Claim Missing Document
Check
Articles

Found 4 Documents
Search

Analisa Perbandingan Algoritma Bubble Sort, Insert Sort dan Selection Sort Yunial, Agus Heri
Jurnal Informatika Universitas Pamulang Vol 10 No 1 (2025): JURNAL INFORMATIKA UNIVERSITAS PAMULANG
Publisher : Teknik Informatika Universitas Pamulang

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

Abstract

The algorithm in a program describes the flow or sequence of the program. A good program must have a good algorithm, where an algorithm is said to be good, one of which is the best use of time in processing the program. A sorting algorithm is an algorithm that carries out the sorting process in the program. Some existing sorting programs include bubble sort, insert sort and selection sort. In this research, the processing time of the three algorithms will be compared in sorting 100-10,000 random data both ascending and descending which are arranged in 15 combinations of data sequences. The sorting process is carried out using the C++ programming language. From the test results it was found that for fully random data the bubble sort algorithm performs the longest sorting process and the selection sort algorithm performs the process with the fastest average time and for almost sorted data the bubble sort algorithm performs the longest sorting process and the insert sort algorithm performs the process with the fastest average time
Optimalisasi Random Forest untuk Sentimen Bahasa Indonesia dengan GridSearch dan SMOTE Fauzi, Ahmad; Yunial, Agus Heri; Saputro, Dede Eko; Saputra, Reza
Jurnal Ilmu Komputer dan Sistem Informasi Vol. 4 No. 2 (2025): Mei 2025
Publisher : LKP Unity Academy

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70340/jirsi.v4i2.207

Abstract

This research focuses on optimizing the Random Forest algorithm for sentiment analysis of social media x in Indonesian using TextBlob as a labeling tool, followed by the SMOTE data balancing technique and hyperparameter optimization with GridSearch. The data used was taken from 611 tweets with the keyword ukt (single tuition). Sentiment labeling using TextBlob produces 438 negative sentiments and 173 positive sentiments. The SMOTE method is used to balance the data by first dividing the data into 75% training data and 25% test data. Data vectorization using tf-idf. The Random Forest algorithm model was evaluated with an initial accuracy using split data of 73%, and cross validation evaluation with 10 k-folds produced an accuracy value of 75%. Optimization carried out with GridSearch hyperparameters succeeded in increasing the accuracy value to 74%, while cross validation evaluation using 10 k-fold accuracy was 89%. In this research, the SMOTE method was effective in balancing unbalanced data, and gridsearch hyperparameter optimization succeeded in increasing the accuracy value of the Random Forest algorithm in classifying social media sentiment x in Indonesian with automatic texblob labeling.
Analisis Sentimen pada Ulasan Aplikasi FinTech di Indonesia: Studi Komparatif Model Machine Learning dan Deep Learning Fauzi, Ahmad; Fuadi, Achmad Lutfi; Yunial, Agus Heri; Hidayat, Andrian; Napila, Ade
Journal of Innovative and Creativity Vol. 6 No. 1 (2026)
Publisher : Fakultas Ilmu Pendidikan Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/joecy.v6i1.6939

Abstract

Pertumbuhan sektor Teknologi Finansial (FinTech) telah menjadikan umpan balik pelanggan dari platform digital sebagai sumber penting untuk pengambilan keputusan strategis. Namun, volume dan ketidakstrukturan data, khususnya dalam bahasa informal seperti Bahasa Indonesia, menimbulkan tantangan analitis yang signifikan. Penelitian ini bertujuan untuk mengidentifikasi pipeline optimal untuk klasifikasi sentimen pada ulasan pengguna Livin' by Mandiri, super-app perbankan digital Indonesia. Kami melakukan analisis komparatif menggunakan dataset dunia nyata berisi 117.471 ulasan yang tidak seimbang (55% negatif, 31% positif, 14% netral) yang dibersihkan dari Google Play Store. Dua teknik vektorisasi teks, Bag-of-Words (BoW) dan TF-IDF, diuji pada empat classifier machine learning: Random Forest, Logistic Regression, Decision Tree, dan SVM, serta dibandingkan dengan model Deep Learning berbasis Long Short-Term Memory (LSTM). Hasilnya menunjukkan bahwa model LSTM unggul dengan akurasi 98,02% dan weighted F1-score 0,99, sementara model machine learning terbaik, Logistic Regression dengan TF-IDF, menghasilkan weighted F1-score 0,92. Temuan ini menegaskan bahwa meskipun machine learning tradisional efektif, LSTM lebih unggul dalam menangkap konteks dalam data sekuensial yang kompleks dan tidak seimbang. Penelitian ini menawarkan kerangka kerja yang berguna bagi institusi keuangan untuk menerapkan sistem analisis sentimen otomatis yang akurat dan efektif.
Comparative Analysis of Hybrid CNN-ViT and CNN for Brain Tumor Classification Fauzi, Ahmad; Fuadi, Achmad Lutfi; Yunial, Agus Heri
JISKA (Jurnal Informatika Sunan Kalijaga) Vol. 11 No. 1 (2026): January 2026
Publisher : UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/jiska.5860

Abstract

The automated categorization of brain cancers from MRI is essential for improving diagnostic precision. Traditional Convolutional Neural Networks (CNNs) are proficient in local feature extraction but are constrained in their ability to capture long-range spatial relationships, hence impairing performance on intricate malignancies. We propose a hybrid parallel architecture that merges a CNN with a Vision Transformer (ViT) to combine local and global feature modeling. We assessed our dual-branch model in comparison to a conventional CNN baseline using a curated dataset of 15,000 MRI images categorized into three classes: glioma, meningioma, and pituitary. The hybrid model exhibited enhanced performance, attaining 98.40% accuracy and 0.0783 loss, in contrast to the baseline's 97.40% accuracy and 0.1187 loss. The substantial decrease in misclassifications was validated by additional metrics, such as enhanced recall for the meningioma category. The integration of local and global variables produces a more precise, stable, and generalizable classification framework, demonstrating significant potential as a basis for dependable AI-driven Clinical Decision Support Systems (CDSS) in neuroradiology.