Researchers have developed a highly accurate humidity sensing system that monitors human behavior in real-time by detecting respiratory patterns, achieving 96.2 % accuracy through advanced sensor technology and machine learning.
Image Credit: PeopleImages.com - Yuri A/Shutterstock.com
A highly advanced humidity sensing system has been introduced, capable of monitoring human behaviors in real-time by detecting respiratory patterns. This innovative technology combines a highly sensitive humidity sensor with a thermistor and micro-heater, delivering exceptional accuracy in behavior recognition.
By utilizing porous nanoforests as the sensing material, the system offers outstanding sensitivity, stability, and gas selectivity. With the support of machine learning algorithms, it achieves an impressive accuracy in identifying human behaviors, making it a valuable tool for healthcare, smart homes, and daily health monitoring.
Traditional methods, such as video analysis and wearable devices, often raise privacy concerns, have environmental limitations, or require multiple sensors. Respiration, a fundamental physiological signal, varies with physical conditions, making it a promising metric for behavior recognition. However, existing humidity sensors often lack the sensitivity and stability needed to detect subtle respiratory changes, such as rapid or shallow breathing. This challenge underscores the demand for advanced sensors capable of accurately tracking and analyzing human behavior in real-time.
In a significant development, researchers from the Institute of Microelectronics at the Chinese Academy of Sciences have unveiled a novel humidity sensing system. This system integrates a thermistor and micro-heater with porous nanoforests as the sensing material, achieving a remarkable 96.2 % accuracy in recognizing human behaviors through respiration monitoring. The addition of machine learning enhances the system's ability to provide real-time analysis, paving the way for impactful applications in healthcare and smart home technologies.
At the core of this research is an innovative humidity sensor that leverages porous nanoforests (NFs). Operating within a humidity range of 60–90 % relative humidity (RH), the sensor boasts a sensitivity of 0.56 pF/%RH. A micro-heater amplifies its sensitivity by 5.8 times, allowing for the detection of even the slightest humidity changes in exhaled air. The integration of a thermistor allows for precise temperature monitoring, ensuring long-term stability and accuracy. With a rapid response time of just 2.2 seconds and excellent gas selectivity, the sensor is well-suited for respiratory activity monitoring.
Behavior recognition is driven by a convolutional neural network (CNN) that analyzes humidity, temperature, and time data captured by the sensor. By transforming these one-dimensional signals into three-dimensional maps, the system can classify nine common behaviors—including walking, sleeping, and exercising—with high accuracy. Integrated into a mask, the sensor continuously gathers respiratory data, which is wirelessly transmitted to smartphones or computers for analysis. This seamless integration of hardware and software highlights the system’s practical potential for both healthcare and everyday applications.
This innovative humidity sensing system represents a significant leap forward in real-time behavior recognition. By combining advanced sensor technology with machine learning, we've created a reliable and highly accurate tool for monitoring human behaviors, which has profound implications for both healthcare and smart home technologies.
Dr. Haiyang Mao, Study Lead Researcher, Institute of Microelectronics of the Chinese Academy of Sciences
The potential applications of this intelligent humidity sensing system are vast. In healthcare, it could aid in monitoring patients with respiratory conditions or those tracking their physical activity levels. In smart home environments, it could enhance comfort and safety by adjusting appliances based on occupants’ behaviors.
Additionally, the system's ability to detect subtle respiration changes may offer valuable insights into emotional states, such as anxiety or stress, creating new possibilities for mental health monitoring. With its impressive accuracy and real-time capabilities, this system is set to play a crucial role in the future of health electronics and intelligent living.
Journal Reference:
Yang, H., et al. (2025) An intelligent humidity sensing system for human behavior recognition. Microsystems & Nanoengineering. doi.org/10.1038/s41378-024-00863-6