Shafriza Nisha Basah

Technologies for Assessment of Motor Disorders in Parkinson’s Disease: A Review

Parkinson’s Disease (PD) is characterized as the commonest neurodegenerative illness that gradually degenerates the central nervous system. The goal of this review is to come out with a summary of the recent progress of numerous forms of sensors and systems that are related to diagnosis of PD in the past decades. The paper reviews the substantial researches on the application of technological tools (objective techniques) in the PD field applying different types of sensors proposed by previous researchers. In addition, this also includes the use of clinical tools (subjective techniques) for PD assessments, for instance, patient self-reports, patient diaries and the international gold standard reference scale, Unified Parkinson Disease Rating Scale (UPDRS). Comparative studies and critical descriptions of these approaches have been highlighted in this paper, giving an insight on the current state of the art. It is followed by explaining the merits of the multiple sensor fusion platform compared to single sensor platform for better monitoring progression of PD, and ends with thoughts about the future direction towards the need of multimodal sensor integration platform for the assessment of PD.

New newborn jaundice monitoring scheme based on combination of pre-processing and color detection method

Newborn jaundice is an apparent yellowing of the sclera or yellowish skin in newborn infants. This symptom is caused by a yellow pigment known as bilirubin. A high level of bilirubin in the infant is referred to as hyperbilirubinemia. Significant complications can occur if significantly increased bilirubin levels are not treated promptly. Severe hyperbilirubinemia can be caused by dehydration, lack of adequate nutritional intake, extravasation of blood, cephalohematoma, contusions and asphyxia, and may potentially cause kernicterus. Because many of these problems affect newborns, they may require critical care from specialty medical disciplines. Thus, in this paper we proudly proposed a Combination of pre-processing and the skin color detection method to detect jaundiced infants. Few statistical features are derived from the texture images and used as features to quantify infant image textures. Finally, a k-NN is employed as classifier for discriminating infant image textures. The experimental results reveal that the proposed method can act as a supplement to support earlier detection and more effective treatment due to improved jaundice recognition.

Wearable multimodal sensors for evaluation of patients with Parkinson disease

For a population that is moving towards an elderly stage of development, Parkinsons disease (PD) is characterized in the second place for the most common chronic progressive neurodegenerative illness in the world after Alzheimers disease, which regularly affects older generation. In the next 30 years, this amount is estimated to double due to the increase in the number of ageing people, as age is the leading key risk feature for the start of PD. There are a variety of medications, such as levodopa available to treat PD. With the latest advancement in healthcare technology, current researches permit the monitoring of PD with the application of wearable sensor technology. From previous studies, researchers have realized the application of wearable sensors as a useful tool that had the capability to differentiate various types of PD symptoms using uni-modal sensor or bi-modal sensors (accelerometer and gyroscope). Therefore, early diagnosis of PD through multimodal wearable technology can be considered for this aim. In this paper, the data are collected using on-body triaxial wearable sensors (accelerometer, gyroscope and magnetometer) for classifying people with Parkinson (PWP) from healthy controls. The system performance was characterized based on 10-fold cross validation method, applying the proposed time and frequency domain features and classification algorithms. The strength of the proposed method has been evaluated through several performance measures. In summary, these results show that the proposed machine learning techniques had ability in differentiating PWP from healthy controls with highest average accuracy, sensitivity, specificity and ROC of above 88%.

Analysis of planar-motion segmentation using affine fundamental matrix

Various computer-vision applications involve estimation of multiple motions from images of dynamic scenes. The exact nature of 3D-object motions and the camera parameters are often not known a priori and therefore, the most general motion model (fundamental matrix) is applied. Although the estimation of fundamental matrix and its use for motion segmentation are established, the conditions for segmentation of different types of motions are largely unaddressed. In this study, we analysed the feasibility of motion segmentation using affine-fundamental matrix, focusing on a scene includes multiple planar-motions, viewed by an uncalibrated camera. We show that the successful segmentation of planar motion depends on several scene and motion parameters. Conditions to guarantee successful segmentation are proposed via extensive experiments using synthetic images. Experiments using real-image data were set up to examine the relevance of those conditions to the scenarios in real applications. The experimental results demonstrate the capability of the proposed conditions to correctly predict the outcome of several segmentation scenarios and show the relevance of those conditions in real applications. In practice, the success of motion segmentation could be predicted from obtainable scene and motion parameters. Therefore these conditions serve as a guideline for practitioners in designing motion-segmentation solutions.

Use of technological tools for Parkinson's disease early detection: A review

Over the past fifteen years, quantitative monitoring of human motor control and movement disorders has been an emerging field of research. Recent studies state the fact that Malaysia has been experiencing improved health, longer life expectancy, and low mortality as well as declining fertility like other developing countries. As the population grows older, the prevalence of neurodegenerative diseases also increases exponentially. Parkinson disease (PD) is one of the most common chronic progressive neurodegenerative diseases that are related to movement disorders. After years of research and development solutions for detecting and assessing the symptoms severity in PD are quite limited. With current ongoing advance development sensor technology, development of various uni-modal approaches: technological tools to quantify PD symptom severity had drawn significance attention worldwide. The objective of this review is to compare some available technological tools for monitoring the severity of motor fluctuations in patients with Parkinson (PWP).

Empirical Wavelet Transform Based Features for Classification of Parkinson’s Disease Severity

Parkinson’s disease (PD) is a type of progressive neurodegenerative disorder that has affected a large part of the population till now. Several symptoms of PD include tremor, rigidity, slowness of movements and vocal impairments. In order to develop an effective diagnostic system, a number of algorithms were proposed mainly to distinguish healthy individuals from the ones with PD. However, most of the previous works were conducted based on a binary classification, with the early PD stage and the advanced ones being treated equally. Therefore, in this work, we propose a multiclass classification with three classes of PD severity level (mild, moderate, severe) and healthy control. The focus is to detect and classify PD using signals from wearable motion and audio sensors based on both empirical wavelet transform (EWT) and empirical wavelet packet transform (EWPT) respectively. The EWT/EWPT was applied to decompose both speech and motion data signals up to five levels. Next, several features are extracted after obtaining the instantaneous amplitudes and frequencies from the coefficients of the decomposed signals by applying the Hilbert transform. The performance of the algorithm was analysed using three classifiers – K-nearest neighbour (KNN), probabilistic neural network (PNN) and extreme learning machine (ELM). Experimental results demonstrated that our proposed approach had the ability to differentiate PD from non-PD subjects, including their severity level – with classification accuracies of more than 90% using EWT/EWPT-ELM based on signals from motion and audio sensors respectively. Additionally, classification accuracy of more than 95% was achieved when EWT/EWPT-ELM is applied to signals from integration of both signal’s information.

Design and Kinematic Analysis of Parallel Robot for Ankle Rehabilitation

Ankle injury is one of the most common injuries in sports or domestic related accidents. This injury can usually be treated via a number of rehabilitation exercises. However, currently rehabilitation of ankle injury directly depends of physiotherapy session administered by experts; which is tedious and expensive in nature. In this paper, we proposed a concept based on parallel mechanism to assist patients undergoing ankle rehabilitation procedures. This is due to a number of advantages of parallel mechanism as compared to serial mechanism higher payload-to-weight ratio, structure rigidity, accuracy and relatively simple solution. We reported our design process; including the concept generation and selection according to a number of relevant design parameters. After which, followed by embodiment design involving kinematic analysis of the proposed mechanism. The findings, in terms of conceptual design and kinematic analysis should be able to provide an insight for ankle rehabilitation based on suitable parallel mechanism.

Locality sensitivity discriminant analysis-based feature ranking of human emotion actions recognition.

[Purpose] Computational intelligence similar to pattern recognition is frequently confronted with high-dimensional data. Therefore, the reduction of the dimensionality is critical to make the manifold features amenable. Procedures that are analytically or computationally manageable in smaller amounts of data and low-dimensional space can become important to produce a better classification performance. [Methods] Thus, we proposed two stage reduction techniques. Feature selection-based ranking using information gain (IG) and Chi-square (Chisq) are used to identify the best ranking of the features selected for emotion classification in different actions including knocking, throwing, and lifting. Then, feature reduction-based locality sensitivity discriminant analysis (LSDA) and principal component analysis (PCA) are used to transform the selected feature to low-dimensional space. Two-stage feature selection-reduction methods such as IG-PCA, IG-LSDA, Chisq-PCA, and Chisq-LSDA are proposed. [Results] The result confirms that applying feature ranking combined with a dimensional-reduction method increases the performance of the classifiers. [Conclusion] The dimension reduction was performed using LSDA by denoting the features of the highest importance determined using IG and Chisq to not only improve the effectiveness but also reduce the computational time.

Facial-paralysis diagnostic system based on 3D reconstruction

The diagnostic process of facial paralysis requires qualitative assessment for the classification and treatment planning. This result is inconsistent assessment that potential affect treatment planning. We developed a facial-paralysis diagnostic system based on 3D reconstruction of RGB and depth data using a standard structured-light camera – Kinect 360 – and implementation of Active Appearance Models (AAM). We also proposed a quantitative assessment for facial paralysis based on triangular model. In this paper, we report on the design and development process, including preliminary experimental results. Our preliminary experimental results demonstrate the feasibility of our quantitative assessment system to diagnose facial paralysis.

Camera systems in human motion analysis for biomedical applications

Human Motion Analysis (HMA) system has been one of the major interests among researchers in the field of computer vision, artificial intelligence and biomedical engineering and sciences. This is due to its wide and promising biomedical applications, namely, bio-instrumentation for human computer interfacing and surveillance system for monitoring human behaviour as well as analysis of biomedical signal and image processing for diagnosis and rehabilitation applications. This paper provides an extensive review of the camera system of HMA, its taxonomy, including camera types, camera calibration and camera configuration. The review focused on evaluating the camera system consideration of the HMA system specifically for biomedical applications. This review is important as it provides guidelines and recommendation for researchers and practitioners in selecting a camera system of the HMA system for biomedical applications.