A Systematic Literature Review on Optimizing Mask Detection Systems Using Convolutional Neural Networks for Public Health and Safety
DOI:
https://doi.org/10.56313/jictas.v3i2.391Kata Kunci:
Mask Detection, Convolutional Neural Network (CNN), Public Health, Systematic Review, IoTAbstrak
COVID-19 pandemic significantly impacted public health and safety globally, necessitating strict implementation of health protocols, including mask usage. Monitoring mask compliance remains challenging, particularly in public spaces. This study conducts a systematic literature review on optimizing mask detection systems using Convolutional Neural Networks (CNN) for public health and safety. CNN demonstrates robust performance in recognizing facial patterns and accurately detecting masks, addressing challenges such as lighting variations, occlusions, and diverse facial orientations. The review highlights advancements in CNN-based architectures, dataset utilization, and real-time implementation strategies. The study utilized a dataset comprising images of individuals with and without masks, split into 80% training and 20% testing data, achieving high accuracy in identifying mask usage. Integration possibilities with access control systems, Computer Vision, and Internet of Things (IoT) technologies are explored for scalable, real-time monitoring. The findings contribute significantly to optimizing health protocol enforcement and mitigating COVID-19 transmission risks in public areas
Referensi
L. Yang et al., "COVID-19: Immunopathogenesis and Immunotherapeutics," Springer Nature, Dec. 2020. DOI: 10.1038/s41392-020-00243-2.
T. P. Velavan and C. G. Meyer, "The COVID-19 Epidemic," Tropical Medicine & International Health, vol. 25, no. 3, pp. 278–280, Mar. 2020. DOI: 10.1111/tmi.13383.
M. Mudzakkir et al., "Efforts to Prevent Covid-19 Transmission in District Communities. Kediri," Contribution: Journal of Research and Community Service, vol. 2, no. 1, pp. 56–65, Nov. 2021. DOI: 10.53624/contributi.v2i1.85.
N. F. Dai, "Public Stigma Against the Covid-19 Pandemic," [Online]. Available: https://ojs.literacyinstitute.org/index.php/prosiding-covid19.
F. N. Fadillah and K. Aelani, "Monitoring Use of Masks Among Visitors of STMIK 'AMIKBANDUNG' Using the Convolutional Neural Network (CNN) Algorithm," 2023.
P. Nyoman and P. K. Negara, "Detection of Covid-19 Prevention Masks Using Android-Based Convolutional Neural Network," RESTI Journal (Information Systems and Technology Engineering), vol. 5, no. 3, pp. 576–583, Jun. 2021. DOI: 10.29207/resti.v5i3.3103.
V. Dores, "Mask Identification in Face Detection Using the Haar Cascade and CNN Method," Journal of Information Systems and Technology, Aug. 2022. DOI: 10.37034/jsisfotek.v4i4.154.
N. Adhayanti, T. Nugroho, and R. Susiloatmadja, "Real Time Detection System for Masked Face Using CNN Method," JUST, vol. 2, no. 1, 2023.
D. R. R. Putra and R. A. Saputra, "Implementation of Convolutional Neural Network (CNN) to Detect Mask Use in Images," Journal of Informatics and Applied Electrical Engineering, vol. 11, no. 3, pp. 1–10, Aug. 2023. DOI: 10.23960/jitet.v11i3.3286.
M. Abdillah et al., "Implementation of a Raspberry Pi 4-Based Mask Detection System Using the Convolutional Neural Network (CNN) Method in the COVID-19 Health Protocol Screening Process," IJCCS, vol. 15, no. 4, pp. 101–108, 2022.
R. Syahrial, T. Sukmawati, and E. N. Dewi, "Face Mask Detection Using Python and OpenCV to Detect Violations of COVID-19 Health Protocols," Journal of Information Systems Research, vol. 3, no. 3, pp. 291–299, 2022.
L. Farokhah, "Comparison of Face Detection Methods Using OpenCV Haar Cascade, OpenCV SSD, and DLib CNN," RESTI Journal (Information Systems and Technology Engineering), vol. 5, no. 3, pp. 609–614, Jun. 2021. DOI: 10.29207/resti.v5i3.3125.
S. Megawan, W. S. Lestari, and A. Halim, "Real Time Non-Spoofing Face Detection in Videos Using Faster R-CNN," Journal of Information System Research, vol. 3, no. 3, pp. 291–299, Apr. 2022. DOI: 10.47065/josh.v3i3.1519.
D. Bhatt et al., "CNN Variants for Computer Vision: History, Architecture, Application, Challenges and Future Scope," Electronics, vol. 10, no. 24, pp. 1–20, Oct. 2021. DOI: 10.3390/electronics10202470.
S.-Y. Wang et al., "CNN-Generated Images Are Surprisingly Easy to Spot... for Now," [Online]. Available: https://www.motherjones.com/politics/2019/03/.
R. Jin et al., "Face Recognition Based on MTCNN and FaceNet," AAAI Conference on Artificial Intelligence, 2021. [Online]. Available: www.aaai.org.
X. Xu et al., "Lightweight FaceNet Based on MobileNet," Int. J. Intell. Sci., vol. 11, no. 1, pp. 1–16, 2021. DOI: 10.4236/ijis.2021.111001.
T. Wahyu Qur'ana, "Implementation of the Convolutional Neural Network (CNN) Method for Classifying Motifs in Sasirangan Images," Multidisciplinary Scientific Journal, vol. 1, no. 7, pp. 2986–6340, 2023. DOI: 10.5281/zenodo.8305503.
B. Yanto, A. Lubis, and B. H. Hayadi, "Classification of Pineapple Ripeness Based on Hue Saturation Intensity (HSI) Using CNN," Jurnal Inovtek Polbeng Seri Informatika, vol. 6, no. 2, pp. 259–268, 2021.
Lubis et al., "Designing Architecture of Information Dashboard System to Monitor Economic Census 2016," Proc. of 4th Int. Conf. Information and Communication Technology (ICoICT), pp. 1–6, 2016. DOI: 10.1109/ICoICT.2016.7571910.
