We present a variant of the well sounded Expectation-Maximization Clustering algorithm that is constrained to generate partitions of the input space into high and low values. The motivation of splitting input variables into high and low values is to
favour the semantic interpretation of the final clustering. The Expectation-Maximization binary Clustering is specially useful when a bimodal conditional distribution of the variables is expected or at least when a binary discretization of the input space is deemed meaningful. Furthermore, the algorithm deals with the reliability of the input data such that the larger their uncertainty the less their role in the final clustering. We show here its suitability for behavioural annotation of movement trajectories. However, it can be considered as a general purpose algorithm for the clustering or segmentation of multivariate data or temporal series.
It has been observed cite{break} that breakdown in an 805 MHz pill-box cavi ty occurs at much lower gradients as an external axial magnetic field is inc reased. This effect was not observed with on open iris cavity. It is propose d that this effect d
epends on the relative angles of the magnetic and maximu m electric fields: parallel in the pill-box case; at an angle in the open ir is case. If so, using an open iris structure with solenoid coils in the iris es should perform even better. A lattice, using this principle, is presented, for use in 6D cooling for a Muon Collider. Experimental layouts to test th is principle are proposed.
