Amplifying perceptual demands: How changes in the colour vests affect youth players performance during medium-sided games

This study explored how manipulating the colour of training vests affects footballers’ individual and collective performance during a Gk+6vs6+Gk medium-sided game. A total of 21 under-17 years old players were involved in three experimental conditions in a random order for a total of four days: i) CONTROL, two teams using two different colour vests; ii) SAME, both teams wearing blue vests; iii) MIXED, all 6 players per team wore different colour vests. Players’ positional data was used to compute time-motion and tactical-related variables, while video analysis was used to collect technical variables. Further, these variables were synchronized with spatiotemporal data allowing to capture ball-related actions in a horizontal 2D plan. All variables were analysed from the offensive and defensive perspective. From the offensive perspective, players performed more and further shots to goal during the CONTROL than in SAME and MIXED (small effects) conditions, with a decreased distance to the nearest defender (small effects). While defending, results revealed lower distance to the nearest teammate (small effects) in the CONTROL than in the SAME and MIXED conditions, and higher team longitudinal synchronization (small effects). In addition, the CONTROL showed in general lower values of team width while defending than in the other 2 conditions. Overall, coaches may use the CONTROL condition to emphasize offensive performance and defensive behaviour over the longitudinal direction with increased physical demands. In turn, coaches may use the manipulation of players vests to emphasize defensive performance, as players seem to behave more cohesively under such scenarios.

Expected passes

Passes are by far football’s (soccer) most frequent event, yet surprisingly little meaningful research has been devoted to quantify them. With the increase in availability of so-called positional data, describing the positioning of players and ball at every moment of the game, our work aims to determine the difficulty of every pass by calculating its success probability based on its surrounding circumstances. As most experts will agree, not all passes are of equal difficulty, however, most traditional metrics count them as such. With our work we can quantify how well players can execute passes, assess their risk profile, and even compute completion probabilities for hypothetical passes by combining physical and machine learning models. Our model uses the first 0.4 seconds of a ball trajectory and the movement vectors of all players to predict the intended target of a pass with an accuracy of $$93.0\%$$ 93.0 % for successful and $$72.0\%$$ 72.0 % for unsuccessful passes much higher than any previously published work. Our extreme gradient boosting model can then quantify the likelihood of a successful pass completion towards the identified target with an area under the curve (AUC) of $$93.4\%$$ 93.4 % . Finally, we discuss several potential applications, like player scouting or evaluating pass decisions.

EARLY KYIV OBSERVATIONS OF ASTEROIDS: ANALYSIS AND NEW REDUCTION WITH TYCHO-2 AND GAIA CATALOGS

For more than 50 years, the continuous photographic observations of asteroids have been carried outwith telescopes of the Astronomical Observatory of the Taras Shevchenko National University of Kyiv and the Main Astronomical Observatory of the National Academy of Sciences of Ukraine. About 3,000 photographic plates were obtained, some of which were exposed in 1908. We collected the data on more than 5,500 positions and magnitudes of asteroids on these astroplates taking into account all results of the processing of observations available in various publications and in the Minor Planet Center database. All positional data were compared with JPL ephemeris and analyzed. From different series of asteroid observations the values of positional accuracy were obtained, depending on the methods of measuring and processing the plates and reference catalogs of stars. In order to systematically improve the obtained asteroid positions, we evaluated the possibilities of reprocessing some of the earliest asteroid observations applying the modern star high accuracy catalogs. Using the Tycho-2, Gaia DR2, and Gaia EDR3 as the reference catalogs, the 590 astroplates exposed on the MAO NASU Double Long-Focus Astrograph (DLA) in 1952-1986 were reprocessed based on old plate measurements. All newly determined and previous original asteroid positions were compared with the JPL ephemeris. The comparison results show an improvement in the systematic and random components of the accuracy of coordinates for new positions of asteroids. When comparing the new positions of the asteroids determined in the Tycho-2 and Gaia catalog systems, no significant changes in accuracy were found.

Forward Kinematics of Delta Manipulator by Novel Hybrid Neural Network

For the parallel configuration of the robot manipulator, the solution of Forward Kinematics (FK) is tough as compared to Inverse Kinematics (IK). This work presents a novel hybrid method of optimizing an Artificial Neural Network (ANN) specifically Multilayer Perceptron (MLP) with Genetic Algorithm (GA) and Step-wise Linear Regression (SWLR) to solve the complex FK of Delta Parallel Manipulator (DPM). The joint space angular positional data has been iterated using IK to generate point cloud of Cartesian space positional data. This data set is highly random and broad which leads to higher-order nonlinearity. Hence, normalization of the dataset has been done to avoid outliers from the dataset and to achieve better performance. The developed ANN based MLP gave a mean square error of 0.0000762 and an overall R2 value of 0.99918. Finally, the proposed network has been simulated to solve FK of the parallel manipulator and to check its efficacy. For given joint angles, the proposed network predicted positional values which are in good approximation with known trajectory solved by standard analytical method.

In-play forecasting in football using event and positional data

Two highly relevant aspects of football, namely forecasting of results and performance analysis by means of performance indicators, are combined in the present study by analysing the value of in-play information in terms of event and positional data in forecasting the further course of football matches. Event and positional data from 50 matches, including more than 300 million datapoints were used to extract a total of 18 performance indicators. Moreover, goals from more than 30,000 additional matches have been analysed. Results suggest that surprisingly goals do not possess any relevant informative value on the further course of a match, if controlling for pre-game market expectation by means of betting odds. Performance indicators based on event and positional data have been shown to possess more informative value than goals, but still are not sufficient to reveal significant predictive value in-play. The present results are relevant to match analysts and bookmakers who should not overestimate the value of in-play information when explaining match performance or compiling in-play betting odds. Moreover, the framework presented in the present study has methodological implications for performance analysis in football, as it suggests that researchers should increasingly segment matches by scoreline and control carefully for general team strength.

Support for a “Jelly Sandwich” Model of the Tibetan Plateau

Computer modeling constrained by positional data collected in the aftermath of the 2008 Wenchuan earthquake indicates the lower crust is less viscous than the upper mantle below it.

Match-related physical performance in professional soccer: Position or player specific?

The purpose of this study was to examine to what extent the physical match performance of professional soccer players is both position and player specific. First, official match data from the 2019/20 German Bundesliga season was used to search for players that met the inclusion criteria of playing a minimum of four entire matches in at least two different playing positions. Overall, 25 players met the criteria prior to the COVID-19 induced break, playing a minimum of eight matches. Second, the physical match performance of these players was analyzed separately for each position they played. The following four parameters were captured: total distance, high-intensity distance, sprinting distance, and accelerations. Third, the 25 players’ physical match performance data was then compared to normative data for each position they played to understand whether players adapted their physical performance (position dependent), or maintained their performance regardless of which position they were assigned to (position independent). When switching the position, the change in physical match performance of the respective players could be explained by 44–58% through the normative positional data. Moreover, there existed large individual differences in the way players adapted or maintained their performance when acting in different positions. Coaches and practitioners should be aware that some professional soccer players will likely incur differences in the composition of physical match performance when switching positions and therefore should pay special consideration for such differences in the training and recovery process of these players.

Automated geological map deconstruction for 3D model construction using <i>map2loop</i> 1.0 and <i>map2model</i> 1.0

At a regional scale, the best predictor for the 3D geology of the near-subsurface is often the information contained in a geological map. One challenge we face is the difficulty in reproducibly preparing input data for 3D geological models. We present two libraries (map2loop and map2model) that automatically combine the information available in digital geological maps with conceptual information, including assumptions regarding the subsurface extent of faults and plutons to provide sufficient constraints to build a prototype 3D geological model. The information stored in a map falls into three categories of geometric data: positional data, such as the position of faults, intrusive, and stratigraphic contacts; gradient data, such as the dips of contacts or faults; and topological data, such as the age relationships of faults and stratigraphic units or their spatial adjacency relationships. This automation provides significant advantages: it reduces the time to first prototype models; it clearly separates the data, concepts, and interpretations; and provides a homogenous pathway to sensitivity analysis, uncertainty quantification, and value of information studies that require stochastic simulations, and thus the automation of the 3D modelling workflow from data extraction through to model construction. We use the example of the folded and faulted Hamersley Basin in Western Australia to demonstrate a complete workflow from data extraction to 3D modelling using two different open-source 3D modelling engines: GemPy and LoopStructural.

Exploring how limiting the number of ball touches during small-sided games affects youth football players’ performance across different age groups

This study explored how the number of allowed ball touches per player possession affected the performance of different age groups (U9, U11, U13, U15, U17 and U19) during a Gk + 4vs4+Gk small-sided games. Each day, players randomly performed the following three conditions (for a total of 6 days): i) free-play (FP); ii) maximum of 2 touches (2 T); iii) 1 touch (1 T). Players’ positional data was used to compute time-motion and positional-related variables, while video analysis was used to capture technical performance. In general, no effects were identified in relation to the players distances (team centroid, opponents’ centroid, nearest teammate, and nearest opponent). There were small to moderate decreases in the longitudinal synchronization while playing with 1 T and 2 T in the U9 and U17, but a moderate increase in the U15. There was a general decrease in the distance covered and distance covered while running (small to moderate effects) when playing with limited touches in all age groups. Limiting the touches promoted small to moderate increases in the number of successful passes in the U9, U15, and U17 and a general increase in unsuccessful actions. Overall, playing with limited touches emphasized the passing skill while it also contributed to more unsuccessful actions and lower physical demands. As so, coaches may use the 2 T in young age groups (U9-U13) as they seem less able to successfully cope with 1 T, while using 1 T in older age groups due to their higher ability to interact with environmental information.

Significant sensors and parameters in assessment of dysarthric speech

Purpose Dysarthria is a neuromotor speech disorder caused by neuromuscular disturbances that affect one or more articulators resulting in unintelligible speech. Though inter-phoneme articulatory variations are well captured by formant frequency-based acoustic features, these variations are expected to be much higher for dysarthric speakers than normal. These substantial variations can be well captured by placing sensors in appropriate articulatory position. This study focuses to determine a set of articulatory sensors and parameters in order to assess articulatory dysfunctions in dysarthric speech. Design/methodology/approach The current work aims to determine significant sensors and parameters associated using motion path and correlation analyzes on the TORGO database of dysarthric speech. Among eight informative sensor channels and six parameters per channel in positional data, the sensors such as tongue middle, back and tip, lower and upper lips and parameters (y, z, φ) are found to contribute significantly toward capturing the articulatory information. Acoustic and positional data analyzes are performed to validate these identified significant sensors. Furthermore, a convolutional neural network-based classifier is developed for both phone-and word-level classification of dysarthric speech using acoustic and positional data. Findings The average phone error rate is observed to be lower, up to 15.54% for positional data when compared with acoustic-only data. Further, word-level classification using a combination of both acoustic and positional information is performed to study that the positional data acquired using significant sensors will boost the performance of classification even for severe dysarthric speakers. Originality/value The proposed work shows that the significant sensors and parameters can be used to assess dysfunctions in dysarthric speech effectively. The articulatory sensor data helps in better assessment than the acoustic data even for severe dysarthric speakers.