The design of a specialised query language for content based image retrieval provides a means of addressing many of the problems associated with commonly used query paradigms such as query-by-example and query-by-sketch.
Fig. 14 Example queries: a query with conditions, a graph with fingerprints and a more complex combination of both.
Most of the current solutions try to facilitate high-level querying of sensor data, help to mask the distribution and heterogeneity in the sensor network, and address resource constraints by providing, for example, energy-aware routing and query processing.
Prasad Tadepalli and Stuart Russell, ''Learning from Examples and Membership Queries with Structured Determinations". Machine Learning, 32, 245-95, 1998.
Example (hypercholesterolemia): Using hypercholesterolemia as an example search query and a set of 18 ontologies, we identify 20 objects and 102 attributes initially, as in Figure 1.
The input to the system is an acoustic example per query, and hence prior knowledge of the correct word/subword transcription corresponding to each query is not available.
Therefore, the input to the system is an acoustic example per query, and hence prior knowledge of the correct word/phone transcription corresponding to each query cannot be used.
Due to its statistical nature, this approach can tolerate certain length variance between the query example and database items.
They calculate spectrum energy from sub-band coefficients (SBC) to simulate the melody contour and use it to measure the similarity between the query example and those database items.
Therefore, by right of the power of the stable fingerprint, we can adopt a relatively straightforward yet effective measure, i.e., Hamming distance, to perform exhaustive matching between the query example and those stored recordings.
