Health Monitoring System from Pyralux Copper-Clad Laminate Film and Random Forest Algorithm.

Sensor technologies have been core features for various wearable electronic products for decades. Their functions are expected to continue to play an essential role in future generations of wearable products. For example, trends in industrial, military, and security applications include smartwatches used for monitoring medical indicators, hearing devices with integrated sensor options, and electronic skins. However, many studies have focused on a specific area of the system, such as manufacturing processes, data analysis, or actual testing. This has led to challenges regarding the reliability, accuracy, or connectivity of components in the same wearable system. There is an urgent need for studies that consider the whole system to maximize the efficiency of soft sensors. This study proposes a method to fabricate a resistive pressure sensor with high sensitivity, resilience, and good strain tolerance for recognizing human motion or body signals. Herein, the sensor electrodes are shaped on a thin Pyralux film. A layer of microfiber polyesters, coated with carbon nanotubes, is used as the bearing and pressure sensing layer. Our sensor shows superior capabilities in respiratory monitoring. More specifically, the sensor can work in high-humidity environments, even when immersed in water-this is always a big challenge for conventional sensors. In addition, the embedded random forest model, built for the application to recognize restoration signals with high accuracy (up to 92%), helps to provide a better overview when placing flexible sensors in a practical system.

Identification and Classification of Human Body Exercises on Smart Textile Bands by Combining Decision Tree and Convolutional Neural Networks.

In recent years, human activity recognition (HAR) has gained significant interest from researchers in the sports and fitness industries. In this study, the authors have proposed a cascaded method including two classifying stages to classify fitness exercises, utilizing a decision tree as the first stage and a one-dimension convolutional neural network as the second stage. The data acquisition was carried out by five participants performing exercises while wearing an inertial measurement unit sensor attached to a wristband on their wrists. However, only data acquired along the z-axis of the IMU accelerator was used as input to train and test the proposed model, to simplify the model and optimize the training time while still achieving good performance. To examine the efficiency of the proposed method, the authors compared the performance of the cascaded model and the conventional 1D-CNN model. The obtained results showed an overall improvement in the accuracy of exercise classification by the proposed model, which was approximately 92%, compared to 82.4% for the 1D-CNN model. In addition, the authors suggested and evaluated two methods to optimize the clustering outcome of the first stage in the cascaded model. This research demonstrates that the proposed model, with advantages in terms of training time and computational cost, is able to classify fitness workouts with high performance. Therefore, with further development, it can be applied in various real-time HAR applications.