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
Beyond Positive and Negative: A Directional SHAP Framework for Sequential Multi-Class Classification Ahmet Yalcin; Selim Cetin; Bekir Cetintav
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.v7i3.1375

Abstract

In this study, we address the interpretative limitations of the standard Shapley Additive Explanations (SHAP) method in sequential multi-class classification problems within the scope of Explainable Artificial Intelligence (XAI). Stemming from the observation that classical SHAP is restricted to revealing only positive and negative contributions for a single class, we propose a novel directional framework that categorizes feature effects as 'Lower' (driving towards a lower class), 'Upper' (driving towards a higher class), and 'Ambiguous' (representing inconsistent effects). To validate this approach, a Random Forest model predicting obesity levels across seven hierarchical classes was trained on an open-source dataset, achieving a classification accuracy of 95.5%. Furthermore, a stability analysis comprising 10,000 sampling iterations demonstrated the robustness of the proposed framework, with dominant features retaining their directional categorizations consistently in over 99.9% of the trials. The findings indicate that unlike standard SHAP, our method successfully isolates the specific variables that prevent an instance from ascending to a higher class or descending to a lower one, particularly clarifying the role of ambiguous boundary features. In conclusion, this modification significantly enhances model transparency for complex hierarchical scenarios, and the framework has been released as an open-source Python library to provide researchers with a practical tool for automated directional feature analysis.
Application of Hash Sha-256 Algorithm in Website-Based Sales Software Engineering Fauziah Nikmatul Khasanah
Journal of Applied Data Sciences Vol 3, No 1: JANUARY 2022
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v3i1.50

Abstract

Rapid technological developments can spur changes in the cycle of human activities, one of which is software engineering activities that continue to develop in accordance with technological developments, the development of software engineering activities is also developing methods of data security to withstand attacks from irresponsible parties. answer. This research was conducted to analyze the performance and robustness of the sha-256 data security method with ciphertext customization. The steps that the researchers took in conducting the analysis were collecting theory and case examples, designing programs, implementing programs, testing and saving the results. Based on this process, it can be concluded that ciphertext customization on sha-256 is needed to strengthen security and resistance to attacks from irresponsible parties, besides that the performance of sha-256 calculations with customization on ciphertext and without ciphertext is not too much different where only 65 ms difference based on the results of performance testing that researchers did.
Assessing Drought Risk in Forest Zones Near Coal Mines with TVDI La Taati; Sunardi Sunardi; Isna Syauqiah; A Jauhari
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.v5i2.220

Abstract

This study is quantitative research employing survey techniques and spatial modeling. In the research area, particularly in forested areas, the NDVI values range from 0.25 to 0.55 with LST values of 29°C to 37°C. Cooler temperatures below 34°C were observed in the southwest (outside the mining area). The LST values indicate high temperatures above 37°C in the coal mining area, with effects extending up to 6 km. The linear regression equation between NDVI and LST in the coal mining area, with a regression equation of y = -20.888x + 40.458; R^2 = 0.83; r = -0.91, shows an inverse relationship between NDVI increase and ground surface temperature, indicating a good model fit with the data and a strong negative linear relationship between the two variables. The Urban Heat Island (UHI) effect in the mining area, especially at the mining center, shows a UHI with a temperature difference of more than 0.6 degrees Celsius compared to the cooler surrounding area. At the center of the coal mining area, the TVDI value is 0.6-0.8 (high-very high), but in the eastern part of the mine in forested areas with a certain soil type, the TVDI value is 0.2-0.6 (moderately dry - dry), while in other parts of the forested area with a different soil type, the NDVI value is 0.2 (moist). There is a difference in response to different soil types. Drought increases in the forested areas around the mining site, affecting ecosystem productivity and soil moisture.
TF-EffBiGRU-AttNet: A Novel Deep Learning Framework for Spatio-Temporal Energy Demand Forecasting in Electric Vehicle Charging Networks S Prakash; S Aruna Mary; G Sudhagar; M Batumalay
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.v7i1.805

Abstract

Electric Vehicle Charging Stations (EVCS) are key enablers of sustainable transportation, yet accurate forecasting of their energy demand remains challenging due to complex spatial-temporal variability. This study introduces a novel hybrid deep learning framework, Two-Fold EfficientNetV2 BiGRU with Attention (TF-EffBiGRU-AttNet), optimized using the Self-Adaptive Hippopotamus Optimization Algorithm (SA-HOA), to enhance prediction accuracy and computational efficiency in EVCS energy demand forecasting. The main objective is to integrate multi-scale spatial learning, bidirectional temporal modeling, and adaptive feature prioritization within a single architecture capable of robust and interpretable forecasting. The model’s novelty lies in its dual-fold spatial feature extraction using EfficientNetV2 and dynamic optimization through SA-HOA, which adaptively balances exploration and exploitation during training. Experimental validation on two real-world datasets from Palo Alto and Perth demonstrates that the proposed model consistently outperforms state-of-the-art baselines. For the 7-1 forecasting task, TF-EffBiGRU-AttNet achieved the lowest MAE of 0.012 and RMSE of 0.051 for Palo Alto, and MAE of 0.029 with RMSE of 0.12 for Perth. For the 30-7 task, it achieved MAE of 0.0332, RMSE of 0.1654, and MAPE of 0.20% on Palo Alto, and MAE of 0.0235, RMSE of 0.0824, and MAPE of 0.37% on Perth, outperforming Bi-LSTM and EfficientNet by over 60% in RMSE reduction. Moreover, SA-HOA improved optimization efficiency with a best fitness value of 0.0003 and reduced convergence time to 1.2 seconds, surpassing PSO, GWO, and HOA. These results highlight the framework’s ability to capture spatial-seasonal and nonlinear dependencies while maintaining low computational overhead. The findings confirm the model’s potential as a robust, adaptive, and scalable solution for intelligent EV energy demand forecasting, supporting smart grid planning and sustainable energy management.
Deep Learning Incorporated with Augmented Reality Application for Watch Try-On Andri Andri; Tri Basuki Kurniawan; Deshinta Arrova Dewi; Mashal Kasem Alqudah; Musab Kasim Alqudah; Mohd Zaki Zakaria; Putri Aisha Athira binti Hisham
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.v6i1.529

Abstract

In evaluating the dynamic landscape of online shopping, the integration of Augmented Reality (AR) technologies has emerged as a transformative force, redefining the way consumers engage with products in virtual environments. This research project investigates the intersection of deep learning and AR in the context of online shopping, with a particular focus on a Watch Try-On application. The experimentation involves the use of SSD MobileNet's models for real-time object detection aimed at enhancing the user experience during online watch shopping. Training both SSD MobileNet's V1 and V2 models through 50,000 iterations, the results reveal intriguing insights into their performance. SSD MobileNet's V1 demonstrated superior results, boasting a mean average precision (mAP) of 0.9725 and a significant reduction in total loss from 0.774 to 0.5405. However, the longer training time of 7 hours and 42 minutes prompted the selection of SSD MobileNet's V2 for real-time applications due to its faster inference capabilities. Extending beyond traditional online shopping experiences, the research explores the potential of AR technologies to revolutionize product visualization and interaction. The choice of the Vuforia model target for the Watch Try-On application showcases the synergy between deep learning and AR, allowing users to virtually try on watches and visualize them in their real-world environment. The application successfully detects users' hands with high accuracy, creating an immersive and visually enriching experience. In conclusion, this project contributes to the ongoing discourse on the fusion of deep learning and AR for online shopping. The exploration of SSD MobileNet's models, coupled with the integration of AR technologies, underscores the potential to elevate the online shopping experience by providing users with dynamic, interactive, and personalized ways to engage with products.
An Explainable Uncertainty-Aware Deep Learning Framework for Robust Skin Disease Diagnosis R Karthick Manoj; Aasha Nandhini S; C Batumalai
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.v7i3.1465

Abstract

Automated skin-disease diagnosis from clinical and dermoscopic images remains challenging because of illumination variability, acquisition artifacts, irregular lesion boundaries, limited feature diversity, and the low interpretability of conventional deep learning models. This study proposes EDLF-Skin, an integrated framework that combines Physio-Color Consistency preprocessing, Attentive Multi-scale U-Trans segmentation, Multi-Modal Feature Fusion, a Hybrid Ensemble with Uncertainty, and a Multi-level Explainability Interface. The preprocessing stage normalizes illumination and removes artifacts while preserving diagnostically relevant color and texture information. The segmentation module integrates convolutional feature extraction with transformer-based attention to improve lesion-boundary delineation. Spatial, frequency, and texture representations are subsequently fused through cross-attention and processed by complementary convolutional and transformer classifiers. Predictive uncertainty is estimated to identify low-confidence cases requiring expert review, while Grad-CAM, SHAP attribution, and textual rationales provide multilevel explanations. Experimental results show that the proposed segmentation model achieved a Dice coefficient of 0.956 and an intersection over union of 0.935. The complete classification framework obtained 96.87% accuracy, an F1-score of 0.953, an area under the receiver operating characteristic curve of 0.981, and an expected calibration error of 0.021. These findings indicate that EDLF-Skin improves segmentation accuracy, classification performance, probability calibration, and decision transparency within a unified diagnostic workflow.
Analysis of Efficient Optimization Algorithm for Information Nodes in Wireless Network Communication Chaos Jing Qi; Tru Cao
Journal of Applied Data Sciences Vol 4, No 1: JANUARY 2023
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v4i1.77

Abstract

Due to the poor node optimization effect of traditional mathematical model methods, an efficient node optimization algorithm based on ant colony genetic algorithm is proposed. The ant colony algorithm is a kind of bionic optimization algorithm, and its dynamics and self-similarity are very similar to the optimization principles of messy information nodes. "Chaos node efficient optimization algorithm" is dedicated to effectively aggregating various resources such as computing, storage, knowledge, communication, information, distributed around the world, serving the public, and realizing resource sharing and collaborative work. Among them, chaos nodes efficiently search the excellent problem is particularly prominent. If the number of parent nodes and the order of the nodes are known, the ant colony genetic algorithm is used to find the largest supporting tree, so as to obtain the best node to obtain the largest number of iterations, thereby effectively optimizing the information node.Wireless Network Communication, Chaotic Nodes, Nodes, Efficient Optimization
Data-Driven Optimization of UPQC Performance for Solar PV Systems in Weak Grids Using Simulation and Predictive Modeling R. Rajasree; D. Lakshmi; M. Batumalay
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.v6i3.742

Abstract

The integration of solar photovoltaic (PV) systems into weak power grids presents significant challenges due to low short circuit ratios (SCR), resulting in voltage instability, high harmonic distortion, and diminished fault tolerance. This study proposes a data-driven framework to enhance grid stability and power quality by employing a Unified Power Quality Conditioner (UPQC) integrated with Proportional-Integral (PI) controllers. A comprehensive simulation model was developed using MATLAB/Simulink and validated through hardware-in-the-loop (HIL) experiments. Key electrical performance metrics—such as voltage profiles, total harmonic distortion (THD), and reactive power—were collected and analyzed. To enhance system insight, the dataset was further processed using statistical analysis and predictive modeling techniques to evaluate control response under varying solar irradiance and load conditions. The results demonstrate that the UPQC system maintains stable voltage, reduces THD to within IEEE-519 standards, and improves power factor to 0.98. This research highlights the potential of combining power electronics control with data-centric evaluation to ensure reliable renewable energy integration in weak grid environments. The proposed system contributes toward developing intelligent grid-support solutions for sustainable energy transitions and process innovation.
Early Stopping on CNN-LSTM Development to Improve Classification Performance M. Khairul Anam; Sarjon Defit; Haviluddin Haviluddin; Lusiana Efrizoni; Muhammad Bambang Firdaus
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.v5i3.312

Abstract

Currently, CNN-LSTM has been widely developed through changes in its architecture and other modifications to improve the performance of this hybrid model. However, some studies pay less attention to overfitting, even though overfitting must be prevented as it can provide good accuracy initially but leads to classification errors when new data is added. Therefore, extra prevention measures are necessary to avoid overfitting. This research uses dropout with early stopping to prevent overfitting. The dataset used for testing is sourced from Twitter; this research also develops architectures using activation functions within each architecture. The developed architecture consists of CNN, MaxPooling1D, Dropout, LSTM, Dense, Dropout, Dense, and SoftMax as the output. Architecture A uses default activations such as ReLU for CNN and Tanh for LSTM. In Architecture B, all activations are replaced by Tanh, and in Architecture C, they are entirely replaced by ReLU. This research also performed hyperparameter tuning such as the number of layers, batch size, and learning rate. This study found that dropout and early stopping can increase accuracy to 85% and prevent overfitting. The best architecture entirely uses ReLU activation as it demonstrates advantages in computational efficiency, convergence speed, the ability to capture relevant patterns, and resistance to noise.
Development of Color Segmentation and Texture Analysis Algorithms for Early Detection of Green Vegetable Deterioration in Retail Environments Dinul Akhiyar; Iskandar Fitri; Gunadi Widi Nurcahyo
Journal of Applied Data Sciences Vol 7, No 2: May 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i2.1094

Abstract

Vegetable deterioration in retail environments is often accelerated by improper storage conditions, leading to quality degradation, economic losses, and reduced consumer trust. Early detection of deterioration is therefore essential to enable timely preventive actions before visible spoilage becomes severe. This study proposes an integrated image-based framework for early detection of spinach leaf deterioration by combining K-Means++ for robust color segmentation, Gray Level Co-occurrence Matrix (GLCM) for texture feature extraction, and Convolutional Neural Network (CNN) for classification. K-Means++ improves segmentation stability through optimized centroid initialization, GLCM captures subtle texture variations associated with early spoilage, and CNN enables accurate classification by learning complex visual patterns from segmented images. The dataset consists of 642 spinach leaf images captured under controlled lighting for initial calibration and under varying lighting conditions to simulate real-world retail environments. Experimental results show that the standard K-Means algorithm achieved an average classification accuracy of 77%, while the proposed K-Means++ segmentation improved accuracy to 81.86%. Furthermore, CNN-based validation achieved the highest classification accuracy of 94.82%, demonstrating strong generalization capability. The novelty of this work lies in the optimized integration of K-Means++ segmentation under lighting variability, selective GLCM feature utilization validated through ablation analysis, and end-to-end CNN-based validation with real-time deployment feasibility. The proposed framework offers a practical, scalable, and non-destructive solution for automated freshness monitoring in retail environments and can be extended to other leafy vegetables.

Page 85 of 127 | Total Record : 1270