Good Clusterings Have Large Volume

From Comparing Clusterings to Combining Clusterings

This paper presents a fast simulated annealing framework for combining multiple clusterings (i.e. clustering ensemble) based on some measures of agreement between partitions, which are originally used to compare two clusterings (the obtained clustering vs. a ground truth clustering) for the evaluation of a clustering algorithm. Though we can follow a greedy strategy to optimize these measures a...

Food fortification: good to have or need to have?

Only very small quantities of vitamins and minerals are needed for human health but deficiencies can have disproportionately large, often life-threatening, effects. Micronutrient deficiencies lead to a vicious cycle of malnutrition and infection in poorly nourished populations. Fortification of staple foods is the cheapest, most efficient and most effective way to supply large populations with ...

Geometric Clusterings

A k-clustering of a given set of points in the plane is a partition of the points into k subsets (“clusters”). For any fixed k, we can find a k-clustering which minimizes any monotone function of the diameters or the radii of the clusters in polynomial time. The algorithm is based on the fact that any two clusters in an optimal solution can be separated by a line. AMS 1980 mathematics subject c...

Dairy Cattle Must Have Good Forage

Guidelines have done more harm than good.

Practice guidelines have proliferated in medicine but their impact on actual practice and outcomes is difficult, if not impossible, to quantify. Though guidelines are based largely on observational data and expert opinion, it is widely believed that adherence to them leads to improved outcomes. Data to support this belief simply does not exist. If guidelines are universally ignored, their impac...