Vandha Pradwiyasma Widartha

Mr. Vandha Pradwiyasma Widartha

Information System, Pukyong National University, Busan, Republic of Korea
orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
Vandha Pradwiyasma WidarthaVandha Pradwiyasma Widartha
Vandha Pradwiyasma Widartha
IRIlkyeun Ra
Ilkyeun Ra
SLSu-Yeon Lee
Su-Yeon Lee
CKChang Soo Kim
Chang Soo Kim
Smart lighting control systems represent an advanced approach to reducing energy use. These systems leverage advanced technology to provide users with better control over their lighting, allowing them to manually, remotely, and automatically modify the brightness, color, and timing of their lights. In this study, we aimed to enhance the energy efficiency of smart lighting systems by using light source data. A multifaceted approach was employed, involving the following three scenarios: sensing device, daylight data, and a combination of both. A low-cost sensor and third-party API were used for data collection, and a prototype application was developed for real-time monitoring. The results showed that combining sensor and daylight data effectively reduced energy consumption, and the rule-based algorithm further optimized energy usage. The prototype application provided real-time monitoring and actionable insights, thus contributing to overall energy optimization.

26 December 2025 in Sensors
Verified
Journal Article
Open access
PDF file
Vandha Pradwiyasma WidarthaVandha Pradwiyasma Widartha
Vandha Pradwiyasma Widartha
CKChang Soo Kim
Chang Soo Kim
This study introduces the Hybrid Integrated Prediction-Error Reconstruction-based Anomaly Detection (HIPER-CHAD) model, which addresses the challenge of reliably detecting subtle anomalies in noisy multivariate indoor environmental time-series data. The main objective is to separate temporal modeling of normal behavior from probabilistic modeling of prediction uncertainty, ensuring that the anomaly score becomes robust to stochastic fluctuations while remaining sensitive to truly abnormal events. The HIPER-CHAD architecture first employs a Long Short-Term Memory (LSTM) network to forecast the next time step’s sensor readings, subsequently forming a residual error vector that captures deviations from the expected temporal pattern. A Variational Autoencoder (VAE) is then trained on these residual vectors rather than on the raw sensor data to learn the distribution of normal prediction errors and quantify their probabilistic unicity. The final anomaly score integrates the VAE’s reconstruction error with its Kullback–Leibler (KL) divergence, yielding a statistically grounded measure that jointly reflects the magnitude and distributional abnormality of the residual. The proposed model is evaluated on a real-world multivariate indoor environmental dataset and compared against eight traditional machine learning and deep learning baselines using a synthetic ground truth generated by a 99th percentile-based criterion. HIPER-CHAD achieves an F1-score of 0.8571, outperforming the next best model, the LSTM Autoencoder (F1 = 0.8095), while maintaining perfect recall. Furthermore, a time-step sensitivity analysis demonstrates that a 20-step window yields an optimal F1-score of 0.884, indicating that the proposed residual-based hybrid design provides a reliable and accurate framework for anomaly detection in complex multivariate time-series data.

5 May 2023 in JOIV : International Journal on Informatics Visualization
Verified
Journal Article
Open access
PDF file
RARachmadita Andreswari
Rachmadita Andreswari
RFRokhman Fauzi
Rokhman Fauzi
BIBerlian Maulidya Izzati
Berlian Maulidya Izzati
Vandha Pradwiyasma WidarthaVandha Pradwiyasma Widartha
Vandha Pradwiyasma Widartha
DPDita Pramesti
Dita Pramesti
Independent Campus, Freedom to Learn (ICFL) Program is one of the manifestations of student-centered learning. This program can help students reach their full potential by allowing them to pursue their passions and talents. This study aims to see how the segmentation of students participating in the ICFL program is based on demographic data. This research is based on survey responses from students participating in the ICFL program. The method used in this study is input data preparation, pre-processing, data cleansing, and data analysis. The information will be pre-processed before being utilized and evaluated. To help produce better outcomes in data clustering, the K-Means clustering approach is used, which is processed using the Python computer language. The data is clustered using the K-Means clustering approach based on gender characteristics, Grade Point Average (GPA), university entrance selection, ICFL category, and year or semester when participating in ICFL. This study resulted in three clusters with each of its criteria. The dominant gender is found in clusters 2 (100% female) and 3 (100% male). Software Development was the most popular ICFL category among students in cluster 1, accounting for 67%, while Design and Analysis Information Systems was the most popular in clusters 2 and 3. The most dominant ICFL program is found in three clusters. ICFL - Internship program in which at least 40% of participants come from each cluster. The research results are expected to assist stakeholders in evaluating the implementation of the ICFL program.

28 October 2025 in Journal of Information Systems Engineering and Business Intelligence
Verified
Journal Article
Open access
PDF file
TDTio Dharmawan
Tio Dharmawan
DSDanang Setiawan
Danang Setiawan
MHMuhamad Arief Hidayat
Muhamad Arief Hidayat
Vandha Pradwiyasma WidarthaVandha Pradwiyasma Widartha
Vandha Pradwiyasma Widartha
Background: Some construction workers are often in a situation where injuries can occur from negligence in the use of safety helmets. To avoid this, supervision of the use of safety helmets should be conducted continuously during the work process through the application of computer vision technology. However, the complex background of the construction environment is a challenge to detecting small and densely packed safety helmets accurately. Objective: The construction environment is complex, and the wide workspace allows workers to be in an area far from supervision. The process makes it difficult for models to detect the use of safety helmets in complex, wide, and very high object density construction environments. Therefore, this study aims to overcome the problem by modifying YOLOv5s (You Only Look Once version 5) architecture. Methods: Real-time monitoring of the use of safety helmets could be performed using YOLOv5. This study proposed a modified YOLOv5s model called CBTi-YOLOv5s. The model incorporated Convolutional Block Attention Module (CBAM), Transformer, and Bi-directional Feature Pyramid Network (BiFPN) to improve feature extraction, multi-scale object representation, as well as detection accuracy, specifically on small and high-density objects in complex construction environments. Results: The results showed the modified YOLOv5s architecture had made an improvement of 3.7% in mean average precision (mAP) compared to the base YOLOv5s model. mAP of the base YOLOv5s model was 93.6%, while the modified CBTi-YOLOv5s model achieved 97.3%. The proposed modified YOLOv5s model also achieved an inference speed of 58 frames per second (FPS), and the base model achieved 104 FPS. Conclusion: CBTi-YOLOv5s improved the accuracy, mAP, and ability to detect objects of varying scales. However, this improvement had drawbacks, namely increased model size and decreased inferential speed due to increased model architectural complexity.. Keywords: Bi-FPN, CBAM, CBTi-YOLOv5s, Helmet Detection, Transformer, YOLOv5

23 August 2025 in Indonesian Journal of Information Systems
Verified
Journal Article
Open access
PDF file
TRTri Rochmadi
Tri Rochmadi
Vandha Pradwiyasma WidarthaVandha Pradwiyasma Widartha
Vandha Pradwiyasma Widartha
TSTito Apolinario Sarmento
Tito Apolinario Sarmento
AHAvrillaila Akbar Harahap
Avrillaila Akbar Harahap
IAIbnu Ajis
Ibnu Ajis
Learning Management Systems (LMS) like Moodle are frequently targeted by covert cyberattacks that exploit the credibility of academic domains for illicit purposes. This study uncovers an SEO-based attack method that infiltrates hidden links to gambling sites through Moodle's public directory. Digital forensic methodology was used to trace the perpetrators' footprints from server logs, HTML/JS files, and activity in Google Search Console. The results revealed a comprehensive exploit: fake admin accounts, redirect file injection, and Google indexing manipulation. This research not only highlights an under-researched threat but also offers a mitigation framework based on the ISO/IEC 27001 standard. Key contributions include identifying SEO-based attack techniques in LMSs, analyzing digital artifacts for perpetrator attribution, and strengthening cybersecurity governance in educational institutions.

11 June 2026 in Mathematics
Verified
Journal Article
Open access
PDF file
Vandha Pradwiyasma WidarthaVandha Pradwiyasma Widartha
Vandha Pradwiyasma Widartha
INIfrina Nuritha
Ifrina Nuritha
KRKyung-Hyune Rhee
Kyung-Hyune Rhee
YHYoung Po Hwang
Young Po Hwang
CKChang Soo Kim
Chang Soo Kim
Multivariate time-series anomaly detection on physical sensor networks faces three challenges that generic deep learning models inadequately addressed: heterogeneous sensor reliability, context-dependent anomaly scoring, and inactionable binary outputs lacking per sensor attribution. We propose an uncertainty-aware Temporal Convolutional Network (TCN) framework built on two tightly integrated uncertainty-driven components: (i) an Adaptive Uncertainty-Aware Attention (AUAA) mechanism that gates temporal attention weights by per sensor predictive uncertainty obtained from Monte Carlo dropout; and (ii) a Dynamic Weight Adapter that learns context-sensitive blending of reconstruction error and uncertainty via a GRU over weight history. The architecture also includes an exploratory per sensor attribution head, which we audit rather than claim: a controlled-perturbation test shows it is not yet causally faithful. We complement the empirical architecture with two distribution-free theoretical results: a Chebyshev-type false-positive bound on the hybrid anomaly score, and a Monte Carlo posterior moment convergence result at rate O(M−1/2). Evaluated on four-month indoor air quality sensor data, the Full Enhanced model achieves R2=0.9988 and MSE 1.65×10−4, a 25.2% MSE reduction over the Base TCN (R2=0.9984, MSE 2.20×10−4). Because the IAQ stream is unlabeled, the primary quantitative detection evaluation uses the labeled Skoltech Anomaly Benchmark (SKAB), a publicly available industrial water-circulation corpus disjoint from the IAQ training distribution; it yields an 8.8 × F1 advantage (0.477 vs. 0.054) and a 14.4 × recall advantage (0.418 vs. 0.029) for the proposed model configuration over the Base TCN at a validation-calibrated threshold applied without retuning. Against twelve established detectors under a unified protocol, the proposed model attains the best F1 and recall, while the strongest reconstruction baselines retain higher precision and a marginally higher ROC-AUC, a recall-driven trade-off. Ablation isolates each component’s contribution, the detector degrades gracefully under channel masking and noise, and the distribution-free false-positive bound is empirically respected. The framework retains a low inference cost (0.16 ms per window at M=20 Monte Carlo samples, including the uncertainty pass).