Claim Missing Document
Check
Articles

Found 4 Documents
Search
Journal : Journal of Dinda : Data Science, Information Technology, and Data Analytics

Penerapan Face Recognition Berbasis GUI Visual Studio 2012 Menggunakan Algoritma Eigenface dan Metode Pengembangan Waterfall Pada Sistem Absensi Mahasiswa IT Telkom Purwokerto Ilham Fauzi; Apri Junaidi; Wahyu Andi Saputra
Indonesian Journal of Data Science, IoT, Machine Learning and Informatics Vol 2 No 1 (2022): February
Publisher : Research Group of Data Engineering, Faculty of Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/dinda.v2i1.264

Abstract

Setiap manusia memiliki karakter yang berbeda antara satu dengan yang lainnya, salah satunya adalah karakteristik alami yang dimiliki oleh manusia yaitu wajah. Wajah manusia tentu saja memiliki ciri unik yang membedakan satu dengan lainnya, sehingga dapat dikenali oleh manusia lain maupun oleh suatu sistem yang memiliki kemampuan tersebut. Pengenalan wajah berkaitan erat dengan biometrik manusia, hal tersebut dikarenakan terdapat informasi unik yang terkandung di dalamnya. Teknologi pengenalan wajah dapat dimanfaatkan salah satunya pada sistem presensi kehadiran. Banyak metode yang digunakan pada proses pengenalan wajah, salah satunya dengan menggunakan algoritma eigenface. Eigenface berfungsi untuk menghitung eigenvalue dan eigenvector yang akan digunakan sebagai fitur dalam melakukan pengenalan wajah. Citra akan direpresentasikan dalam sebuah gabungan vektor yang dijadikan satu matriks tunggal. Dari matriks tunggal ini akan di ekstrasi suatu ciri utama yang membedakan antara citra wajah satu dengan citra wajah yang lainnya. Untuk dapat mengenali dan mengidentifikasi wajah seseorang maka pada penelitian ini diperlukan sebuah tools tambahan berupa web camera atau sering kita kenal dengan istilah WebCam dan aplikasi yang akan digunakan adalah Visual Studio 2012. Teknologi pengenalan wajah ini dapat dimanfaatkan oleh IT Telkom Purwokerto sebagai sistem presensi kehadiran mahasiswa. Salah satu hasil evaluasi perlunya pemanfaatan teknologi face recognition sebagai sistem presensi kehadiran mahasiswa dikarenakan belum optimalnya pemanfaatan sistem absensi berbasis RFID yang sebelumnya telah digunakan, berbagai permasalahan teknis yang dihadapi oleh sistem absensi tersebut mengakibatkan proses absensi kembali dilakukan secara manual menggunakan kertas absensi yang diberikan oleh Dosen. Kata kunci: Citra, Eigenface, Face recognition, Image Processing, C#, Sistem Absensi
Klasifikasi Status Gizi Pada Lansia Menggunakan Learning Vector Quantization 3 (LVQ 3) Khurun Ain Muzaqi; Apri Junaidi; Wahyu Andi Saputra
Indonesian Journal of Data Science, IoT, Machine Learning and Informatics Vol 2 No 1 (2022): February
Publisher : Research Group of Data Engineering, Faculty of Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/dinda.v2i1.272

Abstract

The Elderly is someone who has reached the age of 60 years, the main health problem in the elderly is nutritional problems. Nutritional status is a measurement that can assess food intake and the use of nutrients in the body. One of the assessments of nutritional status in the elderly uses anthropometry with the type of measurement of Body Mass Index (BMI). Determination of nutrition is an effort to increase Life Expectancy (UHH). Therefore, a study will be conducted on the classification of nutritional status in the elderly using the Learning Vector Quantization 3 (LVQ 3) method with seven inputs used, namely: gender, age, Bb, Tb, BMI, social status and disease history, and five results of status classification nutritional status, namely inferior nutritional status, poor nutritional status, normal nutritional status, obese nutritional status, and very obese nutritional status. The best parameters used in this study are: learning rate (α) = 0.2, learning rate reduction = 0.4, window (ɛ) = 0.4 and minimum learning rate = 0.001, epoch = 1, 5, 10, 50, 100, 200, 500, 1000 with a comparison of the distribution of training and testing data of 80:20 on a total of 599 data. Based on the test results, the number of epoch values affects the accuracy results. The highest accuracy obtained is 86.67%. The calculations using the confusion matrix in this algorithm are 87% accuracy, 83% precision, and 81% recall. The Learning Vector Quantization 3 (LVQ 3) method can use to classify nutritional status in the elderly.
Klasifikasi Penyakit Daun Padi Menggunakan Convolutional Neural Network Mohtar Khoiruddin; Apri Junaidi; Wahyu Andi Saputra
Indonesian Journal of Data Science, IoT, Machine Learning and Informatics Vol 2 No 1 (2022): February
Publisher : Research Group of Data Engineering, Faculty of Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/dinda.v2i1.341

Abstract

Rice (Oryza sativa) is a grain that comes in third place among all grains after corn and wheat. 80 percent of Indonesians eat rice as a staple diet, especially in Southeast Asian countries, but the International Rice Research Institute (IRRI) reports that farmers lose 37 percent of their rice crops each year owing to pests and illnesses. Based on this study, it is critical to investigate the detection of rice pests and illnesses. Using the Convolution Neural Network (CNN) technique, an automatic classification system to identify and predict plant illnesses has been developed. A study titled Classification of Rice Leaf Diseases was undertaken by the author. The CNN Algorithm is being used to help farmers learn how to combat rice leaf diseases. Bacterial leaf blight, Rice blast, and Rice tungro virus were among the rice leaf types classified in this study. There are 6000 datasets in all, with 80% of them being training data, 10% being validation data, and 10% being testing data. The accuracy of the results obtained for epochs 25, 50, 75, and 100 varies. The best training accuracy results come from epoch 100, which has a 98% accuracy rate, and testing using a confusion matrix has a 98% accuracy rate. In diagnosing rice leaf diseases, the Convolutional Neural Network (CNN) algorithm delivers great accuracy.
Klasifikasi Penyakit Kanker Kulit Menggunakan Metode Convolutional Neural Network (Studi Kasus: Melanoma) Reynaldi Rio Saputro; Apri Junaidi; Wahyu Andi Saputra
Indonesian Journal of Data Science, IoT, Machine Learning and Informatics Vol 2 No 1 (2022): February
Publisher : Research Group of Data Engineering, Faculty of Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/dinda.v2i1.349

Abstract

Skin cancer is one of the most commonly diagnosed cancers worldwide, especially in the white population. One of the most dangerous skin diseases is melanoma cancer. Melanoma is a skin cancer that can develop in melanocytes, the skin pigment cells that produce melanin. Melanin is what absorbs ultraviolet rays and protects the skin from damage. Melanoma is a type of skin cancer that is rare and very dangerous, many laypeople have not been able to distinguish between ordinary moles and melanoma. Therefore, a study on the classification of melanoma skin cancer was carried out using the CNN method, where CNN was able to classify melanoma images. In CNN itself there is an architectural model, while the architecture used in this research is using conv2d layer, max pooling, flatten, dense, dropout, and using ReLu activation. The image size used in this architecture is 128x128, at the 50th epoch, an accuracy rate of 92.64% is obtained. It is hoped that this research can help the community in distinguishing normal moles and melanoma cancer.