scholarly journals Optical Axons for Electro-Optical Neural Networks

Sensors ◽  
2020 ◽  
Vol 20 (21) ◽  
pp. 6119
Author(s):  
Mircea Hulea ◽  
Zabih Ghassemlooy ◽  
Sujan Rajbhandari ◽  
Othman Isam Younus ◽  
Alexandru Barleanu
Keyword(s):  
Neural Networks ◽  
Optical Signal ◽  
Sensor Data ◽  
Line Of Sight ◽  
Optical Intensity ◽  
Digital Signals ◽  
Link Length ◽  
Optical Neural Networks ◽  
Analogue Signals ◽  
Neural Unit

Recently, neuromorphic sensors, which convert analogue signals to spiking frequencies, have been reported for neurorobotics. In bio-inspired systems these sensors are connected to the main neural unit to perform post-processing of the sensor data. The performance of spiking neural networks has been improved using optical synapses, which offer parallel communications between the distanced neural areas but are sensitive to the intensity variations of the optical signal. For systems with several neuromorphic sensors, which are connected optically to the main unit, the use of optical synapses is not an advantage. To address this, in this paper we propose and experimentally verify optical axons with synapses activated optically using digital signals. The synaptic weights are encoded by the energy of the stimuli, which are then optically transmitted independently. We show that the optical intensity fluctuations and link’s misalignment result in delay in activation of the synapses. For the proposed optical axon, we have demonstrated line of sight transmission over a maximum link length of 190 cm with a delay of 8 μs. Furthermore, we show the axon delay as a function of the illuminance using a fitted model for which the root mean square error (RMS) similarity is 0.95.

scholarly journals Deep Convolutional Neural Network with RNNs for Complex Activity Recognition Using Wrist-Worn Wearable Sensor Data

Electronics ◽  
2021 ◽  
Vol 10 (14) ◽  
pp. 1685
Author(s):  
Sakorn Mekruksavanich ◽  
Anuchit Jitpattanakul
Keyword(s):  
Neural Networks ◽  
Activity Recognition ◽  
Human Activities ◽  
Recognition Performance ◽  
Confusion Matrix ◽  
Experimental Studies ◽  
Industrial Applications ◽  
Sensor Data ◽  
Complex Activity ◽  
Activity Data

Sensor-based human activity recognition (S-HAR) has become an important and high-impact topic of research within human-centered computing. In the last decade, successful applications of S-HAR have been presented through fruitful academic research and industrial applications, including for healthcare monitoring, smart home controlling, and daily sport tracking. However, the growing requirements of many current applications for recognizing complex human activities (CHA) have begun to attract the attention of the HAR research field when compared with simple human activities (SHA). S-HAR has shown that deep learning (DL), a type of machine learning based on complicated artificial neural networks, has a significant degree of recognition efficiency. Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are two different types of DL methods that have been successfully applied to the S-HAR challenge in recent years. In this paper, we focused on four RNN-based DL models (LSTMs, BiLSTMs, GRUs, and BiGRUs) that performed complex activity recognition tasks. The efficiency of four hybrid DL models that combine convolutional layers with the efficient RNN-based models was also studied. Experimental studies on the UTwente dataset demonstrated that the suggested hybrid RNN-based models achieved a high level of recognition performance along with a variety of performance indicators, including accuracy, F1-score, and confusion matrix. The experimental results show that the hybrid DL model called CNN-BiGRU outperformed the other DL models with a high accuracy of 98.89% when using only complex activity data. Moreover, the CNN-BiGRU model also achieved the highest recognition performance in other scenarios (99.44% by using only simple activity data and 98.78% with a combination of simple and complex activities).

DESIGNING OF ALL-OPTICAL TRI-STATE LOGIC SYSTEM WITH THE HELP OF OPTICAL NONLINEAR MATERIAL

2008 ◽  
Vol 17 (03) ◽  
pp. 315-328 ◽  
Author(s):  
TANAY CHATTOPADHYAY ◽  
GOUTAM KUMAR MAITY ◽  
JITENDRA NATH ROY
Keyword(s):  
High Speed ◽  
Optical Switch ◽  
Digital Signal ◽  
Optical Signal ◽  
Nonlinear Material ◽  
Digital Signals ◽  
Photonic Networks ◽  
Optical Nonlinear Material ◽  
All Optical ◽  
Logic Operations

Nonlinear optics has been of increased interest for all-optical signal, data and image processing in high speed photonic networks. The application of multi-valued (nonbinary) digital signals can provide considerable relief in transmission, storage and processing of a large amount of information in digital signal processing. Here, we propose the design of an all-optical system for some basic tri-state logic operations (trinary OR, trinary AND, trinary XOR, Inverter, Truth detector, False detector) which exploits the polarization properties of light. Nonlinear material based optical switch can play an important role. Tri-state logic can play a significant role towards carry and borrow free arithmetic operations. The principles and possibilities of the design of nonlinear material based tri-state logic circuits are proposed and described.

Efficient On-Chip Training of Optical Neural Networks Using Genetic Algorithm

ACS Photonics ◽  
2021 ◽  
Author(s):  
Hui Zhang ◽  
Jayne Thompson ◽  
Mile Gu ◽  
Xu Dong Jiang ◽  
Hong Cai ◽  
...  
Keyword(s):  
Genetic Algorithm ◽  
Neural Networks ◽  
Optical Neural Networks ◽  
On Chip
Sign in / Sign up

Export Citation Format

Share Document