Objective: This paper describes how non-invasive wearable sensors can be used in combination with deep learn- ing to classify artificially induced gait alterations without the requirement for a medical professional or gait analyst to be present. This approach is motivated by the goal of diagnosing gait abnormalities on a symptom by symptom basis, irrespective of other neuromuscular movement disorders patients may be affected by. This could lead to improvements in treatment and offer a greater insight into movement disorders. Methods: In-shoe pressure was measured for 12 able-bodied participants, each subject to 8 artificially induced gait alterations, achieved by modifying the underside of the shoe. The data were recorded at 100 Hz over 2520 data channels and was analysed using the deep learning architecture, long term short term memory networks. Additionally, the rationale for the decision-making process of these networks was investigated. Conclusion: Long term short term memory networks are applicable to the classification of gait function. The classifications can be made using only 2 seconds of sparse data (82.0% accuracy over 96,000 instances of test data) from participants who were not part of the training set. Significance: This work provides potential for gait function to be accurately classified using non-invasive techniques, and at more regular intervals, outside of a clinical setting without the need for healthcare professionals to be present.

Recent statistics in suicide prevention show that people are increasingly posting their last words online and with the unprecedented availability of textual data from social media platforms researchers have the opportunity to analyse such data. Furthermore, psychological studies have shown that our state of mind can manifest itself in the linguistic features we use to communicate. In this paper, we investigate whether it is possible to automatically identify suicide notes from other types of social media blogs in two document-level classification tasks. The first task aims to identify suicide notes from depressed and blog posts in a balanced dataset, whilst the second experiment looks at how well suicide notes can be classified when there is a vast amount of neutral text data, which makes the task more applicable to real-world scenarios. Furthermore we perform a linguistic analysis using LIWC (Linguistic Inquiry and Word Count). We present a learning model for modelling long sequences in two experiment series. We achieve an f1-score of 88.26% over the baselines of 0.60 in experiment 1 and 96.1% over the baseline in experiment 2. Finally, we show through visualisations which features the learning model identifies, these include emotions such as love and personal pronouns.

Falls can be detrimental to the quality of life of older people, and therefore the ability to detect falls is beneficial, especially if the person is living alone and has injured themselves. In addition, detecting near falls (when a person is imbalanced or stumbles) has the potential to prevent a fall from occurring. This work focused on the design and engineering of a wearable electronic textile device to monitor falls and near-falls and used a machine learning algorithm to assist in the interpretation of the data. A key driver behind the study was to create a comfortable device that people would be willing to wear. A pair of over-socks incorporating a single motion sensing electronic yarn each were designed. The over-socks were used in a trial involving 13 participants. The participants performed three types of activities of daily living (ADLs), three types of falls onto a crash mat, and one type of near-fall. The trail data was visually analyzed for patterns, and a machine learning algorithm was used to classify the data. The developed over-socks combined with the use of a bidirectional long short-term memory (Bi-LSTM) network have been shown to be able to differentiate between three different ADLs and three different falls with an accuracy of 85.7%, ADLs and falls with an accuracy of 99.4%, and ADLs, falls, and stumbles (near-falls) with an accuracy of 94.2%. In addition, results showed that the motion sensing E-yarn only needs to be present in one over-sock.

This paper describes the artificial epigenetic network, a recurrent connectionist architecture that is able to dynamically modify its topology in order to automatically decompose and solve dynamical problems. The approach is motivated by the behavior of gene regulatory networks, particularly the epigenetic process of chromatin remodeling that leads to topological change and which underlies the differentiation of cells within complex biological organisms. We expected this approach to be useful in situations where there is a need to switch between different dynamical behaviors, and do so in a sensitive and robust manner in the absence of a priori information about problem structure. This hypothesis was tested using a series of dynamical control tasks, each requiring solutions that could express different dynamical behaviors at different stages within the task. In each case, the addition of topological self-modification was shown to improve the performance and robustness of controllers. We believe this is due to the ability of topological changes to stabilize attractors, promoting stability within a dynamical regime while allowing rapid switching between different regimes. Post hoc analysis of the controllers also demonstrated how the partitioning of the networks could provide new insights into problem structure.