Flexible Intelligent Epidermis Warning System: Machine Learning and 3D Bioinspired Conductive MOF Network for Dual Pressure Sensing

*Flexible Intelligent Epidermis Warning System: Machine Learning and 3D Bioinspired Conductive MOF Network for Dual Pressure Sensing

Flexible Intelligent Epidermis Warning System: Machine Learning and 3D Bioinspired Conductive MOF Network for Dual Pressure Sensing

Professor Xu Lin from Jilin University leads a research team addressing the current deficiencies in flexible electronic devices in simulating skin’s three-dimensional structure and synchronously encoding multi-stimuli information capabilities. They have developed an artificial epidermis alarm system based on a three-dimensional conductive MOF network that can recognize risk factors for asthma attacks. By in-situ growing Cu3(HHTP)2 particles on the surface of hollow spherical Ti3C2Tx, they constructed a bioinspired Ti3C2Tx@Cu3(HHTP)2 composite material.

This composite material simulates the stratum corneum and granular layer of the skin, achieving independent responses to nitrogen dioxide gas and pressure. The device exhibits a high sensitivity of up to 2.13% ppm-1 to nitrogen dioxide gas with a response time of 7 seconds, while demonstrating high sensitivity and rapid response/recovery characteristics within a pressure range of 0-6.1 kPa. This flexible intelligent epidermis device has been applied to wireless monitoring of asthma risk factors and has achieved a classification accuracy of up to 97.6% through machine learning algorithms, providing new technological means for early diagnosis and management of chronic diseases such as asthma. The first author of this article is Qingqing Zhou from the School of Electronic Science and Engineering at Jilin University, and the corresponding authors are Xu Lin from Jilin University and Jong Seung Kim from Korea University. Related work was published under the title “A Flexible Smart Healthcare Platform Conjugated with Artificial Epidermis Assembled by Three-Dimensionally Conductive MOF Network for Gas and Pressure Sensing” in Nano-Micro Letters.

Related work can be seen in the series of promotions by Blue Fatty i Textile: Small University of Macau and Shenzhen Advanced Institute 3D bioinspired fiber hair structure self-adhesive electronic skin: Human-machine interaction – enabling machines to perceive human touch (qq.com), Advance Science sports sensing electronic skin: stickable, breathable, and waterproof wearable technology (qq.com), Tsinghua University Zhang Yihui’s team successfully developed a new type of 3D electronic skin simulating human skin (3DAE-Skin).

Flexible Intelligent Epidermis Warning System: Machine Learning and 3D Bioinspired Conductive MOF Network for Dual Pressure Sensing

Self-adhesive electronic skin: Human-machine interaction

*Flexible Intelligent Epidermis Warning System: Machine Learning and 3D Bioinspired Conductive MOF Network for Dual Pressure Sensing

The human skin, as the most expanded organ of the body, interacts and communicates with various external stimuli through external receptors, inducing various bioelectrical impulses based on the nature of mechanical stimuli. Drawing on the unique three-dimensional (3D) topological interconnection architecture of the skin, scientists have carefully designed a series of electronic skins (e-skin) with 3D interlocking hierarchical structures for health monitoring and clinical diagnosis. However, most current electronic skin models exhibit similar or even identical resistance change mechanisms when responding to gas or pressure stimuli, often leading to mixed electrical outputs that severely interfere with signal reception and output. Therefore, there is an urgent need to develop an independent, multifunctional sensor that can provide interference-free response signals and high-precision recognition of stimuli through streamlined and effective processes.

The researchers of this article constructed an artificial skin device by in-situ growing Cu3(HHTP)2 particles on the surface of hollow spherical titanium carbide (Ti3C2Tx), aiming to simultaneously simulate the stratum corneum and granular layer of the skin. By integrating a dual-module sensor into a flexible printed circuit, they independently developed a flexible wearable alarm system with a mobile application terminal. This system can assess risk factors associated with asthma, such as external NO2 gas stimulation, abnormal exhalation behavior, and finger pressure, achieving an identification accuracy of 97.6% with the assistance of machine learning algorithms. This innovative device provides a feasible route for developing intelligent multifunctional medical devices for emerging transformative remote medical diagnostics.

Highlight 1: New type of artificial skin device

A new type of artificial skin device is proposed, mimicking the three-dimensional layout of the epidermis-dermis-subcutaneous layer in human skin, combining conductive Cu3(HHTP)2 with spherical Ti3C2Tx to form a sensor that can independently perceive NO2 gas and pressure stimuli. This design allows the sensor to better simulate human skin’s perception of pressure and strain, improving the accuracy and efficiency of sensing.

Highlight 2: Intelligent wearable alarm system integrated with artificial skin device

An intelligent wearable alarm system integrated with the artificial skin device has been developed. It consists of an artificial skin device that simulates skin structure, dual-mode sensors, a mobile application terminal, a wireless WIFI module, and a power supply. This system can identify asthma-related risk factors with a high accuracy of 97.6% using machine learning algorithms, achieving precise signal capture and timely response to potential health risks in human-machine interaction, providing early warnings for asthma patients and enabling real-time monitoring and health analysis of user physiological parameters. The system can also achieve intelligent medical monitoring and personal health assessment through a cloud platform and mobile application terminal, providing users with a comprehensive health management solution and demonstrating significant application potential in intelligent sensing and remote medical fields.

Flexible Intelligent Epidermis Warning System: Machine Learning and 3D Bioinspired Conductive MOF Network for Dual Pressure Sensing

Figure 1. Intelligent wearable alarm system integrated with artificial skin device

Figure 1 vividly demonstrates the composition and application of this artificial skin device, which mimics the three-dimensional layout of human skin and is composed of dual-mode sensors, exhibiting optimized synergistic effects, enhanced signal conduction capability, and strong hydrophobic properties, enabling stable responses to gas and pressure stimuli in areas of human respiration and sweating. Integrating this dual-mode sensor into a flexible printed circuit allows for wireless real-time assessment of asthma-related risk factors, achieving an accuracy of 97.6% through machine learning algorithms based on 1-D convolutional neural networks (CNNs), providing an innovative solution for remote medical diagnosis.Flexible Intelligent Epidermis Warning System: Machine Learning and 3D Bioinspired Conductive MOF Network for Dual Pressure Sensing

Figure 2. Synthesis process and microscopic characterization of Ti3C2Tx@Cu3(HHTP)2 composite material

Figure 2 illustrates the preparation process and microscopic structure characteristics of Ti3C2Tx@Cu3(HHTP)2 composite material. Through selective etching and self-assembly techniques, Ti3C2Tx MXene flakes and PMMA@Ti3C2Tx spheres were prepared, and hollow Ti3C2Tx foam was formed through high-temperature calcination; Cu3(HHTP)2 particles were synthesized by solvent thermal method and formed a tight composite material with Ti3C2Tx foam through strong electrostatic interactions. Scanning electron microscopy and transmission electron microscopy images reveal the microscopic structure of the material, and high-resolution transmission electron microscopy images and energy-dispersive spectroscopy elemental mapping further confirm the uniform distribution of each element in the composite material, which is crucial for the material’s performance.

Flexible Intelligent Epidermis Warning System: Machine Learning and 3D Bioinspired Conductive MOF Network for Dual Pressure Sensing

Figure 3. Dynamic response of various sensors to different concentrations of NO2 gas at room temperature

Figure 3 demonstrates the response performance of Ti3C2Tx@Cu3(HHTP)2 sensor to NO2 gas. The dynamic response curves of the sensor at different concentration ranges show its sensitivity to NO2 gas, especially its performance at low concentrations (1-60ppm) and high concentrations (80-200ppm). The relationship between the response value and NO2 concentration reveals the sensor’s high sensitivity and rapid response capability. Furthermore, the sensor exhibits good selectivity when monitoring various volatile organic compounds, and tests under different relative humidity conditions indicate its strong resistance to humidity interference. Repeatability and long-term stability test results show that the sensor’s performance remains stable after multiple uses, and its response variations under different bending angles also indicate its good bending stability. Finally, the sensor’s performance is compared with other reported NO2 gas sensors, further validating its superiority in practical applications.

Flexible Intelligent Epidermis Warning System: Machine Learning and 3D Bioinspired Conductive MOF Network for Dual Pressure Sensing

Figure 4. Piezoelectric performance and response characteristics of Ti3C2Tx@Cu3(HHTP)2 pressure sensor

Figure 4 primarily showcases the piezoelectric performance and response characteristics of Ti3C2Tx@Cu3(HHTP)2 pressure sensor. The current-voltage curve of the sensor indicates that as pressure is applied, the resistance decreases linearly, demonstrating good ohmic contact characteristics. The response and recovery time test results of the sensor at different pressures reveal its rapid response capability, and the sensitivity curve shows high sensitivity in the low pressure range. The pressure sensing mechanism of the sensor is also explained, and its potential in capturing human motion signals and sound vibrations is demonstrated through practical applications of the sensor, further proving its wide application prospects in health monitoring and human-machine interaction.

Figure 5. Schematic diagram of flexible intelligent wearable alarm system for monitoring asthma signals

Figure 5 illustrates the design of a flexible intelligent wearable alarm system for monitoring asthma signals, including components such as the ESP32 chip, dual-mode sensors, power supply, and WIFI wireless data transmission module, and demonstrates how the flexible dual-mode sensor is integrated into flexible printed circuit boards (FPCB) for detecting different pressures. This system can respond in real-time to various physiological signals such as NO2 atmosphere, normal and deep breathing, light pressing, and heavy pressing, employing machine learning algorithms based on one-dimensional convolutional neural networks (1-D CNNs) for signal analysis. The system’s classification accuracy for five body movement patterns (light breath, deep breath, light press, heavy press, and NO2 environment) is showcased in a confusion matrix, achieving an overall recognition accuracy of 97.6%, highlighting the system’s potential applications in remote medical diagnostics.

Flexible Intelligent Epidermis Warning System: Machine Learning and 3D Bioinspired Conductive MOF Network for Dual Pressure Sensing

(1) Outstanding performance: Independent response to different stimuli

The artificial skin device can independently perceive NO2 gas and pressure stimuli without external interference, demonstrating outstanding performance, making it highly promising for real-time monitoring of human movement and health status. Additionally, this sensor possesses good selectivity, resistance to interference, and stability, enabling its stable application in flexible intelligent wearable fields.

(2) Well-equipped application system

This new type of artificial skin device is cleverly combined with other integrated circuits to form a comprehensive intelligent wearable alarm system for early monitoring and prevention of chronic diseases such as asthma. This provides new technological means for the intelligent healthcare industry, with broad application prospects in health monitoring and remote medical fields.

Flexible Intelligent Epidermis Warning System: Machine Learning and 3D Bioinspired Conductive MOF Network for Dual Pressure Sensing

DOI: https://doi.org/10.1007/s40820-024-01548-5

Flexible Intelligent Epidermis Warning System: Machine Learning and 3D Bioinspired Conductive MOF Network for Dual Pressure Sensing

1) University of Chinese Academy of Sciences Nat. Commun.: A star-nose-like tactile-olfactory bionic sensing array for robust object recognition in non-visual environments.

(https://doi.org/10.1038/s41467-021-27672-z)

2) Hong Kong University of Science and Technology Science Advances: Biomimetic bimodal haptic perception using triboelectric effect.

(https://doi.org/10.1126/sciadv.ado6793)

3) Southern University of Science and Technology Nano Lett.: Fully Integrated Patch Based on Lamellar Porous Film Assisted GaN Optopairs for Wireless Intelligent Respiratory Monitoring.

(https://doi.org/10.1021/acs.nanolett.3c02071)

Flexible Intelligent Epidermis Warning System: Machine Learning and 3D Bioinspired Conductive MOF Network for Dual Pressure Sensing

Image | Health Textile Research Group Pan ChaomeiText | Health Textile Research Group Pan Chaomei

Editor | Blue Fatty

Initial Review | Yu Xi

Re-examination | OK Laboratory

Disclaimer: This article is based on the Feynman learning method, with some materials sourced from the internet, aiming to convey information and share knowledge, not representing endorsement of the views expressed or confirmation of their authenticity, nor constituting any form of advice. It only provides a communication platform and is not responsible for its copyright. If infringement is involved, please contact us for timely modification or deletion. If there are any offenses, please forgive us! Email: [email protected]

Leave a Comment

×