cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Adie Wahyudi Oktavia Gama
Contact Email
journal@undiknas.ac.id
Phone
+6282236805788
Journal Mail Official
journal@undiknas.ac.id
Editorial Address
Jl. Bedugul No.39, Sidakarya, Kec. Denpasar Sel., Kota Denpasar, Bali 80224
Location
Kota denpasar,
Bali
INDONESIA
TIERS Information Technology Journal
Published by Universitas Pendidikan Nasional
ISSN : 27234533     EISSN : 27234541     DOI : 10.38043
Core Subject : Science,
Computer Science & IT
TIERS Information Technology Journal memuat artikel Hasil Penelitian dan Studi Kepustakaan dari cabang Teknologi Informasi dengan bidang Sistem Informasi, Artificial Intelligence, Internet of Things, Big Data, e-commerce, Financial Technology, Business Digital
Arjuna Subject : Ilmu Komputer (semua kategori) - Sistem Informasi
Articles 120 Documents
 8   9   10   11   12 
A Zero-Shot Aspect-Based Sentiment Analysis of Public Perception Toward AI Chatbots Fauzan, Naufal Andila
TIERS Information Technology Journal Vol. 6 No. 1 (2025)
Publisher : Universitas Pendidikan Nasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38043/tiers.v6i1.6488

Abstract

The rapid development of AI chatbots has sparked public discussion on social media regarding their performance, ethical implications, and related concerns. While past studies primarily focused on individual chatbot model using traditional sentiment analysis, this study implements a novel application of Zero-Shot Aspect-Based Sentiment Analysis (ABSA) on 17,562 tweets mentioning AI chatbots such as ChatGPT, Bard (now Gemini), and DeepSeek, utilizing an efficient sentiment extraction method without supervised training. Six aspects were analyzed to understand the sentiment pattern and the results show the discussion was dominated by negative sentiment, with Bard receiving the most positive sentiment, potentially shaped by brand trust and user familiarity. On the other hand, DeepSeek and ChatGPT attracted more criticism, especially related to performance and bias aspects. This study offers data-driven suggestions for developers, including improving response accuracy to shape user trust, reducing biased output, and developing real-time discourse analysis. Future work should incorporate multiple platforms to avoid bias, analyze more AI chatbot models, and include temporal sentiment for broader insights.
Comparative Analysis of YOLOv5n and YOLOv8n Deep Learning Models for Precision Detection of Klowong Defects in Batik Fabric Hamidi, Rifqi Restu; Herliansyah, Muhammad Kusumawan; Atmaja, Denny Sukma Eka; Sudiarso, Andi
TIERS Information Technology Journal Vol. 6 No. 1 (2025)
Publisher : Universitas Pendidikan Nasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38043/tiers.v6i1.6499

Abstract

This study presents a comparative analysis of two deep learning object detection models, YOLOv5n and YOLOv8n, for the precies identification of Klowong defects in batik fabric. The evaluation was carried out using a custom dataset consisting of 3,138 annotated images, with 921 allocated for testing and containing 1,295 defect instances across nine defect classes. The main findings show that YOLOv8n outperforms YOLOv5n in both speed and accuracy. YOLOv8n achieved a higher F1-score of 0.87 at a lower confidence threshold (0.297), compared to YOLOv5n’s F1-score of 0.86 at a higher threshold (0.46). In addition, YOLOv8n reduced training time significantly (0.320 hours vs. 0.868 hours) and delivered much faster inference speed (2.9 ms/image), nearly three times quicker than YOLOv5n. Although both models performed well in detecting common defects, YOLOv8n showed more stable results on complex defect types. These improvements make YOLOv8n more suitable for real-time applications in batik production environments. Its efficiency and accuracy support the development of fast and reliable automated quality control systems in traditional textile industries. This research emphasizes the importance of using modern lightweight architectures like YOLOv8n to enhance defect detection performance in practical manufacturing settings.
Solving an Optimization Problem of Image View Layout with Priority using Heuristic Approach Hiryanto, Lely; Wirawan, Andhika Putra; Lee, Viciano
TIERS Information Technology Journal Vol. 6 No. 1 (2025)
Publisher : Universitas Pendidikan Nasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38043/tiers.v6i1.6519

Abstract

The image view layout with priority (IVLP) problem focuses on efficiently arranging picture cards of uniform height but varying widths into the minimum number of 2D frames or display sets and prioritizing images with higher priority to be placed at the earlier displays. We mathematically modeled IVLP using integer linear programming. To approximate IVLP solutions, we introduce a greedy-based heuristic, Best-Fit-IVLP (BFI), and a swarm optimization algorithm, Ant Colony Optimization (ACO). BFI allocates picture cards in descending order of priority and width for each display line, seeking another card that can optimally fill the remaining space on each line. In contrast, ACO randomly arranges cards from high to low priority within every line. Experimental results using different numbers of SVG images indicate that BFI and ACO generate solutions close to optimal. BFI demonstrates superior practicality, executing significantly faster than ACO; for 160 images, BFI runs in 0.00044 seconds compared to ACO's 117.93 seconds. Both BFI and ACO achieve space utility rates ranging from 0.578 to 0.8. While BFI consistently produces the same card arrangement, ACO offers diverse arrangements for identical optimal display set counts and space utilization.
Performance Analysis and Traffic Flow Simulation of Tukad Pakerisan Road Segments Using VISSIM in South Denpasar Tapa, I Gede Fery Surya; Yuliadewi, Ni Putu Ary; Candrawengi, Ni Luh Putu Ika; Prakasa, I Made Panji Tirta; Zainordin, Nadzirah; Sutapa, I Ketut
TIERS Information Technology Journal Vol. 6 No. 1 (2025)
Publisher : Universitas Pendidikan Nasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38043/tiers.v6i1.6546

Abstract

The increasing ownership of motor vehicles has significantly contributed to heightened levels of traffic congestion. This study was conducted on Tukad Pakerisan Road in Denpasar City and aims to evaluate the current performance of the road segment by employing traffic modeling through Vissim software. The research adopts the Indonesian Highway Capacity Guidelines (PKJI) as the methodological framework. Data collection was carried out via a 12-hour on-site survey across two road segments of Tukad Pakerisan. The analysis revealed that the traffic flow volume reached 2025.45 Passenger Car Station/hour on Segment A and 1865.65 Passenger Car Station/hour on Segment B. The respective road capacities were 1877.669 Passenger Car Station/hour and 1671.583 Passenger Car Station/hour. The degree of saturation was found to be 1.08 on Segment A and 1.12 on Segment B, indicating Level of Service (LOS) F—characterized by severe traffic congestion. The simulation indicates significant future congestion, with projected saturation levels exceeding 1.5, underscoring the need for integrated mitigation strategies such as adaptive signal control and vehicle restriction policies. A five-year performance projection further suggests a continual increase in the degree of saturation, surpassing the acceptable limit of 0.85 as stipulated in PKJI 2023. These findings underscore the urgent need for capacity enhancement on Tukad Pakerisan Road. The study recommends the installation of additional traffic signage and the implementation of traffic engineering strategies to mitigate congestion along this critical corridor in South Denpasar.
Hybrid Machine Learning Approach for Nutrient Deficiency Detection in Lettuce Zuriati, Zuriati; Widyawati, Dewi Kania; Arifin, Oki; Saputra, Kurniawan; Sriyanto, Sriyanto; Ahmad, Asmala
TIERS Information Technology Journal Vol. 6 No. 2 (2025)
Publisher : Universitas Pendidikan Nasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38043/tiers.v6i2.7143

Abstract

Early detection of nutrient deficiencies in lettuce is essential for precision agriculture. However, this task remains challenging due to limited data availability and class imbalance, which reduce model sensitivity toward minority classes and hinder generalization. This study introduces a hybrid machine learning approach integrating SMOTE, Optuna, and SVM to enhance the accuracy of nutrient deficiency classification using digital leaf image analysis. The dataset, obtained from Kaggle, includes four categories: Nitrogen Deficiency (-N), Phosphorus Deficiency (-P), Potassium Deficiency (-K), and Fully Nutritional (FN). Image features were extracted using MobileNetV2 pretrained on ImageNet and classified with a Support Vector Machine. Three scenarios were tested: (1) SVM before SMOTE, (2) SVM after SMOTE, and (3) Optuna-SVM after SMOTE, evaluated using accuracy, precision, recall, and f1-score. The hybrid model achieved the best performance with accuracy 0.929, precision 0.946, recall 0.835, and f1-score 0.869, outperforming the other scenarios. This hybrid framework effectively addressed class imbalance and improved classification margin stability through adaptive hyperparameter tuning using the Tree Structured Parzen Estimator within Optuna. The novelty of this study lies in combining MobileNetV2 based feature extraction with SMOTE and Optuna-SVM for small agricultural datasets. The proposed approach offers an efficient, accurate, and practical solution for automated nutrient deficiency diagnosis and contributes to the development of AI-driven smart agriculture systems.
YOLOv8-Based Quality Detection of Bali MSMEs Staple Food Dewi, Ni Putu Dita Ariani Sukma; Aryasa, Jiyestha Aji Dharma; Hendrayana, I Gede; Prayoga, I Made Ade; Putri, Sulin Monica
TIERS Information Technology Journal Vol. 6 No. 2 (2025)
Publisher : Universitas Pendidikan Nasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38043/tiers.v6i2.7144

Abstract

Ensuring the quality of staple foods such as rice, cooking oil, milk, and meat is crucial for consumer safety and health. In Indonesian Micro, Small and Medium Enterprises (MSMEs), quality assessment often depends on subjective and time-consuming visual inspection. This study develops an automatic quality detection system using YOLOv8, applied to food MSMEs in Bali, to detect 14 quality categories across the four commodities based on image data. The methodology includes dataset collection from MSMEs, image annotation, preprocessing, training YOLOv8s and YOLOv8m models, and evaluating performance using mAP50, accuracy, precision, recall, and F1-score. Results show that YOLOv8m achieved a mAP50 of 96.5%, indicating high detection accuracy. The system, implemented as a web-based application, has strong potential to improve efficiency, ensure consistent product quality, and support Sustainable Development Goals (SDGs) 2, 3, 8, and 9.
Efficient Rice Leaf Disease Classification Using Enhanced CAE-CNN Architecture Suhada, Destia; Suta Wijaya, I Gede Pasek; Widiartha, Ida Bagus Ketut; Jo, Minho
TIERS Information Technology Journal Vol. 6 No. 2 (2025)
Publisher : Universitas Pendidikan Nasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38043/tiers.v6i2.7159

Abstract

This study introduces an enhanced Convolutional Autoencoder–Convolutional Neural Network (CAE–CNN) model designed for efficient and accurate classification of rice leaf diseases. This study aims to develop an architecture that achieves high accuracy while maintaining computational efficiency, serving as an integrative and applicative technical innovation for rice disease detection. The proposed architecture integrates a Squeeze and Excitation Block (SE-Block), Global Max Pooling (GMP), and Separable Convolution to improve feature extraction while reducing the number of parameters and inference time. A total of 7,430 labeled images from five rice disease classes were used for model training and evaluation. The model was optimized using Optuna-based hyperparameter tuning and validated through an ablation and comparative analysis to assess the impact of each component. Experimental results show that the proposed model achieves 99.39% accuracy with only 85,859 parameters, a compact size of 0.28 MB, and inference time at 0.06657 ms/image with 15,213 FPS. These findings demonstrate that the proposed CAE–CNN effectively combines high accuracy and low computational cost, making it highly suitable for real-time and edge-based rice disease classification systems.
Operating Room Scheduling Optimization Under Surgeon and Nurse Constraints Using Genetic Algorithm Swilugar, Ayu; Herliansyah, Muhammad Kusumawan
TIERS Information Technology Journal Vol. 6 No. 2 (2025)
Publisher : Universitas Pendidikan Nasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38043/tiers.v6i2.7164

Abstract

Operating room scheduling is a complex problem due to the limited availability of surgeons, nurses, and operating rooms, as well as the variability in surgery durations. Inaccurate predictions or scheduling may cause conflicts such as overlapping surgeon schedules, violations of contamination level restrictions, and unavailability of nurses or rooms, ultimately reducing the quality of hospital services. This study integrates multiprocedure surgery duration prediction using machine learning with scheduling optimization based on genetic algorithms. The prediction model considers the American Society of Anesthesiologists (ASA) physical status classification, patient profiles, and sets of surgical procedures variables. Scheduling optimization employs a lexicographic approach with three main objectives: minimizing patient waiting time, nurse overtime, and operating room idle time, while ensuring surgeon presence during critical phases and nurse availability according to shifts. The results show that the Catboost algorithm achieves the best prediction performance. Incorporating the ASA variable reduces prediction errors by 33.880 minutes in MAE and 55.575 minutes in RMSE compared to model without the ASA feature. The optimization model successfully eliminates all scheduling conflicts, ensuring full compliance with medical procedure constraints. Recovery bed utilization remains efficient, with a maximum of five units used, representing less than 50% of the total capacity.
Genre-Based Sentiment and Emotion System for Audience Insight Suwarno, Suwarno; Wesly, Wesly; Syahputra, Bayu
TIERS Information Technology Journal Vol. 6 No. 2 (2025)
Publisher : Universitas Pendidikan Nasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38043/tiers.v6i2.7183

Abstract

Movies can influence people’s moods in different ways depending on film genre. Fear is commonly induced by horror films, whereas joy is typically associated with comedy. Understanding how genre-based expectations shape audience emotions offers valuable insights for producers and digital platforms. However, previous studies have only briefly examined this relationship, with most focusing on general sentiment analysis. This study develops a genre-based sentiment and emotion model to analyze how film genres influence audience reactions. The Cross-Industry Standard Process for Data Mining (CRISP-DM) framework was applied to 46,173 IMDb reviews using Term Frequency–Inverse Document Frequency (TF-IDF) features and three machine learning models: Logistic Regression, Linear Support Vector Classification, and One-vs-Rest Logistic Regression. The results show that Fear (0.704) and Anger (0.684) are the most dominant emotions, indicating that audiences tend to be more emotionally engaged with intense genres. The model was also implemented in a Flask–React web-based system that allows users to analyze and visualize reviews in real time. These findings provide practical implications for filmmakers, producers, and streaming platforms in adjusting genre design, content recommendation, and promotional strategies to align with audience emotional responses.
Optimization CatBoost using GridSearchCV for Sentiment Analysis Customer Reviews in Digital Transportation Industry Ifriza, Yahya Nur; Sanusi, Ratna Nur Mustika; Febriyanto, Hendra; Kamaruddin, Azlina
TIERS Information Technology Journal Vol. 6 No. 2 (2025)
Publisher : Universitas Pendidikan Nasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38043/tiers.v6i2.7201

Abstract

The rapid expansion of ride-hailing services has generated a massive volume of user feedback, making automated sentiment analysis essential for understanding customer satisfaction. This study aims to classify public sentiment towards the Uber application into positive, neutral, and negative categories using the CatBoost algorithm, a gradient boosting method prioritized for its Ordered Boosting mechanism, which effectively prevents overfitting and enhances the model's generalization capabilities. Despite the use of TF-IDF for numerical text representation, CatBoost is selected for its superior performance on heterogeneous datasets compared to other boosting frameworks like XGBoost and LightGBM. The dataset comprises customer reviews collected 12.000 from the Google Play Store between January and March 2024 using web scraping techniques upload in Kaggle. The data underwent rigorous preprocessing, including lemmatization and TF-IDF vectorization, to structure the textual features, to maximize model performance, hyperparameter optimization was conducted using GridSearchCV. The experimental results demonstrate that the optimization process successfully improved the model's generalization capabilities, raising the Accuracy from 0.907 to 0.910 and the F1-Score from 0.893 to 0.897. Most significantly, the AUC score increased from 0.949 to 0.957, indicating a superior ability to distinguish between sentiment classes. However, while the model exhibited high precision in identifying positive and negative polarities, analysis of the confusion matrix revealed limitations in correctly predicting the neutral class, suggesting challenges related to class imbalance. These findings confirm that an optimized CatBoost model is a robust tool for sentiment classification, though future work is recommended to address minority class detection.

Page 12 of 12 | Total Record : 120

 8   9   10   11   12 

Filter by Year

2020 2025


Reset
Filter By Issues
All Issue Vol. 6 No. 2 (2025) Vol. 6 No. 1 (2025) Vol. 5 No. 2 (2024) Vol. 5 No. 1 (2024) Vol. 4 No. 2 (2023) Vol. 4 No. 1 (2023) Vol. 3 No. 2 (2022) Vol. 3 No. 1 (2022) Vol. 2 No. 2 (2021) Vol. 2 No. 1 (2021) Vol. 1 No. 2 (2020) Vol. 1 No. 1 (2020) More Issue