Anwar P.P. Abdul Majeed

The identification of high potential archers based on fitness and motor ability variables: A Support Vector Machine approach

Support Vector Machine (SVM) has been shown to be an effective learning algorithm for classification and prediction. However, the application of SVM for prediction and classification in specific sport has rarely been used to quantify/discriminate low and high-performance athletes. The present study classified and predicted high and low-potential archers from a set of fitness and motor ability variables trained on different SVMs kernel algorithms. 50 youth archers with the mean age and standard deviation of 17.0 ± 0.6 years drawn from various archery programmes completed a six arrows shooting score test. Standard fitness and ability measurements namely hand grip, vertical jump, standing broad jump, static balance, upper muscle strength and the core muscle strength were also recorded. Hierarchical agglomerative cluster analysis (HACA) was used to cluster the archers based on the performance variables tested. SVM models with linear, quadratic, cubic, fine RBF, medium RBF, as well as the coarse RBF kernel functions, were trained based on the measured performance variables. The HACA clustered the archers into high-potential archers (HPA) and low-potential archers (LPA), respectively. The linear, quadratic, cubic, as well as the medium RBF kernel functions models, demonstrated reasonably excellent classification accuracy of 97.5% and 2.5% error rate for the prediction of the HPA and the LPA. The findings of this investigation can be valuable to coaches and sports managers to recognise high potential athletes from a combination of the selected few measured fitness and motor ability performance variables examined which would consequently save cost, time and effort during talent identification programme.

An intelligent active force control algorithm to control an upper extremity exoskeleton for motor recovery

This paper presents the modelling and control of a two degree of freedom upper extremity exoskeleton by means of an intelligent active force control (AFC) mechanism. The Newton-Euler formulation was used in deriving the dynamic modelling of both the anthropometry based human upper extremity as well as the exoskeleton that consists of the upper arm and the forearm. A proportional-derivative (PD) architecture is employed in this study to investigate its efficacy performing joint-space control objectives. An intelligent AFC algorithm is also incorporated into the PD to investigate the effectiveness of this hybrid system in compensating disturbances. The Mamdani Fuzzy based rule is employed to approximate the estimated inertial properties of the system to ensure the AFC loop responds efficiently. It is found that the IAFC-PD performed well against the disturbances introduced into the system as compared to the conventional PD control architecture in performing the desired trajectory tracking.

Modelling and Control of an Upper Extremity Exoskeleton for Rehabilitation

This paper presents the modelling and control of a two degree of freedom upper extremity exoskeleton for rehabilitation. The Lagrangian formulation was employed to obtain the dynamic modelling of both the anthropometric based human upper limb as well as the exoskeleton that comprises of the upper arm and the forearm. A proportional-derivative (PD) architecture is employed to investigate its efficacy performing a joint task trajectory tracking in performing flexion/extension on the elbow joint as well as the forward adduction/abduction on the shoulder joint. An active force control (AFC) algorithm is also incorporated into the aforementioned controller to examine its effectiveness in compensating disturbances. It was found from the study that the AFC-PD performed well against the disturbances introduced into the system without compromising its tracking performances as compared to the conventional PD control architecture.

Velocity Measurements Using High-Speed Imaging System for Impact Test

This paper presents the velocity measurements for an impact test on a laminated fibre-glass composite plate. The free flight kinematic properties of a blunt-nosed cylindrical projectile on the upstream and downstream of a test coupon were measured using a high-speed camera imaging system. A visual geometric detection technique is discussed and it is shown that the uncertainties of velocity measurements are associated with an imposed constraint on the camera viewing area and shutter speed.

Modelling and PID Control of a Quadrotor Aerial Robot

This paper elucidates the modeling of a + quadrotor configuration aerial vehicle and the design of its attitude and altitude controllers. The aircraft model consists of four fixed pitch angle propeller, each driven by an electric DC motor. The hovering flight of the quadrotor is governed by the Newton-Euler formulation. The attitude and altitude controls of the aircraft were regulated using heuristically tuned (Proportional-Integral-Derivative) PID controller. It was numerically simulated via Simulink that a PID controller was sufficient to bring the aircraft to the required altitude whereas the attitude of the vehicle is adequately controlled by a PD controller.

System integration and control of Dynamic Ankle Foot Orthosis for lower limb rehabilitation

Gait disorder is the inability of a person to assume upright position, maintain neither balance nor the aptitude to initiate and sustain rhythmic stepping. This form of disability may originate from cerebellar disease, stroke, spinal injury, cardiac disease or other general conditions that may bring about such disorder. Studies have shown that ones mobility may be improved with continuous locomotor activity. Traditional rehabilitation therapy is deemed labour as well as cost intensive. Rehabilitation robotics has been explored to address the drawbacks of conventional rehabilitation therapy and the increasing demand for gait rehabilitation. This paper presents a simple yet decent technique in the control and actuation of a new Dynamic Ankle-Foot Orthosis (DAFO) designed to rehabilitate the dorsiflexion and plantarflexion motion of the ankle. The DAFO is equipped with two force sensitive resistors (FSR), which act as a limit switch controlling the actuation of the DC motor to a certain dorsiflexion/plantarflexion motion according to the gait phases detected. The results show that the two FSR sensors are sufficient to detect gait phases and act as limit switches to control the actuation of the ankle DC motors, and thus proving the potential of the current system and design for future application.

A hybrid active force control of a lower limb exoskeleton for gait rehabilitation

Abstract Owing to the increasing demand for rehabilitation services, robotics have been engaged in addressing the drawbacks of conventional rehabilitation therapy. This paper focuses on the modelling and control of a three-link lower limb exoskeleton for gait rehabilitation that is restricted to the sagittal plane. The exoskeleton that is modelled together with a human lower limb model is subjected to a number of excitations at its joints while performing a joint space trajectory tracking, to investigate the effectiveness of the proposed controller in compensating disturbances. A particle swarm optimised active force control strategy is proposed to facilitate disturbance rejection of a conventional proportional-derivative (PD) control algorithm. The simulation study provides considerable insight into the robustness of the proposed method in attenuating the disturbance effect as compared to the conventional PD counterpart without compromising its tracking performance. The findings from the study further suggest its potential employment on a lower limb exoskeleton.

Psycho-Fitness Parameters in the Identification of High-Potential Archers

This chapter highlights the relationship of psycho-fitness variables towards the recognition of HPA and LPA. The variables, namely hand grip, upper muscle strength, core muscle strength, static balance, vertical jump and athletic coping skills, were shown to be able to provide a reasonable clustering of the archers. Moreover, it was established that the coarse variation of the k-NN model yields the better classification of the HPA and LPA.

Psychological Variables in Ascertaining Potential Archers

This chapter evaluates the relationship of athletic psychological coping skills with the archers’ performance. It was demonstrated from the study that the possession of certain psychological coping skills, namely coping with adversity, coachability, peaking under pressure, concentration, confidence and achievement motivation, goal setting and mental preparation is non-trivial in the achievement of high archery shooting score. It was also shown that the tansig-based ANN model could provide the better classification of HPA and LPA.

Anthropometry Correlation Towards Archery Performance

This chapter assesses the association of a selection of anthropometry parameters in identifying HPA and LPA. It was shown that the selected parameters, i.e. abdominal circumference, arm span, calf circumference, height, hip circumference, thigh circumference and weight, are essential in the identification of potential of the archers. Furthermore, it was demonstrated that the linear SVM variation model provided the best prediction capability amongst the other evaluated SVM models.