Search

OBJECTIVE: Seizure forecasting using machine learning is possible, but the performance is far from ideal, as indicated by many false predictions and low specificity. Here, we examine false and missing alarms of two algorithms on long-term datasets to show that the limitations are less related to classifiers or features, but rather to intrinsic changes in the data. METHODS: We evaluated two algorithms on three datasets by computing the correlation of false predictions and estimating the information transfer between both classification methods. RESULTS: For 9 out of 12 individuals both methods showed a performance better than chance. For all individuals we observed a positive correlation in predictions. For individuals with strong correlation in false predictions we were able to boost the performance of one method by excluding test samples based on the results of the second method. CONCLUSIONS: Substantially different algorithms exhibit a highly consistent performance and a strong coherency in false and missing alarms. Hence, changing the underlying hypothesis of a preictal state of fixed time length prior to each seizure to a proictal state is more helpful than further optimizing classifiers. SIGNIFICANCE: The outcome is significant for the evaluation of seizure prediction algorithms on continuous data.

Seasonal affective disorder (SAD) is characterised by recurrent episodes in autumn and winter of depression, hypersomnia, augmented appetite with carbohydrate craving, and weight gain, and can be successfully treated with bright light. Circadian rhythm hypotheses (summarized in) have stimulated research into the pathophysiology of SAD, postulating that: 1.The illness is a consequence of delayed phase position, 2.It is correlated with diminished circadian amplitude, or 3.It results from changes in the nocturnal duration between dusk and dawn e.g. of low core body temperature or melatonin secretion. Light is considered to act directly on the circadian pacemaker (‘Process C') and not on sleep dependent processes (‘Process S'). Thus successful treatment of SAD must act via mechanisms within known retinohypothalamic pathways. Conversely, emergence of SAD symptoms may reflect inappropriate neurobiological response to decreasing daylength

The city of Kiruna in Northern Sweden has become known for the need to relocate major parts of the city. Current and future mining activities in the world’s largest underground iron ore mine are the cause of land subsidence that requires relocation of substantial parts of the town including its water infrastructure. Figure 1 shows the area currently affected and projections thereof for the future. The process of relocating the city has started already and will continue for a few decades. It implies the construction of new urban areas and at the same time demolition in abandoned areas. With regard to the life span of water infrastructure, all actions taken now and in the near future will have an impact over five to ten decades. These circumstances place special demands on processes and technical solutions with regard to robustness, flexibility and mobility and require dealing with changes that cannot yet be foreseen., Urbanism, Architecture and The Built Environment