With the rapid growth of sensor networks, innovative technologies can be created to forecast emergency situations like earthquakes, volcanic eruptions, heart attacks, and buried pipeline failures using artificial intelligence (AI). As the number of sensors rises, various challenges arise, such as higher network load, delayed data transfer, and increased power consumption on the server.
To tackle these obstacles, there is a growing demand for in-sensor edge AI devices that integrate AI capabilities within the sensors themselves. Among these, reservoir computing stands out as a highly promising approach designed specifically for time-series data processing with low power consumption. It can be utilized across different frameworks, with physical reservoir computing (PRC) being the most widely recognized.
PRC utilizing optoelectronic artificial synapses (junction structures that allow nerve cells to convey electrical or chemical signals to other cells) that emulate human synaptic functions are anticipated to possess unmatched recognition and real-time processing abilities similar to those of the human visual system.
Nonetheless, PRC, relying on current self-powered optoelectronic synaptic devices, struggles to process time-series data across various timescales found in signals that monitor infrastructure, the natural environment, and health conditions.
Recently, a team of researchers from the Department of Applied Electronics at the Graduate School of Advanced Engineering, Tokyo University of Science (TUS), led by Associate Professor Takashi Ikuno, along with Mr. Hiroaki Komatsu and Ms. Norika Hosoda, have unveiled a self-powered dye-sensitized solar cell-based optoelectronic photopolymeric human synapse. This innovative synapse features a controllable time constant that responds dynamically to input light intensity.
“In order to process time-series input optical data with various time scales, it is essential to fabricate devices according to the desired time scale. Inspired by the afterimage phenomenon of the eye, we came up with a novel optoelectronic human synaptic device that can serve as a computational framework for power-saving edge AI optical sensors,” Dr. Ikuno explains the motivation behind their research.
The innovative solar cell-based device leverages advanced squarylium derivative-based dyes, seamlessly integrating optical input, AI computation, analog output, and power supply functions at the material level. It demonstrates synaptic plasticity when exposed to varying light intensities, exhibiting synaptic characteristics such as paired-pulse facilitation and paired-pulse depression.
Researchers illustrated that modifying the light intensity leads to superior computational performance in tasks involving time-series data, regardless of the width of the input light pulse.
Moreover, when this device was utilized as the reservoir layer of a photonic reservoir computing (PRC) system, it accurately classified human movements—such as bending, jumping, running, and walking—achieving over 90% accuracy. The power consumption remained at only 1% of what traditional systems require, which would significantly lower the related carbon emissions.
“We have demonstrated for the first time in the world that the developed device can operate with very low power consumption and yet identify human motion with a high accuracy rate,” emphasizes Dr. Ikuno.
This innovative device paves the way for the development of edge AI sensors for various temporal scales, with potential applications in surveillance cameras, automotive cameras, and health monitoring.
According to Dr. Ikuno, “This invention can be used as a massively popular edge AI optical sensor that can be attached to any object or person and can impact the cost involved in power consumption, such as car-mounted cameras and car-mounted computers.”
He adds, “This device can function as a sensor that can identify human movement with low power consumption, and thus has the potential to contribute to the improvement of vehicle power consumption. Furthermore, it is expected to be used as a low power consumption optical sensor in stand-alone smartwatches and medical devices, significantly reducing their costs to be comparable or even lower than that of current medical devices.”
This innovative solar cell-driven device could hasten the advancement of energy-efficient edge AI sensors with diverse uses.
Journal reference:
- Hiroaki KomatsuNorika HosodaTakashi Ikun. Self-Powered Dye-Sensitized Solar-Cell-Based Synaptic Devices for Multi-Scale Time-Series Data Processing in Physical Reservoir Computing. ACS Applied Materials & Interfaces, 2024; DOI: 10.1021/acsami.4c11061