Recent Advances in Flexible Piezoresistive Arrays: Materials, Design, and Applications

Classification of coronary artery disease using radial artery pulse wave analysis via machine learning

BACKGROUND

Coronary artery disease (CAD) is a major global cardiovascular health threat and the leading cause of death in many countries. The disease has a significant impact in China, where it has become the leading cause of death. There is an urgent need to develop non-invasive, rapid, cost-effective, and reliable techniques for the early detection of CAD using machine learning (ML).

METHODS

Six hundred eight participants were divided into three groups: healthy, hypertensive, and CAD. The raw data of pulse wave from those participants was collected. The data were de-noised, normalized, and analyzed using several applications. Seven ML classifiers were used to model the processed data, including Decision Tree (DT), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), Extra Trees (ET), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting (LightGBM), and Unbiased Boosting with Categorical Features (CatBoost).

RESULTS

The Extra Trees classifier demonstrated the best classification performance. After tunning, the results performance evaluation on test set are: 0.8579 accuracy, 0.9361 AUC, 0.8561 recall, 0.8581 precision, 0.8571 F1 score, 0.7859 kappa coefficient, and 0.7867 MCC. The top 10 feature importances of ET model are w/t1, t3/tmax, tmax, t3/t1, As, hf/3, tf/3/tmax, tf/5, w and tf/3/t1.

CONCLUSION

Radial artery pulse wave can be used to identify healthy, hypertensive and CAD participants by using Extra Trees Classifier. This method provides a potential pathway to recognize CAD patients by using a simple, non-invasive, and cost-effective technique.

Designs and Applications for the Multimodal Flexible Hybrid Epidermal Electronic Systems

Research on the flexible hybrid epidermal electronic system (FHEES) has attracted considerable attention due to its potential applications in human-machine interaction and healthcare. Through material and structural innovations, FHEES combines the advantages of traditional stiff electronic devices and flexible electronic technology, enabling it to be worn conformally on the skin while retaining complex system functionality. FHEESs use multimodal sensing to enhance the identification accuracy of the wearer's motion modes, intentions, or health status, thus realizing more comprehensive physiological signal acquisition. However, the heterogeneous integration of soft and stiff components makes balancing comfort and performance in designing and implementing multimodal FHEESs challenging. Herein, multimodal FHEESs are first introduced in 2 types based on their different system structure: all-in-one and assembled, reflecting totally different heterogeneous integration strategies. Characteristics and the key design issues (such as interconnect design, interface strategy, substrate selection, etc.) of the 2 multimodal FHEESs are emphasized. Besides, the applications and advantages of the 2 multimodal FHEESs in recent research have been presented, with a focus on the control and medical fields. Finally, the prospects and challenges of the multimodal FHEES are discussed.

A Flexible Double-Sided Curvature Sensor Array for Use in Soft Robotics

This paper describes the design, fabrication, integration, characterization, and demonstration of a novel flexible double-sided curvature sensor array for use in soft robotics. The paper explores the performance and potential applications of a piezoresistive sensor array consisting of four gold strain gauges on a flexible polyimide (PI) substrate arranged in a Wheatstone bridge configuration. Multiple sensor strips were arranged like the fingers of a hand. Integrating Shape Memory Alloy (SMA) foils alongside the fingers was explored to mimic a human hand-gripping motion controlled with temperature, while curvature sensor array strips measure the resulting finger shapes. Moreover, object sensing in a flexible granular material gripper was demonstrated. The sensors were embedded within Polydimethylsiloxane (PDMS) to enhance their tactile feel and adhesive properties. The findings of this study are promising for future applications, particularly in robotics and prosthetics, as the ability to accurately mimic human hand movements and reconstruct sensor surfaces paves the way for robotic hand functionality.

A Novel Resistive Sensor Network Utilizing an SAP-Enhanced Ionic Layer and CNT Doping for Multipoint Pressure Measurement

Amidst the rapid advancements in flexible electronics, flexible pressure sensors have achieved widespread applications in fields such as wearable devices and motion monitoring. Nevertheless, it is still a challenge to design a sensor with high sensitivity, cost-effectiveness, and a simplified manufacturing process. This paper introduces a piezoresistive sensor built upon a composite conductive filler. The sensor incorporates a super absorbent polymer (SAP) to absorb a phosphoric acid solution and doped carbon nanotubes as the composite conductive filler. In contrast to conventional rigid conductive fillers, the elastic polymer SAP enhances the sensor's stability significantly by exhibiting superior compatibility with the polydimethylsiloxane matrix, all the while reducing its Young's modulus. This work aims to theoretically elucidate the underlying principles that enable the sensor to achieve high sensitivity. It focuses on the induction of charge carriers due to pressure, which leads to the formation of a conductive pathway and subsequent changes in resistance, thus facilitating precise pressure detection. The paper also discusses the effects of piezoresistive layers with varying thicknesses and conductive fillers on the sensor's output performance. The results highlight the sensor's high sensitivity (0.094 kPa-1), rapid response time (105 ms), and exceptional cyclic load/unload stability (>5000 cycles). Furthermore, this paper establishes a versatile sensing network by integrating a portable inductance, capacitance, and resistance instrument with a programmable logic controller module. Compared to individual sensors, this system enables multipoint measurements, offering high spatial resolution and real-time monitoring capabilities, significantly expanding its overall practicality.