A stacked sparse auto-encoder and back propagation network model for sensory event detection via a flexible ECoG
- PDF / 2,071,243 Bytes
- 17 Pages / 595.276 x 790.866 pts Page_size
- 106 Downloads / 257 Views
(0123456789().,-volV)(0123456789(). ,- volV)
RESEARCH ARTICLE
A stacked sparse auto-encoder and back propagation network model for sensory event detection via a flexible ECoG Oluwagbenga Paul Idowu1,2,3 • Jianping Huang1,3 • Yang Zhao1,3 • Oluwarotimi William Samuel1,3 Mei Yu1,3 • Peng Fang1,2,3 • Guanglin Li1,2,3
•
Received: 19 December 2019 / Revised: 22 April 2020 / Accepted: 22 May 2020 Ó Springer Nature B.V. 2020
Abstract Current prostheses are limited in their ability to provide direct sensory feedback to users with missing limb. Several efforts have been made to restore tactile sensation to amputees but the somatotopic tactile feedback often results in unnatural sensations, and it is yet unclear how and what information the somatosensory system receives during voluntary movement. The present study proposes an efficient model of stacked sparse autoencoder and back propagation neural network for detecting sensory events from a highly flexible electrocorticography (ECoG) electrode. During the mechanical stimulation with Von Frey (VF) filament on the plantar surface of rats’ foot, simultaneous recordings of tactile afferent signals were obtained from primary somatosensory cortex (S1) in the brain. In order to achieve a model with optimal performance, Particle Swarm Optimization and Adaptive Moment Estimation (Adam) were adopted to select the appropriate number of neurons, hidden layers and learning rate of each sparse auto-encoder. We evaluated the stimulus-evoked sensation by using an automated up-down (UD) method otherwise called UDReader. The assessment of tactile thresholds with VF shows that the right side of the hind-paw was significantly more sensitive at the tibia-(p = 6.50 9 10-4), followed by the saphenous(p = 7.84 9 10-4), and sural-(p = 8.24 9 10-4). We then validated our proposed model by comparing with the state-ofthe-art methods, and recorded accuracy of 98.8%, sensitivity of 96.8%, and specificity of 99.1%. Hence, we demonstrated the effectiveness of our algorithms in detecting sensory events through flexible ECoG recordings which could be a viable option in restoring somatosensory feedback. Keywords Sensory discrimination Sensory feedback Deep neural network model Neural interface model ECoG recordings
Introduction
& Peng Fang [email protected] & Guanglin Li [email protected] 1
CAS Key Laboratory of Human-Machine IntelligenceSynergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China
2
Shenzhen College of Advanced Technology, University of Chinese Academy of Sciences, Shenzhen 518055, China
3
Shenzhen Engineering Laboratory of Neural Rehabilitation Technology, Shenzhen 518055, China
Prostheses are indispensable for amputees in restoring their lost motion functions. In addition, the sense of touch is essential for realizing dexterous manipulation of objects, transfer of emotions, and providing of responses to amputees (Antfolk et al. 2013). However, lack of sensory feedback function is a major drawback with the current pr
Data Loading...
