Parvez Alam

This paper develops a 2.5D deep learning framework for segmenting heterogeneous lizard claw tissues from CT data, achieving high accuracy with an Inception-ResNet-v2 model.

AI-BioMech predicts mechanical behavior of cellular structures from 2D images using deep learning, achieving high accuracy and outperforming traditional methods in speed and scalability.

This paper identifies optimal lizard claw morphologies for bioinspired robotic manipulators by analyzing geometric parameters that influence grip strength and stability.

This study quantifies elastic recoil kinetics in cicada wings, showing faster recoil in upstroke than downstroke and highlighting thoracic involvement in wing stiffness.

This paper demonstrates that a necrobot made from a deceased varanid's skeleton can mimic the sprawling gait of a live varanid across multiple kinematic metrics.

This paper designs and analyzes Sundoli, a necrobot with multi-stiffness joints using geared mechanical metastructures, demonstrating its ability to support high payload ratios through passive deformation.

The paper introduces a standardized imaging method to improve the reliability of insect color analysis using AInsectID Version 1.1 Color Merge, demonstrating its robustness under varying environmental conditions.

This paper introduces Poka, a millimetre-scale necro-robot with a payload ratio of 6847%, surpassing all other robots and achieving high performance through a beetle exoskeleton chassis and bionic design.

AInsectID Version 1.1 is an insect species identification software using transfer learning with CNNs, achieving 99.65% validation accuracy.

This paper investigates the mechanical response of Bombyx mori silk cocoons to knife stabbing, finding that whole cocoons exhibit greater stab resistance than flattened segments due to structural integrity preservation.