Article Per Year (5 Year)
p-Index From 2021 - 2026
1.829
P-Index
This Author published in this journals
All Journal InfoTekJar : Jurnal Nasional Informatika dan Teknologi Jaringan Sinkron : Jurnal dan Penelitian Teknik Informatika JURNAL MEDIA INFORMATIKA BUDIDARMA Journal of Computer System and Informatics (JoSYC) Jurnal Pengabdian Masyarakat IPTEK Jurnal Sistem Informasi Triguna Dharma (JURSI TGD) Proceeding of International Conference on Information Science and Technology Innovation (ICoSTEC) Journal of Technology and Computer (JOTECHCOM) International Journal of Economics and Management Sciences
Yuni Franciska Tarigan
Magister Of Computer Science, Potensi Utama University
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Industrial & Manufacturing Engineering Social Sciences

Published : 10 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 10 Documents
Search

 1 
Implementasi Jaringan Saraf Tiruan Pengenalan Pola Aksara Batak Simalungun Menggunakan Kohonen Self Organizing Map Yuni Franciska Tarigan; B. Herawan Hayadi; Asyahri Hadi Nasyuha
Journal of Computer System and Informatics (JoSYC) Vol 3 No 4 (2022): August 2022
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v3i4.1991

Abstract

The Simalungun Batak script contained in the Batak Letter consists of several variants of forms depending on the language and region, in general there are five variants of the Batak Letter in Sumatra, namely Karo, Toba, Pakpak, Simalungun, Angkola Mandailing. This script is not widely known by the datu, namely people who are respected by the Batak community for mastering magic, fortune-telling, and calendaring so that errors still often occur in the introduction of this script, even though this script can be found in various libraries, namely the traditional books of the Batak community. By utilizing Artificial Neural Networks and using the Kohonen Self Organizing Map method which can be implemented in the Simalungun Batak Letter Recognition Application so that it can make it easier for the public to recognize the Simalungun Batak script. The results of the study that applied an artificial neural network with the kohonen self-organizing map algorithm made the recognition of the Simalungun Batak letter pattern easy for the public to recognize and could also preserve one of the cultures, namely the Simalungun Batak script and make it easier for users to implement it into the android-based application.
Implementasi Metode HSI pada Transformasi Ruang Warna Dalam Mendeteksi Kematangan Buah Mangga Udang Yuni Franciska Br Tarigan; Karina Andriani; Rika Rosnelly; Wanayumini Wanayumini
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 6, No 4 (2022): Oktober 2022
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v6i4.4547

Abstract

Mango is a plant that is widely cultivated in Indonesia. Mango is a fruit that is popular and favored by almost the entire world population. Mango is not a native plant from Indonesia but is a fruit plant native to India that has a distinctive taste. The shelf life is very short because it is a fruit that is easily damaged or rotted in a certain period of time. The use of technology Digital image is an image that can be processed directly by a computer. A digital image can be represented by a matrix consisting of M columns and N rows, where the intersection between the columns and rows is called a pixel (picture element), which is the smallest element of an image. Image processing is a form of processing an image or image by numerical processing of the image, in this case, each pixel or point of the image is processed. One image processing technique utilizes a computer as software to process each pixel of an image. For image processing applications that perform object recognition, it will be easier if the object is identified using the difference in its hue value by limiting a certain value of the hue value to the object. The HSI color space model is a color space system similar to the performance of the human eye. HSI works by combining the color or grayscale contained in the image. Based on the reference value range of the Mango Shrimp fruit that has been determined in the process using the HSI method, it can be concluded that the test image of the Mango Shrimp fruit with a value of H=32 S=0.675 I=83 then the manga can be said to be ripe.
Combination Of SqueezeNet And Multilayer Backpropagation Algorithm In Hanacaraka Script Recognition Yuni Franciska br Tarigan; Teddy Surya Gunawan; B. Herawan Hayadi
Proceeding of International Conference on Information Science and Technology Innovation (ICoSTEC) Vol. 2 No. 1 (2023): Proceeding of International Conference on Information Science and Technology In
Publisher : Universitas Respati Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35842/icostec.v2i1.51

Abstract

Javanese script is one of Indonesia's cultural heritages that are increasingly rarely used today. The difficulty of recognizing the shapes of letters, let alone writing them, is the main obstacle in using the Hanacaraka script. This research offers an alternative to Hanacaraka script recognition using a combination of image feature extraction and machine learning, where we utilize a pre-trained SquzeeNet model and Multilayer Backpropagation algorithm. Of the 18 models built using ReLu, Sigmoid, and Tanh activation functions, we found that the Tanh activation function, using the combination of 50-50-100 neuron configuration and 25 epochs, was the most optimal function used to classify the training data with accuracy, precision, and recall values of 93.8%. Meanwhile, the Tanh activation function, using the 50-100-50 neuron configuration and 50 epochs, is the most optimal function to classify the testing data, with accuracy, precision, and recall values of 89.1%, 89.5%, and 89.5%. All built models show a training and testing performance ratio below 10%. From this result, we conclude that all models have good reliability in the training and testing classification process.
Implementasi Algoritma Hopfield Discreate dalam Rekognisi Aksara Batak Toba Br Tarigan, Yuni Franciska; Gultom, Karyawaty; Mandasari, Sartika; Riandini, Meisarah
Jurnal Sistem Informasi Triguna Dharma (JURSI TGD) Vol. 3 No. 6 (2024): Edisi November 2024
Publisher : STMIK Triguna Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53513/jursi.v3i6.10558

Abstract

Aksara Batak Toba merupakan salah satu aksara tulisan di Indonesia dari salah satu budaya yang ada. Aksara batak toba ini menjadi salah satu di antara aksara batak yang ada yang memiliki ciri khas tertentu. Disamping itu karena ini merupakan salah satu peninggalan budaya, sebagai warga negara yang baik tentunya harus menjaga agar aksara batak toba ini tetap eksis. Jaringan syaraf tiruan merupakan salah satu cabang ilmu kecerdasan buatan yang berkembang. Di dalam jaringan syaraf tiruan terdapat berbagai metode yang dapat di adopsi atau dikembangkan diantaranya metode Hopfield. Metode ini memiliki tingkat akurasi yang cukup baik di dalam pengenalan pola-pola atau data yang terstruktur. Pada penelitian ini akan dilakukan sebuah rekognisi aksara batak toba berdimensi 30x30 piksel dengan citra gambar .png. Berdasarkan hasil ujicoba terhadap pola aksara toba diketahui bahwa metode hopfield dapat mengenali pola lebih baik dan lebih cepat dengan rata-rata waktu pengenalan 0,9792 detik. Sedangkan untuk ketepatan metode Hopfield 90% dapat mengenali poa Aksara Batak Toba.
TGD Technology Workshop Pemanfaatan Teknologi IoT Untuk Kehidupan Sehari-har Br Tarigan, Yuni Franciska; Pane, Usti Fatimah Sari Sitorus; Syahputri, Astri; Yetri, Milfa; Anwar, Badrul
Jurnal Pengabdian Masyarakat IPTEK Vol. 5 No. 1 (2025): Edisi Januari 2025
Publisher : STMIK Triguna Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53513/abdi.v5i1.10591

Abstract

Internet of Things atau IoT yang merupakan konsep terbaru dari penerapan ilmu komputer dan jaringan menjadi salah satu wawasan yang dapat disampaikan kepada mahasiswa pada saat ini. Dimana IoT menjadi satu contoh kombinasi penerapan ilmu komputer, jaringan dan analisa kecerdasan buatan dalam satu konsep implementasi. Penerapan IoT pada sistem kendali cerdas dan monitoring sederhana, hingga penerapan IoT pada pemrograman bersekala besar. Namun pemahaman terkait IoT masih dianggap awam bagi siswa menengah atas saat ini. Hal ini akan berdampak kurang baik bagi integritas sekolah menengah atas saat ini. Kondisi tersebut menjadi salah satu alasan diadakannya kegiatan workshop dan edukasi dalam pemahaman pengembangan teknologi yang cukup menjanjikan bagi siswa/siswi yang ada di SMA Plus Jabal Rahma Mulia sebagai workshop edukasi, kegiatan juga dibekali informasi terkait salah satu program studi yang dianggap mampu memberikan peluang bagi siswa/i untuk melanjutkan pendidikan di perguran tinggi. Oleh karena itu, Akademi Manajemen Informatika dan Komputer Polibisnis berkolaborasi dengan STMIK Triguna Dharma dalam hal ini melalui Civitas akademik dan kemahasiswaa yakni dosen dan mahasiswa menyelenggarakan kegiatan pengabdian masyarakat dan bekerja sama dengan sekolah SMA Plus Jabal Rahma Mulia dalam mengedukasi siswa/i agar lebih termotivasi dalam proses belajar.
Decision Trees in Predicting Loan Default Risk in Customer Relationships within the Financial Sector Syahra, Yohanni; Br. Tarigan, Yuni Franciska; Andriani, Karina; Nazry S, Hevlie Winda; Setik, Roziyani
Sinkron : jurnal dan penelitian teknik informatika Vol. 9 No. 2 (2025): Research Articles April 2025
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v9i2.14672

Abstract

Loan default prediction is an important aspect of risk management in financial institutions. Accurate prediction models enable banks and lending organizations to mitigate risks, allocate resources effectively, and optimize decision-making processes. This study investigates the application of decision tree algorithms in predicting loan default risk in the financial sector. Decision trees are renowned for their interpretability, adaptability to non-linear data, and ability to handle missing values, making them a valuable tool in credit risk analysis. Using a dataset consisting of borrower profiles, credit scores, income levels, and payment history, the model identifies key predictors that influence default outcomes. The study uses the C4.5 decision tree model, which will demonstrate that decision trees achieve high prediction accuracy and offer a transparent decision-making framework, enhancing their applicability in real-world scenarios. Furthermore, the paper highlights the implications of these findings for financial institutions, emphasizing the scalability and cost-effectiveness of the model. By integrating decision tree-based models into existing risk assessment systems, lenders can proactively manage loan portfolios and reduce default rates. Future research directions are proposed to explore hybrid approaches that combine decision trees with advanced combined methods to enhance predictive capabilities. The potential of decision tree algorithms in transforming credit risk assessment and supporting more accurate data-driven financial decision-making processes
Pemanfaatan Sosial Media Dalam Optimalisasi Mandasari, Sartika; Yuni Franciska br Tarigan; Meisarah Riandini; Karina Andriani; Masri Wahyuni
Jurnal Pengabdian Masyarakat IPTEK Vol. 5 No. 2 (2025): Edisi Juli 2025
Publisher : STMIK Triguna Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53513/abdi.v5i2.11265

Abstract

Kegiatan pengabdian masyarakat yang bertujuan untuk mengoptimalkan pemanfaatan media sosial sebagai sarana pembelajaran bagi guru, siswa, dan orang tua. Program ini memberikan pemahaman dan keterampilan praktis dalam menggunakan media sosial secara positif, aman, dan efektif untuk mendukung pembelajaran di era digital. Melalui pelatihan dan pendampingan, peserta belajar tentang platform media sosial, pembuatan konten edukatif, keamanan online, dan praktik terbaik dalam memanfaatkan media sosial sebagai sumber belajar dan diskusi. Hasilnya menunjukkan peningkatan keterampilan peserta dalam menggunakan media sosial untuk pembelajaran, peningkatan motivasi belajar siswa, pengembangan literasi digital, serta peran aktif orang tua dan guru dalam memantau penggunaan media sosial. Kegiatan ini diharapkan menjadi awal pembentukan ekosistem belajar yang adaptif dan inovatif melalui kolaborasi untuk mengoptimalkan media sosial sebagai sumber belajar.Kata kunci: Optimalisasi, Pembelajaran, Media Sosia.
Sentiment Analysis On Police Brigadier Shooting Case Using K-Means Clustering Wahyuni , Masri; Rambe, Basyit Mubarroq; Br Tarigan , Yuni Franciska; Gultom , Karyawaty
Journal of Technology and Computer Vol. 1 No. 2 (2024): May 2024 - Journal of Technology and Computer
Publisher : PT. Technology Laboratories Indonesia (TechnoLabs)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

As a medium that can be used to convey public criticism and aspirations in real time, Twitter is used as a data collection source using crawling techniques, to analyze public sentiment or response to the police brigadier shooting case. Latent dirichlet al-location (LDA) is used to determine the topics that appear in each of the collected tweets, and then used as a feature in grouping the contents of the tweets based on their respective sentiment values. The results of clustering using the k-means clustering algorithm obtained are: 11.9% of netizens gave a positive response, 18.9% of netizens gave a neutral response and 69.2% of netizens gave a negative response to the case. Thus, from the results of this study it can be concluded that netizens tend to give a negative response or reaction to the police brigadier shooting case, when viewed from the percentage of each type of response.
Early Detection of Diabetes Using a Machine Learning Model Based on Laboratory Data Hakim, Arief Rahman; Br Tarigan, Yuni Franciska; Margolang, Khairul Fadhli
InfoTekJar : Jurnal Nasional Informatika dan Teknologi Jaringan Vol 10, No 1 (2025): InfoTekJar September
Publisher : Universitas Islam Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30743/infotekjar.v10i1.12810

Abstract

Diabetes mellitus is a chronic disease whose prevalence continues to increase worldwide, with a projected number of sufferers reaching 643 million by 2030. Early detection of diabetes is crucial to prevent serious complications such as cardiovascular disease, kidney failure, and nerve damage. This study aims to compare the performance of four machine learning algorithms (Random Forest, Support Vector Machine, Logistic Regression, and K-Nearest Neighbors) in detecting diabetes based on clinical parameters, and to identify the most significant predictor variables. The study uses the Pima Indians Diabetes dataset consisting of 768 samples with 8 predictor variables (number of pregnancies, glucose, blood pressure, skin thickness, insulin, BMI, diabetes pedigree function, and age). Data is divided into a training set (70%) and a testing set (30%) using stratified sampling. Data preprocessing includes handling missing values, feature scaling using StandardScaler, and handling imbalanced data using the SMOTE technique. Performance evaluation uses accuracy, precision, recall, F1-score, and Area Under Curve (AUC-ROC) metrics. Results show that the Random Forest model achieves the best performance with an accuracy of 81.8%, precision of 79.2%, recall of 78.5%, F1-score of 78.8%, and AUC of 0.88. Support Vector Machine achieves an accuracy of 78.0%, Logistic Regression 76.0%, and K-Nearest Neighbors 74.5%. Feature importance analysis identifies glucose (28.5%), BMI (19.8%), and age (16.5%) as the most significant predictors in diabetes detection. The Random Forest model produces 17 false negatives and 12 false positives from 231 testing samples. The study concludes that Random Forest is the most effective algorithm for early diabetes detection with good accuracy and superior interpretability through feature importance.
The Influence of Risk Perception, Personal Data Protection, and Digital Service Quality on Customer Trust in Digital Banking Services in Indonesia Widya Rahayu; Helviana Hasibuan; Yuni Franciska Br Tarigan
International Journal of Economics and Management Sciences Vol. 3 No. 2 (2026): May : International Journal of Economics and Management Sciences
Publisher : Asosiasi Riset Ekonomi dan Akuntansi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61132/ijems.v3i2.1203

Abstract

The digital transformation in Indonesia’s banking sector has significantly increased the use of digital banking services; however, it has not been fully accompanied by optimal customer trust. This study aims to examine the effect of perceived risk, data privacy protection, and digital service quality on customer trust, both partially and simultaneously. A quantitative approach was employed using survey data collected from 150 digital banking users in Indonesia. Data were analyzed using Structural Equation Modeling based on Partial Least Square (SEM-PLS). The results indicate that perceived risk has a negative and significant effect on trust, while data privacy protection and digital service quality have positive and significant effects on trust. Simultaneously, all variables significantly influence trust, with an R² value of 0.672, indicating strong explanatory power. Compared to prior studies, this research contributes novelty by integrating these three variables into a comprehensive model. The findings reveal that digital service quality is the most dominant factor influencing customer trust. This study concludes that enhancing customer trust requires an integrated approach through effective risk management, strengthened data protection, and continuous improvement in digital service quality.
Co-Authors Andriani, Karina Anwar, Badrul Arief Rahman Hakim Asyahri Hadi Nasyuha B. Herawan Hayadi B. Herawan Hayadi Gultom , Karyawaty Gultom, Karyawaty Hasibuan, Helviana Hevlie Winda Nazry S Karina Andriani Karina Andriani Mandasari, Sartika Margolang, Khairul Fadhli Masri Wahyuni Meisarah Riandini Pane, Usti Fatimah Sari Sitorus Rambe, Basyit Mubarroq Riandini, Meisarah Rika Rosnelly Setik, Roziyani Syahputri, Astri Teddy Surya Gunawan Wahyuni , Masri Wanayumini Widya Rahayu Yetri, Milfa Yohanni Syahra