Article Per Year (5 Year)
p-Index From 2021 - 2026
1.288
P-Index
This Author published in this journals
All Journal INOVTEK Polbeng - Seri Informatika Jurnal Computer Science and Information Technology (CoSciTech) Bulletin of Computer Science Research Journal of Comprehensive Science Journal Of Artificial Intelligence And Software Engineering Science, Technology, and Communication Journal INOVTEK Polbeng - Seri Informatika
kurnia, fitra
Unknown Affiliation
Computer Science & IT Economics, Econometrics & Finance Electrical & Electronics Engineering Engineering Languange, Linguistic, Communication & Media Library & Information Science Materials Science & Nanotechnology

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 7 Documents
Search

 1 
Diagnosis Dini Penyakit Gagal Ginjal Dengan Metode Dempster Fakhira, Adzra; Insani, Fitri; Irsyad, Muhammad; Vitriani, Yelfi; Kurnia, Fitra
Jurnal Inovtek Polbeng Seri Informatika Vol 8, No 2 (2023)
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/isi.v8i2.3728

Abstract

Terlambatmendeteksipenyakitgagalginjalakanberakibatseriuskarenadiagnosisbiasanya terjadiketika masalah ginjal sudah mencapai tingkat parah. Seperti yang telah terjadi di Indonesia pada tahun 2022 lalu, terdapat 324 kasus terkonfirmasi dan 195 diantaranya meninggal dunia. Hal yang mempengaruhiketerlambatankesadaranpenderitaadalahpengetahuanyangkurangterhadapbahayapenyakit gagal ginjal. Penyakit gagal ginjal dapat disebabkan oleh dehidrasi, penyakit kronis seperti hypertensi dan diabetes, serta kekurangan banyak darah akibat  cedera atau operasi. Penggunaan teknologi dapat terwujud melalui pembuatan sistem pakardengan metode Dempster Shafer guna mendiagnosis penyakit gagal ginjal.Dalam sistem pakardiagnosis dini penyakit gagal ginjal ini penggunadiperintahkan agar mengisi data diri singkatdan gejala-gejala yang dialami. Selanjutnya sistem akan mengkombinasi gejala yang telahdipilih dengan metode Dempster Shafer menggunakan teori kepercayaan pakar sehingga mendapatkan hasil diagnosis berupa persentase pengguna mengidap penyakit gagal ginjal akut atau kronis, dan solusi untuk tindakan pengguna berikutnya. Penelitian ini telah menghasilkan sistem yang mampu mendiagnosis penyakit gagal ginjal dan dapat diterima dengan baik oleh pengguna
Retrieval-Augmented Generation in a Web-Based Question Answering System for Fiqh Books Ahadi, Ridho; Harahap, Nazruddin Safaat; Fikry, Muhammad; Kurnia, Fitra
Journal of Artificial Intelligence and Software Engineering Vol 5, No 2 (2025): June
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i2.7005

Abstract

Mayoritas masyarakat Indonesia yang beragama Islam cenderung tidak mengetahui madzhab yang mereka anut, padahal pemahaman madzhab sangat penting untuk menjalankan ibadah secara benar dan sah. Salah satu madzhab yang berkembang di Indonesia, terutama melalui ulama Hadramaut, adalah madzhab Imam Asy-Syafi’i. Kurangnya akses terhadap literatur fikih otentik serta metode pembelajaran interaktif menyebabkan masyarakat kesulitan memahami fikih secara mendalam. Perkembangan teknologi kecerdasan buatan (AI), memberikan dampak signifikan dalam berbagai aspek, termasuk pendidikan dan keagamaan. Salah satu implementasi AI yang berkembang adalah chatbot, sistem interaktif berbasis percakapan yang mampu memahami dan merespons pertanyaan secara alami. Dalam konteks pembelajaran keislaman, khususnya fikih, penggunaan chatbot AI menghadirkan peluang baru untuk pembelajaran yang lebih personal dan interaktif. Fikih sebagai cabang ilmu hukum Islam menuntut pemahaman mendalam terhadap sumber klasik dan aplikasinya dalam kehidupan modern. Penelitian ini memiliki tujuan untuk mengembangkan sistem tanya jawab fikih berbasis AI dan Natural Language Processing menggunakan Large Language Model (LLM), framework LangChain, serta metode Retrieval-Augmented Generation (RAG). Sistem ini dirancang memberikan jawaban relevan berdasarkan konteks fikih. Evaluasi menggunakan metrik BERTScore menghasilkan precision 86,50%, recall 84,76%, dan F1-score 85,52%, hasil ini menunjukkan akurasi tinggi dalam menjawab pertanyaan fikih.
Application of ARIMA and ARIMAX Methods to Predict the Number of Visitors to Hotel XYZ Pekanbaru Vernando, Julio; Insani, Fitri; Okfalisa, Okfalisa; Kurnia, Fitra
INOVTEK Polbeng - Seri Informatika Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/enrfna19

Abstract

Predicting the number of visitors to Hotel XYZ is one of the steps that can be taken by the hotel to find out how many visitors will increase in each upcoming holiday season. The purpose of this study is to forecast the number of visitors to Hotel XYZ from June 2023 to July 2024 using the ARIMA and ARIMAX comparison methods. The research methodology encompasses problem identification, data collection, data processing, and ARIMA and ARIMAX analysis, which involves testing the parameters (p, d, q) selected based on the ACF and PACF using the AIC Model. Based on the test results, ARIMAX (5, 0, 3) has the lowest AIC, which is 3495.2, followed by ARIMAX (3, 0, 5), which has a slightly higher AIC. The results showed that the ARIMAX (5, 0, 3) model is the most accurate model for predicting data (eg the number of hotel guests, room demand, or income), with an RMSE value of 15.80% and a MAPE of 18.90%. Therefore, research that applies the ARIMAX model can provide real benefits in supporting operational efficiency, resource management, and hotel business strategy, ultimately increasing the competitiveness and profitability of the hotel.
Sistem Pakar Mendiagnosis Penyakit pada Tanaman Jeruk Menggunakan Metode Dempster Shafer Elsilaturrahmi, Elsilaturrahmi; Kurnia, Fitra; Haerani, Elin; Mai Candra , Reski
Journal of Comprehensive Science Vol. 2 No. 1 (2023): Journal of Comprehensive Science (JCS)
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/jcs.v2i1.224

Abstract

Tanaman jeruk termasuk pada komoditas unggulan nasional yang berperan dalam meningkatkan devisa negara. Namun, berbagai penyakit seringkali menyererang tanaman jeruk sehingga diperlukan suatu sistem untuk mendignosis penyakit pada tanaman jeruk. Penelitian ini bertujuan untuk menganalisis sistem pakar dalam mendiagnosis penyakit pada tanaman jeruk. Penelitian ini menggunakan metode Demster Shafer. Hasil penelitian dapat disimpulkan bahwa dengan penelitian yang dilakukan dapat dipahami konsep dan penerapan dari metode Dempster Shafer dalam mendiagnosis penyakit tanaman jeruk.
Klasifikasi Sentimen Masyarakat Terhadap Revisi Undang-Undang Tentara Nasional Indonesia Menggunakan Naïve Bayes Classifier Abdul Haris Kurnia Sandi Harahap; Haerani, Elin; Oktavia, Lola; Okfalisa; Kurnia, Fitra
Bulletin of Computer Science Research Vol. 5 No. 4 (2025): June 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i4.615

Abstract

The revision of the Indonesian National Armed Forces Bill (RUU TNI) has become a hot topic in Indonesian public policy and has sparked controversy among the public due to its sudden emergence and lack of open planning process. This has raised concerns about the potential for military domination and the return of the dual function of the ABRI (Indonesian Armed Forces). The classification of public sentiment towards the RUU TNI is the focus of this study. Comments are categorized into two types of sentiment classes, namely positive and negative. The research stages include data collection, sentiment labeling, data cleaning, text normalization to lowercase letters, sentence or document segmentation into smaller parts, text data normalization, negation handling, stopword removal, and stemming, weighting using the TF-IDF technique, model classification development, and evaluation of the model's performance. The Naïve Bayes Classifier method classified 1,547 comment data points collected from two Instagram social media accounts. The Naïve Bayes Classifier model achieved an accuracy of 83.74%, precision of 81.17%, recall of 87.86%, and an F1-score of 84.38%. This study has limitations, including the limited amount of data collected. These include an imbalance in the amount of data between sentiment categories, data from only one social media platform, and the suboptimal identification of positive and negative sentiments. It is recommended that future research compare this method with other classification methods, expand the dataset, broaden the scope of data collection by involving various social media platforms over a wider time span, thereby providing a more comprehensive picture of public opinion, and test a wider range of algorithm combinations. This study can serve as an initial indicator for rapid policy evaluation, where positive or negative comments from the public on social media can provide important input in assessing the effectiveness of a policy.
Implementation of fuzzy analytical hierarchy process (FAHP) and TOPSIS for scholarship decision support system for the underprivable Kurnia, Fitra; Amri, M Khairul
Science, Technology, and Communication Journal Vol. 6 No. 2 (2026): SINTECHCOM Journal (February 2026)
Publisher : Lembaga Studi Pendidikan dan Rekayasa Alam Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59190/stc.v6i2.361

Abstract

Scholarship is part of assistance given by organization, company, institution or person. One of the existing scholarships at SMKN 2 Bengkalis is underprivileged scholarship given to students with middle to lower economic levels. This research does for helping underprivileged scholarship selectors in SMKN 2 Bengkalis to choose who are recommended eligible students as recipients of underprivileged scholarships with set established criteria before. Fuzzy analytical hierarchy process method implemented in this research with 7. With several criteria having each 4 – 5 values. And this research uses 239 active students data in SMKN 2 Bengkalis in 2021 as a decision alternative. Testing is done with 2 methods that are black box which system has worked in accordance with expected and UAT by 79% of both respondents. After obtaining the preference value, the final results of the ranking are obtained, the order of the smallest value of the student who is most. Entitled to receive scholarship assistance, namely students 1, 5, and 10.
Implementasi Algoritma Random Forest pada Web-App Sebagai Instrumen Deteksi Dini Penyakit Diabetes Fauzan, Habibul; Haerani, Elin; Kurnia, Fitra; Yanti, Novi
Computer Science and Information Technology Vol 7 No 1 (2026): Jurnal Computer Science and Information Technology (CoSciTech)
Publisher : Universitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/coscitech.v7i1.11261

Abstract

Diabetes is a chronic metabolic disease and one of the leading causes of death worldwide, with the number of sufferers projected to reach 1.3 billion by 2050. Delayed diagnosis remains a primary challenge, as nearly half of those affected are unaware of their condition in the early stages, thereby increasing the risk of fatal complications. Data mining approaches using classification algorithms have been widely utilized for early screening. However, the development of medical record models is often hindered by imbalanced data, which causes models to be biased toward the majority class and reduces detection sensitivity for the minority class (patients with diabetes). Furthermore, there is a lack of research integrating these predictive models into responsive application interfaces for end-users. Consequently, this study implements Random Forest optimized with the SMOTE (Synthetic Minority Over-sampling Technique) into a web-based application to serve as a practical early detection tool. Random Forest was selected for its ability to handle complex data and reduce the risk of overfitting. The research stages include data preprocessing, balancing training data using SMOTE, model parameter adjustment through hyperparameter tuning with Grid Search, and the development of a client-server architecture using AstroJS and Flask. The evaluation results demonstrate that the use of SMOTE significantly improves the model's ability to identify the minority class. The model achieved a Recall of 75.0% and an overall accuracy of 95.8%, effectively minimizing False Negative errors. The developed application was verified through Black Box Testing and was declared successful as a responsive and accessible early detection tool for both healthcare professionals and the general public.
Co-Authors Abdul Haris Kurnia Sandi Harahap Ahadi, Ridho Amri, M Khairul Elin Haerani Elsilaturrahmi, Elsilaturrahmi Fakhira, Adzra Fauzan, Habibul Fitri Insani Mai Candra , Reski Muhammad Fikry Muhammad Irsyad Nazruddin Safaat H Novi Yanti Okfalisa Okfalisa Okfalisa Oktavia, Lola Vernando, Julio Vitriani, Yelfi