Branko G. Celler

Unsupervised machine-learning method for improving the performance of ambulatory fall-detection systems

BackgroundFalls can cause trauma, disability and death among older people. Ambulatory accelerometer devices are currently capable of detecting falls in a controlled environment. However, research suggests that most current approaches can tend to have insufficient sensitivity and specificity in non-laboratory environments, in part because impacts can be experienced as part of ordinary daily living activities.MethodWe used a waist-worn wireless tri-axial accelerometer combined with digital signal processing, clustering and neural network classifiers. The method includes the application of Discrete Wavelet Transform, Regrouping Particle Swarm Optimization, Gaussian Distribution of Clustered Knowledge and an ensemble of classifiers including a multilayer perceptron and Augmented Radial Basis Function (ARBF) neural networks.ResultsPreliminary testing with 8 healthy individuals in a home environment yields 98.6% sensitivity to falls and 99.6% specificity for routine Activities of Daily Living (ADL) data. Single ARB and MLP classifiers were compared with a combined classifier. The combined classifier offers the greatest sensitivity, with a slight reduction in specificity for routine ADL and an increased specificity for exercise activities. In preliminary tests, the approach achieves 100% sensitivity on in-group falls, 97.65% on out-group falls, 99.33% specificity on routine ADL, and 96.59% specificity on exercise ADL.ConclusionThe pre-processing and feature-extraction steps appear to simplify the signal while successfully extracting the essential features that are required to characterize a fall. The results suggest this combination of classifiers can perform better than MLP alone. Preliminary testing suggests these methods may be useful for researchers who are attempting to improve the performance of ambulatory fall-detection systems.

Automatic bearing fault diagnosis using particle swarm clustering and Hidden Markov Model

Ball bearings are integral elements in most rotating manufacturing machineries. While detecting defective bearing is relatively straightforward, discovering the source of defect requires advanced signal processing techniques. This paper proposes an automatic bearing defect diagnosis method based on Swarm Rapid Centroid Estimation (SRCE) and Hidden Markov Model (HMM). Using the defect frequency signatures extracted with Wavelet Kurtogram and Cepstral Liftering, SRCE+HMM achieved on average the sensitivity, specificity, and error rate of 98.02%, 96.03%, and 2.65%, respectively, on the bearing fault vibration data provided by Case School of Engineering of the Case Western Reserve University (CSE) which warrants further investigation. Graphical abstractDisplay Omitted HighlightsThis paper proposes an automatic fault diagnosis algorithm for rolling bearing defects.The classification algorithm was Hidden Markov Model optimized with swarm clustering.The features were defect harmonics extracted using wavelet kurtogram and cepstral liftering.The bearing fault vibration data was obtained from Case Western Reserve University.Sensitivity and specificity of 98.02% and 96.03% were achieved on the test data.

WebRTC-based video conferencing service for telehealth

Existing video conferencing systems that are often used in telehealth services have been criticized for a number of reasons: (a) they are often too expensive to purchase and maintain, (b) they use proprietary technologies that are incompatible to each other, and (c) they require fairly skilled IT personnel to maintain the system. There is a need for less expensive, compatible, and easy-to-use video conferencing system. The web real-time communication (WebRTC) promises to deliver such a solution by enabling web browsers with real-time communications capabilities via simple JavaScript APIs. Utilizing WebRTC, users can conduct video/audio calls and data sharing through web browsers without having to purchase or download extra software. Though the promise and prospective of WebRTC have been agreed on, there have not been many cases of real life applications (in particular in telehealth) that utilizes the WebRTC. In this paper, we present our practical experience in the design and implementation of a video conferencing system for telehealth based on WebRTC. Our video conferencing system is a part of a large tele-home monitoring project that is being carried out at six locations in five different states in Australia. One of the aims of the project is to evaluate whether high-bandwidth enabled telehealth services, delivered through tele-home monitoring, can be cost effective, and improve healthcare outcomes and access to care. This paper however focuses on WebRTC-based video conferencing system which allows online meetings between remotely located care coordinators and patients at their home. We discuss the underlying issues, detailed design and implementation, and current limitations of using WebRTC in a real life application.

Home Telemonitoring of Vital Signs—Technical Challenges and Future Directions

The telemonitoring of vital signs from the home is an essential element of telehealth services for the management of patients with chronic conditions, such as congestive heart failure (CHF), chronic obstructive pulmonary disease (COPD), diabetes, or poorly controlled hypertension. Telehealth is now being deployed widely in both rural and urban settings, and in this paper, we discuss the contribution made by biomedical instrumentation, user interfaces, and automated risk stratification algorithms in developing a clinical diagnostic quality longitudinal health record at home. We identify technical challenges in the acquisition of high-quality biometric signals from unsupervised patients at home, identify new technical solutions and user interfaces, and propose new measurement modalities and signal processing techniques for increasing the quality and value of vital signs monitoring at home. We also discuss use of vital signs data for the automated risk stratification of patients, so that clinical resources can be targeted to those most at risk of unscheduled admission to hospital. New research is also proposed to integrate primary care, hospital, personal genomic, and telehealth electronic health records, and apply predictive analytics and data mining for enhancing clinical decision support.

Fault detection and identification spanning multiple processes by integrating PCA with neural network

This paper proposes an effective fault detection and identification method for systems which perform in multiple processes. One such type of system investigated in this paper is COSMED K4b^2. K4b^2 is a standard portable electrical device designed to test pulmonary functions in various applications, such as athlete training, sports medicine and health monitoring. However, its actual sensor outputs and received data may be disturbed by Electromagnetic Interference (EMI), body artifacts, and device malfunctions/faults, which might cause misinterpretations of activities or statuses to people being monitored. Although some research is reported to detect faults in specific steady state, normal approach may yield false alarms in multi-processes applications. In this paper, a novel and comprehensive method, which merges statistical analysis and intelligent computational model, is proposed to detect and identify faults of K4b^2 during exercise monitoring. Firstly the principal component analysis (PCA) is utilized to acquire main features of measured data and then K-means is combined to cluster various processes for abnormalities detection. When faults are detected, a back propagation (BP) neural network is constructed to identify and isolate faults. The effectiveness and feasibility of the proposed model method is finally verified with experimental data.

Advanced portable remote monitoring system for the regulation of treadmill running exercises.

OBJECTIVEnThis study aims to develop an advanced portable remote monitoring system to supervise high intensity treadmill exercises.nnnMATERIALS AND METHODSnThe supervisory level of the developed hierarchical system is implemented on a portable monitoring device (iPhone/iPad) as a client application, while the real-time control of treadmill exercises is accomplished by using an on-line adaptive neural network control scheme in a local computer system. During training or rehabilitation exercises, the intensity (measured by heart rate) is regulated by simultaneously manipulating both treadmill speed and gradient. In order to achieve adaptive tracking performance, a neural network controller has been designed and implemented.nnnRESULTSnSix real-time experiments have been conducted to test the performance of the developed monitoring system. Experimental results obtained in real-time with heart-rate set-point varying from 145 bpm to 180 bmp, demonstrate that the proposed system can quickly and accurately regulate exercise intensity of treadmill running exercises with desired performance (no overshoot, settling time Ts ≤ 100 s). Subjects aged from 29 to 38 years old participated in different set-point experiments to confirm the systems adaptability to inter- and intra-model uncertainty. The desired system performance under external disturbances has also been confirmed in a final real-time experiment demonstrating a user carrying the 10 kg bag then removing it during the exercise.nnnCONCLUSIONnIn contrast with conventional control approaches, the proposed adaptive controller achieves better heart rate tracking performance under inter- and intra-model uncertainty and external disturbances. The developed system can automatically adapt to various individual exercisers and a range of exercise intensity.

An equivalent circuit model for onset and offset exercise response

BackgroundThe switching exercise (e.g., Interval Training) has been a commonly used exercise protocol nowadays for the enhancement of exerciser’s cardiovascular fitness. The current difficulty for simulating human onset and offset exercise responses regarding the switching exercise is to ensure the continuity of the outputs during onset-offset switching, as well as to accommodate the exercise intensities at both onset and offset of exercise.MethodsTwenty-one untrained healthy subjects performed treadmill trials following both single switching exercise (e.g., single-cycle square wave protocol) and repetitive switching exercise (e.g., interval training protocol). During exercise, heart rate (HR) and oxygen uptake (VO 2) were monitored and recorded by a portable gas analyzer (K4b 2, Cosmed). An equivalent single-supply switching resistance-capacitor (RC) circuit model was proposed to accommodate the observed variations of the onset and offset dynamics. The single-cycle square wave protocol was utilized to investigate the respective dynamics at onset and offset of exercise with the aerobic zone of approximate 70% - 77% of HR max, and verify the adaption feature for the accommodation of different exercise strengths. The design of the interval training protocol was to verify the transient properties during onset-offset switching. A verification method including Root-mean-square-error (RMSE) and correlation coefficient, was introduced for comparisons between the measured data and model outputs.ResultsThe experimental results from single-cycle square wave exercises clearly confirm that the onset and offset characteristics for both HR and VO 2 are distinctly different. Based on the experimental data for both single and repetitive square wave exercise protocols, the proposed model was then presented to simulate the onset and offset exercise responses, which were well correlated indicating good agreement with observations.ConclusionsCompared with existing works, this model can accommodate the different exercise strengths at both onset and offset of exercise, while also depicting human onset and offset exercise responses, and guarantee the continuity of outputs during onset-offset switching. A unique adaption feature by allowing the time constant(Continued on next page) (Continued from previous page)and steady state gain to re-shift back to their original states, more closely mimics the different exercise strengths during normal daily exercise activities.

Modelling and regulating of cardio-respiratory response for the enhancement of interval training

BackgroundThe interval training method has been a well known exercise protocol which helps strengthen and improve one’s cardiovascular fitness.PurposeTo develop an effective training protocol to improve cardiovascular fitness based on modelling and analysis of Heart Rate (HR) and Oxygen Uptake (VO2) dynamics.MethodsIn order to model the cardiorespiratory response to the onset and offset exercises, the (K4b2, Cosmed) gas analyzer was used to monitor and record the heart rate and oxygen uptake for ten healthy male subjects. An interval training protocol was developed for young health users and was simulated using a proposed RC switching model which was presented to accommodate the variations of the cardiorespiratory dynamics to running exercises. A hybrid system model was presented to describe the adaptation process and a multi-loop PI control scheme was designed for the tuning of interval training regime.ResultsBy observing the original data for each subject, we can clearly identify that all subjects have similar HR and VO2 profiles. The proposed model is capable to simulate the exercise responses during onset and offset exercises; it ensures the continuity of the outputs within the interval training protocol. Under some mild assumptions, a hybrid system model can describe the adaption process and accordingly a multi-loop PI controller can be designed for the tuning of interval training protocol. The self-adaption feature of the proposed controller gives the exerciser the opportunity to reach his desired setpoints after a certain number of training sessions.ConclusionsThe established interval training protocol targets a range of 70-80% of HRmax which is mainly a training zone for the purpose of cardiovascular system development and improvement. Furthermore, the proposed multi-loop feedback controller has the potential to tune the interval training protocol according to the feedback from an individual exerciser.

A study on the implementation of large-scale home telemonitoring service

We present the early findings from a longitudinal study of a multi-site home telemonitoring program for chronic disease management. The study aims to find out how the telehealth service is integrated into existing models of care at each site and how it impacts on practices and care processes within each particular setting. We identified potential implementation barriers perceived by clinicians. We highlight differences in healthcare settings and various ways that structures and practices have been configured in these sites. Our study seeks to expend the focus of research longitudinally and across different local settings and contributes to recent research in large-scale and home care applications.

A reliable medium access mechanism based on priorities for wireless body sensor networks

Wireless body sensor networks (WBSN) provide health related information for monitoring or professional analysis by collecting various signals of human body or environment information with sensors. But different data acquired in many applications have different transmission requirements. The dropping of life-critical messages could possibly create life threatening results if the network is not reliable. To improve the reliability this paper proposes a novel reliable medium access mechanism (RMAM) which guarantees transmission of data with different priorities in less delay and energy consumption. The mechanism is designed and evaluated by Castalia. The improved performances of latency, packets breakdown and energy consumption are analyzed and depicted with comparison.