cover
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
ISSN : 27215350     EISSN : 27215369     DOI : -
Core Subject : Science,
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.
Articles 292 Documents
Geographic Information System of Dengue Hemorrhagic Fever Area Mapping in the City Of Samarinda Tarsius Aloysius Pedor; Syafei Karim; F.V Astrolabe Sian Prasetya
TEPIAN Vol. 2 No. 4 (2021): December 2021
Publisher : Politeknik Pertanian Negeri Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51967/tepian.v2i4.677

Abstract

Dengue Hemorrhagic Fever (DHF) is still one of the main public health problems in Indonesia. This disease can threaten public health, efforts to prevent its spread need to be done. As the first step for prevention, it is necessary to do the mapping. Environmental factors have a major influence on the increase and transmission of mosquito-borne diseases such as DHF. The most influential factors include the physical environment consisting of rainfall, air humidity, and population density. The city of Samarinda itself has not maximized the DHF control program, because the government is less effective in mapping the DHF-vulnerable areas based on indicators of increasing cases over the last few years using spatial maps. Mapping the DHF area with the spatial method can maximize the implementation of the DHF control program, the implementation of the fogging program, and other DHF control programs. So to get this information, a geographical information system (GIS) is needed or commonly known as a geographic information system (GIS). This web-based geographic information system application for mapping dengue areas can display detailed information such as the address of the Public Health Center that provides information on the number of cases that occur in each sub-district and a polygon map showing which sub-district has the most cases.
Expert System for Diagnosis of Pepper Plant Diseases Using Certainty Factor and Naïve Bayes Methods Karmila; Eny Maria; Annafi' Franz
TEPIAN Vol. 2 No. 4 (2021): December 2021
Publisher : Politeknik Pertanian Negeri Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51967/tepian.v2i4.744

Abstract

Development expert system for diagnosis of pepper plant diseases using certainty factor and naïve bayes methods. Pepper is one type of plant that has long been traded on the European market. So that increasing the quality and quantity of pepper production is the main demand. However, diseases in pepper plants are also familiar to be found so that they can be detrimental to farmers and besides that, agricultural workers who are experts in the field of pepper plant diseases are still limited. Therefore, to overcome this problem, an expert system application is designed where this system can provide information about diseases that attack pepper plants, then provide suggestions or solutions to deal with these diseases. The purpose of this research is to build and design an expert system that is useful for determining pepper plant diseases and to apply certainty factor and nave Bayes methods in providing answers to the results of the consultation. The results of this study are expected to make it easier for users, especially farmers or farm workers in overcoming diseases in pepper plants.
UI/UX Design of a Transparency Platform for the Use of CSR Funds in Supporting Smart Cities Using the Design Thinking Method Arif Wicaksono Septyanto; Henokh Lugo Hariyanto; Sri Rahayu Natasia; Dessy Fitrianitha; Zaka Dimasqi Almeyda; Rifki Anashirul
TEPIAN Vol. 7 No. 3 (2026): September 2026
Publisher : Politeknik Pertanian Negeri Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51967/tepian.v7i3.3634

Abstract

Environmental conservation initiatives increasingly require transparent and accountable management of Corporate Social Responsibility (CSR) funds. However, many CSR-based environmental programs still rely on manual coordination and limited digital transparency, leading to reduced operational efficiency and lower public trust. To address these challenges, this study develops the UI/UX design of the Tanamin Bumi digital platform, a web-based system designed to support CSR fund transparency and environmental activity monitoring in collaboration with Bappeda Litbang Kota Balikpapan. This research employs the Design Thinking approach to create a user-centered and intuitive interface tailored to multiple stakeholders, including companies, government agencies, and the public. The proposed platform integrates several key features, such as digital donation management, environmental campaign monitoring, company partnership profiles, and role-based access control. Usability evaluation was conducted using the System Usability Scale (SUS), resulting in an average score of 87.75, which falls within the “excellent” category and significantly exceeds the standard benchmark score of 68. These findings indicate a high level of usability, effectiveness, and user acceptance. This study contributes by providing a structured UI/UX design framework that integrates digital transparency, CSR management, and smart governance principles into an environmental conservation platform.
Improving Sentiment Classification Performance Using Pseudo-Labeling with Naive Bayes and Random Forest Arvidion Havas Oktavian; Agus Sasmito Aribowo
TEPIAN Vol. 7 No. 3 (2026): September 2026
Publisher : Politeknik Pertanian Negeri Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51967/tepian.v7i3.3796

Abstract

Sentiment analysis has been applied to understand users' opinions expressed in unstructured text on various online platforms. Supervised machine learning approaches typically require large amounts of labeled data; however, annotation is expensive and laborious. This research aims to implement semi-supervised learning via pseudo-labeling to reduce reliance on labeled data and improve the performance of sentiment classification models relative to a supervised baseline. Contributions of this research include a pseudo-labeling framework implemented with limited labeled data, benchmarking of Naive Bayes and Random Forest algorithms across three Indonesian-language datasets with different linguistic characteristics (IndoNLU, E-commerce, and BCA Mobile app reviews), and an analysis of model performance sensitivity to the pseudo-labeling threshold. Count Vectorizer and TF-IDF were utilized for feature extraction with unigram and bigram parameters. Accuracy and F1-score were measured to benchmark model performance. Results show that pseudo-labeling improved performance across all classification models compared to the baseline by an average of 0.005–0.010, and up to 0.030 on the E-commerce dataset. Naive Bayes was found to have more consistent results across datasets, while Random Forest capitalized more on the implementation of pseudo-labeling under the right circumstances. Overall, TF-IDF outperformed Count Vectorizer, and larger threshold values yielded more consistent performance improvements across datasets, though lower values offered greater potential for gains on large, diverse datasets. These results suggest pseudo-labeling is a viable method for incorporating unlabeled data. Its efficacy depends on dataset attributes, feature extraction methods, and the threshold value.
Multivariate LSTM With the RSI-14 Technical Indicator for Stock Price Forecasting Muhammad Jahron; Joan Angelina Widians; Andi Tejawati
TEPIAN Vol. 7 No. 3 (2026): September 2026
Publisher : Politeknik Pertanian Negeri Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51967/tepian.v7i3.3919

Abstract

Stock price forecasting is a key part of investment decision-making, especially for high-capitalization stocks such as PT Bank Central Asia Tbk. (BBCA). Accurate prediction remains challenging because complex market dynamics and nonlinear price movements influence stock prices. This study proposes a multivariate Long Short-Term Memory (LSTM) model that integrates the closing price and the RSI-14 technical indicator as input features to improve accuracy over conventional univariate approaches. We obtained historical data from the Yahoo Finance API covering January 2015 to December 2025, totaling 2,698 trading days after RSI-14 feature engineering. The dataset was split to 80:20 for training and testing, with MinMaxScaler normalization applied only to the training data to prevent data leakage. The LSTM model used 100 neurons with an input shape of (10, 2) and was trained using the Adam optimizer with early stopping at epoch 24 to avoid overfitting. Evaluation results show an RMSE of 169.72 IDR, an MAE of 134.68 IDR, a MAPE of 1.58%, and an R² of 0.9368, indicating a good regression-level fit. Adding the RSI-14 feature improved the regression metrics relative to a univariate closing-price-only LSTM. Given the modest trend-classification accuracy and the lack of trading back testing, transaction costs, or risk-adjusted performance measures, view the results as a methodological contribution rather than direct evidence of practical investment value. Future work could extend this research by exploring hybrid architectures that combine LSTM with attention mechanisms or Transformer-based models, and by validating the approach on other high-capitalization stocks to assess generalizability across market conditions.
Analysis of Hoax News Propagation Patterns on Threads Using GCN-Based Structural Node Embedding Andi Novia Nuzul Qurani; Sitti Zuhriyah; M. Adnan Nur
TEPIAN Vol. 7 No. 3 (2026): September 2026
Publisher : Politeknik Pertanian Negeri Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51967/tepian.v7i3.3929

Abstract

The dissemination of hoax news on social media has become a significant issue because it can influence public opinion and accelerate the spread of misinformation. Although various approaches have been proposed for hoax detection, most of them rely on textual analysis and do not adequately capture the structural relationships among users. Therefore, this study aims to analyze the propagation patterns of hoax news on the Threads social media platform using the Graph Convolutional Network (GCN) method. Data was collected by crawling posts from the Threads platform using hoax-related keywords and represented as a social graph in which nodes represent user accounts, mentions, and hashtags, while edges represent interactions among users. The constructed graph consists of 425 nodes and 697 edges. The proposed GCN model was evaluated based on degree centrality, betweenness centrality, clustering coefficient, and Spearman correlation analysis. The highest clustering coefficient obtained was 0.8046, while the highest Spearman correlation coefficient between the GCN score and degree centrality reached 0.6118. The results demonstrate that GCN effectively represents user relationships, identifies influential nodes, and provides a comprehensive understanding of hoax propagation patterns on the Threads platform.
UI/UX Design Analysis of Students' Integrated Information System Using Design Thinking and Agile Scrum with System Usability Scale (SUS) Evaluation in Jayawijaya District Haris Asso; Kristiawan Nugroho
TEPIAN Vol. 7 No. 3 (2026): September 2026
Publisher : Politeknik Pertanian Negeri Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51967/tepian.v7i3.3930

Abstract

Student scholarship management in Jayawijaya Regency still faces various challenges, including non-integrated data management, administrative processes that are still performed manually, low transparency, and ineffective coordination among stakeholders. These conditions result in delays in scholarship distribution, difficulties in monitoring and decision-making that is not yet supported by integrated data. This study aims to design and evaluate an Integrated Student Information System to support scholarship management by applying the Design Thinking approach combined with the Agile Scrum development framework. The Design Thinking process was used to identify stakeholder needs, formulate system requirements, and generate solution concepts, which were subsequently translated into nine Product Backlog items to be developed incrementally through three development sprints. The resulting prototype includes multi-role authentication, student dashboard, Education Office dashboard, online scholarship application, verification and validation, application status tracking, student data management, communication and notification, and reporting. The prototype was subsequently evaluated using the System Usability Scale involving 41 respondents. The evaluation results produced an average score of 74.39, indicating that the prototype falls within the Acceptable category with good usability. The findings demonstrate that the integration of Design Thinking and Agile Scrum is capable of producing a user-centered prototype, improving transparency, coordination and supporting the digital transformation of scholarship management in Jayawijaya Regency.
Design and Development of a Restaurant Information System for Stasiun Jajanan Agus Ganda Permana; Dewi Safitriani; Devit Setiono
TEPIAN Vol. 7 No. 3 (2026): September 2026
Publisher : Politeknik Pertanian Negeri Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51967/tepian.v7i3.3935

Abstract

The rapid advancement of information technology has encouraged Micro, Small, and Medium Enterprises (MSMEs) to adopt digital solutions to improve business performance and customer service. Stasiun Jajanan is a culinary MSME that offers various fast-food products, including kebabs, burgers, fried tapioca fritters, Indonesian fried tofu meatballs, and beverages. Promotional activities, order processing, and transaction recording are still conducted manually, resulting in limited promotional reach, inefficient data management, and potential recording errors. This study aims to design and develop a web-based restaurant information system to support business promotion, online ordering, and transaction management for Stasiun Jajanan. The system was developed using the System Development Life Cycle (SDLC) with the Waterfall model, consisting of requirement analysis, system design, development, and testing. Unified Modeling Language (UML) was utilized to model the system through use case, activity, sequence, and class diagrams. The developed system provides several features, including menu management, online ordering, payment processing, transaction management, business information services, and WhatsApp integration for customer communication. System testing was conducted using the Black Box Testing method to verify that all functionalities operated according to the specified requirements. The testing results indicate that the developed system successfully supports menu management, customer ordering, payment processing, and transaction recording. The system improves service efficiency, reduces manual recording errors, and provides customers with easier access to product information and ordering services. The proposed system can therefore support the digital transformation and business growth of culinary MSMEs.
Laundry Management Information System Using Laravel Framework for Ema Laundry Syukriyanto Latif; Camelia Praestuti; Letarius Tunjanan; Rahayu Septyaning Mistina
TEPIAN Vol. 7 No. 3 (2026): September 2026
Publisher : Politeknik Pertanian Negeri Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51967/tepian.v7i3.3937

Abstract

The rapid acceleration of small enterprise operations requires service sectors to transition from conventional management practices to high-efficiency computerized architecture. Ema Laundry encountered critical operational bottlenecks, including error-prone manual ledger entries, physical order tracking inefficiencies, and decentralized revenue recording which hampered business growth. This study addresses these challenges by implementing a secure, responsive, web-based laundry management information system designed to optimize micro-business transactional workflows. Developed utilizing the Laravel framework, a relational MySQL database, and Bootstrap components, the platform integrates automated computations to handle complex processing states and evaluate invoice calculations with high precision. The system engineering process undergoes systematic lifecycle validations, including rigorous data flow structural checks and comprehensive functional black-box evaluations to ensure stability under operational load. The implementation establishes clean data normalization patterns, eliminates tracking redundancies, and significantly improves service velocity. By providing a scalable digital transformation blueprint, this system contributes to the field of modern small business informatics, demonstrating that localized enterprise applications can be successfully modernized to enhance overall service delivery quality and administrative accountability. This research serves as a viable technical foundation for future integration with predictive behavioral analytics and broader service management ecosystems.
Implementation of Hybrid Recommender System for Islamic Boarding School Selection Yunifa Miftachul Arif; Zuchrotunisa Zuchrotunisa; Dwi Pebrianti; Muhammad Faisal; Imamudin Imamudin
TEPIAN Vol. 7 No. 3 (2026): September 2026
Publisher : Politeknik Pertanian Negeri Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51967/tepian.v7i3.3944

Abstract

Islamic boarding schools are the oldest Islamic educational institutions in Indonesia that play an important role in shaping the character and moral development of the nation's generation. Along with the massive growth in the number of Islamic educational institutions, prospective students and parents often face the problem of information overload in determining the choice of institution that best suits their needs and applicable regulations. The selection process that has been carried out manually tends to be subjective and has not fully utilized a data-driven approach. This research aims to design and implement a recommendation system to assist prospective students in determining their choice of Islamic boarding school in a more objective, measurable, and efficient manner. The method used in the development of this system is a hybrid approach that combines content-based feature matching with collective user preference patterns through the integration of content-based filtering and collaborative filtering. The dataset used includes the profile data of Islamic boarding school institutions in the Kediri region as well as preference data from a number of respondents. The test results show that the integration of various similarity methods can produce accurate top-ranking recommendation lists. System performance evaluation using testing metrics shows an optimal level of data retrieval completeness, proving that the system is effective in presenting relevant and accountable recommendations for Islamic educational institutions in the digital era.