In December 2019, there was a pandemic caused by a new type of coronavirus, namely SARS-CoV-2 (Severe Acute Respiratory Syndrome Corona Virus 2) spread almost throughout the world. The World Health Organization (WHO) named it COVID-19 (Coronavirus Disease). To minimize the spread of the COVID-19, the Indonesian government announced a policy for the social distancing of 1-2 meters and wearing a medical mask. In this study, a mask detection system was built using the Haar Cascade Classifier method by detecting the facial areas such as the nose and lips. The study aims to distinguish between using masks and on the contrary. It is expected that the mask detection system can be implemented to provide direct warnings to people who do not wear masks in public areas. The results using the Haar Cascade Classifier method show that the system designed is able to detect faces, noses, and lips at a light intensity of 80-140 lux. The face is detected at a distance of 30-120cm, while the nose is at a distance of 30-60cm, while the lips are at a distance of 30-70cm. The system designed can perform the detection process at a speed of 5 fps. The overall test results obtained a success rate of 88,89%.
Internet of things (IoT) merupakan topik yang banyak dikembangkan pada dekade terakhir. Pada saat ini, banyak pengembang teknologi membuat perangkat-perangkat pintar yang dapat mempermudah pekerjaan manusia. Sistem rumah pintar adalah salah satunya. Pada sistem rumah pintar, perangkatperangkat fisik dapat melakukan komunikasi melalui jaringan internet atau jaringan near cable lainnya untuk bertukar informasi atau melakukan perintah dari penghuni rumah. Agar bisa bertukar informasi maka perangkat fisik tersebut di integrasikan dengan sensor dan aktuator. Salah satu implementasi dari rumah pintar yaitu pengontrolan lampu yang dapat diaktifkan atau dinonaktifkan menggunakan perintah suara atau menggunakan gawai pengguna. Tujuan dari penelitian ini yaitu agar pengguna dapat mengontrol lampu rumah dengan menggunakan perintah suara dengan bantuan google assistant untuk mengenali kalimat yang di ucapkan oleh penghuni rumah. Metode yang digunakan dalam penelitian ini yaitu IoT. Metode komunikasi berbasis IoT memungkinkan terjadinya pertukaran data antar device. Hasil dari penelitian ini yaitu dapat dibangun sistem kontrol lampu menggunakan Blynk-Google assistant. Pada sistem tersebut telah di tambahkan fitur untuk memantau konsumsi daya listrik pengguna. Dari hasil pengujian yang dilakukan maka didapatkan hasil bahwa presentase keberhasilan dari sistem tersebut yaitu 96,667%. Keberhasilan dari sistem tersebut dipengaruhi oleh kekuatan sinyal internet dan ketepatan dalam pengucapan kata yang telah terprogram.
<p><em><span>Temperature is an object of research that is often studied. Research on temperature is within the scope of control and monitoring. The process of controlling and monitoring temperature is influenced by the selection of the right temperature sensor. The temperature sensors that are often used are the LM35 sensor and the DHT11 sensor. The LM35 sensor has advantages in terms of a simple design and easy to implement, while the DHT11 sensor has the advantage because in one sensor package there are two functions, namely to measure air temperature and humidity. In this study, temperature measurement accuracy was carried out to facilitate researchers in determining the right temperature sensor. The data monitoring method uses the internet of things (IoT). The results of the research show that the DHT11 temperature sensor is more accurate and more stable than the LM35 temperature sensor. The results of the sensor test at room temperature, the DHT11 sensor has an accuracy rate of 97.21% while the LM35 sensor has an accuracy rate of 96.86%. While the results of the sensor test in the server room, the DHT11 sensor has an accuracy rate of 95.26%, while the LM35 sensor has an accuracy rate of 90.32%.</span></em></p>
The eyes are one of the vital organs owned by humans. One of the common eye diseases is cataracts. This disease is characterized by clouding of the lens of the eye and can interfere with vision. Worst case, sufferers can experience blindness. Cataract maturity can be divided into four categories, namely incipient, immature, mature, and hypermature. Cataracts can be removed through surgery when the cataract is in the mature or hypermature phase. Cataract examination is usually done using a slit lamp. The lack of hospitals that have this equipment can cause delays in the healing process for cataract sufferers. This study created an image processing algorithm for the maturity classification process of cataracts using the Convolutional Neural Network method with LeNet network architecture. The algorithm that has been built is capable of classifying the maturity of cataracts with an accuracy rate of 93.33%
COVID-19 menjadi salah satu pandemi global yang bertanggung jawab atas tingginya angka kematian dan penurunan stabilitas ekonomi selama dua tahun terakhir. Salah satu upaya yang dapat dilakukan untuk mencegah penyebaran virus penyebab pandemi tersebut adalah dengan memakai masker saat berada di tempat umum. Namun dalam kenyataan di lapangan, masih banyak orang yang memakai masker dengan cara yang salah dan bahkan ada yang tidak memakai masker saat berada di tempat umum. Dari permasalah tersebut, dibutuhkan suatu sistem klasifikasi yang dapat digunakan untuk mengidentifikasi penggunaan masker berbasis citra. Dalam artikel ini, dijelaskan suatu penelitian mengenai pengembangan algoritma pengolahan citra yang dipadukan dengan pembelajaran mesin berbasis jaringan syaraf tiruan mendalam untuk proses klasifikasi penggunaan masker. Model dari jaringan syaraf tiruan mendalam yang digunakan adalah LeNet. Dalam proses pembelajaran mesin digunakan dataset sebanyak 400 gambar yang dibagi menjadi 240 gambar untuk kebutuhan training dan 160 gambar untuk kebutuhan validasi. Penelitian ini menghasilkan sistem klasifikasi penggunaan masker dengan tingkat akurasi sebesar 98,75%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.