Claim Missing Document
Check
Articles

Found 2 Documents
Search

Prototype Penggabungan Fuzzy Dan Naive Bayes dalam Analisis Citra Dokumen Untuk Penilaian Margin Laporan Praktikum UINSU Hafiz Aryanda; Randy, Muhammad Randy Fachrezi; Arif Dennis Walidein; Dimas Aqila Aptanta; Alwi Syahputra
Jurnal IT UHB Vol 6 No 2 (2025): Jurnal Ilmu Komputer dan Teknologi
Publisher : Universitas Harapan Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35960/ikomti.v6i2.1854

Abstract

Manual assessment of practicum report margins often faces challenges due to variations in document layout and the large number of reports that must be reviewed, resulting in an inefficient and subjective evaluation process. Therefore, this study aims to develop a prototype that serves as a guideline for automated practicum report assessment. The proposed research introduces a hybrid model integrating Fuzzy Logic and Naive Bayes. Evaluation results show that the model without fuzzy achieved an accuracy of 73.33% but exhibited bias toward the majority class, with low recall for the "Rejected" class. In contrast, the Fuzzy Naive Bayes model improved accuracy to 80% and produced more balanced classification performance, with significant increases in recall and F1 Score for the minority class. The integration of fuzzy logic effectively enhances the detection of margin non-compliance.
Klasifikasi Jenis Bunga Iris Menggunakan Algoritma Klasifikasi Tradisional Alwi Syahputra; Rusma Riansyah; Dimas Aqila Aptanta; Muhammad Farhan; Mhd. Furqan
Jurnal ilmiah Sistem Informasi dan Ilmu Komputer Vol. 5 No. 2 (2025): Juli : Jurnal ilmiah Sistem Informasi dan Ilmu Komputer
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/juisik.v5i2.1228

Abstract

This study aims to implement and compare the performance of two traditional classification algorithms, namely K-Nearest Neighbor (K-NN) and Naive Bayes to classify Iris flower types. The dataset used is the Iris Dataset which is a classic dataset in machine learning consisting of 150 samples with four features (sepal length, sepal width, petal length, and petal width) and three target classes (Iris Setosa, Iris Versicolor, and Iris Virginica). The research methodology includes data preprocessing, algorithm implementation, model evaluation using accuracy, precision, recall, and F1-score metrics, and comparative performance analysis. The results showed that the K-NN algorithm with k = 3 achieved an accuracy of 96.67%, while Naive Bayes achieved an accuracy of 93.33%. Both algorithms showed good performance in classifying Iris flower types, with K-NN slightly superior in terms of accuracy. This study proves that traditional classification algorithms are still relevant and effective for classification problems with less complex datasets.