The emergence of an ageing population is a significant public health concern. This has led to an increase in the number of people living with progressive neurodegenerative disorders. The strain this places on services means providing 24-hour monitoring is not sustainable. No solution exists to non-intrusively monitor the wellbeing of patients with dementia, resulting in delayed intervention. Using machine learning and signal processing, domestic energy supplies can be disaggregated to detect appliance usage. This enables Activities of Daily Living (ADLs) to be assessed. The aim is to facilitate early intervention and enable patients to stay in their homes for longer. A Support Vector Machine (SVM) and Random Decision Forest classifier are modelled using data from three test homes. The trained models are then used to monitor two patients with dementia during a six-month clinical trial undertaken in partnership with Mersey Care NHS Foundation Trust. In the case of load disaggregation, the SVM achieved (AUC=0.86074, Sen=0.756 and Spec=0.92838). While the Decision Forest achieved (AUC=0.9429, Sen=0.9634 and Spec=0.9634). ADLs are also analysed to identify the behavioural patterns of the occupant while detecting alterations in routine. The approach is sensitive in identifying behavioural routines and detecting anomalies in patient behaviour.

This paper presents a novel approach based on the analysis of genetic variants from publicly available genetic profiles and the manually curated database, the National Human Genome Research Institute Catalog. Using data science techniques, genetic variants are identified in the collected participant profiles and then indexed as risk variants in the National Human Genome Research Institute Catalog. Indexed genetic variants or Single Nucleotide Polymorphisms are used as inputs in various machine learning algorithms for the prediction of obesity. Body mass index status of participants is divided into two classes, Normal Class and Risk Class. Dimensionality reduction tasks are performed to generate a set of principal variables - 13 SNPs - for the application of various machine learning methods. The models are evaluated using receiver operator characteristic curves and the area under the curve. Machine learning techniques including gradient boosting, generalized linear model, classification and regression trees, k-nearest neighbours, support vector machines, random forest and multilayer perceptron neural network are comparatively assessed in terms of their ability to identify the most important factors among the initial 6622 variables describing genetic variants, age and gender, to classify a subject into one of the body mass index related classes defined in this study. Our simulation results indicated that support vector machine generated the highest area under the curve value of 90.5%.

Genome-Wide Association Studies (GWAS) are used to identify statistically significant genetic variants in case-control studies. The main objective is to find single nucleotide polymorphisms (SNPs) that influence a particular phenotype. GWAS use a p-value threshold of $5\star 10^{-8}$ to identify highly ranked SNPs. While this approach has proven useful for detecting disease-susceptible SNPs, evidence has shown that many of these are, in fact, false positives. Consequently, there is some ambiguity about the most suitable threshold for claiming genome-wide significance. Many believe that using lower p-values will allow us to investigate the joint epistatic interactions between SNPs and provide better insights into phenotype expression. In this paper, we propose a novel framework, based on nonlinear transformations of combinatorically large SNP data, using stacked autoencoders, to identify higher-order SNP interactions. We focus on the challenging problem of classifying preterm births. Latent representations from original SNP sequences are used to initialize a deep learning classifier before it is fine-tuned for classification tasks. The findings show that important information pertaining to epistasis can be extracted from 4666 raw SNPs generated using logistic regression (p-value= $5\star 10^{-8}$ ) and used to fit a deep learning model and obtain results (Sen=0.9289, Spec=0.9591, Gini=0.9651, Logloss=0.3080, AUC=0.9825, MSE=0.0942) using 500 hidden nodes.

In this paper, association results from genome-wide association studies (GWAS) are combined with a deep learning framework to test the predictive capacity of statistically significant single nucleotide polymorphism (SNPs) associated with obesity phenotype. Our approach demonstrates the potential of deep learning as a powerful framework for GWAS analysis that can capture information about SNPs and the important interactions between them. Basic statistical methods and techniques for the analysis of genetic SNP data from population-based genome-wide studies have been considered. Statistical association testing between individual SNPs and obesity was conducted under an additive model using Iogistic regression. Four subsets of loci after quality-control (QC) and association analysis were selected: P- values lower than l×10 ^-5 (5 SNPs), l×10 ^-4 (32 SNPs), l×10 ^-3 (248 SNPs) and l×10 ^-2 (2465 SNPs). A deep learning classifier is initialised using these sets of SNPs and fine-tuned to classify obese and non-obese observations. Using a deep learning classifier model and genetic variants with P-value <; l×10 ^-2 (2465 SNPs) it was possible to obtain results (SE=0.9604, SP=0.9712, Gini=0.9817, LogLoss=0.1150, AUC=0.9908 and MSE=0.0300). As the P-value increased, an evident deterioration in performance was observed. Results demonstrate that single SNP analysis fails to capture the cumulative effect of less significant variants and their overall contribution to the outcome in disease prediction, which is captured using a deep learning framework.

Technological advancements in the field of electrical energy distribution and utilization are revolutionizing the way consumers and utility providers interact. In addition to allowing utility companies to monitor the status of their network independently in autonomous fashion, data collected by smart meters as part of the wider advanced metering infrastructure, can be valuable for third parties, such as government authorities. The availability of the information, the granularity of the data, and the real-time nature of the smart meter, means that predictive analytics can be employed to profile consumers with high accuracy and approximate, for example, the number of individuals living in a house, the type of appliances being used, or the duration of occupancy, to name but a few applications. This paper presents a machine learning model comparison for unemployment prediction of single household occupants, based on features extracted from smart meter electricity readings. A number of nonlinear classifiers are compared, and benchmarked against a generalized linear model, and the results presented. To ensure the robustness of the classifiers, we use repeated cross validation. The results revealed that it is possible to predict employability status with Area Under Curve (AUC) = 74%, Sensitivity (SE) = 54% and Specificity (SP) = 83%, using a multilayer perceptron neural network with dropout, closely followed by the results produced by a distance weighted discrimination with polynomial kernel model. This shows the potential of using the smart metering infrastructure to provide additional autonomous services, such as unemployment detection, for governments using data collected from an advanced and distributed Internet of Things (IoT) sensor network.

Smart meters have become a core part of the Internet of Things, and its sensory network is increasing globally. For example, in the UK there are over 15 million smart meters operating across homes and businesses. One of the main advantages of the smart meter installation is the link to a reduction in carbon emissions. Research shows that, when provided with accurate and real-time energy usage readings, consumers are more likely to turn off unneeded appliances and change other behavioural patterns around the home (e.g., lighting, thermostat adjustments). In addition, the smart meter rollout results in a lessening in the number of vehicle callouts for the collection of consumption readings from analogue meters and a general promotion of renewable sources of energy supply. Capturing and mining the data from this fully maintained (and highly accurate) sensing network, provides a wealth of information for utility companies and data scientists to promote applications that can further support a reduction in energy usage. This research focuses on modelling trends in domestic energy consumption using density-based classifiers. The technique estimates the volume of outliers (e.g., high periods of anomalous energy consumption) within a social class grouping. To achieve this, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Ordering Points to Identify the Clustering Structure (OPTICS) and Local Outlier Factor (LOF) demonstrate the detection of unusual energy consumption within naturally occurring groups with similar characteristics. Using DBSCAN and OPTICS, 53 and 208 outliers were detected respectively; with 218 using LOF, on a dataset comprised of 1,058,534 readings from 1026 homes.