cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Raissa Amanda Putri
Contact Email
bigint2023@gmail.com
Phone
+6281263607775
Journal Mail Official
aira@aira.or.id
Editorial Address
Jl Pukat Banting IV NO 41 Medan Tembung District Postal Code 20224
Location
Kota medan,
Sumatera utara
INDONESIA
Bigint Computing Journal
Published by Ali Institute of Research and Publication
ISSN : -     EISSN : 30325374     DOI : 10.55537/bigint
Core Subject : Science,
Computer Science & IT
Bigint Computing Journal is a journal that discusses science in the field of computing, namely: Computer Engineering (CE): Computer Engineering/Computer Systems/Information Engineering, Computer Science (CS): Computer Science/Informatics, Software Engineering (SE): Engineering Software, Information Systems (IS): Information Systems, and Information Technology (IT): Information Technology. The Bigint Computing Journal is published two times a year in the January and July editions. The submitted manuscript will be received by the editor and then checked for similarity to the Turnitin application. The review process is carried out using peer review.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 45 Documents
 1   2   3   4   5 
Streamlit-Based Durian Yield Forecasting Using an ARIMA Model Nurul Ifkah Lolona Silalahi; Triase Triase
Bigint Computing Journal Vol 4 No 2 (2026)
Publisher : Ali Institute of Reseach and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/bigint.v4i2.1852

Abstract

Durian production in Dairi Regency, North Sumatra, fluctuates substantially across quarters, creating uncertainty for harvest planning and distribution. This study develops a lightweight decision-support system that integrates an AutoRegressive Integrated Moving Average (ARIMA) forecasting pipeline with a Streamlit web application. The source dataset contains 41,060 agricultural harvest records from 2020–2024, aggregated into 20 quarterly regional observations. The raw series was non-stationary according to the Augmented Dickey–Fuller test (ADF = −0.449, p = 0.901), while first-order differencing produced a stationary series (ADF = −4.120, p = 0.0009). Automated model search selected ARIMA (4,0,1), with AIC = 401.649 and BIC = 407.624. A chronological 80/20 holdout evaluation on the four quarters of 2024 produced an RMSE of 1.16 tons, MAE of 1.15 tons, and MAPE of 4.33%, recalculated from the reported quarter-level forecasts. The Streamlit implementation integrates data management, stationarity diagnosis, automated parameter selection, and forecast visualization. The results indicate that an interpretable ARIMA baseline can provide useful short-horizon regional forecasts when historical data are limited, although the short series requires cautious generalization and further validation.
OCR-LSTM-Based Detection of Pork-Derived Non-Halal Ingredients from Food Labels Muhammad Siddik Hasibuan; Suhardi Suhardi; Bagus Ageng Alfahri
Bigint Computing Journal Vol 4 No 2 (2026)
Publisher : Ali Institute of Reseach and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/bigint.v4i2.1856

Abstract

Packaged food labels may contain technical and multilingual ingredient terms that complicate preliminary screening for pork-derived non-halal substances. This study develops a web-based pipeline that integrates optical character recognition (OCR), automatic translation, and Long Short-Term Memory (LSTM) text classification. A public dataset of 528,092 labeled ingredient records, comprising 291,920 halal and 236,172 pork-related non-halal records, was used for model development. After text normalization, tokenization, and sequence padding, the data were divided into training, validation, and testing subsets using an 80:10:10 ratio. The final test set contained 52,810 records. The confusion matrix contained 29,182 true negatives, 12 false positives, 41 false negatives, and 23,575 true positives, corresponding to 99.90% accuracy, 99.95% precision, 99.83% recall, and a 99.89% F1-score. The web implementation accepts label images, extracts text, translates non-English content, and applies the trained classifier. The reported metrics evaluate the text classifier rather than the complete OCR-to-classification pipeline; therefore, the system should be treated as a preliminary screening tool and not as a substitute for formal halal certification.
Naïve Bayes-Based Classification of Wrestling Athletes Using Physical Performance Data Achmad Zoemirrotin Siregar; Ali Ikhwan
Bigint Computing Journal Vol 4 No 2 (2026)
Publisher : Ali Institute of Reseach and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/bigint.v4i2.1868

Abstract

Objective evaluation of athletes’ physical test data can help reduce subjectivity in athlete assessment. This study develops a web-based classification system using the Naïve Bayes algorithm to classify wrestling athletes as Successful or Unsuccessful based on speed, balance, and agility attributes. The study uses a quantitative approach and the Waterfall software development model. The dataset consists of 36 wrestling athlete records, with 30 records used as training data to calculate prior and conditional probabilities and 6 independent records reserved for final testing; the testing records were not used during the training or probability calculation process. Speed is categorized as Slow, Normal, or Fast; balance as Poor, Fair, or Good; and agility as Low, Medium, or High. The target labels, Successful and Unsuccessful, were assigned independently based on recorded athlete performance assessment outcomes and were not derived from the predictor variables. The Naïve Bayes classification process calculates class priors, attribute likelihoods, posterior probabilities, and predicted classes. For the illustrated test case with Slow speed, Poor balance, and Low agility, the normalized probabilities were 4% for Successful and 96% for Unsuccessful. The six-record performance evaluation produced 83.33% accuracy, 75% precision, 100% recall, and an 85.71% F1-score. The system can support structured and more objective athlete assessment; however, the limited dataset size may restrict the generalizability of the results and requires validation using a larger dataset.
Student Awareness of Information Ethics in the Use of Artificial Intelligence for Academic Writing Based on the PAPA Framework Alya Rasyifa; Franindya Purwaningtyas
Bigint Computing Journal Vol 4 No 2 (2026)
Publisher : Ali Institute of Reseach and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/bigint.v4i2.1879

Abstract

The rapid development of Artificial Intelligence (AI) has provided new opportunities for students in academic activities and scientific writing while raising ethical concerns related to privacy, information accuracy, ownership, and accessibility. This study aimed to describe students’ self-reported awareness and perceptions of Information Ethics in using AI for scientific writing based on Mason’s Privacy, Accuracy, Property, and Accessibility (PAPA) framework. This study employed a quantitative descriptive approach. Data were collected through a closed-ended questionnaire from 100 Universitas Sumatera Utara students selected using purposive sampling. The instrument consisted of 18 Information Ethics items based on the PAPA dimensions and 14 supporting items related to scientific writing, covering aspects of the Theory of Planned Behavior and Information Literacy. Data were analyzed using descriptive statistics, Corrected Item-Total Correlation, and Cronbach’s Alpha. The results showed that the overall mean score of Information Ethics was 3.9689, indicating a high category. Privacy obtained the highest mean score (4.0400), followed by Accuracy (3.9760), Property (3.9500), and Accessibility (3.8900). The supporting constructs also showed relatively high descriptive results. These findings reflect respondents’ self-reported awareness and perceptions rather than direct evidence of actual ethical behavior. The findings provide contextual input for strengthening information literacy and responsible AI-use guidelines in higher education.
Multivariate Analysis of Livestock Feed Availability Using K-Means Clustering for Regional Potential Mapping in Pati Regency Ridwan Potabuga; Fajar Husain Asyari; Ellen Proborini
Bigint Computing Journal Vol 4 No 2 (2026)
Publisher : Ali Institute of Reseach and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/bigint.v4i2.1927

Abstract

Livestock feed availability plays a crucial role in livestock production and regional food security. This study aims to map the potential of sub-districts in Pati Regency based on livestock feed availability from 2020 to 2024 using multivariate clustering with the K-Means algorithm. Secondary data were obtained from the Pati Regency Agriculture Office and used to classify 21 sub-districts according to similarities in annual feed availability, measured in tons of feed per year, which provides the quantitative basis for assessing livestock carrying capacity. The analysis included missing-value checking, outlier detection, data standardisation, dimensionality reduction using principal component analysis, and determination of the optimal number of clusters using the Silhouette Coefficient. Among the non-degenerate solutions (k ≥ 3), three clusters yielded the highest silhouette score (0.4383), and this solution was stable across initialisations and robust to the exclusion of the most extreme observation. Cluster 1 represents sub-districts with moderate feed availability, Cluster 2 represents areas with very high and fluctuating feed availability, and Cluster 3 represents sub-districts with high and stable feed availability. These clusters reveal distinct regional characteristics that can support strategic decision-making in livestock development. Areas with moderate availability require policy intervention, regions with high and stable availability have strong potential for sustainable development, and areas with very high but fluctuating availability require careful resource management. This study demonstrates that the K-Means algorithm is effective for mapping livestock feed availability and supporting regional planning for livestock sector development in Pati Regency.

Page 5 of 5 | Total Record : 45

 1   2   3   4   5 

Filter by Year

2023 2026


Reset
Filter By Issues
All Issue Vol 4 No 2 (2026) Vol 4 No 1 (2026) Vol 3 No 2 (2025) Vol 3 No 1 (2025) Vol 2 No 2 (2024) Vol 2 No 1 (2024) Vol 1 No 2 (2023) Vol 1 No 1 (2023)