This dissertation presents various machine learning applications for predicting different cognitive states of students while they are using a vocabulary tutoring system, DSCoVAR. We conduct four studies, each of which includes a comprehensive analysis of behavioral and linguistic data and provides data-driven evidence for designing personalized…

Syntactic structures are unobserved theoretical constructs which are useful in explaining a wide range of linguistic and psychological phenomena. Language acquisition studies how such latent structures are acquired by human learners through many hypothesized learning mechanisms and apparatuses, which can be genetically endowed or of general…

The Indian Institute of Science is proud to host the fully in-person sixteenth iteration of the International Conference on Educational Data Mining (EDM) during July 11-14, 2023. EDM is the annual flagship conference of the International Educational Data Mining Society. The theme of this year's conference is "Educational data mining for…

This study develops an integrated conceptual representation scheme for multimedia documents that are viewed to comprise an object-oriented database; the necessary abstractions for the conceptual model and extensions to the relational model used as the search structure; a retrieval model that includes associative, semantic and media-specific…

The TETRAD for constraint-based aids to causal model specification project and related work in computer science aims to apply standards of rigor and precision to the problem of using data and background knowledge to make inferences about a model's specifications. Several algorithms that are implemented in the TETRAD II program are presented. (SLD)

Examines how a domain ontology can be reused by different knowledge representation systems. Describes a meta-language which allows a declarative description of any model based on frames, objects, relations, or description logics. Discusses the meta-relation concept which, associated to a definition, represents the signification of the construct…

Presents a three-way, three-mode extension of the two-way, two-mode hierarchical classes model of P. De Boeck and S. Rosenberg (1998) for the analysis of individual differences in binary object x attribute arrays. Illustrates the model with data on psychiatric diagnosis and discusses the relation between the model and other extant models. (SLD)

Discussion of semantic networks and ranked retrieval focuses on two models, the semantic network model with spreading activation and the vector space model with dot product. Suggests a formal method to analyze the two models in terms of their relative performance in the same universe of objects. (Author/LRW)

Discusses latent semantic indexing (LSI) that would allow search engines to reduce the dimension of the document space by mapping it into a space spanned by conceptual indices. Topics include vector space models; singular value decomposition (SVD); unitary operators; the Haar transform; and new algorithms. (Author/LRW)

Describes a modified frequency-sensitive self-organization (FSO) algorithm for image data compression and the associated VLSI architecture. Topics discussed include vector quantization; VLSI neural processor architecture; detailed circuit implementation; and a neural network vector quantization prototype chip. Examples of images using the FSO…

Discussion of information retrieval focuses on an Interaction Information Retrieval model in which documents are interconnected; queries and documents are treated in the same way; and retrieval is the result of the interconnection between query and documents. A theoretical mathematical formulation of this type of retrieval is given. (Contains 31…

A procedure for item analysis using distance clustering is described. Items are grouped according to the predominant factors measured, regardless of what they are. The procedure provides an efficient method of treating unanswered items. (Author/RC)

This report discusses some of the problems and limitations in existing internetwork design for the connection of packet-switching networks of different technologies and presents an algorithm that has been shown to be suitable for internetworks of unbounded size. Using a new form of address and a flat routing mechanism called Cartesian routing,…

Discussion of text compression focuses on a method to reduce the amount of storage needed to represent a Markov model with an extended alphabet, by applying a clustering scheme that brings together similar states. Highlights include probability vectors; algorithms; implementation details; and experimental data with natural languages. (Author/LRW)