Claim Missing Document
Check
Articles

Found 17 Documents
Search

Predicting Non-Performing Loan's Risk Level Using KMeans Clustering and K-Nearest Neighbors Muhammad Mizan Siregar; Roslina Roslina; 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.v2i1.55

Abstract

In data mining, clustering is an unsupervised learning technique often used to group data by similarity. Clustering, especially the K-means clustering algorithm, is a feasible tool for expanding a dataset label by increasing the cluster's number according to the label's categories. This research extends the credit loan label data set from two categories (non-performing and performing loans) to four risk levels (high risk, medium risk, low risk, and no risk). The combination of three K-nearest neighbor’s distance metrics, Euclidean, Manhattan, and Chebyshev distance, with four different K values (K = 3, K = 5, K = 7, and K = 9) produced the best model with accuracy, precision, and recall values of 90%, 90.53571%, and 90%, from the model using the Euclidean distance with K = 9
TEXT MINING IN ONLINE TRANSPORTATION USER SENTIMENT ANALYSIS ON SOCIAL MEDIA TWITTER USING THE MULTINOMIAL NAIVE BAYESIAN CLASSIFIER METHOD AND K-NEAREST NEIGHBOOR METHOD Sartika Mandasari; Roslina Roslina; 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.v2i1.56

Abstract

Text mining is the process of detecting information or something new and researching large information. Text mining can also usually perform an analysis of unstructured text. Social media users in Indonesia, which currently almost reach 200 million users, have resulted in a flood of data. This condition makes text mining a solution to extract knowledge from the flood of data [1] . In exploring knowledge, there are various techniques or methods that can be adopted including the Multinomial Naive Bayesian Clasifier and K-Nearest Neighbor methods. Both of these methods have several phases that are able to explore the potential knowledge of a flood of supervised and unsupervised learning data. It is hoped that the combination of these two methods will help analyze public sentiment or perception towards online motorcycle taxi users in Indonesia
Peran Bendahara Pengeluaran Terhadap Kualitas Laporan Keuangan Dinas Pekerjaan Umum Dan Penataan Ruang Kota Sibolga Syahriani Mewanti; Meily Surianti; Roslina
Al-Kharaj: Jurnal Ekonomi, Keuangan & Bisnis Syariah Vol. 7 No. 6 (2025): Al-Kharaj: Jurnal Ekonomi, Keuangan & Bisnis Syariah
Publisher : Intitut Agama Islam Nasional Laa Roiba Bogor

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47467/alkharaj.v7i6.7959

Abstract

The Expenditure Treasurer contributes to the creation of good governance and accountability as well as timely reporting and quality financial reports. It is best for an expenditure treasurer to have competent human resources, supported by an educational background in accounting, frequent education and training, and has experience in the financial sector. This research aims to determine the role of the expenditure treasurer on the quality of financial reports at the Sibolga City Public Works and Spatial Planning Service, in accordance with the phenomenon where there are still recording errors made by the expenditure treasurer, which affects the financial reports. The method used in this research is descriptive qualitative research, considering that in this research the researcher intends to understand the phenomenon of what the research subjects experience, and the researcher also uses two variables, namely expenditure treasurer with Knowledge and Skill indicators and relevant financial report quality variables, reliable, comparable and understandable. The results of this research show that the role of the treasurer for expenditures at the Public Works and Spatial Planning Service has an important role, although the Knowledge and Skill indicators are not yet optimal for the treasurer of the Sibolga City Public Works and Spatial Planning Service.
Implementation of Convolutional Neural Network (CNN) MobileNetV2 in Lung Disease Classification from X-Ray Images Mohammad Faris Fawwaz; Arif Aryaguna Nauli; Roslina Roslina
Bulletin of Informatics and Data Science Vol 5, No 1 (2026): May 2026
Publisher : PDSI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61944/bids.v5i1.131

Abstract

The classification of lung diseases from X-ray images is often challenged by significant data imbalance, where minority classes like COVID-19 constitute only approximately 20% of the dataset compared to the majority classes. This condition can degrade model performance and introduce bias. This study aims to analyze the impact of data balancing strategies and training parameter variations to improve the accuracy of a Convolutional Neural Network (CNN) model based on the MobileNetV2 architecture. The experimental process systematically compared two learning rates (1e-3 and 1e-4) and two optimizers (Adam and RMSprop) across four distinct data handling scenarios: no augmentation, geometric augmentation only, the Mixup technique only, and a combination of both. The model was evaluated on a four-class X-ray image dataset comprising COVID-19, Normal, Pneumonia, and Tuberculosis. The optimal results were achieved by applying the combined approach of geometric augmentation and Mixup with a 1e-3 learning rate and the Adam optimizer. This configuration significantly outperformed other scenarios, reaching a testing accuracy of 96.62% and an average F1-Score of 96.63%, demonstrating excellent model generalization. This high-performing model has been successfully implemented in a mobile application using Flutter and TensorFlow Lite, serving as a practical tool to support the early diagnosis of lung diseases
Sistem Kontrol PH Tanah Untuk Peningkatan Produksi Sayuran di Desa Tanjung Kubah Kecamatan Air Putih Kabupaten Batubara Sumatera Utara Afritha Amelia; Roslina Roslina; Anriza Witi Nasution; Bakti Viyata Sundawa; Febrin Aulia Batubara; Rahimah Abdul Rahman
Jurnal Pengabdian dan Pemberdayaan Masyarakat Vol. 4 No. 1 (2026): Edisi Juni
Publisher : Jurusan Teknik Sipil, Politeknik Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51510/komposit.v4i1.2895

Abstract

Penggunaan lahan pertanian buatan/greenhouse dalam budidaya tanaman sayuran merupakan salah satu cara untuk mendekati kondisi optimal bagi pertumbuhan tanaman. Greenhouse umumnya berguna untuk melindungi tanaman dari suhu dan kondisi tanah yang ekstrim. Ini memerlukan kajian lebih lanjut terhadap perangkat yang akan digunakan untuk mendukung konsep pertanian greenhouse. Perkembangan teknologi otomasi pada saat ini, maka diharapkan bisa membantu sistem kontrol terhadap parameter-parameter yang mempengaruhi produksi tanaman sayuran seperti PH tanah dan kelembaban tanah. Parameter-parameter ini nantinya akan diukur dan dikontrol agar sesuai dengan syarat tumbuh kembang tanaman sayuran dan produksi sayuran meningkat.
PENGARUH PENERAPAN PENGENDALIAN INTERNAL DAN PENERAPAN TEKNOLOGI INFORMASI TERHADAP KETERBUKAAN LAPORAN KEUANGAN PADA PT BANK SUMUT Arninda Sekar Sari Siregar; Nurlinda Nurlinda; Roslina Roslina
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol. 8 No. 3 (2025): August 2025
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v8i3.3886

Abstract

Abstract: This study aims to empirically prove the influence of internal control policies and the application of information technology on the transparency of financial reports at PT Bank Sumut. The data collection technique used in this study is using a questionnaire. The questionnaire was given to employees and customers of PT Bank Sumut via Google Form. The data analysis used in this study is a quantitative analysis technique using statistical analysis tools, namely using Smart Partial Least Square software. The results of this study indicate that the coefficient values of the internal control policy variables and the application of information technology have an effect on the transparency of financial reports at PT Bank Sumut. Keywords: Implementation of Internal Control, Application of Technology Information, Openness of Finacial Reports Abstrak: Penelitian ini bertujuan untuk membuktikan secara empiris pengaruh penerapan pengendalian internal dan penerapan teknologi informasi terhadap keterbukaan laporan keuangan pada PT Bank Sumut. Teknik pengumpulan data yang digunakan dalam penelitian ini adalah menggunakan kuesioner atau angket. Kuesioner diberikan kepada pegawai dan nasabah PT Bank Sumut melalui google form. Analisis data yang digunakan dalam penelitian ini adalah teknik analisis kuantitatif dengan menggunakan alat bantu analisis statistik yaitu menggunakan software Smart Partial Least Square. Hasil penelitian ini menunjukkan bahwa nilai koefisien variabel penerapan pengendalian internal dan penerapan teknologi informasi berpengaruh terhadap keterbukaan laporan keuangan pada PT Bank Sumut. Kata kunci: Penerapan Pengendalian Internal, Penerapan Teknologi Informasi,  Keterbukaan Laporan Keuangan
Analisis Sentimen Masyarakat Terhadap Program Makan Bergizi Gratis Menggunakan SVM Hendra Subastian; Budi Triandi; Roslina Roslina
Jurnal Minfo Polgan Vol. 15 No. 2 (2026): Artikel Penelitian
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/jmp.v15i2.16343

Abstract

Program Makan Bergizi Gratis merupakan kebijakan strategis nasional yang memicu beragam opini publik di ruang digital. Penelitian ini bertujuan untuk menganalisis sentimen masyarakat terhadap implementasi program tersebut menggunakan data dari media sosial Twitter/X. Pendekatan yang diterapkan berbasis text mining melalui pembobotan Term Frequency-Inverse Document Frequency (TF-IDF) dan klasifikasi menggunakan algoritma Support Vector Machine (SVM), Logistic Regression dan Naïve Bayes. Melalui teknik web scraping, diperoleh dataset awal sebanyak 6.210 twit, yang kemudian menyusut menjadi 4.121 data setelah tahapan deduplikasi. Proses pelabelan manual menunjukkan sebaran sentimen yang tidak seimbang (imbalanced dataset), didominasi oleh kelas positif (82,76%), diikuti negatif (9,73%), dan netral (7,58%). Sebelum pemodelan data melalui tahapan preprocessing yang meliputi cleaning, case folding, tokenization, stopword removal, dan stemming. Hasil pengujian model SVM menunjukkan performa yang cukup baik dengan nilai akurasi sebesar 0,849, F1-score 0,839, dan MCC 0,444, di mana sensitivitas tertinggi berada pada kategori positif dengan recall mencapai 0,946. Sebaliknya, performa pada kelas minoritas (negatif dan netral) masih tergolong rendah akibat bias ketidakseimbangan data. Eksperimen komparatif dengan Logistic Regression menghasilkan akurasi (0,857) dan AUC (0,932) yang sedikit lebih tinggi, namun SVM terbukti lebih konsisten dalam menjaga stabilitas klasifikasi antar-kelas. Secara keseluruhan, pendekatan ini efektif memetakan respons publik, dan disarankan bagi penelitian selanjutnya untuk menerapkan metode penanganan imbalanced data guna mengoptimalkan akurasi pada kelas minoritas.