Health monitoring sensors that are attached to clothing are a new trend of the times, especially stretchable sensors for human motion measurements or biological markers. However, price, durability, and performance always are major problems to be addressed and three-dimensional (3D) printing combined with conductive flexible materials (thermoplastic polyurethane) can be an optimal solution. Herein, we evaluate the effects of 3D printing-line directions (45°, 90°, 180°) on the sensor performances. Using fused filament fabrication (FDM) technology, the sensors are created with different print styles for specific purposes. We also discuss some main issues of the stretch sensors from Carbon Nanotube/Thermoplastic Polyurethane (CNT/TPU) and FDM. Our sensor achieves outstanding stability (10,000 cycles) and reliability, which are verified through repeated measurements. Its capability is demonstrated in a real application when detecting finger motion by a sensor-integrated into gloves. This paper is expected to bring contribution to the development of flexible conductive materials—based on 3D printing.

Among wearable e-textiles, conductive textile yarns are of particular interest because they can be used as flexible and wearable sensors without affecting the usual properties and comfort of the textiles. Firstly, this study proposed three types of piezoresistive textile sensors, namely, single-layer, double-layer, and quadruple-layer, to be made by the Jacquard processing method. This method enables the programmable design of the sensor’s structure and customizes the sensor’s sensitivity to work more efficiently in personalized applications. Secondly, the sensor range and coefficient of determination showed that the sensor is reliable and suitable for many applications. The dimensions of the proposed sensors are 20 × 20 cm, and the thicknesses are under 0.52 mm. The entire area of the sensor is a pressure-sensitive spot. Thirdly, the effect of layer density on the performance of the sensors showed that the single-layer pressure sensor has a thinner thickness and faster response time than the multilayer pressure sensor. Moreover, the sensors have a quick response time (<50 ms) and small hysteresis. Finally, the hysteresis will increase according to the number of conductive layers. Many tests were carried out, which can provide an excellent knowledge database in the context of large-area piezoresistive textile sensors using manufacturing by Jacquard processing. The effects of the percolation of CNTs, thickness, and sheet resistance on the performance of sensors were investigated. The structural and surface morphology of coating samples and SWCNTs were evaluated by using a scanning electron microscope. The structure of the proposed sensor is expected to be an essential step toward realizing wearable signal sensing for next-generation personalized applications.

Wearables have been applied in the field of fitness in recent years to monitor human muscles by recording electromyographic (EMG) signals. Understanding muscle activation during exercise routines allows strength athletes to achieve the best results. Hydrogels, which are widely used as wet electrodes in the fitness field, are not an option for wearable devices due to their characteristics of being disposable and skin-adhesion. Therefore, a lot of research has been conducted on the development of dry electrodes that can replace hydrogels. In this study, to make it wearable, neoprene was impregnated with high-purity SWCNTs to develop a dry electrode with less noise than hydrogel. Due to the impact of COVID-19, the demand for workouts to improve muscle strength, such as home gyms and personal trainers (PT), has increased. Although there are many studies related to aerobic exercise, there is a lack of wearable devices that can assist in improving muscle strength. This pilot study proposed the development of a wearable device in the form of an arm sleeve that can monitor muscle activity by recording EMG signals of the arm using nine textile-based sensors. In addition, some machine learning models were used to classify three arm target movements such as wrist curl, biceps curl, and dumbbell kickback from the EMG signals recorded by fiber-based sensors. The results obtained show that the EMG signal recorded by the proposed electrode contains less noise compared to that collected by the wet electrode. This was also evidenced by the high accuracy of the classification model used to classify the three arms workouts. This work classification device is an essential step towards wearable devices that can replace next-generation PT.

This study presents a 1D Residual Network(ResNet)-based algorithm for human activity recognition (HAR) focused on classifying 14 different workouts, which represent key exercises commonly performed in fitness training, using wearable inertial measurement unit (IMU) sensors. Unlike traditional 1D Convolutional neural network (CNN) models, the proposed 1D ResNet incorporates residual blocks to prevent gradient vanishing and exploding problems, allowing for deeper networks with improved performance. The IMU sensor, placed on the wrist, provided Z-axis acceleration data, which were used to train the model. A total of 901 data samples were collected from five participants, with 600 used for training and 301 for testing. The model achieved a recognition accuracy of 97.09%, surpassing the 89.03% of a 1D CNN without residual blocks and the 92% of a cascaded 1D CNN from previous research. These results indicate that the 1D ResNet model is highly effective in recognizing a wide range of workouts. The findings suggest that wearable devices can autonomously classify human activities and provide personalized training recommendations, paving the way for AI-driven personal training systems.

This study focuses on addressing the issue of unwanted vibrations commonly encountered in various fields by designing an Active Vibration Cancellation (AVC) structure using a flexible piezoelectric composite material macro fiber composite (MFC). A comparative performance analysis was conducted between the AVC and a traditional passive gel that continuously absorbs vibrations. The results showed that AVC was more effective in mitigating vibrations, making it a promising solution for vibration control. The results of this study from extensive vibration–sensing experiments and comparisons revealed that AVC effectively cancels the vibrations and vibration absorption performance of the passive gel. These findings underline the potential of AVC as an efficient method for eliminating and managing undesired vibrations in practical applications. Specifically, AVC demonstrated a high vibration cancellation ratio of approximately 0.96 at frequencies above 10 Hz. In contrast, passive gel exhibited a relatively consistent vibration absorption ratio, approximately 0.70 to 0.75 at all tested frequencies. These quantitative findings emphasize the superior performance of AVC in reducing vibrations to levels below a certain threshold, demonstrating its efficacy for vibration control in real-world scenarios.

The recent development of algorithms through artificial intelligence and the ability to measure the human body through soft textile sensors has enabled the provision of meaningful information to the wearer. In this study, a sensor sleeve using a textile elbow angle sensor that can measure the bending and relaxation of the elbow was manufactured and measured. In addition, biomechanical data from Biomechanical of Bodies (BoB)-4, a software capable of inverse dynamics that can optimally calculate the load on human joints and segments during exercise, was collected. A continuous system of resistance angle and angle biomechanical data was designed with an artificial intelligence multilayer perceptron (MLP) algorithm, and the accuracy and output results were checked. Consequently, the accuracy of MLP1 and MLP2 is exceedingly high, at approximately 0.80 and 1.00, respectively. The biomechanical data of the system is comparable to that of BoB, rendering it suitable for providing reliable information to the wearer. Based on this study, it is possible to develop algorithms and systems that can perform biomechanical analysis for various exercise movements in the future.