A Neural Network Embedded System for Real-time Estimation of Muscle Forces

Lozito, Gabriele Maria; Schmid, Maurizio; Conforto, Silvia; Fulginei, Francesco Riganti; Bibbo, Daniele

doi:10.1016/j.procs.2015.05.196

Cited by 10 publications

(7 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These forces must be estimated by indirect means since the direct measurement is usually neither possible nor practical. Therefore, many studies measure muscle strength through inverse kinematics [38,39], including the fingers [40], upper limbs [41], and lower limbs [42][43][44]. In experimental studies of human movement, muscle strength tests are useful in assessing the recovery of stroke patients [45].…”

Section: Muscle Analysismentioning

confidence: 99%

Analyzing Human Muscle State with Flexible Sensors

Chen

Wang²,

et al. 2022

Journal of Sensors

View full text Add to dashboard Cite

Analyzing human muscle states has attracted extensive attention. EMG (electromyography) pattern recognition methods based on these works have been proposed for many years. However, uncomfortable wearing and high prices make it inconvenient for motion tracking and muscle analysis by using robotic arms and inertial sensors in daily life. In this study, we propose to use smart clothes integrated with flexible sensors to collect arm motion data, estimate the kinematic information of continuous arm motion, and predict the EMG signal of each arm muscle. Firstly, the neural network regression model integrated with the LSTM (long short-term memory) module is used to continuously estimate the sensor resistances collected by the smart clothes and the angles collected by Kinect. Then, six types of shoulder and elbow movements’ angles and the corresponding EMG signals of 5 subjects are preprocessed and aligned. The stacked regression model based on extremely randomized trees (extra trees) is used for regression. Our experimental results show that the average estimation absolute error from the sensor resistances to the joint angle is 3.45 degrees, and the absolute percentage error from the joint angle to the EMG signal is only 1.82%.

show abstract

Section: Muscle Analysismentioning

confidence: 99%

Analyzing Human Muscle State with Flexible Sensors

Chen

Wang²,

et al. 2022

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…There are many examples in literature of neural network architectures in literature being embedded into a microcontroller including sensor non-linearity correction [18], real-time modelling of phenomena from sensor data [19] and optimisation applications. Advancing microcontroller capabilities have even enabled the use genetic algorithms to train neural network algorithms on embedded systems which opens a whole new spectrum of applications with great potential to benefit from multivariable and multi-objective intelligent control methods [20].…”

Section: Future Trendsmentioning

confidence: 99%

A Review of Machine Learning Algorithms for estimating Critical Quality Attributes from Multi-Sensor Data

Mahony¹,

Murphy²,

Panduru³

et al. 2016

IJSED

View full text Add to dashboard Cite

show abstract

“…Many parameters can be set (e.g., A-V delay interval following a sensed atrial depolarization, sensing and pacing thresholds) and can be read information about past events and therapies [19]. Some devices have availability to store intracardiac electrocardiograms of the onset and progress of the event, which is helpful for diagnosis and making programming changes [20,21]. Programmer also performs diagnostic testing of the implanted device (sensing of intrinsic cardiac activity, impedance of leads and threshold of generated pulses).…”

Section: Introductionmentioning

confidence: 99%

An Artificial Heart System for Testing and Evaluation of Cardiac Pacemakers

Augustýnek¹,

Kubicek²,

Thomas³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

The usability assessment of a pacemaker is a complex task where the dedicated programmer for testing programmed algorithms is necessary. This paper provides the outcomes of development and complex testing of the artificial cardiac system to evaluate the pacemaker's functionality. In this work, we used the modular laboratory platform ELVIS II and created graphical user interface in LabVIEW programming environment. The electrical model of the heart allows signals generation (right atrium, right ventricle) and the monitoring of the stimulation pulses. The LabVIEW user interface allows to set the parameters of the generated signals and the simulation of the cardiac rhythm disorders as well as the monitoring and visualization of the pacemaker behavior in real-time. The results demonstrate the capability of proposed system to evaluate the paced and sensed pulses. The proposed solution allows the scientists to test the behavior of any cardiac pacemaker for its pre-programmed settings and pacing mode. In addition, the proposed system can simulate various disorders and test cardiac pacemakers in different working modes.

show abstract

A Neural Network Embedded System for Real-time Estimation of Muscle Forces

Cited by 10 publications

References 31 publications

Analyzing Human Muscle State with Flexible Sensors

Analyzing Human Muscle State with Flexible Sensors

A Review of Machine Learning Algorithms for estimating Critical Quality Attributes from Multi-Sensor Data

An Artificial Heart System for Testing and Evaluation of Cardiac Pacemakers

Contact Info

Product

Resources

About