scholarly journals Investigating improvements to neural network based EMG to joint torque estimation

2011 ◽  
Vol 2 (4) ◽  
Author(s):  
Mervin Chandrapal ◽  
XiaoQi Chen ◽  
WenHui Wang ◽  
Benjamin Stanke ◽  
Nicolas Le Pape
Keyword(s):  
Estimation Error ◽  
Knee Extensor ◽  
Joint Torque ◽  
Training Algorithms ◽  
Flexor Muscle ◽  
Estimation Errors ◽  
Torque Estimation ◽  
Nonlinear Relation ◽  
Universal Approximators ◽  
And Training

AbstractAlthough surface electromyography (sEMG) has a high correlation to muscle force, an accurate model that can estimate joint torque from sEMG is still elusive. Artificial neural networks (NN), renowned as universal approximators, have been employed to capture this complex nonlinear relation. This work focuses on investigating possible improvements to the NN methodology and algorithm that would consistently produce reliable sEMG-to-knee-joint torque mapping for any individual. This includes improvements in number of inputs, data normalization techniques, NN architecture and training algorithms. Data (sEMG) from five knee extensor and flexor muscle from one subject were recorded on 10 random days over a period of 3 weeks whilst subject performed both isometric and isokinetic movements. The results indicate that incorporating more muscles into the NN and normalizing the data at each isometric angle prior to NN training improves torque estimation. The mean lowest estimation error achieved for isometric motion was 10.461% (1.792), whereas the lowest estimation errors for isokinetic motion were larger than 20%.

Isokinetic Strength After ACL Reconstruction: Influence of Concomitant Anterolateral Ligament Reconstruction

2021 ◽  
pp. 194173812110054
Author(s):  
Benoit Gillet ◽  
Yoann Blache ◽  
Isabelle Rogowski ◽  
Grégory Vigne ◽  
Bertrand Sonnery-Cottet ◽  
...  
Keyword(s):  
Muscle Strength ◽  
Ligament Reconstruction ◽  
Knee Extensor ◽  
Anterolateral Ligament ◽  
Flexor Muscle ◽  
Knee Flexor ◽  
Strength Recovery ◽  
Flexor Muscles ◽  
Knee Muscle ◽  
Knee Muscle Strength

Background: To reduce the rate of anterior cruciate ligament (ACL) graft rupture, recent surgeries have involved anterolateral ligament reconstruction (ALLR). This reconstruction procedure harvests more knee flexor muscle tendons than isolated ACL reconstruction (ACLR), but its influence on knee muscle strength recovery remains unknown. This study aimed to assess the influence of ALLR with a gracilis graft on the strength of the knee extensor and flexor muscles at 6 months postoperatively. Hypothesis: The additional amount of knee flexor harvest for ALLR would result in impairment in knee flexor muscle strength at 6 months postoperatively. Study Design: Retrospective cohort study. Level of Evidence: Level 2. Methods: A total of 186 patients were assigned to 2 groups according to the type of surgery: ACL + ALLR (graft: semitendinosus + gracilis, n = 119) or isolated ACLR (graft: semitendinosus, n = 67). The strength of the knee extensor and flexor muscles was assessed using an isokinetic dynamometer at 90, 180, and 240 deg/s for concentric and 30 deg/s for eccentric contractions and compared between groups using analysis of variance statistical parametric mapping. Results: Regardless of the surgery and the muscle, the injured leg produced significantly less strength than the uninjured leg throughout knee flexion and extension from 30° to 90° for each angular velocity (30, 90, 180, and 240 deg/s). However, the knee muscle strength was similar between the ACL + ALLR and ACLR groups. Conclusion: The addition of ALLR using the gracilis tendon during ACLR does not alter the muscle recovery observed at 6 months postoperatively. Clinical Relevance: Although more knee flexor muscle tendons were harvested in ACL + ALLR, the postoperative strength recovery was similar to that of isolated ACLR.

scholarly journals Regional robust secure precise wireless transmission design for multi-user UAV broadcasting system

2020 ◽  
Vol 2020 (1) ◽  
Author(s):  
Tong Shen ◽  
Tingting Liu ◽  
Yan Lin ◽  
Yongpeng Wu ◽  
Feng Shu ◽  
...  
Keyword(s):  
Estimation Error ◽  
Wireless Transmission ◽  
Artificial Noise ◽  
Target Area ◽  
Secrecy Rate ◽  
Estimation Errors ◽  
Transmission Design ◽  
Broadcasting System ◽  
Aerial Vehicle ◽  
Noise Ratio

Abstract In this paper, two regional robust secure precise wireless transmission (SPWT) schemes for multi-user unmanned aerial vehicle (UAV), (1)regional signal-to-leakage-and-noise ratio (SLNR) and artificial-noise-to-leakage-and-noise ratio (ANLNR) (R-SLNR-ANLNR) maximization and (2) point SLNR and ANLNR (P-SLNR-ANLNR) maximization, are proposed to tackle with the estimation errors of the target users’ location. In the SPWT system, the estimation error for SPWT cannot be ignored. However, the conventional robust methods in secure wireless communications optimize the beamforming vector in the desired positions only in statistical means and cannot guarantee the security for each symbol. The proposed regional robust schemes are designed for optimizing the secrecy performance in the whole error region around the estimated location. Specifically, with the known maximal estimation error, we define the target region and wiretap region. Then, we design an optimal beamforming vector and an artificial noise projection matrix, which achieve the confidential signal in the target area having the maximal power while only few signal power is conserved in the potential wiretap region. Instead of considering the statistical distributions of the estimated errors into optimization, we optimize the SLNR and ANLNR of the whole target area, which significantly decreases the complexity. Moreover, the proposed schemes can ensure that the desired users are located in the optimized region, which are more practical than the conventional methods. Simulation results show that our proposed regional robust SPWT design is capable of substantially improving the secrecy rate compared to the conventional non-robust method. The P-SLNR-ANLNR maximization-based method has the comparable secrecy performance with lower complexity than that of the R-SLNR-ANLNR maximization-based method.

scholarly journals Associations of the Stair Climb Power Test With Muscle Strength and Functional Performance in People With Chronic Obstructive Pulmonary Disease: A Cross-Sectional Study

2010 ◽  
Vol 90 (12) ◽  
pp. 1774-1782 ◽  
Author(s):  
Marc Roig ◽  
Janice J. Eng ◽  
Donna L. MacIntyre ◽  
Jeremy D. Road ◽  
W. Darlene Reid
Keyword(s):  
Chronic Obstructive Pulmonary Disease ◽  
Muscle Strength ◽  
Functional Performance ◽  
Knee Extensor ◽  
Chronic Obstructive ◽  
Flexor Muscle ◽  
Cross Sectional ◽  
Obstructive Pulmonary Disease ◽  
Power Test ◽  
Muscle Torque

Background The Stair Climb Power Test (SCPT) is a functional test associated with leg muscle power in older people. Objective The purposes of this study were to compare the results of the SCPT in people with chronic obstructive pulmonary disease (COPD) and people who were healthy and to explore associations of the SCPT with muscle strength (force-generating capacity) and functional performance. Design The study was a cross-sectional investigation. Methods Twenty-one people with COPD and a predicted mean (SD) percentage of forced expiratory volume in 1 second of 47.2 (12.9) and 21 people who were healthy and matched for age, sex, and body mass were tested with the SCPT. Knee extensor and flexor muscle torque was assessed with an isokinetic dynamometer. Functional performance was assessed with the Timed “Up & Go” Test (TUG) and the Six-Minute Walk Test (6MWT). Results People with COPD showed lower values on the SCPT (28%) and all torque measures (∼32%), except for eccentric knee flexor muscle torque. In people with COPD, performance on the TUG and 6MWT was lower by 23% and 28%, respectively. In people with COPD, the SCPT was moderately associated with knee extensor muscle isometric and eccentric torque (r≥.46) and strongly associated (r=.68) with the 6MWT. In people who were healthy, the association of the SCPT with knee extensor muscle torque tended to be stronger (r≥.66); however, no significant relationship between the SCPT and measures of functional performance was found. Limitations The observational design of the study and the use of a relatively small convenience sample limit the generalizability of the findings. Conclusions The SCPT is a simple and safe test associated with measures of functional performance in people with COPD. People with COPD show deficits on the SCPT. However, the SCPT is only moderately associated with muscle torque and thus cannot be used as a simple surrogate for muscle strength in people with COPD.

scholarly journals The Model and Training Algorithm of Compact Drone Autonomous Visual Navigation System

Data ◽  
2018 ◽  
Vol 4 (1) ◽  
pp. 4 ◽  
Author(s):  
Viacheslav Moskalenko ◽  
Alona Moskalenko ◽  
Artem Korobov ◽  
Viktor Semashko
Keyword(s):  
Autonomous Navigation ◽  
Search Algorithm ◽  
Visual Navigation ◽  
Frame Rate ◽  
Raspberry Pi ◽  
Navigation Systems ◽  
Training Algorithms ◽  
Translation Error ◽  
Deep Model ◽  
And Training

Trainable visual navigation systems based on deep learning demonstrate potential for robustness of onboard camera parameters and challenging environment. However, a deep model requires substantial computational resources and large labelled training sets for successful training. Implementation of the autonomous navigation and training-based fast adaptation to the new environment for a compact drone is a complicated task. The article describes an original model and training algorithms adapted to the limited volume of labelled training set and constrained computational resource. This model consists of a convolutional neural network for visual feature extraction, extreme-learning machine for estimating the position displacement and boosted information-extreme classifier for obstacle prediction. To perform unsupervised training of the convolution filters with a growing sparse-coding neural gas algorithm, supervised learning algorithms to construct the decision rules with simulated annealing search algorithm used for finetuning are proposed. The use of complex criterion for parameter optimization of the feature extractor model is considered. The resulting approach performs better trajectory reconstruction than the well-known ORB-SLAM. In particular, for sequence 7 from the KITTI dataset, the translation error is reduced by nearly 65.6% under the frame rate 10 frame per second. Besides, testing on the independent TUM sequence shot outdoors produces a translation error not exceeding 6% and a rotation error not exceeding 3.68 degrees per 100 m. Testing was carried out on the Raspberry Pi 3+ single-board computer.

scholarly journals Optical Recognition of Handwritten Logic Formulas Using Neural Networks

Electronics ◽  
2021 ◽  
Vol 10 (22) ◽  
pp. 2761
Author(s):  
Vaios Ampelakiotis ◽  
Isidoros Perikos ◽  
Ioannis Hatzilygeroudis ◽  
George Tsihrintzis
Keyword(s):  
Neural Networks ◽  
Character Recognition ◽  
Gradient Descent ◽  
Feedforward Neural Networks ◽  
Stochastic Gradient ◽  
Stochastic Gradient Descent ◽  
Training Algorithms ◽  
Gradient Descent Algorithm ◽  
Two Stages ◽  
And Training

In this paper, we present a handwritten character recognition (HCR) system that aims to recognize first-order logic handwritten formulas and create editable text files of the recognized formulas. Dense feedforward neural networks (NNs) are utilized, and their performance is examined under various training conditions and methods. More specifically, after three training algorithms (backpropagation, resilient propagation and stochastic gradient descent) had been tested, we created and trained an NN with the stochastic gradient descent algorithm, optimized by the Adam update rule, which was proved to be the best, using a trainset of 16,750 handwritten image samples of 28 × 28 each and a testset of 7947 samples. The final accuracy achieved is 90.13%. The general methodology followed consists of two stages: the image processing and the NN design and training. Finally, an application has been created that implements the methodology and automatically recognizes handwritten logic formulas. An interesting feature of the application is that it allows for creating new, user-oriented training sets and parameter settings, and thus new NN models.

scholarly journals Application of Attenuation Correction to Quantitative Precipitation Estimation on C-Band Weather Radar in Bengkulu

2021 ◽  
Vol 893 (1) ◽  
pp. 012054
Author(s):  
M F Handoyo ◽  
M P Hadi ◽  
S Suprayogi
Keyword(s):  
Attenuation Correction ◽  
Estimation Error ◽  
Weather Radar ◽  
Radar Data ◽  
Signal Interference ◽  
Active System ◽  
Estimation Errors ◽  
Rain Gauges ◽  
Quantitative Precipitation Estimation ◽  
Precipitation Estimation

Abstract A weather radar is an active system remote sensing tool that observes precipitation indirectly. Weather radar has an advantage in estimating precipitation because it has a high spatial resolution (up to 0.5 km). Reflectivity generated by weather radar still has signal interference caused by attenuation factors. Attenuation causes the Quantitative Precipitation Estimation (QPE) by the C-band weather radar to underestimate. Therefore attenuation correction on C-band weather radar is needed to eliminate precipitation estimation errors. This study aims to apply attenuation correction to determine Quantitative Precipitation Estimation (QPE) on the c-band weather radar in Bengkulu in December 2018. Gate-by-gate method attenuation correction with Kraemer approach has applied to c-band weather radar data from the Indonesian Agency for Meteorology and Geophysics (BMKG) weather radar network Bengkulu. This method uses reflectivity as the only input. Quantitative Precipitation Estimation (QPE) has obtained by comparing weather radar-based rain estimates to 10 observation rain gauges over a month with the Z-R relation equation. Root Mean Square Error (RMSE) is used to calculate the estimation error. Weather radar data are processed using Python-based libraries Wradlib and ArcGIS 10.5. As a result, the calculation between the weather radar estimate precipitation and the observed rainfall obtained equation Z=2,65R1,3. The attenuation correction process with Kreamer's approach on the c-band weather radar has reduced error in the Qualitative Precipitation Estimation (QPE). Corrected precipitation has a smaller error value (r = 0.88; RMSE = 8.38) than the uncorrected precipitation (r = 0.83; RMSE = 11.70).

scholarly journals The Quality of Accruals and Earnings: The Role of Accrual Estimation Errors

2002 ◽  
Vol 77 (s-1) ◽  
pp. 35-59 ◽  
Author(s):  
Patricia M. Dechow ◽  
Ilia D. Dichev
Keyword(s):  
Estimation Error ◽  
Cash Flows ◽  
Empirical Measure ◽  
Earnings Persistence ◽  
Working Capital ◽  
Estimation Errors ◽  
Accrual Quality ◽  
Flows Over Time

This paper suggests a new measure of one aspect of the quality of working capital accruals and earnings. One role of accruals is to shift or adjust the recognition of cash flows over time so that the adjusted numbers (earnings) better measure firm performance. However, accruals require assumptions and estimates of future cash flows. We argue that the quality of accruals and earnings is decreasing in the magnitude of estimation error in accruals. We derive an empirical measure of accrual quality as the residuals from firm-specific regressions of changes in working capital on past, present, and future operating cash flows. We document that observable firm characteristics can be used as instruments for accrual quality (e.g., volatility of accruals and volatility of earnings). Finally, we show that our measure of accrual quality is positively related to earnings persistence.

scholarly journals Minimax Robust Optimal Estimation Fusion for Distributed Multisensor Systems with a Relative Entropy Uncertainty

2014 ◽  
Vol 2014 ◽  
pp. 1-6
Author(s):  
Hua Li ◽  
Jie Zhou
Keyword(s):  
Robust Estimation ◽  
Relative Entropy ◽  
Estimation Error ◽  
Optimal Estimation ◽  
Minimum Variance ◽  
Estimation Errors ◽  
Multisensor Systems ◽  
Error Covariance ◽  
Local Estimation ◽  
Estimation Fusion

This paper considers the robust estimation fusion problem for distributed multisensor systems with uncertain correlations of local estimation errors. For an uncertain class characterized by the Kullback-Leibler (KL) divergence from the actual model to nominal model of local estimation error covariance, the robust estimation fusion problem is formulated to find a linear minimum variance unbiased estimator for the least favorable model. It is proved that the optimal fuser under nominal correlation model is robust while the estimation error has a relative entropy uncertainty.

Sign in / Sign up

Export Citation Format

Share Document