Context-dependent Information Research Articles

Parametric shape recognition using a probabilistic inverse theory

This paper describes a new framework for parametric shape recognition based on a probabilistic model of inverse theory first introduced by Tarantola. The key result is a method for generating classifiers in the form of conditional probability densities for recognizing an unknown from a set of reference models. Our procedure is automatic. Off-line, it invokes an autonomous process to estimate reference model parameters and their statistics. On-line, during measurement, it combines these with a priori context-dependent information, as well as the parameters and statistics estimated for an unknown object, into a single description. That description, a conditional probability density function, represents the likelihood of correspondence between the unknown and a particular reference model. The paper also describes the implementation of this procedure in a system for automatically generating and recognizing 3-D part-oriented models. Specifically we show that recognition performance is near perfect for cases in which complete surface information is accessible to the algorithm, and that it falls off gracefully (minimal false-positive response) when only partial information is available. This leads to the possibility of an active recognition strategy in which the belief measures associated with each classification can be used as feedback for the acquisition of further evidence as required.

Cooperative image workstation based on explicit models of diagnostic information requirements.

A medical image workstation designed to act as a cooperative dialogue partner in diagnostic radiology has been conceived, and a prototype has been made. The system can automatically select relevant information (eg, from current and previous examinations) and generate a meaningful and appropriate image arrangement on the display screen. For a number of routinely performed tasks in radiology, the users' interaction may be as simple as switching from one patient to the next. This is shown to considerably simplify and speed up radiological image access and presentation, saving the user time and effort. The cooperative system response is based on explicit (formalized and computer-accessible) models of diagnostic information requirements. These models are context dependent and take into account that diagnostic information needs vary with radiological work procedures, workstation users, and patient cases. Initial models have been acquired from expert radiologists in two European hospitals and were integrated in a cooperative workstation prototype. For the representation of models, rule-based and object-oriented techniques were applied. The rule base was designed with a distinct modular structure, separating between rule sets for general, task-dependent, and user-dependent information requirements. The installed rule-based mechanism also offers a solution for the automatic prefetching of images to avoid transmission delays in the course of diagnostic work sessions. The first part of the report reviews the objectives for the design of cooperative workstation user interfaces and explains the benefits from the users' point of view. In the second part, the acquisition, structuring, formalization, and representation of context-dependent information requirement models is described. The rule-based model is explained using examples. A layered workstation architecture consisting of model, object, and real-time layers is presented. Difficulties in the implementation of cooperative workstations are discussed that point to future research topics and standardization efforts.

MEMORY PROCESSES IN MEDIA EFFECTS

Memory mediates the effects of mass media on the individual. The nature of memory is such that encoding, storage, and retrieval of episodic (context-dependent) information from mass media messages is often inhibited whereas semantic (thematic, procedural, structural) information retention is often promoted. Therefore, mass media effects are better defined in terms of structural information transmission than in terms of specific content transmission.

The HEARSAY Speech Understanding System

This talk describes the present state of performance of the HEARSAY system. [For more complete descriptions of the system see D. R. Reddy, L. D. Erman, and R. D. Neely, “A Model and a System for Machine Recognition of Speech,” IEEE Trans. Audio Electroacoust. AU-21, 229–238 (1973) and D. R. Reddy, L. D. Erman, R. D. Fennell, and R. B. Neely, “The HEARSAY Speech Understanding System : An Example of the Recognition Process,” Proc. 3rd Int. Joint Conf. on Artificial Intelligence (Aug. 1973)]. The system uses task and context-dependent information to help in the recognition of the utterance; this system consists of a set of cooperating parallel processes, each representing a different source of knowledge (e.g., acoustic-phonetic, syntactic, semantic). The knowledge is used either to predict what may appear in a given context or to verify an hypothesis resulting from a previous prediction. Performance data of the system on several tasks (e.g., medical diagnosis, news retrieval, chess, and programming) will be presented. For example: The voice-chess task contains a 31-word vocabulary with about 5 000 000 possible sentences. One particular set of data contains 19 utterances of three to nine (mean =4.5) words each. Seventy-nine percent of the utterances are correctly recognized (at about four times real time on a PDP10 computer); removing the semantic source of knowledge (but leaving the syntactic and acoustic-phonetic) reduces recognition to 42%.