cover
Contact Name
Husni Teja Sukmana
Contact Email
husni@bright-journal.org
Phone
+62895422720524
Journal Mail Official
jads@bright-journal.org
Editorial Address
Gedung FST UIN Jakarta, Jl. Lkr. Kampus UIN, Cemp. Putih, Kec. Ciputat Tim., Kota Tangerang Selatan, Banten 15412
Location
Kota adm. jakarta pusat,
Dki jakarta
INDONESIA
Journal of Applied Data Sciences
Published by Bright Publisher
ISSN : -     EISSN : 27236471     DOI : doi.org/10.47738/jads
One of the current hot topics in science is data: how can datasets be used in scientific and scholarly research in a more reliable, citable and accountable way? Data is of paramount importance to scientific progress, yet most research data remains private. Enhancing the transparency of the processes applied to collect, treat and analyze data will help to render scientific research results reproducible and thus more accountable. The datasets itself should also be accessible to other researchers, so that research publications, dataset descriptions, and the actual datasets can be linked. The journal Data provides a forum to publish methodical papers on processes applied to data collection, treatment and analysis, as well as for data descriptors publishing descriptions of a linked dataset.
Articles 1,270 Documents
Coverless Text Information Hiding Based on Built-in Features of Arabic Scripts Sabaa Hamid Rashid; Dhamyaa A Nasrawi
Journal of Applied Data Sciences Vol 5, No 2: MAY 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i2.243

Abstract

Text steganography is crucial in information security due to the limited redundancy in text. The Arabic language features offer a new method for data concealment. In this paper, the researchers propose a new coverless text information hidingmethod based on built-in features of Arabic scripts. The first word of each row in the dataset is tested based on eight features to get one byte containing 1 or 0. That is a result of the presence or absence of the following features: mahmoze, diacritics, isolated, two sharp edges, vowels, dotted, looping, and high frequency.Then, each byte is converted to a decimal number (ASCII code) to implement a dynamic mappingprotocol with the most frequent letter.In the hiding process, each character in the secret message is converted to ASCII code and successfully matched in the dataset. Thus, after matching, the candidate text is sent to the receiver. In contrast, the pre-agreed dynamic mappingprotocol was implemented in a receiver to extract secret messages. Three Arabic datasets are used in this paper (SANAD (Single-Label Arabic News Articles Dataset) includes 45500 articles, Arabic Poem Comprehensive Dataset (APCD) contains 1,831,770 poetic verses in total, Arabic Poetry Dataset contains more than 58000 poems). The suggested approach withstands existing detecting methods because of no modification or generation. Moreover, there is an enhancement in hiding capacity, which can conceal a (character /word). Hence, all the messages are embedded successfully using dynamic mapping.
Type Deep Learning Model for Multi-Label Waste Classification in Canal Environments: A Comparative Study with CNN Architectures Najirah Umar; Billy Eden William Asrul; Yuyun Yuyun
Journal of Applied Data Sciences Vol 7, No 1: January 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i1.1066

Abstract

The escalating environmental degradation caused by waste underscores the necessity of developing intelligent and sustainable management systems. This study introduces a deep learning–based framework with proposed a modified ConvNeXt architecture enhanced by a two-layer non-linear MLP classification, specifically designed for multi-object waste classification in canal environments. Specifically, ConvNeXt-CNN is introduced as the primary backbone for extracting visual features from waste images. Then, a modified Multi-Layer Perceptron (MLP) is employed to transform these features into multi-label predictions. To optimize the model’s generalization capability in recognizing the complexity of waste images, a hybrid data augmentation technique combining SMOTE and MixUp was applied during training. The proposed approach was then compared with ten fine-tuned Convolutional Neural Network (CNN) architectures, ResNet18, ResNet50, VGG16, VGG19, DenseNet121, MobileNet_v2, and EfficientNet (B0, B1, B2, and B3), and evaluated using accuracy, precision, recall, and F1-score metrics. The experimental dataset comprises 855 waste images containing a total of 2,662 annotated objects across 18 categories, including Bamboo, Beverage Carton, Cardboard, Fabric, Glass Bottle, Inorganic Waste, Kite, Leaf, Metal, Organic Waste, Paper, Plastic, Plastic Bottle, Plastic Cup, Residual Waste, Rubber, Small E-waste, Styrofoam, and Wood. The results show that the fine-tuned ConvNeXt achieved the best performance with an F1-score of 0.99, surpassing DenseNet121 (0.95), ResNet18 (0.91), and VGG16 (0.94). The ConvNeXt model demonstrated its robust capability by achieving consistently high identification scores across majority 18 waste categories. When it came to training efficiency, the fine-tuned MobileNetV2 model proved to be the top performer, outclassing ten other pretrained models, with a training time of 13.35s per epoch.  Results exhibit that finetuned ConvNext outperforms in terms of accuracy, recall, precision, and F1-score. In conclusion, Integrating ConvNeXt and MLP for multi-object waste classification effectively supports intelligent waste management, enabling practical real-world deployment in smart bins, Material Recovery Facilities, and IoT-integrated urban waste systems.
Rapid Ecosystem-Driven Deep Learning: On-Device Grain Type Classification and Authentication using iOS Swift and Core ML Trianggoro Wiradinata
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1414

Abstract

The 2025 Indonesian rice scandal highlighted major shortfalls in food security and the pressing need for robust, data-based verification of authenticity. The goal of this work is to design a fast, lightweight, and fully offline rice grain classification and verification system that can run directly on consumer mobile hardware. The basic idea to overcome the technical bottleneck of deploying complex computer vision models on edge devices is to use macOS and Apple’s unified ecosystem as a rapid prototyping and deployment platform. The deliberate avoidance of fragmented and high-latency workflows such as external environments (e.g. TensorFlow or PyTorch) and intermediate formats (e.g. ONNX) is mentioned. The study contributes a streamlined pipeline that incorporates an Image Feature Print V1 feature extractor, natively trained with Create ML on a publicly available dataset of 75,000 balanced images of five rice varieties (Arborio, Basmati, Ipsala, Jasmine, and Karacadag), directly into a native iOS application built with SwiftUI. The novelty of this approach is the usage of native tools like VisionKit and Core ML, which enables the complete elimination of third-party bridging code that normally bloats the binary overhead. The results show excellent edge efficiency on an iPhone 15 with a median prediction rate of 2.75 ms, an initial load time of 0.54 ms and a compilation latency of 3.66 ms. Moreover, the results reveal that by employing aggressive data augmentations, including the addition of visual noise, blur, exposure adjustment, flipping and rotation to ensure robustness, and by deliberately not cropping to preserve absolute grain dimensions, the model achieved a remarkable overall accuracy of 97% with an ultra-compact deployment footprint of only 66 KB. These metrics demonstrate that a fast, fully offline and privacy-preserving verification system is well within reach with modern consumer hardware.
Analysis of Heart Rate Variability of College Students in Altitude Training Based on Big Data Huiling Wang; Jingyuan Yang
Journal of Applied Data Sciences Vol 1, No 2: DECEMBER 2020
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v1i2.55

Abstract

Heart activity is regulated by sympathetic and parasympathetic autonomic nerves, which is a common method to measure and evaluate autonomic nerve activity. Collecting ECG data of college students and analyzing heart rate variability can evaluate autonomic nerve activity of college students. This paper discusses the influence of altitude training on students' heart rate variability, and the influence of altitude hypoxia and low pressure on students' autonomic nervous system, which provides a scientific basis for coaches to control the training intensity and amount and reduce the risk factors. The results show that good adaptability of altitude training can improve the activity ability of the vagus nerve.
A Study of Unified Framework for Extremism Classification, Ideology Detection, Propaganda Analysis, and Flagged Data Detection Using Transformers R S Lakshmi Balajia; C S Thiruvenkataswamy; Malathy Batumalay; N. Duraimutharasan; Amar Dev Thirukulam Devadas; Thaweesak Yingthawornsuk
Journal of Applied Data Sciences Vol 6, No 3: September 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i3.702

Abstract

The rise of extremism and its rapid dissemination through propaganda channels have become pressing global challenges, threatening peace, security, and social cohesion. This study aligns with the United Nations Sustainable Development Goal 16 by proposing a unified framework leveraging advanced machine learning and large language models to combat extremism through extremism classification, ideology detection, propaganda analysis, and flagged word recognition. This framework introduces process innovation by integrating state-of-the-art transformer models such as BERT, RoBERTa, DistilBERT and XLNet to streamline the analysis process and overcome traditional limitations in extremism detection with exceptional performance: 90.00% accuracy for extremism classification, 98.82% accuracy for ideology detection, and 99.71% accuracy for flagged word recognition. While the proposed approach demonstrates high precision and recall, it faces challenges such as potential data bias, ethical concerns in dataset usage and the risk of false positives, which could lead to misclassification of benign content. The inclusion of multilingual capabilities broadens the applicability of the framework but variations in linguistic structures and cultural contexts introduce complexities in model generalization. Additionally, ethical considerations in handling extremist content, especially in social media data collection, necessitate stringent privacy safeguards to prevent unintended harm. By providing actionable insights, this research contributes to counter-extremism efforts in areas such as online content moderation, law enforcement and intelligence analysis, laying a foundation for future advancements in safeguarding global security which enhance the process innovation.
Perceived Risk as a Mediator Between Brand Trust, Perceived Fit, and Brand Extension Success: Case Study of China Time-honored Brand Change Lu; Thitima Pulpetch; Liou-Yuan Li
Journal of Applied Data Sciences Vol 5, No 3: SEPTEMBER 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i3.317

Abstract

This study aimed to explore the causal relationship and impact of perceived risk on brand extension success, with a particular focus on insights drawn from China Time-honored brand. The primary research question addressed in this study is: Does perceived risk mediate the effects of brand trust and perceived fit on brand extension success? Based on perceived risk theory, categorization theory, this study constructs a research model by adopting China time-honored brand as the research subject. The study collected 605 valid survey responses using a self-filled questionnaire, employing a combination of purposive and random sampling methods in the location of the parent brands. Quantitative analysis was conducted using partial least squares structural equation modeling (PLS-SEM) to test 4 research hypotheses. The findings indicate that: In the brand extension process of China time-honored brand, 1) perceived risk transmits effects of brand trust to brand extension success; 2) perceived risk transmits effects of perceived fit to brand extension success. These discoveries underscore the importance of considering consumers' perceived risk in the formulation and implementation of brand extension strategies. This study contributes to understanding the causal relationships and impacts of perceived risk in the brand extension of time-honored brands. The empirical evidence provided can serve as a reference for the development of extension strategies and marketing management for China time-honored brands and other heritage brands.
Lightweight Brain Tumor Classification with Histogram Oriented Gradients (HOG) Features and Class-Weighted Support Vector Machine (SVM) Budi Warsito; Husni Fadhilah; Puspita Kartikasari; Arief Rachman Hakim
Journal of Applied Data Sciences Vol 7, No 1: January 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i1.1018

Abstract

Early detection of brain tumors via MRI is crucial for improving patient outcomes. This study investigates a lightweight machine learning approach for multiclass brain tumor classification (glioma, meningioma, pituitary tumor, or no tumor) using Histogram of Oriented Gradients (HOG) for feature extraction and a Support Vector Machine (SVM) classifier. This study utilizes the public Brain Tumor Classification MRI Kaggle dataset, consisting of 2870 training and 394 testing MRI images across four classes. After converting the MRIs to grayscale and resizing them to 16×16 pixels, this study extracts HOG features and applies Principal Component Analysis (PCA) to retain 98% of the variance. An SVM is then trained with a GridSearchCV-optimized kernel and hyperparameters, and a custom class-weighted variant is compared. The best model, a polynomial-kernel SVM with custom class weights, achieved 91.8% test accuracy (95% CI (confidence interval): 90.9-92.7) with an F1-score of 0.919 ± 0.01, outperforming the best unweighted SVM (accuracy 86.0% ± 0.02, F1≈0.847). These results demonstrate that HOG+SVM, with proper weighting for class imbalance, can effectively classify brain tumors on small datasets at low computational cost. The novelty of this work lies in demonstrating that an optimized, class-weighted SVM leveraging compact HOG-PCA features can deliver over 91.8% accuracy with strong generalization on small-scale MRI data, providing a viable and interpretable alternative to complex Convolutional Neural Network (CNN) models. Future work can explore CNN and hybrid feature fusion to improve accuracy and generalization further.
Evaluating Deep Learning Architectures for Potato Pest Identification: A Comparative Study of NasNetMobile, DenseNet, and Inception Models Sri Hadianti; Dwiza Riana; Daning Nur Sulistyowati
Journal of Applied Data Sciences Vol 6, No 1: JANUARY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i1.545

Abstract

Manual potato pest identification that is still applied today is often time-consuming and highly dependent on farmer skills in the field. This causes delays in taking action and inaccurate reporting, especially in pest emergencies. In addition, these limitations slow down the response to pest control which ultimately risks reducing crop yields and farmer income. This study aims to develop a more accurate, fast, and consistent deep learning-based approach to identify potato pests, in order to support practical solutions that farmers can implement independently. This study contributes by comparing three deep learning architecture models, namely NasNetMobile, DenseNet, and Inception which are designed to identify pest images. The potato pest image dataset used was collected from various sources equipped with an augmentation process to increase data diversity. The model was drilled using transfer learning techniques to utilize previously learned features on a large dataset. The evaluation model was carried out comprehensively based on accuracy, precision, and inference time efficiency. The results showed that the DenseNet model achieved the highest accuracy of 97% with an inference time of 11 seconds, and this model maintained a relatively stable performance and was superior several times compared to other models. Based on these results, DenseNet was chosen as the most effective and reliable model to be developed for practical applications in the field. This study provides practical implications in the form of providing a model that can be integrated into a mobile-based application that is easy to use by farmers, including in remote areas. This allows farmers to identify pests independently without requiring in-depth technical expertise. In addition, this study is a new benchmark for the development of artificial intelligence-based pest identification systems in other crops and opens up opportunities for integration with IoT-based technologies to support sustainable agricultural practices.
Real-Time PPE Violation Detection and Tracking in Low-Light Industrial Environments Using YOLOv9t, TensorRT, and ByteTrack Fathorazi Nur Fajri; Kamil Malik; Abu Tholib
Journal of Applied Data Sciences Vol 7, No 4: December 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i4.1513

Abstract

Coal-fired power plants require correct PPE use, but low light in turbine halls, corridors, and nighttime inspection routes limits automated visual monitoring. This study builds and tests a real-time detection-and-tracking pipeline combining a YOLOv9t detector, TensorRT inference, and ByteTrack multi-object tracking for PPE violation monitoring under these conditions. A photometric check of the evaluation footage (mean pixel intensity 117.86/255, 14.68% of pixels below the 64/255 dark-pixel threshold) places it in the dim-illumination band defined by the IEEE 1789 photometric convention, confirming the reported gains were measured under genuinely degraded lighting. Trained on a violation-aware dataset of 11,407 annotated images across eight compliance and violation classes, TensorRT cut mean inference latency from 34.55 ms (PyTorch) to 6.26 ms (FP32) and 5.25 ms (FP16), a paired t-test (t = 13.1223, p 0.001) confirming the engine-level gain, while mAP@50 dropped only marginally (0.9134 to 0.9084). Because TensorRT builds can vary run to run, FP32 and FP16 were each validated across independent builds: FP16 matched FP32 in accuracy and ran 1.32x faster (5.25 vs 6.93 ms, p 0.001), so FP16 was selected for the pipeline below. Extending the comparison beyond one tracker, ByteTrack, DeepSORT, and SORT were benchmarked on identical input from a 128-second, 3,840-frame low-light CCTV clip at the PLTU Paiton gate. ByteTrack reached 82.62 FPS with MOTA 0.7543 (relative to a pseudo ground truth), clearing our 60 FPS real-time threshold (2× the 30 FPS source rate) with the best tracking accuracy of the three; DeepSORT managed only 27.08 FPS despite re-identification embeddings, and SORT (90.29 FPS) produced over 1.3× ByteTrack's identity switches. Across 320 worker identities, mean track duration was 26.74 frames (0.89 s).
A Comparative Study of Feature Selection Techniques in Machine Learning for Predicting Stock Market Trends Adi Suryaputra Paramita; Shalomeira Valencia Winata
Journal of Applied Data Sciences Vol 4, No 3: SEPTEMBER 2023
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v4i3.99

Abstract

This study aims to compare the effectiveness of three feature selection techniques, namely Principal Component Analysis (PCA), Information Gain (IG), and Recursive Feature Elimination (RFE), in predicting stock market conditions. This research uses three distinct Kaggle datasets that contain data for predicting stock market values. The results show that RFE performs better than PCA and IG in predicting market value with fairly precise accuracy. By using the RFE technique, this study was able to identify the most influential features in prediction, reduce the dimensionality of the data, and improve the performance of the prediction model. These provide significant benefits in the world of stocks, including improved investment decisions, reduced investment risk, improved trading strategy performance, and identification of promising investment opportunities. For future research, further comparative studies between other feature selection techniques can be conducted. This research has novelty in several aspects. First, it applies different feature selection techniques, namely Principal Component Analysis (PCA), Information Gain (IG), and Recursive Feature Elimination (RFE), in the context of stock market prediction. Utilizing these techniques to select the most relevant features in predicting stock market conditions provides a deeper understanding of the influence of these features on stock price movements. Furthermore, this research utilizes different datasets from Kaggle, which represent various stock market value predictions. The utilization of diverse datasets provides variation in the data and allows this research to examine the performance of feature selection techniques in multiple stock market contexts. In conclusion, this research provides insight into the effectiveness of feature selection techniques in stock market value prediction. It also provides actionable guidance for market participants to improve investment decisions and trading performance in the stock market.

Page 89 of 127 | Total Record : 1270