Machine learning-coupled tactile recognition with high spatiotemporal resolution based on cross-striped nanocarbon piezoresistive sensor array.

Flexible pressure sensor arrays have been playing important roles in various applications of human-machine interface, including robotic tactile sensing, electronic skin, prosthetics, and human-machine interaction. However, it remains challenging to simultaneously achieve high spatial and temporal resolution in developing pressure sensor arrays for tactile sensing with robust function to achieve precise signal recognition. This work presents the development of a flexible high spatiotemporal piezoresistive sensor array (PRSA) by coupling with machine learning algorithms to enhance tactile recognition. The sensor employs cross-striped nanocarbon-polymer composite as an active layer, though screen printing manufacture processes. A miniaturized signal readout circuit and transmission board is developed to achieve high-speed acquisition of distributed pressure signals from the PRSA. Test results indicate that the developed PRSA platform simultaneously possesses the characteristics of high spatial resolution up to 1.5 mm, fast temporal resolution of about 5 ms, and long-term durability with a variation of less than 2%. The PRSA platform also exhibits excellent performance in real-time visualization of multi-point touch, mapping embossed shapes, and tracking motion trajectory. To test the performance of PRSA in recognizing different shapes, we acquired pressure images by pressing the finger-type device coated with PRSA film on different embossed shapes and implementing the T-distributed Stochastic Neighbor Embedding model to visualize the distinction between images of different shapes. Then we adopted a one-layer neural network to quantify the discernibility between images of different shapes. The analysis results show that the PRSA could capture the embossed shapes clearly by one contact with high discernibility up to 98.9%. Collectively, the PRSA as a promising platform demonstrates its promising potential for robotic tactile sensing.

A biosensing system employing nonlinear dynamic analysis-assisted neural network for drug-induced cardiotoxicity assessment.

Preclinical investigation of drug-induced cardiotoxicity is of importance for drug development. To evaluate such cardiotoxicity, in vitro high-throughput interdigitated electrode-based recording of cardiomyocytes mechanical beating is widely used. To automatically analyze the features from the beating signals for drug-induced cardiotoxicity assessment, artificial neural network analysis is conventionally employed and signals are segmented into cycles and feature points are located in the cycles. However, signal segmentation and location of feature points for different signal shapes require design of specific algorithms. Consequently, this may lower the efficiency of research and the applications of such algorithms in signals with different morphologies are limited. Here, we present a biosensing system that employs nonlinear dynamic analysis-assisted neural network (NDANN) to avoid the signal segmentation process and directly extract features from beating signal time series. By processing beating time series with fixed time duration to avoid the signal segmentation process, this NDANN-based biosensing system can identify drug-induced cardiotoxicity with accuracy over 0.99. The individual drugs were classified with high accuracies over 0.94 and drug-induced cardiotoxicity levels were accurately predicted. We also evaluated the generalization performance of the NDANN-based biosensing system in assessing drug-induced cardiotoxicity through an independent dataset. This system achieved accuracy of 0.85-0.95 for different drug concentrations in identification of drug-induced cardiotoxicity. This result demonstrates that our NDANN-based biosensing system has the capacity of screening newly developed drugs, which is crucial in practical applications. This NDANN-based biosensing system can work as a new screening platform for drug-induced cardiotoxicity and improve the efficiency of bio-signal processing.

Multi-labeled neural network model for automatically processing cardiomyocyte mechanical beating signals in drug assessment.

High-throughput cardiotoxicity assessment is important for large-scale preclinical screening in novel drug development. To improve the efficiency of drug development and avoid drug-induced cardiotoxicity, there is a huge demand to explore the automatic and intelligent drug assessment platforms for preclinical cardiotoxicity investigations. In this work, we proposed an automatic and intelligent strategy that combined automatic feature extraction and multi-labeled neural network (MLNN) to process cardiomyocytes mechanical beating signals detected by an interdigital electrode biosensor for the assessment of drug-induced cardiotoxicity. Taking advantages of artificial neural network, our work not only classified different drugs inducing different cardiotoxicities but also predicted drug concentrations representing severity of cardiotoxicity. This has not been achieved by conventional strategies like principal component analysis and visualized heatmap. MLNN analysis showed high accuracy (up to 96%) and large AUC (more than 98%) for classification of different drug-induced cardiotoxicities. There was a high correlation (over 0.90) between concentrations reported by MLNN and experimentally treated concentrations of various drugs, demonstrating great capacity of our intelligent strategy to predict the severity of drug-induced cardiotoxicity. This new intelligent bio-signal processing algorithm is a promising method for identification and classification of drug-induced cardiotoxicity in cardiological and pharmaceutical applications.

Bio-Inspired Haptic Feedback for Artificial Palpation in Robotic Surgery.

Adding haptic feedback has been reported to improve the outcome of minimally invasive robotic surgery. In this study, we seek to determine whether an algorithm based on simulating responses of a cutaneous afferent population can be implemented to improve the performance of presenting haptic feedback for robot-assisted surgery. We propose a bio-inspired controlling model to present vibration and force feedback to help surgeons localize underlying structures in phantom tissue. A single pair of actuators was controlled by outputs of a model of a population of cutaneous afferents based on the pressure signal from a single sensor embedded in surgical forceps. We recruited 25 subjects including 10 expert surgeons to evaluate the performance of the bio-inspired controlling model in an artificial palpation task using the da Vinci surgical robot. Among the control methods tested, the bio-inspired system was unique in allowing both novices and experts to easily identify the locations of all classes of tumors and did so with reduced contact force and tumor contact time. This work demonstrates the utility of our bio-inspired multi-modal feedback system, which resulted in superior performance for both novice and professional users, in comparison to a traditional linear and the existing piecewise discrete algorithms of haptic feedback.

A Simplified Model for Simulating Population Responses of Tactile Afferents and Receptors in the Skin.

Tactile information about an object can only be extracted from population responses of tactile receptors and their afferents. Thus, to best control tactile information in robots, neuroprostheses or haptic devices, inputs should represent responses from full populations of afferents. Here, we describe a simplified model that recreates afferent population responses of thousands of tactile afferents in a personal computer. The whole model includes a resistance network model to simplify the skin mechanics and an improved version of a single unit model that we have previously described. The whole model was implemented by short and efficient python code. The parameters of the model were fit based on a simple vibrating stimulus, but the simulated outputs generalize to match receptive field sizes, edge enhancement, and neurophysiological responses to dot textures, embossed letters and curved surfaces. We discuss how to use this work to model haptic perception and provide guidance in designing and controlling highly realistic tactile interfaces in robots, neural prostheses and haptic devices.

A Python Code for Simulating Single Tactile Receptors and the Spiking Responses of Their Afferents.

This work presents a pieces of Python code to rapidly simulate the spiking responses of large numbers of single cutaneous tactile afferents with millisecond precision. To simulate the spike responses of all the major types of cutaneous tactile afferents, we proposed an electromechanical circuit model, in which a two-channel filter was developed to characterize the mechanical selectivity of tactile receptors, and a spike synthesizer was designed to recreate the action potentials evoked in afferents. The parameters of this model were fitted using previous neurophysiological datasets. Several simulation examples were presented in this paper to reproduce action potentials, sensory adaptation, frequency characteristics and spiking timing for each afferent type. The results indicated that the simulated responses matched previous neurophysiological recordings well. The model allows for a real-time reproduction of the spiking responses of about 4,000 tactile units with a timing precision of <6 ms. The current work provides a valuable guidance to designing highly realistic tactile interfaces such as neuroprosthesis and haptic devices.