Estimating Throwing Speed in Handball Using a Wearable Device

Throwing speed is likely a key determinant of shoulder-specific load. However, it is difficult to estimate the speed of throws in handball in field-based settings with many players due to limitations in current technology. Therefore, the purpose of this study was to develop a novel method to estimate throwing speed in handball using a low-cost accelerometer-based device. Nineteen experienced handball players each performed 25 throws of varying types while we measured the acceleration of the wrist using the accelerometer and the throwing speed using 3D motion capture. Using cross-validation, we developed four prediction models using combinations of the logarithm of the peak total acceleration, sex and throwing type as the predictor and the throwing speed as the outcome. We found that all models were well-calibrated (mean calibration of all models: 0.0 m/s, calibration slope of all models: 1.00) and precise (R2 = 0.71–0.86, mean absolute error = 1.30–1.82 m/s). We conclude that the developed method provides practitioners and researchers with a feasible and cheap method to estimate throwing speed in handball from segments of wrist acceleration signals containing only a single throw.

Download Full-text

A Novel Method for Estimating Throwing Speed in Handball using a Wearable Device

10.20944/preprints202008.0085.v1 ◽

2020 ◽

Author(s):

Sebastian D Skejø ◽

Jesper Bencke ◽

Merete Møller ◽

Henrik Sørensen

Keyword(s):

Cross Validation ◽

Prediction Models ◽

Mean Absolute Error ◽

Low Cost ◽

Absolute Error ◽

Shoulder Injuries ◽

Specific Load ◽

Cheap Method ◽

Novel Method ◽

3D Motion Capture

Understanding the shoulder-specific load in handball is important for both prevention and rehabilitation of shoulder injuries. The shoulder-specific load is largely a result of the number and speed of throws. However, it is difficult to quantify number and speed of throws in handball due to limitations in the current technology. Therefore, the purpose of this study was to develop a novel method to estimate throwing speed in handball using a low-cost accelerometer-based device. Nineteen experienced handball players each performed 25 throws of varying types while we measured the acceleration of the wrist using the accelerometer and the throwing speed using 3D motion capture. Using cross-validation, we developed four prediction models using combinations of the logarithm of the peak total acceleration, sex and throwing type as the predictor and the throwing speed as the outcome. We found that all models were well-calibrated (mean calibration of all models: 0.0 m/s, calibration slope range: 0.99-1.00) and precise (R2 = 0.71-0.85, mean absolute error = 1.32-1.82 m/s). We conclude that the developed method appear to provide practitioners and researchers with a feasible and cheap method to estimate throwing speeds in handball.

Download Full-text

Earthquake Time Prediction using CatBoost and SVR

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.a3993.119119 ◽

2019 ◽

Vol 9 (1) ◽

pp. 225-229

Keyword(s):

Support Vector Machine ◽

Cross Validation ◽

Mean Absolute Error ◽

Absolute Error ◽

Acoustic Signals ◽

High Accuracy ◽

Support Vector ◽

Time Prediction ◽

Vector Machines ◽

Time Of Failure

Seismic tremors everywhere throughout the globe have been a noteworthy reason for decimation and death toll and property. The following context expects to recognize earthquakes at a beginning time utilizing AI. This will help individuals and salvage groups to make their errand simpler. The information in this manner comprises of these seismic acoustic signals and the time of failure. The model is then prepared utilizing the CatBoost model and the utilization of Support Vector Machines. This will help foresee the time at which a Seismic tremor may happen. CatBoost Regression Algorithm gives a Mean Absolute Error of about 1.860. The Cross Validation (CV) Score for the Support Vector Machine (SVM) approach is -2.1651. The datasets metrics are not reliable on any outer parameter in this manner the variety of exactness is constrained, and high accuracy is accomplished.

Download Full-text

Evaluation and Application of a Novel Low-Cost Wearable Sensing Device in Assessing Real-Time PM2.5 Exposure in Major Asian Transportation Modes

Atmosphere ◽

10.3390/atmos12020270 ◽

2021 ◽

Vol 12 (2) ◽

pp. 270

Author(s):

Wen-Cheng Vincent Wang ◽

Shih-Chun Candice Lung ◽

Chun-Hu Liu ◽

Tzu-Yao Julia Wen ◽

Shu-Chuan Hu ◽

...

Keyword(s):

Particulate Matter ◽

Real Time ◽

Mean Absolute Error ◽

Low Cost ◽

Absolute Error ◽

Laboratory Evaluation ◽

Sensing System ◽

Transportation Modes ◽

Pm2.5 Exposure ◽

Device Location

Small low-cost sensing (LCS) devices enable assessment of close-to-reality PM2.5 exposures, though their data quality remains a challenge. This work evaluates the precision, accuracy, wearability and stability of a wearable particle LCS device, Location-Aware Sensing System (LASS, with Plantower PMS3003), which is 104 × 66 × 46 mm3 in size and less than 162 g in weight. Real-time particulate matter (PM) exposures in six major Asian transportation modes were assessed. Side-by-side laboratory evaluation of PM2.5 between a GRIMM aerosol spectrometer and sensors yielded a correlation of 0.98 and a mean absolute error of 0.85 µg/m3. LASS readings collected in the summer of 2016 in Taiwan were converted to GRIMM-comparable values. Mean PM2.5 concentrations obtained from GRIMM and converted LASS values of the six different transportation microenvironments were 16.9 ± 11.7 (n = 1774) and 17.0 ± 9.5 (n = 3399) µg/m3, respectively, showing a correlation of 0.93. The average one-hour PM2.5 exposure increments (concentration increase above ambient levels) from converted LASS values for Mass Rapid Transit (MRT), bus, car, scooter, bike and walk were 15.6, 6.7, −19.2, 8.1, 6.1 and 7.1 µg/m3, respectively, very close to those obtained from GRIMM. This work is one of the earliest studies applying wearable particulate matter (PM) LCS devices in exposure assessment in different transportation modes.

Download Full-text

Approaches for the Prediction of Leaf Wetness Duration with Machine Learning

Biomimetics ◽

10.3390/biomimetics6020029 ◽

2021 ◽

Vol 6 (2) ◽

pp. 29

Author(s):

Martín Solís ◽

Vanessa Rojas-Herrera

Keyword(s):

Machine Learning ◽

Disease Prevention ◽

Prediction Models ◽

Mean Absolute Error ◽

Model Performance ◽

Absolute Error ◽

Leaf Wetness ◽

Leaf Wetness Duration ◽

Coffee Plantations ◽

Temporal Variables

The prediction of leaf wetness duration (LWD) is an issue of interest for disease prevention in coffee plantations, forests, and other crops. This study analyzed different LWD prediction approaches using machine learning and meteorological and temporal variables as the models’ input. The information was collected through meteorological stations placed in coffee plantations in six different regions of Costa Rica, and the leaf wetness duration was measured by sensors installed in the same regions. The best prediction models had a mean absolute error of around 60 min per day. Our results demonstrate that for LWD modeling, it is not convenient to aggregate records at a daily level. The model performance was better when the records were collected at intervals of 15 min instead of 30 min.

Download Full-text

Machine learning meets pKa

F1000Research ◽

10.12688/f1000research.22090.2 ◽

2020 ◽

Vol 9 ◽

pp. 113 ◽

Cited By ~ 2

Author(s):

Marcel Baltruschat ◽

Paul Czodrowski

Keyword(s):

Machine Learning ◽

Cross Validation ◽

Mean Squared Error ◽

Mean Absolute Error ◽

External Validation ◽

Absolute Error ◽

Source Model ◽

Squared Error ◽

Fold Cross Validation ◽

Better Than

We present a small molecule pKa prediction tool entirely written in Python. It predicts the macroscopic pKa value and is trained on a literature compilation of monoprotic compounds. Different machine learning models were tested and random forest performed best given a five-fold cross-validation (mean absolute error=0.682, root mean squared error=1.032, correlation coefficient r2 =0.82). We test our model on two external validation sets, where our model performs comparable to Marvin and is better than a recently published open source model. Our Python tool and all data is freely available at https://github.com/czodrowskilab/Machine-learning-meets-pKa.

Download Full-text

The Prediction of Body Mass Index from Negative Affectivity through Machine Learning: A Confirmatory Study

Sensors ◽

10.3390/s21072361 ◽

2021 ◽

Vol 21 (7) ◽

pp. 2361

Author(s):

Giovanni Delnevo ◽

Giacomo Mancini ◽

Marco Roccetti ◽

Paola Salomoni ◽

Elena Trombini ◽

...

Keyword(s):

Machine Learning ◽

Body Mass Index ◽

Body Mass ◽

Mean Absolute Error ◽

Absolute Error ◽

Machine Learning Algorithms ◽

Gradient Boosting ◽

Psychological Variables ◽

Novel Method ◽

The Relationship

This study investigates on the relationship between affect-related psychological variables and Body Mass Index (BMI). We have utilized a novel method based on machine learning (ML) algorithms that forecast unobserved BMI values based on psychological variables, like depression, as predictors. We have employed various machine learning algorithms, including gradient boosting and random forest, with psychological variables relative to 221 subjects to predict both the BMI values and the BMI status (normal, overweight, and obese) of those subjects. We have found that the psychological variables in use allow one to predict both the BMI values (with a mean absolute error of 5.27–5.50) and the BMI status with an accuracy of over 80% (metric: F1-score). Further, our study has also confirmed the particular efficacy of psychological variables of negative type, such as depression for example, compared to positive ones, to achieve excellent predictive BMI values.

Download Full-text

Forecasting elections results via the voter model with stubborn nodes

Applied Network Science ◽

10.1007/s41109-020-00342-7 ◽

2021 ◽

Vol 6 (1) ◽

Author(s):

Antoine Vendeville ◽

Benjamin Guedj ◽

Shi Zhou

Keyword(s):

Mean Absolute Error ◽

Absolute Error ◽

Voter Model ◽

Model Parameters ◽

Popular Vote ◽

Political Landscape ◽

The Us ◽

Novel Method ◽

The Uk ◽

Theoretical Results

AbstractIn this paper we propose a novel method to forecast the result of elections using only official results of previous ones. It is based on the voter model with stubborn nodes and uses theoretical results developed in a previous work of ours. We look at popular vote shares for the Conservative and Labour parties in the UK and the Republican and Democrat parties in the US. We are able to perform time-evolving estimates of the model parameters and use these to forecast the vote shares for each party in any election. We obtain a mean absolute error of 4.74%. As a side product, our parameters estimates provide meaningful insight on the political landscape, informing us on the proportion of voters that are strong supporters of each of the considered parties.

Download Full-text

Modelling Bedrock Topography

10.5194/esurf-2019-57 ◽

2019 ◽

Author(s):

Nils-Otto Kitterød ◽

Étienne Leblois

Keyword(s):

Ordinary Kriging ◽

Cross Validation ◽

Mean Absolute Error ◽

Absolute Error ◽

Geological Mapping ◽

Poisson’S Equation ◽

Horizontal Distance ◽

Poisson's Equation ◽

Bedrock Topography ◽

Local Trend

Abstract. The access to digital information from remote sensing; geological mapping; and public databases give an opportunity to express the surface of the bedrock as a mathematical estimation problem. We modelled the bedrock topography as a stochastic function in space. The function is given with high precision in areas where the bedrock is exposed to the surface, but unknown in areas covered by sediments except for a limited number of point information (viz boreholes; wells; geotechnical surveys). Two different approaches were evaluated to reveal the local trend of the bedrock surface: Firstly, we applied the statistical relation between the horizontal distance (L) to the nearest bedrock outcrop and the observed sediment depth (D) in boreholes. The relation between D and L was applied in ordinary kriging and cokriging to include the local trend in the estimation. Secondly, we applied inverse modelling of the Poisson's equation to model the local trend. After minimizing the difference between the point observations and the parabolic surface from the Poisson's equation, we did ordinary kriging of the residuals between the optimal parabolic function and the observations. These approaches were tested against observations from a test site. Estimates derived from the Poisson's equation gave a lowest mean absolute error for cross-validation by leaving one observation out. Ordinary kriging gave a least mean absolute error when an independent dataset was used for cross-validation. The results show that the extreme large soil depths were better reproduced if the local trend was included in the estimation procedure.

Download Full-text

Modeling Superconducting Critical Temperature of 122-Iron-Based Pnictide Intermetallic Superconductor Using a Hybrid Intelligent Computational Method

Materials ◽

10.3390/ma14164604 ◽

2021 ◽

Vol 14 (16) ◽

pp. 4604

Author(s):

Oluwatobi Akomolafe ◽

Taoreed O. Owolabi ◽

Mohd Amiruddin Abd Rahman ◽

Mohd Mustafa Awang Kechik ◽

Mohd Najib Mohd Yasin ◽

...

Keyword(s):

Critical Temperature ◽

Structural Transformation ◽

Mean Absolute Error ◽

Low Cost ◽

Absolute Error ◽

Computational Method ◽

Hole Doping ◽

Support Vector ◽

Ionic Radii ◽

Iron Based

Structural transformation and magnetic ordering interplays for emergence as well as suppression of superconductivity in 122-iron-based superconducting materials. Electron and hole doping play a vital role in structural transition and magnetism suppression and ultimately enhance the room pressure superconducting critical temperature of the compound. This work models the superconducting critical temperature of 122-iron-based superconductor using tetragonal to orthorhombic lattice (LAT) structural transformation during low-temperature cooling and ionic radii of the dopants as descriptors through hybridization of support vector regression (SVR) intelligent algorithm with particle swarm (PS) parameter optimization method. The developed PS-SVR-RAD model, which utilizes ionic radii (RAD) and the concentrations of dopants as descriptors, shows better performance over the developed PS-SVR-LAT model that employs lattice parameters emanated from structural transformation as descriptors. Using the root mean square error (RMSE), coefficient of correlation (CC) and mean absolute error as performance measuring criteria, the developed PS-SVR-RAD model performs better than the PS-SVR-LAT model with performance improvement of 15.28, 7.62 and 72.12%, on the basis of RMSE, CC and Mean Absolute Error (MAE), respectively. Among the merits of the developed PS-SVR-RAD model over the PS-SVR-LAT model is the possibility of electrons and holes doping from four different dopants, better performance and ease of model development at relatively low cost since the descriptors are easily fetched ionic radii. The developed intelligent models in this work would definitely facilitate quick and precise determination of critical transition temperature of 122-iron-based superconductor for desired applications at low cost with experimental stress circumvention.

Download Full-text