The Bornean orangutan population is critically endangered, and efficient methods for identifying and classifying their nests are needed to monitor their populations and track their health. Manual identification and classification are time-consuming and require extensive knowledge of orangutan behavior and their natural habitats. We propose a novel approach to classifying orangutan nests using Support Vector Machines (SVMs). SVMs are a powerful machine learning algorithm that has been shown to be effective in image classification tasks. Our method incorporates a comprehensive image pre-processing and enhancement pipeline, along with a rigorous training and testing procedure. Experimental results indicate that our method can achieve remarkable accuracy in classifying orangutan nests, with an achieved accuracy of 79.90%, an F1-score of 79.87%, a precision of 79.91%, and a recall of 79.82%. These findings underscore the efficacy of our proposed method and highlight the potential of SVMs for this critical conservation task. The proposed method has significant implications for orangutan conservation efforts, enabling researchers and conservationists to efficiently identify and monitor orangutan populations. By automating the nest classification process, it becomes possible to analyze large-scale datasets and gain valuable insights into orangutan behavior, habitat preferences, and population dynamics. In conclusion, our study highlights the effectiveness of SVMs in classifying orangutan nests and contributes to the ongoing efforts in preserving these critically endangered species. The developed methodology offers a promising solution for wildlife conservationists and researchers working towards the preservation of Bornean orangutans.
Kim On, Chin is an Associate Professor at the Faculty of Computing and Informatics, Universiti Malaysia Sabah. His research interests encompass evolutionary computing, machine learning, image processing, Internet of Things (IoT), and biometric security systems. He has successfully secured 30 research grants and 14 community grants, amounting to almost RM 5 million in total. He has authored or co-authored about 130 publications, including journal articles, book chapters, and conference proceedings. As a Senior Member of IEEE, Kim On has actively engaged in over 80 community- based activities. He has developed web applications for teaching and learning using Google Tools and Google Data Studio, and conducted training sessions on Computational Thinking, Arduino, 3D printing, and Python programming. He has also undertaken consultancy projects involving the management of Digital Maker Hubs for Science, Technology, Engineering, Arts, and Mathematics (STEAM), the development of an e-summon system utilizing image processing and neural networks for campus surveillance, and plastic object classification through machine learning-based classifiers for onshore plastic waste detection using near-infrared hyperspectral images. Kim On has more than 18 years of teaching experience, and is highly skilled in delivering professional training courses and giving invited talks. His expertise and contributions in the field of computer science and informatics are significant, making him a valuable asset to the academic community. He is also one of the appointed MBOT and MQA Assessors for computer science programme accreditation.