An efficient model to store and retrieve surface watershed boundaries using graph theoretic approaches is proposed. Our approach utilizes three algorithms and accepts as input standard digital elevation models derived stream catchment boundaries. The first is called Modified Nested Set (MNS), which is a generalized depth first graph traversal algorithm that searches across stream reaches (verti...

Data mining is the process of extracting knowledge structures from continuous, rapid and extremely large stream data which handles quality and data analysis. In such traditional transaction environment it is impossible to perform frequent items mining because it requires analyzing which item is a frequent one to continuously incoming stream data and which is probable to become a frequent item. ...

Dynamic changing nature of stream data are induced a difficulty of training pattern and process of class labeling in classification. The stream data classification has some difficulty such as feature evaluation, data drift, concept evaluation and infinite length. The infinite length and feature evaluation is more realistic problem in stream data classification technique. Different authors used ...

background policy makers need models to be able to detect groups at high risk of hiv infection. incomplete records and dirty data are frequently seen in national data sets. presence of missing data challenges the practice of model development. several studies suggested that performance of imputation methods is acceptable when missing rate is moderate. one of the issues which was of less concern...

Data sampling over data streams is common practice to allow the analysis of data in real-time. However, sampling over data streams becomes complex when the stream does not fit in memory, and worse yet, when the length of the stream is unknown. A well-known technique for sampling data streams is the Reservoir Sampling. It requires a fixed-size reservoir that corresponds to the resulting sample s...

We explore the possibilities of meta-learning on data streams, in particular algorithm selection. In a first experiment we calculate the characteristics of a small sample of a data stream, and try to predict which classifier performs best on the entire stream. This yields promising results and interesting patterns. In a second experiment, we build a meta-classifier that predicts, based on measu...

We consider the problem of extracting informative exemplars from a data stream. Examples of this problem include exemplarbased clustering and nonparametric inference such as Gaussian process regression on massive data sets. We show that these problems require maximization of a submodular function that captures the informativeness of a set of exemplars, over a data stream. We develop an efficien...