Penerapan Modul Ghost dan SimAM pada Sistem Guide Following Kursi Roda Pintar Berbasis YOLOv8N
Kata Kunci:
kursi roda pintar, deteksi objek, pelacakan manusia, YOLOv8N, modul ghost, SimAMAbstrak
Kursi roda merupakan salah satu alat bantu mobilisasi bagi penyandang disabilitas untuk dapat beraktivitas yang sebelumnya tidak mungkin dilakukan sehingga memberi mereka rasa kebebasan dan kemandirian. Namun, kursi roda manual mengharuskan pengguna atau orang lain untuk mengoperasikannya dengan tenaga yang besar. Apabila aktivitas tersebut dilakukan terus menerus dapat meningkatkan resiko gangguan muskuloskeletal. Kursi roda pintar telah banyak berkembang untuk meningkatkan mobilisasi penggunanya. Salah satunya dengan mendeteksi posisi asisten penyandang disabilitas yang ada di depan kursi roda. Algoritma deteksi objek, YOLOv8, menawarkan peforma yang baik untuk deteksi secara real-time. Namun, algoritma tersebut memerlukan sumber daya komputasi yang besar. Penelitian ini akan menerapkan modul ghost dan SimAM pada arsitektur YOLOv8n untuk mengurangi kompleksitas model dan mempertahankan akurasi. Dari hasil pelatihan model tersebut didapatkan nilai mAP50 sebesar 0,995 dan nilai mAP50-95 sebesar 0,864 dengan parameter berkurang menjadi 1,7 juta parameter. Kemudian pada integrasi model dengan kursi roda, didapatkan akurasi sebesar 95%. Hal ini menunjukkan bahwa kursi roda pintar dapat bergerak sesuai hasil deteksi posisi pemandu dengan baik.
Referensi
Alif, M.A.R. and Hussain, M., 2024. YOLOv1 to YOLOv10: A comprehensive review of YOLO variants and their application in the agricultural domain. [online] pp.1–31. Available at: <http://arxiv.org/abs/2406.10139>.
Andika, S. and Utaminingrum, F., 2023. Sistem Automatic Human Tracking pada Kursi Roda Pintar menggunakan Metode YOLOv7-Tiny berbasis Nvidia Jetson TX2. Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, [online] 7(5), pp.2299–2304. Available at: <https://j-ptiik.ub.ac.id/index.php/j-ptiik/article/view/12703>.
Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C. and Xu, C., 2020. GhostNet: More features from cheap operations. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp.1577–1586. https://doi.org/10.1109/CVPR42600.2020.00165.
Jayakody, A., Nawarathna, A., Wijesinghe, I., Liyanage, S. and Dissanayake, J., 2019. Smart Wheelchair to Facilitate Disabled Individuals. 2019 International Conference on Advancements in Computing, ICAC 2019, pp.249–254. https://doi.org/10.1109/ICAC49085.2019.9103409.
Karpov, V.E., Malakhov, D.G., Moscowsky, A.D., Rovbo, M.A., Sorokoumov, P.S., Velichkovsky, B.M. and Ushakov, V.L., 2019. Architecture of a wheelchair control system for disabled people: Towards multifunctional robotic solution with neurobiological interfaces. Sovremennye Tehnologii v Medicine, 11(1), pp.90–100. https://doi.org/10.17691/stm2019.11.1.11.
Kothala, L.P., Jonnala, P. and Guntur, S.R., 2023. Localization of mixed intracranial hemorrhages by using a ghost convolution-based YOLO network. Biomedical Signal Processing and Control, [online] 80(P2), p.104378. https://doi.org/10.1016/j.bspc.2022.104378.
Sohan, M., Sai Ram, T. and Rami Reddy, C.V., 2024. A Review on YOLOv8 and Its Advancements. (January), pp.529–545. https://doi.org/10.1007/978-981-99-7962-2_39.
Xu, J., Yang, H., Wan, Z., Mou, H., Qi, D. and Han, S., 2023a. Wood Surface Defects Detection Based on the Improved YOLOv5-C3Ghost With SimAm Module. IEEE Access, 11(August), pp.105281–105287. https://doi.org/10.1109/ACCESS.2023.3303890.
Xu, Q., Wei, Y., Gao, J., Yao, H. and Liu, Q., 2023b. ICAPD Framework and simAM-YOLOv8n for Student Cognitive Engagement Detection in Classroom. IEEE Access, 11(December), pp.136063–136076. https://doi.org/10.1109/ACCESS.2023.3337435.
Yang, L., Zhang, R.Y., Li, L. and Xie, X., 2021. SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks. Proceedings of Machine Learning Research, 139, pp.11863–11874.
Alif, M.A.R. and Hussain, M., 2024. YOLOv1 to YOLOv10: A comprehensive review of YOLO variants and their application in the agricultural domain. [online] pp.1–31. Available at: <http://arxiv.org/abs/2406.10139>.
Andika, S. and Utaminingrum, F., 2023. Sistem Automatic Human Tracking pada Kursi Roda Pintar menggunakan Metode YOLOv7-Tiny berbasis Nvidia Jetson TX2. Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, [online] 7(5), pp.2299–2304. Available at: <https://j-ptiik.ub.ac.id/index.php/j-ptiik/article/view/12703>.
Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C. and Xu, C., 2020. GhostNet: More features from cheap operations. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp.1577–1586. https://doi.org/10.1109/CVPR42600.2020.00165.
Jayakody, A., Nawarathna, A., Wijesinghe, I., Liyanage, S. and Dissanayake, J., 2019. Smart Wheelchair to Facilitate Disabled Individuals. 2019 International Conference on Advancements in Computing, ICAC 2019, pp.249–254. https://doi.org/10.1109/ICAC49085.2019.9103409.
Karpov, V.E., Malakhov, D.G., Moscowsky, A.D., Rovbo, M.A., Sorokoumov, P.S., Velichkovsky, B.M. and Ushakov, V.L., 2019. Architecture of a wheelchair control system for disabled people: Towards multifunctional robotic solution with neurobiological interfaces. Sovremennye Tehnologii v Medicine, 11(1), pp.90–100. https://doi.org/10.17691/stm2019.11.1.11.
Kothala, L.P., Jonnala, P. and Guntur, S.R., 2023. Localization of mixed intracranial hemorrhages by using a ghost convolution-based YOLO network. Biomedical Signal Processing and Control, [online] 80(P2), p.104378. https://doi.org/10.1016/j.bspc.2022.104378.
Sohan, M., Sai Ram, T. and Rami Reddy, C.V., 2024. A Review on YOLOv8 and Its Advancements. (January), pp.529–545. https://doi.org/10.1007/978-981-99-7962-2_39.
Xu, J., Yang, H., Wan, Z., Mou, H., Qi, D. and Han, S., 2023a. Wood Surface Defects Detection Based on the Improved YOLOv5-C3Ghost With SimAm Module. IEEE Access, 11(August), pp.105281–105287. https://doi.org/10.1109/ACCESS.2023.3303890.
Xu, Q., Wei, Y., Gao, J., Yao, H. and Liu, Q., 2023b. ICAPD Framework and simAM-YOLOv8n for Student Cognitive Engagement Detection in Classroom. IEEE Access, 11(December), pp.136063–136076. https://doi.org/10.1109/ACCESS.2023.3337435.
Yang, L., Zhang, R.Y., Li, L. and Xie, X., 2021. SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks. Proceedings of Machine Learning Research, 139, pp.11863–11874.
Unduhan
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2025 Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Artikel ini berlisensiCreative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
