Analisis Spatiotemporal Pergerakan Pengunjung Ruang Tunggu Rumah Sakit Menggunakan YOLO dan Multi-Object Tracking

Ardiansyah Ardiansyah; Nisrina Akbar Rizky Putri; Rezyana Budi Syahputri

doi:10.56211/sudo.v5i3.1987

Authors

Ardiansyah Ardiansyah Universitas Muhammadiyah Klaten
Nisrina Akbar Rizky Putri Universitas Muhammadiyah Klaten
Rezyana Budi Syahputri Universitas Muhammadiyah Klaten

DOI:

https://doi.org/10.56211/sudo.v5i3.1987

Keywords:

Data Driven; Deep Learning; Multi-Object Tracking; Spatiotemporal; YOLO

Abstract

Peningkatan pemanfaatan layanan kesehatan sebesar 6,6% dibandingkan tahun sebelumnya meningkatkan tekanan terhadap kapasitas pelayanan, sementara standar waktu tunggu rawat jalan ditetapkan <60 menit dan pada kondisi aktual masih ditemukan waktu tunggu >130 menit. Kondisi tersebut menunjukkan kebutuhan akan informasi operasional yang objektif untuk memahami kepadatan dan pergerakan pengunjung secara real-time. Penelitian ini bertujuan mengembangkan analisis spatiotemporal pergerakan pengunjung ruang tunggu rumah sakit berbasis video Closed-Circuit Television (CCTV) menggunakan You Only Look Once (YOLO) dan Multi-Object Tracking (MOT), berbeda dengan pemanfaataan sensor dan pencatatan manual, keduanya rentan bias dalam mengekstraksi dinamika spatiotemporal seperti pola lintasan maupun pemetaan kepadatan area. Penelitian menggunakan YOLOv8n-seg dan YOLOv11n-seg yang dikombinasikan dengan Deep OC-SORT dan StrongSORT pada video dengan frame rate 10 FPS dan 15 FPS. Hasil evaluasi deteksi menunjukkan bahwa kedua model memiliki performa yang tinggi, dengan Precision 0,972 dan Recall 0,971 pada YOLOv8n-seg serta Precision 0,969 dan Recall 0,974 pada YOLOv11n-seg; mAP50 masing-masing mencapai 0,985 dan 0,986, sedangkan F1-Score keduanya sebesar 0,971. Hasil estimasi occupancy menunjukkan bahwa kombinasi YOLOv8n-seg dan Deep OC-SORT menghasilkan MAE 0,94 orang, RMSE 1,31 orang, MAPE 5,98%, dan R² 0,8218 pada 15 FPS. Hasil tracking selanjutnya digunakan untuk membentuk trajectory, heatmap, dan perubahan occupancy terhadap waktu serta diintegrasikan ke dalam dashboard analitik real-time. Penelitian ini menunjukkan bahwa integrasi YOLO dan MOT dapat mentransformasikan data CCTV menjadi informasi spasial dan temporal yang objektif untuk mendukung pemantauan kepadatan ruang tunggu rumah sakit.

Downloads

Download data is not yet available.

References

[1] A. Salinas-Medina and A. Neme, “Enhancing Hospital Efficiency Through Web-Deployed Object Detection: A YOLOv8-Based Approach for Automating Healthcare Operations,” in 2023 Mexican International Conference on Computer Science, ENC 2023, Institute of Electrical and Electronics Engineers Inc., 2023. doi: 10.1109/ENC60556.2023.10508642.

[2] A. Ardiansyah, A. S. Widagdo, K. N. Qodri, S. F. E. Nugroho, and N. A. R. Putri, “Analisis sentimen terhadap pelayanan Kesehatan berdasarkan ulasan Google Maps menggunakan BERT,” JURNAL FASILKOM, vol. 13, no. 02, pp. 326–333, Sep. 2023, doi: 10.37859/jf.v13i02.5170.

[3] R. Hasibuan, “Hospital outpatient waiting time and patient satisfaction: an observational comparative study,” Social Medicine, vol. 18, no. 2, pp. 141–152, May 2025, doi: 10.71164/socialmedicine.v18i2.2025.1611.

[4] Kementrian Kesehatan, Keputusan Menteri Kesehatan Republik Indonesia Nomor 129 Tahun 2008 tentang Standar Pelayanan Minimal Rumah Sakit. Indonesia, 2008.

[5] Muhammad Takwa, Andi Niartiningsih, Nurul Hidayah Nur, Nurfitriani Nurfitriani, and Mene Paradilla, “Analysis of Waiting Time for Patient Service Using Lean Concept in Outstanding Installations Stella Maris Hospital,” International Journal of Medicine and Health, vol. 4, no. 1, pp. 14–23, Jan. 2025, doi: 10.55606/ijmh.v4i1.5469.

[6] F. Y. Sari, R. Rasyid, and F. Firdawati, “Analysis of Waiting Time for Outpatient Services at dr Rasidin Padang Regional Hospital,” Journal La Medihealtico, vol. 6, no. 2, pp. 477–492, 2025, doi: 10.37899/journallamedihealtico.v6i2.2038.

[7] W. Afriana, F. Zulyani, and T. Kurniawan, “Application of Lean Six Sigma Method in Hospital Management Process: Performance Optimization and Waste Reduction,” ENDLESS: INTERNATIONAL JOURNAL OF FUTURE STUDIES, vol. 6, no. 3, pp. 172–184, Nov. 2023, doi: 10.54783/endlessjournal.v6i3.212.

[8] A. Baligh Jahromi, K. Attarian, A. Asgary, and J. Wu, “Advancing Indoor Epidemiological Surveillance: Integrating Real-Time Object Detection and Spatial Analysis for Precise Contact Rate Analysis and Enhanced Public Health Strategies,” Int. J. Environ. Res. Public Health, vol. 21, no. 11, p. 1502, 2024, doi: 10.3390/ijerph21111502.

[9] S. S. Dhanda et al., “Advancement in public health through machine learning: a narrative review of opportunities and ethical considerations,” J. Big Data, vol. 12, no. 1, p. 154, Jul. 2025, doi: 10.1186/s40537-025-01201-x.

[10] L. Deng et al., “Hospital crowdedness evaluation and in-hospital resource allocation based on image recognition technology,” Sci. Rep., vol. 13, no. 1, p. 299, Jan. 2023, doi: 10.1038/s41598-022-24221-6.

[11] A. Jain et al., “Improving Patient Flow in a Healthcare Clinic Post COVID-19: A Data Validation and Exploratory Analysis Approach,” in 2023 Systems and Information Engineering Design Symposium (SIEDS), IEEE, Apr. 2023, pp. 119–124. doi: 10.1109/SIEDS58326.2023.10137848.

[12] A. Ardiansyah and N. F. Hasan, “Deteksi dan Klasifikasi Penyakit Pada Daun Kopi Menggunakan Yolov7,” Jurnal Sisfokom (Sistem Informasi Dan Komputer), vol. 12, no. 1, pp. 30–35, 2023, doi: 10.32736/sisfokom.v12i1.1545.

[13] A. Ardiansyah, A. S. Widagdo, K. N. Qodri, D. Hidayani, and M. Romadhani, “Implementasi Deteksi Tumor Otak Menggunakan YOLOv11 dan Flask,” JURNAL FASILKOM, vol. 15, no. 2, pp. 415–422, 2025, doi: 10.37859/jf.v15i2.9703.

[14] A. Ardiansyah, K. N. Qodri, D. Al Banna, and M. Z. Al-Baihaqi, “Pemanfaatan SAM dan YOLOV8 untuk Deteksi dan Segmentation MRI Tumor Otak,” TEKNIMEDIA: Teknologi Informasi dan Multimedia, vol. 5, no. 1, pp. 82–89, Jun. 2024, doi: 10.46764/teknimedia.v5i1.192.

[15] M. Madhavan et al., “Object Detection Human Activity Recognition for Improved Patient Mobility and Caregiver Ergonomics,” J. WSCG (Plzen)., vol. 33, no. 1–2, 2025, doi: 10.24132/JWSCG.2025-2.

[16] A. Ardiansyah and R. B. Syahputri, “Performance Analysis of YOLOv8, YOLO11, and YOLOE in Detecting Patient Density under Complex Healthcare Conditions,” Jurnal Sisfokom (Sistem Informasi dan Komputer), vol. 14, no. 4, pp. 579–585, 2025, doi: 10.32736/sisfokom.v14i4.2526.

[17] A. Alam, I. Ullah, and Y.-K. Lee, “Video Big Data Analytics in the Cloud: A Reference Architecture, Survey, Opportunities, and Open Research Issues,” IEEE Access, vol. 8, pp. 152377–152422, 2020, doi: 10.1109/ACCESS.2020.3017135.

[18] H. Wang, J. Huang, G. Wang, H. Lu, and W. Wang, “Contactless Patient Care Using Hospital IoT: CCTV-Camera-Based Physiological Monitoring in ICU,” IEEE Internet Things J., vol. 11, no. 4, pp. 5781–5797, Feb. 2024, doi: 10.1109/JIOT.2023.3308477.

[19] G. Hu et al., “Using artificial intelligence and computer vision to detect and monitor unhealthy child-directed food and beverage marketing: a data-driven study,” EClinicalMedicine, vol. 89, p. 103549, Nov. 2025, doi: 10.1016/j.eclinm.2025.103549.

[20] H. Herfandi, O. S. Sitanggang, M. R. A. Nasution, H. Nguyen, and Y. M. Jang, “Real-Time Patient Indoor Health Monitoring and Location Tracking with Optical Camera Communications on the Internet of Medical Things,” Applied Sciences, vol. 14, no. 3, p. 1153, Jan. 2024, doi: 10.3390/app14031153.

[21] C. Li, J. Wang, S. Wang‎, and Y. Zhang, “A review of IoT applications in healthcare,” Neurocomputing, vol. 565, p. 127017, Jan. 2024, doi: 10.1016/j.neucom.2023.127017.

[22] G. V. Orlov and A. N. Kalinichenko, “Computer Vision Model for Analyzing Registry Workload CDC ‘Almazov National Medical Research Centre,’” in 2024 V International Conference on Neural Networks and Neurotechnologies (NeuroNT), IEEE, Jun. 2024, pp. 58–61. doi: 10.1109/NeuroNT62606.2024.10585604.

[23] H.-S. Sim and H.-C. Cho, “Enhanced DeepSORT and StrongSORT for Multicattle Tracking With Optimized Detection and Re-Identification,” IEEE Access, vol. 13, pp. 19353–19364, 2025, doi: 10.1109/ACCESS.2025.3535092.

[24] H. Lee, D. Kang, H. Park, S. Park, D. Jeong, and J. Paik, “Real-Time Human Group Detection and Clustering in Crowded Environments Using Enhanced Multi-Object Tracking,” IEEE Access, vol. 12, pp. 184028–184039, 2024, doi: 10.1109/ACCESS.2024.3503661.

[25] D. A. Maharani, C. Machbub, P. H. Rusmin, and L. Yulianti, “Real-Time Human Tracking Using Multi-Features Visual With CNN-LSTM and Q-Learning,” IEEE Access, vol. 12, pp. 13233–13247, 2024, doi: 10.1109/ACCESS.2024.3355785.

[26] E. Prezioso, F. Giampaolo, S. Izzo, M. Savoia, and F. Piccialli, “Integrating Object Detection and Advanced Analytics for Smart City Crowd Management,” in 2023 IEEE International Conference on Networking, Sensing and Control (ICNSC), IEEE, Oct. 2023, pp. 1–6. doi: 10.1109/ICNSC58704.2023.10318989.

[27] M. Javaid, A. Haleem, R. P. Singh, R. Suman, S. Khan, and S. Rab, “Adoption of Internet of Things for smart city-enabled smart hospitals,” Intelligent Hospital, vol. 1, no. 2, p. 100011, Dec. 2025, doi: 10.1016/j.inhs.2025.100011.

[28] R. Wang, H. Gao, and Y. Liu, “A data fusion-based method for pedestrian detection and flow statistics across different crowd densities,” Journal of Safety Science and Resilience, vol. 6, no. 1, pp. 105–113, Mar. 2025, doi: 10.1016/j.jnlssr.2024.07.004.

[29] D. Hidayani, Mustofa Romadhani, and A. Ardiansyah, “Deep Learning Approach for Sleepiness Detection with YOLOv12,” JKTI Jurnal Keilmuan Teknologi Informasi, vol. 1, no. 1, pp. 5–10, Jun. 2025, doi: 10.61902/jkti.v1i1.1681.

[30] K. Gkountakos, D. Touska, K. Ioannidis, T. Tsikrika, S. Vrochidis, and I. Kompatsiaris, “Spatio-Temporal Activity Detection and Recognition in Untrimmed Surveillance Videos,” in Proceedings of the 2021 International Conference on Multimedia Retrieval, New York, NY, USA: ACM, Aug. 2021, pp. 451–455. doi: 10.1145/3460426.3463591.

[31] S. Tu et al., “Tracking and automatic behavioral analysis of group-housed pigs based on YOLOX+BoT-SORT-slim,” Smart Agricultural Technology, vol. 9, p. 100566, Dec. 2024, doi: 10.1016/j.atech.2024.100566.

[32] Y. Li, B. Zhang, Y. Liu, H. Wang, and S. Zhang, “Personnel Monitoring in Shipboard Surveillance Using Improved Multi-Object Detection and Tracking Algorithm,” Sensors, vol. 24, no. 17, p. 5756, Sep. 2024, doi: 10.3390/s24175756.

[33] S. John, “Efficient Spatial-Temporal Modeling for Real-Time Video Analysis: A Unified Framework for Action Recognition and Object Tracking,” arXiv preprint arXiv:2507.22421, 2025.

[34] Q. Zhang et al., “A Survey of Generative Techniques for Spatial-Temporal Data Mining,” Data Sci. Eng., Mar. 2026, doi: 10.1007/s41019-026-00346-w.

[35] F. I. Hairuddin, S. Azri, and U. Ujang, “Advanced Techniques for Spatio-Temporal Data Management in Graph Databases—A Systematic Review,” Journal of Advances in Information Technology, vol. 17, no. 1, pp. 14–33, 2026, doi: 10.12720/jait.17.1.14-33.

[36] G. Fenu and F. M. Malloci, “DiaMOS plant: A dataset for diagnosis and monitoring plant disease,” Agronomy, vol. 11, no. 11, p. 2107, 2021.

[37] A. Ardiansyah, Buku Monograf Pengenalan Objek Dalam Bidang Kesehatan. PT. Sonpedia Publishing Indonesia, 2024.

[38] T. Iida, “Identifying causes of errors between two wave-related data using performance metrics,” Applied Ocean Research, vol. 148, p. 104024, Jul. 2024, doi: 10.1016/j.apor.2024.104024.

[39] Y. Zhang, Z. Wang, J. Liu, Y. Li, Z. Huang, and X. Yu, “A metaheuristic-driven categorical boosting framework with interpretability for high-precision prediction of mechanical properties in corroded reinforced concrete beams,” Eng. Appl. Artif. Intell., vol. 163, p. 112804, Jan. 2026, doi: 10.1016/j.engappai.2025.112804.