A Novel Method to Determine Dynamic Temperature Trends Applied to In-Shoe Temperature Data During Walking.

Body temperature is one of the fundamental measures considered in the assessment of health and well-being, with various medical conditions known to give rise to abnormal changes in temperature. In particular, abnormal variations in dynamic temperature patterns during walking or exercise may be linked to a range of foot problems, which are of particular concern in diabetic patients.A number of studies have investigated normative temperature patterns of a population by considering data from multiple participants and averaging results after an acclimatisation interval. In this work we demonstrate that the temperature patterns obtained using such an approach may not be truly representative of temperature changes in a population, and the averaging process adopted may yield skewed results.An alternative approach to determine generic reference temperature patterns based on a minimization of root mean square differences between time-shifted versions of temperature data collected from multiple participants is proposed. The results obtained indicate that this approach can yield a general trend that is more representative of actual temperature changes across a population than conventional averaging methods. The method we propose is also shown to better capture and link the effects of factors that influence dynamic temperature trends, which could in turn lead to a better understanding of underlying physiological phenomena.

To train or not to train? A survey on training of feature extraction methods for SSVEP-based BCIs.

OBJECTIVE: Despite the vast research aimed at improving the performance of steady-state visually evoked potential (SSVEP)-based brain-computer interfaces (BCIs), several limitations exist that restrict the use of such applications for long-term users in the real-world. One of the main challenges has been to reduce training time while maintaining good BCI performance. In view of this challenge, this survey identifies and compares the different training requirements of feature extraction methods for SSVEP-based BCIs. APPROACH: This paper reviews the various state-of-the-art SSVEP feature extraction methods that have been developed and are most widely used in the literature. MAIN RESULTS: The main contributions compared to existing reviews are the following: (i) a detailed summary, including a brief mathematical description of each feature extraction algorithm, providing a guide to the basic concepts of the state-of-the-art techniques for SSVEP-based BCIs found in literature; (ii) a categorisation of the training requirements of SSVEP-based methods into three categories, defined as training-free methods, subject-specific and subject-independent training methods; (iii) a comparative review of the training requirements of SSVEP feature extraction methods, providing a reference for future work on SSVEP-based BCIs. SIGNIFICANCE: This review highlights the strengths and weaknesses of the three categories of SSVEP training methods. Training-free systems are more practical but their performance is limited due to inter-subject variability resulting from the complex EEG activity. Feature extraction methods that incorporate some training data address this issue and in fact have outperformed training-free methods: subject-specific BCIs are tuned to the individual yielding the best performance at the cost of long, tiring training sessions making these methods unsuitable for everyday use; subject-independent BCIs that make use of training data from various subjects offer a good trade-off between training effort and performance, making these BCIs better suited for practical use.