Persistent clustered main memory index for accelerating k-NN queries on high dimensional datasets.
Lijuan ZhangAlexander ThomasianPublished in: CVDB (2005)
Keyphrases
- knn
- main memory
- index structure
- nearest neighbor
- high dimensional datasets
- range queries
- disk accesses
- high dimensional data
- k nearest neighbor
- high dimensional spaces
- sequential scan
- inverted index
- query processing
- indexing techniques
- b tree
- indexing structure
- access methods
- r tree
- external memory
- data structure
- text categorization
- high dimensional
- similarity queries
- data distribution
- similarity search
- high dimensionality
- distance function
- database management systems
- join algorithms
- cost model
- disk access
- outlier detection
- metric space
- classification algorithm
- multi dimensional
- text classification
- database
- support vector machine
- query point
- feature selection
- database systems
- decision trees
- concept drift
- training set
- clustering algorithm
- neural network