JKTI Jurnal Keilmuan Teknologi Informasi

Analisis Penerimaan Tekonologi Internet of Things (IoT) Dalam Pertanian Menggunakan Technology Acceptance Model (TAM)

Basiroh Basiroh, Widya Novita Al Afifah Irwanto — Wed, 31 Dec 2025 00:00:00 +0700

This The advancement of digital technology has had a significant impact across various sectors, including agriculture. One of the innovations increasingly applied is the Internet of Things (IoT), which enables more effective and efficient monitoring and control of agricultural activities. However, the success of implementing this technology is highly influenced by the level of user acceptance, particularly among farmers. This study aims to analyze the acceptance of IoT in agriculture using the Technology Acceptance Model (TAM), which includes the variables Perceived Ease of Use (PEOU), Perceived Usefulness (PU), Attitude Toward Using (ATU), Behavioral Intention (BI), and Actual Use (AU). The research employed a quantitative approach, with data collected through questionnaires distributed to farmers who are familiar with or have used IoT-based technologies in their agricultural practices. Data analysis was conducted using Structural Equation Modeling (SEM) with a Partial Least Squares (PLS) approach. The findings reveal that PEOU and PU significantly influence both ATU and BI, which in turn drive the actual use (AU) of IoT technology. Overall, the level of IoT acceptance in agriculture falls into the high category, with respondents’ acceptance percentage exceeding 70%. These results highlight that IoT holds substantial potential to enhance productivity, efficiency, and crop quality. However, its adoption needs to be supported by improved digital literacy, technical assistance, and government policies that facilitate infrastructure development and access to technology

Optimasi Analisis Sentimen Ulasan Platform Pendidikan Daring Menggunakan Arsitektur ALBERT dan Teknik Augmentasi Kontekstual

Sintia Darma Pamuja, Noviyanto — Wed, 31 Dec 2025 00:00:00 +0700

Online learning through global platforms like Coursera generates a massive volume of user reviews, which serve as vital information for educational quality improvement. However, these reviews often exhibit imbalanced label distributions, where positive sentiments significantly dominate negative and neutral ones, hindering traditional classification models. Advanced language models such as ALBERT (A Lite BERT) offer parameter efficiency through cross-layer parameter sharing while maintaining high performance in complex text understanding. This study aims to evaluate the ALBERT model's performance in classifying Coursera user reviews and addressing data imbalance using Contextual Word Embedding augmentation. The methodology involves collecting 10,000 reviews followed by preprocessing steps including case folding, punctuation removal, and tokenization. The augmentation technique utilizes language models to replace words based on context to balance minority classes. The results show that ALBERT provides highly consistent performance, achieving an F1-score of 0.9710 with the contextual augmentation scenario. The model proves effective in capturing linguistic variations and remains computationally efficient. In conclusion, the ALBERT model is highly effective for sentiment analysis on the Coursera dataset, where contextual augmentation significantly enhances the model's ability to recognize minority classes that were previously difficult to identify.

Evaluation of Service Issues in the Classroom Reservation System at XYZ University Using COBIT 5 DSS02

Diesti Hidayani, Fachruddin Edi Nugroho Saputro — Wed, 31 Dec 2025 00:00:00 +0700

The classroom reservation system is an information technology service that plays a vital role in supporting the smooth running of academic activities at XYZ University. However, many service issues still occur during operation. These include system delays, sudden class schedule changes, and suboptimal incident handling. The purpose of this study is to evaluate the capability level of XYZ University's Classroom Reservation system to manage service requests and incident handling, specifically the DSS02 (Manage Service Requests and Incidents) domain. The research method used is a case study with a quantitative approach through observation and the distribution of questionnaires based on the COBIT 5 Process Assessment Model (PAM). The results show that the DSS02 process capability level in its current condition is at Level 1 (Performed Process), while the expected condition is at Level 5 (Optimizing Process). Gap analysis shows a significant difference between the actual and expected conditions, especially in the aspects of process documentation, service performance measurement, and incident management. Therefore, to make the classroom reservation service support academic activities in a more efficient, effective, and reliable manner, planned and sustainable development efforts are needed.

Comparison of CNN Transfer Learning Models for Brain Tumor Detection Based on MRI Images

noviyanto, Sintia Darma Pamuja — Wed, 31 Dec 2025 00:00:00 +0700

Brain tumors require early and accurate detection to support effective clinical decision-making. This study compares the performance of four transfer learning-based Convolutional Neural Network (CNN) models, namely DenseNet121, InceptionV3, MobileNet, and Xception, for brain tumor detection using MRI images. The dataset was preprocessed through resizing, normalization, and data augmentation, and all models were trained for 20 epochs using ImageNet pre-trained weights. Model performance was evaluated using accuracy, precision, recall, and F1-score metrics. The experimental results show that all models achieved accuracies above 90%, with MobileNet outperforming the others by achieving an accuracy of 94.74% and precision, recall, and F1-score values of 0.95, 0.95 and 0,94. These findings indicate that lightweight CNN architectures can deliver superior performance for MRI-based brain tumor classification.