No abstract

In pandemic conditions such as COVID-19, the measurement of vital signs such as body temperature and heart rate becomes the basis for conducting health screenings. To reduce physical contact and potential hazards, this measurement process can be carried out non-contact. The non-contact measurements carried out in this study used a thermal imaging approach. To reduce the potential danger of transmission, this non-contact measurement device is applied to a security robot. The non-contact measurement method using thermal imaging is done by processing a thermal image on the forehead area. Changes in temperature in the forehead area are then entered into a bandpass filter with a frequency of 0.75 Hz to 3 Hz, which is the frequency range of the human heartbeat under normal circumstances. Calculating heart rate is carried out with two approaches, namely peak to peak interval and fast Fourier transform. Based on the peak-to-peak interval approach, the accuracy is 89.24%, with a standard deviation of 5.6. Meanwhile, with the dominant frequency detection approach using the fast Fourier transform, the accuracy value is slightly better, at 91.84%, with a standard deviation of 4.81.

No abstract

<span lang="EN-US">Remote photoplethysmography (rPPG) for non-contact heart rate measurement has been widely developed and shows good development. However, motion artifact due to changes in illumination and subject movement is still the main problem. Especially when measurements are taken in real conditions. In these conditions, it will be vulnerable to rPPG signal readings with poor signal quality. So, in this paper, it is proposed to classify the signal quality using one dimensional convolutional neural network (1D CNN). The classification is carried out based on the extraction of the temporal features of the rPPG signal that has been obtained from the plane orthogonal to skin algorithm and the magnitude of the subject's movement when measured. The classification results are entered into a compensated network if the signal obtained shows moderate quality. The compensated network will provide a more accurate estimate of hr value. The test was carried out using a dataset of 10 subjects, each measured with 3 different types of illumination. In the experiments conducted, the system's performance showed an improvement compared to the POS algorithm alone. The experiment found that the mean absolute error measurement was 2.78, and the mean error was relative at 3.67%.</span>

Hour meter adalah instrument untuk mengukur lama penggunaan peralatan yang biasa digunakan pada sistem untuk mengukur runtime. Tujuan hour meter adalah untuk memonitor penggunaan alat sebagai dasar perawatan peralatan tersebut. Pada penelitian ini bertujuan untuk mengumpulkan data running hour saat kondisi berbeban secara online pada satu server, sehingga dapat lebih mudah memonitor. Menggunakan sensor arus untuk mengukur beban kerja dan lama penggunaan pada motor listrik. Data dikirim oleh mikrokontroler melalui wifi ke server firebase, aplikasi android membaca data firebase dan memproses data dengan metode fuzzy mamdani. Metode fuzzy mamdani akan menglompokan data menjadi tiga kategori penggunaan berdasarkan beban kerja dan lama penggunaan. Sebagai pengujian dan analisa sistem dilakukan pada motor DC dan AC. Pada motor DC dilakukan tiga kali percobaan pada line follower dengan variasi beban yang menghasilkan arus 53-1024 mA sesuai dengan berat beban yang diberikan. Pengujian pada motor AC berhasil dilakukan satu kali dan menujukan output kategori yang sesuai dengan waktu dan beban kerja motor. Berdasarkan pengujian tersebut hour meter dapat diaplikasikan pada line follower dan motor AC dengan hasil yang sangat baik untuk dapat memonitor secara online lama waktu penggunaan perlatan tersebut.