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
-
Editorial Address
-
Location
Kota medan,
Sumatera utara
INDONESIA
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING
Published by Universitas Medan Area
ISSN : 25496247     EISSN : 25496255     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Engineering
JURNAL TEKNIK INFORMATIKA, JITE (Journal of Informatics and Telecommunication Engineering) is a journal that contains articles / publications and research results of scientific work related to the field of science of Informatics Engineering such as Software Engineering, Database, Data Mining, Network, Telecommunication and Artificial Intelligence which published and managed by the Faculty of Informatics Engineering at the University of Medan Area .
Arjuna Subject : -
Articles 412 Documents
 38   39   40   41   42 
Efficient Real and Fake Face detection Using ResNet18 Putri Prasetia, Cintia
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol. 9 No. 1 (2025): Issues July 2025
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v9i1.15128

Abstract

This study aims to develop a classification model for distinguishing between real and fake facial images using a lightweight Convolutional Neural Network architecture, specifically ResNet18. The research addresses the growing misuse of synthetic facial images in biometric security systems and identity verification processes. A combined dataset was used, consisting of secondary data from the 140K Real and Fake Faces dataset on Kaggle and primary images captured via a local camera. Preprocessing steps included resizing all images to 128×128 pixels, horizontal flipping, and normalization. The model was trained for five epochs using the FastAI framework with the one-cycle learning rate strategy. The experimental results show that the ResNet18 model achieved a test accuracy of 92.1%, with balanced precision, recall, and F1-score across both classes. Evaluation metrics were supported by a classification report and confusion matrix. The model contains 11.7 million parameters and completed training in approximately 9 minutes and 42 seconds, indicating its computational efficiency on a T4 GPU environment. While the study referenced deeper architectures such as ResNet34 and ResNet50 for context, no direct comparative experiments were conducted. Therefore, conclusions regarding relative performance are limited to the reported metrics of ResNet18 alone. The findings support the feasibility of deploying ResNet18-based models for real-time facial image classification in resource-constrained environments. Future research is encouraged to explore architecture comparisons, more advanced augmentation techniques, and evaluation using video-based inputs for improved generalization
Development of an IoT-Controlled Automatic Air Fryer with Real-Time Monitoring via Blynk Arya Sakti; Irma Salamah; Ali Nurdin
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol. 9 No. 1 (2025): Issues July 2025
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v9i1.15164

Abstract

The purpose of this study is to develop a prototype of an Internet of Things (IoT)-based automatic air fryer with a timer feature, which allows users to control and monitor the device remotely through the Blynk application. This system utilizes hot air circulation from heating elements and mechanical fans for the cooking process without using large amounts of oil. The methods used include hardware and software design, as well as testing the function of the ESP32-based control system. The main components in the system include a MAX6675 temperature sensor, an ESP32 microcontroller, a solid state relay (SSR), an MK2P relay, and the Blynk application as a user interface. The test results show that the system is able to automatically regulate the temperature and cooking time and provide a fast response via a Wi-Fi network. This study contributes to the development of an IoT-based control system for kitchen appliances, with a focus on the efficiency of remote control and monitoring. Evaluation of cooking quality is not the scope of this study and is recommended as an agenda for further study.
Detection of Chicken Egg Quality with Digital Image using EfficientNet-B7 Vincent; Pasaribu, Hendra Handoko Syahputra; Audrey, Wilbert; Jefanya Alexander Meidi Bangun; Deryck Ethan Hong
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol. 9 No. 1 (2025): Issues July 2025
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v9i1.15233

Abstract

Chicken eggs are one of the staple food ingredients in Indonesia, playing a vital role in fulfilling the nutritional needs of the community. Therefore, an efficient, accurate, and reliable method for assessing egg quality is essential, especially to support the distribution process in the food industry. This study aims to develop a digital image-based classification system for assessing the quality of chicken eggs using deep learning methods with the EfficientNet-B7 architecture. EfficientNet-B7 was selected for its proven high accuracy in image classification tasks through the application of compound scaling, which simultaneously optimizes depth, width, and resolution. The dataset used in this study combines images collected from public sources and primary documentation, representing various conditions commonly found in chicken eggs. The preprocessing stage involved trimming techniques to focus on the egg object, followed by data augmentation using ImageDataGenerator, including rotation, shifting, zooming, and flipping to enhance dataset diversity. Model training was carried out with the early stopping technique to prevent overfitting. The experimental results showed that the model achieved an accuracy of 98.08% in classifying egg quality based on shell condition and other visual indicators. These findings demonstrate that the implementation of the EfficientNet-B7 model has great potential to support the automation of chicken egg quality assessment processes in a faster and more consistent manner. Thus, this research is expected to contribute to improving the efficiency of the food industry, particularly in the distribution process of chicken eggs in Indonesia.
Comparative Analysis Using Xception and MobileNetV2 Deep Learning Models for Brain Tumor Detection in MRI Images Mumtaazah, Muhammad Athar; Anik Nur Handayani
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol. 9 No. 1 (2025): Issues July 2025
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v9i1.15332

Abstract

This study presents a comparative analysis of two deep learning models, Xception and MobileNetV2, for brain tumor detection using MRI images. The selection of these models is based on their respective advantages. Xception is known for its ability to handle large and complex datasets due to its deep architecture and the use of depthwise separable convolutions. It also features a deep structure capable of extracting complex features from high-resolution images, making it well-suited for detailed image recognition tasks. In contrast, MobileNetV2 is designed to be lighter and more computationally efficient, making it ideal for deployment on mobile devices or in resource-constrained environments without significantly compromising performance. These characteristics make both models highly relevant for medical image analysis, particularly in brain tumor detection, which demands both accuracy and efficiency.This study uses a public dataset that has been preprocessed through augmentation and normalization. Both models were trained and evaluated using accuracy, loss, and confusion matrix metrics. The results show that MobileNetV2 achieved higher accuracy (97.8%) compared to Xception (94.9%) with a lower error rate. For precision, recall, and F1-score metrics, the results were identical up to four decimal places, further supporting that MobileNetV2 is more suitable for brain tumor detection in resource-limited settings. Based on the findings, MobileNetV2 demonstrates superior performance compared to Xception, making it the favorable choice.
Port Risk Mitigation with FMEA Method on Port Operational Information System at PT. Pelindo (Persero) Sibolga Branch: Case Study at Port of Sibolga Novita Jambak, Indah; Kurniawan R, Rakhmat
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol. 9 No. 1 (2025): Issues July 2025
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v9i1.15400

Abstract

Port operations face challenges in the form of potential risks such as delays in data recording, data inconsistencies between units, and lack of system integration that can hinder logistics distribution. This study identified 20 potential operational risks using the Failure Mode and Effect Analysis (FMEA) method to help map mitigation priorities through the calculation of the Risk Priority Number (RPN). The results of the risk mapping were used as a basis for designing the functional requirements of a web-based port operational information system. The system was developed using PHP, Laravel, and MySQL to support structured recording of loading and unloading activities, ship scheduling, and logistics monitoring. Although the RPN values were used to understand risk priorities, they did not directly determine the system features. Instead, the risk analysis served to provide an overall understanding for designing a system that better matches operational needs. The validation of system benefits at this stage remains conceptual, and future implementation is needed to test its effectiveness in actual port operations.
Implementation of 4-Directional Depth First Search and Projection Profile for Javanese Manuscript Image Segmentation Indraputra, Gerardus Kristha; Anastasia Rita Widiarti
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol. 9 No. 1 (2025): Issues July 2025
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v9i1.15433

Abstract

One of the key steps in digitizing Javanese manuscripts is image segmentation, which separates elements such as lines and characters. This study evaluates the Projection Profile and Four-Directional Depth-First Search (4-Directional DFS) methods for segmenting handwritten Javanese script. The Projection Profile method is used for line segmentation, while 4-Directional DFS identifies interconnected pixels for character segmentation. A total of 20 scanned images were randomly selected from Serat Pratanda and Serat Primbon Reracikan Jampi Jawi. After grayscale conversion and binarization, each image underwent two treatments: with and without advanced preprocessing, before segmentation. Results showed that line segmentation achieved 100% accuracy in both treatments. Character segmentation reached 91.02% accuracy with advanced preprocessing and 84.28% without it. Segmentation errors were mainly caused by over-segmentation and under-segmentation. These results demonstrate that the Projection Profile and 4-Directional DFS methods are effective in segmenting handwritten Javanese manuscripts. They show promise for supporting future developments in automatic Javanese script transliteration.
Enhancing Visibility in Low-Illumination Street Images Using HE, AHE, and CLAHE Techniques Putra Pratama, Fernandous; Anastasia Rita Widiarti
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol. 9 No. 1 (2025): Issues July 2025
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v9i1.15451

Abstract

Low-quality images, such as those resulting from digital capture under low-light conditions, present a significant challenge in the field of digital image processing. This study aims to enhance image visual quality using three contrast enhancement methods: Histogram Equalization (HE), Adaptive Histogram Equalization (AHE), and Contrast Limited Adaptive Histogram Equalization (CLAHE). The dataset consists of 110 grayscale-converted street images captured under various lighting conditions (morning, noon, night, rainy, and clear weather). Evaluation was conducted using objective metrics, including Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), execution time, and subjective assessment from 35 respondents. The results show that CLAHE consistently produces the best visual quality, achieving the highest PSNR of 12.93 dB and the lowest MSE of 3310.28 on a 32×32 grid, with an average execution time of 2–25 seconds. In comparison, HE recorded the lowest PSNR of 8.07 dB and the highest MSE of 10119.23, but had the fastest runtime of 0.3–0.4 seconds. AHE had the longest processing time, reaching up to 103 seconds, with inconsistent output quality. Based on user preference, 65% of respondents favored AHE, despite CLAHE being objectively superior. This study confirms CLAHE as the most effective method for enhancing image quality under extreme lighting conditions without sacrificing important visual details.
Sentiment Analysis to Evaluate Public Service Perception among Surakarta City Residents Using the BiLSTM Model setiawan, very dwi; Dwi Utai Iswavigra
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol. 9 No. 1 (2025): Issues July 2025
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v9i1.15498

Abstract

The growing use of social media as a platform for public communication has opened new opportunities for understanding public opinion regarding government policies, including public services. One of the cities actively discussed on social media is Surakarta, where citizens openly express both appreciation and criticism of local government performance. This study aims to analyze public sentiment toward public services in Surakarta by employing a deep learning-based sentiment analysis approach, specifically using the Bidirectional Long Short-Term Memory (BiLSTM) model. Data were collected from Twitter/X using a web crawling technique with the keywords “pemerintah solo” (Solo government), “kota Surakarta” (Surakarta city), and “kota solo” (Solo city), resulting in 2,168 tweets. The analysis process involved several stages, including preprocessing, sentiment labeling using a lexicon-based method, feature representation with Word2Vec, and classification using five models: SVM, Random Forest, CNN, LSTM, and BiLSTM. The evaluation results show that BiLSTM achieved the best performance with an accuracy of 90.21%, precision of 91.05%, recall of 89.84%, and F1-score of 90.43%. The conclusion of this study is that BiLSTM can effectively classify public sentiment toward public services, especially in the context of informal social media texts. The implication of this research indicates that sentiment analysis can serve as a decision-support tool for designing more responsive and data-driven public policies and provide strategic insights for local governments in improving the quality of public services.
Analysis Of Mobile Banking User Activity Based On Transaction Time Clustering Using Self-Organizing Map (SOM) Method Syah Putra Lubis, Fachrurrozi; Amalia; Erna Budhiarti Nababan
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol. 9 No. 1 (2025): Issues July 2025
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v9i1.15503

Abstract

The rapid growth of mobile banking services in Indonesia demands a deeper understanding of user behavior, especially in terms of time and transaction patterns. However, the challenge is how to effectively cluster users based on their time habits in making transactions, so that service strategies can be tailored accordingly. To address this issue, this study applies the Self-Organizing Maps (SOM) method to cluster users based on transaction time features, such as the number of transactions in the morning, afternoon, evening, night, and the division between weekdays and weekends. The dataset used includes 87,361 mobile banking users throughout 2023. The results showed that the SOM method was able to form nine different user behavior clusters, with the largest cluster being Early User (Weekday) consisting of 32,324 users (37.0%). Overall, the Early User (Weekday) segment covers about 60.3% of the user population. Meanwhile, there are also minority segments such as Night Owl (Weekday) (5.9%) and Early User (Weekend) (2.7%) that show unique behavior patterns. The model performance evaluation resulted in a Quantization Error (QE) value of 0.339 and Topographic Error (TE) of 0.066, both on validation data and test data, indicating that the clustering results are quite accurate and the data mapping topology is well maintained. This research contributes to the understanding of mobile banking user behavior segmentation and can be used as a basis for a more adaptive and personalized time-based service strategy.
CatBoost Algorithm Implementation for Classifying Women's Fashion Products Madani, Fadillah; Lubis, Andre Hasudungan
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol. 9 No. 1 (2025): Issues July 2025
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v9i1.15604

Abstract

The rapid growth of the women's fashion industry in the digital era has intensified the need for data-driven approaches to understand customer preferences. This study aims to classify women’s clothing products based on customer reviews by applying CatBoost, a gradient boosting algorithm known for its strong performance with categorical features. The dataset, consisting of 23,486 entries and 11 attributes, was obtained from Kaggle and processed through data cleaning, normalization, exploratory analysis, and model training. Hyperparameter optimization was conducted using Grid Search. Model performance was evaluated using accuracy, precision, recall, and F1-score, and benchmarked against four traditional classifiers: Decision Tree (C4.5), Naïve Bayes, Support Vector Machine (SVM), and K-Nearest Neighbor (KNN). The results show that CatBoost achieved an accuracy of 93.70%, an F1-score of 0.9606, and an AUC of 0.9691, indicating excellent and balanced classification performance. This study demonstrates the effectiveness of CatBoost in handling customer review data and contributes to the development of intelligent product classification systems in the fashion industry

Page 41 of 42 | Total Record : 412

 38   39   40   41   42 

Filter by Year

2017 2025


Reset
Filter By Issues
All Issue Vol. 9 No. 1 (2025): Issues July 2025 Vol. 8 No. 3Spc (2025): Special Issues 2025: Innovations in Predictive Analytics and Sentiment Analy Vol. 8 No. 2 (2025): Issues January 2025 Vol. 7 No. 2 (2024): Vol. 7 No. 2 (2024): Issues January 2024 Vol. 8 No. 1 (2024): Issues July 2024 Vol. 7 No. 1 (2023): Issues July 2023 Vol. 6 No. 2 (2023): Issues January 2023 Vol 6, No 1 (2022): Issues July 2022 Vol 5, No 2 (2022): Issues January 2022 Vol 5, No 1 (2021): EDISI JULY 2021 Vol 4, No 2 (2021): EDISI JANUARY 2021 Vol. 4 No. 1 (2020): ---> EDISI JULI Vol 4, No 1 (2020): ---> EDISI JULI Vol 3, No 2 (2020): EDISI JANUARI Vol 3, No 1 (2019): EDISI JULI Vol 2, No 2 (2019): EDISI JANUARI Vol 2, No 2 (2019): EDISI JANUARI Vol 2, No 1 (2018): EDISI JULI Vol 2, No 1 (2018): EDISI JULI Vol 1, No 2 (2018): Edisi Januari Vol 1, No 2 (2018): Edisi Januari Vol 1, No 1 (2017): Edisi Juli Vol 1, No 1 (2017): Edisi Juli More Issue