Nearest Neighbour

We study the formation and growth of equilibrium clusters in a suspension of weakly-charged colloidal particles and small non-adsorbing polymers. The effective potential is characterised by a short-range attraction and a long-range repulsion. The size, shape and local structure of the clusters are studied using three-dimensional particle microscopy. We observe a rapid growth in the mean cluster size and the average number of nearest neighbours approaching the gel boundary.

We report the structural and magnetic properties of the La1−xTbxMn1/2Sc1/2O3 series. LaMn1/2Sc1/2O3 shows a long range ferromagnetic ordering in agreement with a fully polarized Mn-sublattice. The substitution of La with Tb produces structural changes which affect the magnetic properties. This substitution leads to a contraction in the unit cell volume that mainly reduces the M–O–M bond angle (M = Mn,

Gains from productivity and knowledge transmission arising from the presence of foreign firms have received a good deal of empirical attention, but theoretical micro-foundations for this mechanism are limited. Here we develop a dynamic model in which foreign experts may train domestic workers who work with them. Gains from training can in turn be decomposed into two types: (a) obtaining

A technique is presented where actual experimental distributions, measured from a high strength carbon fibre composite, are considered in the development of a novel method to generate statistically equivalent fibre distributions for high volume fraction composites. The approach uses an adjusted measure of nearest neighbour distribution functions to define inter-fibre distances. The statistical distributions, characterising the resulting fibre arrangements, were found to be equivalent to those in the actual microstructure. Finite ...

The purpose of this study was to assess the performance of a real-time ("open-end") version of the dynamic time warping (DTW) algorithm for the recognition of motor exercises. Given a possibly incomplete input stream of data and a reference time series, the open-end DTW algorithm computes both the size of the prefix of reference which is best matched by the input, and the dissimilarity between the matched portions. The algorithm was used to provide real-time feedback to neurological patients undergoing motor rehabilitation. We acquired a dataset of multivariate time series from a sensorized long-sleeve shirt which contains 29 strain sensors distributed on the upper limb. Seven typical rehabilitation exercises were recorded in several variations, both correctly and incorrectly executed, and at various speeds, totaling a data set of 840 time series. Nearest-neighbour classifiers were built according to the outputs of open-end DTW alignments and their global counterparts on exercise pairs. The classifiers were also tested on well-known public datasets from heterogeneous domains. Nonparametric tests show that (1) on full time series the two algorithms achieve the same classification accuracy (p-value =0.32); (2) on partial time series, classifiers based on open-end DTW have a far higher accuracy (kappa=0.898 versus kappa=0.447;p<10(-5)); and (3) the prediction of the matched fraction follows closely the ground truth (root mean square <10%). The results hold for the motor rehabilitation and the other datasets tested, as well. The open-end variant of the DTW algorithm is suitable for the classification of truncated quantitative time series, even in the presence of noise. Early recognition and accurate class prediction can be achieved, provided that enough variance is available over the time span of the reference. Therefore, the proposed technique expands the use of DTW to a wider range of applications, such as real-time biofeedback systems.

The warehouses play a versatile role in the logistics management system. The objective of the warehousing function is to provide a buffer between supply and demand. In most warehouses, order picking is the major activity and involves collecting of products according to customer orders. On the other hand, it is necessary to plan the outside distribution of the orders. Determining the suitable distribution routes from one or more warehouses to a number of geographically separated customers is called vehicle routing problem in the literature. Although the order picking and vehicle routing problems are related to each other, they have been handled separately by this time. In this study, genetic algorithm based approaches which solve order picking and vehicle routing problems connected to each other in a hierarchical manner for both conventional and multiple cross aisles warehouse systems are proposed. While the groups of the orders and customers are determined using Genetic Algorithms, the routes of the vehicles are determined with the help of Savings and Nearest Neighbor Heuristics. In order to investigate the effectiveness of proposed methods, 24 well-known test problems are conducted and the obtained results are compared with previous researches. In conclusion, the improved genetic algorithm based solution approaches provided very close results to the known best results.

This paper describes a document recognition system for the modern neume based notation of Byzantine music. We propose algorithms for page segmentation, lyrics removal, syntactical symbol grouping and the determination of characteristic page dimensions. All algorithms are experimentally evaluated on a variety of printed books for which we also give an optimal feature set for a nearest neighbour classifier. The system is based on the Gamera framework for document image analysis. Given that we cover all aspects of the recognition process, the paper can also serve as an illustration how a recognition system for a non standard document type can be designed from scratch.

Computer assisted avalanche forecasting has become a valuable tool in some forecasting operations in Canada. Avalanche forecasting models are based on statistical, numerical and/or rule-based methods, but usually predict natural rather than skier-triggered avalanches. A nearest neighbour forecasting model for skier-triggered avalanches on post storm weak layers was improved by adding snowpack properties including a stability index to meteorological variables. However, a skier stability index did not improve the forecasting success on storm snow instabilities. The best forecast could be achieved by using meteorological parameters.

In this paper, we study the heat equation on a homogeneous graph, relative to the natural (nearest{neighbour) Laplacian. We nd pointwise esti- mates for the heat and resolvent kernels, and the Lp-Lq mapping properties of the corresponding operators. M. M. H. Pang (P) considered the semigroup (e t)t>0: In this paper, we consider the heat semigroup associated to the canonical Laplace operator on a homogeneous tree, which is perhaps the basic example of a graph where the cardinality of the \ball of radiusr" grows exponentially in r. We study the properties of the heat and resolvent operators, and discover very close analogies with diusions on hyperbolic spaces, in line with the philosophy of the above-mentioned authors. A homogeneous tree X of degree q + 1 is dened to be a connected graph with no loops, in which every vertex is adjacent to q + 1 other vertices. We denote by d the natural distance on X ;d (x;y) being the number of edges between the vertices x and y; and by Lp(X)...

ABC Appliances (Pvt) Ltd.,one of the leading companies in Sri Lanka has supplied and installed a very
large number of air condition units all over the country. The company is currently provides a
comprehensive after sales service for its customers. At present the service department is interesting in
reducing the cost involving in regular after sale servicers. In this research we proposed a Travelling
Salesman Problem (TSP) approach tominimize the cost involving in service tours. We used nearest
neighbourhood search algorithm to obtain the solutions to the TSP. Computational examples show that the
new service routes obtained using this algorithm will reduce the travelling cost significantly in comparison
to existing routs.

In this paper, a feature extraction and hybrid classification scheme, using binary decision tree and nearest neighbour, for machine recognition of Gurmukhi characters is described. The classification process is carried out in three stages. In the first stage, the characters are grouped into three sets depending on their zonal position ( upper zone, middle zone and lower zone). In the

Different applications on the use of Terrestrial Laser Scanner (TLS) on rock slopes are undergoing rapid development, mainly in the characterization of 3D discontinuities and the monitoring of rock slopes. The emphasis of this research is on detection of precursory deformation and its application to spatial prediction of rockfalls. The pilot study area corresponds to the main scarp of an old slide located at Puigcercós (Catalonia, Spain). 3D temporal variations of the terrain were analyzed by comparing sequential TLS datasets. Five areas characterized by centimetric precursory deformations were detected in the study area. Of these deformations, (a) growing deformation across three areas culminated in a rockfall occurrence; and (b) another growing deformation across two areas was detected, making a subsequent rockfall likely. The areas with precursory deformations detected in Puigcercós showed the following characteristics: (a) a sub-vertical fracture delimiting the moving part from the rest of the slope; (b) an increase in the horizontal displacement upwards, typical of a toppling failure mechanism (Muller 1968; Goodman and Bray, 1976). In addition, decimetric-scale rockfalls were observed in the upper part of the moving areas, which is consistent with the observations of Rosser et al., (2007). TLS ILRIS 3D technical characteristics are as follows: high accuracy (7.2 mm at a range of 50 meters), high angular resolution (e.g. 1 point every few cm), fast data acquisition: 2,500 points/second; broad coverage; high maximum range on natural slopes: ~600m. The single point distances between the surface of reference and the successive data point clouds were computed using a conventional methodology (data vs. reference comparison). The direction of comparison was defined as the normal vector of the rock face at its central part. We focused in the study of the small scale displacements towards the origin of coordinates, which reflect the pre-failure deformation on part of the slope. A nearest neighbour (NN) filtering technique was applied to the RAW datasets (Abellán et al., 2009), enabling the accurate detection of centimetric displacements. The parameters of the precursory deformation correlated with the failure mechanism, lithology and volume of the rockfall: higher values of length and duration of the precursory deformation were found in the toppling failure mechanism, ductile materials and rockfalls that involved considerable volumes. These results are consistent with observations in the literature regarding rockfalls of higher magnitude and lower frequency (e.g.: Zvelebil and Moser, 2001; Crosta and Agliardi, 2004; Hungr et al., 2007). It is also important to mention that no precursory indicators were detected prior to each rockfall that occurred in the study areas. This could simply be due to infrequent data acquisition or insufficient instrument accuracy. The application of TLS for the spatial prediction of rockfalls should be validated through: (a) the continuation of the TLS monitoring campaign at the areas which currently show ongoing deformation; (b) the selection of new case studies at different geomorphological sites with different lithologies; and (c) the selection of new case studies with different failure mechanisms (e.g. fall, slide). These tasks are of paramount importance to understand the pre-failure behaviour of rockfalls and to implement these findings in an early warning system.