Yee Mon Aung

Estimation of Upper Limb Joint Angle Using Surface EMG Signal

In the development of robot-assisted rehabilitation systems for upper limb rehabilitation therapy, human electromyogram (EMG) is widely used due to its ability to detect the user intended motion. EMG is one kind of biological signal that can be recorded to evaluate the performance of skeletal muscles by means of a sensor electrode. Based on recorded EMG signals, user intended motion could be extracted via estimation of joint torque, force or angle. Therefore, this estimation becomes one of the most important factors to achieve accurate user intended motion. In this paper, an upper limb joint angle estimation methodology is proposed. A back propagation neural network (BPNN) is developed to estimate the shoulder and elbow joint angles from the recorded EMG signals. A Virtual Human Model (VHM) is also developed and integrated with BPNN to perform the simulation of the estimated angle. The relationships between sEMG signals and upper limb movements are observed in this paper. The effectiveness of our developments is evaluated with four healthy subjects and a VHM simulation. The results show that the methodology can be used in the estimation of joint angles based on EMG.

Shoulder rehabilitation with biofeedback simulation

More than 62,000 Australians were suffered from Traumatic Brain Injury, Spinal Cord Injury and stroke in 2011. The results of such injuries lead to physical disabilities that yield to prohibiting from performing a persons daily life activities and reduce the quality of life. Moreover, the cost of such affects is almost AUD 13 billion per annum in health care sector. To overcome such situation, rehabilitation is essential for recovery to return to normal life. This paper presents the development of an effective shoulder rehabilitation system with motivational approach. Our development aims to reduce the one-to-one patient-therapist treatment relation contact, make it less regular consultation, and reduce high health care cost. The system is made up of two modules: rehabilitation exercises module where rehabilitation exercises are developed and real-time biofeedback simulation module that detect the active muscle in real time based on sEMG threshold which is predefined by therapist. Four rehabilitation exercises are developed and integrated with biofeedback system. The effectiveness of proposed system has been evaluated through testing with ten subjects and got high performance. The system has demonstrated in Port Kembla Rehabilitation Hospital.

Rehabilitation exercise with real-time muscle simulation based EMG and AR

Traumatic Brain Injury (TBI), Spinal Cord Injury (SCI) and Stroke or Cerebrovascular Accident (CVA) cause severe physical disability and affect the persons quality of life. Therefore, rehabilitation therapies are essential for those patients to promote their quality of life and restore their lost functions to perform daily live activities. Daily care cost is very high for TBI, SCI and CVA that become major problem for the patients and their families. Moreover, shortage of therapists is one of the major problems in rehabilitation hospitals due to one to one basic training. To overcome these problems, this paper presents low cost motivated rehabilitation system with minimum supervision of therapist for upper limb system. The propose system can be used as a home based or rehabilitation center therapy system. It is has two modules namely rehabilitation exercise module and real-time muscle simulation module. Several Augmented Reality (AR) games have developed as rehabilitation exercises and integrated with real-time muscle simulation to complete the system. Real-time muscle simulation was achieved based on patients electromyography (EMG) signals in real time. While the system will work to retrain the elastic brain via fast recovery method, it is also will close the gap for the required information, by therapists, about monitoring and tracks the patients muscle performance. The system has tested with five healthy subjects and revealed with potential rehabilitation system for disabled people.

Human computer interactive system for fast recovery based stroke rehabilitation

In Australia, about 88% of stroke survivors live at home with disabilities affecting their daily life activities and quality of their lives. Therefore, there is a need to improve their lost functions and promote their lives via rehabilitation process. One way to improve the stroke rehabilitation process is through human interactive system, which can be achieved by augmented reality technology. This development draws from the work currently being pursued in the gaming industry to make the augmented reality technology more accessible to the medical industry for the improvement of stroke rehabilitation. In this paper, two augmented reality games: Pong Game and Goal Keeper Game were developed. These games have been designed for rehabilitation with consideration to human interactive systems and have features such as on-screen feedbacks and high immersive value to keep stroke victims motivated in the rehabilitation process. The developed games were aimed to replace boring and repetitive traditional rehabilitation exercises. This paper details the success of implementing augmented reality into the rehabilitation process, which will in turn contribute to society by minimizing the number of people living at home with stroke related disabilities and the requirement for direct supervision from therapist.

A novel upper limb rehabilitation system with self-driven virtual arm illusion

This paper proposes a novel upper extremity rehabilitation system with virtual arm illusion. It aims for fast recovery from lost functions of the upper limb as a result of stroke to provide a novel rehabilitation system for paralyzed patients. The system is integrated with a number of technologies that include Augmented Reality (AR) technology to develop game like exercise, computer vision technology to create the illusion scene, 3D modeling and model simulation, and signal processing to detect user intention via EMG signal. The effectiveness of the developed system has evaluated via usability study and questionnaires which is represented by graphical and analytical methods. The evaluation provides with positive results and this indicates the developed system has potential as an effective rehabilitation system for upper limb impairment.

Augmented reality-based RehaBio system for shoulder rehabilitation

This paper presents the development of rehabilitation with biofeedback (RehaBio) system for upper-limb rehabilitation that can be used to restore the upper-limb lost functions of patients who suffer from traumatic brain injury (TBI), spinal cord injury (SCI) or cerebrovascular accident (CVA), which generally result in paralysis on one side of the body. The system aims to close the gap in the requirements of one-to-one attention between physiotherapist and patient, to replace boring traditional upper-limb rehabilitation exercises and to reduce high healthcare cost. RehaBio is made up of three major modules: database module, rehabilitation exercise module and biofeedback simulation module. Database module provides the information of the patients and their rehabilitation progress while rehabilitation exercise module provides with effective and motivated exercises based on augmented reality approach. Biofeedback simulation module in RehaBio serves two purposes: from physiotherapist point of view, it provides the tracking of biofeedback information of patient’s muscle performance and activities. From the patient’s point of view, it serves as a visual reflection of current activated muscles that create as an additional motivation during training process. The effectiveness of the RehaBio system was evaluated by performing the experiments and provided with promising results.

The estimation of Knee Joint angle based on Generalized Regression Neural Network (GRNN)

Capturing of the intended action of the patient and provide assistance as needed is required in the robotic rehabilitation device. The intended action data that can be extracted from surface Electromyography (sEMG) signal may include the intended posture, intended torque, intended knee joint angle and intended desired impedance of the patient. Utilizing such data to drive robotic assistive device like exoskeleton requires a multilayer control mechanism to achieve a smooth Human Machine Interaction force. It is very important that the controller for gait assistive device is able to extract as many information as possible from the patient muscle with impaired limb and predict different parameters associated with gait cycle. Joint kinematics and dynamics are important to be estimated as the Gait cycle of lower limb consists of flexion and extension postures at knee, hip and ankle joints respectively. This paper proposes a new classification and estimation technique of the lower limb joint kinematics and dynamics based on sEMG signal to predict specifically knee joint flexion and extension postures as well as Knee Joint angles of two postures. In the technique proposed, the feature data of raw sEMG data have been filtered with a second order digital filter and then input to train the Neural Network (NN) and to Generalized Regression Neural Network (GRNN) model to estimate the angle of flexion and extension. The GRNN and NN have been tested with RMS, LOG, MAV, IAV, Hjorth, VAR and MSWT features. GRNN with Multi scale Wavelet Transform (MSWT) feature has ensured 1.5704 Mean Square Error which is very promising accuracy. The SVM has been used to predict postures (flexion and extension). The SVM also has classified flexion and extension with accuracy over 95%.

SCALED CONJUGATE GRADIENT BASED DECISION SUPPORT SYSTEM FOR AUTOMATED DIAGNOSIS OF SKIN CANCER

Melanoma is the most deathful form of skin cancer but early diagnosis can ensure a high rate of survival. Early diagnosis is one of the greatest challenges due to lack of experience of general practitioners (GPs). This paper presents a clinical decision support system designed for the use of general practitioners, aiming to save time and resources in the diagnostic process. Segmentation, pattern recognition, and lesion detection are the important steps in the proposed decision support system. The system analyses the images to extract the affected area using a novel proposed segmentation method. It determinates the underlying features which indicate the difference between melanoma and benign images and makes a decision. Considering the efficiency of neural networks in classification of complex data, scaled conjugate gradient based neural network is used for classification. The presented work also considers analyzed performance of other efficient neural network training algorithms on the specific skin lesion diagnostic problem and discussed the corresponding findings. The best diagnostic rates obtained through the proposed decision support system are around 92%.

Continuous prediction of shoulder joint angle in real-time

Continuous prediction of dynamic joint angle from surface electromyography (sEMG) signal is one of the most important applications in rehabilitation area for stroke survivors as these can directly reflect the user motor intention. In this study, new shoulder joint angle prediction method in real-time based on the biosignal: sEMG is proposed. Firstly, sEMG to muscle activation model is built up to extract the user intention from contracted muscles and then feed into the extreme learning machine (ELM) to estimate the angle in real-time continuously. The estimated joint angle is then compare with the webcam captured joint angle to analyze the effectiveness of the proposed method. The result reveals that correlation coefficient between actual angle and estimated angle is as high as 0.96 in offline and 0.93 in online mode. In addition, the processing time for the estimation is less than 32ms in both cases which is within the semblance of human natural movements. Therefore, the proposed method is able to predict the user intended movement very well and naturally and hence, it is suitable for real-time applications.

REAL TIME BIOSIGNAL-DRIVEN ILLUSION SYSTEM FOR UPPER LIMB REHABILITATION

This paper presents design and development of real time biosignal-driven illusion system: Augmented Reality based Illusion System (ARIS) for upper limb motor rehabilitation. ARIS is a hospital / home based selfmotivated whole arm rehabilitation system that aims to improve and restore the lost upper limb functions due to Cerebrovascular Accident (CVA) or stroke. Taking the advantage of human brain plasticity nature, the system incorporates with number of technologies to provide fast recovery by re-establishing the neural pathways and synapses that able to control the mobility. These technologies include Augmented Reality (AR) where illusion environment is developed, computer vision technology to track multiple colors in real time, EMG acquisition system to detect the user intention in real time and 3D modelling library to develop Virtual Arm (VA) model where human biomechanics are applied to mimic the movement of real arm. The system operates according to the user intention via surface electromyography (sEMG) threshold level. In the case of real arm cannot reach to the desired position, VA will take over the job of real arm to complete the exercise. The effectiveness of the developed ARIS has evaluated via questionnaire, graphical and analytical measurements which provided with positive results.