Urban hotspot area detection is an important issue that needs to be explored for urban planning and traffic management. It of great significance mine hotspots from taxi trajectory data, which reflect residents’ travel characteristics the operational status traffic. The existing clustering methods mainly concentrate on number objects contained in within a specified size, neglecting impact local ...

A new coordination framework material, [Zn{MnN(CN)4(H2O)}]·2H2O·MeOH, has been characterised crystallographically and the effect of a terminal nitride on the N2, H2 and CO2 sorption capacities of the material assessed through porosimetery measurements and DRIFTS.

K-nearest neighbor (KNN) is an effective nonparametric classifier that determines the neighbors of a point based only on distance proximity. The classification performance KNN disadvantaged by presence outliers in small sample size datasets and its deteriorates with class imbalance. We propose local Bonferroni Mean Fuzzy K-Nearest Centroid Neighbor (BM-FKNCN) assigns label query dependent neare...

Classification is a challenging task that has important application in real life and its application are excepted to grow more in future. In this paper, we analyze the effectiveness of Modular Neural Network as a modelling tool for data classification. The MNN classifier outperforms the surveyed nets due to its novel task decomposition and multi-module decision-making techniques. In this paper,...

The k-nearest neighbor classifier follows a simple, yet powerful algorithm: collect the k data points closest to an unlabeled instance, according to a given distance measure, and use them to predict that instance’s label. The two components, the parameter k governing the size of used neighborhood, and the distance measure, essentially determine success or failure of the classifier. In this work...

In this paper, we address the approximate nearest neighbor (ANN) search problem over large scale visual descriptors. We investigate a simple but very effective approach, neighborhood graph (NG) search, which conducts the local search by expanding neighborhoods with a best-first manner. Expanding neighborhood makes it efficient to locate the descriptors with high probability being true NNs. Howe...

Graph-based methods are very popular in semi-supervised learning due to their well founded theoretical background, intuitive interpretation of local neighborhood structure, and strong performance on a wide range of challenging learning problems. However, the success of these methods is highly dependent on the pre-existing neighborhood structure in the data used to construct the graph. In this p...