Graph mining refers to extracting knowledge from massive graphs. The data sets of telephone calls we see at AT&T can be viewed as a single graph, with several hundred million phone numbers as nodes, and calls between phone numbers as edges. It is a giant social network, like an internet connections graph or a rich citation network.
Analysis and management of large datasets Parallel distributed software systems design and implementation Component architecture for scientific software Performance tuning for large distributed software
XmdvTool is a public-domain software package for the interactive visual exploration of multivariate data sets. It is available on all major UNIX/LINUX/MAC and Window platforms. XmdvTool is developed based on OpenGL and Tcl/Tk. It supports five methods for displaying flat form data and hierarchically clustered data: 1. Scatterplots 2. Star Glyphs 3. Parallel Coordinates 4. Dimensional Stacking 5. Pixel-oriented Display
"LAMDA" means "Learning And Mining from DatA". The main research interests of LAMDA include machine learning, data mining, information retrieval, pattern recognition, neural computation, evolutionary computation, and some other related areas. Currently our research mainly involves: ensemble learning, semi-supervised learning, multi-instance and multi-label learning, cost-sensitive and class-imbalance learning, dimensionality reduction and feature selection, theoretical foundations of evolutionary computation, improving comprehensibility of learning sytems, content-based image retrieval, web search and mining, face recognition, computer-aided medical diagnosis, etc.
DCCP is a new transport protocol being developed by the IETF to provide a connection-oriented, congestion controlled, unreliable transport service. Most applications that require an unreliable transport currently use UDP and ignore congestion issues, causing concerns about congestion collapse in the general Internet if these applications (especially VoIP) get too popular. DCCP is meant to give these applications an opportunity to become good 'Net citizens without forcing them to individually tackle the difficult problems of developing congestion control mechanisms.
This is the DCCP-TP Wiki. DCCP-TP is a fresh-start implementation of the Datagram Congestion Control Protocol (DCCP) optimized for portability. This site provides source code downloads and documentation for DCCP-TP.
The Datagram Congestion Control Protocol (DCCP) is a transport protocol that provides bidirectional unicast connections of congestion-controlled unreliable datagrams. DCCP is suitable for applications that transfer fairly large amounts of data and that can benefit from control over the tradeoff between timeliness and reliability.
PeerCQ is a peer-to-peer system for information monitoring on the web that uses CQs as its primitives to express information monitoring requests. The primary objective of the PeerCQ system is to build a decentralized Internet scale distributed system for monitoring information change on the web. The system is aimed to be highly scalable, self-organizing and support efficient and robust way of processing CQs.
S. Das, D. Agrawal, and A. Abbadi. DaMoN '08: Proceedings of the 4th international workshop on Data management on new hardware, page 1--10. New York, NY, USA, ACM, (2008)
N. Bandi, A. Metwally, D. Agrawal, and A. Abbadi. SIGMOD '07: Proceedings of the 2007 ACM SIGMOD international conference on Management of data, page 247--256. New York, NY, USA, ACM, (2007)