A Machine Learning-Combined Flexible Sensor for Tactile Detection and Voice Recognition

Self-Powered Hybrid Motion and Health Sensing System Based on Triboelectric Nanogenerators

Triboelectric nanogenerator (TENG) represents an effective approach for the conversion of mechanical energy into electrical energy and has been explored to combine multiple technologies in past years. Self-powered sensors are not only free from the constraints of mechanical energy in the environment but also capable of efficiently harvesting ambient energy to sustain continuous operation. In this review, the remarkable development of TENG-based human body sensing achieved in recent years is presented, with a specific focus on human health sensing solutions, such as body motion and physiological signal detection. The movements originating from different parts of the body, such as body, touch, sound, and eyes, are systematically classified, and a thorough review of sensor structures and materials is conducted. Physiological signal sensors are categorized into non-implantable and implantable biomedical sensors for discussion. Suggestions for future applications of TENG-based biomedical sensors are also indicated, highlighting the associated challenges.

Bionic Spider Web Flexible Strain Sensor Based on CF-L and Machine Learning

At present, the preparation of laser-induced graphene (LIG) has become an important technology in sensor manufacturing. In the conventional preparation process, the CO2 laser is widely used; however, its experimental period is long and its efficiency needs to be improved. We propose an innovative strategy to improve the experimental efficiency. We use the machine learning method to accurately predict the preparation parameters of LIG, so as to optimize the experimental process. Different structures can lead to different sensor performances. The structure constructed by the CO2 laser is rough and has a large size, which can affect the performance of the sensor. Therefore, we propose for the first time an innovative method for intramembrane structure construction that combines the advantages of the CO2 laser and fiber laser (CF-L). With this CF-L method, we have successfully prepared a biomimetic, flexible strain sensor. This sensor not only maintains a high degree of sensitivity, but also has a more refined and optimized structure. The manufacturing process of the whole sensor is simple, economical, and durable and can be prepared in large quantities and can be used to detect the extension and bending of human joints.

Incorporating Machine Learning Strategies to Smart Gloves Enabled by Dual-Network Hydrogels for Multitask Control and User Identification

Smart gloves are often used in human-computer interaction scenarios due to their portability and ease of integration. However, their application in the field of information security has been less studied. Herein, we propose a smart glove using an iontronic capacitive sensor with significant pressure-sensing performance. Besides, an operator interface has been developed to match the smart glove, which is capable of multitasking integration of mouse movement, music playback, game control, and message typing in Internet chat rooms by capturing and encoding finger-tapping movements. In addition, by integrating machine learning, we can mine the characteristics of individual behavioral habits contained in the sensor signals and, based on this, achieve a deep binding of the user to the smart glove. The proposed smart glove can greatly facilitate people's lives, as well as explore a new strategy in research on the application of smart gloves in data security.

Flexible tactile sensors with interlocking serrated structures based on stretchable multiwalled carbon nanotube/silver nanowire/silicone rubber composites

Flexible tactile sensors have attracted significant interest because of their application scope in the fields of biomedicine, motion detection, and human-computer interaction. However, the development of tactile sensors with high sensitivity and flexibility remains a critical challenge. This study develops a patterned, stretchable, and fully elastomeric multiwalled carbon nanotube (MWCNT)/silver nanowire (Ag NW)/silicone rubber (SR) composite. The addition of Ag NWs to MWCNTs enhances the transmission path of the conductive network, yielding a CNT/Ag NW/SR composite with a sensitivity coefficient of 40. This characteristic renders it suitable for use as a piezoresistive sensing material. The interlocking sawtooth structure can convert the mechanical stimuli of the sensor to the tensile strain of the composite, thereby enhancing its sensitivity and flexibility. Experimental results indicate that the developed tactile sensor exhibited a sensitivity of 2.82 N-1 at 0-0.5 N and 1.51 N-1 at 0.5-2 N. These haptic sensors also demonstrate good dynamic response, repeatability, and long life. Furthermore, experimental results show that these haptic sensors exhibit high reproducibility, fast dynamic response, and good mechanical and electrical stability. Because of these exceptional properties, the as-prepared sensor can be applied in the development of smart robots, prosthetics, and wearable devices.

Facile Graphene Oxide Modification Method via Hydroxyl-yne Click Reaction for Ultrasensitive and Ultrawide Monitoring Pressure Sensors

Enhancing the durability and functionality of existing materials through sustainable pathways and appropriate structural design represents a time- and cost-effective strategy for the development of advanced wearable devices. Herein, a facile graphene oxide (GO) modification method via the hydroxyl-yne click reaction is present for the first time. By the click coupling between propiolate esters and hydroxyl groups on GO under mild conditions, various functional molecules are successfully grafted onto the GO. The modified GO is characterized by FTIR, XRD, TGA, XPS, and contact angle, proving significantly improved dispersibility in various solvents. Besides the high efficiency, high selectivity, and mild reaction conditions, this method is highly practical and accessible, avoiding the need for prefunctionalizations, metals, or toxic reagents. Subsequently, a rGO-PDMS sponge-based piezoresistive sensor developed by modified GO-P2 as the sensitive material exhibits impressive performance: high sensitivity (335 kPa-1, 0.8-150 kPa), wide linear range (>500 kPa), low detection limit (0.8 kPa), and long-lasting durability (>5000 cycles). Various practical applications have been demonstrated, including body joint movement recognition and real-time monitoring of subtle movements. These results prove the practicality of the methodology and make the rGO-PDMS sponge-based pressure sensor a real candidate for a wide array of wearable applications.

Machine Learning-Enabled Tactile Sensor Design for Dynamic Touch Decoding

Skin-like flexible sensors play vital roles in healthcare and human-machine interactions. However, general goals focus on pursuing intrinsic static and dynamic performance of skin-like sensors themselves accompanied with diverse trial-and-error attempts. Such a forward strategy almost isolates the design of sensors from resulting applications. Here, a machine learning (ML)-guided design of flexible tactile sensor system is reported, enabling a high classification accuracy (≈99.58%) of tactile perception in six dynamic touch modalities. Different from the intuition-driven sensor design, such ML-guided performance optimization is realized by introducing a support vector machine-based ML algorithm along with specific statistical criteria for fabrication parameters selection to excavate features deeply concealed in raw sensing data. This inverse design merges the statistical learning criteria into the design phase of sensing hardware, bridging the gap between the device structures and algorithms. Using the optimized tactile sensor, the high-quality recognizable signals in handwriting applications are obtained. Besides, with the additional data processing, a robot hand assembled with the sensor is able to complete real-time touch-decoding of an 11-digit braille phone number with high accuracy.

Fabrication of Laser-Induced Graphene Based Flexible Sensors Using 355 nm Ultraviolet Laser and Their Application in Human-Computer Interaction System

In recent years, flexible sensors based on laser-induced graphene (LIG) have played an important role in areas such as smart healthcare, smart skin, and wearable devices. This paper presents the fabrication of flexible sensors based on LIG technology and their applications in human-computer interaction (HCI) systems. Firstly, LIG with a sheet resistance as low as 4.5 Ω per square was generated through direct laser interaction with commercial polyimide (PI) film. The flexible sensors were then fabricated through a one-step method using the as-prepared LIG. The applications of the flexible sensors were demonstrated by an HCI system, which was fabricated through the integration of the flexible sensors and a flexible glove. The as-prepared HCI system could detect the bending motions of different fingers and translate them into the movements of the mouse on the computer screen. At the end of the paper, a demonstration of the HCI system is presented in which words were typed on a computer screen through the bending motion of the fingers. The newly designed LIG-based flexible HCI system can be used by persons with limited mobility to control a virtual keyboard or mouse pointer, thus enhancing their accessibility and independence in the digital realm.

Flexible tactile sensors with biomimetic microstructures: Mechanisms, fabrication, and applications

In recent years, flexible devices have gained rapid development with great potential in daily life. As the core component of wearable devices, flexible tactile sensors are prized for their excellent properties such as lightweight, stretchable and foldable. Consequently, numerous high-performance sensors have been developed, along with an array of innovative fabrication processes. It has been recognized that the improvement of the single performance index for flexible tactile sensors is not enough for practical sensing applications. Therefore, balancing and optimization of overall performance of the sensor are extensively anticipated. Furthermore, new functional characteristics are required for practical applications, such as freeze resistance, corrosion resistance, self-cleaning, and degradability. From a bionic perspective, the overall performance of a sensor can be optimized by constructing bionic microstructures which can deliver additional functional features. This review briefly summarizes the latest developments in bionic microstructures for different types of tactile sensors and critically analyzes the sensing performance of fabricated flexible tactile sensors. Based on this, the application prospects of bionic microstructure-based tactile sensors in human detection and human-machine interaction devices are introduced.