Visual search strategies of performance monitoring used in action anticipation of basketball players.

INTRODUCTION: Numerous studies have found that expert players anticipate better than novices. If more accurate prediction represents performance monitoring of experts, what are the advantages of elite basketball players in identifying and processing available cues? There is still a lack of sufficient evidence. This study examined the visual search in basketball players and explored the performance monitoring of action anticipation, adopting an expert-novice paradigm and eye-movement technology. METHODS: Forty basketball players were recruited in this study: 20 in the expert group and 20 in the novice group. Participants were asked to predict the outcome of videotaped basketball throws and their accuracy and eye-movement characteristics were record. RESULTS: The accuracy of the expert was significantly higher than that of the novice. The experts were able to instantly search and identify important cues in anticipation, and the gaze area of the experts was concentrated on the area of interest of the body. Additionally, the expert group showed long, repetitive, and rapid visual search of vital information, and improved their performance of the task. CONCLUSION: The experts could monitor the performance of prediction by grabbing vital shooting information (such as the body of a player). The results suggest the athletes and coaches that if they want to improve the ability of prediction, it may be useful to shift their focus of attention from ball trajectory to body action.

Cerebellar connectome alterations and associated genetic signatures in multiple sclerosis and neuromyelitis optica spectrum disorder.

BACKGROUND: The cerebellum plays key roles in the pathology of multiple sclerosis (MS) and neuromyelitis optica spectrum disorder (NMOSD), but the way in which these conditions affect how the cerebellum communicates with the rest of the brain (its connectome) and associated genetic correlates remains largely unknown. METHODS: Combining multimodal MRI data from 208 MS patients, 200 NMOSD patients and 228 healthy controls and brain-wide transcriptional data, this study characterized convergent and divergent alterations in within-cerebellar and cerebello-cerebral morphological and functional connectivity in MS and NMOSD, and further explored the association between the connectivity alterations and gene expression profiles. RESULTS: Despite numerous common alterations in the two conditions, diagnosis-specific increases in cerebellar morphological connectivity were found in MS within the cerebellar secondary motor module, and in NMOSD between cerebellar primary motor module and cerebral motor- and sensory-related areas. Both diseases also exhibited decreased functional connectivity between cerebellar motor modules and cerebral association cortices with MS-specific decreases within cerebellar secondary motor module and NMOSD-specific decreases between cerebellar motor modules and cerebral limbic and default-mode regions. Transcriptional data explained > 37.5% variance of the cerebellar functional alterations in MS with the most correlated genes enriched in signaling and ion transport-related processes and preferentially located in excitatory and inhibitory neurons. For NMOSD, similar results were found but with the most correlated genes also preferentially located in astrocytes and microglia. Finally, we showed that cerebellar connectivity can help distinguish the three groups from each other with morphological connectivity as predominant features for differentiating the patients from controls while functional connectivity for discriminating the two diseases. CONCLUSIONS: We demonstrate convergent and divergent cerebellar connectome alterations and associated transcriptomic signatures between MS and NMOSD, providing insight into shared and unique neurobiological mechanisms underlying these two diseases.

Application of hybrid SFLA-ACO algorithm and CAM softwares for optimization of drilling tool path problems.

Abstract: In drilling process almost seventy percent time is spent in tool switching and moving the spindle from one hole to the other. This time travel is non productive as it does not take part in actual drilling process. Therefore, this non productive time needs to be optimized. Different metaheuristic algorithms have been applied to minimize this non productive tool travel time. In this study, two metaheuristic approaches, shuffled frog leaping algorithm (SFLA) and ant colony optimization (ACO) have been hybridized. In industry, the CAM softwares are employed for minimization of non productive tool travel time and it is considered that the path obtained by using the CAM softwares is the optimized path. However this is not the case in all problems. In order to show the contribution of the SFLA-ACO algorithm and to prove that results achieved through CAM softwares are not always optimized, hybrid SFLA-ACO algorithm has been applied to two drilling problems as case studies with the main objective of minimization of non productive tool travel time. The drilling problems which are taken from the manufacturing industry include ventilator manifold problem and lift axle mounting bracket problem. The results of hybrid SFLA-ACO algorithm have been compared with the results of commercially available computer aided manufacturing (CAM) software. For comparison purpose, the CAM softwares used are Creo 6.0, Pro E, Siemens NX and Solidworks. The comparison shows that the results of proposed hybrid SFLA-ACO algorithm are better than commercially available CAM softwares in both real world manufacturing problems. Article highlights: Different optimization techniques are being used for optimization of drilling tool path problems. In this paper two techniques SFLA and ACO has been combined to form a hybrid SFLA-ACO algorithm and has been applied to the real world industrial problems.Two real world problems have been taken from the local manufacturing industries. In both the problems the objective is to optimize the tool traveling time through hybrid SFLA-ACO and compare it with CAM software.Four CAM softwares have been used for comparison purpose. The problems undertaken are solved through these CAM software and compared with the results of hybrid SFLA-ACO results. As result of comparison it is found that in both the problems the performance of hybrid SFLA-ACO algorithm remains outclass. This signifies that results of CAM software in case of optimization of drilling tool path are not always optimal and these can be improved by using different optimization techniques.

A novel multi-criteria decision-making approach for prioritization of elective surgeries through formulation of "weighted MeNTS scoring system".

Background: Publicly funded healthcare system has long non-manageable elective surgery waiting lists due to the non-existence of systematic mathematical modelling that can assess the relative priority of patients on elective surgery waiting lists thus denying the provision of surgical support to the patients with higher urgency. Mostly the patients of general surgery are entertain with highly subjective "time-honoured" methods that are inadequate to measure and compare the urgency of surgical procedure. Objective: A methodology of assigning priorities to patients on elective surgery waiting lists has been presented in this paper using weighted criteria objectives. The objectives hve been chosen and assigned weights based on hospital conditions, and in consultation with the surgeons in hospital in Pakistan. Methods: The proposed methodology presents two working contributions; first, a scoring mechanism based on MeNTS scoring system with weighted criterion that objectively translate the condition of patient prior to the surgical procedure; and second, a patient prioritization methodology to select patients for surgeries according to the corresponding scores. Detailed simulation results from actual patient data have been presented to evaluate the effectiveness of the proposed methodology, and its applicability and ease of use has been tested in real-time by surgeons while providing consultations to their patients. Results: The proposed methodology outperforms the traditional "first-come-first-serve" methodology as there was a 30% reduction in average waiting time in elective surgery waiting lists (from 4.246 to 2.956 days) with 103 (90%) of patients being entertained before or within the unprioritized surgeries time span, with 94 patients having surgery within 1 day of being on waiting list (an increase of 47 patients). Moreover, transparency and equity were also found in the adaptation of this strategy to prioritize the elective surgery patients. Conclusions: Prioritizing patients on elective surgery waiting lists is an important concern in surgical field. In most of the methodologies presented in earlier research, prioritization of patients for surgery is carried out subjectively. This study shows that the proposed technique has the potential to decrease the waiting times for patients on elective surgery waiting lists, as well as be presented as an objective methodology for preparing the elective surgery waiting lists to increase the transparency in waiting list.

Novel fNIRS study on homogeneous symmetric feature-based transfer learning for brain-computer interface.

The brain-computer interface (BCI) provides an alternate means of communication between the brain and external devices by recognizing the brain activities and translating them into external commands. The functional Near-Infrared Spectroscopy (fNIRS) is becoming popular as a non-invasive modality for brain activity detection. The recent trends show that deep learning has significantly enhanced the performance of the BCI systems. But the inherent bottleneck for deep learning (in the domain of BCI) is the requirement of the vast amount of training data, lengthy recalibrating time, and expensive computational resources for training deep networks. Building a high-quality, large-scale annotated dataset for deep learning-based BCI systems is exceptionally tedious, complex, and expensive. This study investigates the novel application of transfer learning for fNIRS-based BCI to solve three objective functions (concerns), i.e., the problem of insufficient training data, reduced training time, and increased accuracy. We applied symmetric homogeneous feature-based transfer learning on convolutional neural network (CNN) designed explicitly for fNIRS data collected from twenty-six (26) participants performing the n-back task. The results suggested that the proposed method achieves the maximum saturated accuracy sooner and outperformed the traditional CNN model on averaged accuracy by 25.58% in the exact duration of training time, reducing the training time, recalibrating time, and computational resources.

Motor Training Using Mental Workload (MWL) With an Assistive Soft Exoskeleton System: A Functional Near-Infrared Spectroscopy (fNIRS) Study for Brain-Machine Interface (BMI).

Mental workload is a neuroergonomic human factor, which is widely used in planning a system's safety and areas like brain-machine interface (BMI), neurofeedback, and assistive technologies. Robotic prosthetics methodologies are employed for assisting hemiplegic patients in performing routine activities. Assistive technologies' design and operation are required to have an easy interface with the brain with fewer protocols, in an attempt to optimize mobility and autonomy. The possible answer to these design questions may lie in neuroergonomics coupled with BMI systems. In this study, two human factors are addressed: designing a lightweight wearable robotic exoskeleton hand that is used to assist the potential stroke patients with an integrated portable brain interface using mental workload (MWL) signals acquired with portable functional near-infrared spectroscopy (fNIRS) system. The system may generate command signals for operating a wearable robotic exoskeleton hand using two-state MWL signals. The fNIRS system is used to record optical signals in the form of change in concentration of oxy and deoxygenated hemoglobin (HbO and HbR) from the pre-frontal cortex (PFC) region of the brain. Fifteen participants participated in this study and were given hand-grasping tasks. Two-state MWL signals acquired from the PFC region of the participant's brain are segregated using machine learning classifier-support vector machines (SVM) to utilize in operating a robotic exoskeleton hand. The maximum classification accuracy is 91.31%, using a combination of mean-slope features with an average information transfer rate (ITR) of 1.43. These results show the feasibility of a two-state MWL (fNIRS-based) robotic exoskeleton hand (BMI system) for hemiplegic patients assisting in the physical grasping tasks.

Enhanced Accuracy for Multiclass Mental Workload Detection Using Long Short-Term Memory for Brain-Computer Interface.

Cognitive workload is one of the widely invoked human factors in the areas of human-machine interaction (HMI) and neuroergonomics. The precise assessment of cognitive and mental workload (MWL) is vital and requires accurate neuroimaging to monitor and evaluate the cognitive states of the brain. In this study, we have decoded four classes of MWL using long short-term memory (LSTM) with 89.31% average accuracy for brain-computer interface (BCI). The brain activity signals are acquired using functional near-infrared spectroscopy (fNIRS) from the prefrontal cortex (PFC) region of the brain. We performed a supervised MWL experimentation with four varying MWL levels on 15 participants (both male and female) and 10 trials of each MWL per participant. Real-time four-level MWL states are assessed using fNIRS system, and initial classification is performed using three strong machine learning (ML) techniques, support vector machine (SVM), k-nearest neighbor (k-NN), and artificial neural network (ANN) with obtained average accuracies of 54.33, 54.31, and 69.36%, respectively. In this study, novel deep learning (DL) frameworks are proposed, which utilizes convolutional neural network (CNN) and LSTM with 87.45 and 89.31% average accuracies, respectively, to solve high-dimensional four-level cognitive states classification problem. Statistical analysis, t-test, and one-way F-test (ANOVA) are also performed on accuracies obtained through ML and DL algorithms. Results show that the proposed DL (LSTM and CNN) algorithms significantly improve classification performance as compared with ML (SVM, ANN, and k-NN) algorithms.