Claim Missing Document
Check
Articles

Found 26 Documents
Search

Pemanfaatan Algoritma Random Forest Regression dalam Memprediksi Kepuasan Mahasiswa Terhadap Dosen Rostika Listyaningrum; Riyadi Purwanto; Dwi Novia Prasetyanti; Cahya Vikasari; Artdhita Fajar Pratiwi
Infotekmesin Vol 16 No 2 (2025): Infotekmesin: Juli 2025
Publisher : P3M Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/infotekmesin.v16i2.2808

Abstract

Student satisfaction with lecturers is a key indicator in assessing the quality of higher education. However, commonly used evaluation approaches remain largely descriptive and subjective, making them less effective in supporting sustainable quality improvement. Moreover, the comprehensive use of lecturer competency indicators in predictive models is still limited. This study addresses the gap by developing a student satisfaction prediction model using the Random Forest Regression algorithm, optimized through grid search and feature selection using the Recursive Feature Elimination (RFE) method combined with 5-fold cross-validation. Data were collected from the EDOM system of Politeknik Negeri Cilacap, involving 24 indicators based on national lecturer competency standards, and analyzed using R software. The best model was achieved with parameters mtry = 1 and ntree = 300, yielding RMSE = 0.0222, MAE = 0.0118, and R² = 0.9959. The three most influential indicators identified were structured assignments, diversity of teaching methods, and punctuality. These findings are expected to inform policies for improving the quality of higher education.
Studi Perbandingan Kinerja Support Vector Machine Pada Klasifikasi Diabetes Mellitus Menggunakan Fitur Regular Expression dan Non-Regular Expression Nur Wachid Adi Prasetya; Linda Perdana Wanti; Riyadi Purwanto
Infotekmesin Vol 17 No 1 (2026): Infotekmesin: Januari 2026
Publisher : P3M Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/infotekmesin.v17i1.3125

Abstract

Diabetes mellitus is a rapidly progressing non-communicable disease that significantly affects quality of life. Clinical information in electronic medical records, such as prescriptions and laboratory results, often appears as unstructured text and therefore requires text-mining techniques for accurate classification. This research compares the performance of the Support Vector Machine (SVM) classifier on diabetes mellitus data processed with and without feature extraction using Regular Expressions (Regex). The workflow includes data preprocessing, feature extraction, TF-IDF weighting, model training, and evaluation using accuracy, precision, recall, and F1-score. Results show that both approaches achieve high accuracy (98.8–98.9%), with the non-Regex model performing slightly better at 98.93% compared to 98.83% for the Regex-based model. These findings indicate that SVM is effective for classifying text-based clinical data, while Regex provides potential benefits but requires further optimization to ensure its suitability for various medical text contexts.
Improving Diagnostic Accuracy on Prescription Text Data Using SMOTE-Optimized SVM Linda Perdana Wanti; Nur Wachid Adi Prasetya; Riyadi Purwanto; Rahmat Mulyadi; Akmal Fauzan Ananta
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 2 (2026): April 2026
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i2.7441

Abstract

Disease classification based on drug prescription data plays a crucial role in helping healthcare professionals understand patient health conditions and supporting clinical decision-making. Drug prescription data actually contains a wealth of information regarding disease indications, but is generally presented in unstructured, free-text form. Furthermore, the data distribution across disease classes is often imbalanced, with some diseases receiving less data than others. This can lead to inaccurate classification models that favor disease classes with more data. This study aims to enhance the performance of disease classification based on drug prescription data by combining text mining approaches, the Synthetic Minority Oversampling Technique (SMOTE), and the Support Vector Machine (SVM) algorithm. The research process begins with text preprocessing, which includes case folding, tokenization, stopword removal, and stemming, to clean and normalize the prescription data. Next, the text data is converted into numeric features using the Term Frequency–Inverse Document Frequency (TF-IDF) method to enable processing by machine learning algorithms. To address the class imbalance issue, the SMOTE method is applied to training data by generating synthetic data for a limited number of disease classes. A classification model was then built using the SVM algorithm, known to be effective in handling high-dimensional text data. Model performance was evaluated using accuracy, precision, recall, and F1-score metrics. The results showed that the application of SMOTE and parameter optimization in Support Vector Machine significantly improved classification performance, with an accuracy of 92.6%, a precision of 91.8%, a recall of 93.4%, and an F1-score of 92.6%. The increased recall value in the class of patients diagnosed with diabetes indicates that the model is able to correctly identify most diabetes cases based on medical prescription data.
Clustering Achievement Records and Socioeconomic Profiles of KIP Kuliah Recipients Riyadi Purwanto; Fajar Mahardika; Dwi Novia Prasetyanti; Cahya Vikasari
Journal of Embedded Systems, Security and Intelligent Systems Vol 7 No 3 (2026): September 2026
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v7i3.13311

Abstract

Purpose – This study aims to identify patterns in the achievement records and socioeconomic characteristics of KIP Kuliah recipients to support institutional monitoring, differentiated student development, and administrative data-quality evaluation. Design/methods/approach – A quantitative unsupervised learning approach was employed using two complementary analytical streams. Achievement records were processed using text preprocessing, Term Frequency–Inverse Document Frequency (TF-IDF), Truncated Singular Value Decomposition, and K-Means clustering, with cluster selection and stability assessment used to evaluate the resulting segmentation. Socioeconomic characteristics of verified recipients were analyzed using Density-Based Spatial Clustering of Applications with Noise (DBSCAN), supported by parameter-sensitivity and alternative-distance analyses. Findings – The achievement analysis revealed distinct segments reflecting district-level academic and sports achievements, general district-level championships, national-level and olympiad achievements, and diverse sports and non-academic accomplishments. However, the achievement segments showed limited separation and should therefore be interpreted as descriptive patterns rather than definitive natural groupings. Socioeconomic clustering revealed heterogeneous recipient profiles and a substantial group of observations that did not form dense patterns. Sensitivity analysis further demonstrated that apparent low-income clusters were primarily driven by incomplete administrative records rather than verified economic vulnerability. Research implications/limitations – The findings support descriptive monitoring, differentiated achievement development, and improved verification of administrative data. Individual-level integration was not possible because the achievement and socioeconomic datasets lacked a common identifier. Originality/value – This study demonstrates how complementary text and socioeconomic clustering can reveal both meaningful recipient patterns and critical data-quality limitations in scholarship monitoring.
Development of a Hydroponic System using an Atmega 2560 Microcontroller with Automatic Nutrition and pH Settings for Lettuce Cultivation Hera Susanti; Zaenurrohman; Riyadi Purwanto
Jurnal E-Komtek (Elektronika-Komputer-Teknik) Vol 7 No 1 (2023)
Publisher : Politeknik Piksi Ganesha Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37339/e-komtek.v7i1.1170

Abstract

Hydroponic system is a technique of cultivating plants without using soil as a growing medium, but using water that is given nutrients and oxygen as a growing medium. Cultivation with hydroponic techniques must be able to pay attention and control nutrients, water content, and water ph. This research aims to create a lettuce cultivation system with intelligent hydroponic techniques using the ATmega2560 microcontroller. This system uses Arduino Mega as the control center, TDS sensor to monitor nutrition, PH sensor to monitor water acidity, and ultrasonic sensor to monitor water level. The optimal growth characteristic of lettuce is that the acidity level must be at pH 5.5-6.5 with the nutrients provided at 685-950 ppm. This system can help lettuce cultivation with hydroponic techniques by monitoring and controlling nutrients, pH, and water content in cultivated plants in real time to optimize lettuce growth.
Metode Simple Multi Attribute Rating Technique Method (SMART) dalam Penentuan Uang Kuliah Tunggal Mahasiswa Ummu Habibah Nur’Aini; Ratih Hafsarah Maharrani; Andesita Prihantara; Riyadi Purwanto
Jurnal Sains dan Informatika Vol. 11 No. 1 (2025): Jurnal Sains dan Informatika
Publisher : Pusat Penelitian dan Pengabdian kepada Masyarakat Politeknik Negeri Tanah Laut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34128/jsi.v11i1.764

Abstract

Uang Kuliah Tunggal (UKT) adalah sebuah sistem pengenaan biaya pendidikan yang diterapkan di beberapa perguruan tinggi di Indonesia. UKT bertujuan untuk mengakomodasi perbedaan kemampuan ekonomi mahasiswa dan keluarganya dalam membayar biaya Pendidikan. Dalam sistem UKT, biaya pendidikan yang harus dibayarkan oleh mahasiswa ditentukan berdasarkan kemampuan ekonomi keluarga dan tingkat pendapatan mereka. Selama ini, proses penentuan UKT masih belum konsisten dan seringkali berubah acuannya. Selain itu penentuannya pun membutuhkan waktu yang cukup lama karena terdapat beberapa point yang memerlukan penilaian berdasar kondisi ekonomi dari mahasiswa. Perguruan tinggi akan menentukan kategori UKT yang berbeda dengan besaran biaya pendidikan yang berbeda pula. Biasanya terdapat beberapa kategori UKT, misalnya UKT 0 (untuk keluarga dengan kemampuan ekonomi terbatas), UKT 1, UKT 2, UKT 3, dan seterusnya. Mahasiswa dan keluarganya akan diberikan UKT sesuai dengan kategori yang telah ditentukan. Metode SMART (Simple Multi Atribute Rating Technique) diimplementasikan pada penelitian ini dalam proses penentuan Uang Kuliah Tunggal Mahasiswa. Kerangka kerja yang terstruktur dan sistematis diberikan oleh metode SMART untuk membandingkan alternatif berdasarkan kriteria yang relevan. Beberapa kriteria yang digunakan dalam penelitian yakni jumlah asset, tanggungan, jarak rumah, jumlah penghasilan orang tua, daya listrik, sumber dari air rumah tangga, jenis pekerjaan bagi ayah dan ibu. Penelitian menghasilkan nilai peringkat uang kuliah tunggal dengan 8 golongan UKT yang ditentukan berdasarkan dari parameter yang telah ditentukan sebelumnya.