Article Per Year (5 Year)
p-Index From 2021 - 2026
1.745
P-Index
This Author published in this journals
All Journal Bina Insani ICT Journal Jurnal Nasional Komputasi dan Teknologi Informasi Jurnal Teknologi Terpadu MULTINETICS JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) Jurnal Sistem Komputer dan Informatika (JSON) Community Development Journal: Jurnal Pengabdian Masyarakat Joutica : Journal of Informatic Unisla Journal of Education Transportation and Business
Sri Dewi
Universitas Negeri Medan
Aerospace Engineering Humanities Automotive Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Health Professions Neuroscience Public Health Transportation

Published : 9 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 9 Documents
Search

 1 
Analisis perbandingan Algoritma Support Vector Machine, Naive Bayes dan Regresi Logistik untuk Memprediksi Donor Darah Hendriyana Hendriyana; Ichwanul Muslim Karo Karo; Sri Dewi
Jurnal Teknologi Terpadu Vol. 8 No. 2 (2022): December, 2022
Publisher : LPPM STT Terpadu Nurul Fikri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54914/jtt.v8i2.581

Abstract

Blood supplies and stocks are urgently needed. Regular donations from healthy volunteers are the only way to keep up with the blood supply. This research aims to develop and evaluate a machine-learning algorithm to predict whether a volunteer will donate or not. The machine learning algorithms are Naïve Bayes, Logistic Regression, and Support Vector Machine (SVM). This study also applies the process of normalizing data with a Z-score to standardize the dataset scale. The dataset is sourced from the Hsin-Chu City Blood Transfusion Service, Taiwan, and stored in the UCI repository. The evaluation methods are accuracy, precision, recall, and F-1 score. The research results with the Naïve Bayes algorithm were 89.90%, Logistic Regression 82.59%, and SVM 94.79%. The normalization process using the Z-Score method contributes positively to improving the performance of the classification model. Based on this performance, it provides predictive results for volunteers who will return to donate blood to offer blood reserves to those in need.
Hoax Detection on Indonesian Tweets using Naïve Bayes Classifier with TF-IDF Ichwanul Muslim Karo Karo; Romia Romia; Sri Dewi; Putri Maulidina Fadilah
Journal of Information System Research (JOSH) Vol 4 No 3 (2023): April 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v4i3.3317

Abstract

Twitter is one of the most popular social media platforms in the world nowadays. Twitter users in Indonesia are the fifth largest in the world and are always active in expressing themselves and getting information through tweets. A hoax is a lie created as if it were true. Hoaxes are also often spread via tweets. The spread of hoaxes is extremely dangerous because it can cause social discord and even misunderstanding. Therefore, hoaxes must be resisted. This study aims to build a system to detect hoaxes on Indonesian tweets. The objective of this research is to identify hoax Indonesian tweets by using the Naïve Bayes classifier with Term Frequency Inverse Document Frequency (TF-IDF). This study collects and annotates tweets from hoax tweets post which sent by a user account. This study also applied several text preprocessing techniques to provide datasets. To provide the best hoax prediction model, this work splits datasets into training and testing datasets. There are four experimental scenarios that refer to splitting the dataset. The experimental results showed that the hoax prediction model using Naïve Bayes with TF-IDF had 64% accuracy and recall, 69% and 67% precision, and a F1-score respectively. This result is also superior to the hoax prediction model when using the Naïve Bayes classifier without the TF-IDF. It means that TF-IDF has made a positive contribution to improving model performance. Finally, this research contributes by detecting news with a proclivity for hoaxes and filtering what is classified as hoaxes or not.
Penerapan Metode Forward Chaining pada Sistem Pakar Diagnosa Penyakit Tanaman Kelapa Sawit Sri Dewi
Bahasa Indonesia Vol 10 No 1 (2023): Bina Insani ICT Journal (Juni) 2023
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat Universitas Bina Insani

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51211/biict.v10i1.2301

Abstract

Sitem Pakar adalah sistem berbasis komputer yang dirancang untuk dapat meniru keahlian seorang pakar dalam memecahkan masalah. Metode yang digunakan dalam perancangan sistem pakar ini adalah metode Forward Chaining. Metode Forward Chaining merupakan suatu metode penalaran yang dimulai dari fakta untuk mendapatkan kesimpulan. metode Forward Chaining digunakan dalam sistem pakai ini sehingga dapat mendiagnosa penyakit tanaman kelapa sawit dan dapat memberikan solusi serta cara pengendalian penyakit tanaman kelapa sawit yang terserang penyakit berdasarkan gejala-gejala yang dipilih oleh user. Ada 5 jenis penyakit tanaman kelapa sawit dan 19 gejala penyakit tanaman kelapa sawit dengan 11 rule yang diterapkan dalam sistem pakar yang dirancang. Hasil prosedur ini akan menghasilkan fakta - fakta penyakit tanaman kelapa sawit dan solusi yang ditawarkan sistem untuk selanjutnya dilakukan penanganan pada tanaman kelapa sawit.
Perbandingan Kinerja Algoritma Naive Bayes dan Random Forest dalam Analisis Sentimen Publik Terhadap Batas Usia Calon Presiden dan Wakil Presiden di Twitter Mei Lammi Malau; Steviana Viviola Wicesti Nasution; Putri Tasya Agustina; Sri Dewi; Fanny Ramadhani
Journal of Education Transportation and Business Vol 1, No 2 (2024): Desember 2024
Publisher : CV. Rayyan Dwi Bharata

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57235/jetbus.v1i2.4187

Abstract

Pada pemilu di tahun 2024 ini, terdapat pro dan kontra terkait perubahan batas usia calon presiden dan wakil presiden yang memicu perdebatan di kalangan masyarakat khususnya perdebatan yang terjadi pada media sosial seperti X(twitter). Penelitian ini akan membandingkan dua algoritma machine learning yaitu Naive Bayes dan Random Forest untuk melihat kinerja yang lebih baik dalam mengklasifikasikan sentimen. Penelitian ini bertujuan untuk mengukur sentimen publik terhadap perubahan kebijakan perubahan batas usia calon presiden dan wakil presiden pada  media sosial X(twitter) dengan menggunakan teknik analisis sentimen. Penelitian ini membandingkan kinerja algoritma Naive Bayes dan Random Forest dalam analisis sentimen publik terkait batas usia calon presiden dan wakil presiden di Indonesia, menggunakan data X (Twitter). Data sentimen yang dianalisis berasal dari 500 tweet pengguna X (Twitter) menggunakan kata kunci "Putusan MK Usia Capres". Proses praproses meliputi cleaning, case folding, normalisasi, tokenisasi, penghapusan stopword, stemming kemudian fitur teks diekstraksi menggunakan metode TF-IDF. Hasil dari penelitian ini menunjukan bahwa algoritma Random Forest memiliki kinerja yang lebih baik dan tingkat akurasi yang lebih tinggi dari algoritma Naive Bayes dengan nilai akurasi 50.00%.
Sistem Informasi Travel Haji dan Umroh Berbasis Website Erika Putri Fadluna; Sri Dewi; Deswita Ananda; Nur Rizkah Khoiriyah Pohan
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 8, No 2 (2025): April 2025
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v8i2.8954

Abstract

Abstrak - Perkembangan teknologi informasi telah mendorong transformasi sistem pelayanan pada berbagai sektor, termasuk industri perjalanan haji dan umrah. Penelitian ini mengembangkan sebuah sistem informasi manajemen berbasis web yang dirancang untuk meningkatkan efisiensi dan akurasi proses pendaftaran serta pengelolaan data calon jamaah. Metodologi yang digunakan meliputi identifikasi masalah, studi literatur, observasi langsung, analisa kebutuhan sistem, perancangan model menggunakan UML, dan pembuatan prototipe melalui metode prototyping. Implementasi sistem mencakup fitur-fitur seperti halaman homepage, form login, formulir pendaftaran, pengelolaan data jamaah, dan pengelolaan pembayaran, yang diuji melalui serangkaian pengujian untuk memastikan validitas dan kesesuaian fungsionalitasnya. Hasil penelitian menunjukkan bahwa sistem berbasis web ini mampu mengatasi keterbatasan sistem manual, meningkatkan kecepatan serta akurasi pengolahan data, dan memberikan kemudahan akses bagi calon jamaah. Dengan demikian, sistem ini diharapkan dapat meningkatkan profesionalisme penyelenggaraan dan daya saing layanan haji dan umrah di era digital.Kata kunci: Teknologi Informasi, Sistem Informasi Manajemen, Haji dan Umrah, Pendaftaran Online, Prototyping, UML Abstract  - The advancement of information technology has driven the transformation of service systems across various sectors, including the Hajj and Umrah travel industry. This research develops a web-based management information system designed to improve the efficiency and accuracy of the registration process and the management of prospective pilgrims' data. The methodology employed includes problem identification, literature review, direct observation, system requirements analysis, model design using UML, and prototype development through the prototyping method. The system implementation features components such as a homepage, login form, registration form, management of pilgrim data, and payment management, which are tested through a series of evaluations to ensure functionality validity and adequacy. The study's results indicate that this web-based system is capable of overcoming the limitations of manual systems, enhancing the speed and accuracy of data processing, and providing easier access for prospective pilgrims. Thus, this system is expected to improve the professionalism of service provision and the competitiveness of Hajj and Umrah services in the digital era.Keywords: Information Technology, Management Information System, Hajj and Umrah, Online Registration, Prototyping, UML
BOOTCAMP TEKNIK JARINGAN TELEKOMUNIKASI FIBER OPTIK UNTUK SISWA/I TKJ SMKS TRI SAKTI LUBUK PAKAM Dedy Kiswanto; Hermawan Syahputra; Suvriadi Panggabean; Sri Dewi; Nurul Maulida Surbakti
Community Development Journal : Jurnal Pengabdian Masyarakat Vol. 6 No. 2 (2025): Volume 6 No. 2 Tahun 2025
Publisher : Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/cdj.v6i2.43050

Abstract

Kegiatan bootcamp teknik teknik jaringan telekomunikasi fiber optik untuk siswa/siswi teknik komputer dan jaringan di SMKS Tri Sakti Lubuk Pakam bertujuan untuk meningkatkan kompetensi siswa/i jurusan Teknik Komputer dan Jaringan (TKJ) di SMKS Tri Sakti Lubuk Pakam terkait instalasi jaringan fiber optik. Kegiatan ini diadakan untuk menjawab kebutuhan industri yang terus berkembang, di mana instalasi fiber optik menjadi standar dalam jaringan telekomunikasi secara Global. Metode yang dilakukan meliputi training materi teori instalasi fiber optik oleh praktisi Industri, demonstrasi, dan pelatihan langsung instalasi fiber optik. Hasil dari kegiatan ini menunjukkan bahwa sebagian besar peserta mampu memahami prinsip dasar fiber optik, jenis kabel yang digunakan, dan teknik instalasi yang benar. Namun, masih terdapat beberapa peserta yang belum sepenuhnya memahami aspek-aspek teknis tertentu. Diakhir kegiatan dilakukan penyerahan alat instalasi fiber optik kepada sekolah dengan harapan dapat mendukung peningkatan kompetensi instalasi fiber optik lebih lanjut dan memastikan kesiapan siswa menghadapi dunia kerja pada bidang telekomunikasi fiber optik.
District Level Child Nutrition Vulnerability in North Sumatra Using Composite Indeks, Machine Learning Benchmarking Fanny Ramadhani; Sri Dewi; Dian Septiana; Diah Retno Wahyuningrum; Andy Satria
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 7 No. 4 (2026): Juni 2026
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v7i4.9785

Abstract

Child nutrition vulnerability is a multidimensional issue influenced by health outcomes, socioeconomic conditions, environmental factors, maternal education, dietary patterns, and access to health services. This study developed the Child Nutrition Vulnerability Index (IKGA) to map district level vulnerability in 33 districts or cities of North Sumatra during 2021-2023 and to examine the stability of the resulting priority ranking. Birth, severe malnutrition, and low birth weight data were obtained from the North Sumatra Provincial Health Office; sanitation was derived from Riskesdas; and supporting socioeconomic and service access variables were compiled from district level research and statistical datasets. The method included indicator transformation, annual min-max normalization, weighted composite aggregation, tertile-based relative risk classification, spatial visualization, one-at-a-time and Monte Carlo sensitivity analyses, and exploratory machine learning benchmarking using Random Forest, Decision Tree, and K-Means. The 2023 average IKGA was 0.3486, with the highest score in Nias (0.5573) and the lowest in Kota Binjai (0.1934). Monte Carlo sensitivity analysis produced an average Spearman rank correlation of 0.9957, indicating stable rankings under moderate weight variation. Random Forest reproduced the IKGA categories better than Decision Tree and K-Means, with 0.727 accuracy and 0.724 macro-F1. The IKGA provides an interpretable district level prioritization tool for SI-GIZI SIGAP, but the categories should be interpreted as relative provincial priorities rather than absolute nutritional risk thresholds.
Ekstraksi Informasi Bencana Banjir Dari Berita Online Berbasis Named Enitity Recognition Ichwanul Muslim Karo Karo; Sri Dewi; Alvin Syahrin
MULTINETICS Vol. 11 No. 1 (2025): MULTINETICS Mei (2025)
Publisher : POLITEKNIK NEGERI JAKARTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32722/multinetics.v11i1.7499

Abstract

Banjir merupakan bencana yang paling sering terjadi di Indonesia, sehingga informasi cepat dan akurat tentang lokasi terdampak menjadi sangat penting. Penelitian ini bertujuan untuk mengembangkan model Named Entity Recognition (NER) berbasis Conditional Random Field (CRF) guna mengekstrak entitas penting (nama kota dan waktu) dari berita online terkait banjir. Data diambil dari 200 artikel berita tahun 2023 melalui metode web scraping dan manual dari lima portal berita nasional. Proses preprocessing mencakup pembersihan teks, tokenisasi, stemming, stopword removal, dan POS tagging. Data kemudian dilabeli menggunakan metode chunking dan IOB tagging untuk meningkatkan performansi identifikasi entitas. Evaluasi menunjukkan bahwa penggunaan IOB tagging pada CRF meningkatkan kinerja model, dengan F1-score = 93.6%. Hasil penelitian ini menunjukkan bahwa CRF efektif dalam mengekstrak informasi bencana banjir, dan dapat mendukung pengambilan keputusan cepat dalam upaya penanggulangan bencana.
An optimized kernel SVM framework for game review sentiment analysis using particle swarm optimization Ichwanul Muslim Karo Karo; Sri Dewi; Alvi Sahrin Nasution
Joutica Vol 11 No 1 (2026): MARET
Publisher : Universitas Islam Lamongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30736/jti.v11i1.1633

Abstract

The digital game industry’s rapid growth has increased interaction between developers and players through online review platforms. These reviews contain vital information about gaming experiences and satisfaction, serving as guides for future game versioning. Sentiment analysis provides a strategic approach to automatically classify reviews, offering data-driven insights for developers. This study focuses on enhancing sentiment analysis performance for Player Unknown's Battlegrounds (PUBG) reviews by integrating Kernel Support Vector Machine (SVM) with Particle Swarm Optimization (PSO). A dataset of 1,205 reviews from the Google Play Store was analyzed using TF-IDF feature extraction and 5-fold cross-validation. While default Kernel SVM achieved 76.78% accuracy, it suffered from low precision (56.9%). Implementing PSO for parameter optimization significantly improved performance, reaching 86.42% accuracy, 70.98% precision, and an 83.03% F1-score. Comparisons with Naïve Bayes, basic SVM, BERT, and Lexicon + SVM confirm that the Kernel SVM + PSO model provides superior and more stable performance. These findings highlight PSO’s effectiveness in SVM parameter tuning. Future research should investigate combining metaheuristic optimization with deep learning models to improve model generalization.
Co-Authors Alvi Sahrin Nasution Alvin Syahrin Andy Satria Dedy Kiswanto Deswita Ananda Diah Retno Wahyuningrum Dian Septiana Erika Putri Fadluna Hendriyana Hendriyana Hermawan Syahputra Ichwanul Muslim Karo Karo Mei Lammi Malau Nur Rizkah Khoiriyah Pohan Nurul Maulida Surbakti Putri Maulidina Fadilah Putri Tasya Agustina Ramadhani, Fanny Romia Romia Steviana Viviola Wicesti Nasution Suvriadi Panggabean