction method for efficient acoustic-based animal recognition in wireless acoustic sensor networks
EURASIP Journal on Wireless Communications and Networking ( IF 2.6 ) Pub Date : 2020-12-14 , DOI: 10.1186/s13638-020-01878-z
Fatima Al-Quayed , Adel Soudani , Saad Al-Ahmadi

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.



中文翻译:

用于无线声传感器网络中基于声的动物有效识别的轻量特征提取方法

无线声传感器网络代表了一种有吸引力的解决方案,可以将其部署到受监视区域内的动物检测和识别中。此应用程序的典型配置是通过多跳通信将整个获取的音频信号传输到远程服务器以进行识别。但是,连续的数据流可能会导致传感器能量的严重下降,从而缩短网络寿命并质疑应用程序的可行性。减少传感器无线电活动的有效解决方案是在源传感器上执行识别任务,然后将结果传送到远程服务器。这种方法旨在节省声源传感器的能量,并使网络免于承载可能无用的数据。然而,该解决方案的有效性取决于执行传感器上新声事件的检测和准确识别的能效。在这种情况下,本文提出了一种基于低复杂度方法的传感器上节能动物声学识别的新方案,用于使用Haar小波变换进行特征提取。与原始信号的传输相比,该方案可实现86%以上的识别精度,同时节省71.59%的传感器能​​量。

更新日期:2020-12-14
down
wechat
bug