Simulation of sports movement training based on machine learning and brain-computer interface

2020 ◽  
pp. 1-12
Author(s):  
Linuo Wang

Injuries and hidden dangers in training have a greater impact on athletes ’careers. In particular, the brain function that controls the motor function area has a greater impact on the athlete ’s competitive ability. Based on this, it is necessary to adopt scientific methods to recognize brain functions. In this paper, we study the structure of motor brain-computer and improve it based on traditional methods. Moreover, supported by machine learning and SVM technology, this study uses a DSP filter to convert the preprocessed EEG signal X into a time series, and adjusts the distance between the time series to classify the data. In order to solve the inconsistency of DSP algorithms, a multi-layer joint learning framework based on logistic regression model is proposed, and a brain-machine interface system of sports based on machine learning and SVM is constructed. In addition, this study designed a control experiment to improve the performance of the method proposed by this study. The research results show that the method in this paper has a certain practical effect and can be applied to sports.

2020 ◽  
Vol 30 (6) ◽  
pp. 063116 ◽  
Author(s):  
Yu Huang ◽  
Zuntao Fu ◽  
Christian L. E. Franzke

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Sergio Martin del Campo Barraza ◽  
William Lindskog ◽  
Davide Badalotti ◽  
Oskar Liew ◽  
Arash Toyser

Data-based models built using machine learning solutions are becoming more prominent in the condition monitoring, maintenance, and prognostics fields. The capacity to build these models using a machine learning approach depends largely in the quality of the data. Of particular importance is the availability of labelled data, which describes the conditions that are intended to be identified. However, properly labelled data that is useful in many machine learning strategies is a scare resource. Furthermore, producing high-quality labelled data is expensive, time-consuming and a lot of times inaccurate given the uncertainty surrounding the labeling process and the annotators.  Active Learning (AL) has emerged as a semi-supervised approach that enables cost and time reductions of the labeling process. This approach has had a delayed adoption for time series classification given the difficulty to extract and present the time series information in such a way that it is easy to understand for the human annotator who incorporates the labels. This difficulty arises from the large dimensionality that many of these time series possess. This challenge is exacerbated by the cold-start problem, where the initial labelled dataset used in typical AL frameworks may not exist. Thus, the initial set of labels to be allocated to the time series samples is not available. This last challenge is particularly common on many condition monitoring applications where data samples of specific faults or problems does not exist. In this article, we present an AL framework to be used in the classification of time series from industrial process data, in particular vibration waveforms originated from condition monitoring applications. In this framework, we deal with the absence of labels to train an initial classification model by introducing a pre-clustering step. This step uses an unsupervised clustering algorithm to identify the number of labels and selects the points with a stronger group belonging as initial samples to be labelled in the active learning step. Furthermore, this framework presents two approaches to present the information to the annotator that can be via time-series imaging and automatic extraction of statistical features. Our work is motivated by the interest to facilitate the effort required for labeling time-series waveforms, while maintaining a high level of accuracy and consistency on those labels. In addition, we study the number of time-series samples that require to be labelled to achieve different levels of classification accuracy, as well as their confidence intervals. These experiments are carried out using vibration signals from a well-known rolling element bearing dataset and typical process data from a production plant.   An active learning framework that considers the conditions of the data commonly found in maintenance and condition monitoring applications while presenting the data in ways easy to interpret by human annotators can facilitate the generation reliable datasets. These datasets can, in turn, assist in the development of data-driven models that describe the many different processes that a machine undergoes.


2021 ◽  
Author(s):  
Martijn Witjes ◽  
Leandro Parente ◽  
Chris J. van Diemen ◽  
Tomislav Hengl ◽  
Martin Landa ◽  
...  

Abstract A seamless spatiotemporal machine learning framework for automated prediction, uncertainty assessment, and analysis of land use / land cover (LULC) dynamics is presented. The framework includes: (1) harmonization and preprocessing of high-resolution spatial and spatiotemporal covariate datasets (GLAD Landsat, NPP/VIIRS) including 5 million harmonized LUCAS and CORINE Land Cover-derived training samples, (2) model building based on spatial k-fold cross-validation and hyper-parameter optimization, (3) prediction of the most probable class, class probabilities and uncertainty per pixel, (4) LULC change analysis on time-series of produced maps. The spatiotemporal ensemble model was fitted by combining random forest, gradient boosted trees, and artificial neural network, with logistic regressor as meta-learner. The results show that the most important covariates for mapping LULC in Europe are: seasonal aggregates of Landsat green and near-infrared bands, multiple Landsat-derived spectral indices, and elevation. Spatial cross-validation of the model indicates consistent performance across multiple years with 62%, 70%, and 87% accuracy when predicting 33 (level-3), 14 (level-2), and 5 classes (level-1); with artificial surface classes such as 'airports' and 'railroads' showing the lowest match with validation points. The spatiotemporal model outperforms spatial models on known-year classification by 2.7% and unknown-year classification by 3.5%. Results of the accuracy assessment using 48,365 independent test samples shows 87% match with the validation points. Results of time-series analysis (time-series of LULC probabilities and NDVI images) suggest gradual deforestation trends in large parts of Sweden, the Alps, and Scotland. An advantage of using spatiotemporal ML is that the fitted model can be used to predict LULC in years that were not included in its training dataset, allowing generalization to past and future periods, e.g. to predict land cover for years prior to 2000 and beyond 2020. The generated land cover time-series data stack (ODSE-LULC), including the training points, is publicly available via the Open Data Science (ODS)-Europe Viewer.


2021 ◽  
Author(s):  
Martijn Witjes ◽  
Leandro Parente ◽  
Chris J. van Diemen ◽  
Tomislav Hengl ◽  
Martin Landa ◽  
...  

Abstract A seamless spatiotemporal machine learning framework for automated prediction, uncertainty assessment, and analysis of long-term LULC dynamics is presented. The framework includes: (1) harmonization and preprocessing of high-resolution spatial and spatiotemporal input datasets (GLAD Landsat, NPP/VIIRS) including 5~million harmonized LUCAS and CORINE Land Cover-derived training samples, (2) model building based on spatial k-fold cross-validation and hyper-parameter optimization, (3) prediction of the most probable class, class probabilities and uncertainty per pixel, (4) LULC change analysis on time-series of produced maps. The spatiotemporal ensemble model consists of a random forest, gradient boosted tree classifier, and a artificial neural network, with a logistic regressor as meta-learner. The results show that the most important variables for mapping LULC in Europe are: seasonal aggregates of Landsat green and near-infrared bands, multiple Landsat-derived spectral indices, long-term surface water probability, and elevation. Spatial cross-validation of the model indicates consistent performance across multiple years with overall accuracy (weighted F1-score) of 0.49, 0.63, and 0.83 when predicting 44 (level-3), 14 (level-2), and 5 classes (level-1). The spatiotemporal model outperforms spatial models on known-year classification by 2.7% and unknown-year classification by 3.5%. Results of the accuracy assessment using 48,365 independent test samples shows 87% match with the validation points. Results of time-series analysis (time-series of LULC probabilities and NDVI images) suggest forest loss in large parts of Sweden, the Alps, and Scotland. An advantage of using spatiotemporal ML is that the fitted model can be used to predict LULC in years that were not included in its training dataset, allowing generalization to past and future periods, e.g. to predict land cover for years prior to 2000 and beyond 2020. The generated land cover time-series data stack (ODSE-LULC), including the training points, is publicly available via the Open Data Science (ODS)-Europe Viewer. Functions used to prepare data and run modeling are available via the eumap library for python.


Author(s):  
Paul Gilmore

This chapter examines Poe’s exploration of how the human brain functions in his critical essays and tales. It locates his ideas concerning the brain’s functions within mid-nineteenth-century theories about the mind and the brain, specifically phrenology, and alongside his description of intuition as an alternative or supplement to a scientific epistemology based purely in induction and deduction. After doing so, it theorizes how his views might intersect with recent developments in neuroscience and the cognitive sciences, especially as applied to aesthetics. Like many other Romantic authors, Poe approached scientific pursuits and methods, especially those regarding human mental faculties and functions, with both skepticism and a great deal of interest. Ranging over a number of Poe’s works, from Eureka to “The Imp of the Perverse,” “Murders in the Rue Morgue” to “Philosophy of Composition,” the chapter argues that Poe’s celebration and critique of human rationality and the limits of scientific methods, especially in regards to the human brain, provide a valuable template for thinking through the application of developments in brain science to literary-aesthetic questions in the twenty-first century.


2018 ◽  
Vol 2 (2) ◽  
pp. 175-199 ◽  
Author(s):  
Oscar Miranda-Dominguez ◽  
Eric Feczko ◽  
David S. Grayson ◽  
Hasse Walum ◽  
Joel T. Nigg ◽  
...  

Recent progress in resting-state neuroimaging demonstrates that the brain exhibits highly individualized patterns of functional connectivity—a “connectotype.” How these individualized patterns may be constrained by environment and genetics is unknown. Here we ask whether the connectotype is familial and heritable. Using a novel approach to estimate familiality via a machine-learning framework, we analyzed resting-state fMRI scans from two well-characterized samples of child and adult siblings. First we show that individual connectotypes were reliably identified even several years after the initial scanning timepoint. Familial relationships between participants, such as siblings versus those who are unrelated, were also accurately characterized. The connectotype demonstrated substantial heritability driven by high-order systems including the fronto-parietal, dorsal attention, ventral attention, cingulo-opercular, and default systems. This work suggests that shared genetics and environment contribute toward producing complex, individualized patterns of distributed brain activity, rather than constraining local aspects of function. These insights offer new strategies for characterizing individual aberrations in brain function and evaluating heritability of brain networks.


2021 ◽  
Vol 12 ◽  
Author(s):  
Huihui Chen ◽  
Yining Zhang ◽  
Limei Zhang ◽  
Lishan Qiao ◽  
Dinggang Shen

Brain functional network (BFN) analysis is becoming a crucial way to explore the inherent organized pattern of the brain and reveal potential biomarkers for diagnosing neurological or psychological disorders. In so doing, a well-estimated BFN is of great concern. In practice, however, noises or artifacts involved in the observed data (i.e., fMRI time series in this paper) generally lead to a poor estimation of BFN, and thus a complex preprocessing pipeline is often used to improve the quality of the data prior to BFN estimation. One of the popular preprocessing steps is data-scrubbing that aims at removing “bad” volumes from the fMRI time series according to the amplitude of the head motion. Despite its helpfulness in general, this traditional scrubbing scheme cannot guarantee that the removed volumes are necessarily unhelpful, since such a step is fully independent to the subsequent BFN estimation task. Moreover, the removal of volumes would reduce the statistical power, and different numbers of volumes are generally scrubbed for different subjects, resulting in an inconsistency or bias in the estimated BFNs. To address these issues, we develop a new learning framework that conducts BFN estimation and data-scrubbing simultaneously by an alternating optimization algorithm. The newly developed algorithm adaptively weights volumes (instead of removing them directly) for the task of BFN estimation. As a result, the proposed method can not only reduce the difficulty of threshold selection involved in the traditional scrubbing scheme, but also provide a more flexible framework that scrubs the data in the subsequent FBN estimation model. Finally, we validate the proposed method by identifying subjects with mild cognitive impairment (MCI) from normal controls based on the estimated BFNs, achieving an 80.22% classification accuracy, which significantly improves the baseline methods.


1970 ◽  
Vol 6 (1) ◽  
Author(s):  
Muskinul Fuad

The education system in Indonesia emphasize on academic intelligence, whichincludes only two or three aspects, more than on the other aspects of intelligence. For thatreason, many children who are not good at academic intelligence, but have good potentials inother aspects of intelligence, do not develop optimally. They are often considered and labeledas "stupid children" by the existing system. This phenomenon is on the contrary to the theoryof multiple intelligences proposed by Howard Gardner, who argues that intelligence is theability to solve various problems in life and produce products or services that are useful invarious aspects of life.Human intelligence is a combination of various general and specific abilities. Thistheory is different from the concept of IQ (intelligence quotient) that involves only languageskills, mathematical, and spatial logics. According to Gardner, there are nine aspects ofintelligence and its potential indicators to be developed by each child born without a braindefect. What Gardner suggested can be considered as a starting point to a perspective thatevery child has a unique individual intelligence. Parents have to treat and educate theirchildren proportionally and equitably. This treatment will lead to a pattern of education that isfriendly to the brain and to the plurality of children’s potential.More than the above points, the notion that multiple intelligences do not just comefrom the brain needs to be followed. Humans actually have different immaterial (spiritual)aspects that do not refer to brain functions. The belief in spiritual aspects and its potentialsmeans that human beings have various capacities and they differ from physical capacities.This is what needs to be addressed from the perspective of education today. The philosophyand perspective on education of the educators, education stakeholders, and especially parents,are the first major issue to be addressed. With this step, every educational activity andcommunication within the family is expected to develop every aspect of children'sintelligence, especially the spiritual intelligence.


2020 ◽  
Author(s):  
Pathikkumar Patel ◽  
Bhargav Lad ◽  
Jinan Fiaidhi

During the last few years, RNN models have been extensively used and they have proven to be better for sequence and text data. RNNs have achieved state-of-the-art performance levels in several applications such as text classification, sequence to sequence modelling and time series forecasting. In this article we will review different Machine Learning and Deep Learning based approaches for text data and look at the results obtained from these methods. This work also explores the use of transfer learning in NLP and how it affects the performance of models on a specific application of sentiment analysis.


Sign in / Sign up

Export Citation Format

Share Document