Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
25,289
result(s) for
"Performance Classification."
Sort by:
Building a Framework for a Dual Task Taxonomy
The study of dual task interference has gained increasing attention in the literature for the past 35 years, with six MEDLINE citations in 1979 growing to 351 citations indexed in 2014 and a peak of 454 cited papers in 2013. Increasingly, researchers are examining dual task cost in individuals with pathology, including those with neurodegenerative diseases. While the influence of these papers has extended from the laboratory to the clinic, the field has evolved without clear definitions of commonly used terms and with extreme variations in experimental procedures. As a result, it is difficult to examine the interference literature as a single body of work. In this paper we present a new taxonomy for classifying cognitive-motor and motor-motor interference within the study of dual task behaviors that connects traditional concepts of learning and principles of motor control with current issues of multitasking analysis. As a first step in the process we provide an operational definition of dual task, distinguishing it from a complex single task. We present this new taxonomy, inclusive of both cognitive and motor modalities, as a working model; one that we hope will generate discussion and create a framework from which one can view previous studies and develop questions of interest.
Journal Article
Aligning categories of mental health conditions with intervention types in high-performance sports: A narrative cornerstone review and classification framework
Epidemiological studies suggest that psychiatric disorders are as prevalent amongst high-performance athletes as in general populations, challenging the myth of invulnerability. Despite efforts of sport organisations to highlight the significance of athletes' mental health, it is still many times tough to combine the sport performance ethos with a discourse on mental health. This narrative cornerstone review examines challenges related to definitions and classifications of athlete mental health in high-performance sports and how these influence assessments and the implementation of interventions. We discuss challenges with concept creep and psychiatrisation and outline their consequences for sport healthcare professionals. Based on this, we present a framework that aligns different categories of athlete mental health conditions (from the reduction of wellbeing to psychiatric disorders) with intervention types (from the provision of supporting environments to pharmacotherapy). We conclude that researchers and sport practitioners need to carefully consider conceptual creep and the risk of pathologising normal and healthy, albeit emotionally aversive, reactions to athlete lifeworld events when assessing athlete mental health. A clear separation of terminology denoting the athlete's resources to handle the lifeworld (including salutogenic factors) and terms describing psychiatric conditions and their management is necessary to avoid misguidance in intervention planning.
Journal Article
Guiding Evidence-Based Classification in Para Sporting Populations: A Systematic Review of Impairment Measures and Activity Limitations
As the focus of classification shifts towards an evidence-based approach, it is crucial to establish a robust system that relies on valid and reliable measures of impairment to ensure legitimate and competitive opportunities for all Para athletes. However, the lack of methods that possess the necessary measurement properties for assessing impairments in Para sporting populations presents significant challenges to developing an evidence-based classification system.
This review aimed to identify and evaluate measures of impairment and activity limitation measures that have been used to assess eligible impairments in Para sport athletes for potential use in evidence-based classification.
Six electronic databases (MEDLINE, Embase, SPORTDiscus, CINAHL, Scopus, Web of Science) were searched from their earliest record to December 2023.
Fifty-one articles were identified, with twenty-one studies focusing on physical impairment measures. Isometric and grip strength emerged as effective measures. Coordination measures, such as tapping tasks, showed variations with performance. Additionally, six studies focused on intellectual impairments, revealing differences between impaired and non-impaired athletes through generic cognitive tests. Vision impairment measures, including visual acuity and visual field assessments, displayed varying associations with performance across sports.
Although research on evidence-based classification in Para sport is limited, this review provides valuable insights for sports in developing a testing battery that adheres to evidence-based protocols. Ongoing research efforts by sport governing bodies to prioritise research in this area will improve our understanding of the impairment-performance relationship, leading to better decision making and increased credibility in Para sport classification systems.
Journal Article
Relating instance hardness to classification performance in a dataset: a visual approach
Machine Learning studies often involve a series of computational experiments in which the predictive performance of multiple models are compared across one or more datasets. The results obtained are usually summarized through average statistics, either in numeric tables or simple plots. Such approaches fail to reveal interesting subtleties about algorithmic performance, including which observations an algorithm may find easy or hard to classify, and also which observations within a dataset may present unique challenges. Recently, a methodology known as Instance Space Analysis was proposed for visualizing algorithm performance across different datasets. This methodology relates predictive performance to estimated instance hardness measures extracted from the datasets. However, the analysis considered an instance as being an entire classification dataset and the algorithm performance was reported for each dataset as an average error across all observations in the dataset. In this paper, we developed a more fine-grained analysis by adapting the ISA methodology. The adapted version of ISA allows the analysis of an individual classification dataset by a 2-D hardness embedding, which provides a visualization of the data according to the difficulty level of its individual observations. This allows deeper analyses of the relationships between instance hardness and predictive performance of classifiers. We also provide an open-access Python package named PyHard, which encapsulates the adapted ISA and provides an interactive visualization interface. We illustrate through case studies how our tool can provide insights about data quality and algorithm performance in the presence of challenges such as noisy and biased data.
Journal Article
Trying to use temporal and kinematic parameters for the classification in wheelchair badminton
This study explores the potential for the temporal and kinematic datas link to propulsion technique and athlete performance collected here to contribute to evidence-based classification for wheelchair badminton athletes.
Nineteen experienced wheelchair badminton players underwent propulsion tests with a badminton racket. Wheelchair were equipped with inertial measurement units. The first analysis conducted involved comparing the parameters between class WH1 and WH2. Subsequently, a hierarchical clustering analysis was performed on the parameters with significant differences.
Regarding propulsion technique parameters, WH1 athletes exhibit a longer braking phase compared to WH2 athletes. Generally, the performance of WH1 athletes is inferior to that of WH2 athletes. Concerning hierarchical clustering analysis, the results reveal the formation of three clusters based on principal components explaining 70% of the variation in the parameters considered in the analysis.
Thus, the results of this study indicate a longer braking time for WH1 athletes compared to WH2, along with lower overall performance. The clusters results could suggest a potential evolution of the current classification towards three distinct classes of wheelchair badminton players. However, these findings should be interpreted with caution, given that the included performance parameters can be influenced by numerous factors, potentially undermining the robustness of the clustering methodology employed. This study highlights the need to strengthen the current classification process in wheelchair badminton.
Journal Article
The Effect of Preprocessing Techniques, Applied to Numeric Features, on Classification Algorithms’ Performance
It is recognized that the performance of any prediction model is a function of several factors. One of the most significant factors is the adopted preprocessing techniques. In other words, preprocessing is an essential process to generate an effective and efficient classification model. This paper investigates the impact of the most widely used preprocessing techniques, with respect to numerical features, on the performance of classification algorithms. The effect of combining various normalization techniques and handling missing values strategies is assessed on eighteen benchmark datasets using two well-known classification algorithms and adopting different performance evaluation metrics and statistical significance tests. According to the reported experimental results, the impact of the adopted preprocessing techniques varies from one classification algorithm to another. In addition, a statistically significant difference between the considered data preprocessing techniques is demonstrated.
Journal Article
Changes in physical demands between game quarters of U18 elite official basketball games
The aim of this study was to describe the physical demands during U18 elite basketball games according to the game quarter and to identify a smaller subset of variables and threshold scores that distinguish players' physical performance in each quarter.
Data was collected from ninety-four players who participated in the study (age: 17.4 ± 0.74 years; height: 199.0 ± 0.1 cm; body mass: 87.1 ± 13.1 kg) competing in the Euroleague Basketball Next Generation Tournament. Players' movements during the games were measured using a portable local positioning system (LPS) (WIMU PRO®, Realtrack Systems SL, Almería, Spain) and included relative distance (total distance / playing duration), relative distance in established speed zones, high-intensity running (18.1-24.0 km·h-1) and sprinting (> 24.1 km·h-1). player load, peak speed (km·h-1) and peak acceleration (m·s-2) number of total accelerations and total decelerations, high intensity accelerations (> 2 m·s-2) and decelerations (< -2 m·s-2).
There was an overall decrease in distance covered, player load, number of high intensity accelerations and decelerations between the first and last quarter of the games in all playing positions. A classification tree analysis showed that the first quarter had much influence of distance covered (above 69.0 meters), distance covered <6.0 km·h-1 and accelerations (> 2 m·s-2), whereas the fourth quarter performance had much influence of distance covered (below 69.0) and distance covered 12.1-18.0 km·h-1.
A significant reduction in physical demands occurs during basketball, especially between first and last quarter for players in all playing positions during basketball games of under 18 elite players.
Journal Article
A Novel Medical Image Enhancement Algorithm for Breast Cancer Detection on Mammography Images Using Machine Learning
Mammography is the most preferred method for breast cancer screening. In this study, computer-aided diagnosis (CAD) systems were used to improve the image quality of mammography images and to detect suspicious areas. The main contribution of this study is to reveal the optimal combination of various pre-processing algorithms to enable better interpretation and classification of mammography images because pre-processing algorithms significantly affect the accuracy of segmentation and classification methods. In this study, the effect of combinations of different preprocessing methods in differentiating benign and malignant breast lesions was investigated. All image processing algorithms used for lesion detection were used in the mini-MIAS database. In the first step, label information and pectoral muscle resulting from the acquisition of mammography images were removed. In the second step, median filter (MF), contrast limited adaptive histogram equalization (CLAHE), and unsharp masking (USM) algorithms with different combinations of the resolution and visibility of images are increased. In the third step, suspicious regions are extracted from the mammograms using the k-means clustering technique. Then, features were extracted from the obtained ROIs. Finally, feature datasets were classified as normal/abnormal, and benign/malign (two class classification) using Machine Learning algorithms. Test performance measures of the classification methods were examined. In both classifications made in the study, lower classification performance values were obtained when the CLAHE algorithm was used alone as a pre-processing method compared to other pre-processing combinations. When the median filter and unsharp masking algorithms are added to the CLAHE algorithm, the performance of the classification methods has increased. In terms of classification success, Support Vector Machines, Random Forest, and Neural Networks showed the best performance. It was found by comparing the performances of the classification methods that different preprocessing algorithms were effective in detecting the presence of breast lesions and distinguishing benign and malignant.
Journal Article
A Robust Deep Learning Framework for Skill Level Discrimination in Tennis Strokes Using Bilateral IMU Measurements
In tennis, where performance is governed by complex kinetic chain interactions, objective skill classification is vital for coaching and talent identification. This study presents a hierarchical deep learning framework leveraging synchronized bilateral Inertial Measurement Unit (IMU) data from 39 participants (11 elite, 28 amateur). The proposed system successfully distinguishes expertise levels across a total of 4594 strokes, including augmented samples. A hybrid Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) architecture was developed to autonomously extract spatiotemporal features from the raw kinematic signals of forehand, backhand, service, and volley strokes. The proposed model achieved an accuracy of 95.54%, significantly outperforming both traditional machine learning and state-of-the-art deep learning benchmarks. Qualitative t-distributed Stochastic Neighbor Embedding (t-SNE) analyses revealed that elite athletes form highly homogeneous clusters in the feature space. Furthermore, quantitative Asymmetry Index assessments confirmed that professionals exhibit superior bilateral coordination stability. These findings demonstrate that the proposed end-to-end system offers a robust, field-applicable solution for identifying technical excellence. It provides coaches with reliable digital biomarkers, thereby overcoming the limitations of subjective visual observation.
Journal Article