Garuda - Garba Rujukan Digital

Penggunaan Text Modeling Untuk Identifikasi Kesalahan Penulisan Kata Pada Teks Pidato Bupati Banggai Sulawesi Tengah Suparno, Daffa Setiawan; Rosyda, Miftahurrahma
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 5, No 3 (2021): Juli 2021
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v5i3.3051

Typing errors or typography are errors made when typing a document or text, typing errors can occur due to mechanical failure or slipping of the hand or finger. Generally, typing errors are something that often occurs when someone is typing and is considered normal, but this typing error in some contexts can change the meaning of the word or even the meaning of the sentence itself, This causes the need for correction again after someone has finished typing, but the correction process is mostly still manually so the results of the correction depend on how carefully someone makes corrections and how many documents will be corrected. Therefore we need a system that can make corrections quickly and accurately, the correction process can be done by various methods, one of which is using the text modeling method. In this study, the test data used 10 documents of the Banggai Regent's important speech, Central Sulawesi. The text modeling method can be combined with other supporting methods such as word2vec, where word2vec will be used as a recommendation for corrected words. This study creates a system that can correct word errors in important speech documents of the Banggai Regent, Central Sulawesi by using text modeling and Word2Vec methods, the results obtained from the system that has been made are the system has good performance and gets maximum test results

Sistem Pendukung Keputusan Penerima Bantuan Langsung Tunai Dana Desa di Pekandangan Menggunakan Metode AHP-TOPSIS Habibah, Umu; Rosyda, Miftahurrahma
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 6, No 1 (2022): Januari 2022
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v6i1.3471

Government efforts to reduce the burden on the community indonesia poor affected by providing aid covid-19 the cash that is a source of the funds from the village or commonly called cash transfer village funds (BLT-DD). The distribution of blt-dd this needs to be done quickly and directed. But in the election of a candidate BLT-DD recipients this are still being undertaken in an unconventional manner so that , the determination of certification BLT-DD recipients to less than optimal. The purpose of this research was a concept to build the system with applies the methods of analitycal hierarchy processes (AHP) - technique for order preference by similarity to ideal solution (TOPSIS) in the determination of the communities in receipt of BLT-DD that can help the village administration Pekandangan in choosing recipients BLT-DD. Criteria used is 3 criteria that is the community who were not currently other social help PKH ( Program Keluarga Harapan ) / the cards pre workings etc, jobs / reserve enough of financial three months fore, and has family members and sick or chronic perennials. eight priority was obtained from the calculation on to the method AHP and used in seeking value matrix normalization terbobot to the method TOPSIS. Testing the accuracy of this research using confusion matrix , and the results of 91 % accuracy. Ranking it produces the research data alternative pekandangan village used by government for consideration decision making in choosing BLT-DD recipients.

Implementasi Aplikasi Laporjalanku untuk Pemetaan dan Pelaporan Jalan Rusak di Wilayah Kota Tarakan Wardani, Ade; Rosyda, Miftahurrahma
Jurnal Saintekom : Sains, Teknologi, Komputer dan Manajemen Vol 14 No 1 (2024): Maret 2024
Publisher : STMIK Palangkaraya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33020/saintekom.v14i1.489

Tarakan City has road facilities with various degrees of damage, ranging from minor to severe conditions. To address this issue, a WebGIS application is required to provide information about the road conditions. This research aims to develop the "Laporjalanku" application, designed to assist the public in reporting road damage in Tarakan City and mapping information about damaged roads. The application enables the public to easily report complaints via the web or their Android smartphones. Its features include information such as images of damaged roads, the location of damage, and estimated repair times. The development methodology used is the waterfall model, ensuring a systematic and sequential system development process. Black-box testing showed that the system functions well. Meanwhile, the System Usability Scale (SUS) test resulted in a score of 84.5%, categorized as good, and meeting user experience requirements. This application streamlines the road mapping and reporting process, providing accurate information to the Department of Public Works. Additionally, it serves as a vital tool for the government and the public to improve collaboration in maintaining the city's road conditions.

Analisis Pengelompokan Penjualan Produk Silver Jewelry Pada CV. Borobudur Silver Menggunakan Metode Algoritma K-Means nurfahrani, Nurfahrani; Rosyda, Miftahurrahma
Jurnal Sarjana Teknik Informatika Vol. 12 No. 2 (2024): Juni
Publisher : Program Studi Informatika, Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/jstie.v12i2.28209

CV. Borobudur Silver adalah perusahaan di Yogyakarta yang bergerak di bergerak di bidang perdagangan perhiasan perak. Masalah yang masih terjadi pada toko adalah peningkatan permintaan suatu produk dari pelanggan tetapi toko tidak mampu memenuhi karena stok produk tidak tersedia. Hal tersebut terjadi karena kurang pemahaman terkait pola penjualan sehingga penyediaan stok produk tidak efisien. Oleh karena itu, dibutuhkan pengetahuan terkait pola penjualan dengan dilakukan pengelompokan data berdasarkan tingkat penjualan. Pengelompokan dapat dilakukan menggunakan metode clustering data mining dengan menerapkan algoritma k-means. Penelitian ini dimulai dengan tahap pembersihan data, penentuan nilai k dengan metode elbow, implementasi dengan algoritma k-means, dan pengujian dengan metode silhouette coefficient. Proses analisis menggunakan 526 data transaksi produk dari bulan Oktober sampai Desember tahun 2022. Pengelompokan Oktober, cluster tertinggi didominasi produk gelang kaki, cluster sedang didominasi produk anting, dan cluster rendah didominasi produk gelag tangan dengan hasil pengujian kualitas cluster sebesar 0,685. Pengelompokan November, untuk cluster tertinggi didominasi cincin, cluster sedang didominasi produk kalung, dan cluster rendah didominasi produk anting dengan hasil pengujian kualitas cluster sebesar 0,898. Pengelompokan Desember, cluster tertinggi didominasi produk bros plated, cluster sedang didominasi produk gelang tangan, dan cluster rendah didominasi produk anting dengan hasil pengujian kualitas cluster sebesar 0,823.

Comparison of Machine Learning Algorithms for Species Family Classification using DNA Barcode Riza, Lala Septem; Rahman, M Ammar Fadhlur; Prasetyo, Yudi; Zain, Muhammad Iqbal; Siregar, Herbert; Hidayat, Topik; Samah, Khyrina Airin Fariza Abu; Rosyda, Miftahurrahma
Knowledge Engineering and Data Science Vol 6, No 2 (2023)
Publisher : Universitas Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17977/um018v6i22023p231-248

Classifying plant species within the Liliaceae and Amaryllidaceae families presents inherent challenges due to the complex genetic diversity and overlapping morphological traits among species. This study explores the difficulties in accurate classification by comparing 11 supervised learning algorithms applied to DNA barcode data, aiming to enhance the precision of species family classification in these taxonomically intricate plant families. The ribulose-1,5-bisphosphate carboxylase-oxygenase large sub-unit (rbcL) gene, selected as a DNA barcode locus for plants, is used to represent species within the Amaryllidaceae and Liliaceae families. The experimental results demonstrate that nearly all tested models achieve accurate species classification into the appropriate families, with an accuracy rate exceeding 97%, except for the Naïve Bayes model. Regarding computational time, the Random Forest model requires significantly more time for training than other models. Regarding memory usage, the Least Squares Support Vector Machine with a polynomial kernel, and Regularized Logistic Regression consume more memory than other models. These machine learning models exhibit strong concordance with NCBI's classifications when predicting families using the test dataset, effectively categorizing species into the Amaryllidaceae and Liliaceae families.

Analisis Pengelompokan Penjualan Produk Silver Jewelry Pada CV. Borobudur Silver Menggunakan Metode Algoritma K-Means nurfahrani, Nurfahrani; Rosyda, Miftahurrahma
Jurnal Sarjana Teknik Informatika Vol. 12 No. 2 (2024): Juni
Publisher : Program Studi Informatika, Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/jstie.v12i2.28209

CV. Borobudur Silver adalah perusahaan di Yogyakarta yang bergerak di bergerak di bidang perdagangan perhiasan perak. Masalah yang masih terjadi pada toko adalah peningkatan permintaan suatu produk dari pelanggan tetapi toko tidak mampu memenuhi karena stok produk tidak tersedia. Hal tersebut terjadi karena kurang pemahaman terkait pola penjualan sehingga penyediaan stok produk tidak efisien. Oleh karena itu, dibutuhkan pengetahuan terkait pola penjualan dengan dilakukan pengelompokan data berdasarkan tingkat penjualan. Pengelompokan dapat dilakukan menggunakan metode clustering data mining dengan menerapkan algoritma k-means. Penelitian ini dimulai dengan tahap pembersihan data, penentuan nilai k dengan metode elbow, implementasi dengan algoritma k-means, dan pengujian dengan metode silhouette coefficient. Proses analisis menggunakan 526 data transaksi produk dari bulan Oktober sampai Desember tahun 2022. Pengelompokan Oktober, cluster tertinggi didominasi produk gelang kaki, cluster sedang didominasi produk anting, dan cluster rendah didominasi produk gelag tangan dengan hasil pengujian kualitas cluster sebesar 0,685. Pengelompokan November, untuk cluster tertinggi didominasi cincin, cluster sedang didominasi produk kalung, dan cluster rendah didominasi produk anting dengan hasil pengujian kualitas cluster sebesar 0,898. Pengelompokan Desember, cluster tertinggi didominasi produk bros plated, cluster sedang didominasi produk gelang tangan, dan cluster rendah didominasi produk anting dengan hasil pengujian kualitas cluster sebesar 0,823.

ANALISIS SENTIMEN DALAM APLIKASI X TERHADAP PENGUNGSI ROHINGYA DENGAN LSTM Pratama, Andri; Rosyda, Miftahurrahma
SKANIKA: Sistem Komputer dan Teknik Informatika Vol 8 No 1 (2025): Jurnal SKANIKA Januari 2025
Publisher : Universitas Budi Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36080/skanika.v8i1.3329

Rohingya refugees in Indonesia face discrimination and hate speech due to disinformation in Indonesian society The polemic over the influx of Rohingya refugees to Indonesia has created a variety of responses among the public. Understanding the perspectives and reactions of the Indonesian public regarding this issue is crucial, especially in analyzing the growing sentiment. This research was conducted to evaluate the views and sentiments of Indonesians towards the Rohingya through X social media platforms. Data was collected through web scraping using twikit during December 2023, resulting in 17,613 tweets. Labeling was done using the trained IndoBERTweet model with the IndoNLU smsa_doc-sentiment-prosa dataset. The Long Short-Term Memory (LSTM) model is applied with two class balancing methods, Random Oversampling and SMOTE. The results show that with Random Oversampling, the model achieves precision 0.9139, recall 0.9632, F1 score 0.9379, and accuracy 0.9069. Meanwhile, the use of SMOTE resulted in precision 0.9092, recall 0.9445, F1 score 0.9265, and accuracy 0.8906.

Perbandingan Kinerja Algoritma Convolutional Neural Network (CNN) dan Recurrent Neural Network (RNN) pada Analisis Sentimen Pemilu Presiden 2024 Rahma, Ghaitsa Zahira; Rosyda, Miftahurrahma
Jurnal Pendidikan dan Teknologi Indonesia Vol 5 No 2 (2025): JPTI - Februari 2025
Publisher : CV Infinite Corporation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jpti.652

Penelitian ini mengevaluasi kinerja algoritma Convolutional Neural Network (CNN) dan Recurrent Neural Network (RNN) dalam analisis sentimen opini masyarakat terkait Pemilihan Umum Presiden 2024 di Indonesia. Pentingnya penelitian ini terletak pada upaya memahami pola sentimen masyarakat terhadap isu politik melalui pendekatan pembelajaran mendalam. Data dikumpulkan dari opini pengguna Twitter menggunakan kata kunci tertentu selama periode November 2023 hingga April 2024. Metode yang digunakan meliputi crawling data, preprocessing, pembobotan TF-IDF, serta penyeimbangan data dengan metode SMOTETomek. Model dievaluasi menggunakan K-Fold Cross Validation. Hasil penelitian menunjukkan bahwa CNN dengan resampling mencapai rata-rata akurasi validasi 99%, sedangkan RNN hanya mencapai 77,13%. Tanpa resampling, CNN memiliki rata-rata akurasi 94% dibandingkan dengan RNN sebesar 87,04%. CNN terbukti unggul dalam presisi dan efisiensi waktu, terutama pada dataset tidak seimbang. Temuan ini memberikan wawasan penting tentang pemanfaatan algoritma pembelajaran mendalam untuk analisis sentimen politik dan dapat menjadi dasar bagi pengembangan metode serupa di masa depan.

A comparative study on SMOTE, CTGAN, and hybrid SMOTE-CTGAN for medical data augmentation Khoirunnisa, Ninda; Rosyda, Miftahurrahma
Science in Information Technology Letters Vol 6, No 1 (2025): May 2025
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/sitech.v6i1.2203

The imbalance of clinical datasets remains a challenge in medical data mining, often resulting in models biased toward majority outcomes and reduced sensitivity to rare but clinically critical cases. This study presents a comparative evaluation of three augmentation strategies—Synthetic Minority Oversampling Technique (SMOTE), Conditional Tabular GAN (CTGAN), and a hybrid SMOTE+CTGAN—on the Framingham Heart Study dataset for cardiovascular disease prediction. Augmented datasets were evaluated using Decision Tree, Random Forest, and XGBoost classifiers across multiple metrics, including accuracy, precision, recall, and F1-score. Results demonstrate that classifiers trained on imbalanced data achieved high accuracy but poor minority recall (0.40), confirming model’s bias toward majority class. SMOTE yielded the strongest improvements in minority recall (up to 0.88 with XGBoost) and balanced F1 across classes, though at the cost of reduced majority recall. CTGAN and SMOTE+CTGAN delivered more moderate improvements in minority recall (0.66–0.77) while preserving higher majority recall (0.86), providing a gentler trade-off. These findings indicate that while SMOTE remains a robust baseline for addressing imbalance, hybrid and GAN-based approaches offer practical alternatives for preserving majority performance. The results highlight that augmentation choice should be informed by clinical context.

Pengecekan Pilihan Ganda Hasil Ujian pada Lembar Jawab secara Realtime Menggunakan Teknik Pengolahan Citra Yudadiningrat, Rizki Nur Rachmadi; Rosyda, Miftahurrahma
RIGGS: Journal of Artificial Intelligence and Digital Business Vol. 4 No. 3 (2025): Agustus - October
Publisher : Prodi Bisnis Digital Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/riggs.v4i3.2431

Pendidikan memerlukan evaluasi untuk memastikan pencapaian tujuan dan efektivitas proses. Penelitian ini menangani masalah pengecekan jawaban pilihan ganda pada lembar jawaban yang tidak berbasis komputer. Metode pengolahan citra, seperti grayscaling, filtering, thresholding, deteksi kontur, warp perspective, dan pengurutan kontur, digunakan untuk mendeteksi dan mengevaluasi secara otomatis lembar jawaban yang telah didigitalisasi. Metode ini menawarkan kecepatan, keandalan, dan efisiensi biaya untuk pengenalan jawaban pilihan ganda. Sistem ini, diimplementasikan menggunakan perpustakaan OpenCV di Python, mencapai akurasi sebesar 93,85% dengan jarak kamera ke lembar jawaban sekitar 17 cm. Pengujian SUS menunjukkan hasil kegunaan sebesar 85%, menjadikan perangkat lunak ini sebagai alat berharga untuk menilai jawaban pilihan ganda dengan efisien dan akurat dari berbagai lembar jawaban

Title

Found 11 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 11 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 11 Documents
Search