scholarly journals A Data-Driven Model to Identify Fatigue Level Based on the Motion Data from a Smartphone

2019 ◽  
Author(s):  
Swapnali Karvekar ◽  
Masoud Abdollahi ◽  
Ehsan Rashedi
Keyword(s):  
Perceived Exertion ◽  
Poor Performance ◽  
Machine Learning Algorithms ◽  
Motion Sensors ◽  
Motion Data ◽  
Work Related ◽  
Proactive Approach ◽  
Fatiguing Exercise ◽  
Four Levels ◽  
Work Related Musculoskeletal Disorder

AbstractThe fatigue due to repetitive and physically challenging jobs may result in workers’ poor performance and Work-related Musculoskeletal Disorder (WMSD). Thus, it is imperative to frequently monitor fatigue and take necessary recovery actions. Our purpose was to develop a methodology to objectively classify subjects’ fatigue level in the workplace utilizing the motion sensors embedded in the smartphones. An experiment consisting of twenty-four participants (12 M, 12 F) with a smartphone attached to their right shank was conducted using a fatiguing exercise (squatting), targeted mainly the lower extremity musculature. After each set of an exercise (2-min squatting), participants were asked about their ratings of perceived exertion (RPE), then a reference gait data were collected during a straight walk of 20-32 steps. This process was continued until they reported strong fatigue (≥17). Using the RPE to label the gait data, we have developed machine learning algorithms (i.e., binary and multi-class SVM models) to classify the individuals’ gait into two (no-vs. strong-fatigue) and four levels (no-, low-, medium-, and strong-fatigue). The models reached the accuracies of 91% and 61% for two and four-level classification, respectively. The outcomes of this study may facilitate the implementation of a proactive approach in continuous monitoring of operators’ fatigue level, which may subsequently increase the workers’ performance and reduce the risk of WMSDs.

scholarly journals Musculoskeletal Disorders’ Classification Proposal for Application in Occupational Medicine

2021 ◽  
Vol 18 (15) ◽  
pp. 8223
Author(s):  
Pablo Monteiro Pereira ◽  
João Amaro ◽  
Bruno Tillmann Ribeiro ◽  
Ana Gomes ◽  
Paulo De De Oliveira ◽  
...  
Keyword(s):  
Musculoskeletal Disorders ◽  
Development Process ◽  
Clinical Pathology ◽  
Clinical Activity ◽  
Occupational Physicians ◽  
Work Related ◽  
Therapeutic Measures ◽  
Clinical Questions ◽  
Four Levels ◽  
Tissue Alterations

Occupational-specific classifications of musculoskeletal disorders (MSD) are scarce and do not answer specific clinical questions. Thus, a specific classification was developed and proposed, covering criteria applicable to daily clinical activity. It was considered that the disorder development process is the same across all work-related MSDs (WRMSDs). Concepts of clinical pathology were applied to the characteristics of WRMSDs pathophysiology, cellular and tissue alterations. Then, the correlation of the inflammatory mechanisms with the injury onset mode was graded into four levels (MSDs 0–3). Criteria of legal, occupational and internal medicine, semiology, physiology and orthopaedics, image medicine and diagnostics were applied. Next, the classification was analysed by experts, two occupational physicians, two physiatrists and occupational physicians and one orthopaedist. This approach will allow WRMSD prevention and improve therapeutic management, preventing injuries from becoming chronic and facilitating communication between occupational health physicians and the other specialities. The four levels tool relate aetiopathogenic, clinical, occupational and radiological concepts into a single classification. This allows for improving the ability to determine a WRMSD and understanding what preventive and therapeutic measures should be taken, avoiding chronicity. The developed tool is straightforward, easy to understand and suitable for WRMSDs, facilitating communication between occupational physicians and physicians from other specialities.

scholarly journals Competitive Caching with Machine Learned Advice

2021 ◽  
Vol 68 (4) ◽  
pp. 1-25
Author(s):  
Thodoris Lykouris ◽  
Sergei Vassilvitskii
Keyword(s):  
Online Algorithms ◽  
Empirical Evaluation ◽  
Optimal Solution ◽  
Poor Performance ◽  
Machine Learning Algorithms ◽  
Average Error ◽  
Generalization Error ◽  
Worst Case ◽  
Future Events ◽  
Real World Datasets

Traditional online algorithms encapsulate decision making under uncertainty, and give ways to hedge against all possible future events, while guaranteeing a nearly optimal solution, as compared to an offline optimum. On the other hand, machine learning algorithms are in the business of extrapolating patterns found in the data to predict the future, and usually come with strong guarantees on the expected generalization error. In this work, we develop a framework for augmenting online algorithms with a machine learned predictor to achieve competitive ratios that provably improve upon unconditional worst-case lower bounds when the predictor has low error. Our approach treats the predictor as a complete black box and is not dependent on its inner workings or the exact distribution of its errors. We apply this framework to the traditional caching problem—creating an eviction strategy for a cache of size k . We demonstrate that naively following the oracle’s recommendations may lead to very poor performance, even when the average error is quite low. Instead, we show how to modify the Marker algorithm to take into account the predictions and prove that this combined approach achieves a competitive ratio that both (i) decreases as the predictor’s error decreases and (ii) is always capped by O (log k ), which can be achieved without any assistance from the predictor. We complement our results with an empirical evaluation of our algorithm on real-world datasets and show that it performs well empirically even when using simple off-the-shelf predictions.

scholarly journals Work-related Musculoskeletal Disorder (WRMD) among Production Operators: Studies of Differences in Age and Gender

2018 ◽  
Vol 1049 ◽  
pp. 012023 ◽  
Author(s):  
Nor Hazana Abdullah ◽  
Nor Aziati Abdul Hamid ◽  
Eta Wahab ◽  
Alina Shamsuddin ◽  
Rosli Asmawi
Keyword(s):  
Musculoskeletal Disorder ◽  
Age And Gender ◽  
Work Related ◽  
And Gender ◽  
Work Related Musculoskeletal Disorder

scholarly journals Using Coronial Records to Provide Novel In-Depth Insights into Work-Related Fatal Injury

2020 ◽  
Vol 5 (5) ◽  
Author(s):  
Rebbecca Lilley ◽  
Gabrielle Davie ◽  
Bronwen McNoe ◽  
Tim Driscoll
Keyword(s):  
Occupational Safety ◽  
Poor Performance ◽  
Population Data ◽  
Traffic Fatalities ◽  
Fatal Injury ◽  
Work Activities ◽  
Work Related ◽  
Additional Group ◽  
Data Collections ◽  
Official Data

IntroductionNew Zealand’s (NZ) workplace fatality record is very poor compared to similar OECD countries. The reasons for NZ’s poor performance are highly debated yet inadequately informed due to a lack of high quality fatality data. Due to incomplete official data on work fatalities in NZ, it is not currently possible to use routine official data collections to reliably report: i) who is fatally injured due to work activities, and ii) what groups should be prioritised for action. Objectives and ApproachThis study uses coronial records to overcome the limitations of existing official data collections to provide the most complete and detailed evidence platform for occupational safety policy and action in NZ. A work-related fatal injury dataset spanning the period 2005-2014 was created by: 1) identifying possible cases aged 0-84 years from the Mortality Collection using selected external cause of injury codes, 2) linking these to Coronial records and 3) identifying and coding work-related cases. ResultsOf 7,730 injury fatalities with corresponding Coronial records retrieved and reviewed, 1,924 (24%) were work-related, of which 955 were workers. Fifty-nine per cent more worker deaths were identified compared to available official NZ Government estimates from notification and compensation data. Workers killed on public roads were the main additional group identified. Official data do not provide occupation-based fatality rates; our study found ‘Miners and drillers’, ‘deckhands and fishermen’ and ‘loggers’ had the highest rates of fatal injury. Conclusion / ImplicationsCoronial records offer a rich source of population data on work-related fatal injury deaths, providing better estimates of work-traffic fatalities and high risk occupations than are otherwise available as well as evidence for establishing prevention strategies in NZ.

scholarly journals Correlation between thumb length on handgrip strength, hand dexterity and musculoskeletal problem among dental professional

2016 ◽  
Vol 19 (3) ◽  
pp. 23 ◽  
Author(s):  
Tilak Francis ◽  
Siva Anandhi
Keyword(s):  
Grip Strength ◽  
Musculoskeletal Disorder ◽  
Hand Grip Strength ◽  
Dominant Hand ◽  
Work Related ◽  
Finger Dexterity ◽  
Hand Grip ◽  
Dental Practitioners ◽  
Dental Professional ◽  
Work Related Musculoskeletal Disorder

<p><strong>Objective: </strong>The  key  factor  for  potency  of  the  teeth  is  their  muscular  strength.  The dominant  hand  plays  an  important  role  in  most  of  the  daily  muscular  activities  involving  dental  procedure.  There  are  many  factors,  which  may  affect  the  grip strength,  and  very  few  studies  especially  in  India  have  shown  their  correlation with  grip  strength. Work related musculoskeletal disorders (WRMSD) are an important occupational health problem affecting dental practitioners. This study assessed the prevalence of WRMSD in dental interns in relation to the thumb length and hand grip strength. <strong>Material and Methods</strong>: Thumb  length  template,  jammer  dynamometer,  nine-hole  peg board,  and RULA   assessment. Methods: Thumb  length  was measured  by  thumb  length template.  Grip  strength was measured  by  jammer  dynamometer, unilateral  hand  finger  dexterity was measured  by  nine-hole  pegboard,  and  work  related  musculoskeletal  disorder  was assessed  by  RULA. <strong>Results</strong>: Thumb  length was  positively   correlated  with  grip  strength  and  work related  musculoskeletal  disorder.  Thumb  length  was  negatively  correlated  with unilateral  hand  finger  dexterity  among  dental  professionals. <strong>Conclusion</strong>: Thumb  length  is  a  better  predictor  for  measuring  hand  grip strength   and   work related musculoskeletal   disorder,   than    unilateral   hand   finger dexterity.</p><p><strong>Keywords</strong></p><p>Dental professional; Hand grip strength; Thumb length; Unilateral hand finger dexterity; Work related musculoskeletal disorder.                                            </p>

scholarly journals Acute Effects of Salvia Supplementation on Cognitive Function in Athletes During a Fatiguing Cycling Exercise: A Randomized Cross-Over, Placebo-Controlled, and Double-Blind Study

2021 ◽  
Vol 8 ◽  
Author(s):  
Nicolas Babault ◽  
Ahmad Noureddine ◽  
Nicolas Amiez ◽  
Damien Guillemet ◽  
Carole Cometti
Keyword(s):  
Heart Rate ◽  
Reaction Time ◽  
Cognitive Function ◽  
Stroop Task ◽  
Perceived Exertion ◽  
Digit Span ◽  
Acute Effects ◽  
Warm Up ◽  
Positive Effects ◽  
Fatiguing Exercise

Background:Salvia (sage) supplementation has been shown to improve the cognition function in healthy individuals or patients (e.g., attention, memory). To date, no study has explored its relevancy in the context of sporting performance. The aim of this study was to explore the acute effects of a combination of Salvia officinalis and Salvia lavandulaefolia on cognitive function in athletes performing a fatiguing cycling task.Methods: Twenty-six volunteers were included in this cross-over, randomized, double-bind vs. placebo trial. Two hours before the two experimental sessions (here called SAGE and PLACEBO), volunteers randomly received a supplementation of sage or placebo. During each experimental session, participants were tested at four occasions while cycling during a warm-up, in the middle and at the end of a fatiguing task and after a short 5-min recovery. Tests included a Stroop task, a simple reaction time task, and a backward digit span memory task. Heart rate and rating of perceived exertion (RPE) were also measured at the beginning of the four test sessions.Results: Heart rate was significantly greater during the fatiguing exercise than during warm-up and recovery (P &lt; 0.001) without any supplementation effect. RPE was greater during the fatiguing exercise than during warm-up and recovery (P &lt; 0.001). Moreover, RPE was significantly lower during the SAGE session as compared to PLACEBO (P = 0.002). Reaction time was not altered during the exercise but was significantly shorter with SAGE as compared to PLACEBO (P = 0.023). The Stroop task only revealed significantly longer reaction time during warm-up as compared to recovery (P = 0.02) independently of the supplementation. The digit span memory test revealed a significant greater span score with SAGE as compared to PLACEBO (P = 0.044).Conclusion: The combination of Salvia improved the cognitive functions (perceived exertion, working memory, and reaction time). The positive effects were obtained in fresh condition and were maintained with fatigue.

Machine-Learning-Based External Plagiarism Detecting Methodology From Monolingual Documents

2018 ◽  
pp. 122-139
Author(s):  
Saugata Bose ◽  
Ritambhra Korpal
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Confusion Matrix ◽  
False Negative ◽  
False Negative Rate ◽  
Search Space ◽  
Machine Learning Algorithms ◽  
C4.5 Decision Tree ◽  
N Gram ◽  
Four Levels

In this chapter, an initiative is proposed where natural language processing (NLP) techniques and supervised machine learning algorithms have been combined to detect external plagiarism. The major emphasis is on to construct a framework to detect plagiarism from monolingual texts by implementing n-gram frequency comparison approach. The framework is based on 120 characteristics which have been extracted during pre-processing steps using simple NLP approach. Afterward, filter metrics has been applied to select most relevant features and supervised classification learning algorithm has been used later to classify the documents in four levels of plagiarism. Then, confusion matrix was built to estimate the false positives and false negatives. Finally, the authors have shown C4.5 decision tree-based classifier's suitability on calculating accuracy over naive Bayes. The framework achieved 89% accuracy with low false positive and false negative rate and it shows higher precision and recall value comparing to passage similarities method, sentence similarity method, and search space reduction method.

Sign in / Sign up

Export Citation Format

Share Document