cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Reza Andrea
Contact Email
reza.andrea@gmail.com
Phone
+6285388729017
Journal Mail Official
admin.tepian@politanisamarinda.ac.id
Editorial Address
Kampus Sei Keledang Jl. Samratulangi, Samarinda Kode Pos 75131
Location
Kota samarinda,
Kalimantan timur
INDONESIA
TEPIAN
Published by Politeknik Pertanian Negeri Samarinda
ISSN : 27215350     EISSN : 27215369     DOI : -
Core Subject : Science,
Computer Science & IT
The purpose of TEPIAN is to publish original research studies directly relevant to computer science. TEPIAN encompasses the full spectrum of information technology and computer science, including information system, hardware technology, intelligent system, and multimedia applications. TEPIAN welcomes original papers, reviews and commentaries. Suggestions for special issues covering selected topics may be considered. TEPIAN is devoted to publish manuscripts that advance the knowledge of information technology and communication beyond state-of-the-art. Authors may contact the Editor-in-Chief in advance to inquire about whether their research topic is suitable for consideration by TEPIAN. Through an Open Access publishing model, TEPIAN provides an important forum where computer science researchers in academic, public and private arenas can present the latest results from research on information technology and communication in a broad sense.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 7 Documents
 1 
Search results for , issue "Vol. 6 No. 2 (2025): June 2025" : 7 Documents clear
Automatic Temperature and Humidity Regulation System Design for Oyster Mushroom Growth Kadek Reda Setiawan Suda; I Wayan Arsa Suteja; Made Adi Surya Antara; I Gede Eka Wiantara Putra; Ida Bagus Putu Wija
TEPIAN Vol. 6 No. 2 (2025): June 2025
Publisher : Politeknik Pertanian Negeri Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51967/tepian.v6i2.3251

Abstract

Oyster mushrooms are safe for consumption. The growth of mushrooms in mushroom houses is highly dependent on physical factors such as temperature, humidity, light, pH of the growing medium, and aeration. In this paper researcher concern research physical factors of temperature as a control growth of mushrooms in mushroom houses. The temperature in the mushroom house is very important to note because temperature is one of the factors that affects the performance of enzymes and the metabolism of oyster mushrooms. By implementing automatic temperature and humidity control in mushroom houses, the quality of oyster mushroom harvests can be improved and the income of local oyster mushroom farmers can be increased, thereby helping the government in increasing regional income. The results obtained from this automatic control are that the automatic temperature and humidity device was successfully made according to the design. Furthermore, the results of the tool testing, namely for the electronic tool expert test, obtained 95.45% in very decent qualifications, the results of the small group test were 90.85% in very good qualifications, and the results of the large group test were 91.80% in very good qualifications. The temperature and humidity control device can be of positive benefit to the community, especially to oyster mushroom farmers.
Development of Video Learning Materials on Computational Thinking in Class XI Students of Private High School Tunas Kelapa Samarinda Academic Year 2024/2025 Nadilla Putri Mulyadi; Galih Yudha Saputra
TEPIAN Vol. 6 No. 2 (2025): June 2025
Publisher : Politeknik Pertanian Negeri Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51967/tepian.v6i2.3253

Abstract

In the digital era, science and technologies are developing so fast, it’s also influences developments of students’ mindset and character in learning. so the Indonesian governments try to improve the existing curriculum of the name “Kurikulum Merdeka”. In this curriculum, students are required to have high order thinking skill levels to support their lives in keeping up with changing times. Of course, it’s also requiring teachers to be more creative and provide innovation in the teaching and learning process. The aim of the research is to develop learning media products in the form of videos learning and see the eligibility of the product being developed and implement the product for students whose result is the form of pretest and posttest scores and N-Gain scores to determine whether it's works to improve student learning outcomes. The method used in this research is Research and Development (R&D) with the ASSURE model (Analyze, State, Select, Utilize, Require, Evaluate, and Revise). The results of the eligibility test carried out by three media and one material expert were analyzed using a Likert scale. For the respective results obtained of the three media expert were 93%, 92%, 96% with an average of 93% which was included in the very eligible category, and the result from the material experts is 98% with “very eligible” category. Then for the results of the product implementation in the form of a pretest score with an average of 38, a posttest score with an average of 96, an average N-Gain Score of 0,95 and a percent of N-Gain is 95% which was included in the “high” dan “effective” category. Based on the results of this assessment, it can be concluded that the development of video learning materials on computational thinking in 11th grade class at Private High School Tunas Kelapa Samarinda is “very eligible” to be used in the learning process and is effective in improving student learning outcomes.
Optimisation of Network Logs for Fake Bandwidth Classification using CNN Azriel Christian Nurcahyo; Ting Huong Yong; Abdulwahab Funsho Atanda
TEPIAN Vol. 6 No. 2 (2025): June 2025
Publisher : Politeknik Pertanian Negeri Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51967/tepian.v6i2.3260

Abstract

The goal of this study is to enhance the classification accuracy of fake bandwidth using a CNN model, leveraging network logs collected in real-time. For this research, the network logs from the Cyber Security Laboratory of the University of Technology Sarawak are used as a dataset for training the CNN model. The dataset consists of 20 days of continuous network activity logging, which results in over 500,000 data entries. According to the model evaluation results, the trained CNN model demonstrated high accuracy in classifying genuine bandwidth (Precision: 0.92, Recall: 0.95). Moreover, it achieved considerable success in detecting fake bandwidth (Precision: 0.89, Recall: 0.90) and the no heavy activity category (Precision: 0.98, Recall: 0.84). Analysis of Loss Over Epochs showed a dramatic decrease in loss during the training phase, with optimal convergence reached by epoch 2000. Identifying these characteristics enables monitoring systems to classify network data with high certainty, detecting bandwidth manipulation in expansive networks. Thus, this research aids the design of dynamic network monitoring systems that require minimal response time while maintaining high accuracy.
Development of Mobile Learning Based on Android Using Smart Apps Creator in Informatics Lessons of Grade XI in MA Negeri 2 Samarinda Nur Raudah Datun Nisa; Fahmi Romisa
TEPIAN Vol. 6 No. 2 (2025): June 2025
Publisher : Politeknik Pertanian Negeri Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51967/tepian.v6i2.3292

Abstract

In the rapidly developing digital era, Indonesia has shown significant progress in the use of technology, including in the world of education. Technology is used to facilitate various learning activities, such as accessing information, supporting learning activities, and facilitating tasks by teachers. However, the application of technology in education still faces several challenges, such as the implementation of the Independent Curriculum and limited facilities and infrastructure. Therefore, this study aims to develop mobile learning media and then assess the feasibility of the product through assessments from material experts, media experts and responses from teachers and students. The method used in this study is R&D (Research and Development) with the 4D model (Define, Design, Development, and Disseminate). With the results of the mobile learning feasibility test by one material expert with an average score of 94% with the criteria "very feasible". The results of the mobile learning feasibility test by three media experts with an average score of 93%, 92%, 99% with the criteria "very feasible". If the average score of the three validators is averaged, it gets a score of 95% with the criteria "very feasible". The level of feasibility of mobile learning based on the results of the validation of materials and media obtained an average of 94% with the criteria of "Very Feasible" which states that mobile learning is very feasible and valid for use. can be seen and the media display is 94%. After being processed, the overall average is 95% with the criteria of "Very Good". While the average results of student responses, the value of two aspects, namely the material aspect is 91% and the media display is 93%. After being processed, the overall average is 92% with the criteria of "Very Good". Therefore, the android-based mobile learning product in informatics lessons for class XI MA Negeri 2 Samarinda is very feasible to use in the learning process to be more effective, interactive, and flexible, so that it can increase student motivation and learning outcomes.
Measuring Work Performance from Keyboard and Mouse Use Dodi Wirawan Irawanto; Jusak Jusak; Noorsy Zidna Nabiela; Putri Oktaviani Syaiful
TEPIAN Vol. 6 No. 2 (2025): June 2025
Publisher : Politeknik Pertanian Negeri Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51967/tepian.v6i2.3302

Abstract

In this modern and in age of industrial era 4.0 that was fostered by COVID-19 pandemic the challenge of increasing employee productivity is the main key to company success. One of the predictors of work performance for office workers are the use of computer aids such as keyboard and mouse. This study aims to explore how keyboard and mouse usage behavior affects work performance. The study shows that in the IoT era, poor predictability of work-related behavior from the use of computer accessories is encouraged. The sampling technique with accidental sampling, distributing 100 questionnaires to the target respondents giving the respond rates of 76% respondents using several survey techniques. The instruments use is developed from previous studies that prove to be effective in asking the perception of respondents. The data were analyzed using multiple linear regression, simple linear regression, and correlation through the Statistical Package for the Social Sciences (SPSS) version 27. The findings of this study revealed that keyboard usage behavior plays a significant and positive role in influencing work performance. In contrast, mouse usage behavior was not found to have a significant impact on work performance. This may be because some employees have other alternatives compared to using a mouse, namely a touchpad. Several recommendations for organization that employed office workers that mostly rely on computer for their work is posed to support work performance. This study is the bridging study to computer related study that can measures the productivity, and others work performance variables using more specific IoT tools such as sensors that enable to more accurate results better than perception study.
Comparative Evaluation of Large Language Models for Intent Classification in Indonesian Text Markus Karjadi; Handri Santoso
TEPIAN Vol. 6 No. 2 (2025): June 2025
Publisher : Politeknik Pertanian Negeri Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51967/tepian.v6i2.3355

Abstract

Large Language Models (LLMs) have shown tremendous potential in intent classification tasks, yet their practical deployment in low-resource language environments remains underexplored. This study presents an informatics-based evaluation framework to compare three LLM architectures—GPT-Neo (fine-tuned), Mistral, and Phi-2.0 (zero-shot inference)—on Indonesian intent classification. The methodology integrates classic informatics approaches such as stratified sampling, label encoding, model evaluation using Scikit-learn, and a REST API-based local inference pipeline via the Ollama framework. The study also benchmarks computational efficiency by profiling execution times on consumer-grade hardware. GPT-Neo achieved 100% accuracy after fine-tuning, while Mistral and Phi-2.0 scored approximately 55% and 18%, respectively, in zero-shot settings. The hybrid architecture designed in this work demonstrates how LLMs can be systematically evaluated and deployed using lightweight, modular informatics workflows. Results suggest that fine-tuned lightweight models are viable for high-accuracy deployment, while zero-shot models enable rapid prototyping under constrained resources.
Improving Meta Ads Efficiency through Multi-Level Campaign Structuring and Budget Optimization Mario Sutardiman; Teddy Mantoro
TEPIAN Vol. 6 No. 2 (2025): June 2025
Publisher : Politeknik Pertanian Negeri Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51967/tepian.v6i2.3386

Abstract

The rise of digital advertising has transformed the way businesses interact with consumers, making platforms like Meta Ads a cornerstone of marketing strategies. However, achieving optimal efficiency in Meta Ads remains challenging due to the complexity of campaign setups and budget allocation. This study addresses the issue by examining key configurations at three levels: campaigns, ad sets, and individual ads. The research explores how advertisers can tailor campaigns to specific objectives, such as driving traffic or increasing sales, while leveraging ad set customization for audience targeting, placement optimization, and A/B testing. To improve ad performance, this study emphasizes the importance of refining content at the ad level, ensuring alignment with campaign goals. Budget management is also highlighted, contrasting Campaign Budget Optimization (CBO) with Ad Set Budget Optimization (ABO), and offering insights into leveraging these tools to maximize returns. The study further recommends adjusting budgets based on audience behavior patterns, such as spikes in purchasing activity during twin dates or paydays. By providing actionable strategies for configuring Meta Ads, this study contributes to the field of digital marketing by bridging practical implementation and theoretical insights. Evaluation of these strategies is supported through examples of best practices, with recommendations for advertisers to enhance their Meta Ads efficiency through continual testing and strategic budgeting.

Page 1 of 1 | Total Record : 7

 1 

Filter by Year

2025 2025


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