Bird Species Recognizer using LMS Algorithm
K. Shivaani1, Munukutla Vandana2, Malaya Kumar Hota3
1K. Shivaani, Department of Electronics and Communication Engineering, Vellore Institute of Technology, Vellore 632014, Tamil Nadu, India.
2Munukutla Vandana, Department of Electronics and Communication Engineering, Vellore Institute of Technology, Vellore 632014, Tamil Nadu, India.
3Malaya Kumar Hota*, Professor, Department of Communication Engineering, School of Electronics Engineering, Vellore Institute of Technology, Vellore 632014, Tamil Nadu, India.
Manuscript received on January 05, 2020. | Revised Manuscript received on January 25, 2020. | Manuscript published on January 30, 2020. | PP: 4745-4750 | Volume-8 Issue-5, January 2020. | Retrieval Number: E6758018520/2020©BEIESP | DOI: 10.35940/ijrte.E6758.018520
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Birds play a vital role in many ecosystems, acting as both predators and preys for other living organisms. Therefore its important to monitor the population of various bird species in the environment in order to maintain balance in the ecosystem. This process will become tedious if it is done manually as it involves handling large sets of data at the same instant. We can do this by developing an automatic bird species recognizer which identifies the bird species based on bird songs and voice signals. In this research, we have used a tenth-order LMS adaptive filter to remove noise from bird voice signals which are recorded in different environmental conditions where different noise frequencies are present. The design of a tenth-order LMS adaptive filter using MATLAB has been implemented. The performance and characteristics of the filter for five different methods of LMS has been shown. After removal of noise from the noisy bird voice signal using LMS algorithm, we have made use of cross correlation to identify the bird species that it corresponds to. Signal to Noise Ratio (SNR) and Mean Square Error (MSE) of the filtered bird signals obtained using the variants of LMS like Normalized LMS, Sign-Data LMS, Sign-Error LMS and Sign-Sign LMS have been estimated and compared. We have made use of signal processing tool kits and various noise parameter schemes have been computed to show the effectiveness of the designed filter in the field of bird recognition.
Keywords: Adaptive Filter, Cross-Correlation, LMS Algorithm, Normalized LMS.
Scope of the Article: Parallel and Distributed Algorithms.