A Resource Constrained Neural Network for the Design of Embedded Human Posture Recognition Systems

Licciardo, Gian Domenico; Russo, Alessandro; Naddeo, Alessandro; Cappetti, Nicola; Benedetto, Luigi Di; Rubino, Alfredo; Liguori, Rosalba

doi:10.3390/app11114752

Cited by 10 publications

(9 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, as mentioned before, this study began by classifying seven classes of postures but finally combined the two most difficult postures to distinguish into a single class. We observed this same disadvantage in studies performed by Wang et al [40] and Licciardo et al [39], where the number of sensors used were 56 and 181 respectively and large Deep Learning models were used as classifier. The number of sensors is substantially reduced, as can be seen in [37].…”

Section: Classification Resultssupporting

confidence: 52%

“…This work was conducted with 62 participants and it achieved a classification accuracy of 90%. The study described in [39] presented a Deep Learning Fully Convolutional Network to classify eight sitting postures using the samples sensed by a medilogic ® Seat Pressure Measurement System. This system consisted of 480 piezoresistive sensors, but a subsampling was applied in order to reduce the number of sensing elements to 56.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

IoT Device for Sitting Posture Classification Using Artificial Neural Networks

et al. 2021

View full text Add to dashboard Cite

Nowadays, the percentage of time that the population spends sitting has increased substantially due to the use of computers as the main tool for work or leisure and the increase in jobs with a high office workload. As a consequence, it is common to suffer musculoskeletal pain, mainly in the back, which can lead to both temporary and chronic damage. This pain is related to holding a posture during a prolonged period of sitting, usually in front of a computer. This work presents a IoT posture monitoring system while sitting. The system consists of a device equipped with Force Sensitive Resistors (FSR) that, placed on a chair seat, detects the points where the user exerts pressure when sitting. The system is complemented with a Machine Learning model based on Artificial Neural Networks, which was trained to recognize the neutral correct posture as well as the six most frequent postures that involve risk of damage to the locomotor system. In this study, data was collected from 12 participants for each of the seven positions considered, using the developed sensing device. Several neural network models were trained and evaluated in order to improve the classification effectiveness. Hold-Out technique was used to guide the training and evaluation process. The results achieved a mean accuracy of 81% by means of a model consisting of two hidden layers of 128 neurons each. These results demonstrate that is feasible to distinguish different sitting postures using few sensors allocated in the surface of a seat, which implies lower costs and less complexity of the system.

show abstract

Section: Classification Resultssupporting

confidence: 52%

Section: Related Workmentioning

confidence: 99%

IoT Device for Sitting Posture Classification Using Artificial Neural Networks

et al. 2021

View full text Add to dashboard Cite

show abstract

“…All datasets consisted of data collected from at least 8 participants [11,12]. Except for [13] and this work, reviewed approaches do not contemplate resource-constrained devices, but rather the deployment of CNN models in high-performance processors [6,11,12]. Authors in [13] proposed a custom hardware design of a CNN to classify sitting and laying posture, deployed on an FPGA (field programmable gate array) this clearly outperforms the software solutions [6,11,12].…”

Section: Introductionmentioning

confidence: 99%

“…Except for [13] and this work, reviewed approaches do not contemplate resource-constrained devices, but rather the deployment of CNN models in high-performance processors [6,11,12]. Authors in [13] proposed a custom hardware design of a CNN to classify sitting and laying posture, deployed on an FPGA (field programmable gate array) this clearly outperforms the software solutions [6,11,12]. In contrast, this work considers the deployment of an artificial neural network (ANN) and a CNN posture classifier model for laparoscopic surgical skills training.…”

Section: Introductionmentioning

confidence: 99%

Novel Low Memory Footprint DNN Models for Edge Classification of Surgeons’ Postures

Hanneman

Fawden

Branciforte

et al. 2023

IEEE Embedded Syst. Lett.

View full text Add to dashboard Cite

Skill assessment is fundamental to enhance current laparoscopic surgical training and reduce the incidence of musculoskeletal injuries from performing these procedures. Recently, deep neural networks (DNNs) have been used to improve human posture and surgeons' skills training. While they work well in lab, they normally require significant computational power which makes it impossible to use them on edge devices. This paper presents two low memory footprint DNN models used for classifying laparoscopic surgical skill levels at the edge. Trained models were deployed on three Arm Cortex-M processors using the X-Cube-AI and TensorFlow Lite Micro (TFLM) libraries. Results show that the CUBE-AI-based models give the best relative performance, memory footprint, and accuracy trade-offs when executed on the Cortex-M7.

show abstract

“…The system can achieve high recognition accuracy of lying and sitting postures. By using a limited number of pressure sensors, the optimized hardware implementation allows to stay close to the data source based on edge computing and supports the design of embedded HGR systems [6]. Nadeem et al pointed out a new method for automatic human pose estimation.…”

Section: Introductionmentioning

confidence: 99%

The Image Processing Using Soft Robot Technology in Fitness Motion Detection Under the Internet of Things

Ye¹,

Zheng

2022

IEEE Access

View full text Add to dashboard Cite

In order to study the application of robotic technology in fitness motion detection, this study develops a modular high accuracy and low-latency Human Gesture Recognition (HGR) system. Firstly, an improved HGR algorithm is introduced, which compresses the HGR model through content extraction and reduces the number of parameters. Methods such as Simulated Annealing and Semi-Supervised Learning are introduced to improve content extraction, further improving the compression of the model. Secondly, a human pose recognition system is constructed based on Deep Learning (DL) and robotics, and each module is recommended. Finally, the effectiveness of the system is verified. The results show that when the accuracy is close to HRNet-32. The inference speed of the model is increased by about 2.4 times, and the model parameters are compressed by about 67%. The data demonstrate the effectiveness of the method. The robothuman posture detection technology can effectively solve human posture recognition in fitness exercises.

show abstract

A Resource Constrained Neural Network for the Design of Embedded Human Posture Recognition Systems

Cited by 10 publications

References 31 publications

IoT Device for Sitting Posture Classification Using Artificial Neural Networks

IoT Device for Sitting Posture Classification Using Artificial Neural Networks

Novel Low Memory Footprint DNN Models for Edge Classification of Surgeons’ Postures

The Image Processing Using Soft Robot Technology in Fitness Motion Detection Under the Internet of Things

Contact Info

Product

Resources

About