Carl Chalmers

Smart Health Monitoring Using the Advance Metering Infrastructure

Around the world, a large scale implementation of smart meters is underway. The UK alone will install and configure over 50 million smart meters by the end of 2020. These smart devices enable consumer electricity usage monitoring with a high degree of accuracy. Each device records consumer data at regular intervals, which can be used to identify and profile half-hourly routines and habits. This enables the detection of sudden abnormal changes in behaviour based on the analysis of regular activities a consumer would undertake during a 24 hour period. The challenge, however, is to develop a system that can distinguish reliably between subtle changes in energy usage. The system could then be used to provide accurate monitoring for people living with self-limiting conditions, who wish to live independently in their own home for as long as possible. The proposed system facilitates the direct analysis of energy usage by employing data classification techniques to identify any anomalies in energy consumption. The system itself performs a modular adaptation that changes the way in which data is analysed and presented, to suit both an organisations or an individuals needs, based on their condition.

Machine learning Ensemble Modelling to classify caesarean section and vaginal delivery types using cardiotocography traces

Human visual inspection of Cardiotocography traces is used to monitor the foetus during labour and avoid neonatal mortality and morbidity. The problem, however, is that visual interpretation of Cardiotocography traces is subject to high inter and intra observer variability. Incorrect decisions, caused by miss-interpretation, can lead to adverse perinatal outcomes and in severe cases death. This study presents a review of human Cardiotocography trace interpretation and argues that machine learning, used as a decision support system by obstetricians and midwives, may provide an objective measure alongside normal practices. This will help to increase predictive capacity and reduce negative outcomes. A robust methodology is presented for feature set engineering using an open database comprising 552 intrapartum recordings. State-of-the-art in signal processing techniques is applied to raw Cardiotocography foetal heart rate traces to extract 13 features. Those with low discriminative capacity are removed using Recursive Feature Elimination. The dataset is imbalanced with significant differences between the prior probabilities of both normal deliveries and those delivered by caesarean section. This issue is addressed by oversampling the training instances using a synthetic minority oversampling technique to provide a balanced class distribution. Several simple, yet powerful, machine-learning algorithms are trained, using the feature set, and their performance is evaluated with real test data. The results are encouraging using an ensemble classifier comprising Fishers Linear Discriminant Analysis, Random Forest and Support Vector Machine classifiers, with 87% (95% Confidence Interval: 86%, 88%) for Sensitivity, 90% (95% CI: 89%, 91%) for Specificity, and 96% (95% CI: 96%, 97%) for the Area Under the Curve, with a 9% (95% CI: 9%, 10%) Mean Square Error.

Developing a Productivity Accelerator Platform to Support UK Businesses in the Industry 4.0 Revolution

The growing Internet of Things (IoT), the increasing use of sensor technology and the digitisation of traditionally isolated analogue devices are transforming manufacturing and private dwellings in the UK. This ongoing revolution is often referred to as Industry 4.0, where real-time data informs the product value chain and digital applications are used for automating service allocation. Within this emerging environment, good practice is essential for productivity. Yet, the access to good practice guides and information is a challenge. Consequently, in this paper, the Productivity Accelerator (ProAccel) platform design is proposed. The system is a modular cloud-based multimedia platform that has the goal of helping UK businesses improve their productivity. ProAccel employs advanced machine learning and gamification techniques to revolutionise the way productivity information is shared.

A Performance Evaluation of Systematic Analysis for Combining Multi-class Models for Sickle Cell Disorder Data Sets

Machine learning approach is considered as a field of science aiming specifically to extract knowledge from the data sets. The main aim of this study is to provide a sophisticate model to difference applications of machine learning models for medically related problems. We attempt for classifying the amount of medications for each patient with Sickle Cell disorder. We present a new technique to combine two classifiers between the Levenberg-Marquartdt training algorithm and the k-nearest neighbours algorithm. In this paper, we introduce multi-class label classification problem in order to obtain training and testing methods for each models along with other performance evaluations. In machine learning, the models utilise a training sets in association with building a classifier that provide a reliable classification. This research discusses different aspects of machine learning approaches for the classification of biomedical data. We are mainly focus on the multi-class label classification problem where many number of classes are available in the data sets. Results have indicated that for the machine learning models tested, the combination classifiers were found to yield considerably better results over the range of performance measures that been selected for this research.

Adaptive Health Monitoring Using Aggregated Energy Readings from Smart Meters

Worldwide, the number of people living with self-limiting conditions, such as Dementia, Parkinson’s disease and depression, is increasing. The resulting strain on healthcare resources means that providing 24-hour monitoring for patients is a challenge. As this problem escalates, caring for an ageing population will become more demanding over the next decade, and the need for new, innovative and cost effective home monitoring technologies are now urgently required. The research presented in this thesis directly proposes an alternative and cost effective method for supporting independent living that offers enhancements for Early Intervention Practices (EIP). In the UK, a national roll out of smart meters is underway. Energy suppliers will install and configure over 50 million smart meters by 2020. The UK is not alone in this effort. In other countries such as Italy and the USA, large scale deployment of smart meters is in progress. These devices enable detailed around-the-clock monitoring of energy usage. Specifically, each smart meter records accurately the electrical load for a given property at 10 second intervals, 24 hours a day. This granular data captures detailed habits and routines through user interactions with electrical devices. The research presented in this thesis exploits this infrastructure by using a novel approach that addresses the limitations associated with current Ambient Assistive Living technologies. By applying a novel load disaggregation technique and leveraging both machine learning and cloud computing infrastructure, a comprehensive, nonintrusive and personalised solution is achieved. This is accomplished by correlating the detection of individual electrical appliances and correlating them with an individual’s Activities of Daily Living. By utilising a random decision forest, the system is able to detect the use of 5 appliance types from an aggregated load environment with an accuracy of 96%. By presenting the results as vectors to a second classifier both normal and abnormal patient behaviour is detected with an accuracy of 92.64% and a mean squared error rate of 0.0736 using a random decision forest. The approach presented in this thesis is validated through a comprehensive patient trial, which demonstrates that the detection of both normal and abnormal patient behaviour is possible.

A Smart Health Monitoring Technology

With the implementation of the Advanced Metering Infrastructure (AMI), comes the opportunity to gain valuable insights into an individual’s daily habits, patterns and routines. A vital part of the AMI is the smart meter. It enables the monitoring of a consumer’s electricity usage with a high degree of accuracy. Each device reports and records a consumer’s energy usage readings at regular intervals. This facilitates the identification of emerging abnormal behaviours and trends, which can provide operative monitoring for people living alone with various health conditions. Through profiling, the detection of sudden changes in behaviour is made possible, based on the daily activities a patient is expected to undertake during a 24-h period. As such, this paper presents the development of a system which detects accurately the granular differences in energy usage which are the result of a change in an individual’s health state. Such a process provides accurate monitoring for people living with self-limiting conditions and enables an early intervention practice (EIP) when a patient’s condition is deteriorating. The results in this paper focus on one particular behavioural trend, the detection of sleep disturbances; which is related to various illnesses, such as depression and Alzheimer’s. The results demonstrate that it is possible to detect sleep pattern changes to an accuracy of 95.96 % with 0.943 for sensitivity, 0.975 for specificity and an overall error of 0.040 when using the VPC Neural Network classifier. This type of behavioral detection can be used to provide a partial assessment of a patient’s wellbeing.

Securing the smart grid: threats and remediation

The implementation of the smart grid brings many improvements over the traditional energy grid by leveraging a vast interconnected infrastructure that allows two way communication and automation throughout the entire grid. A key difference over the existing grid is the introduction of the advanced metering infrastructure (AMI) which contains many new components such as the smart meter and the communication gateways. The focus of this paper is to examine the possible effects on the energy supply should these devices become compromised. Smart meters are one of the most important components in the smart grid implementation which allow a real time flow of information to/from the consumer on their energy usage. The paper also discusses how closing coal and oil power plant has increased our demand on gas power stations in the UK. Our experiments show that manipulating smart meter readings can create a massive shortfall in gas provisioning.