Umang Dobhal
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Umang Dobhal has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Christina Garcia
Kyushu Institute of Technology, Kitakyushu, Fukuoka, Japan
3 shared publications - Sozo Inoue
Kyushu Institute of Technology, Fukuoka, Japan
3 shared publications - Hirofumi Tanaka
Department of Human Intelligence Systems Graduate School of Life Science and Systems Engineering Kyushu Institute of Technology Kitakyushu Japan
1 shared publication - Tu Truong Huynh
Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology
1 shared publication
Latest Publications
- 1 April 2026
- Published by Springer Nature
- p. 230-244
Sample Selection Strategy for Synthetic Data Generation on Gesture Phase Recognition
- 1 April 2026
- Published by Springer Nature
- p. 230-244
Sample Selection Strategy for Synthetic Data Generation on Gesture Phase Recognition
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1082-1088
Two-Stage Reservoir Computing for Sensor-Specific Activity Recognition Using the WEAR Inertial Dataset
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1082-1088
Open AccessTwo-Stage Reservoir Computing for Sensor-Specific Activity Recognition Using the WEAR Inertial Dataset
- Open Access
- 5 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 493-499
Synthetic Skeleton Data Generation using Large Language Model for Nurse Activity Recognition
In this paper, we improve nurse activity recognition by employing a Large Language Model (LLM) to generate synthetic pose estimation data. Keypoint data extracted from recorded videos of a single nurse performing Endotracheal suctioning (ES) activities using You Only Look Once v7 (YOLOv7) is used as a database. We explore the issue of data imbalances that hinder the effectiveness of activity recognition algorithms. To counter this, we utilize LLMs to artificially augment the dataset by generating varied synthetic samples through prompting strategies with different content and context. A Random Forest (RF) classifier is trained on annotations of medical activities and corresponding keypoints. Additionally, we generate synthetic datasets in equal volumes using Random Sampling and Generative Adversarial Networks (GAN) to benchmark against our LLM-based approach. To evaluate, we compared the performance between baseline data and different augmentation approaches. The similarity between original and synthetic data is measured using the Kolmogorov-Smirnov (K-S) test. The proposed approach using LLM with prompts containing the explanation of the task with the description of the datasets to generate synthetic data has improved the overall ES classification performance. Our study illustrates the critical role of context and content in prompts for optimizing LLMs for synthetic data generation.
- 5 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 493-499
Open AccessSynthetic Skeleton Data Generation using Large Language Model for Nurse Activity Recognition
In this paper, we improve nurse activity recognition by employing a Large Language Model (LLM) to generate synthetic pose estimation data. Keypoint data extracted from recorded videos of a single nurse performing Endotracheal suctioning (ES) activities using You Only Look Once v7 (YOLOv7) is used as a database. We explore the issue of data imbalances that hinder the effectiveness of activity recognition algorithms. To counter this, we utilize LLMs to artificially augment the dataset by generating varied synthetic samples through prompting strategies with different content and context. A Random Forest (RF) classifier is trained on annotations of medical activities and corresponding keypoints. Additionally, we generate synthetic datasets in equal volumes using Random Sampling and Generative Adversarial Networks (GAN) to benchmark against our LLM-based approach. To evaluate, we compared the performance between baseline data and different augmentation approaches. The similarity between original and synthetic data is measured using the Kolmogorov-Smirnov (K-S) test. The proposed approach using LLM with prompts containing the explanation of the task with the description of the datasets to generate synthetic data has improved the overall ES classification performance. Our study illustrates the critical role of context and content in prompts for optimizing LLMs for synthetic data generation.