The future of AI with solar-powered synaptic devices

The future of AI with solar-powered synaptic devices

by Riko Seibo

Tokyo, Japan (SPX) Nov 26, 2024

Artificial intelligence (AI) is increasingly relied upon for predicting critical events such as heart attacks, natural disasters, and infrastructure failures. These applications demand technologies capable of rapidly processing data. One such promising approach is reservoir computing, particularly physical reservoir computing (PRC), known for its efficiency in handling time-series data with minimal power consumption. Optoelectronic artificial synapses in PRC, mimicking human neural synaptic structures, are poised to enable advanced real-time data processing and recognition akin to the human visual system.

Existing self-powered optoelectronic synaptic devices, however, struggle to process time-series data across diverse timescales, which is essential for applications in environmental monitoring, infrastructure maintenance, and healthcare.

Addressing this challenge, researchers at Tokyo University of Science (TUS), led by Associate Professor Takashi Ikuno and including Hiroaki Komatsu and Norika Hosoda, have developed an innovative self-powered dye-sensitized solar cell-based optoelectronic photopolymeric human synapse. This groundbreaking device, featuring a controllable time constant based on input light intensity, represents a major advancement in the field. The study, published on October 28, 2024, in ‘ACS Applied Materials and Interfaces’, highlights the potential of this technology.

Dr. Ikuno explained, “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.”

The new device integrates squarylium derivative-based dyes, incorporating optical input, AI computation, analog output, and power supply at the material level. It demonstrates synaptic plasticity, exhibiting features such as paired-pulse facilitation and depression in response to light intensity. The device achieves high computational performance in time-series data processing tasks while maintaining low power consumption, regardless of the input light pulse width.

Remarkably, the device achieved over 90% accuracy in classifying human movements, including bending, jumping, running, and walking, when used as the reservoir layer of PRC. Its power consumption is only 1% of that required by traditional systems, significantly reducing carbon emissions. Dr. Ikuno emphasized, “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.”

This innovation holds significant promise for edge AI applications, including surveillance cameras, automotive sensors, and health monitoring systems. “This invention can be used as a massively popular edge AI optical sensor that can be attached to any object or person,” noted Dr. Ikuno. He further highlighted its potential to improve vehicle energy efficiency and reduce costs in standalone smartwatches and medical devices.

The novel solar cell-based device could redefine energy-efficient edge AI sensors across various applications, marking a significant leap forward in both technology and sustainability.

Research Report:Self-Powered Dye-Sensitized Solar-Cell-Based Synaptic Devices for Multi-Scale Time-Series Data Processing in Physical Reservoir Computing