cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
jieet@unesa.ac.id
Editorial Address
Jurusan Teknik Informatika, Fakultas Teknik Universitas Negeri Surabaya Kampus Ketintang, Gedung A10, lt.2, Surabaya-Indonesia, 60231.
Location
Kota surabaya,
Jawa timur
INDONESIA
JIEET (Journal of Information Engineering and Educational Technology)
Published by Universitas Negeri Surabaya
ISSN : -     EISSN : 2549869X     DOI : http://dx.doi.org/10.26740/
Core Subject : Science, Engineering,
Computer Science & IT Engineering
Journal Description: JIEET (Journal of Information Engineering and Educational Technology) is a scientific journal that publishes the peer-reviewed research papers in the field of Computer Engineering, Distributed and Parallel Systems, Business Informatics, Computer Science, Computer Security, System & Software Engineering and Educational Technology.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 230 Documents
 19   20   21   22   23 
Batik Sketch Coloring Using Generative Adversarial Network Pix2pix Abdilqoyyim, Fanky; Muhammad Ali Syakur; Fitri Damayanti
JIEET (Journal of Information Engineering and Educational Technology) Vol. 9 No. 2 (2025)
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jieet.v9n2.p113-128

Abstract

Batik, an Indonesian cultural heritage recognized by UNESCO, involves a complex and time-consuming coloring process. Digitalization offers a crucial solution for the preservation and development of batik art in the modern era. This research implements a Generative Adversarial Network (GAN), specifically the Pix2Pix model, to automate the transformation of batik sketches into colored images. The primary focus is a performance comparison between the U-Net generator architecture, which excels at preserving spatial details via skip-connections, and the ResNet architecture, which is capable of learning deeper and more complex features. This study utilized 1164 paired images, divided into 931 training, 117 validation, and 116 test data points. The models were trained with consistent hyperparameters, including an Adam optimizer and a combination of L1 and binary cross-entropy loss functions, with evaluations at 50 and 100 epochs. Quantitative evaluation was performed using Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Fréchet Inception Distance (FID) metrics. The results indicate that the model with the ResNet generator trained for 100 epochs achieved the most balanced and superior performance, with a PSNR of 8.11, SSIM of 0.39, and an FID of 120.72. Overall, the ResNet generator proved more capable of producing realistic and high-quality colored batik images, offering an innovative solution to enhance the efficiency of the coloring process while supporting cultural preservation.
Forecasting Light Rail Transit Passenger Demand Using Parameter-Tuned Exponential Smoothing Models Gustriansyah, Rendra; Puspasari, Shinta; Sanmorino, Ahmad; Suhandi, Nazori
JIEET (Journal of Information Engineering and Educational Technology) Vol. 9 No. 2 (2025)
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jieet.v9n2.p101-112

Abstract

Accurate passenger demand forecasting is essential for optimizing the operational efficiency and sustainability of urban rail systems. This study aims to forecast monthly passenger numbers in the Palembang Light Rail Transit (LRT) system using optimized Exponential Smoothing (ES) models with parameter tuning for improved predictive accuracy. Three variants of the ES method are examined: Simple Exponential Smoothing (SES), Double Exponential Smoothing (DES), and Brown's Exponential Smoothing (BES). Furthermore, Seasonal ARIMA (SARIMA) is used as a benchmark to evaluate whether simpler ES models can match or outperform complex statistical approaches. Data from August 2018 to December 2023 are analyzed and split into training and testing sets (ratio 80:20). Model performance is evaluated using Mean Absolute Percentage Error (MAPE), Diebold–Mariano (DM), and Ljung–Box Q (LBQ) tests. The results show that the SES model with a smoothing parameter α = 0.9 achieves the best forecasting accuracy on the test data (MAPE = 8.6%), outperforming other ES variants and previous SARIMA-based models. These findings highlight that simpler ES-based models can effectively capture short-term transportation demand patterns in developing urban transit systems. Practically, the results of this study can provide valuable insights for LRT operators and municipal planners in designing responsive, data-driven operational strategies.
Expert System For Corn Plant Disease Diagnosis Using Hybrid Fuzzy Tsukamoto And Naive Bayes Method Kartika Imam Santoso; Eko Supriyadi; Andri Triyono; Dhika Malita Puspita
JIEET (Journal of Information Engineering and Educational Technology) Vol. 9 No. 2 (2025)
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jieet.v9n2.p141-155

Abstract

Corn is a strategic food commodity in Indonesia, with production of 22.44 million tons in 2023. However, disease attacks can cause productivity declines of up to 30-80%, mainly from downy mildew, leaf rust, and leaf spot. The limited number of pathology experts in the field leads to delayed diagnosis, resulting in significant economic losses for farmers. This research aims to develop an expert system for diagnosing corn plant diseases using a hybrid Fuzzy Tsukamoto and Naive Bayes method to enhance diagnosis accuracy, taking into account uncertainty in symptom severity levels. The system was developed using Durkin's Expert System Development Life Cycle (ESDLC), which consists of six phases. A knowledge base was built from SINTA and Scopus-indexed literature, identifying five diseases and 17 symptoms. The fuzzy Tsukamoto method was employed for the fuzzification of symptom severity, utilizing three membership functions (intensity, coverage, and severity), after which Naive Bayes calculated the posterior probability. The hybrid score was calculated with 40% Fuzzy and 60% Bayes weights. The system was successfully developed with an interactive web interface. Accuracy testing using 30 validation cases yielded an accuracy of 86.67%, with 85% sensitivity and 88% specificity. Expert testing by three plant pathology experts gave excellent ratings (average 4.6/5.0) for diagnosis accuracy, knowledge base completeness, and usability aspects. The hybrid Fuzzy Tsukamoto and Naive Bayes method is effective for diagnosing corn plant diseases, achieving 86.67% accuracy, which is 6.67% higher than the Certainty Factor method and 11.67% higher than the single Naive Bayes method. This system can help farmers perform early diagnosis and reduce dependence on experts.
Predicting Software Sales Performance Using Support Vector Regression (SVR) and Linear Regression Algorithms : A Comparative Study on Machine Learning Approaches for Sales Forecasting Muhammad Athallah Rafi; Alvin Adam Anton Suryadarma; Hazbie Alfarhizi Syahwadana; Aji Setiawan
JIEET (Journal of Information Engineering and Educational Technology) Vol. 9 No. 2 (2025)
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jieet.v9n2.p80-88

Abstract

Software has become an essential part of everyday life, both in the workplace and in education. Various applications such as Microsoft Office and Google Workspace are widely used to enhance productivity. As public demand for digital solutions continues to rise, software distribution through global platforms such as Amazon has also seen significant growth. However, not all software products are able to achieve high sales figures due to the lack of effective strategies in understanding consumer behavior and market demands. Therefore, accurate sales prediction plays a crucial role in supporting successful software marketing strategies.   This study aims to predict the best-selling software on Amazon by applying two algorithms: Linear Regression and Support Vector Regression (SVR). Before implementing these algorithms, several stages were conducted, including identifying the research object, preprocessing the data—where the original dataset consisting of 2,424 rows was reduced to 1,338 rows—followed by splitting the dataset into 80% training, 10% validation, and 10% testing sets. The final stage involved developing and comparing prediction models using both the Linear Regression and SVR algorithms. The results of this study are expected to contribute to determining the most suitable algorithm for predicting software sales and to serve as a reference for future research in this field
A Hybrid Clustering–Classification Framework for SMEs Success Level Prediction Saputra, Andika Dermawan; Yustanti, Wiyli
JIEET (Journal of Information Engineering and Educational Technology) Vol. 9 No. 2 (2025)
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jieet.v9n2.p89-100

Abstract

Micro, Small, and Medium Enterprises (SMEs) are vital to economic growth, yet their complex success determinants necessitate advanced predictive modeling. This study proposes a hybrid clustering-classification framework to classify and predict SME success levels based on 22 multidimensional indicators, including financial literacy, FinTech adoption, and entrepreneurial resilience. K-Means clustering was first applied to the survey data, yielding three optimal success personas, validated by the highest Silhouette Score (0.5238). These clusters were labeled with Beginner and Conventional, Stable Digital Adopter, and Digital Innovator SMEs. These empirically derived clusters served as pseudo-labels for the classification stage. Classification algorithms were tested with and without the Synthetic Minority Oversampling Technique (SMOTE). While ensemble methods (Random Forest, LightGBM) and SVM performed well, the K-Nearest Neighbors (KNN) algorithm consistently outperformed all others, achieving the highest F1-Score (0.9324) under SMOTE implementation. The findings validate the effectiveness of the hybrid clustering-classification approach in accurately mapping and predicting SME success levels. The resulting model serves as a robust, data-driven tool for policymakers to guide targeted interventions and digital training programs, fostering sustainable SME development.
MD-ViT: Multidomain Vision Transformer Fusion for Fair Demographic Attribute Recognition Putri, Rezky Arisanti; Putra, Ricky Eka; Yamasari, Yuni
JIEET (Journal of Information Engineering and Educational Technology) Vol. 9 No. 2 (2025)
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jieet.v9n2.p64-79

Abstract

Demographic attribute recognition particularly race and gender classification from facial images, plays a critical role in applications ranging from precision healthcare to digital identity systems. However, existing deep learning approaches often suffer from algorithmic bias and limited robustness, especially when trained on imbalanced or non-representative data. To address these challenges, this study proposes MD-ViT, a novel framework that leverages multidomain Vision Transformer (ViT) fusion to enhance both accuracy and fairness in demographic classification. Specifically, we integrate embeddings from two task-specific pretrained ViTs: ViT-VGGFace (fine-tuned on VGGFace2 for structural identity features) and ViT-Face Age (trained on UTKFace and IMDB-WIKI for age-related morphological cues), followed by classification using XGBoost to model complex feature interactions while mitigating overfitting. Evaluated on the balanced DemogPairs dataset (10,800 images across six intersectional subgroups), our approach achieves 89.07% accuracy and 89.06% F1-score, outperforming single-domain baselines (ViT-VGGFace: 88.61%; ViT-Age: 78.94%). Crucially, fairness analysis reveals minimal performance disparity across subgroups (F1-score range: 87.38%–91.03%; σ = 1.33), indicating effective mitigation of intersectional bias. These results demonstrate that cross-task feature fusion can yield representations that are not only more discriminative but also more equitable. We conclude that MD-ViT offers a principled, modular, and ethically grounded pathway toward fairer soft biometric systems, particularly in high-stakes domains such as digital health and inclusive access control.
A Performance Comparison of LSTM and GRU Architectures for Forecasting Daily Bitcoin Price Volatility Nafisah, Nurun; Yamasari, Yuni; Yohannes, Ervin
JIEET (Journal of Information Engineering and Educational Technology) Vol. 9 No. 2 (2025)
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jieet.v9n2.p156-167

Abstract

The highly volatile movement of Bitcoin prices necessitates the use of prediction methods capable of accurately capturing complex and rapidly changing patterns. This study aims to compare the performance of two recurrent neural network architectures, namely Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), in forecasting Bitcoin prices based on historical time series data. The analysis was conducted using daily closing price data, with several parameter configurations applied, including dropout value, learning rate, and number of epochs at a window size of 30. The training process was carried out using a univariate approach to assess the fundamental ability of each model to learn temporal patterns without the influence of external variables. The results indicate that the GRU model consistently outperforms LSTM across most experimental settings. The best performance was achieved with 30 epochs, dropout 0.1, and a learning rate of 0.001, producing RMSE 1478.333, MAE 1000.900, R² 0.996081, and MAPE 1.973072. These metrics demonstrate a lower error level and a stronger fit to actual Bitcoin price movements. Moreover, a paired t-test confirmed that the performance gap between the two models is statistically significant. Overall, the findings suggest that the Gated Recurrent Unit architecture is more efficient in capturing nonlinear patterns and responding to the volatile dynamics of cryptocurrency price fluctuations, making it a promising approach for future predictive modeling in financial time series.
Homomorphically Encrypted Evaluation of The Autoregressive Component of an ARIMA Model Rini Deviani; Dini Handayani
JIEET (Journal of Information Engineering and Educational Technology) Vol. 10 No. 01 (2026)
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jieet.v10n01.p1-13

Abstract

Across domains like healthcare, finance and environmental monitoring time series forecasting has many applications and often deals with sensitive data. Although ARIMA models are popular due to high interpretability and accuracy and the basic form of ARIMA does not need a large amount of data for modeling, it requires plaintext data access which raises problems in cloud computing with privacy. Homomorphically Evaluating the Autoregressive Component of ARIMA for Privacy-Preserving Forecasting through CKKS-based Fully Homomorphic Encryption (FHE) in the TenSEAL library A temperature dataset was used to train an ARIMA(2,1,1) model with the autoregressive coefficients in plaintext and more specifically, as part of plaintext and encrypted workflows. The CKKS Model Recent observations were encrypted with CKKS thus allowing forecasting on ciphertext without ever exposing the data. The outcomes indicate, that the prediction using ciphertext matched pretty well to the one with plaintext and had an absolute error of 0.000001 along with accuracy of 99.995%. Our findings validate that not only does CKKS-based FHE retain forecasting accuracy in a secure manner and enable the combination of FHE with classical forecasting models, but also gives rise to future work on encrypted ARIMA modelling, multivariate forecasting as well as privacy-preserving machine learning.
DETECTION OF TOBACCO LEAF QUALITY USING THE YOLOv11 ALGORITHM suwarno arieska; I Gusti Putu Asto Buditjahjanto; Wiyli Yustanti
JIEET (Journal of Information Engineering and Educational Technology) Vol. 10 No. 01 (2026)
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jieet.v10n01.p26-38

Abstract

Accurate and efficient detection of tobacco quality is essential to identify the quality of tobacco leaves and improve farmers' tobacco yields. However, due to the high similarity between classes, significant intraclass differences and complex backgrounds among different tobacco leaves, accurately identifying tobacco quality through neural network models can pose significant challenges. To address this problem, this paper is presented with a fast and accurate method of detecting and identifying tobacco leaf quality using YOLO (You Only Look Once). This model uses YOLOv11 which incorporates an efficient detection head designed to detect the characteristics of tobacco leaves. In addition, an in-depth surveillance layer is introduced into the network along with incorporating and enhancing dynamic upsampling modules. Experimental data include public data sets of L1L, L2L, L3L, L3R, L4R, L10, L10F, and LND tobacco leaf quality. The results of the experiment showed that Yolov11 outperformed the Yolov8 and Yolov12 algorithms with a precision of 0.853, an F1 score of 0.73 mAP@0.5, 0.811 and mAP@0.5:0.95 of 0.631.
Performance Analysis YOLO11n Model for Chili Leaf Diseases Detection Rayyan Nur Fauzan; Ervin Yohannes; Ricky Eka Putra; Avirmed Enkhbat
JIEET (Journal of Information Engineering and Educational Technology) Vol. 10 No. 01 (2026)
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jieet.v10n01.p14-25

Abstract

Chili plants are a strategic agricultural commodity with high economic value, yet their production is often disrupted by disease attacks causing significant yield reduction. Early and accurate detection of chili leaf diseases is crucial for implementing precision agriculture practices. This research implements the YOLO11n (You Only Look Once version 11 nano) model for automated chili leaf disease detection using the "Chili Plant Leaf Disease and Growth Stage Dataset from Bangladesh" containing 1,856 high-resolution images across six categories: Bacterial Spot, Cercospora Leaf Spot, Curl Virus, Healthy Leaf, Nutrition Deficiency, and White Spot. The model was trained for 100 epochs on Google Colab with Tesla T4 GPU using 640×640 pixel input resolution. Evaluation results demonstrate excellent detection performance with precision of 83.7%, recall of 84.3%, mAP@0.5 of 92.3%, and mAP@0.5:0.95 of 74.5%. Per-class analysis reveals that Nutrition Deficiency achieved the highest performance (mAP@0.5 = 99.2%), while Curl Virus presented the greatest detection challenge (recall = 55.6%). The lightweight YOLO11n architecture with only 2.58 million parameters and 6.3 GFLOPs, making it highly suitable for deployment on edge devices such as agricultural drones, mobile applications, and IoT monitoring systems. This research contributes to smart agriculture applications by providing an efficient and accurate solution for automated chili leaf disease detection under real field conditions.

Page 23 of 23 | Total Record : 230

 19   20   21   22   23 

Filter by Year

2017 2026


Reset
Filter By Issues
All Issue Vol. 10 No. 01 (2026) Vol. 9 No. 2 (2025) Vol. 9 No. 1 (2025) Vol. 8 No. 2 (2024) Vol. 8 No. 1 (2024) Vol. 7 No. 2 (2023) Vol. 7 No. 1 (2023) Vol. 6 No. 2 (2022) Vol. 6 No. 1 (2022) Vol. 5 No. 2 (2021) Vol. 5 No. 1 (2021) Vol 5, No 1 (2021) Vol. 4 No. 2 (2020) Vol 4, No 2 (2020) Vol 4, No 1 (2020) Vol. 4 No. 1 (2020) Vol 3, No 2 (2019) Vol. 3 No. 2 (2019) Vol. 3 No. 1 (2019) Vol 3, No 1 (2019) Vol 2, No 2 (2018) Vol. 2 No. 2 (2018) Vol 2, No 1 (2018) Vol. 2 No. 1 (2018) Vol. 1 No. 2 (2017) Vol 1, No 2 (2017) Vol 1, No 1 (2017) Vol. 1 No. 1 (2017) More Issue