cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Shinta Puspasari
Contact Email
shinta@uigm.ac.id
Phone
+6281541477256
Journal Mail Official
lppm@uigm.ac.id
Editorial Address
Jl. Jend Sudirman No 629 KM 4 Palembang
Location
Kota palembang,
Sumatera selatan
INDONESIA
Jurnal Software Engineering and Computational Intelligence
Published by Universitas Indo Global Mandiri
ISSN : -     EISSN : 29882028     DOI : https://doi.org/10.36982/jseci.v1i1
Core Subject : Science,
Computer Science & IT
Journal of Software Engineering and Computational Intelligence (JSECI) is a scientific journal in software engineering and computational intelligence containing the scientific literature on studies of pure and applied research in informatics and computer sciences, public review of the development of theory, method, and applied sciences related to the subject. The topics covered include but are not limited to: Artificial Intelligence, Computer Vision, Cryptography, Genetic Algorithm, Human-Computer Interaction, Image Processing, Intelligent Home Environments, Machine Learning, Natural Language Processing, Neural Network, Pattern Recognition, Software Engineering (Implementation of Computational Intelligent), Steganography
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 38 Documents
 1   2   3   4 
Perbandingan Naïve Bayes dan SVM terhadap Analisis Sentimen QRIS di Luar Negeri Pambudi, Readysna Krisna; Prasetyo, Zavier Billy; Pribadi, Muhammad Rizky
Jurnal Software Engineering and Computational Intelligence Vol 3 No 02 (2025)
Publisher : Informatics Engineering, Faculty of Computer Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36982/jseci.v3i02.5424

Abstract

Penelitian ini membandingkan algoritma Naïve Bayes dab SVM (Support Vector Machine) dalam analisis sentimen terhadap komentar pengguna TikTok mengenai penggunaan QRIS di luar negeri. Data dikumpulkan dengan data scraping dari komentar TikTok, kemudian melakukan prepocessing text, transformasi TF-IDF, dan penerapan SMOTE. Setiap komentar diberi label secara manual ke dalam kategori positif, negatif, atau netral. Hasil Evaluasi menunjukkan bahwa algoritma SVM menunjukkan hasil yang lebih tinggi dibandingkan algoritma Naïve Bayes dengan accuracy sebesar 62.30%, sedangkan Naïve Bayes 57.40%. Precision SVM sebesar 63.44%, sedangkan Naïve Bayes 62.98%. Recall SVM sebesar 62.30%, sedangkan Naïve Bayes 57.40%. F1-Score SVM sebesar 59.60%, sedangkan Naïve Bayes 51.33%. Dengan demikian algoritma SVM lebih efektif digunakan dalam analisis sentimen dibandingkan algoritma Naïve Bayes.
IMPLEMENTASI DEEP LEARNING UNTUK ANALISIS SENTIMEN PADA DATA X DALAM PREDIKSI TREN KOREAN STYLE Siska Lestari; Hermanto; Dian Hafidh Zulfikar
Jurnal Software Engineering and Computational Intelligence Vol 3 No 02 (2025)
Publisher : Informatics Engineering, Faculty of Computer Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36982/jseci.v3i02.6137

Abstract

This study implements a deep learning model based on Convolutional Neural Network (CNN) for sentiment analysis of Indonesian-language tweets related to the Korean Style trend. A dataset of 7,187 tweets was collected via web crawling using keywords such as “Korean Style”, “K-pop”, and “Korean fashion”. The preprocessing pipeline included case folding, removal of special characters and emojis, stopword elimination, tokenization, and lemmatization. Word2Vec and FastText embeddings were employed for text representation. The CNN model classified tweets into three sentiment categories: positive, negative, and neutral. Evaluation metrics included accuracy, precision, recall, F1-score, and confusion matrix. Results showed 71.26% validation accuracy with the highest F1-score of 0.81 for the neutral class, while negative sentiment classification remained weak due to class imbalance. Word2Vec outperformed FastText in stability. This research contributes to sentiment analysis in Indonesian social media using deep learning and provides insights into public opinion on Korean cultural trends
EfficientNet-Based Flower Recognition with LAB and CLAHE Enhancement Kurniawan, Rudi; Intan, Bunga
Jurnal Software Engineering and Computational Intelligence Vol 3 No 02 (2025)
Publisher : Informatics Engineering, Faculty of Computer Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36982/jseci.v3i02.6197

Abstract

Accurate flower recognition is a challenging task in computer vision due to high intra-class variation, complex background textures, and illumination inconsistencies. This study proposes an enhanced image classification framework integrating LAB color space transformation and Contrast Limited Adaptive Histogram Equalization (CLAHE) with the EfficientNet architecture. The proposed approach aims to improve visual feature separability by enhancing color stability and local contrast prior to network training. Experiments were conducted using a 17-class flower dataset, and the model achieved an overall accuracy of 98.53%, a macro-averaged F1-score of 0.9704, and AUC values close to 1.00 for most species. Visual analysis through the confusion matrix and ROC curves confirmed the model’s robustness, with only minor misclassifications observed between morphologically similar classes such as Iris–Crocus and Daffodil–Tulip. These findings demonstrate that combining LAB and CLAHE preprocessing with EfficientNet significantly enhances model generalization and visual discriminability. The method provides a lightweight yet effective solution for applications in biodiversity monitoring, precision agriculture, and automated plant taxonomy.
Pengaruh Deteksi Tepi Citra Urat Daun Pada Pengenalan Jenis Bibit Jeruk Menggunakan Metode Pengenalan JST-PB dan GLCM Dimas Apriandi; Gasim; Muhammad Haviz Irfani; Muhammad Ikhwan Jambak
Jurnal Software Engineering and Computational Intelligence Vol 3 No 02 (2025)
Publisher : Informatics Engineering, Faculty of Computer Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36982/jseci.v3i02.6219

Abstract

Identifikasi awal jenis bibit jeruk sangat penting untuk menjamin kualitas bibit dan meningkatkan produktivitas pertanian. Identifikasi secara manual membutuhkan keahlian khusus dan rentan terhadap kesalahan. Penelitian ini bertujuan untuk menganalisis pengaruh metode deteksi tepi terhadap akurasi klasifikasi bibit jeruk menggunakan Jaringan Syaraf Tiruan Propagasi Balik (JST-PB) dan fitur tekstur yang diekstraksi dengan Gray Level Co-occurrence Matrix (GLCM). Tiga metode deteksi tepi yaitu Canny, Laplacian of Gaussian (LoG), dan Roberts yang diterapkan pada citra daun jeruk dari empat varietas antara lain: Kunci, Nipis, Purut, dan Sambal. Fitur tekstur berupa contrast, correlation, homogeneity, dan entropy digunakan sebagai masukan dalam pelatihan JST-PB. Hasil penelitian menunjukkan bahwa metode Roberts dengan 30 neuron tersembunyi memberikan kinerja terbaik dengan precision rata-rata 75,56%, recall 75,00%, dan F1-score 74,97%. Hal ini menunjukkan bahwa pemilihan metode deteksi tepi berpengaruh signifikan terhadap akurasi klasifikasi. Kombinasi metode deteksi tepi Roberts, ekstraksi fitur GLCM, dan JST-PB terbukti efektif untuk pengenalan otomatis jenis bibit jeruk berbasis citra digital.    
Evaluasi Pengalaman Pengguna Aplikasi e-Dempo Samsat Sumatera Selatan menggunakan Metode UEQ-S Junitu, Zebri; Sulpin Agung Saputra, Muhammad; Ayonda Saputra, Licka; Permatasari, Indah
Jurnal Software Engineering and Computational Intelligence Vol 3 No 02 (2025)
Publisher : Informatics Engineering, Faculty of Computer Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36982/jseci.v3i02.6297

Abstract

Aplikasi e-Dempo merupakan inovasi layanan publik digital unggulan dari Samsat Sumatera Selatan yang bertujuan mempermudah masyarakat dalam melakukan pembayaran pajak kendaraan bermotor secara daring, guna meningkatkan efisiensi dan aksesibilitas layanan publik. Meskipun menawarkan kemudahan waktu dan proses, evaluasi mendalam terhadap pengalaman pengguna (User Experience) sangat diperlukan untuk memastikan layanan yang diberikan benar-benar sesuai dengan ekspektasi serta kenyamanan masyarakat pengguna. Penelitian ini bertujuan untuk mengevaluasi pengalaman pengguna aplikasi e-Dempo menggunakan metode Short User Experience Questionnaire (UEQ-S). Penelitian ini menggunakan pendekatan kuantitatif deskriptif dengan melibatkan 31 responden yang dipilih melalui teknik purposive sampling. Analisis data dilakukan untuk mengukur dua dimensi utama pengalaman pengguna: Kualitas Pragmatis (efisiensi, kejelasan) dan Kualitas Hedonis (stimulasi, kebaruan). Hasil analisis menunjukkan bahwa aplikasi e-Dempo memiliki kinerja keseluruhan yang positif dengan skor rata-rata 0,933. Secara spesifik, aplikasi ini sangat unggul pada dimensi Kualitas Pragmatis dengan skor 0,933, yang menandakan fungsinya sangat efisien, mudah dipelajari, dan efektif dalam membantu pengguna menyelesaikan tugas. Namun, dimensi Kualitas Hedonis memperoleh skor yang lebih rendah yaitu 0,633 (kategori netral), mengindikasikan bahwa aspek desain antarmuka, daya tarik visual, dan inovasi aplikasi masih perlu ditingkatkan karena dianggap standar dan kurang menggugah secara emosional. Berdasarkan temuan ini, penelitian merekomendasikan perbaikan strategis pada desain visual antarmuka dan penambahan fitur interaktif untuk meningkatkan kepuasan pengguna tanpa mengurangi fungsionalitas utama yang sudah berjalan baik.
Perancangan Robot Penyiraman pada Tanaman Tomat Beef (Lycopersicum esculentum Mill) menggunakan Metode Forward Chaining Baginda siregar; Daren Sulistio
Jurnal Software Engineering and Computational Intelligence Vol 4 No 01 (2026)
Publisher : Informatics Engineering, Faculty of Computer Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36982/jseci.v4i01.6808

Abstract

Plants, especially tomatoes, have high economic value and require regular maintenance, especially watering, to maintain optimal growth. This study developed an automatic tomato plant watering robot named "Farmbot" based on the forward chaining method, which allows for intelligent monitoring and regulation of water needs. The application of forward chaining as a rule-based expert system simplifies decision-making in watering, and this tool has the potential to be applied to other plants by reconfiguring environmental parameters. This study was conducted to prove the reliability of the forward chaining method in the process of designing a plant watering robot. The main microcontroller used in this study is the NodeMCU ESP32, then for the input device uses a soil moisture sensor to generate humidity data and a DS18B20 temperature sensor to generate temperature data on the soil. Various facts and rules are used to control the movement and watering process on the Farmbot robot. The results of this study show that the accuracy of the forward chaining method is 75.472% which is a good result and is not far from the fuzzy logic method which produces an MAE value of 4.5535 and has an accuracy value in the range of 92.149%. From these results, it can be concluded that the forward chaining method can be relied upon as a method for designing watering robots.
Sistem E-Cuti Berbasis Website Berbasis Intelligent System untuk Meningkatkan Efisiensi Administrasi Sekolah Akhsani Taqwiym; Nurussama
Jurnal Software Engineering and Computational Intelligence Vol 4 No 01 (2026)
Publisher : Informatics Engineering, Faculty of Computer Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36982/jseci.v4i01.7073

Abstract

Leave administration management in elementary schools is still largely conducted manually, resulting in various issues such as unstructured documentation, difficulties in data retrieval, and delays in the approval process. This study aims to design and develop a web-based e-leave application to improve the efficiency and effectiveness of leave management for teaching staff. The system was developed using the Waterfall method, which consists of requirement analysis, system design, implementation, and testing stages. Data collection was carried out through observation, interviews, and documentation to understand the existing system. The results show that the developed e-leave application successfully integrates the entire leave submission process into a structured digital system. The system provides key features such as user authentication, teacher data management, department and position management, leave variables, as well as leave submission and monitoring. System testing was conducted using the Black Box Testing method, and the results indicate that all system functions operate correctly without any errors. The implementation of this system has a positive impact on improving administrative efficiency, accelerating the leave submission and approval process, and enhancing data accuracy and transparency. Therefore, the web-based e-leave application can serve as an effective solution to support digital transformation in educational administration.
Prediksi Saham IHSG Menggunakan Extreme Gradient Boosting, Support Vector Machine, K-Nearest Neighbors Dan Autoregressive Integrated Moving Average Renaldy Pratama; Shinta Puspasari; Muhammad Haviz Irfani
Jurnal Software Engineering and Computational Intelligence Vol 4 No 01 (2026)
Publisher : Informatics Engineering, Faculty of Computer Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36982/jseci.v4i01.7141

Abstract

The Jakarta Composite Index (JCI) is a key indicator in assessing the performance of the Indonesian capital market. Dynamic stock price fluctuations require accurate prediction methods to assist investors in decision making. This study aims to compare the performance of four prediction algorithms, namely Support Vector Machine (SVM), K-Nearest Neighbors (K-NN), Extreme Gradient Boosting (XGBoost), and Autoregressive Integrated Moving Average (ARIMA) in predicting the closing price of JCI. The data used is the JCI daily historical data for the 2019-2024 period obtained from Yahoo Finance. The research process includes data pre-processing, prediction model implementation, model training and testing, and performance evaluation using Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) metrics on a 0-1 normalization scale.The results showed that the ARIMA model provided the most stable results with an RMSE value of 0.4038 and MAE of 0.3945, followed by K-NN and SVM. Although SVM has the lowest MAE value, its RMSE is still higher than ARIMA and K-NN. SVM showed the lowest performance in this experiment. Based on the evaluation results, ARIMA is recommended as the best algorithm in predicting JCI closing price based on historical data. The Jakarta Composite Index (JCI) is a key indicator in assessing the performance of the Indonesian capital market. Dynamic stock price fluctuations require accurate prediction methods to assist investors in decision making. This study aims to compare the performance of four prediction algorithms, namely Support Vector Machine (SVM), K-Nearest Neighbors (K-NN), Extreme Gradient Boosting (XGBoost), and Autoregressive Integrated Moving Average (ARIMA) in predicting the closing price of JCI. The data used is the JCI daily historical data for the 2019-2024 period obtained from Yahoo Finance. The research process includes data pre-processing, prediction model implementation, model training and testing, and performance evaluation using Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) metrics on a 0-1 normalization scale.The results showed that the ARIMA model provided the most stable results with an RMSE value of 0.4038 and MAE of 0.3945, followed by K-NN and SVM. Although SVM has the lowest MAE value, its RMSE is still higher than ARIMA and K-NN. SVM showed the lowest performance in this experiment. Based on the evaluation results, ARIMA is recommended as the best algorithm in predicting JCI closing price based on historical data.

Page 4 of 4 | Total Record : 38

 1   2   3   4 

Filter by Year

2023 2026


Reset
Filter By Issues
All Issue Vol 4 No 01 (2026) Vol 3 No 02 (2025) Vol 3 No 01 (2025) Vol 2 No 02 (2024) Vol 2 No 01 (2024) Vol 1 No 2 (2023) Vol 1 No 1 (2023)