TY - GEN
T1 - Towards Estimating the Stiffness of Soft Fruits using a Piezoresistive Tactile Sensor and Neural Network Schemes
AU - Erukainure, Frank Efe
AU - Parque, Victor
AU - Hassan, Mohsen A.
AU - Fathelbab, Ahmed M.R.
N1 - Funding Information:
ACKNOWLEDGMENT The authors would like to thank the Japan International Cooperation Agency (JICA), and the Science and Technology Development Fund (STDF-12417) project of the Egyptian Ministry of Scientific Research for their generous contributions towards this research.
Funding Information:
*This work was supported by the generous contribution of Japan International Cooperation Agency (JICA) 1Frank Efe Erukainure is with the Department of Mechatronics and Robotics Engineering, Egypt-Japan University of Science and Technology, Alexandria, Egypt frank.erukainure@ejust.edu.eg 2Victor Parque is with the Department of Modern Mechanical Engineering, Waseda University, Tokyo, Japan parque@aoni.waseda.jp 3Mohsen A. Hassan is with the Department of Materials Science and Engineering, Egypt-Japan University of Science and Technology, Alexandria, Egypt mohsen.khozami@ejust.edu.eg 4Ahmed M.R. FathElbab is with the Department of Mechatronics and Robotics Engineering, Egypt-Japan University of Science and Technology, Alexandria, Egypt ahmed.rashad@ejust.edu.eg
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Measuring the ripeness of fruits is one of the key challenges to enable optimal and just-in-time strategies across the fruit supply chain. In this paper, we study the performance of a tactile sensor to estimate the ground truth of the stiffness of fruits, with kiwifruit as a case study. Our sensor configuration is based on a three-beam cantilever arrangement with piezoresistive elements, enabling the stable acquisition of sensor readings over independent trials. Our estimation scheme is based on the com-pact feed-forward neural networks, allowing us to find effective nonlinear relationships between instantaneous sensor readings and the ground truth of stiffness of fruits. Our experiments using several kiwifruit specimens show the competitive performance frontiers of stiffness approximation using 25 compact feed-forward neural networks, converging to MSE loss at 10-5 across training-validation-testing in most of the cases, and the utmost predictive performance of a pyramidal class of feed-forward architectures. Our results pinpoint the potential to realize robust fruit ripeness measurement with intelligent tactile sensors.
AB - Measuring the ripeness of fruits is one of the key challenges to enable optimal and just-in-time strategies across the fruit supply chain. In this paper, we study the performance of a tactile sensor to estimate the ground truth of the stiffness of fruits, with kiwifruit as a case study. Our sensor configuration is based on a three-beam cantilever arrangement with piezoresistive elements, enabling the stable acquisition of sensor readings over independent trials. Our estimation scheme is based on the com-pact feed-forward neural networks, allowing us to find effective nonlinear relationships between instantaneous sensor readings and the ground truth of stiffness of fruits. Our experiments using several kiwifruit specimens show the competitive performance frontiers of stiffness approximation using 25 compact feed-forward neural networks, converging to MSE loss at 10-5 across training-validation-testing in most of the cases, and the utmost predictive performance of a pyramidal class of feed-forward architectures. Our results pinpoint the potential to realize robust fruit ripeness measurement with intelligent tactile sensors.
UR - http://www.scopus.com/inward/record.url?scp=85136269120&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85136269120&partnerID=8YFLogxK
U2 - 10.1109/AIM52237.2022.9863245
DO - 10.1109/AIM52237.2022.9863245
M3 - Conference contribution
AN - SCOPUS:85136269120
T3 - IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM
SP - 290
EP - 295
BT - 2022 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2022
Y2 - 11 July 2022 through 15 July 2022
ER -