[Paper Review] Progress in artificial intelligence applications based on the combination of self-driven sensors and deep learning

Weixiang Wan, Wenjian Sun+4 more|arXiv (Cornell University)|Jan 30, 2024

Advanced Sensor and Control Systems16 citations

TL;DR

The paper reviews using triboelectric nanogenerator (TENG) based self-driven sensors for intelligent sound monitoring and recognition, and evaluates the feasibility of a sound perception module in ubiquitous sensor networks.

ABSTRACT

In the era of Internet of Things, how to develop a smart sensor system with sustainable power supply, easy deployment and flexible use has become a difficult problem to be solved. The traditional power supply has problems such as frequent replacement or charging when in use, which limits the development of wearable devices. The contact-to-separate friction nanogenerator (TENG) was prepared by using polychotomy thy lene (PTFE) and aluminum (AI) foils. Human motion energy was collected by human body arrangement, and human motion posture was monitored according to the changes of output electrical signals. In 2012, Academician Wang Zhong lin and his team invented the triboelectric nanogenerator (TENG), which uses Maxwell displacement current as a driving force to directly convert mechanical stimuli into electrical signals, so it can be used as a self-driven sensor. Teng-based sensors have the advantages of simple structure and high instantaneous power density, which provides an important means for building intelligent sensor systems. At the same time, machine learning, as a technology with low cost, short development cycle, strong data processing ability and prediction ability, has a significant effect on the processing of a large number of electrical signals generated by TENG, and the combination with TENG sensors will promote the rapid development of intelligent sensor networks in the future. Therefore, this paper is based on the intelligent sound monitoring and recognition system of TENG, which has good sound recognition capability, and aims to evaluate the feasibility of the sound perception module architecture in ubiquitous sensor networks.

Motivation & Objective

• Motivate the development of smart sensor systems with sustainable power and easy deployment.
• Explore the use of triboelectric nanogenerators (TENG) as self-driven sensors for wearable and ambient sensing.
• Assess the feasibility of a sound perception module architecture within ubiquitous sensor networks.

Proposed method

• Discuss the triboelectric nanogenerator (TENG) as a direct source of electrical signals driven by Maxwell displacement current.
• Highlight the advantages of TENG-based sensors such as simple structure and high instantaneous power density.
• Integrate machine learning techniques to process the electrical signals from TENG sensors for sound recognition.
• Present a focus on intelligent sound monitoring and recognition systems leveraging TENG sensors.

Experimental results

Research questions

• RQ1 Can TENG-based self-driven sensors reliably support sound perception tasks in ubiquitous sensor networks?
• RQ2 What architectural considerations enable effective integration of TENG sensors with deep learning for sound recognition?
• RQ3 What are the advantages and limitations of TENG sensors for wearable and ambient sensing in smart systems?

Key findings

• TENG sensors offer simple structure and high instantaneous power density, enabling self-powered sensing.
• Machine learning can process the electrical signals produced by TENG sensors for sound recognition tasks.
• The paper emphasizes feasibility and architectural considerations for deploying TENG-based sound perception in ubiquitous sensor networks.
• An intelligent sound monitoring and recognition system based on TENG demonstrates potential for rapid development of smart sensor networks.