cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
,
INDONESIA
JOURNAL OF APPLIED INFORMATICS AND COMPUTING
Published by Politeknik Negeri Batam
ISSN : -     EISSN : 25486861     DOI : 10.3087
Core Subject : Science,
Computer Science & IT
Journal of Applied Informatics and Computing (JAIC) Volume 2, Nomor 1, Juli 2018. Berisi tulisan yang diangkat dari hasil penelitian di bidang Teknologi Informatika dan Komputer Terapan dengan e-ISSN: 2548-9828. Terdapat 3 artikel yang telah ditelaah secara substansial oleh tim editorial dan reviewer.
Arjuna Subject : -
Articles 1,006 Documents
 97   98   99   100   101 
Comparative Analysis of Random Forest and Long Short-Term Memory for Predicting Optical Power Degradation in FTTH Networks Hermansyah Hermansyah; Taufiq Taufiq; Defry Hamdhana; Munirul Ula; Muhammad Ikhwanus
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13717

Abstract

Fiber-to-the-Home (FTTH) networks are widely used to provide high-speed broadband services, but optical power degradation can reduce network performance and service quality. This study compares Random Forest (RF) and Long Short-Term Memory (LSTM) for predicting FTTH network conditions classified as Normal, Warning, and Critical. The study used 63,145 historical records collected from 58 Optical Network Terminals (ONTs) between March and May 2026. To provide a fair comparison, RF was trained using engineered tabular features, including lag and rolling-window statistics, while LSTM used six-step sequential data representing approximately the previous six hours. Model performance was evaluated using accuracy, precision, recall, F1-score, Mean Absolute Error (MAE), Root Mean Square Error (RMSE), training time, and inference time. The results show that RF substantially outperformed LSTM, achieving 98.41% accuracy, precision, recall, and F1-score, with an MAE of 0.0173 and RMSE of 0.1420. RF also required only 2.667 seconds for training and 0.0102 ms for inference, compared with 189.98 seconds and 0.1856 ms for LSTM. Per-class evaluation confirmed that RF performed well across all network conditions, with precision and recall above 99% for Normal, above 94% for Warning, and above 90% for Critical. A strict chronological train-test split further confirmed the robustness of RF, which achieved 98.59% accuracy. Feature importance analysis showed that historical optical power, particularly lag-based features, was the most influential predictor of network degradation. These findings indicate that FTTH optical power degradation can be effectively modeled using engineered tabular features rather than a purely sequential approach. Finally, the RF model was integrated into a web-based monitoring dashboard with WhatsApp-based early warnings to support proactive FTTH network maintenance.
Performance Comparison of Point-to-Point and Point-to-Multipoint Fiber Optic Networks Using QoS Parameters and the Analytical Hierarchy Process (AHP) Husni Husni; Taufiq Taufiq; Defry Hamdhana; Muhammad Daud; Asrianda Asrianda
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13728

Abstract

The rapid growth of internet traffic in Indonesia, including in Aceh Province, requires an optical fiber network infrastructure that is both efficient and reliable. Two fundamental architectures, Point-to-Point (P2P) and Point-to-Multipoint (P2MP), offer different trade-offs between service quality and cost efficiency, yet a quantitative comparison that combines Quality of Service (QoS) measurement with a structured multi-criteria decision-making method remains limited. This study experimentally measures the throughput, delay, jitter, packet loss, and bandwidth of P2P and P2MP networks implemented at Universitas Almuslim, Bireuen, Aceh, using iPerf3 and Wireshark under varying client loads of 1, 2, 4, 8, and 16 users, and applies the Analytical Hierarchy Process (AHP) to weight the QoS criteria and rank the two architectures. The results show that P2P consistently outperforms P2MP on every QoS parameter, maintaining an average throughput of 95 Mbps, a delay of 2.68 ms, a jitter of 0.85 ms, a packet loss of 0.054%, and a fixed bandwidth of 100 Mbps, whereas P2MP degrades progressively as the number of users increases. AHP weighting identified throughput as the most influential criterion (0.50), followed by bandwidth (0.26), delay (0.13), jitter (0.07), and packet loss (0.03), with a Consistency Ratio of 0.054, confirming that the pairwise judgments were consistent. The resulting AHP scores were 9.00 for P2P and 2.66 for P2MP, indicating that P2P is the more optimal architecture for QoS-sensitive deployments, while P2MP remains advantageous where cost efficiency and wide coverage are prioritized.
IoT-Based Sign Language Translation System for Deaf Individuals Nafla Zahira Semry; Iman Fahruzi
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13742

Abstract

Deaf-mute individuals face significant communication barriers due to limited public familiarity with sign language. In Indonesia, SIBI (Sistem Isyarat Bahasa Indonesia) is the government-standardised one-handed finger-spelling system used as the basis of communication for the hearing-impaired. This paper presents the design, implementation, and evaluation of an IoT-based hand sign language translator glove that recognises all 26 SIBI alphabet letters and displays the result on an Android application. The glove integrates five flex sensors for finger-bending detection, a GY-91 module (MPU-9250 + BMP280) for wrist orientation measurement, and a CD4051 analog multiplexer, all processed by a Wemos D1 Mini (ESP8266) microcontroller. Sensor readings are classified using a threshold-based decision method calibrated across three subjects. Classified letter data are transmitted via MQTT over Wi-Fi to a cloud broker and rendered in real time by an Android application. Experimental evaluation covers flex sensor resistance characterisation for all 26 SIBI letters, GY-91 gyroscope orientation profiling, multi-subject threshold calibration, end-to-end application display accuracy, and voltage measurement error percentage. Results confirm that the combined flex-sensor and gyroscope approach identifies SIBI alphabet letters with 90.00% end-to-end display accuracy and a voltage measurement error below 5%, indicating the preliminary feasibility of a low-cost, single-hand wearable IoT glove as an assistive sign-language communication aid, based on testing with a small number of participants. The system in its current form translates individual static SIBI alphabet letters only; it does not yet recognise dynamic gestures, whole words, or continuous sentence-level sign language.
Convolutional Neural Network-Based Approach For In-Ovo Embryo Classification Khoironi Khoironi; Ibram Maulana Akhsanul Qasasi; Ahmad Khairul Umam; Much Chafid; Ahmad Walid Hujairi; I Wayan Rangga Pinastawa; Musthofa Galih Pradana
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13752

Abstract

The egg hatching process is a crucial stage in chicken breeding, as the quality of the resulting embryos will greatly determine the productivity and success of the cultivation. However, monitoring the internal condition of eggs during incubation is still limited and is generally done manually using the candling method. Therefore, a non-invasive approach is needed to support the process of monitoring embryo development. This study aims to develop a chicken embryo classification system based on in-ovo images using a Convolutional Neural Network (CNN). This system utilizes internal egg images taken with a camera integrated in the incubator, so that the condition of the eggs can be automatically classified into categories of fertile, infertile, and developmental failure. The research stages include collecting in-ovo image data, preprocessing in the form of removing the background using the rembg library, and resizing the images to 224 × 224 pixels. The dataset was then divided into training data and test data with a ratio of 90%:10%. The CNN model was built with several layers, namely convolution, max pooling, dropout, flattening, and fully connected, then trained for 28 epochs with a batch size of 32. The results showed that the developed CNN model was able to achieve an accuracy of 90.5% in the 24th epoch and experienced a decrease in the 26th to 28th epochs. Testing also used images from different incubators than those used from the dataset showed that the model could classify egg conditions well.
Implementation of a Hybrid TabNet–XGBoost Model Based on Radiosonde Data for Predicting Daily Rainfall Intensity in Surabaya Annabel Gracia Puryani; Aviolla Terza Damaliana; Alfan Rizaldy Pratama
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13767

Abstract

Rainfall prediction plays an important role in supporting hydrometeorological disaster mitigation and weather-related decision-making. However, accurate rainfall prediction remains challenging because atmospheric processes are highly nonlinear and governed by complex interactions among multiple meteorological variables. This study proposes a Hybrid TabNet–XGBoost model for daily rainfall prediction using integrated radiosonde and surface meteorological observations collected at the BMKG Juanda Class I Meteorological Station. The dataset covers the period from 2019 to 2025 and consists of 2,551 daily observations. TabNet was employed to select the fifteen most informative atmospheric variables based on feature importance, while temporal dependencies were incorporated through lag features generated using Autocorrelation Function (ACF) and Partial Autocorrelation Function (PACF) analyses. Hyperparameter optimization was performed using Optuna with TimeSeriesSplit cross-validation prior to model training. Experimental results on the testing dataset achieved an RMSE of 19.1347 mm, an MAE of 11.9742 mm, a MAPE of 17.62%, and an R² of 0.0449. The proposed model was able to capture the general temporal pattern of daily rainfall and produced satisfactory predictions under the dominant rainfall conditions represented in the dataset. However, the model exhibited reduced sensitivity to high-intensity rainfall events, resulting in the underestimation of extreme rainfall and a relatively low R² value, primarily due to the imbalanced rainfall distribution and the complexity of rainfall processes. The optimized model was subsequently applied to generate daily rainfall projections for 2026 based on historical atmospheric observations. Since the corresponding observational data were unavailable at the time of this study, these projections should be interpreted as model-based forecasts rather than validated prediction results. Overall, the proposed Hybrid TabNet–XGBoost framework demonstrates the potential of integrating radiosonde and surface meteorological observations for daily rainfall prediction while highlighting the need for additional atmospheric and spatial information to improve the prediction of extreme rainfall events.
Comparative Analysis of Siamese BiLSTM and IndoBERT for Semantic Textual Similarity Detection in Functional Scientific Papers of Meteorology, Climatology, and Geophysics Officers at BMKG Dhedy Listyawan; Ahmad Musyafa; Choirul Basir
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13773

Abstract

The competency assessment process for Meteorology, Climatology, and Geophysics (PMG) functional officers at BMKG requires manual review of Scientific Paper (KTI) similarity, a task that is time-consuming, prone to subjectivity, and increasingly burdensome as submission volume grows. While Semantic Textual Similarity (STS) research has advanced considerably for high-resource languages, empirical evidence for Indonesian-language technical documents in specialized scientific domains remains limited, and prior work has not established which neural architecture is preferable under such data-constrained conditions. This study addresses that gap by empirically comparing two Siamese Network architectures, Siamese BiLSTM and IndoBERT, for automatic STS detection on 87 PMG KTI documents, yielding 3,741 document pairs automatically labeled using the 90th percentile of TF-IDF cosine similarity scores and validated against manual annotation (Cohen's Kappa κ=0.82). Siamese BiLSTM employs Word2Vec embeddings with Focal Loss, while IndoBERT fine-tunes the pretrained indobert-base-p1 model with Contrastive Loss; both apply class weighting to address the 90:10 class imbalance, with classification thresholds independently calibrated via grid search. Evaluated on 1,123 held-out test pairs, Siamese BiLSTM achieves an F1-Score of 64.84% (Accuracy 91.99%, Precision 58.04%, Recall 73.45%) at threshold 0.60, outperforming IndoBERT's F1-Score of 57.73% (Accuracy 89.05%, Precision 47.19%, Recall 74.34%) at threshold 0.935, a difference confirmed statistically significant by McNemar's test (χ²=7.6992; p=0.0055). This result runs counter to the common assumption that Transformer-based models universally outperform recurrent architectures, suggesting that smaller, domain-tuned embeddings can be more effective under limited-data, domain-specific conditions. The better-performing Siamese BiLSTM model, requiring only 16.77 MB with no GPU dependency, was deployed as a Streamlit web application, enabling the BMKG PMG Assessment Team to perform similarity detection quickly and consistently within their existing workflow.

Page 101 of 101 | Total Record : 1006

 97   98   99   100   101 

Filter by Year

2017 2026


Reset
Filter By Issues
All Issue Vol. 10 No. 4 (2026): August 2026 Vol. 10 No. 3 (2026): June 2026 Vol. 10 No. 2 (2026): April 2026 Vol. 10 No. 1 (2026): February 2026 Vol. 9 No. 6 (2025): December 2025 Vol. 9 No. 5 (2025): October 2025 Vol. 9 No. 4 (2025): August 2025 Vol. 9 No. 3 (2025): June 2025 Vol. 9 No. 2 (2025): April 2025 Vol. 9 No. 1 (2025): February 2025 Vol. 8 No. 2 (2024): December 2024 Vol. 8 No. 1 (2024): July 2024 Vol. 7 No. 2 (2023): December 2023 Vol. 7 No. 1 (2023): July 2023 Vol. 6 No. 2 (2022): December 2022 Vol 6 No 1 (2022): July 2022 Vol. 5 No. 2 (2021): December 2021 Vol 5 No 2 (2021): December 2021 Vol 5 No 1 (2021): July 2021 Vol. 5 No. 1 (2021): July 2021 Vol 4 No 2 (2020): Desember 2020 Vol. 4 No. 2 (2020): Desember 2020 Vol 4 No 1 (2020): Juli 2020 Vol 3 No 2 (2019): Desember 2019 Vol 3 No 1 (2019): Juli 2019 Vol 2 No 2 (2018): Desember 2018 Vol 2 No 1 (2018): Juli 2018 Vol. 2 No. 1 (2018): Juli 2018 Vol 1 No 2 (2017): Desember 2017 Vol 1 No 1 (2017): Juli 2017 More Issue