scholarly journals Towards Detecting Biceps Muscle Fatigue in Gym Activity Using Wearables

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 759
Author(s):  
Mohamed Elshafei ◽  
Emad Shihab
Keyword(s):  
Muscle Fatigue ◽  
Random Forests ◽  
Linear Models ◽  
Wearable Sensors ◽  
Feedforward Neural Networks ◽  
Biceps Muscle ◽  
Real World Application ◽  
Naturally Occurring ◽  
Subject Specific ◽  
Machine Learning Models

Fatigue is a naturally occurring phenomenon during human activities, but it poses a bigger risk for injuries during physically demanding activities, such as gym activities and athletics. Several studies show that bicep muscle fatigue can lead to various injuries that may require up to 22 weeks of treatment. In this work, we adopt a wearable approach to detect biceps muscle fatigue during a bicep concentration curl exercise as an example of a gym activity. Our dataset consists of 3000 bicep curls from twenty middle-aged volunteers at ages between 27 to 30 and Body Mass Index (BMI) ranging between 18 to 28. All volunteers have been gym-goers for at least 1 year with no records of chronic diseases, muscle, or bone surgeries. We encountered two main challenges while collecting our dataset. The first challenge was the dumbbell’s suitability, where we found that a dumbbell weight (4.5 kg) provides the best tradeoff between longer recording sessions and the occurrence of fatigue on exercises. The second challenge is the subjectivity of RPE, where we average the reported RPE with the measured heart rate converted to RPE. We observed from our data that fatigue reduces the biceps’ angular velocity; therefore, it increases the completion time for later sets. We extracted a total of 33 features from our dataset, which have been reduced to 16 features. These features are the most overall representative and correlated with bicep curl movement, yet they are fatigue-specific features. We utilized these features in five machine learning models, which are Generalized Linear Models (GLM), Logistic Regression (LR), Random Forests (RF), Decision Trees (DT), and Feedforward Neural Networks (FNN). We found that using a two-layer FNN achieves an accuracy of 98% and 88% for subject-specific and cross-subject models, respectively. The results presented in this work are useful and represent a solid start for moving into a real-world application for detecting the fatigue level in bicep muscles using wearable sensors as we advise athletes to take fatigue into consideration to avoid fatigue-induced injuries.

scholarly journals A Subject-Specific Approach to Detect Fatigue-Related Changes in Spine Motion Using Wearable Sensors

Sensors ◽  
2020 ◽  
Vol 20 (9) ◽  
pp. 2646 ◽  
Author(s):  
Victor C.H. Chan ◽  
Shawn M. Beaudette ◽  
Kenneth B. Smale ◽  
Kristen H.E. Beange ◽  
Ryan B. Graham
Keyword(s):  
Muscle Fatigue ◽  
Wearable Sensors ◽  
Composite Index ◽  
Spine Kinematics ◽  
Flexion Extension ◽  
Main Effect ◽  
Subject Specific ◽  
Spine Motion ◽  
Measurement Units ◽  
The Individual

An objective method to detect muscle fatigue-related kinematic changes may reduce workplace injuries. However, heterogeneous responses to muscle fatigue suggest that subject-specific analyses are necessary. The objectives of this study were to: (1) determine if wearable inertial measurement units (IMUs) could be used in conjunction with a spine motion composite index (SMCI) to quantify subject-specific changes in spine kinematics during a repetitive spine flexion-extension (FE) task; and (2) determine if the SMCI was correlated with measures of global trunk muscle fatigue. Spine kinematics were measured using wearable IMUs in 10 healthy adults during a baseline set followed by 10 sets of 50 spine FE repetitions. After each set, two fatigue measures were collected: perceived level of fatigue using a visual analogue scale (VAS), and maximal lift strength. SMCIs incorporating 10 kinematic variables from 2 IMUs (pelvis and T8 vertebrae) were calculated and used to quantify subject-specific changes in movement. A main effect of set was observed (F (1.7, 15.32) = 10.42, p = 0.002), where the SMCI became significantly greater than set 1 starting at set 4. Significant correlations were observed between the SMCI and both fatigue VAS and maximal lift strength at the individual and study level. These findings support the use of wearable IMUs to detect subject-specific changes in spine motion associated with muscle fatigue.

Evidence of Inflated Prediction Performance: A Commentary on Machine Learning and Suicide Research

2021 ◽  
Vol 9 (1) ◽  
pp. 129-134 ◽  
Author(s):  
Ross Jacobucci ◽  
Andrew K. Littlefield ◽  
Alexander J. Millner ◽  
Evan M. Kleiman ◽  
Douglas Steinley
Keyword(s):  
Machine Learning ◽  
Random Forests ◽  
Linear Models ◽  
Prediction Performance ◽  
Machine Learning Algorithms ◽  
Learning Approaches ◽  
Learning Models ◽  
Internal Validation ◽  
Flexible Machine ◽  
Machine Learning Models

The use of machine learning is increasing in clinical psychology, yet it is unclear whether these approaches enhance the prediction of clinical outcomes. Several studies show that machine-learning algorithms outperform traditional linear models. However, many studies that have found such an advantage use the same algorithm, random forests with the optimism-corrected bootstrap, for internal validation. Through both a simulation and empirical example, we demonstrate that the pairing of nonlinear, flexible machine-learning approaches, such as random forests with the optimism-corrected bootstrap, provide highly inflated prediction estimates. We find no advantage for properly validated machine-learning models over linear models.

scholarly journals On the Impact of Biceps Muscle Fatigue in Human Activity Recognition

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1070
Author(s):  
Mohamed Elshafei ◽  
Diego Elias Costa ◽  
Emad Shihab
Keyword(s):  
Muscle Fatigue ◽  
Activity Recognition ◽  
Human Activity ◽  
Human Activity Recognition ◽  
Feedforward Neural Network ◽  
Muscular Endurance ◽  
Biceps Muscle ◽  
Smart Systems ◽  
Subject Specific ◽  
The Impact

Nowadays, Human Activity Recognition (HAR) systems, which use wearables and smart systems, are a part of our daily life. Despite the abundance of literature in the area, little is known about the impact of muscle fatigue on these systems’ performance. In this work, we use the biceps concentration curls exercise as an example of a HAR activity to observe the impact of fatigue impact on such systems. Our dataset consists of 3000 biceps concentration curls performed and collected from 20 volunteers aged between 20–35. Our findings indicate that fatigue often occurs in later sets of an exercise and extends the completion time of later sets by up to 31% and decreases muscular endurance by 4.1%. Another finding shows that changes in data patterns are often occurring during fatigue presence, causing seven features to become statistically insignificant. Further findings indicate that fatigue can cause a substantial decrease in performance in both subject-specific and cross-subject models. Finally, we observed that a Feedforward Neural Network (FNN) showed the best performance in both cross-subject and subject-specific models in all our evaluations.

scholarly journals Modern machine learning outperforms GLMs at predicting spikes

2017 ◽  
Author(s):  
Ari S. Benjamin ◽  
Hugo L. Fernandes ◽  
Tucker Tomlinson ◽  
Pavan Ramkumar ◽  
Chris VerSteeg ◽  
...  
Keyword(s):  
Machine Learning ◽  
Neural Activity ◽  
Linear Models ◽  
Feedforward Neural Networks ◽  
Predictive Performance ◽  
Machine Learning Techniques ◽  
Machine Learning Methods ◽  
Learning Techniques ◽  
Neural Spiking ◽  
Modern Machine

AbstractNeuroscience has long focused on finding encoding models that effectively ask “what predicts neural spiking?” and generalized linear models (GLMs) are a typical approach. It is often unknown how much of explainable neural activity is captured, or missed, when fitting a GLM. Here we compared the predictive performance of GLMs to three leading machine learning methods: feedforward neural networks, gradient boosted trees (using XGBoost), and stacked ensembles that combine the predictions of several methods. We predicted spike counts in macaque motor (M1) and somatosensory (S1) cortices from standard representations of reaching kinematics, and in rat hippocampal cells from open field location and orientation. In general, the modern methods (particularly XGBoost and the ensemble) produced more accurate spike predictions and were less sensitive to the preprocessing of features. This discrepancy in performance suggests that standard feature sets may often relate to neural activity in a nonlinear manner not captured by GLMs. Encoding models built with machine learning techniques, which can be largely automated, more accurately predict spikes and can offer meaningful benchmarks for simpler models.

scholarly journals Machine Learning the Redox Potentials of Phenazine Derivatives: A Comparative Study on Molecular Features

2021 ◽  
Author(s):  
Siddharth Ghule ◽  
Sayan Bagchi ◽  
Kumar Vanka
Keyword(s):  
Machine Learning ◽  
Energy Storage ◽  
Linear Models ◽  
High Accuracy ◽  
Active Species ◽  
Learning Models ◽  
Training Set ◽  
Molecular Features ◽  
Redox Active ◽  
Machine Learning Models

<div>Electricity generation is a major contributing factor for greenhouse gas emissions. Energy storage systems available today have a combined capacity to store less than 1% of the electricity being consumed worldwide. Redox Flow Batteries (RFBs) are promising candidates for green and efficient energy storage systems. RFBs are being used in renewable energy systems, but their widespread adoption is limited due to high production costs and toxicity associated with the transition-metal-based redox-active species. Therefore, cheaper and greener alternative organic redox-active species are being investigated. Recent reports have shown organic molecules based on phenazine are promising candidates for redox-active species in RFBs. However, the large number of available organic compounds makes the conventional experimental and DFT methods impractical to screen thousands of molecules in a reasonable amount of time. In contrast, machine-learning models have low development time, short prediction time, and high accuracy; thus, are being heavily investigated for virtual screening applications. In this work, we developed machine-learning models to predict the redox potential of phenazine derivatives in DME solvent using a small dataset of 185 molecules. 2D, 3D, and Molecular Fingerprint features were computed using readily available and easy-to-use python libraries, making our approach easily adaptable to similar work. Twenty linear and non-linear machine-learning models were investigated in this work. These models achieved excellent performance on the unseen data (i.e., R<sup>2</sup> > 0.98, MSE < 0.008 V2 and MAE < 0.07 V). Model performance was assessed in a consistent manner using the training and evaluation pipeline developed in this work. We showed that 2D molecular features are most informative and achieve the best prediction accuracy among four feature sets. We also showed that often less preferred but relatively faster linear models could perform better than non-linear models when the feature set contains different types of features (i.e., 2D, 3D, and Molecular Fingerprints). Further investigations revealed that it is possible to reduce the training and inference time without sacrificing prediction accuracy by using a small subset of features. Moreover, models were able to predict the previously reported promising redox-active compounds with high accuracy. Also, significantly low prediction errors were observed for the functional groups. Although some functional groups had only one compound in the training set, best-performing models could achieve errors (MAPE) less than 10%. The major source of error was a lack of data near-zero and in the positive region. Therefore, this work shows that it is possible to develop accurate machine-learning models that could potentially screen millions of compounds in a short amount of time with a small training set and limited number of easy to compute features. Thus, results obtained in this report would help in the adoption of green energy by accelerating the field of materials discovery for energy storage applications.</div>

scholarly journals Machine learning v. traditional regression models predicting treatment outcomes for binge-eating disorder from a randomized controlled trial

2021 ◽  
pp. 1-12
Author(s):  
Lauren N. Forrest ◽  
Valentina Ivezaj ◽  
Carlos M. Grilo
Keyword(s):  
Machine Learning ◽  
Eating Disorder ◽  
Binge Eating ◽  
Treatment Outcomes ◽  
Random Forests ◽  
Predictive Accuracy ◽  
Controlled Trial ◽  
Randomized Controlled ◽  
Linear Regressions ◽  
Machine Learning Models

Abstract Background While effective treatments exist for binge-eating disorder (BED), prediction of treatment outcomes has proven difficult, and few reliable predictors have been identified. Machine learning is a promising method for improving the accuracy of difficult-to-predict outcomes. We compared the accuracy of traditional and machine-learning approaches for predicting BED treatment outcomes. Methods Participants were 191 adults with BED in a randomized controlled trial testing 6-month behavioral and stepped-care treatments. Outcomes, determined by independent assessors, were binge-eating (% reduction, abstinence), eating-disorder psychopathology, and weight loss (% loss, ⩾5% loss). Predictors included treatment condition, demographic information, and baseline clinical characteristics. Traditional models were logistic/linear regressions. Machine-learning models were elastic net regressions and random forests. Predictive accuracy was indicated by the area under receiver operator characteristic curve (AUC), root mean square error (RMSE), and R2. Confidence intervals were used to compare accuracy across models. Results Across outcomes, AUC ranged from very poor to fair (0.49–0.73) for logistic regressions, elastic nets, and random forests, with few significant differences across model types. RMSE was significantly lower for elastic nets and random forests v. linear regressions but R2 values were low (0.01–0.23). Conclusions Different analytic approaches revealed some predictors of key treatment outcomes, but accuracy was limited. Machine-learning models with unbiased resampling methods provided a minimal advantage over traditional models in predictive accuracy for treatment outcomes.

scholarly journals Simple Linear Cancer Risk Prediction Models with Novel Features Outperform Complex Approaches

2021 ◽  
Author(s):  
Scott Kulm ◽  
Lior Kofman ◽  
Jason Mezey ◽  
Olivier Elemento
Keyword(s):  
Machine Learning ◽  
Cancer Survival ◽  
Linear Models ◽  
Prediction Models ◽  
Learning Algorithm ◽  
Learning Performance ◽  
Health Study ◽  
Learning Models ◽  
The Uk ◽  
Machine Learning Models

ABSTRACTA patient’s risk for cancer is usually estimated through simple linear models that sum effect sizes of proven risk factors. In theory, more advanced machine learning models can be used for the same task. Using data from the UK Biobank, a large prospective health study, we have developed linear and machine learning models for the prediction of 12 different cancers diagnoses within a 10 year time span. We find that the top machine learning algorithm, XGBoost (XGB), trained on 707 features generated an average area under the receiver operator curve of 0.736 (with a range of 0.65-0.85). Linear models trained with only 10 features were found to be statistically indifferent from the machine learning performance. The linear models were significantly more accurate than the prominent QCancer models (p = 0.0019), which are trained on 45 million patient records and available to over 4,000 United Kingdom general practices. The increase in accuracy may be caused by the consideration of often omitted feature types, including survey answers, census records, and genetic information. This approach led to the discovery of significant novel risk features, including self-reported happiness with own health (relevant to 12 cancers), measured testosterone (relevant to 8 cancers), and ICD codes for rehabilitation procedures (relevant to 3 cancers). These ten feature models can be easily implemented within the clinic, allowing for personalized screening schedules that may increase the cancer survival within a population.

Sign in / Sign up

Export Citation Format

Share Document