Multilayer Perceptron Algorithm-Assisted Flexible Piezoresistive PDMS/Chitosan/cMWCNT Sponge Pressure Sensor for Sedentary Healthcare Monitoring

A Monolithic Neuromorphic Device for In-Sensor Tactile Computing

To emulate the tactile perception of human skin, the integration of tactile sensors with neuromorphic devices has emerged as a promising approach to achieve near-sensor information processing. Here, we present a monolithic electronic device that seamlessly integrates tactile perception and neuromorphic computing functionalities within a single architecture, with synaptic plasticity directly tunable by tactile inputs. This unique capability stems from our engineered device structure employing SnO2 nanowires as the conductive channel coupled with a pressure-sensitive chitosan layer ionic gating layer. The device demonstrates pressure-dependent memory retention and learning behaviors, effectively mimicking the enhanced cognitive functions observed in humans under stressful conditions. Furthermore, the integrated design exhibits potential for implementing bioinspired electronic systems requiring adaptive tactile information processing.

Machine Learning-Based Risk Factor Analysis and Prediction Model Construction for the Occurrence of Chronic Heart Failure: Health Ecologic Study

BACKGROUND

Chronic heart failure (CHF) is a serious threat to human health, with high morbidity and mortality rates, imposing a heavy burden on the health care system and society. With the abundance of medical data and the rapid development of machine learning (ML) technologies, new opportunities are provided for in-depth investigation of the mechanisms of CHF and the construction of predictive models. The introduction of health ecology research methodology enables a comprehensive dissection of CHF risk factors from a wider range of environmental, social, and individual factors. This not only helps to identify high-risk groups at an early stage but also provides a scientific basis for the development of precise prevention and intervention strategies.

OBJECTIVE

This study aims to use ML to construct a predictive model of the risk of occurrence of CHF and analyze the risk of CHF from a health ecology perspective.

METHODS

This study sourced data from the Jackson Heart Study database. Stringent data preprocessing procedures were implemented, which included meticulous management of missing values and the standardization of data. Principal component analysis and random forest (RF) were used as feature selection techniques. Subsequently, several ML models, namely decision tree, RF, extreme gradient boosting, adaptive boosting (AdaBoost), support vector machine, naive Bayes model, multilayer perceptron, and bootstrap forest, were constructed, and their performance was evaluated. The effectiveness of the models was validated through internal validation using a 10-fold cross-validation approach on the training and validation sets. In addition, the performance metrics of each model, including accuracy, precision, sensitivity, F1-score, and area under the curve (AUC), were compared. After selecting the best model, we used hyperparameter optimization to construct a better model.

RESULTS

RF-selected features (21 in total) had an average root mean square error of 0.30, outperforming principal component analysis. Synthetic Minority Oversampling Technique and Edited Nearest Neighbors showed better accuracy in data balancing. The AdaBoost model was most effective with an AUC of 0.86, accuracy of 75.30%, precision of 0.86, sensitivity of 0.69, and F1-score of 0.76. Validation on the training and validation sets through 10-fold cross-validation gave an AUC of 0.97, an accuracy of 91.27%, a precision of 0.94, a sensitivity of 0.92, and an F1-score of 0.94. After random search processing, the accuracy and AUC of AdaBoost improved. Its accuracy was 77.68% and its AUC was 0.86.

CONCLUSIONS

This study offered insights into CHF risk prediction. Future research should focus on prospective studies, diverse data, advanced techniques, longitudinal studies, and exploring factor interactions for better CHF prevention and management.

Superhydrophobic, Anti-Freezing and Multi-Cross-Linked Wearable Hydrogel Strain Sensor for Underwater Gesture Recognition

Conductive hydrogel is considered to be one of the most potential sensing materials for wearable strain sensors. However, both the hydrophilicity of polymer chains and high water content severely inhibit the potential applications of hydrogel-based sensors in extreme conditions. In this study, a multicross-linked hydrogel was prepared by simultaneously introducing a double-network matrix, multiple conductive fillers, and free-moving ions, which can withstand an ultralow temperature below -80 °C. A superhydrophobic Ecoflex layer with a water contact angle of 159.1° was coated on the hydrogel using simple spraying and laser engraving methods. Additionally, the smart glove integrating five hydrogel strain sensors with a microprocessor was developed to recognize 12 types of diving gestures and synchronously transmit recognition results to smartphones. The superhydrophobic and antifreezing hydrogel strain sensor proposed in this study emerges promising potentials in wearable electronics, human-machine interfaces, and underwater applications.

Wireless breathable face mask sensor for spatiotemporal 2D respiration profiling and respiratory diagnosis

Owing to air pollution and the pandemic outbreak, the need for quantitative pulmonary monitoring has greatly increased. The COVID-19 outbreak has aroused attention for comfortable wireless monitoring of respiratory profiles and more real-time diagnosis of respiratory diseases. Although respiration sensors have been investigated extensively with single-pixel sensors, 2D respiration profiling with a pixelated array sensor has not been demonstrated for both exhaling and inhaling. Since the pixelated array sensor allowed for simultaneous profiling of the nasal breathing and oral breathing, it provides essential respiratory information such as breathing patterns, respiration habit, breathing disorders. In this study, we introduced an air-permeable, stretchable, and a pixelated pressure sensor that can be integrated into a commercial face mask. The mask sensor showed a strain-independent pressure-sensing performance, providing 2D pressure profiles for exhalation and inhalation. Real-time 2D respiration profiles could monitor various respiratory behaviors, such as oral/nasal breathing, clogged nose, out-of-breath, and coughing. Furthermore, they could detect respiratory diseases, such as rhinitis, sleep apnea, and pneumonia. The 2D respiratory profiling mask sensor is expected to be employed for remote respiration monitoring and timely patient treatment.

Research Progress of Flexible Piezoresistive Sensors Based on Polymer Porous Materials

Flexible piezoresistive sensors are in high demand in areas such as wearable devices, electronic skin, and human-machine interfaces due to their advantageous features, including low power consumption, excellent bending stability, broad testing pressure range, and simple manufacturing technology. With the advancement of intelligent technology, higher requirements for the sensitivity, accuracy, response time, measurement range, and weather resistance of piezoresistive sensors are emerging. Due to the designability of polymer porous materials and conductive phases, and with more multivariate combinations, it is possible to achieve higher sensitivity and lower detection limits, which are more promising than traditional flexible sensor materials. Based on this, this work reviews recent advancements in research on flexible pressure sensors utilizing polymer porous materials. Furthermore, this review examines sensor performance optimization and development from the perspectives of three-dimensional porous flexible substrate regulation, sensing material selection and composite technology, and substrate and sensing material structure design.