scholarly journals Meta Products towards a “gait/running style app”

2014 ◽  
Author(s):  
Martin Daumer ◽  
Andreas N. Schneider ◽  
Damian Mrowca ◽  
Rui Ding ◽  
Han Gao ◽  
...  
Keyword(s):  
High Speed ◽  
Injury Risk ◽  
The Body ◽  
Three Dimensions ◽  
Treadmill Running ◽  
Machine Learning Techniques ◽  
Stride Frequency ◽  
Learning Techniques ◽  
Outdoor Environments ◽  
The Individual

Background: The individual running style has an impact on the running performance as well as the running injury risk. In order to increase the performance and lower the injury risk, runners should be educated towards a healthy running style. But before advices can be made it is crucial to distinguish running styles from each other.Aim: The stretch goal is to build a running style app, which is able to track and display the user’s current running style by using accelerometry data, based on which advice can be given for a healthy and efficient running style with the help of gaming tools. To validate the approach, a gold standard with outdoor running acceleration data has to be created.Methods: The accelerometry data used by the smartphone app is gathered from the “actibelt”, an accelerometer included in a belt buckle. This sensor collects data close to the body COM in all three dimensions which is transferred to a smartphone via Bluetooth in real-time. The focus of this work is the validation of an acceleration based detection of different running styles, namely heel strikes, midfoot strikes and forefoot strikes. Features, which are able to clearly distinguish different running styles, have to be extracted out of the accelerometry data with machine learning techniques (SVM). Laboratory experiments have been conducted to analyze the actibelt data of three test persons performing heel, midfoot and forefoot strikes on a pressure sensitive treadmill with video control. As running apps are mainly used outdoors, the results had to be reproduced with outdoor running data. In an extreme ends approach four test persons with different running experience ranging from professional to occasional runners were asked to successively run on their heels, midfoot and forefoot, while accelerometry data was recorded and synchronized with mobile high speed video. The different running styles were performed on different substrates, with different shoes and speeds. Discussion/Conclusion: While significant differences in the accelerometry data of the running styles have been observed in the laboratory, those differences couldn’t be reproduced in outdoor environments. Characteristic peak patterns (Lieberman, nature 463, 531-535) could be reproduced in the laboratory but disappeared in outdoor running. The most distorting aspects are the harder and less comfortable surface and an irregular speed compared to treadmill running. Hence, for a reliable detection of the running style, the actibelt data may be complemented by further sensors, e.g. placed in the socks. A promising idea is to influence the stride frequency of runners at given speeds to improve the individual running style.

scholarly journals Meta Products towards a “gait/running style app”

2014 ◽  
Author(s):  
Martin Daumer ◽  
Andreas N. Schneider ◽  
Damian Mrowca ◽  
Rui Ding ◽  
Han Gao ◽  
...  
Keyword(s):  
High Speed ◽  
Injury Risk ◽  
The Body ◽  
Three Dimensions ◽  
Treadmill Running ◽  
Machine Learning Techniques ◽  
Stride Frequency ◽  
Learning Techniques ◽  
Outdoor Environments ◽  
The Individual

Background: The individual running style has an impact on the running performance as well as the running injury risk. In order to increase the performance and lower the injury risk, runners should be educated towards a healthy running style. But before advices can be made it is crucial to distinguish running styles from each other.Aim: The stretch goal is to build a running style app, which is able to track and display the user’s current running style by using accelerometry data, based on which advice can be given for a healthy and efficient running style with the help of gaming tools. To validate the approach, a gold standard with outdoor running acceleration data has to be created.Methods: The accelerometry data used by the smartphone app is gathered from the “actibelt”, an accelerometer included in a belt buckle. This sensor collects data close to the body COM in all three dimensions which is transferred to a smartphone via Bluetooth in real-time. The focus of this work is the validation of an acceleration based detection of different running styles, namely heel strikes, midfoot strikes and forefoot strikes. Features, which are able to clearly distinguish different running styles, have to be extracted out of the accelerometry data with machine learning techniques (SVM). Laboratory experiments have been conducted to analyze the actibelt data of three test persons performing heel, midfoot and forefoot strikes on a pressure sensitive treadmill with video control. As running apps are mainly used outdoors, the results had to be reproduced with outdoor running data. In an extreme ends approach four test persons with different running experience ranging from professional to occasional runners were asked to successively run on their heels, midfoot and forefoot, while accelerometry data was recorded and synchronized with mobile high speed video. The different running styles were performed on different substrates, with different shoes and speeds. Discussion/Conclusion: While significant differences in the accelerometry data of the running styles have been observed in the laboratory, those differences couldn’t be reproduced in outdoor environments. Characteristic peak patterns (Lieberman, nature 463, 531-535) could be reproduced in the laboratory but disappeared in outdoor running. The most distorting aspects are the harder and less comfortable surface and an irregular speed compared to treadmill running. Hence, for a reliable detection of the running style, the actibelt data may be complemented by further sensors, e.g. placed in the socks. A promising idea is to influence the stride frequency of runners at given speeds to improve the individual running style.

Importance of Various Training-Load Measures in Injury Incidence of Professional Rugby League Athletes

2017 ◽  
Vol 12 (6) ◽  
pp. 819-824 ◽  
Author(s):  
Heidi R. Thornton ◽  
Jace A. Delaney ◽  
Grant M. Duthie ◽  
Ben J. Dascombe
Keyword(s):  
Risk Factors ◽  
High Speed ◽  
Injury Risk ◽  
Perceived Exertion ◽  
Rugby League ◽  
Training Load ◽  
Rating Of Perceived Exertion ◽  
Machine Learning Techniques ◽  
Injury Incidence ◽  
The Individual

Purpose:To investigate the ability of various internal and external training-load (TL) monitoring measures to predict injury incidence among positional groups in professional rugby league athletes.Methods:TL and injury data were collected across 3 seasons (2013–2015) from 25 players competing in National Rugby League competition. Daily TL data were included in the analysis, including session rating of perceived exertion (sRPE-TL), total distance (TD), high-speed-running distance (>5 m/s), and high-metabolic-power distance (HPD; >20 W/kg). Rolling sums were calculated, nontraining days were removed, and athletes’ corresponding injury status was marked as “available” or “unavailable.” Linear (generalized estimating equations) and nonlinear (random forest; RF) statistical methods were adopted.Results:Injury risk factors varied according to positional group. For adjustables, the TL variables associated most highly with injury were 7-d TD and 7-d HPD, whereas for hit-up forwards they were sRPE-TL ratio and 14-d TD. For outside backs, 21- and 28-d sRPE-TL were identified, and for wide-running forwards, sRPE-TL ratio. The individual RF models showed that the importance of the TL variables in injury incidence varied between athletes.Conclusions:Differences in risk factors were recognized between positional groups and individual athletes, likely due to varied physiological capacities and physical demands. Furthermore, these results suggest that robust machine-learning techniques can appropriately monitor injury risk in professional team-sport athletes.

User Profiles for Personalizing Digital Libraries

2009 ◽  
pp. 149-158 ◽  
Author(s):  
Giovanni Semeraro ◽  
Pierpaolo Basile ◽  
Marco de Gemmis ◽  
Pasquale Lops
Keyword(s):  
Machine Learning ◽  
Digital Libraries ◽  
Machine Learning Techniques ◽  
Linguistic Knowledge ◽  
User Profiles ◽  
User Interests ◽  
Learning Techniques ◽  
Document Filtering ◽  
The Individual ◽  
Machine Readable

Exploring digital collections to find information relevant to a user’s interests is a challenging task. Information preferences vary greatly across users; therefore, filtering systems must be highly personalized to serve the individual interests of the user. Algorithms designed to solve this problem base their relevance computations on user profiles in which representations of the users’ interests are maintained. The main focus of this chapter is the adoption of machine learning to build user profiles that capture user interests from documents. Profiles are used for intelligent document filtering in digital libraries. This work suggests the exploiting of knowledge stored in machine-readable dictionaries to obtain accurate user profiles that describe user interests by referring to concepts in those dictionaries. The main aim of the proposed approach is to show a real-world scenario in which the combination of machine learning techniques and linguistic knowledge is helpful to achieve intelligent document filtering.

scholarly journals Ensemble Learning to Improve the Prediction of Fetal Macrosomia and Large-for-Gestational Age

2020 ◽  
Vol 9 (2) ◽  
pp. 380 ◽  
Author(s):  
Shangyuan Ye ◽  
Hui Zhang ◽  
Fuyan Shi ◽  
Jing Guo ◽  
Suzhen Wang ◽  
...  
Keyword(s):  
Ensemble Learning ◽  
Gestational Age ◽  
Prediction Accuracy ◽  
Ensemble Methods ◽  
Machine Learning Techniques ◽  
Fetal Macrosomia ◽  
Large For Gestational Age ◽  
Empirical Formulas ◽  
Learning Techniques ◽  
The Individual

Background: The objective of this study was to investigate the use of ensemble methods to improve the prediction of fetal macrosomia and large for gestational age from prenatal ultrasound imaging measurements. Methods: We evaluated and compared the prediction accuracies of nonlinear and quadratic mixed-effects models coupled with 26 different empirical formulas for estimating fetal weights in predicting large fetuses at birth. The data for the investigation were taken from the Successive Small-for-Gestational-Age-Births study. Ensemble methods, a class of machine learning techniques, were used to improve the prediction accuracies by combining the individual models and empirical formulas. Results: The prediction accuracy of individual statistical models and empirical formulas varied considerably in predicting macrosomia but varied less in predicting large for gestational age. Two ensemble methods, voting and stacking, with model selection, can combine the strengths of individual models and formulas and can improve the prediction accuracy. Conclusions: Ensemble learning can improve the prediction of fetal macrosomia and large for gestational age and have the potential to assist obstetricians in clinical decisions.

From machine learning to sustainable taxation: GPS traces of trucks circulating in Belgium

2020 ◽  
Author(s):  
Arnaud Adam ◽  
Isabelle Thomas
Keyword(s):  
Machine Learning ◽  
Point Of View ◽  
Machine Learning Techniques ◽  
Spatial Effects ◽  
Space And Time ◽  
Learning Techniques ◽  
Other Information ◽  
Gps Traces ◽  
The Individual ◽  
Taxation System

<p>Transport geography has always been characterized by a lack of accurate data, leading to surveys often based on samples that are spatially not representative. However, the current deluge of data collected through sensors promises to overpass this scarcity of data. We here consider one example: since April 1<sup>st</sup> 2016, a GPS tracker is mandatory within each truck circulating in Belgium for kilometre taxes. Every 30 seconds, this tracker collects the position of the truck (as well as some other information such as speed or direction), leading to an individual taxation of trucks. This contribution uses a one-week exhaustive database containing the totality of trucks circulating in Belgium, in order to understand transport fluxes within the country, as well as the spatial effects of the taxation on the circulation of trucks.</p><p>Machine learning techniques are applied on over 270 million of GPS points to detect stops of trucks, leading to transform GPS sequences into a complete Origin-Destination matrix. Using machine learning allows to accurately classify stops that are different in nature (leisure stop, (un-)loading areas, or congested roads). Based on this matrix, we firstly propose an overview of the daily traffic, as well as an evaluation of the number of stops made in every Belgian place. Secondly, GPS sequences and stops are combined, leading to characterise sub-trajectories of each truck (first/last miles and transit) by their fiscal debit. This individual characterisation, as well as its variation in space and time, are here discussed: is the individual taxation system always efficient in space and time?</p><p>This contribution helps to better understand the circulation of trucks in Belgium, the places where they stopped, as well as the importance of their locations in a fiscal point of view. What are the potential modifications of the trucks routes that would lead to a more sustainable kilometre taxation? This contribution illustrates that combining big-data and machine learning open new roads for accurately measuring and modelling transportation.</p>

Predictive Analysis of Diabetes Mellitus Using Machine Learning Techniques

2020 ◽  
Vol 17 (8) ◽  
pp. 3449-3452
Author(s):  
M. S. Roobini ◽  
Y. Sai Satwick ◽  
A. Anil Kumar Reddy ◽  
M. Lakshmi ◽  
D. Deepa ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Machine Learning ◽  
Early Stage ◽  
The Body ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Pima Indians ◽  
Classification Techniques ◽  
Learning Techniques ◽  
Prediction Of Diabetes

In today’s world diabetes is the major health challenges in India. It is a group of a syndrome that results in too much sugar in the blood. It is a protracted condition that affects the way the body mechanizes the blood sugar. Prevention and prediction of diabetes mellitus is increasingly gaining interest in medical sciences. The aim is how to predict at an early stage of diabetes using different machine learning techniques. In this paper basically, we use well-known classification that are Decision tree, K-Nearest Neighbors, Support Vector Machine, and Random forest. These classification techniques used with Pima Indians diabetes dataset. Therefore, we predict diabetes at different stage and analyze the performance of different classification techniques. We Also proposed a conceptual model for the prediction of diabetes mellitus using different machine learning techniques. In this paper we also compare the accuracy of the different machine learning techniques to finding the diabetes mellitus at early stage.

scholarly journals Predictive Modeling of Pressure Injury Risk in Patients Admitted to an Intensive Care Unit

2020 ◽  
Vol 29 (4) ◽  
pp. e70-e80
Author(s):  
Mireia Ladios-Martin ◽  
José Fernández-de-Maya ◽  
Francisco-Javier Ballesta-López ◽  
Adrián Belso-Garzas ◽  
Manuel Mas-Asencio ◽  
...  
Keyword(s):  
Machine Learning ◽  
Intensive Care Unit ◽  
Intensive Care ◽  
Injury Risk ◽  
Area Under The Curve ◽  
University Hospital ◽  
Machine Learning Techniques ◽  
Real Environment ◽  
Learning Techniques ◽  
Pressure Injury

Background Pressure injuries are an important problem in hospital care. Detecting the population at risk for pressure injuries is the first step in any preventive strategy. Available tools such as the Norton and Braden scales do not take into account all of the relevant risk factors. Data mining and machine learning techniques have the potential to overcome this limitation. Objectives To build a model to detect pressure injury risk in intensive care unit patients and to put the model into production in a real environment. Methods The sample comprised adult patients admitted to an intensive care unit (N = 6694) at University Hospital of Torrevieja and University Hospital of Vinalopó. A retrospective design was used to train (n = 2508) and test (n = 1769) the model and then a prospective design was used to test the model in a real environment (n = 2417). Data mining was used to extract variables from electronic medical records and a predictive model was built with machine learning techniques. The sensitivity, specificity, area under the curve, and accuracy of the model were evaluated. Results The final model used logistic regression and incorporated 23 variables. The model had sensitivity of 0.90, specificity of 0.74, and area under the curve of 0.89 during the initial test, and thus it outperformed the Norton scale. The model performed well 1 year later in a real environment. Conclusions The model effectively predicts risk of pressure injury. This allows nurses to focus on patients at high risk for pressure injury without increasing workload.

scholarly journals Vehicle Price Prediction using SVM Techniques

2020 ◽  
Vol 9 (8) ◽  
pp. 398-401
Keyword(s):  
Machine Learning ◽  
Research Area ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Data Set ◽  
Network Support ◽  
Java Application ◽  
Learning Techniques ◽  
The Individual

The prediction of price for a vehicle has been more popular in research area, and it needs predominant effort and information about the experts of this particular field. The number of different attributes is measured and also it has been considerable to predict the result in more reliable and accurate. To find the price of used vehicles a well defined model has been developed with the help of three machine learning techniques such as Artificial Neural Network, Support Vector Machine and Random Forest. These techniques were used not on the individual items but for the whole group of data items. This data group has been taken from some web portal and that same has been used for the prediction. The data must be collected using web scraper that was written in PHP programming language. Distinct machine learning algorithms of varying performances had been compared to get the best result of the given data set. The final prediction model was integrated into Java application

Sign in / Sign up

Export Citation Format

Share Document