• Publications
  • Influence
Toward accurate dynamic time warping in linear time and space
This paper introduces FastDTW, an approximation of DTW that has a linear time and space complexity and shows a large improvement in accuracy over existing methods. Expand
FastDTW: Toward Accurate Dynamic Time Warping in Linear Time and Space
This paper introduces FastDTW, an approximation of DTW that has a linear time and space complexity that uses a multilevel approach that recursively projects a solution from a coarse resolution and refines the projected solution. Expand
Determining the number of clusters/segments in hierarchical clustering/segmentation algorithms
  • S. Salvador, P. Chan
  • Computer Science
  • 16th IEEE International Conference on Tools with…
  • 15 November 2004
This work proposes an efficient algorithm, the L method, that finds the "knee" in a '# of clusters vs. clustering evaluation metric' graph, using the knee is well-known, but is not a particularly well-understood method to determine the number of clusters. Expand
AdaCost: Misclassification Cost-Sensitive Boosting
It is formally show that AdaCost reduces the upper bound of cumulative misclassification cost of the training set, which is significant reduction in the cumulative mis classification cost over AdaBoost without consuming additional computing power. Expand
An Analysis of the 1999 DARPA/Lincoln Laboratory Evaluation Data for Network Anomaly Detection
This investigation of the 1999 background network traffic suggests the presence of simulation artifacts that would lead to overoptimistic evaluation of network anomaly detection systems. Expand
Cost-based modeling for fraud and intrusion detection: results from the JAM project
There is clear evidence that state-of-the-art commercial fraud detection systems can be substantially improved in stopping losses due to fraud by combining multiple models of fraudulent transaction shared among banks. Expand
Learning nonstationary models of normal network traffic for detecting novel attacks
This paper proposes a learning algorithm that constructs models of normal behavior from attack-free network traffic that can be combined to increase coverage of traditional intrusion detection systems. Expand
PHAD: packet header anomaly detection for identifying hostile network traffic
An experimental packet header anomaly detector (PHAD) that learns the normal range of values for 33 fields of the Ethernet, IP, TCP, UDP, and ICMP protocols, and results were obtained by examining packets and fields in isolation, and by using simple nonstationary models. Expand
JAM: Java Agents for Meta-Learning over Distributed Databases
The overall architecture of the JAM system is described and the specific implementation currently under development at Columbia University is described, one of JAM's target applications is fraud and intrusion detection in financial information systems. Expand
Toward Scalable Learning with Non-Uniform Class and Cost Distributions: A Case Study in Credit Card Fraud Detection
A multi-classifier meta-learning approach to address very large databases with skewed class distributions and non-uniform cost per error and empirical results indicate that the approach can significantly reduce loss due to illegitimate transactions. Expand