Explore my Research Publication 

Publication

The research addresses fabric defects in the apparel industry, which cause material and financial losses. Using data from six Sri Lankan factories, it aimed to improve waste prediction at the inspection stage, reducing material wastage. After preprocessing, 633 data points were analyzed with ten machine learning models. The Artificial Neural Network (ANN) model achieved the best performance, with a Mean Absolute Error (MAE) of 22.08. Statistical validation confirmed its reliability, making ANN a valuable tool for minimizing material wastage in garment production.

Publication

This study investigates the effectiveness of a companion robot in reducing stress for professionals working from home. The robot observes user behavior, detects facial emotions, stress levels, and speech, and engages in friendly conversations, offering stress-reducing suggestions. Results indicate the robot effectively reduces stress, improves workability, minimizes distractions, and enhances user well-being. The study highlights the potential for such systems in various settings, though further research is needed to evaluate long-term effectiveness and ethical implications.