In this paper, we integrate some ideas of sparse autoencoder of deep learning into compressed sensing (CS) theory, and set up a sparse autoencoder compressed sensing (SAECS) model, which can improve the compressed sam...
详细信息
Interpolation is a common data processing step in the study of interface pressure data collected at the wheelchair seating interface. However, there has been no focused study on the effect of interpolation on features...
详细信息
Interpolation is a common data processing step in the study of interface pressure data collected at the wheelchair seating interface. However, there has been no focused study on the effect of interpolation on features extracted from these pressure maps, nor on whether these parameters are sensitive to the manner in which the interpolation is implemented. Here, two different interpolation paradigms, bilinear versus bicubic spline, are tested for their influence on parameters extracted from pressure array data and compared against a conventional low-pass filtering operation. Additionally, analysis of the effect of tandem filtering and interpolation, as well as the interpolation degree (interpolating to 2, 4, and 8 times sampling density), was undertaken. The following recommendations are made regarding approaches that minimized distortion of features extracted from the pressure maps: (1) filter prior to interpolate (strong effect);(2) use cubic interpolation versus linear (slight effect);and (3) ensure nominal difference between interpolation orders of 2, 4, and 8 times (negligible effect). We invite other investigators to perform similar benchmark analyses on their own data in the interest of establishing a community consensus of best practices in pressure array data processing.
In this article, sparse autoencoder in deep learning is integrated into the compressed sensing (CS) theory, and a reconstruction algorithm is designed based on the biological mechanism of human brain synaptic connecti...
详细信息
In this article, sparse autoencoder in deep learning is integrated into the compressed sensing (CS) theory, and a reconstruction algorithm is designed based on the biological mechanism of human brain synaptic connections. The compressive sampling process is modeled as a neural network model. Then a biological mechanism-inspired stacked long short-term memory (LSTM) network model is proposed as a reconstruction algorithm of CS theory. Consequently, a CS network (ComsensNet) model is introduced, by integrating the compressive sampling process and reconstruction algorithm. ComsensNet can provide a bridge between sparse autoencoder in deep learning, synapses in human brain neurons and the CS theory. A deep neural network is designed based on the synaptic biological mechanism of human brain neurons, and then combine with the theory of CS. The effectiveness of ComsensNet is investigated by using acquired pressure data from the human body model. The experimental results demonstrate that the biological mechanism-inspired stacked LSTM network in ComsensNet can improve the reconstruction accuracy compared to other reconstruction algorithms.
For pressure sensors, high sensitivity and broad effective sensing range are often incompatible. To balance the relationship between them, herein, a flexible pressure sensor employing 3-D porousMXene/reducedgraphene o...
详细信息
For pressure sensors, high sensitivity and broad effective sensing range are often incompatible. To balance the relationship between them, herein, a flexible pressure sensor employing 3-D porousMXene/reducedgraphene oxide (MXene/rGO) hybrid foam as piezoresistive sensing material is developed by an efficient hydrothermal synthesis and a novel reduction method of flash instantaneous irradiation. Compared with conventional reduction methods, this instantaneous reduction process can effectively maintain MXene nanoflakes in tightly interconnected rGO sheets, resulting in robustmechanical elasticity and high conductivity of the proposed MXene/rGO hybrid foam. On account of the 3-D porous skeleton structure of MXene/rGO hybrid foam, the proposed pressure sensor presents a high sensitivity up to 3.75 kPa(-1), a broad sensing range from0 to 28 kPa, an ultralow detectable limit down to 1.5 Pa, rapid dynamic response/recovery times with 20/40 ms, a low hysteresis of 2.95%, as well as a strong stability for over 2000 Hz. Notably, the flexible pressure sensor possesses the superior function of precisely detecting some subtle human activities (pulse, vocalization, breathing, etc.) and large joints (knee, finger, elbow, wrist, etc.) movements in real time. Besides, a matrix pressure array of 4 x 4 pixels has been exploited for multipoint recognition.
A smart fabric based multichannel pressure mapping Data Acquisition System (DAS) was specially designed to read and visualize real time pressure data from an array of piezoresistive fabric pressure sensor. This DAS is...
详细信息
ISBN:
(纸本)9789811075544;9789811075537
A smart fabric based multichannel pressure mapping Data Acquisition System (DAS) was specially designed to read and visualize real time pressure data from an array of piezoresistive fabric pressure sensor. This DAS is important to enable rapid monitoring of pressure distribution for biomedical engineering applications. A customized pressure mapping circuit using off-the-shelf components has been designed and fabricated. In addition, a pressure mapping algorithm which runs on Arduino platform and MATLAB was developed to continuously read and visualize pressure profile from the fabric pressure sensor. To ensure low component count and simple hardware, the concept of multiplexing has been employed in the hardware architecture and the firmware was written to support this architecture. This approach allows the system to perform even with single processor and single ADC. The reliability of the system was tested with array of fabric pressure sensor using a special portable load cell (Advance Force Gauge by MECMESIN). pressure profile for each sensor unit matches the sensor resistive load characteristic, repeatability and accuracy of a commercial data acquisition system. The system is suitable for reading slow changing analog signal. If one desired to measure fast changing signal, the same architecture can still be used but specifications of the components must be higher. In conclusion, a smart multichannel pressure mapping Data Acquisition System (DAS) was designed, fabricated and tested. The unit capable of acquiring and visualizing pressure data from the developed sensor array. The speed of the system can be increased by using higher speed components while maintaining the same architecture.
暂无评论