Claim Missing Document
Check
Articles

Found 26 Documents
Search

Modification CNN Transfer Learning for Classification MRI Brain Tumor Wardhani, Retno; Nafi'iyah, Nur
Telematika Vol 16, No 2: August (2023)
Publisher : Universitas Amikom Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35671/telematika.v16i2.2272

Abstract

Identification, or detecting the infected part of a brain tumor on an MRI image, requires precision and takes a long time. MRI (Magnetic Resonance Imaging) is a magnetic resonance imaging technique to examine and take pictures of organs, tissues, and skeletal systems. The brain is essential because it is the center of the nervous system, which controls all human activities. Therefore, MRI of the brain has an important role, one of which is used for analysis or consideration before performing surgery. However, MRI images cannot provide optimal results when analyzed due to noise, and the bone and tumor (lumps of flesh) have the same appearance. AI (artificial intelligence), or digital image processing and computer vision, can analyze MRI images to detect or identify tumors correctly. This study proposes changes to the last layer of CNN (Convolution Neural Network) transfer learning (VGG16, InceptionV3, and ResNet-50) to identify brain tumor disease on MRI. Data were taken from Kaggle with types of glioma, meningioma, no tumor, and pituitary, with a total of 5712 training images and 1311 testing images. The proposed changes include a flattening layer and a pooling layer. The result is that replacing the flatten layer further improves accuracy, and the accuracy of the transfer learning CNNs (VGG16, InceptionV3, and ResNet-50) is 0.918, 0.762, and 0.934, respectively.
Perbandingan Otsu Dan Iterative Adaptive Thresholding Dalam Binerisasi Gigi Kaninus Foto Panoramik Nur Nafi'iyah; Retno Wardhani
Jurnal Ilmiah Teknologi Informasi Asia Vol 11 No 1 (2017): Volume 11 Nomor 1 (10)
Publisher : LP2M INSTITUT TEKNOLOGI DAN BISNIS ASIA MALANG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32815/jitika.v11i1.39

Abstract

Proses binerisasi bertujuan untuk memudahkan pengenalan citra dalam tahap computer vision. Binerisasi merupakan cara mengubah bentuk warna citra ke hitam putih atau biner. Metode otsu merupakan metode konversi citra ke bentuk hitam putih. Metode iterative dan adaptive thresholding merupakan gabungan metode dalam mengubah citra ke biner. Tujuan dari penelitian ini, yaitu: memudahkan dalam tahap ekstraksi citra atau pengambilan informasi terpenting dalam citra. Sehingga proses selanjutnya seperti pengenalan citra atau recognition. Hasil dari penelitian ini berupa citra biner gigi kaninus foto panoramik. Dari perbandingan metode, metode iterative dan adaptive thresholding menghasilkan gambar biner yang lebih baik.
Comparison of Machine Learning for Mental Health Identification (The DASS-21 Questionnaire) Wardhani, Retno; Nafi'iyah, Nur
Jurnal Teknologi Informasi dan Pendidikan Vol. 18 No. 1 (2025): Jurnal Teknologi Informasi dan Pendidikan
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/jtip.v18i1.860

Abstract

Stress appears at almost any age. Stress can disrupt mental and physical balance, and even students can experience it. Early detection of an individual's emotions is crucial. Researchers hope that by taking such actions, an individual can maintain self-control and prevent the stress they are experiencing from worsening. Bodily characteristics such as speech, body language, eye contact, and facial expressions indicate stress, depression, and anxiety. Psychological activities and human life are associated with physiological emotions. The three categories of negative thoughts or sad emotions are stress, anxiety, and depression. This research assesses or finds students who experience anxiety, depression, and stress. This study compares methods for determining mental health through the distribution of DASS-21 scale questionnaires. The researcher classified the research results using Naive Bayes, Decision Tree, k-NN, SVM, and Logistic Regression methods. According to experiments, SVM is effective for identifying mental health anxiety, depression, and stress with accuracy, recall, and precision of 0.86, 0.90, and 0.80. At Universitas Islam Lamongan, 138 engineering faculty students answered the DASS-21 questionnaire.
Prediksi Curah Hujan di Kabupaten Tuban Menggunakan Metode Fuzzy Time Series Sri Wahyuningsih; Wardhani, Retno
Joutica Vol 10 No 1 (2025): MARET
Publisher : Universitas Islam Lamongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30736/informatika.v10i1.1383

Abstract

Curah hujan adalah faktor penting dalam sektor pertanian dan pengelolaan sumber daya alam, terutama di Kabupaten Tuban. Memperkirakan curah hujan dengan akurat sangat penting untuk perencanaan dan pengambilan keputusan yang efektif. Penelitian ini bertujuan untuk mengembangkan model prediksi curah hujan di Kabupaten Tuban menggunakan metode Fuzzy Time Series. Penelitian ini mencakup beberapa tahapan, yaitu studi literatur, analisis kebutuhan sistem, desain, implementasi, serta pengujian dan evaluasi. Data curah hujan yang digunakan dalam penelitian ini berasal dari Stasiun Kabupaten Tuban dengan 11 jumlah data pada tahun 2023. Metode Fuzzy Time Series dipilih karena kemampuannya dalam menangani ketidakpastian dan kompleksitas Data Time Series. Hasil penelitian menunjukkan bahwa metode Fuzzy Time Series efektif dalam memprediksi curah hujan, dengan tingkat kesalahan yang rendah dan hasil prediksi yang dapat diandalkan. Hasil dari perhitungan menggunakan metode Fuzzy Time Series dalam prediksi curah hujan di Kabupaten Tuban menghasilkan nilai Mean Absolute Percentage Eror di setiap masing masing variabel curah hujan MAPE 55%, kelembapan rata rata MAPE 98%, kecepatan angin rata rata MAPE 71%, temperatur rata rata MAPE 98%. Penelitian ini memberikan kontribusi signifikan dalam perkembangan ilmu pengetahuan terkait prediksi cuaca menggunakan metode Fuzzy Time Series, serta memberikan manfaat praktis dalam meningkatkan ketangguhan dan ketahanan Kabupaten Tuban dalam menghadapi perubahan kondisi cuaca yang dinamis.
Recognizing the Types of Beans Using Artificial Intelligence Nafi'iyah, Nur; Setyati, Endang; Kristian, Yosi; Wardhani, Retno
Register: Jurnal Ilmiah Teknologi Sistem Informasi Vol 9 No 2 (2023): July
Publisher : Information Systems - Universitas Pesantren Tinggi Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26594/register.v9i2.3054

Abstract

Many studies have previously addressed the recognition of plant leaf types. The process of identifying these leaf types involves a crucial feature extraction stage. Image feature extraction is pivotal for distinguishing the types of objects, thus demanding optimal feature analysis for accurate leaf type determination. Prior research, which employed the CNN method, faced challenges in effectively distinguishing between long bean and green bean leaves when identifying bean leaves. Therefore, there is a need to conduct optimal feature analysis to correctly classify bean leaves. In our research, we analyzed 69 features and explored their correlations within various image types, including RGB, L*a*b, HSV, grayscale, and binary images. The primary objective of this study is to pinpoint the features most strongly correlated with the recognition of bean leaf types, specifically green bean, soybeans, long beans, and peanuts. Our dataset, sourced from farmers' fields and verified by experienced senior farmers, consists of 456 images. The most highly correlated feature within the bean leaf image category is STD b in the L*a*b image. Furthermore, the most effective method for leaf type recognition is Neural Network Backpropagation, achieving an accuracy rate of 82.28% when applied to HSV images.
IDENTIFICATION OF MENTAL HEALTH WORKERS IN LAMONGAN WITH MACHINE LEARNING Retno Wardhani; Nur Nafi'iyah
Jurnal Teknologi Informasi Universitas Lambung Mangkurat (JTIULM) Vol. 8 No. 2 (2023)
Publisher : Fakultas Teknik Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/jtiulm.v8i2.160

Abstract

COVID-19 has caused a global health crisis, with increasing numbers of people being infected and dying every day. Various countries have tried to control its spread by applying the basic principles of social aggregation and testing. Experts agree that physical and mental health are interrelated and must be managed and balanced. The government must pay attention to balancing physical and mental health during a pandemic. The Ministry of Health has issued a guidebook for Mental Health and Psychosocial Support (DKJPS) during the COVID-19 pandemic. Based on the mental health conditions of the community or medical personnel, we are trying to create a system for mental health analysis for medical professionals based on the results of questionnaires using the machine learning method (Naive Bayes, Decision Tree, k-NN, SVM, Backpropagation, and Logistic Regression). A total of 24 question questionnaires were submitted to respondents. This study aimed to create a machine learning model (Naive Bayes, Decision Tree, k-NN, SVM, Backpropagation, and Logistic Regression) to identify the mental health of medical personnel during the COVID-19 pandemic. The results of this study are machine learning models that have the highest accuracy in identifying health workers' mental health and are 100% SVM.