Udayanga Sasanga Samarakoon

Mr. Udayanga Sasanga Samarakoon

Mechatronic, Sri Lanka Technological Campus, Padukka, Sri Lanka
orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
12 February 2025 in Biomimetics
Verified
Journal Article
Open access
PDF file
Udayanga Sasanga SamarakoonUdayanga Sasanga Samarakoon
Udayanga Sasanga Samarakoon
HHH. M. K. K. M. B. Herath
H. M. K. K. M. B. Herath
LYLasith Yasakethu
Lasith Yasakethu
DFDileepa Fernando
Dileepa Fernando
NVNuwan Madusanka Vithanage
Nuwan Madusanka Vithanage
BLByeong-il Lee
Byeong-il Lee
Restoring strength, function, and mobility following an illness, accident, or surgery is the primary goal of upper arm rehabilitation. Exoskeletons offer adaptable support, enhancing patient engagement and accelerating recovery. This work proposes an adjustable, wearable robotic exoskeleton powered by electromyography (EMG) data for upper arm rehabilitation. Three activation levels—low, medium, and high—were applied to the EMG data to forecast the Pulse Width Modulation (PWM) based on the range of motion (ROM) angle. Conventional machine learning (ML) models, including K-Nearest Neighbor Regression (K-NNR), Support Vector Regression (SVR), and Random Forest Regression (RFR), were compared with neural network approaches, including Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTM) to determine the best ML model for the ROM angle prediction. The LSTM model emerged as the best predictor with a high accuracy of 0.96. The system achieved 0.89 accuracy in exoskeleton control and 0.85 accuracy in signal categorization. Additionally, the proposed exoskeleton demonstrated a 0.97 performance in ROM correction compared to conventional methods (p = 0.097). These findings highlight the potential of EMG-based, LSTM-enabled exoskeleton systems to deliver accurate and adaptive upper arm rehabilitation, particularly for senior citizens, by providing personalized and effective support.

12 December 2024
Verified
Conference Paper
Closed access
CPC.N. Perera
C.N. Perera
BAB.G.C. Ananda
B.G.C. Ananda
Udayanga Sasanga SamarakoonUdayanga Sasanga Samarakoon
Udayanga Sasanga Samarakoon
HHH. M. K. K. M. B. Herath
H. M. K. K. M. B. Herath
SYS.L.P. Yasakethu
S.L.P. Yasakethu
Venipuncture is essential for diagnosis and therapy, but it frequently has problems with vein identification and needle placement precision, which can result in consequences like bruises and bleeding. The proposed medical robot uses Cartesian coordinate mechanisms to locate and puncture forearm veins with low discomfort, producing precise and repeatable movements, especially under intelligent healthcare. The device combines cutting-edge sensor and image technology to pinpoint the best places for punctures and direct the placement of needles. By reducing human error, enhancing patient outcomes, and optimizing healthcare workers' workflow, this innovation seeks to make venipuncture operations more dependable and effective. The experiment findings indicate a promising breakthrough in healthcare robots for increased accuracy and cost-efficiency, with 90.9 % accuracy in box prediction, 94.9 % in vein segmentation, and 98.7 % in vein puncturing. The proposed mechanism can be used for automated tasks.