Array Of Force Sensing Resistors Research Articles

Performance Evaluation of Neonatal Anti-Pressure Ulcer Bed Using a Novel Force-Sensing Array

Abstract Pressure ulcer (PU) is a serious issue among newborns, particularly those who are premature and have medical conditions that require hospitalization. Existing conventional beds require modifications that can reduce the chance of PU and the extra effort of nursing staff. In this work, a force-sensing resistor array (FSRA) mattress is implemented that detects high-pressure points. The microcontroller processes the data that are collected from the FSRA using an electronic circuit based on the principle of voltage divider circuits. The multiplexer identifies the pixels of high-pressure points and plots the heat maps using matlab. The results of the FSRA mattress use an alternately inflating and deflating pressure channel bed to act as an anti-PU bed and compare it with the currently deployed bed. The demonstrated work was validated using the finite element modeling framework. This anti-PU bed is effective in detecting high-pressure points; based on that, chances of PUs in neonates can be prevented. The performance evaluation of the designed and tested anti-PU bed with more accuracy and automatically varies the contact position to reduce the efforts made by the nursing staff. This innovation significantly improves the quality of life as compared to the conventional methods to avoid PUs for neonatal intensive care units (NICUs).

An Application of Deep Learning to Tactile Data for Object Recognition under Visual Guidance.

Drawing inspiration from haptic exploration of objects by humans, the current work proposes a novel framework for robotic tactile object recognition, where visual information in the form of a set of visually interesting points is employed to guide the process of tactile data acquisition. Neuroscience research confirms the integration of cutaneous data as a response to surface changes sensed by humans with data from joints, muscles, and bones (kinesthetic cues) for object recognition. On the other hand, psychological studies demonstrate that humans tend to follow object contours to perceive their global shape, which leads to object recognition. In compliance with these findings, a series of contours are determined around a set of 24 virtual objects from which bimodal tactile data (kinesthetic and cutaneous) are obtained sequentially and by adaptively changing the size of the sensor surface according to the object geometry for each object. A virtual Force Sensing Resistor array (FSR) is employed to capture cutaneous cues. Two different methods for sequential data classification are then implemented using Convolutional Neural Networks (CNN) and conventional classifiers, including support vector machines and k-nearest neighbors. In the case of conventional classifiers, we exploit contourlet transformation to extract features from tactile images. In the case of CNN, two networks are trained for cutaneous and kinesthetic data and a novel hybrid decision-making strategy is proposed for object recognition. The proposed framework is tested both for contours determined blindly (randomly determined contours of objects) and contours determined using a model of visual attention. Trained classifiers are tested on 4560 new sequential tactile data and the CNN trained over tactile data from object contours selected by the model of visual attention yields an accuracy of 98.97% which is the highest accuracy among other implemented approaches.

Multimodality Evaluation of Pressure Relief Surfaces

Multimodality evaluation of six different support surfaces was performed measuring interface pressure, transcutaneous oxygen tension, and blood flow in pressure ulcer-prone areas on healthy subjects. Interface pressure was measured with a flexible force-sensing resistor array. The interface pressure distribution patterns of 10 healthy male volunteers were measured in the supine and lateral positions using a pressure sensor (force sensing resistor) array. Transcutaneous oxygen (TcPO2) and laser Doppler flowmeter probes were placed over the sacrum, the right trochanter, and the right ischium. Data were recorded for 15 minutes each with the subject in the supine and lateral decubitus positions. Statistically significant differences (p < 0.05) between the various surfaces could be observed for blood flow and pressure measurements, especially in the lateral position over the trochanter and for the TcPO2 measurements in the supine position over the sacrum. We conclude that measuring interface pressure, transcutaneous oxygen tension, and blood flow allows a more thorough evaluation of the physiologic effects of special support surfaces than any single technique. Future studies on patients will assess algorithms for using these measurement techniques to predict the efficacy of various support surfaces in minimizing pressure ulceration.

Application of adaptive neural network to localization of objects using pressure array transducer

SUMMARYPattern recognition and object localization, using various sensors such as vision and tactile sensors, are two important areas of research in the application of robotic systems. This paper demonstrates the feasibility of using some relatively inexpensive array of pressure sensors and a neural network approach to achieve object localization and pattern recognition. The sensors that are used are force sensing resistors (FSRs), more specifically, a 16 x 16 array of FSRs. Because of the nonlinearity associated with a FSR, three possible approaches for gathering output from the sensor array are used. The neural network that is used consists of two 2-layer counterpropagation networks (CPNs). One of the CPNs is trained to recognize contact signatures of different objects placed on a fixed reference position on the sensor array.