Missing values exist in nearly all clinical studies because data for a variable or question are not collected or not available. Inadequate handling of missing values can lead to biased results and loss of statistical power in analysis. Existing models usually do not consider privacy concerns or do not utilise the inherent correlations across multiple features to impute the missing values. In healthcare applications, we are usually confronted with high dimensional and sometimes small sample size datasets that need more effective augmentation or imputation techniques. Besides, imputation and augmentation processes are traditionally conducted individually. However, imputing missing values and augmenting data can significantly improve generalisation and avoid bias in machine learning models. A Bayesian approach to impute missing values and creating augmented samples in high dimensional healthcare data is proposed in this work. We propose folded Hamiltonian Monte Carlo (F-HMC) with Bayesian inference as a more practical approach to process the cross-dimensional relations by applying a random walk and Hamiltonian dynamics to adapt posterior distribution and generate large-scale samples. The proposed method is applied to a cancer symptom assessment dataset and confirmed to enrich the quality of data in precision, accuracy, recall, F1 score, and propensity metric.
Behavioural symptoms and urinary tract infections (UTI) are among the most common problems faced by people with dementia. One of the key challenges in the management of these conditions is early detection and timely intervention in order to reduce distress and avoid unplanned hospital admissions. Using in-home sensing technologies and machine learning models for sensor data integration and analysis provides opportunities to detect and predict clinically significant events and changes in health status. We have developed an integrated platform to collect in-home sensor data and performed an observational study to apply machine learning models for agitation and UTI risk analysis. We collected a large dataset from 88 participants with a mean age of 82 and a standard deviation of 6.5 (47 females and 41 males) to evaluate a new deep learning model that utilises attention and rational mechanism. The proposed solution can process a large volume of data over a period of time and extract significant patterns in a time-series data (i.e. attention) and use the extracted features and patterns to train risk analysis models (i.e. rational). The proposed model can explain the predictions by indicating which time-steps and features are used in a long series of time-series data. The model provides a recall of 91\% and precision of 83\% in detecting the risk of agitation and UTIs. This model can be used for early detection of conditions such as UTIs and managing of neuropsychiatric symptoms such as agitation in association with initial treatment and early intervention approaches. In our study we have developed a set of clinical pathways for early interventions using the alerts generated by the proposed model and a clinical monitoring team has been set up to use the platform and respond to the alerts according to the created intervention plans.
We introduce the conceptual formulation, design, fabrication, control and commercial translation with IoT connection of a hybrid-face social robot and validation of human emotional response to its affective interactions. The hybrid-face robot integrates a 3D printed faceplate and a digital display to simplify conveyance of complex facial movements while providing the impression of three-dimensional depth for natural interaction. We map the space of potential emotions of the robot to specific facial feature parameters and characterise the recognisability of the humanoid hybrid-face robot's archetypal facial expressions. We introduce pupil dilation as an additional degree of freedom for conveyance of emotive states. Human interaction experiments demonstrate the ability to effectively convey emotion from the hybrid-robot face to human observers by mapping their neurophysiological electroencephalography (EEG) response to perceived emotional information and through interviews. Results show main hybrid-face robotic expressions can be discriminated with recognition rates above 80% and invoke human emotive response similar to that of actual human faces as measured by the face-specific N170 event-related potentials in EEG. The hybrid-face robot concept has been modified, implemented, and released in the commercial IoT robotic platform Miko (My Companion), an affective robot with facial and conversational features currently in use for human-robot interaction in children by Emotix Inc. We demonstrate that human EEG responses to Miko emotions are comparative to neurophysiological responses for actual human facial recognition. Finally, interviews show above 90% expression recognition rates in our commercial robot. We conclude that simplified hybrid-face abstraction conveys emotions effectively and enhances human-robot interaction.
The Urinary Tract Infections (UTIs) are one of the top reasons for unplanned hospital admissions in people with dementia, and if detected early, they can be timely treated. However, the standard UTI diagnosis tests, e.g. urine tests, will be only taken if the patients are clinically suspected of having UTIs. This causes a delay in diagnosis and treatment of the conditions and in some cases like people with dementia, the symptoms can be difficult to observe. Delay in detection and treatment of dementia is one of the key reasons for unplanned hospital admissions in people with dementia. To address these issues, we have developed a technology-assisted monitoring system, which is a Class 1 medical device. The system uses off-the-shelf and low-cost in-home sensory devices to monitor environmental and physiological data of people with dementia within their own homes. We have designed a machine learning model to use the data and provide risk analysis for UTIs. We use a semi-supervised learning model which leverage the environmental data, i.e. the data collected from the motion sensors, smart plugs and network-connected body temperature monitoring devices in the home, to detect patterns that can show the risk of UTIs. Since the data is noisy and partially labelled, we combine the neural networks and probabilistic neural networks to train an auto-encoder, which is to extract the general representation of the data. We will demonstrate our smart home management by videos/online, and show how our model can pick up the UTI related patterns.
The proliferation of IoT sensors and edge devices makes it possible to use deep learning models to recognise daily activities locally using in-home monitoring technologies. Recently, federated learning systems that use edge devices as clients to collect and utilise IoT sensory data for human activity recognition have been commonly used as a new way to combine local (individual-level) and global (group-level) models. This approach provides better scalability and generalisability and also offers higher privacy compared with the traditional centralised analysis and learning models. The assumption behind federated learning, however, relies on supervised learning on clients. This requires a large volume of labelled data, which is difficult to collect in uncontrolled IoT environments such as remote in-home monitoring. In this paper, we propose an activity recognition system that uses semi-supervised federated learning, wherein clients conduct unsupervised learning on autoencoders with unlabelled local data to learn general representations, and a cloud server conducts supervised learning on an activity classifier with labelled data. Our experimental results show that using autoencoders and a long short-term memory (LSTM) classifier, the accuracy of our proposed system is comparable to that of a supervised federated learning system. Meanwhile, we demonstrate that our system is not affected by the Non-IID distribution of local data, and can even achieve better accuracy than supervised federated learning on some datasets. Additionally, we show that our proposed system can reduce the number of needed labels in the system and the size of local models without losing much accuracy, and has shorter local activity recognition time than supervised federated learning.
The robustness of neural networks is challenged by adversarial examples that contain almost imperceptible perturbations to inputs, which mislead a classifier to incorrect outputs in high confidence. Limited by the extreme difficulty in examining a high-dimensional image space thoroughly, research on explaining and justifying the causes of adversarial examples falls behind studies on attacks and defenses. In this paper, we present a collection of potential causes of adversarial examples and verify (or partially verify) them through carefully-designed controlled experiments. The major causes of adversarial examples include model linearity, one-sum constraint, and geometry of the categories. To control the effect of those causes, multiple techniques are applied such as $L_2$ normalization, replacement of loss functions, construction of reference datasets, and novel models using multi-layer perceptron probabilistic neural networks (MLP-PNN) and density estimation (DE). Our experiment results show that geometric factors tend to be more direct causes and statistical factors magnify the phenomenon, especially for assigning high prediction confidence. We believe this paper will inspire more studies to rigorously investigate the root causes of adversarial examples, which in turn provide useful guidance on designing more robust models.
Conventional deep learning models have limited capacity in learning multiple tasks sequentially. The issue of forgetting the previously learned tasks in continual learning is known as catastrophic forgetting or interference. When the input data or the goal of learning change, a continual model will learn and adapt to the new status. However, the model will not remember or recognise any revisits to the previous states. This causes performance reduction and re-training curves in dealing with periodic or irregularly reoccurring changes in the data or goals. The changes in goals or data are referred to as new tasks in a continual learning model. Most of the continual learning methods have a task-known setup in which the task identities are known in advance to the learning model. We propose Task Conditional Neural Networks (TCNN) that does not require to known the reoccurring tasks in advance. We evaluate our model on standard datasets using MNIST and CIFAR10, and also a real-world dataset that we have collected in a remote healthcare monitoring study (i.e. TIHM dataset). The proposed model outperforms the state-of-the-art solutions in continual learning and adapting to new tasks that are not defined in advance.
Continual learning models allow to learn and adapt to new changes and tasks over time. However, in continual and sequential learning scenarios in which the models are trained using different data with various distributions, neural networks tend to forget the previously learned knowledge. This phenomenon is often referred to as catastrophic forgetting. The catastrophic forgetting is an inevitable problem in continual learning models for dynamic environments. To address this issue, we propose a method, called Continual Bayesian Learning Networks (CBLN), which enables the networks to allocate additional resources to adapt to new tasks without forgetting the previously learned tasks. Using a Bayesian Neural Network, CBLN maintains a mixture of Gaussian posterior distributions that are associated with different tasks. The proposed method tries to optimise the number of resources that are needed to learn each task and avoids an exponential increase in the number of resources that are involved in learning multiple tasks. The proposed method does not need to access the past training data and can choose suitable weights to classify the data points during the test time automatically based on an uncertainty criterion. We have evaluated our method on the MNIST and UCR time-series datasets. The evaluation results show that our method can address the catastrophic forgetting problem at a promising rate compared to the state-of-the-art models.
Learning and adapting to new distributions or learning new tasks sequentially without forgetting the previously learned knowledge is a challenging phenomenon in continual learning models. Most of the conventional deep learning models are not capable of learning new tasks sequentially in one model without forgetting the previously learned ones. We address this issue by using a Kalman Optimiser. The Kalman Optimiser divides the neural network into two parts: the long-term and short-term memory units. The long-term memory unit is used to remember the learned tasks and the short-term memory unit is to adapt to the new task. We have evaluated our method on MNIST, CIFAR10, CIFAR100 datasets and compare our results with state-of-the-art baseline models. The results show that our approach enables the model to continually learn and adapt to the new changes without forgetting the previously learned tasks.