Oculomotor Behavior Predict Professional Cricket Batting and Bowling Performance

Importance: A new, shorter version of cricket was introduced recently (Twenty20; T20). Since its inception, T20 cricket has rapidly become a popular and exciting format of cricket. However, there is little understanding of factors such as visual-motor control that influence expert performance.Objective: The purpose of this project is to determine if a series of oculomotor measures can predict batting and bowling performance in professional cricket players.Design: This study used a cross-sectional design. Each participant took part in a suite of eye-tracking tests to measure oculomotor behavior compared to their performance data.Participants: This study used a sample of 59 male T20 league professional cricket players (30 Bowlers and 29 Batsman).Results: One-way univariate analyses of variance examined the differences in oculomotor behavior between batsman and bowlers. A series of multiple regression analyses was conducted to evaluate how well the visual variables predict bowling and batting performance variables. Results demonstrate that several oculomotor eye tracking measures were good predictors of run performance and strike rate, including sports total score, sports on-field score, and sports functional score. Likewise, several of the same metrics predicted Runs and Wicket performance for bowlers. Overall, results provided further validation to a growing body of literature supporting the use of eye-tracking technology in performance evaluation.

Deep learning–assisted prostate cancer detection on bi-parametric MRI: minimum training data size requirements and effect of prior knowledge

Objectives To assess Prostate Imaging Reporting and Data System (PI-RADS)–trained deep learning (DL) algorithm performance and to investigate the effect of data size and prior knowledge on the detection of clinically significant prostate cancer (csPCa) in biopsy-naïve men with a suspicion of PCa. Methods Multi-institution data included 2734 consecutive biopsy-naïve men with elevated PSA levels (≥ 3 ng/mL) that underwent multi-parametric MRI (mpMRI). mpMRI exams were prospectively reported using PI-RADS v2 by expert radiologists. A DL framework was designed and trained on center 1 data (n = 1952) to predict PI-RADS ≥ 4 (n = 1092) lesions from bi-parametric MRI (bpMRI). Experiments included varying the number of cases and the use of automatic zonal segmentation as a DL prior. Independent center 2 cases (n = 296) that included pathology outcome (systematic and MRI targeted biopsy) were used to compute performance for radiologists and DL. The performance of detecting PI-RADS 4–5 and Gleason > 6 lesions was assessed on 782 unseen cases (486 center 1, 296 center 2) using free-response ROC (FROC) and ROC analysis. Results The DL sensitivity for detecting PI-RADS ≥ 4 lesions was 87% (193/223, 95% CI: 82–91) at an average of 1 false positive (FP) per patient, and an AUC of 0.88 (95% CI: 0.84–0.91). The DL sensitivity for the detection of Gleason > 6 lesions was 85% (79/93, 95% CI: 77–83) @ 1 FP compared to 91% (85/93, 95% CI: 84–96) @ 0.3 FP for a consensus panel of expert radiologists. Data size and prior zonal knowledge significantly affected performance (4%, $$p<0.05$$ p < 0.05 ). Conclusion PI-RADS-trained DL can accurately detect and localize Gleason > 6 lesions. DL could reach expert performance using substantially more than 2000 training cases, and DL zonal segmentation. Key Points • AI for prostate MRI analysis depends strongly on data size and prior zonal knowledge. • AI needs substantially more than 2000 training cases to achieve expert performance.

Cognitive control

What role might intuition and deliberation play during the performance of well-learned skills? Dreyfus and Dreyfus’ (1986) influential phenomenological analysis of skill-acquisition proposes that expert performance is guided by non-cognitive responses which are fast, effortless, and intuitive in nature. Although Dreyfus and Dreyfus (1986) recognize that, on occasions (e.g. when performance goes awry for some reason), a form of ‘detached deliberative rationality’ may be used by experts to improve their performance, they see no role for calculative problem solving or deliberation (i.e. drawing on rules or mental representations) when performance is going well. The current chapter counters this argument by drawing on empirical evidence and phenomenological description to argue that skilled performers use cognitive control (an executive function) across a range of sporting situations (i.e. in training, pre-performance routines, on-line skill execution) in order to maintain and enhance performance proficiency.

Somnotate: A robust automated sleep stage classifier that exceeds human performance and identifies ambiguous states in mice

Manual sleep stage annotation is a time-consuming but often essential step in the analysis of sleep data. To address this bottleneck several algorithms have been proposed that automate this process, reporting performance levels that are on par with manual annotation according to measures of inter-rater agreement. Here we first demonstrate that inter-rater agreement can provide a biased and imprecise measure of annotation quality. We therefore develop a principled framework for assessing performance against a consensus annotation derived from multiple experienced sleep researchers. We then construct a new sleep stage classifier that combines automated feature extraction using linear discriminant analysis with inference based on vigilance state-dependent contextual information using a hidden Markov model. This produces automated annotation accuracies that exceed expert performance on rodent electrophysiological data. Furthermore, our classifier is shown to be robust to errors in the training data, robust to experimental manipulations, and compatible with different recording configurations. Finally, we demonstrate that the classifier identifies both successful and failed attempts to transition between vigilance states, which may offer new insights into the occurrence of short awake periods between REM and NREM sleep. We call our classifier 'Somnotate' and make an implementation available to the neuroscience community.

Visual behavior and upper limb variability in coordination comparision between novices and experts performers in basketball free throws

The objective of the present research is to determine the differences in visual behavior and the upper limbs variability in coordination between expert performers and novice performers in basketball free throws. Methods: Nine right-handed men were tested. The skilled group consisted of four players who had an experience of 9.2 years (SD: 1.2) and play 9 hours per week (SD: 12). The novice group consisted of five players with no experience in Basketball. Visual behavior was evaluated using an eye-tracker head mounted and the upper limb kinematic behavior using a High-speed camera during 30 free throws. Results: There was a significant difference between the expert and novice performers in accuracy for the 30 trials (p<0.034). In Visual behavior were no significant differences the duration of the last visual fixation before the onset of elbow extension in execution phase (p>0,05) between expert and novice groups. There were statistically significant differences in the elbow-wrist variability in coordination in the throws duration time-windows of 100%, 90%, 80%, 30% (pvalue <0.05). 100% represent the last time-windows before ball release. The expert performers shows greater consistency in coordination, however novice subjects exhibit greater variability in the coordination in these intervals. Conclusion: The results suggest that the task of shooting free throws requires a long visual fixation to the site of interest, which temporarily is similar in subjects with different levels of skill. The higher reproducibility pattern suggests elbow-wrist coordination to be the key perceptuo-motor behavior in order to reach expert performance. El objetivo de la presente investigación es determinar las diferencias en el comportamiento visual y la variabilidad de los miembros superiores en la coordinación entre ejecutantes expertos y ejecutantes novatos en los tiros libres de baloncesto. Métodos: Se examinaron nueve hombres diestros. El grupo de expertos estaba formado por cuatro jugadores que tenían una experiencia de 9,2 años (SD: 1,2) y jugaban 9 horas a la semana (SD: 12). El grupo de novatos estaba formado por cinco jugadores sin experiencia en baloncesto. El comportamiento visual fue evaluado utilizando un eye-tracker montado en la cabeza y el comportamiento cinemático del miembro superior utilizando una cámara de alta velocidad durante 30 tiros libres. Resultados: Hubo una diferencia significativa entre los expertos y los novatos en la precisión de los 30 ensayos (p<0,034). En el comportamiento visual no hubo diferencias significativas en la duración de la última fijación visual antes del inicio de la extensión del codo en la fase de ejecución (p>0,05) entre los grupos de expertos y novatos. Hubo diferencias estadísticamente significativas en la variabilidad codo-muñeca en la coordinación en las ventanas de tiempo de duración de los lanzamientos del 100%, 90%, 80%, 30% (pvalor <0,05). El 100% representa las últimas ventanas de tiempo antes del lanzamiento del balón. Los ejecutantes expertos muestran una mayor consistencia en la coordinación, sin embargo los sujetos novatos exhiben una mayor variabilidad en la coordinación en estos intervalos. Conclusiones: Los resultados sugieren que la tarea de lanzar tiros libres requiere una larga fijación visual al sitio de interés, que temporalmente es similar en sujetos con diferentes niveles de habilidad. El patrón de mayor reproducibilidad sugiere que la coordinación codo-muñeca es la conducta perceptivo-motora clave para alcanzar un rendimiento experto.

Application of Ensemble Learning Using Weight Voting Protocol in the Prediction of Pile Bearing Capacity

Accurate prediction of pile bearing capacity is an important part of foundation engineering. Notably, the determination of pile bearing capacity through an in situ load test is costly and time-consuming. Therefore, this study focused on developing a machine learning algorithm, namely, Ensemble Learning (EL), using weight voting protocol of three base machine learning algorithms, gradient boosting (GB), random forest (RF), and classic linear regression (LR), to predict the bearing capacity of the pile. Data includes 108 pile load tests under different conditions used for model training and testing. Performance evaluation indicators such as R-square (R2), root mean square error (RMSE), and MAE (mean absolute error) were used to evaluate the performance of models showing the efficiency of predicting pile bearing capacity with outstanding performance compared to other models. The results also showed that the EL model with a weight combination of w 1 = 0.482, w 2 = 0.338, and w 3 = 0.18 corresponding to the models GB, RF, and LR gave the best performance and achieved the best balance on all data sets. In addition, the global sensitivity analysis technique was used to detect the most important input features in determining the bearing capacity of the pile. This study provides an effective tool to predict pile load capacity with expert performance.

Reimagining the body image

This chapter considers a variety of criticisms and a number of applications in which the usefulness of the body image/body schema distinction is still apparent. The chapter suggests that one can find complexity in this distinction by exploring several theoretical and practical directions, for example, by developing a non-reductive neuroscientific explanation, by investigating various pathologies, by exploring deeper psychoanalytic aspects, and by analysing different forms of embodied performance. Each of these projects are complex ones and some of them involve social and cultural analyses, as reflected in recent work in feminist, race, and gender studies. More specifically, this chapter discusses body image and body-schematic processes in cases of expert performance.