cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Muhammad Fadlan
Contact Email
fadlan@ppkia.ac.id
Phone
+6281216123988
Journal Mail Official
jbidai@ppkia.ac.id
Editorial Address
Kampus STMIK PPKIA Tarakanita Rahmawati, Jl. Halmahera 99 Oval Ladang IV Tarakan 77113 – Kalimantan Utara
Location
Kota tarakan,
Kalimantan utara
INDONESIA
Journal of Big Data Analytic and Artificial Intelligence
Published by Sekolah Tinggi Ilmu Manajemen Informatika dan Komputer Tarakanita Rahmawati
ISSN : 25979604     EISSN : 27223256     DOI : https://doi.org/10.71302
Core Subject : Science,
Computer Science & IT
JBIDAI adalah jurnal nasional berbahasa Indonesia versi online yang dikelola oleh Prodi Sistem Informasi STMIK PPKIA Tarakanita Rahmawati. Jurnal ini memuat hasil-hasil penelitian dengan cakupan fokus penelitian meliputi : Artificial Intelligence, Big Data, Data Mining, Information Retrieval, Knowledge Doscovering in Database dan bidang-bidang lainnya yang termasuk ke dalam rumpun ilmu tersebut.
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 7 Documents
 1 
Search results for , issue "Vol 8 No 2 (2025): JBIDAI Desember 2025" : 7 Documents clear
Penerapan K-Nearest Neighbor Untuk Klasifikasi Status Gizi Balita Di Puskesmas Karang Rejo Nurfadilah, Asriani; Anto, Anto; Fadlan, Muhammad
Journal of Big Data Analytic and Artificial Intelligence Vol 8 No 2 (2025): JBIDAI Desember 2025
Publisher : STMIK PPKIA Tarakanita Rahmawati

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.71302/jbidai.v8i2.71

Abstract

The issue of nutritional status in toddlers is one of the crucial concerns in the health sector, particularly in efforts to prevent stunting and malnutrition. At Karang Rejo Public Health Center, the assessment of toddlers’ nutritional status is still conducted manually by relying on weight-based estimation, which makes the classification process less efficient and increases the risk of inaccuracies in determining nutritional status. This study aims to apply the K-Nearest Neighbor (K-NN) algorithm as a faster and more accurate method for classifying toddlers’ nutritional status. The research stages include data collection, data processing, and the application of the K-NN algorithm. The data used consist of 100 toddler records, including the variables of weight-for-age (BB/U), height-for-age (TB/U), and weight-for-height (BB/TB) as the basis for determining nutritional status. The results show that the application of the K-NN algorithm with an optimal k value of 3 is able to produce nutritional status classifications that are consistent with doctors’ assessments. Performance evaluation using a Confusion Matrix on the test data yields an accuracy of 100%, with precision and recall values also reaching 100% for each nutritional status category. These findings indicate that all test data are classified correctly. Therefore, the application of this method is expected to assist healthcare workers at Karang Rejo Public Health Center in diagnosing and monitoring toddlers’ nutritional status more effectively and efficiently.
Implementasi Association Rule Mining pada Penentuan Pola Tata Letak Barang Menggunakan Metode Frequent Pattern Growth Virra Ayu Andira; Fitria, Fitria; Lies Hartono; Risma Sakila
Journal of Big Data Analytic and Artificial Intelligence Vol 8 No 2 (2025): JBIDAI Desember 2025
Publisher : STMIK PPKIA Tarakanita Rahmawati

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.71302/jbidai.v8i2.72

Abstract

CV. HKA (CV. Harapan Kaltim Abadi) is a distributor that sells several skin care, hair care, perfume, deodorant and baby care products, which will be distributed to customers. CV. HKA does not yet have a layout pattern for goods in the warehouse so that the storage of goods in the warehouse is irregular. Arranging the layout pattern of goods is needed to speed up the helper's performance so that it can shorten time and make it easier to pick up goods. Therefore, we need a system that can help determine item layout patterns by applying data mining. Association rules are used to search and find relationships between items in a dataset. The application of data mining with association rules aims to find information on items that are related to each other in the form of rules. Frequent Pattern-Growth (FP-Growth) is a method that can be used to determine the data set that appears most frequently (frequent item set) in a data set. This method aims to determine the layout decisions often taken by the helper. The results of the application using the FP-Growth method are rules that explain the helper's tendency to take goods simultaneously. These rules will determine the placement of goods in the warehouse. Based on the analysis system that has been created, it produces 10 rules from a combination of 2 items with the highest confidence value of 0.63, namely the Caplang brand item MKP and the Mandom brand item MR so that the two brands can be recommended to be placed close together. Apart from that, the resulting lift ratio value is more than 1, namely 1.21, the higher the lift ratio value, the stronger the resulting association rule.
Analisis Absorbansi Erionyl Blue Berbasis AI dan Synthetic Data pada Kuvet Kuarsa dan Akrilik Hartami Dewi; Wardani, Lestari; Saputra, Andri
Journal of Big Data Analytic and Artificial Intelligence Vol 8 No 2 (2025): JBIDAI Desember 2025
Publisher : STMIK PPKIA Tarakanita Rahmawati

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.71302/jbidai.v8i2.75

Abstract

The use of UV-Vis spectrophotometry in absorbance determination is a fundamental yet critical technique within the textile industry, particularly for quality control in dyeing processes. Recent advancements in Big Data and Artificial Intelligence (AI) offer opportunities to enhance the precision of spectrophotometric analysis through more extensive, accurate, and adaptive data processing. This study compares the performance of two cuvette materials, quartz and acrylic in the absorbance measurement of the synthetic textile dye Erionyl Blue. Samples were measured at six concentration levels with ten repetitions each, generating 120 data points. The dataset was analyzed using conventional statistical methods (two-way ANOVA with replication) and further enriched through AI-assisted data profiling to examine microvariance patterns.The ANOVA results indicated a statistically significant difference between quartz and acrylic cuvettes (p < 0.0001). However, AI-based profiling revealed that the effect size of this difference was minimal (<1.5%), suggesting negligible practical impact on absorbance interpretation. Therefore, acrylic cuvettes can be considered an economical alternative for academic and educational laboratory use, especially in high-throughput measurement scenarios.
Klasifikasi Kemiskinan Kabupaten dan Kota di Indonesia Berdasarkan Indikator Sosial Ekonomi Menggunakan Algoritma C4.5 Anugrah Suseno, Lorencia; Basami Hutapea, Tio; Kurniawan, Arga
Journal of Big Data Analytic and Artificial Intelligence Vol 8 No 2 (2025): JBIDAI Desember 2025
Publisher : STMIK PPKIA Tarakanita Rahmawati

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.71302/jbidai.v8i2.80

Abstract

Poverty remains major social issue in Indonesia, so an analysis of its causal factors is necessary to assist the government in making informed decisions. This study aims to classify poverty levels using the C4.5 algorithm by utilizing a dataset containing various socio-economic indicators such as education level, unemployment, and per capita expenditure. The research stages began with data collection and cleaning, transformation, splitting the dataset into training and testing data, and building the classification model. The results show that the C4.5 algorithm is capable of classifying poverty levels effectively and producing clear decision tree patterns. Based on the generated model, the per capita expenditure variable was identified as the dominant factor most influencing poverty status in a region. This model is expected to serve as a basis for formulating more targeted policies to reduce poverty levels in Indonesia.
Analisis Konseptual Fusi Multimodal Wajah dan Visual Speech untuk Autentikasi Biometrik Non-Vokal terhadap Deepfake Roihan, Ahmad; Dwi, Rosmawati; Astriyani, Erna
Journal of Big Data Analytic and Artificial Intelligence Vol 8 No 2 (2025): JBIDAI Desember 2025
Publisher : STMIK PPKIA Tarakanita Rahmawati

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.71302/jbidai.v8i2.84

Abstract

Biometric authentication systems still face fundamental limitations, particularly in unimodal approaches that are vulnerable to environmental variations and visual spoofing attacks. To address these challenges, multimodal biometrics integrating physiological and behavioral traits have become an increasingly relevant approach. This study presents an analytical review of recent research in visual multimodal biometrics, with a focus on score-level fusion strategies and the integration of static face recognition and dynamic lip movement analysis as a non-vocal authentication mechanism. The literature synthesis indicates that score-level fusion is the most flexible and stable approach for combining heterogeneous biometric modalities, especially when integrating static spatial features and dynamic temporal patterns. Furthermore, Transformer-based deep learning architectures are identified as having significant potential for modeling the temporal dependencies of lip movements. This study also highlights key security challenges, particularly presentation attacks and visual-only deepfakes, and emphasizes the importance of visual dynamics–based liveness detection as an integral component of biometric authentication systems. Based on these findings, the study formulates a conceptual framework for visual multimodal biometric authentication that integrates identity verification and liveness detection within a unified process, while also identifying future research opportunities, including self-supervised learning, model optimization for resource-constrained devices, and the design of more discriminative visual passphrases.
Implementasi K-Means Clustering untuk Mengelompokkan Data Produktivitas Penelitian Dosen di Una’im Yapis Wamena Syarifah, Syarifah; Ali, Muhammad; Samad, Asman; Nabillah Azza, Fayra; M, Hasriani; Susiana, Susiana
Journal of Big Data Analytic and Artificial Intelligence Vol 8 No 2 (2025): JBIDAI Desember 2025
Publisher : STMIK PPKIA Tarakanita Rahmawati

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.71302/jbidai.v8i2.90

Abstract

Una'im Yapis Wamena, as one of the higher education institutions in Papua, has a number of lecturers with various research activities. However, the challenge faced is the difficulty of comprehensively identifying the patterns and characteristics of faculty research. Without proper analysis, it is difficult for the institution to determine the research productivity profile of faculty members, identify those who require mentoring, or determine the focus of research capacity development. This can result in suboptimal allocation of resources, research support, and research development planning within the institution. This study aims to help determine the level of productivity of lecturers in research with high, medium, and low categories. With this grouping, it is hoped that the Una'im Yapis Wamena Campus can more easily make decisions about the appropriate coaching methods to improve the research results of lecturers. The method used in this study is K-means Clustering. The data analyzed included 45 lecturers with variables such as number of publications, number of citations, H-index, funded research, and research collaboration. The results of this study show that the level of faculty research productivity can be grouped into three categories, namely: Cluster 1 (High Productivity) consisting of 8 faculty members, Cluster 2 (Medium Productivity) consisting of 25 faculty members, and Cluster 3 (Low Productivity) consisting of 12 faculty members. The clustering process reached convergence in the 6th iteration with stable results. These clustering results can serve as a guide for Una'im Yapis Wamena in determining policies to increase lecturer research productivity in the future.
Implementasi Data Mining Pada Penentuan Kelayakan Penerima Beasiswa SMA Kristen Tunas Kasih Arrafi, Haykal Fachmi; Wendy, Jefferi Ciu; Bintari, Evi Dianti; Anto, Anto; Lusiana, Lusiana
Journal of Big Data Analytic and Artificial Intelligence Vol 8 No 2 (2025): JBIDAI Desember 2025
Publisher : STMIK PPKIA Tarakanita Rahmawati

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.71302/jbidai.v8i2.82

Abstract

Determining the eligibility of scholarship recipients often faces problems of subjectivity and inaccuracy of targeting due to the limitations of manual assessment. This research implements the Modified K-Nearest Neighbor (MKNN) method to determine scholarship eligibility at SMA Kristen Tunas Kasih, under the auspices of the Gereja Kebagunan Kalam Allah Indonesia (GKKAI). The goal is to build an accurate and objective classification system for selecting financially disadvantaged yet promising students. The dataset consists of 112 active students from the 2023/2024 academic year, divided into 90 training data and 22 testing data (80:20 ratio). Classification criteria include parental employment, parental income, and parental status. The MKNN method is implemented through several stages: Euclidean distance calculation, data normalization, validation, and weight voting. The system is developed as a web application using PHP and MySQL, featuring student data management, training-testing data division, weight calculation, and result visualization. Testing results show an accuracy of 95.45%, precision of 100%, recall of 75%, and F-measure of 85.71%. Out of 22 testing data, 21 were classified correctly, with only 1 mismatch. The optimal K value found through Grid Search is K = 3, yielding the best classification. This study demonstrates that the MKNN method delivers strong performance in determining scholarship recipient eligibility.

Page 1 of 1 | Total Record : 7

 1 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol 8 No 2 (2025): JBIDAI Desember 2025 Vol 8 No 1 (2025): JBIDAI Juni 2025 Vol 7 No 2 (2024): JBIDAI Desember 2024 Vol 7 No 1 (2024): JBIDAI Juni 2024 Vol 6 No 2 (2023): JBIDAI Desember 2023 Vol 6 No 1 (2023): JBIDAI Juni 2023 Vol 5 No 1 (2019): JBIDAI Juni 2019 Vol 4 No 1 (2018): JBIDAI Juni 2018 Vol 3 No 1 (2017): JBIDAI Juni 2017