“Face Mask Detection Using the Convolutional Neural Network” is a PC based program that aims to detect and classify human beings whether a person is using a mask or not with access through a webcam camera. This program is created using the Python language with several libraries. The classification of face masks uses the Convolutional Neural Network method with the MobileNetV2 architecture. Meanwhile, human face detection uses the Haarcascade Classifier. How the program works is by accessing the connected camera and if the person detected is wearing a mask, the person will be labeled "using a mask" and given a green box to mark the detection along with the analysis value, whereas if not, it will be labeled "not using a mask" and a red box with also the predicted value. From the test results, it can be proven that the accuracy program is good enough to detect the use of face masks with an average object detection accuracy of 88.53% and the classifier for the use of mask an average of 84.45%.
Diabetes adalah penyakit yang terjadi ketika kandungan glukosa di dalam darah tinggi. Tes glukosa yang menghasilkan keakuratan tinggi harus dilakukan beberapa kali untuk mendeteksi diabetes di dalam tubuh. Beberapa indikator di dalam tubuh dapat menjadi titik awal untuk mendeteksi diabetes. Bagaimanapun juga, keterbatasan seorang tenaga medis dalam mendeteksi dalam jumlah data yang sangat besar dengan cara manual menjadi kendala. Salah satu solusi untuk gap tersebut adalah menggunakan komputer sebagai perhitungan matematika dalam metode pengelompokan K-Means dan Fuzzy C-Means. Pengelompokan terdiri dari kelompok diabetes dan non-diabetes. Pengujian untuk masing-masing metode dilakukan terhadap 9 data. Hasil pengujian terbaik metode K-Means adalah 73,438% dan untuk metode Fuzzy C-Means adalah 82,812%.
Car Type Detection and Recogniton system is an application that is developed using You Only Look Once (YOLO) and Convolutional Neural Network (CNN) algorithm. This application purpose is to detect and recognize the car image from the data input. In this application the input image will be divided into two parts, namely the training image and test image. For the training image, the first step, the training image will be divided into two process stages, namely detecting the image of a car and searching for the unique features of a car.To detect the image of the car, the image will be processed to detect parts of the image of the car and not the car using the YOLO method. After obtaining a part of the car image, the image of the car will be saved as a detection model. The image that has been detected will be learning the car image by the CNN method. For the test images of the stages carried out as in the training image, after the image of the car is detected, an introduction will be made based on learning that has been done with the CNN method to obtain output in the form of a car that is successfully recognized and detected will be labeled by the application.
Tomato is one of the farming commodities in Indonesia, easy to plant but easy to get sick. Analizing the disease in plain view still not yet achieve high accuracy result, so we use the help of Convolutional Neural Network (CNN) algorithm. This research is quantitative, with image of a single tomato leaf that is infected as the input. The constructed model gains an accuracy of 58.33% with 12.716 image consisting of Bacterial Spot, Early Blight, Late Blight, Leaf Mold, Target Spot, Spider Mites, Mosaic Virus, Yellow Leaf Curl Virus, Septoria Leaf Spot and healthy leaf. The conclusion from this research is that classification of Tomato leaf disease using CNN can help achieve a higher accuracy but using LeNet-5 as the model architecture is not very effective.
Sistem Isyarat Bahasa Indonesia merupakan salah satu media untuk berkomunikasi sesamakaum tunarungu. Maka untuk mendukung terwujudnya seperangkat isyarat jari, perludirancang program aplikasi pengenalan pola bahasa isyarat. Perancangan ini menggunakantransformasi Haar Wavelet dan Momentum Backpropagation Neural Network. Haar Waveletdigunakan untuk mendapatkan ciri penting citra dan Momentum Backpropagation NeuralNetwork untuk melakukan proses pembelajaran dan pengenalan. Tujuan perancangan iniadalah untuk mengetahui pola bentuk tangan yang benar dalam mempelajari abjad bahasaisyarat. Perancangan aplikasi ini menggunakan bahasa pemograman Visual Basic dan SQLserver sebagai database. Hasil pengujian menunjukkan bahwa persentase pengenalan dengandata pengujian sebesar 46,36% dan 36.36% dengan data pembelajaran. Gambar pola tanganyang hampir sama menyebabkan ciri yang dominan sulit untuk didapat.
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.