Abstract
Endemic species are under threat from various factors, including habitat destruction, illegal hunting, and climate change, which necessitate urgent and effective monitoring solutions. This research introduces an advanced AI system for real-time threat detection and response, utilizing the YOLOv8 algorithm. The system is specifically developed for the protection of endemic species. It combines the strengths of YOLOv8 with enhancements like a multi-scale detection module to tackle the challenges of identifying small or camouflaged species and threats across different ecological environments. In the proposed study, a customized dataset that is developed through the application of the Histogram of Oriented Gradients (HOG) technique along with the Firefly Algorithm is employed. This approach facilitates the efficient fine-tuning of all images within the dataset, enhancing the overall effectiveness of the analysis. The Roboflow platform is used for training, validation, and testing the customized dataset for real-time object detection. YOLOv8 achieves 97.9% mAP, 94.7% precision, and 91.9% recall. Threats are recorded in a Blockchain ledger and sent to Twilio SMS alert system, making it cost-effective and efficient. The proposed framework offers high accuracy, precision, and recall, minimizing false alarms and facilitating quick interventions, making it suitable for smart environmental management systems and biodiversity conservation.
References
Saheed, Yakub Kayode. "A binary firefly algorithm based feature selection method on high dimensional intrusion detection data." In Illumination of artificial intelligence in cybersecurity and forensics, Cham: Springer International Publishing, 2022. 273-288.
Anbu, M., and G. S. Anandha Mala. "Feature selection using firefly algorithm in software defect prediction." Cluster Computing 22 (2019): 10925-10934.
Mistry, Kamlesh, Li Zhang, Graham Sexton, Yifeng Zeng, and Mengda He. "Facial expression recongition using firefly-based feature optimization." In 2017 IEEE congress on evolutionary computation (CEC), IEEE, 2017. 1652-1658.
Mizuno, Kosuke, Yosuke Terachi, Kenta Takagi, Shintaro Izumi, Hiroshi Kawaguchi, and Masahiko Yoshimoto. "Architectural study of HOG feature extraction processor for real-time object detection." In 2012 IEEE Workshop on Signal Processing Systems, IEEE, 2012. 197-202
Putra, FAI Achyunda, Fitri Utaminingrum, and Wayan Firdaus Mahmudy. "HOG feature extraction and KNN classification for detecting vehicle in the highway." IJCCS (Indonesian Journal of Computing and Cybernetics Systems) 14, no. 3 (2020): 231-242.
Davis, Matt, and Ferat Sahin. "HOG feature human detection system." In 2016 IEEE international conference on systems, man, and cybernetics (SMC), IEEE, 2016. 002878-002883.
Venkatesan, Supreeta, A. Jawahar, S. Varsha, and N. Roshne. "Design and implementation of an automated security system using Twilio messaging service." In 2017 International Conference on Smart Cities, Automation & Intelligent Computing Systems (ICON-SONICS), IEEE, 2017. 59-63.
Choi, Brendan. "Python Network Automation Labs: Ansible, pyATS, Docker, and the Twilio API." In Introduction to Python Network Automation: The First Journey, Berkeley, CA: Apress, 2021. 675-732.
Abdulnabi, Abrar H., Gang Wang, Jiwen Lu, and Kui Jia. "Multi-task CNN model for attribute prediction." IEEE Transactions on Multimedia 17, no. 11 (2015): 1949-1959.
Rangdale, Sonali, Nihar Ranjan, Prathamesh Ukirde, Shruti Pagade, Shantanu Hanchate, and Nikhil Mehtre. "A Computer Vision-based algorithm for accident detection, severity classification and rapid emergency response using YOLOv8 and Twilio Programmable Messaging API." In 2024 OPJU International Technology Conference (OTCON) on Smart Computing for Innovation and Advancement in Industry 4.0, IEEE, 2024. 1-6.
Xu, Lily, Shahrzad Gholami, Sara McCarthy, Bistra Dilkina, Andrew Plumptre, Milind Tambe, Rohit Singh et al. "Stay ahead of Poachers: Illegal wildlife poaching prediction and patrol planning under uncertainty with field test evaluations (Short Version)." In 2020 IEEE 36th International Conference on Data Engineering (ICDE), IEEE, 2020. 1898-1901.
Edemacu, Kennedy, Jong Wook Kim, Beakcheol Jang, and Hung Kook Park. "Poacher detection in African game parks and reserves with IoT: Machine learning approach." In 2019 International Conference on Green and Human Information Technology (ICGHIT), IEEE, 2019. 12-17.
Park, Noseong, Edoardo Serra, Tom Snitch, and V. S. Subrahmanian. "APE: a data-driven, behavioral model-based anti-poaching engine." IEEE Transactions on Computational Social Systems 2, no. 2 (2015): 15-37.
Wang, Jian, Xinqi Li, Jiafu Chen, Lihui Zhou, Linyang Guo, Zihao He, Hao Zhou, and Zechen Zhang. "Dph-yolov8: Improved yolov8 based on double prediction heads for the uav image object detection." IEEE Transactions on Geoscience and Remote Sensing (2024).
Sharma, Sangeeta. "Apple Leaf Disease Prediction Using modified YOLOv8 Algorithm." In 2024 International Conference on Integrated Circuits, Communication, and Computing Systems (ICIC3S), vol. 1, IEEE, 2024. 1-6.
Khan, Zahid Farooq, Muhammad Ramzan, Mudassar Raza, Muhammad Attique Khan, Areej Alasiry, Mehrez Marzougui, and Jungpil Shin. "Real-Time Polyp Detection from Endoscopic Images using YOLOv8 with YOLO-Score Metrics for Enhanced Suitability Assessment." IEEE Access (2024).
Rios, Franklin Emanuel Ramirez, and Alicia María Reyes Duke. "Building of a Convolutional Neuronal Network for the prediction of mood states through face recognition based on object detection with YOLOV8 and Python." In 2023 IEEE International Conference on Machine Learning and Applied Network Technologies (ICMLANT), IEEE, 2023. 1-6.
Yuvaneswaren, R. S., S. Tarun Prakash, and K. Sudha. "A YOLOv8-based model for precise corrosion segmentation in industrial imagery." In 2024 3rd International Conference on Artificial Intelligence For Internet of Things (AIIoT), IEEE, 2024. 1-6.
Sharma, Subek, Sisir Dhakal, and Mansi Bhavsar. "Transfer Learning for Wildlife Classification: Evaluating YOLOv8 against DenseNet, ResNet, and VGGNet on a Custom Dataset." Journal of Artificial Intelligence and Capsule Networks 6, no. 4 (2024): 415-435.
https://docs.ultralytics.com/datasets/detect/african-wildlife/