Mobile-Based Multi-Output Animal Taxonomy Classification Using CNN with Edge and Cloud Deployment
DOI:
https://doi.org/10.30871/jaic.v9i5.10780Keywords:
Android, Deep Learning, Convolutional Neural Network (CNN), Animal Taxonomy Classification, Multi-output Multi-class ClassificationAbstract
Distinguishing animals that appear visually similar but belong to different species or taxonomic groups, such as Eurasian and house sparrows, koi and common carp, or leopard cat and domestic cat, remains challenging and hinders biodiversity education. This study develops a Convolutional Neural Network (CNN)-based multi-output, multi-class taxonomy classification system capable of identifying seven animal species across five taxonomic levels (class, order, family, genus, species), producing 35 possible outputs. The dataset comprised 6,998 images from public sources. Among various configurations, the best-performing model (D3-M2), trained using the High Dataset with 256×256 input size, 0.2 dropout, and four hidden layers, achieved 90.15% average accuracy, the highest F1-score at the family level (98.11%), and 95.99% at the species level. Slightly lower species-level performance was due to high visual similarity among particular species. Edge AI deployment offered faster inference (0.17s) and offline capability, making it ideal for field use. Real-world testing under bright and low light at 30, 60, and 100 cm showed higher accuracy (64.8%) than low light (57.1%), with the most stable performance at 60 cm. However, limitations include an imbalanced dataset and limited environmental variation affecting species-level accuracy. Future work will focus on expanding dataset diversity and employing advanced architectures to improve fine-grained classification. This system offers a practical tool for biodiversity education and species identification, particularly in field environments where rapid, offline, and accurate classification is essential.
Downloads
References
[1] R. R. Andriani, R. Sitorus, S. A. P. Zai, and Y. S. Pasaribu, “Penggunaan Algoritma CNN untuk Mengidentifikasi Jenis Anjing Menggunakan Metode Supervised Learning,” Mutiara: Jurnal Penelitian dan Karya Ilmiah, vol. 1, no. -, pp. 394–402, 2023. [Online]. Available: https://doi.org/10.59059/mutiara.v1i6.741
[2] Antara News, “Masyarakat Sering Keliru Mengidentifikasi Satwa Liar di Sekitar Pemukiman,” Antaranews.com, 2022.
[3] K. Antonio and E. Hartati, “Klasifikasi Spesies Ular Menggunakan Metode Convolutional Neural Network,” Jurnal Ilmu Komputer dan Informatika, vol. 3, no. -, pp. 357–363, 2023.
[4] AWS Amazon, "What is Python?" AWS Amazon. [Online]. Available: https://aws.amazon.com/id/what-is/python/
[5] S. K. Card, T. P. Moran, and A. Newell, The Psychology of Human-Computer Interaction, 1st ed. Boca Raton, FL, USA: CRC Press, 1983.
[6] Codecademy, "Deep Learning Workflow," Codecademy. [Online]. Available: https://www.codecademy.com/article/deep-learning-workflow
[7] Dicoding Intern, “Python: Pengertian, Contoh Penggunaan, dan Manfaat Mempelajarinya,” Dicoding, May 31, 2023. [Online]. Available: https://www.dicoding.com/blog/python-pengertian-contoh-penggunaan-dan-manfaat-mempelajarinya/
[8] J. Dodge, G. Ilharco, R. Schwartz, A. Farhadi, H. Hajishirzi, and N. Smith, "Fine-tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping," arXiv, 2020. [Online]. Available: http://arxiv.org/pdf/2002.06305
[9] R. A. Fitriansyah and Saparudin, “Penerapan Ensemble Stacking untuk Klasifikasi Multi Kelas,” Prosiding Annual Research Seminar, vol. 2, pp. 240–243, 2016. [Online]. Available: https://www.neliti.com/publications/171917/penerapan-ensemble-stacking-untuk-klasifikasi-multi-kelas
[10] GeeksforGeeks, "Understanding the Confusion Matrix in Machine Learning," GeeksforGeeks. [Online]. Available: https://www.geeksforgeeks.org/confusion-matrix-machine-learning/#what-is-a-confusion-matrix
[11] Hugging Face, "Spaces," Hugging Face. [Online]. Available: https://huggingface.co/docs/hub/spaces
[12] IBM, "Apa itu Convolutional Neural Network?"IBM. [Online]. Available: https://www.ibm.com/id-id/topics/convolutional-neural-networks
[13] IBM, "What is Edge AI?"IBM. [Online]. Available: https://www.ibm.com/think/topics/edge-ai
[14] Ilmu Pengetahuan Alam, Pusat Kurikulum dan Perbukuan; Badan Penelitian dan Pengembangan dan Perbukuan; Kementerian Pendidikan, Kebudayaan, Riset, dan Teknologi, 2021. [Online]. Available: https://static.buku.kemdikbud.go.id/content/pdf/bukuteks/kurikulum21/IPA-BS-KLS%20VII.pdf
[15] S. Jain, "Convolutional Neural Network (CNN) in Machine Learning," GeeksforGeeks, Mar. 13, 2024. [Online]. Available: https://www.geeksforgeeks.org/convolutional-neural-network-cnn-in-machine-learning/
[16] A. Joly, L. Wehenkel, and P. Geurts, "Gradient Tree Boosting with Random Output Projections for Multi-label Classification and Multi-output Regression," arXiv, pp. 1–40, 2019. [Online]. Available: https://arxiv.org/pdf/1905.07558
[17] KKP RI, “Mengenal Perbedaan Ikan Mas dan Ikan Koi,” Kementerian Kelautan dan Perikanan Republik Indonesia, 2021.
[18] Kompas, “Perbedaan Burung Gereja Lokal dan Eurasia,” Kompas.com, 2020.
[19] Mongabay Indonesia, “Mengenal Kucing Kuwuk, Satwa Liar yang Sering Disangka Kucing Rumahan,” Mongabay.co.id, 2018.
[20] P. Moreno-Muñoz, A. Artés-Rodríguez, and M. A. Álvarez, "Heterogeneous Multi-output Gaussian Process Prediction," in Proc. 32nd Conf. Neural Information Processing Systems (NeurIPS), 2018. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2018/file/165a59f7cf3b5c4396ba65953d679f17-Paper.pdf
[21] M. Mosbach, M. Andriushchenko, and D. Klakow, "On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines," in Proc. Int. Conf. Learning Representations (ICLR), 2021. [Online]. Available: https://openreview.net/forum?id=nzpLWnVAyah
[22] Nazirman, “Laporan Proyek Akhir Aplikasi Interaktif Pembelajaran Pengenalan Hewan dengan Penerapan Convolutional Neural Network (CNN) (Studi Kasus: TK Al Husniyah),” Politeknik Caltex Riau, 2023.
[23] R. I. Ndun, “Mendeteksi Jenis Burung Berdasarkan Gambar Menggunakan Deep Learning,” Universitas Dinamika, 2020.
[24] P. Nugraha, A. Komarudin, and E. Ramadhan, “Deteksi Objek dan Jenis Burung Menggunakan Convolutional Neural Network dengan Arsitektur Inception ResNet-V2,” INFOTECH Journal, vol. 8, no. -, pp. 47–55, 2022. [Online]. Available: https://doi.org/10.31949/infotech.v8i2.2889
[25] D. P. Pamungkas and M. F. Amrulloh, “Analisis Hasil Klasifikasi Penyakit Daun Bawang Merah Menggunakan CNN Arsitektur Exception,” Jurnal Ilmiah Penelitian dan Pembelajaran Informatika, vol. 10, 2025.
[26] I. Y. Pangestu and S. R. Ramadhani, “Perancangan Sistem Deteksi Penyakit Kulit pada Kucing Menggunakan Deep Learning Berbasis Android,” TEKNIKA, vol. 12, pp. 173–182, 2023. [Online]. Available: https://doi.org/10.34148/teknika.v12i3.673
[27] J. W. G. Putra, Pengenalan Konsep Pembelajaran Mesin dan Deep Learning, 1.4 ed., 2020. [Online]. Available: https://wiragotama.github.io/resources/ebook/intro-to-ml-secured.pdf
[28] Rina, “Memahami Confusion Matrix: Accuracy, Precision, Recall, Specificity, dan F1-score untuk Evaluasi Model Klasifikasi,” Medium, Jun. 12, 2023. [Online]. Available: https://esairina.medium.com/memahami-confusion-matrix-accuracy-precision-recall-specificity-dan-f1-score-610d4f0db7cf
[29] K. Sampigethaya, M. Li, and R. Poovendran, "Real-time Computing Systems and Applications for Intelligent Transportation," IEEE Trans. Intell. Transp. Syst., vol. 18, no. -, pp. 2744–2755, 2017. [Online]. Available: https://doi.org/10.1109/TITS.2017.2654242
[30] L. Sari, “Klasifikasi Multikelas dengan Menggunakan Metode Multicategory Kernel Distance Weighted Discrimination pada Data Keuangan Sektor Publik di Indonesia,” 2018. [Online]. Available: https://repository.unpad.ac.id/bitstreams/01b164fe-299b-4c1b-b94f-55873f009d63/download
[31] C. Shorten and T. M. Khoshgoftaar, "A Survey on Image Data Augmentation for Deep Learning," Journal of Big Data, vol. 6, pp. 1–48, 2019. [Online]. Available: http://journalofbigdata.springeropen.com/articles/10.1186/s40537-019-0197-0#citeas
[32] Vercel, "Get Started with Vercel," Vercel, Dec. 18, 2024. [Online]. Available: https://vercel.com/docs/getting-started-with-vercel
[33] S. R. Widjajanti, Seribu Pena Biologi SMA untuk Kelas X Rangkuman Materi Contoh Soal dan Pembahasan Soal-soal Evaluasi. Jakarta, Indonesia: Erlangga, 2005.
[34] D. C. Youvan, "AI at the Edge vs. AI in the Cloud: A Comparative Analysis of High-end and Edge AI Systems," ResearchGate, Jun. 13, 2024. [Online]. Available: https://www.researchgate.net/publication/381402818_AI_at_the_Edge_vs_AI_in_the_Cloud_A_Comparative_Analysis_of_High-End_and_Edge_AI_Systems
[35] M. S. Aryanta, C. A. Sari, and E. H. Rachmawanto, "A Banana Disease Detection Using MobileNetV2 Model Based on Adam Optimizer," Journal of Applied Informatics and Computing (JAIC), vol. 9, no. 4, pp. 1207–1218, 2025. [Online]. Available: https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/10183
[36] A. Angdresey, A. F. Ramadhan, and S. Hadiyoso, "Detection of Pests and Plant Diseases Using EfficientNet-B0 Model," Journal of Applied Informatics and Computing (JAIC), vol. 9, no. 4, pp. 1137–1145, 2025. [Online]. Available: https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/9870
[37] M. Fauzan, D. S. Rahardjo, and R. Andriani, "Identification of Rice Plant Diseases Using Convolutional Neural Networks," Journal of Applied Informatics and Computing (JAIC), vol. 9, no. 4, pp. 1770–1777, 2025. [Online]. Available: https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/9373
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Jason Patrick, Shumaya Resty Ramadhani
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
