SOUND RECOGNITION OF BIRD SPECIES USING MACHINE LEARNING ALGORITHMS
| dc.contributor.author | Nelson Lee Chin Sheng | |
| dc.date.accessioned | 2026-04-16T02:13:07Z | |
| dc.date.issued | 2025 | |
| dc.description | Analysis of bird species using their sounds in the ecosystem is crucial for the effective conservation of natural habitats. However, this method requires significant expertise and knowledge on the part of the observer, and with increasing lengths of bird sound recordings taken every year, such expertise resources will become limited. The complexity and scale of this challenge necessitates an automated classification system, which can be effectively implemented through machine learning techniques. This paper examined the performance of three machine learning algorithms, Naïve Bayes, Support Vector Machines (SVM), and Central Neural Network (CNN), in classifying publicly accessible, crowd-sourced bird sound recordings. These algorithms were implemented using Python scripts and libraries. This work also utilizes the highest-performing machine learning model to develop a bird sound recognition application. The application was developed using React Native and Python, and evaluated following the System Usability Scale. The results of this study show that CNN was the most effective machine learning algorithm for classifying bird audio, with a classification accuracy of 0.3492, compared to Naive Bayes (0.0849) and SVM (0.2720). Through the System Usability Scale (SUS), the application obtained a SUS Score of 83.91, suggested users have positive experiences with the mobile application. This study shows the potential of CNN for bird audio classification, and further work could be done to enhance its accuracy and robustness, such as data augmentation, data expansion and examination of different data feature extraction and deep learning architecture. | |
| dc.identifier.uri | https://scholarhub.unimas.my/handle/123456789/369 | |
| dc.language.iso | English | |
| dc.publisher | UNIVERSITI MALAYSIA SARAWAK | |
| dc.relation.ispartofseries | Faculty of Computer Science and Information Technology | |
| dc.title | SOUND RECOGNITION OF BIRD SPECIES USING MACHINE LEARNING ALGORITHMS | |
| dc.type | Final Year Project |