Claim Missing Document
Check
Articles

Found 10 Documents
Search

Training of Trainers (TOT) Data Science for Teaching Doctors Rinabi Tanamal; Felicia Graciella; Michelle Chandra; Trianggoro Wiradinata; Yosua Soekamto; Theresia Ratih Dewi Saputri
ABDIMAS: Jurnal Pengabdian Masyarakat Vol. 5 No. 2 (2022): ABDIMAS UMTAS: Jurnal Pengabdian Kepada Masyarakat
Publisher : LPPM Universitas Muhammadiyah Tasikmalaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (726.932 KB) | DOI: 10.35568/abdimas.v5i2.2488

Abstract

Due to the rapid development of technology, technology has become very attached to various fields in Indonesia. The health sector is no exception. If more and more data in the health sector is used properly, it will provide good benefits for the world of health and patients. Therefore, a Data Science Training of Trainers Activity was held for Doctors by the Profession of Doctors at Universitas Ciputra Surabaya. Activities are carried out by providing materials and working on questions by the doctors involved. Thus, it is hoped that the doctors participating in this activity can provide medical literacy knowledge to prospective doctor students at Universitas Ciputra. From the results of this TOT evaluation, it has a positive impact on doctors regarding alternative ways to process the data needed for medical research.
What do Indonesians talk when they talk about COVID-19 Vaccine: A Topic Modeling Approach with LDA Theresia Ratih Dewi Saputri; Caecilia Citra Lestari; Salmon Charles Siahaan
JUITA : Jurnal Informatika JUITA Vol. 10 No. 2, November 2022
Publisher : Department of Informatics Engineering, Universitas Muhammadiyah Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (955.666 KB) | DOI: 10.30595/juita.v10i2.13500

Abstract

To end the COVID-19 pandemics, the government attempted to accelerate the vaccination through various programs and collaboration. Unfortunately, the number is still relatively small compared to the number of populations in Indonesia. There are some reasons attributed to this challenge, one of them being the reluctance of citizens to accept the COVID-19 vaccine due to various factors. Knowing this factor to increase public compliance, the vaccination program can be speed-up. Unfortunately, traditionally acquiring the knowledge related to COVID-19 vaccine rejection can be challenging.  One of the ways to capture the knowledge is by conducting a survey or interview related to COVID-19 vaccine acceptance. This method can be inefficient in terms of cost and resources. To address those problem, we propose a novel method for analyzing the topics related to the COVID-19 Indonesians’ opinions on Twitter by implementing topic modeling algorithm called Latent Dirichlet Allocation. We gathered more than 22000 tweets related to the COVID-19 vaccine. By applying the algorithm to the collected dataset, we can capture the what is general opinion and topic when people discuss about COVID-19 vaccine. The result was validated using the labeled dataset that have been gathered in the previous research. Once we have the important term, the strategy based on can be determined by the medical professional who are responsible to administer the COVID-19 vaccine. 
MINI SERI COMPUTATIONAL THINGKING UNTUK GURU SEKOLAH YAYASAN CIPUTRA PENDIDIKAN Yuwono Marta Dinata; Laura Mahendratta Tjahjono; Mychael Maoeretz Engel; Theresia Ratih Dewi Saputri; Evan Tanuwijaya
Jurnal Pendidikan dan Pengabdian Masyarakat Vol. 4 No. 2 (2021): Mei
Publisher : FKIP Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (215.357 KB) | DOI: 10.29303/jppm.v4i2.2659

Abstract

Kegiatan pengabdian kepada masyarakat (abdimas) ini bertujuan memperluas wawasan mengenai computational thinking (CT) bagi guru Sekolah. Program mini seri ini dilakukan secara berkala dan berkesinambungan. Program ini diprioritaskan kepada Guru di berbagai sekolah. Pada kesempatan kali ini diperuntukkan kepada Guru-guru di Yayasan Ciputra Pendidikan. CT sendiri merupakan salah satu problem solving yang perlu diajarkan sejak dini. Dengan melihat perkembangan teknologi dalam bidang ilmu komputer yang berkembang pesat maka pendekatan CT ini sangat diperlukan. Universitas Ciputra Surabaya khususnya Fakultas Teknologi Informasi bekerjasama dengan Komunitas Bebras untuk memperluas penggunaan CT bagi siswa/i seluruh Indonesia. Mini seri ini dilakukan dengan memberikan wawasan CT kepada guru sekolah, sehingga guru tersebut dapat menyampaikan dan melatih para siswanya untuk dapat terbiasa menggunakan CT ini dalam kehidupan mereka sehari-hari. Dalam melakukan pengabdian masyarakat ini dilakukan dengan terlebih dahulu berkoordinasi dan berdiskusi dengan koordinator pusat Yayasan, membuat materi computational thinking berupa materi power point maupun website yang siap diakses peserta. Pokok pembahasan dibagi menjadi empat sesi yaitu pendahuluan tentang computational thinking, computational thinking in everyday life, Developing Computational Thinking task dan menerapkan CT dalam pembelajaran di kelas. Kegiatan ini menyasar pada 134 guru Yayasan Sekolah Ciputra dengan durasi pelaksanaan kurang lebih tiga bulan dari persiapan, penyiapan materi, koordinasi, penyuluhan, serta penyusunan laporan dan luaran.
Comparative Study on Regression Algorithms for Predicting Price of Online Course: Udemy Case Study Maximus Aurelius Wiranata; Theresia Ratih Dewi Saputri
Jurnal Informatika Universitas Pamulang Vol 8, No 2 (2023): JURNAL INFORMATIKA UNIVERSITAS PAMULANG
Publisher : Teknik Informatika Universitas Pamulang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32493/informatika.v8i2.30562

Abstract

Talent in the field of information technology is much needed. However, studying in the field of information technology requires a sizable fee. Online courses are a cost-effective option for learning. Online course sites like Udemy provide and sell hundreds of thousands of courses and have thousands of trusted instructors. With so many Udemy instructors, prices vary widely because the course pricing system is completely set by the teaching instructor. This means that the selling price of the course is not affected by the quality of the course, so not all courses are recommended to be purchased. To overcome this problem, a system is needed that can predict course prices so that it can advise instructors in determining selling prices. To compare the best algorithms used to create this system, three algorithms are used in this study: multiple linear regression, polynomial regression, and K-Nearest Neighbors Regression. The researcher uses 1200 data sample from web scraping results from the Udemy site, with one test for each algorithm. As a result, the K-Nearest Neighbors Regression got the best evaluation results with a root mean squared error value of 231659.49, a mean absolute percentage error of 0.43, and a coefficient of determination of 0.18.
Rancang Bangun Aplikasi Diet untuk Ibu Menyusui Pasca Persalinan dengan Algoritma Mifflin-St Jeor Tinara Nathania Wiryonoputro; Theresia Ratih Dewi Saputri
Jurnal Informatika: Jurnal Pengembangan IT Vol 8, No 3 (2023)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v8i3.5733

Abstract

Pregnancy is a significant and transformative period for women, both physically and emotionally. During this time, it is crucial for expectant mothers to prioritize their own health and well-being to create a healthy environment for their growing baby. One of the physical changes that many breastfeeding mothers experience after childbirth is weight gain. Factors contributing to this include increased caloric needs, lack of sleep, reduced physical activity, and feelings of stress and fatigue due to caring for a newborn. Maintaining a healthy weight is vital to reduce the risk of various health issues and ensure the quality of breast milk for the baby. However, it is important to note that mothers should not engage in strict dieting during the postpartum period, or the puerperium, which lasts up to 40 days after delivery. During this time, mothers should gradually resume normal activities and movement. To support breastfeeding mothers in maintaining their health after childbirth, a structured and monitored approach that provides tailored information according to each stage of development is necessary. The Laav application, available for iOS, is designed to calculate and record the caloric intake of breastfeeding mothers, helping them achieve proper nutrition while maintaining an ideal weight. The application is built using the User-Centered Design (UCD) methodology and uses the Mifflin-St Jeor algorithm to calculate calories. The application is programmed in SwiftUI, a language optimized for the iOS platform
Penerapan Metode Image-to-Speech melalui Kamera dalam Aplikasi berbasis Kecerdasan Buatan untuk Orang dengan Disleksia Daniel Aprillio; Anna Bella Atmadjaja; Bryan; Mychael Wijaya; Theresia Ratih Dewi Saputri
Jurnal Informatika Universitas Pamulang Vol 9 No 1 (2024): JURNAL INFORMATIKA UNIVERSITAS PAMULANG
Publisher : Teknik Informatika Universitas Pamulang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32493/informatika.v9i1.39173

Abstract

Dyslexia occurs worldwide despite the culture or language. Dyslexia affects about 9% - 12% of the population, with 2% - 4% of the population experiencing significant reading impairments. This research aims to develop an artificial intelligence-based application using the Image-to-Speech method that can convert digital text into audible sound for individuals with dyslexia without requiring their brain to process the writing. This method can assist people with dyslexia in daily life challenges such as reading traffic signs, books, or documents. Results from 10 experiments on the implementation of the proposed method indicate that individuals with dyslexia can scan the text they want to read using a camera from a smartphone or laptop. The expirements also shows that the application can convert text in image form into sound comprehensible to those with dyslexia, thus facilitating their recognition of digital writing with 90% accuracy. The application also demonstrates efficiency in terms of data processing time. The average time required for image to audio conversion is 0.22 seconds, with an average memory usage of 163.2 MiB.
RANCANG BANGUN APLIKASI POLA MAKAN DASH BAGI PENDERITA HIPERTENSI Bryan; Saputri, Theresia Ratih Dewi
IT Explore: Jurnal Penerapan Teknologi Informasi dan Komunikasi Vol 3 No 2 (2024): IT-Explore Juni 2024
Publisher : Fakultas Teknologi Informasi, Universitas Kristen Satya Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24246/itexplore.v3i2.2024.pp177-193

Abstract

Hipertensi merupakan salah satu penyakit tidak menular yang umum terjadi di dunia. Salah satu penyebab umum hipertensi adalah pola makan yang tidak sehat. Dalam menanggapi hal tersebut, Dietary Approach to Stop Hypertension (DASH) disarankan sebagai pola makan yang efektif untuk mengurangi tekanan darah. Meskipun telah terbukti efektif, penderita hipertensi masih belum dapat menerapkan pola makan tersebut secara konsisten. Salah satu faktor penghambat penerapan pola makan DASH adalah ketidaktahuan penderita hipertensi dalam memodifikasi pola makan sesuai anjuran yang ada. Berdasarkan permasalahan tersebut, penelitian ini bertujuan untuk merancang pembuatan aplikasi pola makan DASH bagi penderita hipertensi berbasis mobile yang dapat memberikan rencana makan sesuai pola makan DASH. Rencana makan dalam jangka waktu tujuh hari yang dibuat setiap harinya meliputi sarapan, makan siang, dan makan malam. Menu makanan akan dirancang dan disesuaikan dengan jumlah kebutuhan kalori harian. Penderita juga dapat memantau asupan natrium sesuai dengan makanan yang telah dikonsumsi. Sebelum mengembangkan aplikasi, usability testing dilakukan menggunakan metode heuristic evaluation untuk mengevaluasi desain pada prototype. Pengembangan aplikasi dilakukan menggunakan metode waterfall model dengan arsitektur BLoC. Aplikasi mobile dikembangkan menggunakan bahasa pemrograman Dart, framework Flutter, Bloc, Firebase, dan Edamam untuk sistem operasi Android. Pengujian black box kemudian dilakukan dengan metode functional testing. Setiap fitur yang diujikan berhasil berjalan sesuai yang diharapkan dan dinyatakan lolos pengujian. Hasil penelitian menunjukkan bahwa aplikasi Milda dapat digunakan oleh penderita hipertensi untuk menjalankan pola makan sehat dengan memberikan rencana makan sesuai dengan pola makan DASH. Rencana makan yang diberikan mendorong penderita hipertensi untuk memulai atau mencoba kembali pola makan DASH. Selain itu, variasi menu makanan yang menarik juga mendorong penderita hipertensi untuk lebih konsisten dalam menjalankan pola makan DASH.
Online Measuring Feature for Batik Size Prediction using Mobile Device: A Potential Application for a Novelty Technology Wiradinata, Trianggoro; Saputri, Theresia Ratih Dewi; Sutanto, Richard Evan; Soekamto, Yosua Setyawan
Journal of Applied Data Sciences Vol 4, No 3: SEPTEMBER 2023
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v4i3.121

Abstract

The garment industry, particularly the batik sector, has experienced significant growth in Indonesia, coinciding with a rise in the number of online consumers who purchase batik products through e-Marketplaces. The observed upward trend in growth has seemingly presented certain obstacles, particularly in relation to product alignment and product information dissemination. Typically, batik entrepreneurs originate from micro, small, and medium enterprises (MSMEs) that have not adhered to global norms. Consequently, the sizes of batik products offered for sale sometimes exhibit inconsistencies. The issue of size discrepancies poses challenges for online consumers seeking to purchase batik products through e-commerce platforms. An effective approach to address this issue involves employing a smartphone camera to anticipate body proportions, specifically the length and width of those engaged in online shopping. Subsequently, by the utilization of machine learning techniques, the optimal batik size can be determined. The UKURIN feature was created as a response to a specific requirement. However, it is essential to establish a methodology for investigating the elements that impact the intention to use this feature. This will enable developers to prioritize their feature development strategies more effectively. A total of 179 participants completed an online questionnaire, and subsequent analysis was conducted utilizing the Extended Technology Acceptance Model framework. The findings indicate that Perceived Usefulness emerged as the most influential factor. Consequently, when designing and developing the novelty feature of UKURIN, it is imperative for designers and application developers to prioritize the benefits aspect.
COMPARATIVE STUDY OF CNN-BASED ARCHITECTURES ON EYE DISEASES CLASSIFICATION USING FUNDUS IMAGES TO AID OPHTHALMOLOGIST Yaurentius, Evelyn Callista; Saputri, Theresia Ratih Dewi; Tanuwijaya, Evan; Sutanto, Richard Evan
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 1 (2025): JUTIF Volume 6, Number 1, February 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.1.3699

Abstract

Eye health has a significant impact on quality of life, with more than 2.2 billion people experiencing vision problems. Many of these cases can be prevented or treated. The use of AI for eye disease classification helps healthcare professionals provide optimal care. However, the complexity of fundus images challenges classification performance. This study examines various Convolutional Neural Network (CNN) architectures using Transfer Learning and Adam optimization. Fundus images are processed using CLAHE (clip limit and grid size) and the Wiener filter (size) to enhance contrast and reduce noise. Afterward, ResNet-152, EfficientNet, MobileNetV1, and DenseNet-121 are tested to identify the most effective model. The study aims to determine the optimal CNN architecture for eye disease classification, assisting ophthalmologists in diagnosing eye diseases through fundus images. The best CNN model, ResNet-152, achieved an accuracy of 94.82%, outperforming other models by 3.95 - 8.29%.
Nature-based Hyperparameter Tuning of a Multilayer Perceptron Algorithm in Task Classification: A Case Study on Fear of Failure in Entrepreneurship Saputri, Theresia Ratih Dewi; Kurniawan, Edwin; Lestari, Caecilia Citra; Antonio, Tony
Journal of Applied Data Sciences Vol 6, No 2: MAY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i2.539

Abstract

Entrepreneurship plays a key role in generating economic growth, encouraging innovation, and creating job opportunities. Understanding which demographic, psychological, and socio-economic factors contribute to fear of failure in entrepreneurship is essential to developing proper standards in entrepreneurship education and policy. However, it remains challenging to accurately classify these factors, especially when balancing model performance with model complexity in a multilayer perceptron algorithm. An effective model requires the correct parameter setting via a hyperparameter tuning process. Adjusting each hyperparameter by hand requires significant effort and knowledge, as there are frequently multiple combinations to consider. Furthermore, manual tuning is prone to human error and may overlook optimal configurations, resulting in inferior model performance and prediction accuracy. This study evaluates nature-inspired optimization techniques, including particle swarm optimization (PSO), genetic algorithm (GA), and grey wolf optimization (GWO). Several parameters are tuned in the present multilayer perceptron model, including the number of hidden layers and the number of nodes in each hidden layer, learning rate, and activation functions. The used dataset which consists of 39 features from 333 samples captured individual fears, loss score, and computational efficiency as the required amount of time for finding the best parameter combination. Model accuracy performance scores are 45.16%, 53.76%, and 58.61% for GA, PSO, and GWO, respectively. Meanwhile their execution time are 10 minutes, 27 minutes, and 23 minutes, for GA, PSO, and GWO, respectively. Experiment results further reveal that each optimization algorithm has distinct advantages: GA excels at speedy convergence, PSO provides a robust exploration of hyperparameter space, and GWO offers remarkable adaptability to complicated parameter interdependencies. This study provides empirical evidence for the efficacy of nature-inspired hyperparameter modification in improving multilayer perceptron performance for fear of failure categorization tasks.