43 Hits in 6.2 sec

A Systematic Literature Review of Intelligent Data Analysis Methods for Smart Sport Training

Alen Rajšp, Iztok Fister Fister
2020 Applied Sciences  
Sport domains in which SST is already used are presented, and phases of training are identified, together with the maturity of SST methods.  ...  Intelligent data analysis methods are presented, which are currently used in the field of Smart Sport Training (SST).  ...  The system proposes varied objectives, without repeating the lessons to trainers, via the utilization same exercises. of case-based reasoning. [130] Archery SVM Predicting the class of archers based Archers  ... 
doi:10.3390/app10093013 fatcat:mjdbbec6orb6rlk2zbgmzqjcfa

Machine and deep learning for sport-specific movement recognition: a systematic review of model development and performance

Emily E Cust, Alice J Sweeting, Kevin Ball, Sam Robertson
2018 Journal of Sports Sciences  
A kernel form of the Support Vector Machine algorithm was used in 53% of IMU and 50% of vision-based studies.  ...  The implementation of automated detection and recognition of sport-specific movements overcomes the limitations associated with manual performance analysis methods.  ...  A review on human activity 1027 recognition using vision-based method. Journal of Healthcare Engineering, 2017, 1-31.  ... 
doi:10.1080/02640414.2018.1521769 pmid:30307362 fatcat:h3flbavuivbilbo6ekwvmnjg6i

Using Opponent Modeling to Adapt Team Play in American Football [chapter]

Kennard R. Laviers, Gita Sukthankar
2014 Plan, Activity, and Intent Recognition  
In this chapter, we introduce several methods for using opponent modeling, in the form of predictions about the players' physical movements, to learn team policies.  ...  An issue with learning effective policies in multi-agent adversarial games is that the size of the search space can be prohibitively large when the actions of both teammates and opponents are considered  ...  The views expressed in this document are those of the authors and do not reflect the official policy or position of the United States Air Force, Department of Defense, or the U.S. Government.  ... 
doi:10.1016/b978-0-12-398532-3.00013-0 fatcat:obft3365vrhvnkmi6ho75ycpwm

Basketball Activity Recognition using Wearable Inertial Measurement Units

Le Nguyen Ngu Nguyen, Daniel Rodríguez-Martín, Andreu Català, Carlos Pérez-López, Albert Samà, Andrea Cavallaro
2015 Proceedings of the XVI International Conference on Human Computer Interaction - Interacción '15  
Camera-based techniques are the most spread method to evaluate although frequently this method can be cumbersome and, furthermore, specific movements where performance is analyzed are not possible to distinguish  ...  Analysis of human movement is a growing research area within the field of sport monitoring which aims to enhance the performance of athletes, predicting injuries or optimizing training programs.  ...  We use LibSVM library [16] to implement the multi-class SVM classifier. In Figure 7 , the actual and predicted labels of standing and moving of one player are depicted.  ... 
doi:10.1145/2829875.2829930 dblp:conf/interaccion/NguyenMCPSC15 fatcat:pn6jneg7wrbabgrcbwyui4uvm4

A Study of Vision based Human Motion Recognition and Analysis

Geetanjali Vinayak Kale, Varsha Hemant Patil
2016 International Journal of Ambient Computing and Intelligence (IJACI)  
The paper emphasizes on human motion representation and the recognition methods along with their advantages and disadvantages.  ...  Vision based human motion recognition has fascinated many researchers due to its critical challenges and a variety of applications.  ...  Complicated action requires multi layered approaches. Detailed discussion of recognition methods is given in section 3.4.  ... 
doi:10.4018/ijaci.2016070104 fatcat:doyiyb2fizh75dntg6kvmqoqey

A Novice Guide towards Human Motion Analysis and Understanding [article]

Ahmed Nabil Mohamed
2015 arXiv   pre-print
on those that can be useful for computer vision researchers.  ...  The purpose of this article is to shed some light on this very important subject, so it can be a good insight for a novice computer vision researcher in this field by providing him/her with a wealth of  ...  Examples of pattern-recognition methods include SVM, nearest neighbor, neural networks, and boosting.  ... 
arXiv:1509.01074v1 fatcat:kpqf277iw5f2bmlmog2ya2awci

Soft computing in intrusion detection: the state of the art

Chet Langin, Shahram Rahimi
2010 Journal of Ambient Intelligence and Humanized Computing  
The state of the art is explored in using soft computing (SC) methods for network intrusion detection, including the examination of efforts in ten specific areas of SC as well as consecutive, ensemble,  ...  Numerous comparisons of these methods are listed followed by a recommendation for future research. This paper can be used as a reference of strategies, and as a resource for planning future research.  ...  , Recognition, Substitution, and Rejection rates (RSR), the Predictive Rate Method (PRM), and Rogova's Class Level Method.  ... 
doi:10.1007/s12652-010-0012-4 fatcat:itlsb2cjm5aybgb6b2a4mmc4o4

Activity representation with motion hierarchies

Adrien Gaidon, Zaid Harchaoui, Cordelia Schmid
2013 International Journal of Computer Vision  
We show that pervideo hierarchies provide additional information for activity recognition.  ...  We provide an efficient positive definite kernel that computes the structural and visual similarity of two hierarchical decompositions by relying on models of their parent-child relations.  ...  Acknowledgements This work was partially funded by the MSR/INRIA joint project, the European integrated project AXES, the PASCAL 2 Network of Excellence, the Gargantua project under program Mastodons of  ... 
doi:10.1007/s11263-013-0677-1 fatcat:hwagpdkv4jgxfmb7flr5n4m6ny

Wearable Sensing for Solid Biomechanics

Charence Wong, Zhiqiang Zhang, Benny Ping Lai Lo, Guang-Zhong Yang
2015 IEEE Sensors Journal  
methods, and different methods for reducing the impact of these sources of errors are described in this review.  ...  Conventional laboratorybased biomechanical analysis systems and observation-based tests are only designed to capture brief snapshots of the mechanics of movement.  ...  Thus far, model constraints based methods and multi sensor-based methods have been proposed to further reduce drift, while interference estimation based solutions and noise adjustment methods have also  ... 
doi:10.1109/jsen.2015.2393883 fatcat:sgnyhgnafjhk5ozq4tmvwzbemq

Understanding web images by object relation network

Na Chen, Qian-Yi Zhou, Viktor Prasanna
2012 Proceedings of the 21st international conference on World Wide Web - WWW '12  
This paper presents an automatic method for understanding and interpreting the semantics of unannotated web images.  ...  We present an automatic system which takes a raw image as input and creates an ORN based on image visual appearance and the guide ontology.  ...  Thus we can train a multi-class classifier (based on object visual features) to assign a classification score for each category, and apply the calibration method proposed in [30] to transform these scores  ... 
doi:10.1145/2187836.2187876 dblp:conf/www/ChenZP12 fatcat:j4dod4u6dfhopg4mfkgj7tq3qq

Review of Wearable Devices and Data Collection Considerations for Connected Health

Vini Vijayan, James Connolly, Joan Condell, Nigel McKelvey, Philip Gardiner
2021 Sensors  
The volume of data collected by wearable sensors during long-term assessment of ambulatory movement can become immense in tuple size.  ...  These assessments are time consuming and costly and depend on subjective patient recall. Moreover, measurements may not accurately demonstrate the patient's functional ability whilst at home.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s21165589 pmid:34451032 pmcid:PMC8402237 fatcat:qubolay6wjb35orvkwtunwz7e4

Unrestricted Bridging Resolution

Yufang Hou, Katja Markert, Michael Strube
2018 Computational Linguistics  
However, most of them only consider antecedent selection, assuming that bridging anaphora recognition has been performed.  ...  The problem addressed in this thesis is based on her work during her visiting stay at HITS as a Humboldt scholarship holder. She closely guided me in my first year at HITS.  ...  This two-stage model significantly outperforms a pairwise model and a reimplementation of a previous rule-based system.  ... 
doi:10.1162/coli_a_00315 fatcat:ezgwhbvbrffi5jgx3edhigvx4a

North American Society for the Psychology of Sport and Physical Activity Virtual Conference June 9-11, 2021

2021 Journal of Sport & Exercise Psychology (JSEP)  
Learning of movements benefits from two parallel brain mechanisms: one that has access to explicit knowledge and benefits from coaching, and another that relies on implicit, unconscious correction.  ...  However, it is unclear how these systems interact: does enhancing one system's contributions, for example through instruction, impair the other, or do they learn independently?  ...  Coaches' Influence on Team Dynamics in  ... 
doi:10.1123/jsep.2021-0103 fatcat:6add57uuzja2pcd2qbkc6s5zei

Autonomous Driving in Adverse Weather Conditions: A Survey [article]

Yuxiao Zhang, Alexander Carballo, Hanting Yang, Kazuya Takeda
2021 arXiv   pre-print
State-of-the-art techniques on perception enhancement with regard to each kind of weather are thoroughly reported.  ...  a holistic overview on the obstacles and directions of ADS development in terms of adverse weather driving conditions.  ...  The highlight of this technique to do multi-class weather classification based sensor is that even with contamination like sawdust ad- on the pre-training of multi-class weather recognition  ... 
arXiv:2112.08936v1 fatcat:hmgjhywy7rgx3fgrk6yxnu56ie

A Multi-Lingually Applicable Journalist Toolset For The Big-Data Era

G. Kiomourtzis, G. Giannakopoulos, V. Karkaletsis, A. Kosmopoulos
2016 Zenodo  
This research was supported in part by a Discovery and Innovation Research Seed award from the Office of the Vice Provost for Research at Cornell.  ...  The project Digitale Kuratierungstechnologien is supported by the German Federal Ministry of Education and Research, Unternehmen Region, Wachstumskern-Potenzial (No. 03WKP45).  ...  The method we described is based on statistical analysis of words distributions over epochs reflected on the Romanian printing press and a statistical classifier, SVM, for each epoch.  ... 
doi:10.5281/zenodo.1242850 fatcat:nfkqg7jhjffdvgezdjzc6xxppa
« Previous Showing results 1 — 15 out of 43 results