Article Per Year (5 Year)
p-Index From 2021 - 2026
1.347
P-Index
This Author published in this journals
All Journal KOMIK (Konferensi Nasional Teknologi Informasi dan Komputer) JURIKOM (Jurnal Riset Komputer) JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) KLIK: Kajian Ilmiah Informatika dan Komputer EXPLORER BEES: Bulletin of Electrical and Electronics Engineering Journal of Informatics, Electrical and Electronics Engineering
Eka Irawan
STIKOM Tunas Bangsa, Pematangsiantar
Aerospace Engineering Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering

Published : 14 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 14 Documents
Search

 1   2 
Penerapan Sistem Pakar pada Diagnosa Penyakit Tanaman Karet dengan Metode Forward Chaining (FC) Nazira Ayu Ananda; Eka Irawan; Muhammad Ridwan Lubis; M Safii
Journal of Information System Research (JOSH) Vol 2 No 1 (2020): Oktober 2020
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (388.883 KB)

Abstract

The study aimed to analyze rubber plant diseases using expert system techniques. Sources of data obtained from PT. Bridgestone Jl. Dolok Merangir Satu, Simalungun Regency by conducting observations and interviews with PT. Bridgestone. The presence of several diseases in rubber plants can make PT. Bridgestone incurs losses, so it needs proper handling. The solution given is the Forward Chaining (FC) method, which is part of an expert system so that a more efficient solution is to detect diseases in rubber plants. The results of the study indicate that the analysis can be carried out using the FC method in the diagnosis of rubber plants by implementing it into a web-based programming language so that the company can detect rubber plant diseases based on the symptoms given and find out solutions to overcome diseases in rubber plants.
Rekomendasi Pemilihan Peserta Lomba Kompetensi Siswa (LKS) Tingkat Kejuruan Dengan Teknik Promethee Andi Sahputra; Eka Irawan; Harly Okprana
Journal of Informatics, Electrical and Electronics Engineering Vol. 1 No. 1 (2021): September 2021
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Participants in the student competency competition (LKS) of the RK Bintang Timur Pematangsiantar Private Vocational School were conducted manually by collecting students, counting and comparing with supporting data such as competency report cards by productive teachers. Therefore the RK Bintang Timur Pematangsiantar Private Vocational School needs to overcome problems in selecting students as participants in the student competency competition to be more effective and on target. The Promethee algorithm is used in order of order or priority in an efficient and simple multi-criteria analysis. Based on the research data sample, the highest score was obtained in alternative A1 with a value of 0.406 with 6 criteria, namely academic value, number of absences, student council scores, attitude, craft and tidiness. Then proceed to the matrix normalization process which produces the outflow, inflow and net flow values ??used in the ranking process
Integrasi Strategi Pre-processing Data untuk Optimalisasi Akurasi Algoritma Backpropagation Widodo Saputra; Saifullah Saifullah; Eka Irawan; Anjar Wanto
Explorer Vol 6 No 2 (2026): July 2026
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/explorer.v6i2.2743

Abstract

Backpropagation is one of the artificial neural network algorithms widely used in classification and prediction processes due to its ability to recognize data patterns accurately. However, the performance of this algorithm is highly influenced by the quality of the input data. Unstructured data, differences in data scales, missing values, and irrelevant features can reduce the model’s accuracy. This study aims to analyze the effect of integrating data pre-processing strategies to optimize the accuracy of the Backpropagation algorithm. The dataset used in this research was obtained from the Badan Pusat Statistik (BPS) in the form of Open Unemployment Rate data for the population aged 15 years and above in North Sumatra Province from 2019 to 2024. The applied pre-processing stages included data cleaning, normalization, missing value handling, and feature reduction. The research method was conducted by comparing the model testing results using standard pre-processing and partial pre-processing on several network architectures. The results showed that the implementation of pre-processing strategies was able to improve the performance of the Backpropagation model. The highest accuracy value was obtained in the 3-56-1 architecture with an increase from 80.00% to 85.88%. In addition to improving accuracy, the model training process became more stable and the error convergence was achieved faster. Therefore, the integration of data pre-processing strategies has proven to be effective in optimizing the accuracy of the Backpropagation algorithm for numerical data-based prediction problems
Optimasi Support Vector Machine Menggunakan Particle Swarm Optimization pada Analisis Sentimen Ulasan Shopee COD Eka Irawan; Wendi Robiansyah; Widodo saputra; Anjar Wanto
Explorer Vol 6 No 2 (2026): July 2026
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/explorer.v6i2.2744

Abstract

The Cash on Delivery (COD) service provided by the Shopee e-commerce platform often elicits a large volume of user reviews that exhibit unconventional language structures, prompting the need for a precise and automated sentiment analysis mechanism. This research endeavor seeks to categorize sentiments expressed in Shopee reviews as either positive or negative by leveraging the Support Vector Machine (SVM) algorithm, which has been fine-tuned using Particle Swarm Optimization (PSO). A key obstacle in text analysis lies in the vast feature space, which can impair model efficacy. Thus, PSO is utilized as a feature selection technique to identify the most pertinent set of terms from the TF-IDF feature extraction. The findings reveal that the integration of PSO successfully decreased feature dimensionality by 45% from the initial set of 1,000 features. Despite the substantial reduction in features, the SVM-PSO model achieved an enhanced accuracy of 81.21%, surpassing the baseline model's 78.79%. With an AUC value of 0.845, it is evident that the model retains stability and effectiveness in discerning sentiment even with a considerably reduced feature set. This investigation illustrates the efficacy of PSO optimization in eliminating extraneous features and refining the model's focus on sentiment-carrying vocabulary.
Co-Authors Agus Perdana Windarto Ali Akhbar Nasution Andi Sahputra Dedi Suhendro Dedi Suhendro Dedy Hartama Dinda Nabila Batubara Eka Desriani Aritonang Fitri Rizki Heru Satria Tambunan Ilham Syahputra Saragih Indah Syahputri Irawan Irawan Irfan Sudahri Damanik Jaya Tata Hardinata M Fauzan M Safii Masduki Nizam Fadli Mawaddah Anjelita Muhammad Ridwan Lubis Muhammad Zarlis Nazira Ayu Ananda Nila Soraya Damanik Nur Afriani Manihuruk Nur Arief Okprana, Harly Saifullah Saifullah Syahyulita Fachri Tanti Bonita Wanto, Anjar Wendi Robiansyah Widodo Saputra