Retrieval systems, best match

Case-based reasoning is very much dependent on the structure and content of its cases and their representation because case retrieval involves identifying those features in the problem that best match those in the case base. The dynamic addition of new cases means that CBR is intrinsically a learning methodology such that the performance of an expert system based on this approach will improve with time [9]. Systems may be developed with conventional computer languages or shells [7]. 

Apphcation of the similarity index provides a classification of the references by separating these in two classes compounds that may be and compounds that cannot be the same as the unknown. In terms of hypothesis testing, this is equivalent to acceptance or rejection of the null hypothesis that the unknown and the reference compound are identical. A library search system based on this principle should retrieve all references of the may be class, i.e., all references with a similarity index exceeding a predefined threshold value, rather than the 5 or 10 best matches (which may also be very bad matches). 

The goal of video retrieval is to retrieve video that best matches the query. Information retrieval is a method in which the user is able to convert his need for information into an actual list of videos. In this paper, a model for information retrieval based on keywords distribution in a video has been proposed. This system returns, as result, a list of videos, in which the keyword entered by the learner is spoken. Videos are ranked according to the keyword frequency. In each video of retrieved list, frame number is also mentioned where the word is spoken for the first time. Link for each video is given upon clicking the link, the video starts playing from the mentioned frame number. Frame gap is used for analysis of the system. It is found that the system gives the results with 95 % accuracy. The display of frame related to the spoken word reduces the considerable effort on the part of the user to search through the video. 

Anderson and Covert (1967) have described a computer search system for the retrieval of infrared data. The system uses an IBM 7080 computer to search the data on magnetic tape for about 100,000 compounds, 90,000 of which are from the ASTM collection. Eastman Organic Chemicals, Rochester, New York 14650, runs a service based on this system. One can send copies of the infrared curve or curves of unknown compounds and ask for service under the catalogue number Eastman No. 6070. The computer output is a printed report listing in order of best probable match the names of up to 25 compounds most closely resembling the unknown compound. This search service supplies names of compounds only, not infrared spectra. 

---