Garuda - Garba Rujukan Digital

Application of K-Means Algorithm for Segmentation Analysis of Youtube Viewers in Indonesia Halim, Ryan Artanto; Pratiwi, Heny; Azahari, Azahari
INFOKUM Vol. 13 No. 03 (2025): Infokum
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58471/infokum.v13i03.2850

The application of K-Means as a clustering method in segmentation analysis is common. However, academic research on YouTube audience segmentation in Indonesia is still limited. YouTube audiences in Indonesia are diverse, ranging from entertainment, education, to news, so more in-depth analysis is needed to identify user segments more specifically. YouTube audience segmentation can provide a deeper understanding of people's video consumption behavior. This understanding can help content creators and digital industry players develop more effective content strategies. K-Means was chosen as the clustering method in this study because it can group YouTube viewers in Indonesia based on their interaction patterns with YouTube content. In addition, K-Means' ability to handle large data is suitable for segmenting platforms with a large number of users such as YouTube. This research uses three main features, namely views, duration, and engagement rate to group viewers into five clusters. Cluster evaluation using Silhouette Score (0.3445), Davies-Bouldin Index (0.9576), and Calinski-Harabasz Index (481.4730) shows that the resulting segmentation is of good quality. The analysis shows that there are differences in video consumption patterns across clusters, reflecting variations in viewer preferences and engagement levels.

Eye Disease Classification Using Convolutional Neural Network (CNN) with Web-based MobileNetV2 Architecture Fahriawan, Muhammad; Pratiwi, Heny; Harpad, Bartolomius
INFOKUM Vol. 13 No. 03 (2025): Infokum
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58471/infokum.v13i03.2851

The high prevalence of preventable eye diseases, such as cataracts, glaucoma, and diabetic retinopathy, emphasizes the importance of accessible and efficient diagnostic solutions. This research aims to develop a web-based eye disease classification system using a lightweight Convolutional Neural Network (CNN) architecture, MobileNetV2, to overcome computational limitations in real-time applications. CRISP-DM methodology is applied, including dataset preparation, transfer learning with MobileNetV2 and VGG16, model evaluation, and implementation using Flask. The dataset from Kaggle consisting of 4,217 eye fundus images with four classes (cataract, glaucoma, diabetic retinopathy, and normal) was divided into 80% training, 10% validation, and 10% testing. Data augmentation and normalization were performed to improve model generalization. The results showed MobileNetV2 achieved the highest accuracy (90.14%) with low computational requirements, outperforming VGG16 (89.66%) and CNN (86.78%). MobileNetV2 displays balanced precision (89-99%), recall (74-96%), and F1-score (81-99%) across all classes, especially excelling in diabetic retinopathy detection. Its efficiency on resource-constrained environments makes it ideal for web integration. The developed Flask-based application allows users to upload images for instant classification, bridging the healthcare access gap. This research proves the effectiveness of MobileNetV2 in combining high accuracy and computational efficiency, offering a scalable solution for early screening of eye diseases, especially in remote areas.

Evaluation of the New Student Admission Website of STMIK Widya Cipta Dharma Using the End-User Computing Satisfaction Method Damaya, Filio Angga; Pratiwi, Heny; Yunita, Y
IJISTECH (International Journal of Information System and Technology) Vol 8, No 6 (2025): The April edition
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/ijistech.v8i6.381

The New Student Admission (PMB) website is one of the platforms used in the admission and registration process for prospective students at STMIK Widya Cipta Dharma. An evaluation of the PMB website is necessary to ensure user convenience and satisfaction during the registration process. This study aims to evaluate the new student admission website of STMIK Widya Cipta Dharma using the End-User Computing Satisfaction (EUCS) method. The EUCS method consists of five main dimensions: content, accuracy, format, ease of use, and timeliness. Data was collected through questionnaires distributed to registered students, prospective students of STMIK Widya Cipta Dharma, and users of the PMB website. The analysis results indicate user satisfaction in using the PMB website.

Application of Large Language Model for New Student Admission Chatbot Anwar, Rafidan; Pratiwi, Heny; Wahyuni, W
IJISTECH (International Journal of Information System and Technology) Vol 8, No 6 (2025): The April edition
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/ijistech.v8i6.379

This study aims to develop a chatbot system based on a Large Language Model (LLM) that provides information related to new student admission in higher education. The system utilizes the SentenceTransformer model to generate embeddings of question and answer texts, as well as FAISS for vector-based search. Additionally, LLAMA is used to generate context-based answers, allowing the chatbot to provide more dynamic and relevant responses. System evaluation is conducted using ROUGE-1, ROUGE-2, and ROUGE-L metrics. The evaluation results show an average ROUGE-1 Precision of 54.89%, ROUGE-2 Precision of 47.37%, and ROUGE-L Precision of 52.72%. The Recall scores for ROUGE-1, ROUGE-2, and ROUGE-L are 89.43%, 74.08%, and 82.91%, respectively

Optimization of Spareparts Stock Data Management at PT. Astra Motor Kaltim 2 using the Trend Moment Method Adeputra, James; Pratiwi, Heny; Wahyuni, W
IJISTECH (International Journal of Information System and Technology) Vol 8, No 6 (2025): The April edition
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/ijistech.v8i6.380

Spareparts inventory management is a crucial aspect of operations in automotive companies, including PT. Astra Motor Kaltim 2. An imbalance between demand and spareparts availability can lead to stockpiling or stock shortages, ultimately resulting in operational cost inefficiencies. Therefore, this study aims to analyze and forecast spareparts sales using the Trend Moment method to optimize stock management. The Trend Moment method is used to identify sales trend patterns for sparepart 44711K59A12, based on historical sales data from September 2024 to February 2025. The forecasted results are then adjusted using a seasonal index to improve accuracy. Forecast accuracy is evaluated using the Mean Absolute Percentage Error (MAPE), which provides an overview of how close the forecasted results are to the actual data. The results of the study show that the Trend Moment method can provide fairly accurate predictions in estimating the demand for sparepart 44711K59A12 in the upcoming periods. By implementing this method, the company can develop a more efficient stock procurement strategy, reduce the risk of overstocking or stockouts, and improve customer satisfaction. In conclusion, this forecasting approach can serve as a solution to enhance the effectiveness of spareparts inventory management at PT. Astra Motor Kaltim 2

Application of Large Language Model for New Student Admission Chatbot Anwar, Rafidan; Pratiwi, Heny; Wahyuni, W
IJISTECH (International Journal of Information System and Technology) Vol 8, No 6 (2025): The April edition
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/ijistech.v8i6.379

This study aims to develop a chatbot system based on a Large Language Model (LLM) that provides information related to new student admission in higher education. The system utilizes the SentenceTransformer model to generate embeddings of question and answer texts, as well as FAISS for vector-based search. Additionally, LLAMA is used to generate context-based answers, allowing the chatbot to provide more dynamic and relevant responses. System evaluation is conducted using ROUGE-1, ROUGE-2, and ROUGE-L metrics. The evaluation results show an average ROUGE-1 Precision of 54.89%, ROUGE-2 Precision of 47.37%, and ROUGE-L Precision of 52.72%. The Recall scores for ROUGE-1, ROUGE-2, and ROUGE-L are 89.43%, 74.08%, and 82.91%, respectively

Optimization of Spareparts Stock Data Management at PT. Astra Motor Kaltim 2 using the Trend Moment Method Adeputra, James; Pratiwi, Heny; Wahyuni, W
IJISTECH (International Journal of Information System and Technology) Vol 8, No 6 (2025): The April edition
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/ijistech.v8i6.380

Spareparts inventory management is a crucial aspect of operations in automotive companies, including PT. Astra Motor Kaltim 2. An imbalance between demand and spareparts availability can lead to stockpiling or stock shortages, ultimately resulting in operational cost inefficiencies. Therefore, this study aims to analyze and forecast spareparts sales using the Trend Moment method to optimize stock management. The Trend Moment method is used to identify sales trend patterns for sparepart 44711K59A12, based on historical sales data from September 2024 to February 2025. The forecasted results are then adjusted using a seasonal index to improve accuracy. Forecast accuracy is evaluated using the Mean Absolute Percentage Error (MAPE), which provides an overview of how close the forecasted results are to the actual data. The results of the study show that the Trend Moment method can provide fairly accurate predictions in estimating the demand for sparepart 44711K59A12 in the upcoming periods. By implementing this method, the company can develop a more efficient stock procurement strategy, reduce the risk of overstocking or stockouts, and improve customer satisfaction. In conclusion, this forecasting approach can serve as a solution to enhance the effectiveness of spareparts inventory management at PT. Astra Motor Kaltim 2

Evaluation of the New Student Admission Website of STMIK Widya Cipta Dharma Using the End-User Computing Satisfaction Method Damaya, Filio Angga; Pratiwi, Heny; Yunita, Y
IJISTECH (International Journal of Information System and Technology) Vol 8, No 6 (2025): The April edition
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/ijistech.v8i6.381

The New Student Admission (PMB) website is one of the platforms used in the admission and registration process for prospective students at STMIK Widya Cipta Dharma. An evaluation of the PMB website is necessary to ensure user convenience and satisfaction during the registration process. This study aims to evaluate the new student admission website of STMIK Widya Cipta Dharma using the End-User Computing Satisfaction (EUCS) method. The EUCS method consists of five main dimensions: content, accuracy, format, ease of use, and timeliness. Data was collected through questionnaires distributed to registered students, prospective students of STMIK Widya Cipta Dharma, and users of the PMB website. The analysis results indicate user satisfaction in using the PMB website.

The Impact of Cancer on Poverty: An Analytical Study Using Big Data and OLS Regression Pratiwi, Heny; Muhammad Ibnu Sa’ad; Wahyuni, Wahyuni; Syamsuddin Mallala
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 3 (2025): June 2025
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i3.6112

Cancer is one of the leading causes of death worldwide and has a significant impact on the economic condition of families, especially in developing countries. High medical costs and loss of work productivity often push families of patients with cancer into poverty. This study aimed to analyze the relationship between cancer mortality rates and poverty levels using the Ordinary Least Squares (OLS) regression method and big data covering various socio-economic indicators. The data in this study include cancer mortality rates and other socioeconomic indicators, which were then analyzed using the OLS regression method to understand the quantitative relationship between the two variables. The results of the analysis show a positive correlation between cancer mortality rates and increasing poverty, with the regression model explaining 73.8% of the variation in the target variable. The regression model demonstrated strong explanatory power and minimal error, with an R-squared value of 0.738, indicating that 73.8% of the data variability was explained by the model. Model quality was supported by low AIC (19070.4) and BIC (19110.4) values. Linearity was confirmed by a significant F-statistic of 1314.0 (p < 0.01), suggesting a robust linear relationship between independent and dependent variables. All parameters exhibited statistical significance (p < 0.05) at the 95% confidence level, with mean residuals close to zero, satisfying the unbiased expectation assumption. Although the model results show good performance, the model's estimators show low variance, as evidenced by small standard errors (e.g., Incidence_Rate: 0.009, Med_Income: 1.89e-05) and a Durbin-Watson statistic of 1.725, indicating no autocorrelation. These metrics collectively confirmed the reliability and stability of the regression model.

Strategi Manajemen Pendidikan Berbasis Machine Learning untuk Prediksi Prestasi Siswa Pratiwi, Heny; Sa'ad, Muhammad Ibnu; Salmon
BEduManagers Journal : Borneo Educational Management and Research Journal Vol. 6 No. 1 (2025): BEduManagers Journal : Borneo Educational Management and Research Journal
Publisher : Manajemen Pendidikan Program Doktor

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30872/bedu.v6i1.5016

Prediksi prestasi akademik siswa berbasis data menjadi keperluan strategis dalam manajemen pendidikan modern. Studi ini mengkaji efektivitas dua model Machine Learning—Support Vector Machine (SVM) dan Random Forest—dalam memprediksi capaian akademik peserta didik SMA Negeri menggunakan data sintetis yang menyerupai data riil sekolah. Dataset dikembangkan dari tiga variabel utama: nilai semester, tingkat kehadiran, dan latar belakang sosial ekonomi. Model diuji menggunakan validasi silang lima lipat dan dievaluasi melalui metrik akurasi, presisi, recall, serta F1-score. Hasil menunjukkan bahwa Random Forest lebih stabil dan unggul secara akurasi dibandingkan SVM dalam konteks data multidimensi non-linier. Studi ini menunjukkan potensi integrasi sistem prediktif ke dalam praktik manajerial sekolah untuk mendukung pengambilan keputusan berbasis data yang lebih akurat dan preventif terhadap kegagalan akademik.

Title

Found 26 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 26 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 26 Documents
Search