scholarly journals Using Wearable Sensors and a Convolutional Neural Network for Catch Detection in American Football

Sensors ◽  
2020 ◽  
Vol 20 (23) ◽  
pp. 6722
Author(s):  
Bernhard Hollaus ◽  
Sebastian Stabinger ◽  
Andreas Mehrle ◽  
Christian Raschner
Keyword(s):  
Neural Network ◽  
Degrees Of Freedom ◽  
Wearable Sensors ◽  
Professional Sports ◽  
American Football ◽  
Data Logging ◽  
Sensor Platform ◽  
Magnetometer Data ◽  
Audio Data ◽  
New Type

Highly efficient training is a must in professional sports. Presently, this means doing exercises in high number and quality with some sort of data logging. In American football many things are logged, but there is no wearable sensor that logs a catch or a drop. Therefore, the goal of this paper was to develop and verify a sensor that is able to do exactly that. In a first step a sensor platform was used to gather nine degrees of freedom motion and audio data of both hands in 759 attempts to catch a pass. After preprocessing, the gathered data was used to train a neural network to classify all attempts, resulting in a classification accuracy of 93%. Additionally, the significance of each sensor signal was analysed. It turned out that the network relies most on acceleration and magnetometer data, neglecting most of the audio and gyroscope data. Besides the results, the paper introduces a new type of dataset and the possibility of autonomous training in American football to the research community.

scholarly journals Studying the Potential of Graphcore® IPUs for Applications in Particle Physics

2021 ◽  
Vol 5 (1) ◽  
Author(s):  
Samuel Maddrell-Mander ◽  
Lakshan Ram Madhan Mohan ◽  
Alexander Marshall ◽  
Daniel O’Hanlon ◽  
Konstantinos Petridis ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Kalman Filter ◽  
Particle Physics ◽  
Processing Unit ◽  
Network Architectures ◽  
Track Reconstruction ◽  
Event Simulation ◽  
Scattering Correction ◽  
New Type

AbstractThis paper presents the first study of Graphcore’s Intelligence Processing Unit (IPU) in the context of particle physics applications. The IPU is a new type of processor optimised for machine learning. Comparisons are made for neural-network-based event simulation, multiple-scattering correction, and flavour tagging, implemented on IPUs, GPUs and CPUs, using a variety of neural network architectures and hyperparameters. Additionally, a Kálmán filter for track reconstruction is implemented on IPUs and GPUs. The results indicate that IPUs hold considerable promise in addressing the rapidly increasing compute needs in particle physics.

scholarly journals Dark Photon Searches at BESIII

2018 ◽  
Vol 46 ◽  
pp. 1860046 ◽  
Author(s):  
Dayong Wang
Keyword(s):  
Degrees Of Freedom ◽  
New Physics ◽  
Beyond The Standard Model ◽  
Gauge Bosons ◽  
Data Set ◽  
Decay Modes ◽  
Dark Photon ◽  
The Standard Model ◽  
New Type ◽  
Low Mass

Many models beyond the Standard Model, motivated by the recent astrophysical anomalies, predict a new type of weak-interacting degrees of freedom. Typical models include the possibility of the low-mass dark gauge bosons of a few GeV and thus making them accessible at the BESIII experiment running at the tau-charm region. The BESIII has recently searched such dark bosons in several decay modes using the high statistics data set collected at charmonium resonaces. This talk will summarize the recent BESIII results of these dark photon searches and related new physics studies.

scholarly journals Generalization of Patterns by Identification with Polynomial Neural Network

2010 ◽  
Vol 61 (2) ◽  
pp. 120-124 ◽  
Author(s):  
Ladislav Zjavka
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Functional Dependence ◽  
Polynomial Neural Network ◽  
New Type ◽  
Input Variables ◽  
The Brain ◽  
Functional Output ◽  
Simplified Form

Generalization of Patterns by Identification with Polynomial Neural Network Artificial neural networks (ANN) in general classify patterns according to their relationship, they are responding to related patterns with a similar output. Polynomial neural networks (PNN) are capable of organizing themselves in response to some features (relations) of the data. Polynomial neural network for dependence of variables identification (D-PNN) describes a functional dependence of input variables (not entire patterns). It approximates a hyper-surface of this function with multi-parametric particular polynomials forming its functional output as a generalization of input patterns. This new type of neural network is based on GMDH polynomial neural network and was designed by author. D-PNN operates in a way closer to the brain learning as the ANN does. The ANN is in principle a simplified form of the PNN, where the combinations of input variables are missing.

scholarly journals Design of a 2DoF Ankle Exoskeleton with a Polycentric Structure and a Bi-Directional Tendon-Driven Actuator Controlled Using a PID Neural Network

Actuators ◽  
2021 ◽  
Vol 10 (1) ◽  
pp. 9
Author(s):  
Taehoon Lee ◽  
Inwoo Kim ◽  
Yoon Su Baek
Keyword(s):  
Neural Network ◽  
Degrees Of Freedom ◽  
Plantar Flexion ◽  
Length Change ◽  
Talocrural Joint ◽  
Lower Limb Exoskeleton ◽  
Exoskeleton Robot ◽  
The Difference ◽  
Ankle Exoskeleton ◽  
The Stability

Lower limb exoskeleton robots help with walking movements through mechanical force, by identifying the wearer’s walking intention. When the exoskeleton robot is lightweight and comfortable to wear, the stability of walking increases, and energy can be used efficiently. However, because it is difficult to implement the complex anatomical movements of the human body, most are designed simply. Due to this, misalignment between the human and robot movement causes the wearer to feel uncomfortable, and the stability of walking is reduced. In this paper, we developed a two degrees of freedom (2DoF) ankle exoskeleton robot with a subtalar joint and a talocrural joint, applying a four-bar linkage to realize the anatomical movement of a simple 1DoF structure mainly used for ankles. However, bidirectional tendon-driven actuators (BTDAs) do not consider the difference in a length change of both cables due to dorsiflexion (DF) and plantar flexion (PF) during walking, causing misalignment. To solve this problem, a BTDA was developed by considering the length change of both cables. Cable-driven actuators and exoskeleton robot systems create uncertainty. Accordingly, adaptive control was performed with a proportional-integral-differential neural network (PIDNN) controller to minimize system uncertainty.

A New Type of a Wavelet Neural Network

2018 ◽  
Vol 27 (3) ◽  
pp. 152-160 ◽  
Author(s):  
A. Efitorov ◽  
S. Dolenko
Keyword(s):  
Neural Network ◽  
Wavelet Neural Network ◽  
New Type

scholarly journals The Use of LEDBased Digital Optical Ministicks as MultiFunctional Controls for Unified HumanMachine Interfaces

2018 ◽  
pp. 188-193
Author(s):  
Sergey A. Golubin ◽  
Vladimir S. Nikitin ◽  
Roman B. Belov
Keyword(s):  
Remote Control ◽  
Degrees Of Freedom ◽  
Light Emitting Diodes ◽  
System Control ◽  
Visual Contact ◽  
Light Emitting ◽  
Comparison Results ◽  
New Type ◽  
Scientific Task ◽  
Control Devices

The active development of robotics requires increasingly complex remote control devices. The remote control devices are increasingly large, complex, and expensive. They decrease economic efficiency of robotics and increase their price. The scientific task is the research into possibility of applying optical ministicks on the basis of light emitting diodes as the new type basic multifunctional controls of unified human­machine interfaces allowing us to control commonly known robotic equipment types using identical devices. During the research original ergonomic methods of purposeful combination of two ministicks on two actuating levers were used so that to provide convenience of tactile control of various robots without visual contact with controls. As a result of the research, new controls were created and patented. They became known as “polyjoysticks” (patent of Russian Federation No. 2497177) and allow controlling engineering facilities having up to 20 degrees of freedom which exceeds the similar parameters of known controls by factor of 3 to 5. Due to combined use of optical ministicks, two polyjoysticks and a video mask, a new generalpurpose generation humanmachine interface was created. It allows controlling various robots and vehicles, from tractor to aircraft. The discussion of the obtained results was carried out by comparing them with parameters of control panels of different robotics systems. The analysis of the comparison results has shown that the controls based on polyjoysticks and digital optical ministicks on the basis of light emitting diodes have the best indices in terms of implemented among known control devices, in terms of ratio of functionality to weight and volume of the devices. New interfaces have already been applied for developing multiagent robotic system control system for fire forest extinguishing.

scholarly journals Control Strategies for Gait Tele-Rehabilitation System Based on Parallel Robotics

2021 ◽  
Vol 11 (23) ◽  
pp. 11095
Author(s):  
Antonio P. L. Bo ◽  
Leslie Casas ◽  
Gonzalo Cucho-Padin ◽  
Mitsuhiro Hayashibe ◽  
Dante Elias
Keyword(s):  
Degrees Of Freedom ◽  
Control Strategies ◽  
Subjective Evaluation ◽  
Wearable Sensors ◽  
Movement Data ◽  
Trunk Inclination ◽  
Limited Degree ◽  
Parallel Robotics ◽  
Limb Rehabilitation ◽  
Technical Capacity

Among end-effector robots for lower limb rehabilitation, systems based on Stewart–Gough platforms enable independent movement of each foot in six degrees of freedom. Nevertheless, control strategies described in recent literature have not been able to fully explore the potential of such a mechatronic system. In this work, we propose two novel approaches for controlling a gait simulator based on Stewart–Gough platforms. The first strategy provides the therapist direct control of each platform using movement data measured by wearable sensors. The following scheme is designed to improve the level of engagement of the patient by enabling a limited degree of control based on trunk inclination. Both strategies are designed to facilitate future studies in tele-rehabilitation settings. Experimental results have illustrated the feasibility of both control interfaces, either in terms of system performance or user subjective evaluation. Technical capacity to deploy in tele-rehabilitation was also verified in this work.

scholarly journals “Take a Knee” Protests in Professional Sports: An Empirical Study about the Influence on Customer Loyalty to Nike in Germany

2020 ◽  
Vol 4 (1) ◽  
pp. 92-105
Author(s):  
Carsten Giebe ◽  
Lana Löffler ◽  
Sandra Schneider
Keyword(s):  
San Francisco ◽  
Customer Loyalty ◽  
Relevant Literature ◽  
Professional Sports ◽  
The United States ◽  
American Football ◽  
Literary Sources ◽  
Marketing Activities ◽  
Sporting Goods ◽  
The Impact

The article deals with the research of opportunities and prospects to use “Take a knee” protest in professional sports for Nike marketing purposes in terms of influencing customer loyalty to that brand. The action “Take a knee” became widely known in 2016, when the coloured quarterback of the San Francisco 49ers, Colin Kaepernick, knelt in protest while singing the national anthem of the United States of America before several games to denounce police violence against blacks and coloured people. In 2017 the European community for professional sports firstly supported that action, when Hertha BSC’s Bundesliga team went down on their knees before the kick-off of a Bundesliga game to demonstrate for diversity, tolerance and responsibility. Since Hertha BSC is equipped with the sporting goods of Nike manufacturer, the article suggested and tested the hypothesis that “Take a knee” could have an impact on customer loyalty growth to the Nike brand. The systematization of the relevant literature sources and approaches to study the demand for sports goods indicates the lack of comprehensive research on the analysis regarding the impact of the atypical advertising measures on consumer behaviour. Based on the systematization of literary sources, the article identifies the controversy of marketing activities with people who engage in politics. Furthermore, the article defines the moral role of individual athletes or teams of different sports using the example of American football and football (also known as soccer). The methodological basis of the study was analytical and comparative methods, methods of analysis, synthesis, and logical generalization. The paper presents the results of an empirical analysis based on a survey of potential customers of sporting goods in Germany in early 2020 with a sample size of 135 respondents. The authors substantiate the importance of continuous and systematic work by the advertising companies aimed at attracting famous people who are politically engaged in advertising companies as a guarantee of increasing customer loyalty. The results of the study can be useful for both business and advertising companies in terms of the choice of marketing communication tools between manufacturer and customer. Keywords: advertising, business ethics, competitiveness, customer loyalty, marketing, Nike, sport and politics, Take a Knee.

scholarly journals A Novel Neural Network Model for Blood Pressure Estimation Using Photoplethesmography without Electrocardiogram

2018 ◽  
Vol 2018 ◽  
pp. 1-9 ◽  
Author(s):  
Ludi Wang ◽  
Wei Zhou ◽  
Ying Xing ◽  
Xiaoguang Zhou
Keyword(s):  
Neural Network ◽  
Blood Pressure ◽  
Mean Absolute Error ◽  
Wearable Sensors ◽  
Absolute Error ◽  
Noninvasive Estimation ◽  
Treatment Of Hypertension ◽  
The Mean ◽  
Artificial Neural Network Ann ◽  
Blood Pressure Estimation

The prevention, evaluation, and treatment of hypertension have attracted increasing attention in recent years. As photoplethysmography (PPG) technology has been widely applied to wearable sensors, the noninvasive estimation of blood pressure (BP) using the PPG method has received considerable interest. In this paper, a method for estimating systolic and diastolic BP based only on a PPG signal is developed. The multitaper method (MTM) is used for feature extraction, and an artificial neural network (ANN) is used for estimation. Compared with previous approaches, the proposed method obtains better accuracy; the mean absolute error is 4.02 ± 2.79 mmHg for systolic BP and 2.27 ± 1.82 mmHg for diastolic BP.

Sign in / Sign up

Export Citation Format

Share Document