cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Wandi Syahindra
Contact Email
wandi.syahindra@iaincurup.ac.id
Phone
+6285268383345
Journal Mail Official
arcitech.journal@iaincurup.ac.id
Editorial Address
Jl. Dr. AK Gani No. 01 Curup, Rejang Lebong Bengkulu Indonesia
Location
Kab. rejang lebong,
Bengkulu
INDONESIA
Arcitech: Journal of Computer Science and Artificial Intelligence
Published by Institut Agama Islam Negeri Curup
ISSN : 29623669     EISSN : 29622360     DOI : http://dx.doi.org/10.29240/arcitech
Core Subject : Science,
Computer Science & IT
Arcitech: Journal of Computer Science and Artificial Intelligence, is an Open Access and peer-reviewed journal published by the State Islamic Institute (IAIN) Curup. This journal focuses on the field of computer science and artificial intelligence covering all aspects of information technology, computer science, computer engineering, information systems, Software Engineering and its development, software engineering Computer networks, IoT, security systems, Simulation Modeling and Applied Computing, Computing High Performance, Image and speech processing, big data and data mining, and artificial intelligence. The journal is published by Institut Agama Islam Negeri (IAIN) Curup, online and printed twice a year, in June and December.
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 76 Documents
 4   5   6   7   8 
Analisis Sentimen Publik terhadap Pengaruh Kecerdasan Buatan pada Produksi Animasi Berbasis Data Media Sosial X Menggunakan Metode Lexicon-Based VADER Ginanjar Setyo Nugroho; Troy; Samuel Gandang Gunanto; Venus Khesya Tyasmara
Arcitech: Journal of Computer Science and Artificial Intelligence Vol. 6 No. 1 (2026): June 2026
Publisher : Institut Agama Islam Negeri (IAIN) Curup

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29240/arcitech.v6i1.16391

Abstract

Artificial Intelligence (AI) has emerged as a primary driver in various industries, yet its integration into animation production faces mixed reactions, creating a dualism between innovation and professional sustainability. Despite growing research on AI's technical efficiency in animation, there remains a significant gap in understanding public sentiment toward its broader impacts, particularly through large-scale social media analysis. This study aims to address this gap by analyzing public sentiment regarding the impact of AI on animation production. Using the Lexicon-Based VADER method, this study collected and analyzed 1,545 tweets from the social media platform X (formerly Twitter) during the period from June 1 to 30, 2025. The results showed a dominance of positive sentiment with 935 tweets, 385 neutral tweets, and 225 negative tweets. The results of this study are expected to provide insights, reference for decision-making, and further exploration. These findings not only highlight widespread support for AI but also underscore the need for ethical frameworks to mitigate job displacement risks, offering actionable implications for industry stakeholders to foster balanced human-AI collaboration in creative fields.
Analisis Komparatif Pemodelan Topik Promosi Judi Online pada Komentar YouTube Menggunakan Latent Dirichlet Allocation dan BERTopic Nur Aisyah Wahyuni; Hafiz Irsyad
Arcitech: Journal of Computer Science and Artificial Intelligence Vol. 6 No. 1 (2026): June 2026
Publisher : Institut Agama Islam Negeri (IAIN) Curup

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29240/arcitech.v6i1.16764

Abstract

This study aims to analyze topics in YouTube comments related to online gambling using Latent Dirichlet Allocation (LDA) and BERTopic, as well as to compare the performance of both methods. The dataset consists of 6,350 YouTube comments obtained from Kaggle. The analysis process includes preprocessing, topic modeling, and evaluation using topic coherence and topic diversity metrics. The results show that LDA achieves a topic coherence score of 0.511 and a topic diversity score of 1.0, while BERTopic achieves a topic coherence score of 0.667 and a topic diversity score of 0.449. These findings indicate that BERTopic produces more semantically coherent topics compared to LDA, although it has a higher level of overlap between topics. Furthermore, the interpretation results reveal that several identified topics are related to online gambling promotion, while others are influenced by noise in the comment data. Therefore, BERTopic is considered more effective for analyzing short and unstructured text data.
Evaluasi dan Perancangan Ulang UI/UX Website Dealer Otomotif Menggunakan Design Thinking dan User Experience Questionnaire Octarian Rudy Husin; Ahmad Farisi
Arcitech: Journal of Computer Science and Artificial Intelligence Vol. 6 No. 1 (2026): June 2026
Publisher : Institut Agama Islam Negeri (IAIN) Curup

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29240/arcitech.v6i1.16910

Abstract

The rapid growth of digital transformation has encouraged automotive dealer websites to function not only as information platforms but also as tools that provide effective and engaging user experiences. However, previous UI/UX studies have primarily focused on education, e-commerce, and general service sectors, while research on automotive dealer websites remains limited. This study aims to redesign the user interface and user experience of the Dealer ABC Palembang website using the Design Thinking method and evaluate its user experience quality through the User Experience Questionnaire Short Version (UEQ-S) and the User Experience Questionnaire (UEQ). The research was conducted through the five stages of Design Thinking: empathize, define, ideate, prototype, and testing. The initial evaluation using UEQ-S involved 42 respondents, while the final evaluation using UEQ involved 38 respondents after prototype testing. The results indicate positive scores across all UEQ dimensions, namely Attractiveness (1.33), Perspicuity (2.02), Efficiency (2.06), Dependability (1.93), Stimulation (1.97), and Novelty (1.49). Based on the UEQ benchmark, Perspicuity and Efficiency achieved the Excellent category, while the remaining dimensions were classified as Above Average to Good. These findings demonstrate that Design Thinking effectively enhances the user experience quality of automotive dealer websites.
Perancangan dan Evaluasi UI/UX Aplikasi Perpustakaan Digital Menggunakan Metode Design Thinking dan System Usability Scale Muhammad Patria; Steven Juan Felix Sihombing; Ilham Setiawan
Arcitech: Journal of Computer Science and Artificial Intelligence Vol. 6 No. 1 (2026): June 2026
Publisher : Institut Agama Islam Negeri (IAIN) Curup

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29240/arcitech.v6i1.16917

Abstract

Digital libraries play an important role in improving information accessibility and supporting digital literacy. However, many digital library applications still face usability challenges, particularly in navigation, collection retrieval, and digital reading experiences. In addition, previous studies have often focused on either interface design or usability evaluation separately, resulting in limited integration between user-centered design and usability assessment. This study aims to design and evaluate a digital library application by integrating Design Thinking and the System Usability Scale (SUS). The Design Thinking approach was implemented through five stages: empathize, define, ideate, prototype, and test, to identify user needs and develop a clickable prototype using Figma. Usability evaluation was conducted with ten respondents using the SUS instrument. The proposed prototype includes key features such as book search, category-based catalogs, digital reading, and an administrative dashboard. The evaluation produced a SUS score of 77.75, indicating a good level of usability and positive user perception. This study contributes by integrating Design Thinking and SUS within a unified development process to create a user-centered and quantitatively validated digital library prototype.
Analisis Komparatif Model Transfer Learning Inception-v3 dan Inception-v4 untuk Klasifikasi Citra Daun Tanaman Herbal Yosefa Camilia Moniung; Muhammad Ezar Al Rivan
Arcitech: Journal of Computer Science and Artificial Intelligence Vol. 6 No. 1 (2026): June 2026
Publisher : Institut Agama Islam Negeri (IAIN) Curup

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29240/arcitech.v6i1.16936

Abstract

Herbal plants represent one of Indonesia's rich biodiversity resources that have long been utilized in traditional medicine. However, manual identification remains challenging due to morphological similarities among plant species. Various studies have applied Convolutional Neural Network (CNN) for herbal plant classification, yet comparative analysis between Inception-v3 and Inception-v4 in this domain remains limited. This comparison is necessary as increased architectural complexity in Inception-v4 does not always guarantee better performance on small-scale datasets. This study aims to compare the performance of Inception-v3 and Inception-v4 transfer learning in classifying 10 herbal plant species using 1,000 leaf images. The novelty lies in a direct comparative analysis considering data augmentation and hyperparameter tuning. Pre-processing includes image resizing and augmentation, while hyperparameter tuning applies learning rate variations (0.001; 0.0001; 0.00001) and batch sizes (16, 32, 64). Evaluation was conducted using accuracy, precision, recall, and F1-score. Inception-v3 achieved the best performance with 98.50% accuracy, 98.55% precision, 98.50% recall, and 98.50% F1-score, providing an empirical benchmark for Inception architecture selection in leaf-based herbal plant classification.
Klasifikasi Penyakit Tanaman Jeruk Berdasarkan Citra Daun Menggunakan Metode Convolutional Neural Network Arsitektur EfficientNetV2-S Christian Richie Wijaya; Muhammad Rizky Pribadi
Arcitech: Journal of Computer Science and Artificial Intelligence Vol. 6 No. 1 (2026): June 2026
Publisher : Institut Agama Islam Negeri (IAIN) Curup

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29240/arcitech.v6i1.17003

Abstract

The classification of citrus leaf diseases still largely relies on traditional assessment by farmers, which may lead to errors in identifying disease types. Previous studies have widely applied Convolutional Neural Networks (CNNs) for plant disease classification; however, most have utilized first-generation EfficientNet architectures, while the application of EfficientNetV2-S for citrus leaf disease classification remains relatively limited. Furthermore, the implementation of a progressive fine-tuning strategy on the EfficientNetV2-S architecture for this task has not been extensively investigated. Therefore, this study aims to implement the EfficientNetV2-S architecture for citrus leaf disease classification. The dataset used was the Citrus Leaves Prepared dataset from Kaggle, consisting of 596 images categorized into four classes: blackspot, canker, greening, and healthy. The data underwent preprocessing and image augmentation, including flipping, rotation, and zooming, before being divided into training, validation, and testing sets with a ratio of 70:10:20. The model was developed using a transfer learning approach combined with progressive fine-tuning. Experimental results demonstrated that the proposed model achieved a testing accuracy of 93.33% under the 100-epoch training scenario. With this level of accuracy, the model shows strong potential for implementation as an early detection system for citrus leaf diseases, assisting farmers in making timely and appropriate decisions to prevent crop failure.
Implementasi Sistem Informasi Kluster Penjualan Beras Menggunakan Algoritma K-Means Syahrul Adi Saputra; Galet Guntoro Setiaji; Ahmad Rifa’i
Arcitech: Journal of Computer Science and Artificial Intelligence Vol. 6 No. 1 (2026): June 2026
Publisher : Institut Agama Islam Negeri (IAIN) Curup

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29240/arcitech.v6i1.17056

Abstract

Manual processing of rice sales transaction data results in data being archived and cannot be used optimally in decision-making. Therefore, business owners find it difficult to manage stock in sales planning. The K-Means Clustering algorithm was implemented in a web-based information system to create a recommendation feature for the best-selling rice. UD Maju Mapan, located in Demak Regency, was the location for the sales transaction data collection process for the sales period from October 2025 to March 2026. Data was processed using the Min-Max Normalization method and the K-Means algorithm with 3 clusters: premium, standard, and economy. The grouping will automatically appear in the dashboard display of the web-based information system, providing information for decision-making. The results show that the standard cluster has the largest amount of data compared to the premium and economy clusters. A value of 0.5361 is the result of the evaluation process using the Davies Bouldin Index method, which can be interpreted as quite good cluster quality. The rice sales information system is capable of managing and determining sales strategies and stock procurement based on the results of real transaction data analysis.
Klasifikasi Penyakit Daun Kelapa Menggunakan Xception Pada Data Imbalanced Dengan Smote Muhammad Totti Alfarabi; Daniel Udjulawa
Arcitech: Journal of Computer Science and Artificial Intelligence Vol. 6 No. 1 (2026): June 2026
Publisher : Institut Agama Islam Negeri (IAIN) Curup

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29240/arcitech.v6i1.17118

Abstract

The decline in coconut production due to Weligama Coconut Leaf Wilt Disease (WCLWD) and Coconut Caterpillar Infestation (CCI) can be detected using deep learning. However, previous studies have largely ignored extreme data imbalance ratios, leaving models vulnerable to pseudo-accuracy and failure in recognizing minority classes. Furthermore, no existing studies on coconut disease classification have specifically evaluated model robustness against visual anomalies and background bias. To fill this gap, this study not only integrates the Xception architecture with the SMOTE oversampling technique to overcome imbalanced data but also conducts comprehensive stress testing. Using 5,139 images distributed in a 70:15:15 ratio, SMOTE was specifically applied to the training data. The model was optimized using a 299x299 resolution, a learning rate of 0.00001, and a 0.5 Dropout layer. Testing demonstrated optimal results with an overall accuracy of 99%. The implementation of SMOTE successfully handled data imbalance without sacrificing the sensitivity of the minority class (healthy leaves), evidenced by a 0.95 Recall and 0.82 F1-Score. Moreover, as a novel evaluation, testing using anomalous Out-of-Distribution images revealed a background bias in the CCI class. Nevertheless, the low predictive confidence level (43.06%) confirms that the model's regularization effectively prevents overconfident predictions and optimally calibrates visual uncertainty.
Sistem Cerdas Deteksi Risiko Anemia Berbasis Hybrid Convolutional Neural Network dan Expert System pada Analisis Citra Konjungtiva Mata dan Gejala Klinis Pasien Ghefira Zahra Nur Fadhilah; Muh. Yamin; Asa Hari Wibowo
Arcitech: Journal of Computer Science and Artificial Intelligence Vol. 6 No. 1 (2026): June 2026
Publisher : Institut Agama Islam Negeri (IAIN) Curup

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29240/arcitech.v6i1.17146

Abstract

Anemia remains a global health problem, requiring early detection to prevent serious complications. Hemoglobin testing is invasive, while previous non-invasive screening approaches rely on a single parameter, limiting early detection effectiveness. This study develops a non-invasive anemia screening system using conjunctival images and clinical symptoms based on a Convolutional Neural Network (CNN) with MobileNetV2, an expert system, and a weighted hybrid method. A total of 3,870 conjunctival images were used for training and validation, while 50 test samples were collected using a smartphone and clinical symptom data. The results show that the CNN achieved 94% accuracy, the expert system 90%, and the hybrid method achieved 96% accuracy, 100% precision, 89% recall, and a 94% F1-score. These findings indicate that the integration of methods improves screening performance and supports a fast, easy, non-invasive, and practical anemia screening system for early detection that can be used independently at home with accessible devices.
Random Forest-Based Poverty Forecasting Using Socioeconomic Indicators in Bangka Belitung Islands Province Burham Isnanto; Rahmat Sulaiman
Arcitech: Journal of Computer Science and Artificial Intelligence Vol. 6 No. 1 (2026): June 2026
Publisher : Institut Agama Islam Negeri (IAIN) Curup

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29240/arcitech.v6i1.17171

Abstract

Poverty remains a significant socioeconomic challenge in the Bangka Belitung Islands Province, Indonesia, where economic dependence on tin mining and plantation commodities creates structural vulnerabilities that influence regional welfare conditions. Poverty remains a significant socioeconomic challenge in the Bangka Belitung Islands Province, Indonesia, where economic dependence on tin mining and plantation commodities creates structural vulnerabilities that influence regional welfare conditions. Previous poverty forecasting studies in Indonesia have predominantly employed statistical and econometric models, which are often limited in modeling non-linear socioeconomic interactions and are rarely validated using subnational panel data. Consequently, the potential of machine learning techniques, particularly Random Forest, for poverty prediction at the regency and municipal level remains underexplored. This study addresses this gap by developing a Random Forest-based poverty prediction model using socioeconomic indicators from 2019–2025. This study proposes a machine learning approach to predict poverty rates using the Random Forest algorithm implemented in Altair AI Studio (RapidMiner). Panel data covering the period 2019–2025 were collected from official publications of Badan Pusat Statistik (BPS) Bangka Belitung Islands Province. Three socioeconomic indicators were used as predictor variables: the Human Development Index (HDI), Open Unemployment Rate (OUR), and the number of poor people in each regency or municipality. The dataset consists of 49 observations representing seven administrative regions across seven years. The developed Random Forest model achieved an R² value of 0.800, an RMSE of 0.722, and an MAE of 0.561, demonstrating good predictive accuracy. The validated model was subsequently used to estimate poverty rates for 2026, producing predictions ranging from 2.762% to 6.244%. These findings highlight the potential of machine learning techniques to support poverty forecasting and evidence-based regional development policies.

Page 7 of 8 | Total Record : 76

 4   5   6   7   8 

Filter by Year

2021 2026


Reset
Filter By Issues
All Issue Vol. 6 No. 1 (2026): June 2026 Vol. 5 No. 2 (2025): December 2025 Vol. 5 No. 1 (2025): June 2025 Vol. 4 No. 2 (2024): December 2024 Vol. 4 No. 1 (2024): June 2024 Vol. 3 No. 2 (2023): December 2023 Vol. 3 No. 1 (2023): June 2023 Vol. 2 No. 2 (2022): December 2022 Vol. 2 No. 1 (2022): June 2022 Vol. 1 No. 2 (2021): December 2021 Vol. 1 No. 1 (2021): June 2021 More Issue