Multi-scale support vector algorithms for hot spot detection and modelling

The algorithmic approach to data modelling has developed rapidly these last years, in particular methods based on data mining and machine learning have been used in a growing number of applications. These methods follow a data-driven methodology, aiming at providing the best possible generalization and predictive abilities instead of concentrating on the properties of the data model. One of the most successful groups of such methods is known as Support Vector algorithms. Following the fruitful developments in applying Support Vector algorithms to spatial data, this paper introduces a new extension of the traditional support vector regression (SVR) algorithm. This extension allows for the simultaneous modelling of environmental data at several spatial scales. The joint influence of environmental processes presenting different patterns at different scales is here learned automatically from data, providing the optimum mixture of short and large-scale models. The method is adaptive to the spatial scale of the data. With this advantage, it can provide efficient means to model local anomalies that may typically arise in situations at an early phase of an environmental emergency. However, the proposed approach still requires some prior knowledge on the possible existence of such short-scale patterns. This is a possible limitation of the method for its implementation in early warning systems. The purpose of this paper is to present the multi-scale SVR model and to illustrate its use with an application to the mapping of Cs137 activity given the measurements taken in the region of Briansk following the Chernobyl accident.

Behavioral and psychological symptoms and cognitive decline in patients with amnestic MCI and mild AD: a two-year follow-up study.

BACKGROUND: Mild cognitive impairment (MCI) has been defined as a transitional state between normal aging and dementia. In many cases, MCI represents an early stage of developing cognitive impairment. Patients diagnosed with MCI do not meet the criteria for dementia as their general intellect and everyday activities are preserved, although minor changes in instrumental activities of daily living (ADL) may occur. However, they may exhibit significant behavioral and psychological signs and symptoms (BPS), also frequently observed in patients with Alzheimer's disease (AD). Hence, we wondered to what extent specific BPS are associated with cognitive decline in participants with MCI or AD. METHODS: Our sample consisted of 164 participants, including 46 patients with amnestic (single or multi-domain) MCI and 54 patients with AD, as well as 64 control participants without cognitive disorders. Global cognitive performance, BPS, and ADL were assessed using validated clinical methods at baseline and at two-year follow-up. RESULTS: The BPS variability over the follow-up period was more pronounced in the MCI group than in patients with AD: some BPS improve, others occur newly or worsen, while others still remain unchanged. Moreover, specific changes in BPS were associated with a rapid deterioration of the global cognitive level in MCI patients. In particular, an increase of euphoria, eating disorders, and aberrant motor behavior, as well as worsened sleep quality, predicted a decline in cognitive functioning. CONCLUSIONS: Our findings confirm a higher variability of BPS over time in the MCI group than in AD patients. Moreover, our results provide evidence of associations between specific BPS and cognitive decline in the MCI group that might suggest a risk of conversion of individuals with amnestic MCI to AD.