COLLEGE DIRECTORY       :      VISIT ELLER      :      LOG IN 
Eller College of Management
Eller College Home > MIS > Artificial Intelligence Laboratory > Research > Digital Libraries > NanoPort
Artificial Intelligence Laboratory

Digital Libraries Projects - NanoPort

Nano Technology Portal

Introduction

NanoPort is an online search system designed to facilitate efficient and precise searching of nanoscale science and engineering information for research professionals and the general public.

Instruction

NanoConceptSpace:
NanoPort Concept Space is a "thesaurus" of nanotechnology built by Artificial Intelligent Lab in MIS department in the University of Arizona. We employed a text mining approach to extract terminologies and their weighted relationships to generate the concept space. Its main purpose is to help users to find the best keywords when they are doing a search in our NanoPort web portal.

NanoPort Concept Space contains 1,711,740 terms with over 130 millions relationships. Currently, it is built based on documents in three databases: Medline, INSPEC, and BIOSIS.
The Concept Space will cover more area of nanotechnology related fields in the future. We recognize that the current version of our Concept Space mainly cover biology/medicine fields but very few engineering domains. However, two more databases, NanoPort database and Compendex, are underdevelopment. The next version of concept space will be more representative and have broader coverage in Nanotechnology related domain.

NanoSearch:
NanoSearch is a search engine created specifically for the domain of nanoscale science and engineering. It was developed by the Artificial Intelligence Lab at the University of Arizona.
NanoSearch contains 700,000 quality pages. It has the largest collection of nano science related documents in the United States. Those pages contain over 20,000 PDF files, 3,000 MS Word and Excel files.

There are over 170,000 sites in the NanoSearch collection. The majority of site types include 68,000 commercial sites, 19,000 educational sites, 16,000 organizational sites, 7,000 network sites, 3,000 governmental sites and 600 military sites. In addition to the web pages from the United States, the collection contains pages from almost 200 other countries, including the United Kingdom, Germany, Japan, Canada and so on.
The AI Lab’s Search Engine Toolkit and Meta Search module are used to collect pages. An advanced page collecting methodology is used to ensure the quality and coverage of the collection. Furthermore, a content analysis algorithm and link analysis algorithm are used to rank the search results as well as filter out unrelated pages. Microsoft SQL Server is used as a backend database server.

Return to Top

Meta Search:
The idea of meta searching is to send queries to multiple search engines, and literature databases, online journals, and to collate only the highest-ranking subset from each data source, thus increasing precision. Meta search provides a simple uniform user interface that promises significant advances in coping with information overload and low-precision issues.

Document Categorization and Visualization:
An ideal Information Retrieval (IR) system should categorize retrieved documents automatically and give the user rapid access to various aspects of the subject of interest. NanoPort renders immediate assistance in locating useful information and determining the relevancy of retrieved documents. The documents retrieved from the Meta Search are classified into different categories based on the occurance of keywords extracted from the documents. A visualization tool helps to facilitate the elucidation of meaning and understanding.

Return to Top