Ramona Rednic

A Web-Based System for Home Monitoring of Patients With Parkinson's Disease Using Wearable Sensors

This letter introduces MercuryLive, a platform to enable home monitoring of patients with Parkinsons disease (PD) using wearable sensors. MercuryLive contains three tiers: a resource-aware data collection engine that relies upon wearable sensors, web services for live streaming and storage of sensor data, and a web-based graphical user interface client with video conferencing capability. Besides, the platform has the capability of analyzing sensor (i.e., accelerometer) data to reliably estimate clinical scores capturing the severity of tremor, bradykinesia, and dyskinesia. Testing results showed an average data latency of less than 400 ms and video latency of about 200 ms with video frame rate of about 13 frames/s when 800 kb/s of bandwidth were available and we used a 40% video compression, and data feature upload requiring 1 min of extra time following a 10 min interactive session. These results indicate that the proposed platform is suitable to monitor patients with PD to facilitate the titration of medications in the late stages of the disease.

Home monitoring of patients with Parkinson's disease via wearable technology and a web-based application

Objective long-term health monitoring can improve the clinical management of several medical conditions ranging from cardiopulmonary diseases to motor disorders. In this paper, we present our work toward the development of a home-monitoring system. The system is currently used to monitor patients with Parkinsons disease who experience severe motor fluctuations. Monitoring is achieved using wireless wearable sensors whose data are relayed to a remote clinical site via a web-based application. The work herein presented shows that wearable sensors combined with a web-based application provide reliable quantitative information that can be used for clinical decision making.

Edge Mining the Internet of Things

This paper examines the benefits of edge mining -data mining that takes place on the wireless, battery-powered, and smart sensing devices that sit at the edge points of the Internet of Things. Through local data reduction and transformation, edge mining can quantifiably reduce the number of packets that must be sent, reducing energy usage, and remote storage requirements. In addition, edge mining has the potential to reduce the risk in personal privacy through embedding of information requirements at the sensing point, limiting inappropriate use. The benefits of edge mining are examined with respect to three specific algorithms: linear Spanish inquisition protocol (L-SIP), ClassAct, and bare necessities (BN), which are all instantiations of general SIP. In general, the benefits provided by edge mining are related to the predictability of data streams and availability of precise information requirements; results show that L-SIP typically reduces packet transmission by around 95% (20-fold), BN reduces packet transmission by 99.98% (5000-fold), and ClassAct reduces packet transmission by 99.6% (250-fold). Although energy reduction is not as radical because of other overheads, minimization of these overheads can lead up to a 10-fold battery life extension for L-SIP, for example. These results demonstrate the importance of edge mining to the feasibility of many IoT applications.

Postural activity monitoring for increasing safety in bomb disposal missions

In enclosed suits, such as those worn by explosive ordnance disposal (EOD) experts, evaporative cooling through perspiration is less effective and, particularly in hot environments, uncompensable heat stress (UHS) may occur. Although some suits have cooling systems, their effectiveness during missions is dependent on the operatives posture. In order to properly assess thermal state, temperature-based assessment systems need to take posture into account. This paper builds on previous work for instrumenting EOD suits with regard to temperature monitoring and proposes to also monitor operative posture with MEMS accelerometers. Posture is a key factor in predicting how body temperature will change and is therefore important in providing local or remote warning of the onset of UHS. In this work, the C4.5 decision tree algorithm is used to produce an on-line classifier that can differentiate between nine key postures from current acceleration readings. Additional features that summarize how acceleration is changing over time are used to improve average classification accuracy to around 97.2%. Without such temporal feature extraction, dynamic postures are difficult to classify accurately. Experimental results show that training over a variety of subjects, and in particular, mixing gender, improves results on unseen subjects. The main advantages of the on-line posture classification system described here are that it is accurate, does not require integration of acceleration over time, and is computationally lightweight, allowing it to be easily supported on wearable microprocessors.

Wearable posture recognition systems: Factors affecting performance

This paper presents an investigation into the design space for real-time, wearable posture classification systems; specifically, it analyses the impact of various factors/design choices on classification accuracy when using C4.5 decision trees. The factors can be broadly divided into: 1) system factors (such as sensor sampling rate and number of sensors used) and 2) algorithm and training factors (such as quantity of training data and temporal data features used). These factors are analysed in the context of a case study involving postural activity monitoring of Explosive Ordinance Disposal (EOD) operatives. The case study involves classifying a set of eight postures commonly encountered in EOD missions: sitting, walking, crawling, laying (on all sides) and kneeling. Design guidelines and generic lessons for a wider class of applications can be drawn from the work.

Long-Term Behavioural Change Detection through Pervasive Sensing

The paper proposes an information generation and summarisation algorithm to detect behavioural change in applications such as long-term monitoring of vulnerable people. The algorithm learns the monitored subjects behaviour autonomously post-deployment and provides time-suppressed summaries of the activity types engaged with by the subject over the course of their day to day life. It transmits updates to external observers only when the summary changes by more than a defined threshold. This technique substantially reduces the number of transmission required by a wearable monitoring system, both through summarisation of the raw data into useful information and by preventing transmission of duplicated or predictable data and information. Based on evaluation using simulated activity data, the proposed algorithm results in an average of one transmission per month following an initial convergence period (reaching less than 1 transmission per day after only three days) and detects a change in behaviour after an average of 1.1 days.

Fielded Autonomous Posture Classification Systems: Design and Realistic Evaluation

Few Body Sensor Network (BSN) based posture classification systems have been fielded to date, despite laboratory based research work confirming their theoretical suitability for a range of applications. This paper reports and reflects on two algorithms which i) improve the accuracy of real-time, multi-accelerometer based posture classifiers when dealing with natural movement and transitions and ii) maximize a wearable systems battery life through distributed computation at nodes. The EWV transition filters proposed here increase the classification accuracy by 1% over unfiltered results in realistic scenarios and significantly reduces spurious classifier output in real-time visualizations. A 200 fold transmission reduction from the on-body system to an outside system was achieved in practice by combining the transition filters with an event-based design. Furthermore, a method of reducing transmissions between on-body data gathering nodes based on distributed processing of the classifier rules (but maintaining a one-way flow of communications during system use) is also described. This provides a 3.3 fold reduction in packets and a 13.5 fold reduction in data transmitted from one node to the other in a two-node wearable system.