Search

In this work, a predictive maintenance system is discussed as a modern solution for reducing downtimes in complex systems such as airplanes’ jet engines. The developed predictive maintenance system is based on prognostic and predictive algorithms which will be constructed by using machine learning techniques. Bayesian theorem is specially studied and employed for this purpose in this paper. The design and implementation of a Naive Bayesian classifier will be presented to demonstrate and challenge the practicality of the method. A turbofan jet engine health check system was chosen as a complex and live industrial testbed example. We also demonstrate that the system in question has a high entropy and despite this, the Bayesian approach is sufficient enough to eliminate the critical errors as well as maintain a satisfactory overall accuracy.

Dementia and stroke have been considered two major causes of disability in the UK. The field of rehabilitation robotics emerged since early 90’s as a tool to assist therapists with assessing stroke and dementia patients and providing the necessary therapy. The present article aims to offer a review of how current hard robotic devices utilized in upper and lower limb rehabilitation, and how successful they were in increasing the efficiency of the recovery process. Their bottlenecks and short comes are discussed and soft robotics are presented as alternative techniques to resolve them. Novel pneumatic Muscle Actuators (pMA) capable of bending in contrary to traditional pMA are studied here. In particular, we investigate and propose a novel exoskeleton soft robotic arm, which made of several novel pMA for elbow joint rehabilitation. For this purpose, analysis, design, integration and characterization of the proposed arm are presented and geometrical and numerical models are obtained. This study shows that how our proposed exoskeleton soft robotic arm with a lower cost can increase the efficiency of rehabilitation recovery process.

Early indication of some diseases such as Parkinson and Multiple Sclerosis often manifests with walking difficulties. Gait analysis provides vital information for assessing the walking patterns during the locomotion, especially when the outcomes are quantitative measures. This paper explores methods that can respond to the changes in the gait features during the swing stage using Kinect Camera, a low cost, marker-free, and portable device offered by Microsoft. Kinect has been exploited for tracking the skeletal positional data of body joints to assess and evaluate the gait performance. Linear kinematic gait features are extracted to discriminate between walking speeds by using five supervised modulation based machine-learning classifiers as follow: Decision Trees (DT), linear/nonlinear Support Vector Machines (SVMs), subspace discriminant and k-Nearest Neighbour (k-NN). The role of modulation techniques such as Frequency Modulation (FM) for increasing the efficiency of classifiers have been explored. The experimental results show that all five classifiers can successfully distinguish gait futures signal associated with walking patterns with high accuracy (average expected value of 86.19% with maximum of 92.9%). This validates the capability of the presented methodology in detecting key “indicators” of health events.\ud Keywords: Gait Analysis, Kinematic Gait Features, Amplitude and Frequency Modulations, Baseband Signal, Passband Mapping, Machine-Learning, Classification Technique

Human gait analysis can provide vital information especially with optical sensor to track and asses the changes in gait pattern. In this paper, the Kinect v2 based system is used for classifying a several walk speeds and Convolutional Encoder (CE) technique is validated. Positional skeletal data is collected from the lower body's joints and Amplitude Modulation (AM) is used to modify gait signal for extracting the gait features namely baseband frequency and modulation index. The obtained results show that 97.8% of the considered parameters are appropriate for classifying between three kinds of walk speeds.