Clemson University
 
James (Zijun) Wang
School of Computing

Current Research Projects

G-SESAME: Gene SEmantic Similarity Analysis and MEasurement tools

Since many biological data analysis methods require numeric representation of the functional similarity of genes, automatically discovering the descriptive similarities of genes and converting them into measurable numeric values are very important for such analyses. This research project will solve this important problem by designing novel algorithms to measure the semantic similarity of vocabularies used to annotate genes and, in turn, devising effective algorithms to determine the functional similarity of genes.

Ontology-based P2P Information Retrieval.

In this project, we study the ontology-based approaches to search the large-scale P2P network. This research is expected to address two fundamental scientific issues: (1) Modeling the semantics of queries and text documents and their semantic match without the need to analyze the entire document corpus, and (2) Decentralized autonomous self-adaptive design of semantic overlay network for fast information retrieval in P2P networks.The long-term goal is to design an ontology-based P2P information-sharing framework that efficiently manages the distributed semantics of all peers in the network and intelligently routes the content-based P2P queries in a self-adaptive and decentralized fashion.

Non-invasive Skin Cancer Detection using Optial Device

This research of combining PLS and MSLS technologies to investigate skin tissue has been motivated by an attempt to synthesize some of the best aspects of the various approaches under investigation. Toward this end, we are currently conducting a 3-year research project of advancing a novel spectroscopic method for skin cancer detection by focusing on improving feature extraction algorithms and enhancing classification software. This research is expected to make a significant contribution to early screening and detection of skin cancer which will maximize cure rates and reduce or even avoid unnecessary biopsies.

Online Brain Image Annotation and Classification Tools

The goal of this project is to build a set of online tools to automatically process and classify brain images to assist the diagnosis of minor brain impairs. In this study, we will conduct the advanced research on 3-D image segmentation, classification, and visualization.

Virtual Storage System in Corporation Network

In this project, we will explore the existing commodity storage space in the corporation network and build a virtual file system on top of existing heterogeneous file systems to provide large scale virtual storage system that is robust, self-managed, automatically protected and fast access.