Evaluation of Accuracy and Class-wise Precision of a Convolutional Neural Network Model Trained with Teachable Machine in a Pet Identification and Search Application
DOI:
https://doi.org/10.55204/trc.v5i1.e428Keywords:
software, Python, pets, web applicationAbstract
In this study, the issue of searching for lost pets is addressed through the use of convolutional neural networks, specifically implemented on Google's Teachable Machine platform. The limitation of traditional methods, such as social networks and physical posters, is highlighted, and there is a proposal to enhance the identification and search for lost pets through artificial intelligence. The methodology involves gathering a dataset composed of images of cats and dogs, using the Teachable Machine platform to train the convolutional neural network model. An evaluation of the model's accuracy is conducted with datasets of different sizes (10, 30, and 50 images). The results show that the model's accuracy varies significantly among the datasets, emphasizing the importance of providing a greater number of images to improve accuracy. It is suggested to ensure optimal lighting conditions in the images, highlight distinctive features of the pets, and maintain consistency in the number of images in the datasets. The importance of considering the dimension of rescaling the original images during the model's development is also highlighted.
Downloads
References
Agustian, D., Pertama, P. P. G. P., Crisnapati, P. N., & Novayanti, P. D. (2021). Implementation of Machine Learning Using Google’s Teachable Machine Based on Android. 1-7. https://doi.org/10.1109/ICORIS52787.2021.9649528
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021). Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. Journal of big Data, 8(1), 53. https://doi.org/10.1186/s40537-021-00444-8
Andreae, P. M., & Andreae, J. H. (1978). A teachable machine in the real world. International Journal of Man-Machine Studies, 10(3), 301-312. https://doi.org/10.1016/S0020-7373(78)80048-0
Artola Moreno, Á. (2019). Clasificación de imágenes usando redes neuronales convolucionales en Python [Trabajo Fin de Grado, Universidad de Sevilla]. https://idus.us.es/server/api/core/bitstreams/c22e9088-218a-4554-9b27-6c0ebf89d0e8/content
Arulprakash, E., & Aruldoss, M. (2022). A study on generic object detection with emphasis on future research directions. Journal of King Saud University-Computer and Information Sciences, 34(9), 7347-7365. https://doi.org/10.1016/j.jksuci.2021.08.001
Bodero, E. M., Lopez, M. P., Congacha, A. E., Cajamarca, E. E., & Morales, C. H. (2020). Google Colaboratory como alternativa para el procesamiento de una red neuronal convolucional. Revista Espacios, 41(07).
Carney, M., Webster, B., Alvarado, I., Phillips, K., Howell, N., Griffith, J., Jongejan, J., Pitaru, A., & Chen, A. (2020). Teachable machine: Approachable Web-based tool for exploring machine learning classification. 1-8. https://doi.org/10.1145/3334480.3382839
Kacorri, H. (2017). Teachable machines for accessibility. ACM SIGACCESS accessibility and computing, 119, 10-18. https://doi.org/10.1145/3167902.316790
Liu, X., Soh, K. G., Dev Omar Dev, R., Li, W., & Yi, Q. (2023). Design and implementation of adolescent health Latin dance teaching system under artificial intelligence technology. Plos one, 18(11), e0293313. https://doi.org/10.1371/journal.pone.0293313
Massiris, M., Delrieux, C., & Fernández Muñoz, J. Á. (2018). Detección de equipos de protección personal mediante red neuronal convolucional YOLO. Jornadas de Automática, Badajoz, 5(7), 1022-1029. https://doi.org/10.17979/spudc.9788497497565.1022
O’shea, K., & Nash, R. (2015). An introduction to convolutional neural networks. Neural and Evolutionary Computing. https://doi.org/10.48550/arXiv.1511.08458
Prasad, R., & Manjunath, T. (2024). AI-ML Trained Object Recognition System Development using Google Teachable Machine with the Help of Data Sciences. Grenze International Journal of Engineering & Technology (GIJET), 10.
Saqib, S. M., Iqbal, M., Mazhar, T., Shahzad, T., Ouahada, K., & Hamam, H. (2025). Effectiveness of Teachable Machine, mobile net, and YOLO for object detection: A comparative study on practical applications. Egyptian Informatics Journal, 30, 100680. https://doi.org/10.1016/j.eij.2025.100680
Sharma, T., Debaque, B., Duclos, N., Chehri, A., Kinder, B., & Fortier, P. (2022). Deep learning-based object detection and scene perception under bad weather conditions. Electronics, 11(4), 563. https://doi.org/10.3390/electronics11040563
Siddiqui, N. (2023). Creating Deep Convolutional Neural Networks for Image Classification. The Programming Historian. https://doi.org/10.46430/phen0108
Tjaden, J., & Tjaden, B. (2023). MLpronto: A tool for democratizing machine learning. Plos one, 18(11), e0294924. https://doi.org/10.1371/journal.pone.0294924
Trujillo Santillán, N. S., Grijalva Rosero, C. J., & Herrera Mendoza, B. R. (2024). Estimación de la población de perros y gatos en situación de calle dentro del cantón Riobamba -Ecuador. RECIENA Edición Especial, 4(1), 27-32. https://doi.org/10.47187/tfw9et71
Zhou, M., Fung, I., Yang, L., Wan, N., Di, K., & Wang, T. (2023). LostNet: A smart way for lost and find. arXiv preprint arXiv:2301.02277. https://doi.org/10.48550/arXiv.2301.02277
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Sofía Haro – Orozco, Diego Mayorga - Pérez
This work is licensed under a Creative Commons Attribution 4.0 International License.
The authors retain the moral and patrimonial rights of their works. They only give to the magazine Tesla Revista Científica the right to the first publication of this. Since Tesla Revista Científica is an open access publication, readers can fully or partially reproduce its content as long as they properly credit the corresponding authors and the journal itself. Tesla Revista Científica undertakes not to make commercial use of the texts it receives and/or publishes.
Our journal is governed by the international policies SHERPA/RoMEO: Green journal: They allow the self-archiving of both the pre-print (draft of a paper) and the post-print (the version corrected and reviewed by peers) and even the final version ( layout as it will be published in the journal).
See also "Copyright and licences".
