Related Experiment Video
Updated: May 8, 2026
09:59
Fabrication of Flexible Image Sensor Based on Lateral NIPIN Phototransistors
Published on: June 23, 2018
7.7K
A Flexible, Large-Scale Sensing Array with Low-Power In-Sensor Intelligence.
Zhangyu Xu1,2, Fan Zhang1,2, Erxuan Xie1,2
1State Key Laboratory of Intelligent Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan 430074, China.
Research (Washington, D.C.)
|November 14, 2024
Summary
This study introduces a flexible sensor array with integrated artificial intelligence (AI) for real-time monitoring. This in-sensor intelligence reduces energy use and bandwidth needs, enhancing AI of Things (AIoT) systems.
Area of Science:
- Flexible electronics
- Artificial Intelligence of Things (AIoT)
- Sensor technology
Background:
- Current AIoT systems require external computers for machine learning, leading to inefficiencies.
- External processing in AIoT systems causes issues with energy consumption, data privacy, and bandwidth limitations.
- There is a need for intelligent monitoring systems that integrate AI directly into sensing devices.
Purpose of the Study:
- To propose a flexible, large-scale sensing array with integrated, low-power in-sensor intelligence.
- To enable real-time recognition and learning of new patterns directly on the sensing device.
- To overcome the limitations of traditional computer-assisted AIoT systems.
Main Methods:
- Development of a flexible sensing array utilizing a compression hypervector encoder.
- Implementation of in-sensor intelligence for autonomous data processing and learning.
- Evaluation of system performance in terms of recognition speed, accuracy, energy consumption, and bandwidth reduction.
Main Results:
- Achieved significant reductions in communication bandwidth (1,024x) and energy consumption (500x).
- Demonstrated high recognition accuracy (approx. 99%) and rapid recognition speed (hundreds of milliseconds).
- Successfully enabled in-sensor learning of new postures without external computer processing, ensuring data privacy.
Conclusions:
- The proposed system effectively integrates AI into flexible sensors, addressing key limitations of current AIoT.
- In-sensor intelligence significantly enhances efficiency, privacy, and performance for real-time monitoring applications.
- This technology holds substantial potential for advancing AIoT and flexible electronics integration.
Related Concept Videos
01:26Inductively Coupled Plasma Atomic Emission Spectroscopy: Instrumentation
Inductively coupled plasma (ICP) is the common plasma source used in atomic emission spectroscopy (AES), a technique that detects and analyzes various elements in a sample. This method is often called inductively coupled plasma atomic emission spectroscopy (ICP-AES).
There are three main types of inductively coupled plasma atomic emission spectroscopy (ICP-AES) instruments: sequential, simultaneous multichannel, and Fourier transform instruments, with the latter being less commonly used.
There are three main types of inductively coupled plasma atomic emission spectroscopy (ICP-AES) instruments: sequential, simultaneous multichannel, and Fourier transform instruments, with the latter being less commonly used.
01:17Microbial Biosensors
Microbial biosensors are analytical devices that utilize living microbes to detect specific substances through measurable signals. These devices consist of two main components: biosensing organisms and signal-transducing elements. Biosensing organisms, such as Escherichia coli or Saccharomyces cerevisiae, are typically housed in multiwell plates connected to transducers, enabling rapid, real-time detection of target analytes.Signal Generation MechanismWhen a target analyte—such as...