Prognostic Validity of Statistical Prediction Methods Used for Talent Identification in Youth Tennis Players Based on Motor Abilities

(1) Background: The search for talented young athletes is an important element of top-class sport. While performance profiles and suitable test tasks for talent identification have already been extensively investigated, there are few studies on statistical prediction methods for talent identification. Therefore, this long-term study examined the prognostic validity of four talent prediction methods. (2) Methods: Tennis players (N = 174; n♀ = 62 and n♂ = 112) at the age of eight years (U9) were examined using five physical fitness tests and four motor competence tests. Based on the test results, four predictions regarding the individual future performance were made for each participant using a linear recommendation score, a logistic regression, a discriminant analysis, and a neural network. These forecasts were then compared with the athletes’ achieved performance success at least four years later (U13‒U18). (3) Results: All four prediction methods showed a medium-to-high prognostic validity with respect to their forecasts. Their values of relative improvement over chance ranged from 0.447 (logistic regression) to 0.654 (tennis recommendation score). (4) Conclusions: However, the best results are only obtained by combining the non-linear method (neural network) with one of the linear methods. Nevertheless, 18.75% of later high-performance tennis players could not be predicted using any of the methods.

Download Full-text

ECG Biometrics Using Deep Learning and Relative Score Threshold Classification

Sensors ◽

10.3390/s20154078 ◽

2020 ◽

Vol 20 (15) ◽

pp. 4078

Author(s):

David Belo ◽

Nuno Bento ◽

Hugo Silva ◽

Ana Fred ◽

Hugo Gamboa

Keyword(s):

Neural Network ◽

High Performance ◽

Similarity Score ◽

Pattern Recognition Problem ◽

Individual Traits ◽

Score Threshold ◽

Relative Score ◽

The Individual ◽

Time Required ◽

Robust Systems

The field of biometrics is a pattern recognition problem, where the individual traits are coded, registered, and compared with other database records. Due to the difficulties in reproducing Electrocardiograms (ECG), their usage has been emerging in the biometric field for more secure applications. Inspired by the high performance shown by Deep Neural Networks (DNN) and to mitigate the intra-variability challenges displayed by the ECG of each individual, this work proposes two architectures to improve current results in both identification (finding the registered person from a sample) and authentication (prove that the person is whom it claims) processes: Temporal Convolutional Neural Network (TCNN) and Recurrent Neural Network (RNN). Each architecture produces a similarity score, based on the prediction error of the former and the logits given by the last, and fed to the same classifier, the Relative Score Threshold Classifier (RSTC).The robustness and applicability of these architectures were trained and tested on public databases used by literature in this context: Fantasia, MIT-BIH, and CYBHi databases. Results show that overall the TCNN outperforms the RNN achieving almost 100%, 96%, and 90% accuracy, respectively, for identification and 0.0%, 0.1%, and 2.2% equal error rate (EER) for authentication processes. When comparing to previous work, both architectures reached results beyond the state-of-the-art. Nevertheless, the improvement of these techniques, such as enriching training with extra varied data and transfer learning, may provide more robust systems with a reduced time required for validation.

Download Full-text

Dlouhodobé sledování úrovně výkonnostních předpokladů vybraných tenistů

Studia sportiva ◽

10.5817/sts2014-1-4 ◽

2014 ◽

Vol 8 (1) ◽

pp. 35-42

Author(s):

Michal Polách ◽

Jiří Zháněl ◽

Ondřej Hubáček

Keyword(s):

High Performance ◽

Sport Performance ◽

Statistical Dependence ◽

Tennis Players ◽

Individual Variables ◽

The Individual ◽

High Level ◽

The Relationship ◽

Game Performance

Monitoring the level of individual factors or performance predispositions is an essential part of athlete´s training process. The article discusses the results of the diagnostic performance predispositions research of the selected group of tennis players. In the research, we first made a selection of players according to the criterion of the frequency of participation in testing and the other criterion was the performance level, ranking, they reached. In the next phase, we analyzed the individual test results of the players in the long-term perspective. The final step was to assess the relationship between age, the results of the test battery and game performance. Due to the small number of measurements and the complexity of sport performance in tennis we did not expect very tight dependence (correlation) of individual variables. We came to the conclusion that by all observed players a high level of motor performance predisposition were recorded which corresponds with their high performance in tennis and ranking, although statistical dependence was not proven.

Download Full-text

Tax Arrears Versus Financial Ratios in Bankruptcy Prediction

Journal of Risk and Financial Management ◽

10.3390/jrfm12040187 ◽

2019 ◽

Vol 12 (4) ◽

pp. 187 ◽

Cited By ~ 1

Author(s):

Oliver Lukason ◽

Art Andresson

Keyword(s):

Logistic Regression ◽

Multilayer Perceptron ◽

Prediction Accuracy ◽

Bankruptcy Prediction ◽

Financial Ratios ◽

Prediction Methods ◽

Combined Model ◽

The Individual ◽

Practical Implications

This paper aims to compare the usefulness of tax arrears and financial ratios in bankruptcy prediction. The analysis is based on the whole population of Estonian bankrupted and survived SMEs from 2013 to 2017. Logistic regression and multilayer perceptron are used as the prediction methods. The results indicate that closer to bankruptcy, tax arrears’ information yields a higher prediction accuracy than financial ratios. A combined model of tax arrears and financial ratios is more useful than the individual models. The results enable us to outline several theoretical and practical implications.

Download Full-text

ECG Biometrics using RNN and CNN

10.21203/rs.2.22270/v1 ◽

2020 ◽

Author(s):

David Belo ◽

Nuno Bento ◽

Hugo Silva ◽

Ana Fred ◽

Hugo Gamboa

Keyword(s):

Neural Network ◽

High Performance ◽

Deep Neural Networks ◽

State Of The Art ◽

Acquisition Time ◽

Pattern Recognition Problem ◽

Individual Traits ◽

Biometric Systems ◽

The Individual ◽

Electrocardiogram Ecg

Abstract Background: Biometric Systems (BS) are based on a pattern recognition problem where the individual traits of a person are coded and compared. The Electrocardiogram (ECG) as a biometric emerged, as it fulfills the requirements of a BS. Methods: Inspired by the high performance shown by Deep Neural Networks(DNN), this work proposes two architectures to improve current results in both identification and authentication: Temporal Convolutional Neural Network (TCNN) and Recurrent Neural Network (RNN). The last two results weresubmitted to a simple classifier, which exploits the error of prediction of theformer and the scores given by the last. Results: The robustness and applicability of these architectures were tested onFantasia, MIT-BIH and CYBHi databases. The TCNN outperforms the RNNachieving 100%, 96% and 90% of accuracy, respectively, for identification and 0.0%, 0.1% and 2.2% equal error rate for authentication. Conclusions: When comparing to previous work, both architectures reachedresults beyond the state-of-the-art. Even though this experience was a success,the inclusion of these techniques may provide a system that could reduce thevalidation acquisition time.

Download Full-text

Prediction of Prolonged Ventilation after Coronary Artery Bypass Grafting: Data from an Artificial Neural Network

The Heart Surgery Forum ◽

10.1532/hsf.1566 ◽

2017 ◽

Vol 20 (1) ◽

pp. 007 ◽

Cited By ~ 13

Author(s):

Eric Stephen Wise ◽

David P. Stonko ◽

Zachary A. Glaser ◽

Kelly L. Garcia ◽

Jennifer J. Huang ◽

...

Keyword(s):

Neural Network ◽

Mechanical Ventilation ◽

Artificial Neural Network ◽

Logistic Regression ◽

Cardiopulmonary Bypass ◽

Coronary Artery ◽

Early Identification ◽

Artery Bypass ◽

Bypass Grafting ◽

Prolonged Ventilation

Objectives: The need for mechanical ventilation 24 hours after coronary artery bypass grafting (CABG) is considered a morbidity by the Society of Thoracic Surgeons. The purpose of this investigation was twofold: to identify simple preoperative patient factors independently associated with prolonged ventilation and to optimize prediction and early identification of patients prone to prolonged ventilation using an artificial neural network (ANN).Methods: Using the institutional Adult Cardiac Database, 738 patients who underwent CABG since 2005 were reviewed for preoperative factors independently associated with prolonged postoperative ventilation. Prediction of prolonged ventilation from the identified variables was modeled using both “traditional” multiple logistic regression and an ANN. The two models were compared using Pearson r2 and area under the curve (AUC) parameters.Results: Of 738 included patients, 14% (104/738) required mechanical ventilation ≥ 24 hours postoperatively. Upon multivariate analysis, higher body-mass index (BMI; odds ratio [OR] 1.10 per unit, P < 0.001), lower ejection fraction (OR 0.97 per %, P = 0.01) and use of cardiopulmonary bypass (OR 2.59, P = 0.02) were independently predictive of prolonged ventilation. The Pearson r2 and AUC of the multivariate nominal logistic regression model were 0.086 and 0.698 ± 0.05, respectively; analogous statistics of the ANN model were 0.159 and 0.732 ± 0.05, respectively.BMI, ejection fraction and cardiopulmonary bypass represent three simple factors that may predict prolonged ventilation after CABG. Early identification of these patients can be optimized using an ANN, an emerging paradigm for clinical outcomes modeling that may consider complex relationships among these variables.

Download Full-text

МЕТОДЫ ДОСТИЖЕНИЯ МАКСИМАЛЬНОЙ ЭФФЕКТИВНОСТИ ПЛАТФОРМЫ ПРОТОТИПИРОВАНИЯ ВЫСОКОПРОИЗВОДИТЕЛЬНЫХ СИСТЕМ НА КРИСТАЛЛЕ НА ЗАДАЧАХ ИСКУССТВЕННОГО ИНТЕЛЛЕКТА

Nanoindustry Russia ◽

10.22184/1993-8578.2020.13.3s.585.588 ◽

2020 ◽

Vol 96 (3s) ◽

pp. 585-588

Author(s):

С.Е. Фролова ◽

Е.С. Янакова

Keyword(s):

Neural Network ◽

Artificial Intelligence ◽

Computer Vision ◽

High Performance ◽

Systems On Chip ◽

High Performance Systems ◽

On Chip ◽

Network Technologies ◽

Neural Network Technologies

Предлагаются методы построения платформ прототипирования высокопроизводительных систем на кристалле для задач искусственного интеллекта. Изложены требования к платформам подобного класса и принципы изменения проекта СнК для имплементации в прототип. Рассматриваются методы отладки проектов на платформе прототипирования. Приведены результаты работ алгоритмов компьютерного зрения с использованием нейросетевых технологий на FPGA-прототипе семантических ядер ELcore. Methods have been proposed for building prototyping platforms for high-performance systems-on-chip for artificial intelligence tasks. The requirements for platforms of this class and the principles for changing the design of the SoC for implementation in the prototype have been described as well as methods of debugging projects on the prototyping platform. The results of the work of computer vision algorithms using neural network technologies on the FPGA prototype of the ELcore semantic cores have been presented.

Download Full-text

Improving Efficiency in Robot Assisted Belt Grinding of High Performance Materials

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.907.139 ◽

2014 ◽

Vol 907 ◽

pp. 139-149 ◽

Cited By ~ 3

Author(s):

Eckart Uhlmann ◽

Florian Heitmüller

Keyword(s):

Gas Turbines ◽

High Performance ◽

Scale Effects ◽

Turbine Blades ◽

Repair Process ◽

Industrial Robots ◽

Robot Assisted ◽

Belt Grinding ◽

Economy Of Scale ◽

The Individual

In gas turbines and turbo jet engines, high performance materials such as nickel-based alloys are widely used for blades and vanes. In the case of repair, finishing of complex turbine blades made of high performance materials is carried out predominantly manually. The repair process is therefore quite time consuming. And the costs of presently available repair strategies, especially for integrated parts, are high, due to the individual process planning and great amount of manually performed work steps. Moreover, there are severe risks of partial damage during manually conducted repair. All that leads to the fact that economy of scale effects remain widely unused for repair tasks, although the piece number of components to be repaired is increasing significantly. In the future, a persistent automation of the repair process chain should be achieved by developing adaptive robot assisted finishing strategies. The goal of this research is to use the automation potential for repair tasks by developing a technology that enables industrial robots to re-contour turbine blades via force controlled belt grinding.

Download Full-text

A comprehensive study on statistical prediction and reduction of tire/road noise

Journal of Vibration and Control ◽

10.1177/10775463211013184 ◽

2021 ◽

pp. 107754632110131

Author(s):

Somaye Mohammadi ◽

Abdolreza Ohadi ◽

Mostafa Irannejad-Parizi

Keyword(s):

Neural Network ◽

Road Transport ◽

Relevance Vector Machine ◽

Statistical Investigation ◽

Statistical Prediction ◽

Support Vector ◽

Prediction Ability ◽

Vector Method ◽

Tire Noise ◽

Rolling Noise

Promoting safe tires with low external rolling noise increases the environmental efficiency of road transport. Although tire builders have been striving to reduce emitted noise, the issue’s sophisticated nature has made it difficult. This article aims to make the problem straightforward, relying on recent significant improvements in statistical science. In this regard, the prediction ability of new methods in this field, including support vector machine, relevance vector machine, and convolutional neural network, along with the new architecture of the neural network is compared. Tire noise is measured under the coast-by condition. Two training strategies are proposed: extracting features from a tread pattern image and directly importing an image to the model. The relevance vector method, which is trained using the first strategy, has provided the most accurate results with an error of 0.62 dB(A) in predicting the total noise level. This precise model is used instead of experimentation to analyze the sensitivity of tire noise to its parameters using a small central composite design. The parametric study reveals striking tips for reducing noise, especially in terms of interactions between parameters that have not previously been shown. Finally, a novel two-stage approach for reducing noise by tread pattern optimization is proposed, inspired by two regression models derived from statistical investigation and variance analysis. Changes in tread pattern specifications of two case studies and their randomization have resulted in a reduction of 3.2 dB(A) for a high-noise tire and 0.4 dB(A) decrement for a quieter tire.

Download Full-text

Adaptive Precision Block-Jacobi for High Performance Preconditioning in the Ginkgo Linear Algebra Software

ACM Transactions on Mathematical Software ◽

10.1145/3441850 ◽

2021 ◽

Vol 47 (2) ◽

pp. 1-28

Author(s):

Goran Flegar ◽

Hartwig Anzt ◽

Terry Cojean ◽

Enrique S. Quintana-Ortí

Keyword(s):

Linear Algebra ◽

Graphics Processing Units ◽

High Performance ◽

Numerical Algorithms ◽

Mixed Precision ◽

Before And After ◽

Memory Accesses ◽

Specialized Hardware ◽

The Individual ◽

Graphics Processing

The use of mixed precision in numerical algorithms is a promising strategy for accelerating scientific applications. In particular, the adoption of specialized hardware and data formats for low-precision arithmetic in high-end GPUs (graphics processing units) has motivated numerous efforts aiming at carefully reducing the working precision in order to speed up the computations. For algorithms whose performance is bound by the memory bandwidth, the idea of compressing its data before (and after) memory accesses has received considerable attention. One idea is to store an approximate operator–like a preconditioner–in lower than working precision hopefully without impacting the algorithm output. We realize the first high-performance implementation of an adaptive precision block-Jacobi preconditioner which selects the precision format used to store the preconditioner data on-the-fly, taking into account the numerical properties of the individual preconditioner blocks. We implement the adaptive block-Jacobi preconditioner as production-ready functionality in the Ginkgo linear algebra library, considering not only the precision formats that are part of the IEEE standard, but also customized formats which optimize the length of the exponent and significand to the characteristics of the preconditioner blocks. Experiments run on a state-of-the-art GPU accelerator show that our implementation offers attractive runtime savings.

Download Full-text

Using Convolutional Neural Network and Candlestick Representation to Predict Sports Match Outcomes

Applied Sciences ◽

10.3390/app11146594 ◽

2021 ◽

Vol 11 (14) ◽

pp. 6594

Author(s):

Yu-Chia Hsu

Keyword(s):

Neural Network ◽

Time Series ◽

Pattern Recognition ◽

Logistic Regression ◽

Regression Model ◽

Convolutional Neural Network ◽

Logistic Regression Model ◽

National Football League ◽

Performance Metrics ◽

Betting Market

The interdisciplinary nature of sports and the presence of various systemic and non-systemic factors introduce challenges in predicting sports match outcomes using a single disciplinary approach. In contrast to previous studies that use sports performance metrics and statistical models, this study is the first to apply a deep learning approach in financial time series modeling to predict sports match outcomes. The proposed approach has two main components: a convolutional neural network (CNN) classifier for implicit pattern recognition and a logistic regression model for match outcome judgment. First, the raw data used in the prediction are derived from the betting market odds and actual scores of each game, which are transformed into sports candlesticks. Second, CNN is used to classify the candlesticks time series on a graphical basis. To this end, the original 1D time series are encoded into 2D matrix images using Gramian angular field and are then fed into the CNN classifier. In this way, the winning probability of each matchup team can be derived based on historically implied behavioral patterns. Third, to further consider the differences between strong and weak teams, the CNN classifier adjusts the probability of winning the match by using the logistic regression model and then makes a final judgment regarding the match outcome. We empirically test this approach using 18,944 National Football League game data spanning 32 years and find that using the individual historical data of each team in the CNN classifier for pattern recognition is better than using the data of all teams. The CNN in conjunction with the logistic regression judgment model outperforms the CNN in conjunction with SVM, Naïve Bayes, Adaboost, J48, and random forest, and its accuracy surpasses that of betting market prediction.

Download Full-text