No abstract

In this paper, the application of soft computing techniques in prediction of an occupant's behaviour in an inhabited intelligent environment is addressed. In this research, daily activities of elderly people who live in their own homes suffering from dementia are studied. Occupancy sensors are used to extract the movement patterns of the occupant. The occupancy data is then converted into temporal sequences of activities which are eventually used to predict the occupant behaviour. To build the prediction model, different dynamic recurrent neural networks are investigated. Recurrent neural networks have shown a great ability in finding the temporal relationships of input patterns. The experimental results show that non-linear autoregressive network with exogenous inputs model correctly extracts the long term prediction patterns of the occupant and outperformed the Elman network. The results presented here are validated using data generated from a simulator and real environments.

Background Parkinson’s disease is the second most common long-term chronic, progressive, neurodegenerative disease, affecting more than 10 million people worldwide. There has been a rising interest in wearable devices for evaluation of movement disorder diseases such as Parkinson’s disease due to the limitations in current clinic assessment methods such as Unified Parkinson’s Disease Rating Scale (UPDRS) and the Hoehn and Yahr (HY) scale. However, there are only a few commercial wearable devices available, which, in addition, have had very limited adoption and implementation. This inconsistency may be due to a lack of users’ perspectives in terms of device design and implementation. This study aims to identify the perspectives of healthcare professionals and patients linked to current assessment methods and to identify preferences, and requirements of wearable devices. Methods This was a qualitative study using semi-structured interviews followed by focus groups. Transcripts from sessions were analysed using an inductive thematic approach. Results It was noted that the well-known assessment process such as Unified Parkinson’s Disease Rating Scale (UPDRS) was not used routinely in clinics since it is time consuming, subjective, inaccurate, infrequent and dependent on patients’ memories. Participants suggested that objective assessment methods are needed to increase the chance of effective treatment. The participants’ perspectives were positive toward using wearable devices, particularly if they were involved in early design stages. Patients emphasized that the devices should be comfortable, but they did not have any concerns regarding device visibility or data privacy transmitted over the internet when it comes to their health. In terms of wearing a monitor, the preferable part of the body for all participants was the wrist. Healthcare professionals stated a need for an economical solution that is easy to interpret. Some design aspects identified by patients included clasps, material choice, and form factor. Conclusion The study concluded that current assessment methods are limited. Patients’ and healthcare professionals’ involvement in wearable devices design process has a pivotal role in terms of ultimate user acceptance. This includes the provision of additional functions to the wearable device, such as fall detection and medication reminders, which could be attractive features for patients.

No abstract

A new approach to creating an ensemble of novelty detection algorithms is proposed in this paper. The novelty detection process identifies new or unknown data by detecting if a test data differs significantly from the data available during training. It is applicable for anomaly detection in a situation where there is sufficiently large training data representing the normal class and little or no training data for the anomalous (abnormal) class. Abnormality in Activities of Daily Living (ADL) is identified as any significant deviation from an individual's usual behavioural routine. Novelty detection is relevant to ADL anomaly detection since abnormalities in ADL are rare and data representing the anomalous cases are not readily available. The proposed Consensus Novelty Detection Ensemble approach is based on the concept of internal and external consensus. The internal consensus is an internal voting scheme within each model in the ensemble while the external consensus is an external voting scheme among the ensemble models. The weight of each model is estimated based on its performance and a score, called "Normality Score". Computed score is used in classifying the data as abnormal (anomalous) based on certain threshold crossing, normal otherwise. Experimental evaluation is conducted to detect abnormalities in ADL data obtained from CASAS repository as well as experimental dataset collected for this research. The obtained results show that the proposed approach is able to identify anomalous instances. The proposed approach offers more flexibility compared with the existing approaches by allowing the Normality Score threshold to be adjusted without retraining the models.