Abstract | ||
---|---|---|
Tactile data processing and analysis is still essentially an open challenge. In this framework, we demonstrate a method to achieve touch modality classification using pre-trained convolutional neural networks (CNNs). The 3D tensorial tactile data generated by real human interactions on an electronic skin (E-Skin) are transformed into 2D images. Using a transfer learning approach formalized through a CNN, we address the challenging task of the recognition of the object that was touched by the E-Skin. The feasibility and efficiency of the proposed method are proven using a real tactile dataset outperforming classification results obtained with the same dataset in the literature. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/PRIME.2019.8787748 | 2019 15th Conference on Ph.D Research in Microelectronics and Electronics (PRIME) |
Keywords | Field | DocType |
convolutional neural network (CNN),Tactile sensing,prosthetic,deep learning,signal processing | Data processing,Task analysis,Pattern recognition,Convolutional neural network,Computer science,Transfer of learning,Electronic skin,Control engineering,Feature extraction,Artificial intelligence,Data classification,Tactile sensor | Conference |
ISBN | Citations | PageRank |
978-1-7281-3550-2 | 0 | 0.34 |
References | Authors | |
10 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mohamad Alameh | 1 | 0 | 0.34 |
Ali Ibrahim | 2 | 0 | 0.68 |
M. Valle | 3 | 97 | 19.19 |
Gabriele Moser | 4 | 919 | 76.92 |