Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Indonesian Journal of Artificial Intelligence and Data Mining Jurnal Software Engineering and Computational Intelligence
Santoti, Jennifer Velensia
Unknown Affiliation
Computer Science & IT

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Implementasi Term Frequency - Inverse Document Frequency dan Cosine Similarity untuk Analisis Kemiripan Deskripsi Produk Halal Santoti, Jennifer Velensia; Jocelyn, Jennifer; Irsyad, Hafiz
Jurnal Software Engineering and Computational Intelligence Vol 3 No 01 (2025)
Publisher : Informatics Engineering, Faculty of Computer Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36982/jseci.v3i01.5421

Abstract

Di era digital saat ini, kejelasan informasi produk telah menjadi aspek penting untuk mendukung keputusan konsumen dalam proses pembelian. Penelitian ini difokuskan pada implementasi ekstraksi fitur dari deskripsi produk menggunakan metode TF-IDF (Term Frequency - Inverse Document Frequency) dan Cosine Similarity untuk memprediksi deskripsi produk yang membingungkan.  Metodologi penelitian ini meliputi beberapa tahap preprocessing, yang meliputi tokenizing, stopword removal, filtering, penghapusan data null dan data NaN, serta ekstraksi fitur teks menggunakan metode TF-IDF dan Cosine Similarity. Hasil evaluasi menunjukkan bahwa sistem berhasil mengenali produk halal dengan nilai precision sebesar 96%, recall sebesar 98%, dan F1-score sebesar 97%, yang mengindikasikan bahwa adanya keseimbangan yang baik antara precision dan recall. Untuk produk haram mencapai precision sebesar 98%, recall sebesar 95%, dan F1-score sebesar 97%. Secara keseluruhan, sistem berhasil mendapatkan nilai akurasi sebesar 97%. Hasil evaluasi menunjukkan bahwa model lebih baik dalam mengenali produk halal, dengan hasil recall sebesar 98%, sementara hasil recall produk haram sebesar 95%. Hal ini mengindikasikan bahwa metode yang digunakan sangat efektif dalam memprediksi kejelasan deskripsi produk. Kesimpulan dari penelitian ini menegaskan bahwa kombinasi TF-IDF dan Cosine Similarity efektif dalam mengidentifikasi ambiguitas deskripsi produk, sehingga dapat meningkatkan transparansi informasi bagi konsumen.
A Hybrid Deep Feature Based VGG19 and Support Vector Machine Approach for Durian Leaf Classification Santoti, Jennifer Velensia; Devella, Siska
Indonesian Journal of Artificial Intelligence and Data Mining Vol 9, No 1 (2026): March 2026
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v9i1.38831

Abstract

Durian leaf classification has remained challenging due to high visual similarity among superior durian varieties and the limited robustness of conventional convolutional neural network models that rely on Softmax classifiers. This study aimed to address this limitation by investigating a deep feature-based classification framework that combined VGG19 as a feature extractor with a Support Vector Machine classifier. The experiments were conducted on a dataset of 1,530 durian leaf images representing four varieties: Bawor, Duri Hitam, Musang King, and Super Tembaga. Four experimental scenarios were designed to evaluate classification performance using Support Vector Machine and Softmax classifiers under both imbalanced and balanced data conditions through the application of Synthetic Minority Over-sampling Technique. The research gap addressed in this study lay in the absence of prior investigations that systematically evaluated the integration of VGG19 and Support Vector Machine for durian leaf variety classification under varying data distributions. Experimental results showed that the proposed VGG19–Support Vector Machine framework consistently achieved higher accuracy and more stable performance than Softmax-based models. This study demonstrated that replacing the conventional Softmax classifier with a Support Vector Machine significantly improved classification robustness compared to previous approaches that employed end-to-end convolutional neural network architectures.
Co-Authors Devella, Siska Hafiz Irsyad Jocelyn, Jennifer