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
Price Prediction of Aglaonema Ornamental Plants Using the Long Short-Term Memory (LSTM) Algorithm Yuni Sugiarti; Arif Imam Suroso; Irman Hermadi; Euis Sunarti; Fadhilah Bt Mat Yamin
Journal of Applied Data Sciences Vol 6, No 2: MAY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i2.640

Abstract

The Aglaonema ornamental plant is a horticultural commodity with high economic value and promising prospects. It is well known for its attractive leaf variations, earning it the nickname "Queen of Leaves." However, unpredictable price fluctuations make investing in Aglaonema speculative and high-risk. This research aims to predict the price of Aglaonema over the next five years using the Long Short-Term Memory (LSTM) algorithm. LSTM is considered superior to other algorithms in handling time series data. The model's performance was evaluated using Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) on a weekly Aglaonema price dataset covering the period from January 2012 to December 2023. The results demonstrate that the LSTM algorithm can predict Aglaonema prices with high accuracy, as indicated by the following metrics: MSE: 0.005 – Represents the average squared difference between predicted and actual prices. A lower MSE indicates higher model accuracy. RMSE: 0.07-RMSE provides a more interpretable error measurement as it retains the same units as the original data. A low RMSE signifies that the model's predictions closely align with actual values. MAE: 0.04 – Measures the absolute average difference between predicted and actual prices. A lower MAE value reflects a smaller prediction error. Thus, this research makes a significant contribution to the development of a machine learning-based price prediction system for the ornamental plant industry.
The Mediating Role of Perceived Value in the Relationship Between Brand Image and Repurchase Intention: A Case Study of the Chinese Tea Market Rui Luo; Umawasee Sriboonlue; Suraporn Onputtha
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.v5i2.227

Abstract

This study is dedicated to exploring how brand image influences repurchase intention through perceived value in the Chinese tea market. Five randomly selected tea brands among the top twenty tea brands in Sichuan Province were chosen as the study sample. Corporate image, product image and user image were used to measure brand image; meanwhile, functional value, emotional value, social value and price value were used to assess perceived value; and repurchase intention was directly measured through questionnaires. Six hundred valid questionnaires from consumers of these five brands were collected through the Questionnaire Star platform and analyzed by structural equation modeling using SMARTPLS 4.0 software. The results show that brand image has a significant positive effect on perceived value and repurchase intention, and perceived value plays a significant mediating role between brand image and repurchase intention. These findings not only enrich the theoretical framework, but also provide practical strategic recommendations for brand management in the Chinese tea market, emphasizing the need to pay attention to the impact of brand image on consumer repurchase intention through perceived value in the process of brand image construction and management, so as to enhance consumer loyalty and promote sustained purchase behavior.
A Stacking Ensemble Model for Predicting Student High School Graduation Outcomes Fitriyani Fitriyani; Ari Amir Alkodri; Fajar Aswin
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.v7i1.1067

Abstract

This study develops and evaluates machine learning models to predict high school graduation outcomes and identify at-risk students for early intervention. Using a quantitative approach, data from 1,017 students across three public high schools were analyzed, encompassing academic performance (average yearly scores), behavioral factors (attendance rates and extracurricular participation), and socio-economic background (proxied by parental occupation). A comparative modeling strategy was applied, beginning with a Decision Tree baseline and advancing to a Stacking Ensemble model that integrated three heterogeneous base learners—Support Vector Machine (SVM), k-Nearest Neighbors (k-NN), and Decision Tree—combined through a Logistic Regression meta-model. Both models were optimized using GridSearchCV and adjusted for class imbalance between graduates (93.4%) and at-risk students (6.6%). The results showed that academic variables, particularly third-year average scores (mean = 82.6, SD = 6.4) and attendance rate (mean = 94.3%), were the strongest predictors of graduation, while socio-economic indicators had minimal impact. The Stacking Ensemble achieved a notable improvement over the Decision Tree, reaching an accuracy of 99.6%, precision of 0.909, recall of 1.000, F1-score of 0.952, and AUC of 1.000, compared to the baseline accuracy of 94.9% (F1-score = 0.519, AUC = 0.83). These findings indicate the superior predictive capability of the ensemble model in identifying students at risk of non-graduation. The study’s novelty lies in combining interpretable and high-performance models to construct a practical early-warning framework that can guide educators and policymakers in targeted academic interventions. However, the near-perfect metrics also suggest potential overfitting, emphasizing the need for validation using external datasets before broader application. Overall, this research contributes a robust, data-driven methodology for improving student retention through predictive analytics in educational settings.
Object-Level Sentiment Analysis Use a Language Model Thuy Thi Le; Tuoi Thi Phan
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.v6i1.448

Abstract

Sentiment analysis remains a prominent area of research in the natural language processing (NLP) community and holds significant practical value in domains such as commerce and education. Most existing approaches evaluate sentiments for a single object or product, typically categorizing them as positive or negative. However, when a text involves comparisons between multiple objects, it can be challenging to identify which sentiment or emotion is associated with which object. Few studies have addressed this issue, often stopping at evaluating emotions at the sentence level or for individual words related to aspects or objects. This study proposes an object-level sentiment analysis problem that produces a set of pairs or triples consisting of an object, aspect, and sentiment. Additionally, in texts expressing opinions or comments on a specific aspect, the aspect may be implied through references to the object without being explicitly mentioned. Identifying such implicit aspects is crucial, as it ensures no loss of information and enhances the efficiency of extraction of information in object-level sentiment analysis. The integration of implicit aspect identification and object-level sentiment analysis is the primary focus of this research. In recent years, many language models have been developed and effectively applied to various NLP tasks. Therefore, to address the proposed challenges, this study utilizes deep learning that incorporates language models combined with NLP methods such as parsing and dependency analysis, to achieve the desired output. Using language model and NLP techniques automatically generate training data for the learning model. The proposed method achieves an accuracy of 90%, making a substantial contribution to the field of NLP.
Multi Domain Feature Fusion and Boosting Based Learning for Robust Gallbladder Ultrasound Image Classification Gede Angga Pradipta; Pharan Chawaphan; Sutikno Sutikno; Putu Desiana Desiana Ayu; Dandy Pramana Hostiadi; Made Liandana
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.v7i3.1268

Abstract

Accurate identification of gallbladder conditions is critically important in the medical sector, as early detection of diseases such as gallstones, cholecystitis, carcinoma, and polyps can substantially improve treatment outcomes, reduce complications, and guide timely surgical or therapeutic interventions. Existing literature on gallbladder disease classification still presents notable gaps. Most prior works rely solely on single-domain feature extraction either deep CNN-based spatial descriptors or handcrafted statistical/texture features without exploiting the complementary strengths of multi-domain feature fusion. This study addresses these gaps by proposing a hybrid framework that combines advanced preprocessing, multi-domain feature fusion, feature selection, and ensemble classification. The preprocessing pipeline applies Non-Local Means (NLM) denoising, Contrast Limited Adaptive Histogram Equalization (CLAHE), frequency-domain low-pass filtering, and Gabor filtering to enhance image quality and highlight diagnostically relevant structures. Features are extracted by fusing deep spatial descriptors from a pretrained Inception V3 network with handcrafted statistical and texture-based features, including Gray Level Dependency Matrix (GLDM) measures. Dimensionality reduction is performed using ANOVA k-best selection to retain the most discriminative attributes. The refined features are classified using LightGBM, XGBoost, Histogram Gradient Boosting, and AdaBoost, enabling a comprehensive performance comparison. Experiments conducted on the balanced UIdataGB dataset (10,692 annotated images across nine diagnostic categories) demonstrate that LightGBM, XGBoost, and Histogram Gradient Boosting achieve near-perfect performance, with accuracies exceeding 98.6% and AUC values of 0.98 across all classes, while AdaBoost shows markedly lower discriminative capability.The results suggest that gradient boosting approaches are a promising option for multi-class gallbladder disease detection, particularly when combined with multi-domain feature fusion and appropriate preprocessing and feature selection techniques.
Embedded Image Recognition System for Lightweight Convolutional Neural Networks Jie Fang; Xiangping Zhang
Journal of Applied Data Sciences Vol 3, No 3: SEPTEMBER 2022
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v3i3.62

Abstract

In this paper, we design and implement an embedded image recognition system based on STM32 for the problem of limited storage space of embedded systems to run convolutional neural networks efficiently, and for the loading of lightweight convolutional neural network and the hook-up requirement of the quadrotor. The system hardware adopts the idea of modular design to improve the compatibility of the system, and the system software adopts the training of handwritten image recognition based on convolutional neural network, lightweight processing of the convolutional neural network, and transplanting the trained network to the embedded system. Finally, the system can finish the recognition of handwritten images stably and efficiently. This system can provide a low-cost and highly integrated solution for such image processing systems. The lightweight target detection model CED-Det is designed by combining CED-Net and dense feature pyramid network, which firstly performs feature extraction by CED-Net, then performs feature fusion by stacking two layers of dense pyramid network, and finally, the fused feature maps are used for classification prediction and position prediction by two 3×3 convolutions, respectively. CED-Det is used in VOC and Experimental results on COCO datasets show that CED-Det is more suitable for embedded platforms in terms of accuracy, inference speed, and a total number of parameters compared with other target detection models.
The Impact of Supplier-Customer Collaboration on Sustainability-Oriented Capability: The Mediating Role of Communication Effectiveness and Technology Adoption in Micro-Enterprises Seree Gronphet; Suraporn Onputtha
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.v6i3.725

Abstract

With many businesses transforming digitally to lead future trends driven by sustainability, supplier-customer collaboration is key in empowering MSMEs. Nevertheless, effective collaborative practices remain challenging for MSMEs due to resource constraints and operational limitations. This study examines the mediating role of communication effectiveness and technology adoption in the relationship between supplier-customer collaboration and sustainability capabilities. Data was collected from 400 MSMEs in Bangkok and metropolitan area, Thailand, and analyzed using partial least squares-structural equation modeling (PLS-SEM). Results indicate that supplier-customer collaboration positively influences sustainability capability directly (β=0.345, p 0.001) and indirectly through communication effectiveness (β=0.370, p 0.001) and technology adoption (β=0.043, p 0.001). Effectiveness of communication appeared to be the superior mediator, providing evidence that the impact of technology adoption is less influential in resource-constrained environments. The study’s novelty lies in its focus on micro-enterprises’ unique constraints and the creation of a contextualized framework that prioritizes effective communication over technological investments, challenging conventional sustainability models derived from large organizations and offering context-specific policy recommendations for enhancing micro-enterprise sustainability in developing economies.
A Multilingual Corpus for Panic and Worry in Code-Mixed Tweets by VADER Sentiment Analysis Razailin Abdul Rashid; Siti Hafizah Ab Hamid; Faisal Fahmi
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.v5i3.259

Abstract

The phenomenon of code-mixing in online discourse, on platforms such as X, offers an interesting setting to detect preliminary markers of anxiety within diverse linguistic expressions. The usage of more than one language within a single text or tweet necessitates the creation of a multilingual corpus to identify initial indicators of anxiety in code-mixed texts or tweets, contributing to a comprehensive understanding of mental health in the digital age. Existing research on code-mixed textual context primarily centres on code-mixed language of English with Spanish or Hindi, leaving a gap in our comprehension of other code-mixed languages, in particular; English with Malay or Indonesian language. Thus, our study focuses on anxiety-related linguistic expressions in Malay and Indonesian languages, such as ‘bimbang’, ‘bingung’, ‘panik’, ‘gelisah’, ‘cemas’, ‘takut’, ‘kacau’, ‘gemetar’, ‘gugup’, ‘teror’ and occasionally the usage of slangs such as ‘neves’, ‘gabra’, and ‘cape bgt’. In this paper, we introduce CORPUS4PANWO, an annotated sentiment-driven multilingual corpus for panic and worry detection in tweets. To experiment the corpus, we applied a corpus-based sentiment analysis utilizing VADER on diverse events, achieving accuracy of between 76.6% - 88.0% when used on tweets in negative circumstances. The corpus is a valuable resource for Southeast Asian linguistics, enabling exploration of emotional expression in diverse contexts.
Spatial Analysis of Ensemble Learning Models for Agricultural Drought Early Warning Sudianto Sudianto; Khoirun Ni'amah; Atika Ratna Dewi; Afan Ramadhan; Jeti Aprilia; Arsita Wiwit Tiyaswening; Syalaisha Nisrina Anataya
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.v7i1.1108

Abstract

Drought poses a serious threat to rice production and local food security, triggered by climate anomalies such as El Niño. This study aims to evaluate and compare the performance of Ensemble Learning Models in classifying drought levels and analyze its correlation with periods of climate anomalies. This study uses Landsat 9 image data in the simulation period from June 2024 to July 2025, which is processed with HSV-based pan-sharpening and spectral index extraction (NDVI, NDWI, NDDI, EVI, LST). The modeling process applied undersampling to address class imbalance and hyperparameter tuning optimization using Optuna. The models compared included Random Forest, LightGBM, AdaBoost, XGBoost, and Gradient Boosting. The results showed that Gradient Boosting excelled with a train accuracy of 96,85% in original dataset with split dataset 70:30, whereas rise to 98.98% after tuning. Spatial validation was conducted in other rice field plots, however its steadfastly on research area with same treatment. The classification map shows the dominance of the moderate category, which temporally coincides with the period of rainfall decline associated with El Niño, although a direct causal relationship requires further investigation. These findings confirm that remote sensing combined with machine learning is effective for drought monitoring, with the caveat that the application of undersampling and limited spatial validation that is, confined solely to the research area; needs to be considered in the interpretation of results.
Fuzzy TOPSIS-Based Group Decision Model for Selecting IT Employees Abigail Vania; Ditdit Nugeraha Utama
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.v6i1.511

Abstract

In the era of digitalization, the demand for competent IT employees is growing rapidly. However, the IT employee selection process often faces various challenges, such as biased selection criteria, many applicants, and difficulty in objective assessment. These challenges can lead to inaccurate selection decisions and have a negative impact on company performance. This research aims to develop a Group Decision Support Model (GDSM) for IT Employee Selection using the Fuzzy TOPSIS method to enhance objectivity and reliability in decision-making. This GDSM combines assessments from HRD and User IT groups by considering the weight of each criterion. The proposed model overcomes bias, uncertainty, and subjectivity in judgments from both groups. The GDSM is constructed with 8 parameters/sub-criteria (2 criteria) from the HRD group and 12 parameters (5 criteria) from the User IT group from interviews and research. Thus, the total is 20 assessment parameters, consisting of coding test, education, certification, computer literacy, openness to experience, conscientiousness, extroversion, agreeableness, neuroticism, verbal, numerical, ability to learn, appearance attitude, work experience, communication skills, time management, job knowledge, motivation to apply, decision making, and service orientation. The methodology involves determining parameters, weights, fuzzification and this GDSM was tested through a limited simulation of IT employee selection using 11 respondents from Computer Science students for evaluation of the model. The result of this model is a ranking of the candidates. The best candidate is Cand. 8, with a closeness coefficient (CC) value of 0.896. The worst candidate is Cand. 3, with CC 0.241. The model is acceptable because it has no difference value between coding and manual for all candidates. This study contributes to increasing objectivity in IT employee selection and offers an implementation model for companies that want to improve the effectiveness of the recruitment process.