Abraham Kandel Knihy

This book presents a unified framework focusing on three major components: Search Engine Performance, Link Analysis, and User Web Behavior. The rapid expansion and accessibility of the World Wide Web have spurred significant research in information retrieval. The three aspects of web mining—Link Analysis, Search Engines, and User Behavior—are explored in a cohesive manner. The book is divided into three sections. Section I (chapters 2–4) delves into Link Analysis through the hubs and authorities framework, which ranks hyperlink structures to assess the relative authority of web pages and enhance search result algorithms. It examines the HITS Algorithm by Kleinberg, proposing a study of HITS in a new 2-D space defined by In-degree and Out-degree variables. The categorization of web pages into specific topologies allows for an analysis of how these topologies affect HITS performance in this new dimensionality. Additionally, the PageRank Algorithm is discussed within the same 2-D context, highlighting the challenges HITS faces across various web graph topologies. The exploration of these algorithms aims to improve understanding and effectiveness in web mining practices.

This book presents novel graph-theoretic methods for complex computer vision and pattern recognition tasks. It presents the application of graph theory to low-level processing of digital images, presents graph-theoretic learning algorithms for high-level computer vision and pattern recognition applications, and provides detailed descriptions of several applications of graph-based methods to real-world pattern recognition tasks.

Many business decisions are made in the absence of complete information about the decision consequences. Credit lines are approved without knowing the future behavior of the customers; stocks are bought and sold without knowing their future prices; parts are manufactured without knowing all the factors affecting their final quality; etc. All these cases can be categorized as decision making under uncertainty. Decision makers (human or automated) can handle uncertainty in different ways. Deferring the decision due to the lack of sufficient information may not be an option, especially in real-time systems. Sometimes expert rules, based on experience and intuition, are used. Decision tree is a popular form of representing a set of mutually exclusive rules. An example of a two-branch tree is: if a credit applicant is a student, approve; otherwise, decline. Expert rules are usually based on some hidden assumptions, which are trying to predict the decision consequences. A hidden assumption of the last rule set is: a student will be a profitable customer. Since the direct predictions of the future may not be accurate, a decision maker can consider using some information from the past. The idea is to utilize the potential similarity between the patterns of the past (e. g., „most students used to be profitable“) and the patterns of the future (e. g., „students will be profitable“).