Article Per Year (5 Year)
p-Index From 2020 - 2025
1.259
P-Index
This Author published in this journals
All Journal Jurnal Informatika Universitas Pamulang IJID (International Journal on Informatics for Development) Simtek : Jurnal Sistem Informasi dan Teknik Komputer Jurnal Engine: Energi, Manufaktur, dan Material Media Informatika Internet of Things and Artificial Intelligence Journal Applied Science and Technology Research Journal
sapriani gustina, sapriani
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering Materials Science & Nanotechnology Mechanical Engineering

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 7 Documents
Search

 1 
Aplikasi Machine Learning untuk Mendeteksi Kematangan Tomat menggunakan Metode Backpropagation Gustina, Sapriani
Jurnal Engine: Energi, Manufaktur, dan Material Vol. 8 No. 1 (2024)
Publisher : Proklamasi 45 University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30588/jeemm.v8i1.1815

Abstract

The rapid development of artificial intelligence has now been widely used in various industrial fields, with various benefits that make it easier, speed up work processes, automate and be efficient in resources to improve cyber security and can be implemented easily and of course will continue to be developed further, such as In the agricultural industry, artificial intelligence can be used to identify certain types of fruit or plant leaves and their level of maturity. This research will create a machine learning application to identify the level of ripeness of tomatoes with 3 types of tomatoes, old tomatoes, young tomatoes and rotten tomatoes. From each type of tomato there are 50 object images in the form of images in .jpg format, of which 15 object images are used as training data and 35 images as test data to detect tomato images using the Backpropagation method which will utilize image feature extraction in the form of RGB colors. The results obtained from testing images of young, old and rotten tomatoes obtained an accuracy rate of 83%.
Design of a Web-Based E-Commerce Sales System for the Economic Empowerment of Tambak Fish Farmers Siburian, Dian Prima Trendi; Hartiyani, Selvi Dwi; Wicaksono, Ardy; Gustina, Sapriani
IJID (International Journal on Informatics for Development) Vol. 13 No. 1 (2024): IJID June
Publisher : Faculty of Science and Technology, UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/ijid.2024.4440

Abstract

This research addresses the economic challenges of fish farmers in Argomulyo Village, Cangkringan District, by developing a web-based e-commerce sales system. The primary issue identified is the limited market access experienced by these farmers. To address this, the study employs a qualitative research methodology using the Waterfall software development model and gathers data through observation, interviews, literature reviews, and questionnaires. The e-commerce platform aims to enhance economic opportunities for local fish farmers by providing a digital marketplace to overcome limited market access. Quantitative data was collected from 15 respondents using a questionnaire with 10 statements to evaluate the system. The analysis results show that the validity test (R Calculated > R Table) confirms all statements are valid, and reliability is tested with a Cronbach's Alpha of 0.958, exceeding the reference value of 0.6, indicating high reliability. The e-commerce system has proven effective in broadening market reach, boosting sales, and increasing farmers' income. The study results highlight the e-commerce system's positive impact on fish farmers' economic empowerment, demonstrating its potential to foster sustainable growth and market expansion in the digital era. This research provides valuable insights into the use of technology to enhance and advance the lives of farmers in rural communities.
IDENTIFIKASI PENGENALAN CITRA WAJAH MENGGUNAKAN METODE PRINCIPAL COMPONENT ANALYSIS (PCA) Gustina, Sapriani; Gunadi, Aan; Sudarmana, Landung
Simtek : jurnal sistem informasi dan teknik komputer Vol. 10 No. 1 (2025): April 2025
Publisher : STMIK Catur Sakti Kendari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51876/simtek.v10i1.1492

Abstract

Penelitian ini bertujuan untuk mengembangkan sistem identifikasi citra wajah berbasis metode Principal Component Analysis (PCA) untuk meningkatkan akurasi dan efisiensi proses pengenalan wajah. Metode PCA dipilih karena kemampuannya dalam mereduksi dimensi data citra tanpa menghilangkan informasi penting, sehingga mempermudah ekstraksi fitur utama wajah. Penelitian ini dilakukan dengan menggunakan dataset sebanyak 150 gambar wajah dari 10 individu, masing-masing memiliki 15 pose dengan variasi sudut dan pencahayaan. Tahapan penelitian meliputi pengumpulan data citra wajah, pre-processing berupa cropping, resize, dan segmentasi citra, serta implementasi algoritma PCA. Hasil penelitian menunjukkan bahwa sistem mampu mencapai tingkat akurasi sebesar 100% pada data latih dan 96% pada data uji, dalam mengidentifikasi wajah pada berbagai kondisi, seperti variasi sudut dan pencahayaan. Sistem ini diharapkan dapat memberikan kontribusi signifikan dalam pengembangan teknologi pengenalan wajah berbasis biometrik.
Penerapan Sistem Keamanan Berbasis Internet of Things (IoT) dengan Sensor Alarm Buzzer Adetia, Silvia; Wicaksono, Ardy; Gustina, Sapriani; Hartiyani, Selvi Dwi
Media Informatika Vol 24 No 1 (2025)
Publisher : P3M STMIK LIKMI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37595/mediainfo.v24i1.323

Abstract

Keamanan ruangan menjadi perhatian utama dalam menjaga aset dan lingkungan dari potensi ancaman pencurian atau intrusi. Penelitian ini bertujuan untuk menerapkan sistem keamanan berbasis Internet of Things (IoT) dengan menggunakan sensor alarm buzzer dan notifikasi WhatsApp sebagai sistem peringatan real-time. Sistem ini dirancang untuk memberikan solusi keamanan yang lebih responsif dan efisien dalam berbagai kondisi.  Metode yang digunakan dalam penelitian ini adalah Approach Research, yang berfokus pada penerapan teknologi dalam lingkungan nyata serta evaluasi kinerja sistem. Sistem ini dikembangkan menggunakan Wemos D1 Mini sebagai mikrokontroler utama, yang terhubung dengan sensor Passive Infrared (PIR), buzzer alarm, serta layanan Twilio API untuk mengirimkan notifikasi WhatsApp secara otomatis saat terjadi deteksi pergerakan mencurigakan. Pengujian dilakukan dalam berbagai skenario untuk menilai akurasi sensor, kecepatan notifikasi, serta keandalan sistem dalam mendeteksi ancaman keamanan.  Hasil penelitian menunjukkan bahwa sistem yang dikembangkan mampu mendeteksi gerakan mencurigakan dengan akurasi tinggi dan waktu respons rata-rata 4 detik. Implementasi sistem berbasis IoT ini memungkinkan pengguna untuk menerima peringatan secara instan, sehingga dapat mengambil tindakan cepat dalam menghadapi potensi ancaman. Selain itu, sistem ini juga mudah diterapkan di berbagai lingkungan, seperti rumah, kantor, atau kamar kost, dengan fleksibilitas tinggi dalam konfigurasi dan penggunaan daya yang efisien. Kesimpulan dari penelitian ini adalah bahwa penerapan sistem keamanan berbasis IoT mampu meningkatkan efektivitas pengawasan ruangan secara otomatis, real-time, dan jarak jauh. Untuk pengembangan lebih lanjut, disarankan agar sistem ini dilengkapi dengan fitur tambahan seperti kamera pengawas dan kecerdasan buatan (AI) guna meningkatkan akurasi deteksi dan analisis ancaman secara lebih presisi.
A Student Grouping Based on Final Exam Values of the Courses with the K-Means Classification Method Using KNIME Gustina, Sapriani
Internet of Things and Artificial Intelligence Journal Vol. 1 No. 2 (2021): Volume 1, Issue 2, 2021 [May]
Publisher : Association for Scientific Computing, Electronics, and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (845.79 KB) | DOI: 10.31763/iota.v1i2.378

Abstract

In learning, each student must have a different way of learning and learning patterns which will have an impact on the results of their learning evaluation at the end of each semester. Assessing a student who excels in learning is one of them by looking at the score of the final exam results that maybe the student can easily get good grades because they do have expertise in that field or get good grades because they are diligent in studying. The scores of students' final semester exams in several courses will be summarized here in order to be used as a basis for classifying students into several groups, namely smart, average, and less good students.
Design System Monitoring Quality Air Internet Of Things Based Indoor Damayanti, Devi Fania; Wicaksono, Ardy; Hartiyani, Selvi Dwi; Gustina, Sapriani
APPLIED SCIENCE AND TECHNOLOGY REASERCH JOURNAL Vol. 4 No. 1 (2025): Applied Science and Technology Research Journal
Publisher : Lembaga Penelitian dan Pengabdian Mayarakat (LPPM) Universitas PGRI Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31316/astro.v4i1.7624

Abstract

Air is one of the elements that support life on Earth. Without air, humans and animals cannot breathe, and plants cannot photosynthesize. Quality air is often influenced by pollutants. Because that is, air pollution can be interpreted as the presence of foreign objects or substances in the air that change the composition of the air from normal to bad. In the research, the method used is the development method with the Research approach. And Development (R&D), method development Which used In this study, the Analysis, Design, Development, Implementation, Evaluation (ADDIE) model was used. This study was conducted to obtain accuracy from the overall system testing. Testing on quality monitoring air use sensor MQ 135 (For air), sensor DHT 11 (for temperature and humidity sensors), OLED LCD ( hardware interface ), and ESP 8266 microcontroller have been completed. This system can be used by all parties as an air quality control system, for indoor temperature and humidity using Thingspeak.
Application of the K-Nearest Neighbor (KNN) Algorithm for Stunting Diagnosis in Infants Aged 1-12 Months kholik, Moh abdul; Pratomo, Cucut Hariz; Gustina, Sapriani
Jurnal Informatika Universitas Pamulang Vol 9 No 2 (2024): JURNAL INFORMATIKA UNIVERSITAS PAMULANG
Publisher : Teknik Informatika Universitas Pamulang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32493/informatika.v9i2.40983

Abstract

Stunting in toddlers must be addressed immediately because it has a negative impact on their growth and development. Stunting is a disorder where toddlers experience chronic malnutrition, thus their physical growth and height do not match their age. According to the Indonesian Nutritional Status Survey (SSGI), stunting is more common among toddlers from aged 0 to 1 year than overall. Stunting can have short-term and long-term impacts. This research examines data from the Temanggung District Health Service on 3,999 toddlers aged 0 to 12 months between 2019 and 2022.  Many studies have exclusively looked at stunting in children aged one to five years, especially research on stunting using the KNN method, even though stunting can actually be recognized from an early age. Therefore, researchers are more specific in using the KNN method for cases of babies 1 to 12 months so as to differentiate it from previous researchers. The aim of this research is to use the K-Nearest Neighbor (KNN) algorithm to detect stunting nutritional status in toddlers. K-Nearest Neighbor (KNN) is a classification algorithm that uses a set of K values ​​from the closest data (its neighbors) as a reference to determine the class of incoming data. KNN classifies data based on its similarity or closeness to other data. The dataset used includes parameters of age, gender and height. The research approach is the CRISP-DM (Cross Industry Standard Process for Data Mining) method, which begins with business knowledge, followed by EDA and modeling, evaluation, testing and report preparation. The result shows that the KNN algorithm can accurately categorize children as stunted or not based on age (U) and height (TB), with the maximum level of accuracy and the lowest error rate at k = 5. At this optimal value (k), this algorithm has an accuracy of 99.87%, Recall 99.84%, and precision 99.73.
Co-Authors Adetia, Silvia Damayanti, Devi Fania Gunadi, Aan Hartiyani, Selvi Dwi kholik, Moh abdul Landung Sudarmana, Landung Pratomo, Cucut Hariz Siburian, Dian Prima Trendi Wicaksono, Ardy