Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal Journix: Journal of Informatics and Computing Jurnal Komputasi
Erin Eka Citra
Universitas Lampung
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Improving the Accuracy of Social Media Sentiment Classification with the Combination of TF-IDF Method and Random Forest Algorithm Siti Mutmainah; Fathir; Erin Eka Citra
Journix: Journal of Informatics and Computing Vol. 1 No. 1 (2025): April
Publisher : Ran Edu Center

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63866/journix.v1i1.2

Abstract

Sentiment classification on social media text data is one of the main challenges in public opinion analysis. The large volume of data and the diversity of informal languages make sentiment analysis a challenge in itself, especially in the context of Indonesian. This research aims to improve the accuracy of social media sentiment classification by combining Term Frequency-Inverse Document Frequency (TF-IDF) method as a text representation technique and Random Forest algorithm as a classification model. The dataset used consists of 20,000 Indonesian opinion data collected from Twitter and Instagram, and has been labeled into three sentiment categories: positive, negative, and neutral. This data went through a preprocessing stage, including text cleaning, tokenization, stopword removal, stemming, and normalization. Experimental results show that the combination of TF-IDF and Random Forest yields an accuracy of 91.2% with average precision, recall, and F1-score values above 0.90. The confusion matrix analysis revealed that the model was highly effective in classifying positive and negative sentiments, although there were challenges in distinguishing neutral sentiments. These findings indicate that the approach used is quite reliable and can be used as a foundation for the development of sentiment analysis systems on an industrial scale as well as further research.
Genetic Algorithm Optimization for Solving the Traveling Salesman Problem in the Indonesian Business Environment Siti Mutmainah; Teguh Ansyor Lorosae; Erin Eka Citra
Journix: Journal of Informatics and Computing Vol. 1 No. 2 (2025): August
Publisher : Ran Edu Center

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63866/journix.v1i2.14

Abstract

The Traveling Salesman Problem (TSP) is one of the combinatorial optimization problems that is highly relevant in distribution and logistics route planning. This study aims to optimize the Genetic Algorithm (GA) for solving TSP in the Indonesian business environment, which has complex geographical characteristics and diverse logistics infrastructure. The proposed approach combines dynamic parameter adaptation and regional clustering to improve convergence efficiency and solution quality. Experiments were conducted on the distribution route data of an Indonesian logistics company with three scenarios: conventional GA, adaptive GA, and clustering-based GA. Performance evaluation was based on total travel distance, computation time, solution stability, and convergence rate. The results show that adaptive AG produces the best performance, with a reduction in total travel distance of up to 20% more efficient, faster convergence time (95 iterations compared to 120 iterations in conventional AG), and solution stability reaching 90.6%. These findings indicate that parameter adaptation in AG can significantly improve the effectiveness of TSP optimization in the Indonesian business context. The contribution of this research not only strengthens the development of adaptive metaheuristic algorithms but also provides practical benefits for the logistics industry in designing more efficient, cost-effective, and sustainable distribution routes.
Breast Cancer Detection Using EfficientNetV2 Variants and Data Augmentation: A Comparative Study Erin Eka Citra; Siti Mutmainah; Bambang Hermanto
Jurnal Komputasi Vol. 13 No. 1 (2025)
Publisher : Jurusan Ilmu Komputer Fakultas MIPA Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/komputasi.v13i1.281

Abstract

Kanker merupakan penyebab utama kematian kedua di dunia yang menyebabkan sekitar 9,6 juta kematian. Deteksi dini kanker dan penanganannya sedini mungkin dapat menurunkan angka kematian. Metode deep learning terbukti mampu mengenali pola dalam citra medis dan memberikan hasil klasifikasi yang akurat, EfficientNet merupakan salah satu metode deep learning. Penelitian ini bertujuan untuk mengeksplorasi penggunaan berbagai varian EfficientNetV2, yaitu EfficientNetV2-S, EfficientNetV2-M, dan EfficientNetV2-L untuk mendeteksi kanker payudara berdasarkan citra medis. Dataset yang digunakan yakni gambar USG wanita berusia antara 25 dan 75 tahun sebanyak 600 wanita, dengan total 780 gambar USG yang memiliki ukuran rata- rata 500×500 piksel dalam format PNG. Setiap gambar dalam dataset ini diklasifikasikan ke dalam tiga label yaitu normal, jinak (benign), dan ganas (malignant). Penelitian ini mendapatkan hasil akurasi terbaik pada model EfficientNetV2-L dibandingkan model EfficientNetV2-S dan EfficientNetV2-M. Nilai akurasi pelatihan yang didapatkan sebesar 89% dan nilai akurasi validasi sebesar 86% dengan nilai loss pelatihan sebesar 0.30 dan nilai loss validasi sebesar 0.37. Berdasarkan hasil tersebut, penelitian ini memiliki potensi sebagai solusi pendukung keputusan medis yang efisien dalam praktik klinis sehari-hari untuk deteksi dini kanker payudara.
Co-Authors Bambang Hermanto Fathir Fathir Siti Mutmainah Siti Mutmainah Teguh Ansyor Lorosae