Garuda - Garba Rujukan Digital

Analisa Distance Metric Algoritma K-Nearest Neighbor Pada Klasifikasi Kredit Macet Khairul Fadhli Margolang; Muhammad Mizan Siregar; Sugeng Riyadi; Zakarias Situmorang
Journal of Information System Research (JOSH) Vol 3 No 2 (2022): Januari 2022
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Data mining is a method that can classify data into different classes based on the features in the data. With data mining, non-performance loan categories can be classified based on data on lending from cooperatives to their members. This study uses K-Nearest Neighbor to classify non-performance loan categories with various distance metric variations such as Chebyshev, Euclidean, Mahalanobis, and Manhattan. The evaluation results using 10-fold cross-validation show that the Euclidean distance has the highest accuracy, precision, F1, and sensitivity values compared to other distance metrics. Chebyshev distance has the lowest accuracy, precision, sensitivity, while Mahalanobis distance has the lowest F1 value. Euclidean and Manhattan distances have the highest reliability values for true-positive and true-negative class classifications. Mahalanobis distance has the lowest reliability value for false-positive class classification, while Chebyshev distance has the lowest value for false-negative class classification

ANALYSIS OF SVM AND NAIVE BAYES ALGORITHM IN CLASSIFICATION OF NAD LOANS IN SAVE AND LOAN COOPERATIVES Sugeng Riyadi; Muhammad Mizan Siregar; Khairul fadhli Fadhli Margolang; Karina Andriani
JURTEKSI (Jurnal Teknologi dan Sistem Informasi) Vol 8, No 3 (2022): Agustus 2022
Publisher : STMIK Royal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33330/jurteksi.v8i3.1483

Abstract: Non-performing loan (NPL) is a risk that credit unions must face and to avoid that, prospective debtors need to be surveyed. With previous loan data, support vector machine and naïve bayes can be used as classification methods to give a decision about NPL. We use a data set with 61 data and process the data with orange 3.30 application to see the difference between SVM using linear (SVM-L), polynomial (SVM-P), RBF (SVM-R) and sigmoid (SVM-S) kernel with naïve bayes. We use a cross validation technique with various folds to measure the classification results and a convusion matrix to measure the data training classification results. Naïve bayes scores the highest in terms of accuracy and SVM-R scores the highest in terms of F1, precision and recall. SVM-P scores the lowest in terms of accuracy, F1, precision and recall. Naïve bayes scores the highest in terms of proportion of predicted for true negative class and proportion of actual for true positive class. SVM-S scores the highest in terms of proportion of predicted for true positive class and proportion of actual for true negative class. SVM-P scores the lowest in both proportion of predicted and proportion of actual. Keywords: classification; naïve bayes; non-performing loan; support vector machine Abstrak: Kredit macet merupakan resiko yang sering dialami koperasi simpan pinjam, sehingga perlu dilakukan survei terhadap calon debitur agar kredit menjadi sehat. Dengan menggunakan data pemberian kredit sebelumnya, support vector machine dan naïve bayes digunakan sebagai metode klasifikasi untuk memberikan keputusan macet atau tidaknya kredit anggota koperasi Mutiara Sejahtera. Data set yang berjumlah 61 data diolah menggunakan aplikasi Orange 3.30 dan dilihat perbandingan antara metode SVM dengan kernel linear, polynomial, RBF dan sigomoid dengan metode naïve bayes. Cross validation dengan jumlah fold bervariasi digunakan sebagai nilai ukur klasifikasi dan convusion matrix digunakan sebagai nilai ukur klasifikasi data training. Hasil yang diperoleh adalah naïve bayes memiliki nilai accuracy tertinggi dan SVM kernel RBF memiliki nilai F1, precision dan recall tertinggi. SVM kernel polynomial memiliki nilai terendah untuk accuracy, F1, precision dan recall. Naïve bayes memiliki nilai tertinggi untuk proportion of predicted (PoP) kelas true negative dan proportion of actual (PoA) kelas true positive. SVM kernel sigmoid memiliki nilai tertinggi untuk PoP kelas true positive dan PoA kelas true negative. SVM kernel polynomial memiliki nilai terendah baik untuk PoP maupun PoA true negative dan kelas true positive. Kata kunci: klasifikasi; kredit macet; naive bayes; SVM

Sentiment Classification on Mandalika MotoGP Event Using K-Means Clustering and Random Forest Khairul Fadhli Margolang; Muhammad Zarlis; Hartono Hartono
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.v2i1.35

As one the most famous world-class motorcycle racing competition, MotoGP is an event broadcast live on television with millions of viewers on each race. Indonesia, especially the Pertamina Mandalika Circuit, will hold this prestigious racing event in the 19th series of 2022. This event sparks Indonesian netizens' reactions on social media, especially on Twitter. This research aims to analyze the public sentiment and emotional value regarding this event, with the data collected from Twitter social media. With the features of sentiment and emotion values extracted from the contents of this tweet, we use K-means clustering to generate sentiment clusters as targets for the classification using the Random Forest (RF) algorithm. From the evaluation using the 5-fold and 10-fold cross-validation, we get the highest accuracy of 0.99, the highest precision of 0.990175, and the highest recall of 0.99 from the RF model with ten trees configuration. We also get the lowest accuracy, precision, and recall values of 0.96, 0.960934, and 0.96 from the RF models with 15 and 20 trees configuration, with the 10-fold evaluation

Pengenalan Masker Wajah Menggunakan VGG-16 dan Multilayer Perceptron Margolang, Khairul Fadhli; Riyadi, Sugeng; Rosnelly, Rika; Wanayumini, Wanayumini
Jurnal Telematika Vol. 17 No. 2 (2022)
Publisher : Yayasan Petra Harapan Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61769/telematika.v17i2.519

Penggunaan masker wajah pada masa pandemi Covid-19 dapat diidentifikasi berdasarkan citra yang diambil dari wajah seseorang kemudian diklasifikasi berdasarkan hasil ekstraksi fiturnya. VGG 16 merupakan sebuah pre-trained CNN model yang dapat mengekstrak 4.096 fitur dari sebuah citra dan melakukan transfer learning kepada algoritme multilayer perceptron dalam mengklasifikasikan seseorang menggunakan masker wajah atau tidak. Hasil dari penelitian ini menunjukkan bahwa kombinasi aktivasi ReLu dengan optimasi adaptive moment (Adam) dan stochastic gradient descent (SGD), kombinasi ReLu dan Adam, menghasilkan performa klasifikasi terbaik dengan nilai accuracy, precision, dan recall sebesar 98,1%.

Analisis Keamanan Data Rekam Medis Digital Menggunakan Algoritma Kriptografi AES Hakim, Arief Rahman; Margolang, Khairul Fadhli
Jurnal Teknologi Sistem Informasi dan Sistem Komputer TGD Vol. 8 No. 2 (2025): J-SISKO TECH EDISI JULI
Publisher : STMIK Triguna Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53513/jsk.v8i2.11461

Keamanan data rekam medis digital merupakan aspek krusial dalam sistem informasi kesehatan elektronik (EHR). Kriptografi berperan penting dalam menjaga kerahasiaan dan integritas informasi pasien. Algoritma Advanced Encryption Standard (AES) dikenal luas sebagai metode kriptografi simetris yang kuat dan efisien. Penelitian ini bertujuan untuk menganalisis keamanan dan efisiensi algoritma AES dalam melindungi data rekam medis digital. Penelitian dilakukan melalui simulasi enkripsi dan dekripsi terhadap data medis dalam berbagai ukuran file menggunakan Python. Hasil menunjukkan bahwa AES mampu menjaga integritas dan kerahasiaan data, serta memiliki waktu proses yang relatif cepat. Penelitian ini memberikan kontribusi terhadap pengembangan sistem keamanan data medis berbasis enkripsi. Kata Kunci : Keamanan Data, Rekam Medis Digital, AES, Kriptografi, EHR

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

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.

Pelatihan Motion Graphics Berbasis Canva Untuk Meningkatkan Daya Saing Kreatif Siswa SMK Azizi Arief Rahman Hakim; Khairul Fadhli Margolang; Yuni Franciska Br. Tarigan; Lathifah Tsamratul Ain; Nahdah Salsabiil Damanik; Hafni Zahra
Sevaka : Hasil Kegiatan Layanan Masyarakat Vol. 3 No. 4 (2025): November : Sevaka : Hasil Kegiatan Layanan Masyarakat
Publisher : STIKES Columbia Asia Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62027/sevaka.v3i4.625

The gap between vocational students’ competencies and the needs of the digital creative industry requires efforts to enhance students’ technological and creative skills. This community service program aimed to improve the digital competence and creativity of vocational students through Canva-based motion graphics training. The program was conducted at SMK Swasta Nur Azizi Tanjung Morawa using lectures, demonstrations, hands-on practice, and mentoring methods. The results showed that participants were able to understand bassic motion graphics concepts and produce simple animated works using Canva. Evaluation results indicated that more than 80% of participants were able to operate Canva’s basic animation features, and all participants successfully produced at least one motion graphics project, with an average competency improvement of approximately 30% compared to pre-training levels. Overall, the training proved effective in enhancing students’ creative skills, confidence, and readiness to meet the demands of the digital creative industry.

Indonesian Social Media Text Classification for Mental Health Risk Detection Using Bidirectional LSTM Arief Rahman Hakim Arief; Yuni Franciska Br. Tarigan; Khairul Fadhli Margolang
Hanif Journal of Information Systems Vol. 4 No. 1 (2026): August Edition
Publisher : Ilmu Bersama Center

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

Mental health disorders, particularly depression and anxiety, have become increasingly prevalent in Indonesia, affecting millions of individuals across all age groups. However, limited access to mental health professionals and persistent social stigma frequently prevent timely early detection and intervention. Social media platforms serve as digital diaries where Indonesian users express their emotional states, presenting a unique opportunity for automated mental health risk screening. This study proposes a deep learning approach using Bidirectional Long Short-Term Memory (BiLSTM) for classifying Indonesian social media text into three mental health risk categories: Normal (low risk), Depression (high risk), and Anxiety (moderate risk). Unlike standard LSTM, which processes text in a single direction, BiLSTM captures contextual information from both forward and backward directions — a critical advantage for understanding nuanced expressions in Indonesian informal language. A dataset of 1,488 Indonesian text samples (500 Normal, 494 Depression, 494 Anxiety) was collected from Twitter and labeled by expert annotators with an inter-annotator agreement (Cohen's Kappa) of 0.87. Comprehensive text preprocessing was applied, including case folding, noise removal, stopword elimination using NLTK, and stemming using Sastrawi. The proposed BiLSTM model was evaluated against three baseline methods: Naïve Bayes, Support Vector Machine (SVM), and standard LSTM. Experimental results demonstrate that BiLSTM achieves superior performance with 87.5% accuracy, 86.8% precision, 86.2% recall, and 86.5% F1-score, outperforming standard LSTM by 4.2% and SVM by 12.1%. A desktop application with a graphical user interface was developed for practical deployment, featuring real-time detection, confidence scoring, and prediction history logging. This research contributes an effective, reproducible, and deployable deep learning-based screening tool for mental health risk detection from Indonesian social media text.

Early Detection of Diabetes Using a Machine Learning Model Based on Laboratory Data Arief Rahman Hakim; Yuni Franciska Br Tarigan; Khairul Fadhli Margolang
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

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.

Title

Found 9 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 9 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 9 Documents
Search