Extensions to the repetitive branch and bound algorithm for globally optimal clusterwise regression

A branch and bound strategy is proposed for solving the clusterwise regression problem, extending Brusco's repetitive branch and bound algorithm (RBBA). The resulting strategy relies upon iterative heuristic optimization, new ways of observation sequencing, and branch and bound optimization of a limited number of ending subsets. These three key features lead to significantly faster optimization of the complete set and the strategy has more general applications than only for clusterwise regression. Additionally, an efficient implementation of incremental calculations within the branch and bound search algorithm eliminates most of the redundant ones. Experiments using both real and synthetic data compare the various features of the proposed optimization algorithm and contrasts them against a benchmark mixed logical-quadratic programming formulation optimized by CPLEX. The results indicate that all components of the proposed algorithm provide significant improvements in processing times, and, when combined, generally provide the best performance, significantly outperforming CPLEX.     

Correlation between machining direction,cutter geometry and step-over distance in 3-axis milling: Application to milling by zones

Computer-Aided Manufacturing (CAM) occupies an increasingly important role in engineering with all it has to offer in terms of new possibilities and improving designer/manufacturer productivity. The present study addresses machining of free-form surfaces on a 3-axis NC machine tool. There have recently been a large number of studies devoted to planning tool paths on free-form surfaces with various strategies being adopted. These strategies are intended to increase efficiency by reducing the overall length of machining. Often, the choice of the cutter is arbitrary and the work focuses on planning. In order to boost productivity, the present work offers assistance in choosing the cutting tool, the machining direction and cutting by surface zones, adopting a milling strategy by parallel planes. To do so, a comparison is made between milling using a spherical end milling cutter and a torus end milling cutter with the same outer radius. This comparison relates to the radius of curvature of the trace left by the cutter at the point of contact between the tool and the workpiece in relation to the direction of feed motion.     

Force Curve Measurements with the AFM: Application to the In Situ Determination of Grafted Silicon-Wafer Surface Energies

The atomic force microscope (AFM) can be used to perform surface force measurements in the quasi-static mode (cantilever is not oscillating) to investigate nanoscale surface properties. Nevertheless, there is still a lack of literature proposing a complete systematic and rigorous experimental procedure that enables one to obtain reproducible and significant quantitative data. This article focuses on the fundamental experimental difficulties arising when making force curve measurements with the AFM in air. On the basis of this AFM calibration procedure, quantitative assessment values were used to determine, in situ, SAM (or Self Assembled Monolayer)-tip thermodynamic work of adhesion at a local scale, which have been found to be in good agreement with quoted values. Finally, determination of surface energies of functionalised silicon wafers (as received, CH₃, OH functionalised silicon wafers) with the AFM (at a local scale) is also proposed and compared with the values obtained by wettability (at a macroscopic scale). In particular, the effect of the capillary forces is discussed.     

A Computational Damage Micromodel of Laminated Composites

A new computational damage micromodel for laminates, which takes into account classical experimental micro- and macro-observations for various stacking sequences, is described. The first computational examples are shown.     

Formal verification of conflict detection algorithms

Safety assessment of new air traffic management systems is a main issue for civil aviation authorities. Standard techniques such as testing and simulation have serious limitations in new systems that are significantly more autonomous than the older ones. In this paper, we present an innovative approach for establishing the correctness of conflict detection systems. Fundamental to our approach is the concept of trajectory, and how we represent a continuous physical trajectory by a continuous path in the x-y plane constrained by physical laws and operational requirements. From the model of trajectories, we extract, and formally prove, high-level properties that can serve as a framework to analyze conflict scenarios. We use the AILS (Airborne Information for Lateral Spacing) alerting algorithm as a case study of our approach. Published online: 19 November 2002     

Estimation of catchment-scale water-balance with a soil-vegetation-atmosphere transfer model

Catchments with a small elevation range and relatively long dry periods in high radiation conditions may be described as an array of vertical one-dimensional pathways for water and energy. Such a representation enhances the ability of SVAT modeling to simulate mass exchanges across the catchment. This note reports on a comparison of a Soil-Vegetation-Atmosphere Transfer (SVAT) model (Braud et al., 1995), a deterministic hydrological model (Dawes and Hatton, 1993) and a stochastic hydrological model (Sivapalan and Woods, 1995; Kalma et al., 1995). The original version of the SVAT model only considers vertical transport and this one-dimensional representation must be aggregated to describe the entire catchment. Therefore, two new versions have been developed: a deterministic SVAT model which sub-divides the catchment into 40 sub-regions linked by surface flow, and a stochastic model which provides a distribution of the output fluxes as related to the spatial distribution of initial water content and/or soil properties. All simulations have been made for a 60-day period.     

Learning switching dynamic models for objects tracking

Many recent tracking algorithms rely on model learning methods. A promising approach consists of modeling the object motion with switching autoregressive models. This article is involved with parametric switching dynamical models governed by an hidden Markov Chain. The maximum likelihood estimation of the parameters of those models is described. The formulas of the EM algorithm are detailed. Moreover, the problem of choosing a good and parsimonious model with BIC criterion is considered. Emphasis is put on choosing a reasonable number of hidden states. Numerical experiments on both simulated and real data sets highlight the ability of this approach to describe properly object motions with sudden changes. The two applications on real data concern object and heart tracking.     

Quantitative x-ray microanalysis of spherical inclusions embedded in a matrix using a SEM and Monte Carlo simulations

The current schemes of quantification of x-ray microanalysis in the SEM [ZAF and σ(ρZ) methods] are valid for specimens of homogeneous composition. The determination of the chemical composition of small inclusions using these techniques is impossible because the volume of x-ray emission is not of homogeneous composition. A scheme of quantification to determine the composition of small inclusions embedded in a matrix has been developed using Monte Carlo simulations. This scheme is similar to that developed by Kyser and Murata (1974) for the quantification of thin foils deposited on a substrate using x-ray microanalysis in the SEM.     

Line of sight controller tuning using Bayesian optimisation: application to a double stage stabilisation platform

The inertial stabilisation of the line of sight of an imager fixed on a mobile carrier is considered in order to acquire good quality images despite the disturbances generated by the carrier. A double stage mechanical stabilisation architecture is proposed, where a second stabilisation stage, based on a piezoelectric actuator, is added to the usual structure. The piezoelectric actuator transfer function and hysteresis are characterised through experiments. In order to design the controllers of both stages, a high-level image quality criterion (the modulation transfer function (MTF)) is considered, together with design constraints on the main variables of interest. The criterion and the constraints are evaluated by realistic simulations based on some input and noise profiles measured on a real-life system. The MTF evaluation being time-consuming, a Bayesian optimisation method specially dedicated to expensive-to-evaluate functions is used to obtain the parameters of the controllers. The obtain experimental results are displayed and their performances discussed.