Sitting posture recognition using screen printed large area pressure sensors

Author(s):  
Jawad Ahmad ◽  
Henrik Andersson ◽  
Johan Siden
2021 ◽  
Vol 11 (11) ◽  
pp. 4752
Author(s):  
Gian Domenico Licciardo ◽  
Alessandro Russo ◽  
Alessandro Naddeo ◽  
Nicola Cappetti ◽  
Luigi Di Benedetto ◽  
...  

A custom HW design of a Fully Convolutional Neural Network (FCN) is presented in this paper to implement an embeddable Human Posture Recognition (HPR) system capable of very high accuracy both for laying and sitting posture recognition. The FCN exploits a new base-2 quantization scheme for weight and binarized activations to meet the optimal trade-off between low power dissipation, a very reduced set of instantiated physical resources and state-of-the-art accuracy to classify human postures. By using a limited number of pressure sensors only, the optimized HW implementation allows keeping the computation close to the data sources according to the edge computing paradigm and enables the design of embedded HP systems. The FCN can be simply reconfigured to be used for laying and sitting posture recognition. Tested on a public dataset for in-bed posture classification, the proposed FCN obtains a mean accuracy value of 96.77% to recognize 17 different postures, while a small custom dataset has been used for training and testing for sitting posture recognition, where the FCN achieves 98.88% accuracy to recognize eight positions. The FCN has been prototyped on a Xilinx Artix 7 FPGA where it exhibits a dynamic power dissipation lower than 11 mW and 7 mW for laying and sitting posture recognition, respectively, and a maximum operation frequency of 47.64 MHz and 26.6 MHz, corresponding to an Output Data Rate (ODR) of the sensors of 16.50 kHz and 9.13 kHz, respectively. Furthermore, synthesis results with a CMOS 130 nm technology have been reported, to give an estimation about the possibility of an in-sensor circuital implementation.


2016 ◽  
Vol 65 (9) ◽  
pp. 1557-1563 ◽  
Author(s):  
Sangyong Ma ◽  
Sangpyo Hong ◽  
Hyeon-min Shim ◽  
Jang-Woo Kwon ◽  
Sangmin Lee

Author(s):  
Max Hendrichs ◽  
Milan Padilla ◽  
Johann Walter ◽  
Florian Clement ◽  
Bernd Rech

1999 ◽  
Author(s):  
Hong Z. Tan

Abstract This paper is concerned with how objects in an environment can be made aware of people via haptic sensing. It was motivated by the desire to make our environment “smarter” by providing it with sensory systems similar to our own. The work reported here focuses on an object that is involved in virtually all human-computer interactions, yet has remained sensory-deprived — the chair. A real-time sitting posture classification system has been developed using surface-mounted pressure sensors placed on the seatpan and backrest of a chair. The ultimate goal of this work is to build a robust multi-user sitting-posture tracking system that will have many applications including ergonomics and automatic control of airbag deployment in a car. Challenges for reaching the goal and plans of nature work are discussed.


Author(s):  
Jiang Zhao ◽  
Jiahao Gui ◽  
Jinsong Luo ◽  
Jing Gao ◽  
Caidong Zheng ◽  
...  

Abstract Graphene-based pressure sensors have received extensive attention in wearable devices. However, reliable, low-cost, and large-scale preparation of structurally stable graphene electrodes for flexible pressure sensors is still a challenge. Herein, for the first time, laser-induced graphene (LIG) powder are prepared into screen printing ink, and shape-controllable LIG patterned electrodes can be obtained on various substrates using a facile screen printing process, and a novel asymmetric pressure sensor composed of the resulting screen-printed LIG electrodes has been developed. Benefit from the 3D porous structure of LIG, the as-prepared flexible LIG screen-printed asymmetric pressure sensor has super sensing properties with a high sensitivity of 1.86 kPa−1, low detection limit of about 3.4 Pa, short response time, and long cycle durability. Such excellent sensing performances give our flexible asymmetric LIG screen-printed pressure sensor the ability to realize real-time detection of tiny body physiological movements (such as wrist pulse and pronunciation action). Besides, the integrated sensor array has a multi-touch function. This work could stimulate an appropriate approach to designing shape-controllable LIG screen-printed patterned electrodes on various flexible substrates to adapt the specific needs of fulfilling compatibility and modular integration for potential application prospects in wearable electronics.


Author(s):  
Yusuke Manabe ◽  
Kenji Sugawara

Realization of human-computer symbiosis is an important idea in the context of ubiquitous computing. Symbiotic Computing is a concept that bridges the gap between situations in Real Space (RS) and data in Digital Space (DS). The main purpose is to develop an intelligent software application as well as establish the next generation information platform to develop the symbiotic system. In this paper, the authors argue that it is necessary to build ’Mutual Cognition’ between human and system. Mutual cognition consists of two functions: ’RS Cognition’ and ’DS Cognition’. This paper examines RS Cognition, which consists of many software functions for perceiving various situations like events or humans’ activities in RS. The authors develop two perceptual functions, sitting posture recognition and human’s location estimation for a person, as RS perception tasks. In the resulting experiments, developed functions are quite competent to recognize a human’s activities.


Author(s):  
Yusuke Manabe ◽  
Kenji Sugawara

Realization of human-computer symbiosis is an important idea in the context of ubiquitous computing. Symbiotic Computing is a concept that bridges the gap between situations in Real Space (RS) and data in Digital Space (DS). The main purpose is to develop an intelligent software application as well as establish the next generation information platform to develop the symbiotic system. In this paper, the authors argue that it is necessary to build ’Mutual Cognition’ between human and system. Mutual cognition consists of two functions: ’RS Cognition’ and ’DS Cognition’. This paper examines RS Cognition, which consists of many software functions for perceiving various situations like events or humans’ activities in RS. The authors develop two perceptual functions, sitting posture recognition and human’s location estimation for a person, as RS perception tasks. In the resulting experiments, developed functions are quite competent to recognize a human’s activities.


Author(s):  
Naomi Nandakumar ◽  
John Rodriguez ◽  
Thomas Kluge ◽  
Thomas Groβe ◽  
Lauretta Fondop ◽  
...  
Keyword(s):  

Sign in / Sign up

Export Citation Format

Share Document