Direct Versus Iterated Multi-Step Forecasting of Glycaemia in Type 1 Diabetics Using Autoregressive Models.

The paper compares two approaches to multi-step ahead glycaemia forecasting. While the direct approach uses a different model for each number of steps ahead, the iterative approach applies one one-step ahead model iteratively. Although it is well known that the iterative approach suffers from the error accumulation problem, there are no clear outcomes supporting a proper choice between those two methods. This paper provides such comparison for different ARX models and shows that the iterative approach outperformed the direct method for one-hour ahead (12-steps ahead) forecasting. Moreover, the classical linear ARX model outperformed more complex non-linear versions for training data covering one-month period.

Ensemble methods in combination with compartment models for blood glucose level prediction in type 1 diabetes mellitus.

Backgroung: Type 1 diabetes is a disease that adversely affects the daily life of a large percentage of people worldwide. Daily glucose levels regulation and useful advices provided to patients regarding their diet are essential for diabetes treatment. For this reason, the interest of the academic community has focused on developing innovative systems, such as decision support systems, based on glucose prediction algorithms. The present work presents the predictive capabilities of ensemble methods compared to individual algorithms while combining each method with compartment models for fast acting insulin absorption simulation. Methods: An approach of combining widely used glycemia prediction algorithms is proposed and three different ensemble methods (Linear, Bagging and Boosting metaregressor) are applied and evaluated on their ability to provide accurate predictions for 30, 45 and 60 minutes ahead prediction horizon. Moreover, glycemia levels, long and short acting insulin dosages and consumed carbohydrates from six type one people with diabetes are used as input data and the results are evaluated in terms of root-mean square error and Clarke error grid analysis. Results: According to results, ensemble methods can provide more accurate glucose concentration in comparison to individual algorithms. Bagging metaregressor, specifically, performed better than individual algorithms in all prediction horizons for small datasets. Bagging ensemble method improved the percentage in zone A according to Clarkes error grid analysis by 4% and in some cases by 9%. Moreover, compartment models are proved to improve results in combination with any method at any prediction horizon. This strengthen the potential practical usefulness of the ensemble methods and the importance of building accurate compartment models.

Towards biological plausibility of electronic noses: A spiking neural network based approach for tea odour classification.

The paper presents a novel encoding scheme for neuronal code generation for odour recognition using an electronic nose (EN). This scheme is based on channel encoding using multiple Gaussian receptive fields superimposed over the temporal EN responses. The encoded data is further applied to a spiking neural network (SNN) for pattern classification. Two forms of SNN, a back-propagation based SpikeProp and a dynamic evolving SNN are used to learn the encoded responses. The effects of information encoding on the performance of SNNs have been investigated. Statistical tests have been performed to determine the contribution of the SNN and the encoding scheme to overall odour discrimination. The approach has been implemented in odour classification of orthodox black tea (Kangra-Himachal Pradesh Region) thereby demonstrating a biomimetic approach for EN data analysis.

Wrapper feature selection for small sample size data driven by complete error estimates.

This paper focuses on wrapper-based feature selection for a 1-nearest neighbor classifier. We consider in particular the case of a small sample size with a few hundred instances, which is common in biomedical applications. We propose a technique for calculating the complete bootstrap for a 1-nearest-neighbor classifier (i.e., averaging over all desired test/train partitions of the data). The complete bootstrap and the complete cross-validation error estimate with lower variance are applied as novel selection criteria and are compared with the standard bootstrap and cross-validation in combination with three optimization techniques - sequential forward selection (SFS), binary particle swarm optimization (BPSO) and simplified social impact theory based optimization (SSITO). The experimental comparison based on ten datasets draws the following conclusions: for all three search methods examined here, the complete criteria are a significantly better choice than standard 2-fold cross-validation, 10-fold cross-validation and bootstrap with 50 trials irrespective of the selected output number of iterations. All the complete criterion-based 1NN wrappers with SFS search performed better than the widely-used FILTER and SIMBA methods. We also demonstrate the benefits and properties of our approaches on an important and novel real-world application of automatic detection of the subthalamic nucleus.