Garuda - Garba Rujukan Digital

IMPLEMENTASI SUPPORT VECTOR MACHINE UNTUK ANALISIS SENTIMEN PENGGUNA TWITTER TERHADAP PELAYANAN TELKOM DAN BIZNET Sari, Bety Wulan; Haranto, Fadholi Fat
Jurnal Pilar Nusa Mandiri Vol 15 No 2 (2019): Pilar Nusa Mandiri : Journal of Computing and Information System Periode Septemb
Publisher : LPPM Universitas Nusa Mandiri

Sosial media merupakan suatu media yang dapat digunakan untuk berekspresi oleh penggunanya. Twitter cukup populer dan sering digunakan di Indonesia, pengguna twitter dapat berekspresi dan beraspirasi tanpa adanya batasan. Tweet yang berupa ekspresi dan aspirasi yang ditulis oleh pengguna twitter dapat digunakan untuk ulasan sebuah produk atau layanan. Pada penelitian ini, peneliti menggunakan teknik text mining dengan menerapkan algoritma Support Vector Machine yang dipergunakan untuk analisis sentimen pengguna twitter terhadap pelayanan Telkom dan Biznet. Data pada pelayanan Telkom dan Biznet akan dilakukan perhitungan pada penelitian ini dengan jumlah dataset sebanyak 500 tweet yang berasal dari crawling data twitter, terdapat 250 tweet yang dijadikan dataset pada masing-masing objek. Sejumlah data tersebut akan dipergunakan untuk data training serta data testing dalam proses pembuatan model menggunakan algoritma Support Vector Machine. Metode yang digunakan untuk pengujian model adalah Confusion Matrix sedangkan K-Fold Cross Validation ditujukan untuk untuk membagi data training dan data testing sesuai lipatan yang digunakan. Hasil pengujian yang diperoleh menggunakan metode K-Fold Cross Validation dan Confusion Matrix pada model yang dibuat menggunakan algoritma Support Vector Machine yang memberikan hasil nilai accuracy 79,6%, precision 76,5%, recall 72,8% , dan F1-score 74,6% untuk Telkom, serta accuracy 83,2%, precision 78,8%, recall 71,6%, dan F1-score 75% untuk Biznet.

IMPLEMENTATION OF MOORA METHOD FOR DECISION SUPPORT SYSTEM SCHOLARSHIP SELECTION IN SMK MUHAMMADIYAH PRAMBANAN Perdana, Dinar Abdi; Prabowo, Donni; Sari, Bety Wulan
Jurnal Pilar Nusa Mandiri Vol 18 No 1 (2022): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Peri
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v18i1.2261

Decision Support System for Scholarship Selection at SMK Muhammadiyah Prambanan Using the MOORA Method aims to implement the Multi-Objective Optimization method on the basis of Ration Analysis. In determining scholarship recipients based on predetermined criteria and building a system in the form of a website to help provide alternative decisions in determining the acceptance of scholarships at SMK Muhammadiyah Prambanan. Based on the source of the data obtained, using primary data including interview and observation methods supported by secondary data obtained by literature studies that are relevant to the problem. Scholarship data is calculated and then ranked based on the final value generated from the MOORA calculation. The process of scholarships selection is based on criteria including report card grades, dependents of parents, the income of parents, percentage of attendance, and the number of siblings. The results of this study are the Scholarship Selection Decision Support System Using the MOORA Method, where the final value in the form of an alternative that has the greatest preference value will be placed at the top rank. The alternative will be a recommendation to receive a scholarship.

Implementation of Smarter Method for Prospective Student Council Selection System SMK Negeri 1 Rembang Sari, Bety Wulan; Prabowo, Donni; Lestari, Wahyu Puji
Jurnal Pilar Nusa Mandiri Vol 19 No 2 (2023): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Peri
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v19i2.4591

One of the schools that has attempted to make the student council active and the primary platform for student development to encourage student activities at school is SMK Negeri 1 Rembang. OSIS administrators can execute numerous labor programs in both academic and non-academic domains. Participants must pass several selection processes to join the SMK Negeri 1 Rembang OSIS board. This student council board's election procedure still employs manual methods. The selection procedure may take longer and allow for subjective evaluations depending on the number of candidates and the criteria used. As a result, it is essential to develop a decision support system (SPK) that uses Rank Order Centroid (ROC) weighting and the Simple Multi-Attribute Rating Technique Exploiting Rank (SMARTER) method to help choose student council administrators. The SMARTER technique addressed disproportionality because the weights assigned do not provide a hierarchy or order of importance between the current criteria and their sub-criteria. Based on the computation of the final value of the standards and sub-criteria on each alternative, the system produces results in the form of the biggest to most minor order. Blackbox testing of this program demonstrates that it can operate and be used at SMK N 1 Rembang both in terms of functionality and outcomes from the system.

SISTEM PAKAR UNTUK DIAGNOSA PENYAKIT KUCING KAMPUNG DENGAN MENGGUNAKAN METODE CERTAINTY FACTOR Irawan , Mikhael Alexander Andy; Prabowo, Donni; Sari, Bety Wulan; Laksono, Aziz Catur
Information System Journal Vol. 7 No. 02 (2024): Information System Journal (INFOS)
Publisher : Universitas Amikom Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24076/infosjournal.2024v7i02.1915

Kucing kampung merupakan hewan peliharaan yang umum di Indonesia, namun kesehatan mereka sering diabaikan, menyebabkan berbagai penyakit. Penelitian ini bertujuan merancang sistem pakar berbasis website menggunakan metode certainty factor untuk mendiagnosa penyakit pada kucing kampung. Sistem ini mengumpulkan data dari pakar dan literatur medis untuk menganalisis gejala dan memberikan solusi yang tepat. Metode certainty factor digunakan untuk menghitung tingkat kepastian diagnosis berdasarkan data pengguna dan basis pengetahuan. Hasil penelitian menunjukkan bahwa sistem ini dapat memberikan diagnosis dengan baik, disertai solusi perawatan dan informasi penyakit lain. Sistem pakar ini memberikan kontribusi dengan menawarkan alternatif akses informasi diagnosa penyakit kucing kampung yang praktis dan efisien bagi masyarakat. Pengujian menunjukkan sistem berjalan sesuai kebutuhan, menjadikannya sistem pakar ini bermanfaat untuk pemelihara kucing kampung

Analisis Perbandingan Prediksi Harga Rumah Dengan Random Forest, Gradient Boosting, dan XGBoost Wulan Sari, Bety; Prabowo, Donni
Intellect : Indonesian Journal of Learning and Technological Innovation Vol. 4 No. 1 (2025): Intellect : Indonesian Journal of Learning and Technological Innovation
Publisher : Yayasan Lembaga Studi Makwa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57255/intellect.v4i1.1385

House price prediction poses a significant challenge in the property sector, especially in the Yogyakarta region, which exhibits a wide range of price variations. This study aims to compare the performance of three regression algorithms such as Random Forest, Gradient Boosting, and XGBoost, in building predictive models based on features such as land area, building area, number of bedrooms, bathrooms, and garage availability. The dataset analyzed consists of 1,642 entries, with house prices ranging from IDR 7 million to IDR 4.37 billion, an average price of IDR 1.14 billion, and a mode of IDR 775 million. Model evaluation was conducted using Mean Squared Error (MSE) and the coefficient of determination (R²), where XGBoost achieved the best performance with an MSE of 1.56 × 10¹⁴ IDR², an R² of 0.7746, and a Root Mean Squared Error (RMSE) of approximately IDR 12.5 million. These results indicate that XGBoost outperforms the other two models in handling complex tabular data and provides more accurate predictions. The predictive model has practical potential to be utilized by property developers, real estate agents, and local governments as a decision-support tool for price estimation, market evaluation, and data-driven urban planning. These findings highlight that selecting the appropriate algorithm can significantly enhance the quality of house price prediction. Abstrak Prediksi harga rumah menjadi tantangan penting dalam bidang properti, khususnya di wilayah Yogyakarta yang memiliki variasi harga cukup ekstrem. Penelitian ini bertujuan untuk membandingkan performa tiga algoritma regresi yaitu Random Forest, Gradient Boosting, dan XGBoost digunakan untuk membangun model prediksi harga rumah berdasarkan fitur seperti luas tanah, luas bangunan, jumlah kamar tidur, kamar mandi, dan garasi. Data yang dianalisis mencakup 1.642 entri dengan harga rumah berkisar antara Rp 7 juta hingga Rp 4,37 miliar, harga rata-rata sebesar Rp 1,14 miliar, dan modus Rp 775 juta. Evaluasi model dilakukan menggunakan metrik Mean Squared Error (MSE) dan koefisien determinasi (R²), di mana XGBoost menghasilkan performa terbaik dengan MSE sebesar 1,56 × 10¹⁴ rupiah², R² sebesar 0,7746, dan Root Mean Squared Error (RMSE) sekitar 12,5 juta rupiah. Hasil ini menunjukkan bahwa XGBoost lebih unggul dalam menangani data tabular kompleks dan memiliki akurasi prediksi yang lebih baik dibanding dua model lainnya. Model prediktif ini berpotensi digunakan oleh pengembang properti, agen real estate, maupun pemerintah daerah sebagai alat bantu dalam penetapan harga, evaluasi pasar, dan perencanaan tata ruang yang berbasis data. Temuan ini memberikan gambaran bahwa pemilihan algoritma yang tepat dapat meningkatkan kualitas prediksi harga properti.

Comparison of Light Gradient Boosting Machine, eXtreme Gradient Boosting, and CatBoost with Balancing and Hyperparameter Tuning for Hypertension Risk Prediction on Clinical Dataset Murtiningsih, Dewi Ayu; Sari, Bety Wulan; Fajri, Ika Nur
Journal of Applied Informatics and Computing Vol. 9 No. 5 (2025): October 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i5.10400

Hypertension is a long-lasting condition that is highly prevalent and significantly contributes to cardiovascular issues, making early identification a crucial preventive action. This research evaluates the efficacy of three boosting algorithms, eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LGBM), and CatBoost in forecasting hypertension risk. A publicly accessible dataset consisting of 4,363 samples was employed, followed by data preprocessing, feature selection through a voting method that integrates Boruta, Recursive Feature Elimination (RFE), and SelectKBest, as well as addressing class imbalance using the Synthetic Minority Over-sampling Technique (SMOTE) and ADASYN (Adaptive Synthetic Sampling Approach). The models were additionally fine-tuned through hyperparameter optimization using GridSearchCV and Repeated Stratified K-Fold Cross Validation. The evaluation results demonstrate that all three algorithms exhibited strong predictive capabilities, with CatBoost leading the way, achieving an accuracy of 0.992, precision of 0.992, recall of 0.992, F1-score of 0.992, and ROC-AUC of 0.9987. Analyzing the confusion matrix further validated that CatBoost had the lowest number of misclassifications when compared to XGBoost and LGBM. Additionally, the use of SHapley Additive exPlanations (SHAP) for model interpretability highlighted that the key factors influencing the prediction of hypertension risk are blood pressure, body mass index (BMI), overall physical activity, waist circumference, triglyceride levels, age, and LDL cholesterol levels, aligning with established medical knowledge. To facilitate real-world use, the top-performing model was implemented into a user-friendly website interface, allowing users to predict their hypertension risk interactively. These findings illustrate that boosting algorithms, especially CatBoost, offer an accurate, dependable, and interpretable machine learning method for creating hypertension risk prediction systems.

Sentiment Analysis of the Film "JUMBO" on Twitter Using the Naive Bayes Method and Support Vector Machine (SVM) with a Text Mining Approach Widodo, Tegar Robi; Fajri, Ika Nur; Sari, Bety Wulan
Journal of Applied Informatics and Computing Vol. 9 No. 5 (2025): October 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i5.10557

This study aims to perform sentiment analysis on reviews of the film “JUMBO” collected from the Twitter platform, using the Naive Bayes and Support Vector Machine (SVM) methods. The data were gathered through a crawling process on Twitter, yielding 2,011 tweets, which were then processed through several pre-processing steps, including case folding, cleaning, normalization, tokenization, stopword removal, and stemming. Subsequently, the data were transformed into numerical representations using TF-IDF, followed by sentiment labeling into positive, negative, and neutral categories. For the Naive Bayes method, training and evaluation were conducted using 5-fold Cross Validation. The results showed that the Naive Bayes model achieved an accuracy of 80.60%, precision of 73.83%, recall of 73.50%, and an F1-score of 69.98%. Meanwhile, the SVM method obtained an accuracy of 75.87%, precision of 76.36%, recall of 62.45%, and an F1-score of 65.64%. Compared to the baseline random classifier, which only achieved an accuracy of 32.47%, both primary methods significantly outperformed it in classifying film review sentiments. The analysis also indicates that the F1-score is lower than the accuracy due to the imbalanced data distribution, with a considerably higher number of positive reviews. This study also presents visualizations of sentiment distribution and word clouds to provide a clearer understanding of audience opinions. The results demonstrate that the Naive Bayes method performs well and has potential for use in sentiment analysis of films on social media platforms. These findings are expected to provide valuable insights for the creative industry, particularly in evaluating audience responses and improving the quality of future film productions.

Transfer Learning-Based Convolutional Neural Network for Accurate Detection of Rice Leaf Disease in Precision Agriculture Sari, Bety Wulan; Prabowo, Donni; Pristyanto, Yoga; Aminuddin, Afrig
Journal of Information Systems Engineering and Business Intelligence Vol. 11 No. 3 (2025): October
Publisher : Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20473/jisebi.11.3.420-432

Background: Traditional approaches to rice disease identification depend mainly upon visual examination, which is quite labor-intensive and generally demands a certain skill level from people engaged in this activity. However, these approaches suffer from high time costs and potential errors and are impractical for large-scale daily monitoring. The recent rise of deep learning has offered opportunities for automated detection process improvement, which needs to be fast-accurate as good farmer-centric. Objective: This study aims to enhance the accuracy of image rice leaf disease classification via feature extraction for rice leaf disease in four instances of pre-trained CNN models and provide an automated solution for early detection ahead of timely care by obtaining insights into crop production through precision agriculture. Methods: This study combined transfer learning with four pre-trained CNN models - InceptionResNetV2, MobileNetV2, DenseNet121, and VGG16. Results: The outcome of this research enables the identification of the optimal model to relate datasets where DenseNet121 achieved the highest accuracy, i.e. 99.10%, followed by MobileNetV2, having a precision of 97.10%. Conclusion: The new framework results in a highly accurate and high-throughput early disease detection element in precision agriculture, better than state-of-the-art approaches based on traditional techniques. Keywords: Deep Learning, DenseNet121, Image Classification, Rice Leaf Diseases, Transfer Learning

Title

Found 8 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 8 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 8 Documents
Search