Sciweavers

ICMLA
2007
13 years 10 months ago
Soft Failure Detection Using Factorial Hidden Markov Models
In modern business, educational, and other settings, it is common to provide a digital network that interconnects hardware devices for shared access by the users (e.g., in an ofï¬...
Guillaume Bouchard, Jean-Marc Andreoli
ICMLA
2007
13 years 10 months ago
Semi-Supervised Active Learning for Modeling Medical Concepts from Free Text
We apply a new active learning formulation to the problem of learning medical concepts from unstructured text. The new formulation is based on maximizing the mutual information th...
Rómer Rosales, Praveen Krishnamurthy, R. Bh...
ICMLA
2007
13 years 10 months ago
Memory-based context-sensitive spelling correction at web scale
We study the problem of correcting spelling mistakes in text using memory-based learning techniques and a very large database of token n-gram occurrences in web text as training d...
Andrew Carlson, Ian Fette
ICMLA
2007
13 years 10 months ago
Understanding Challenges in Preserving and Reconstructing Computer-Assisted Medical Decision Processes
— This paper addresses the problem of understanding preservation and reconstruction requirements for computeraided medical decision-making. With an increasing number of computer-...
Sang-Chul Lee, Peter Bajcsy
ICMLA
2007
13 years 10 months ago
A Clustering-Based Approach to Predict Outcome in Cancer Patients
Abstract—The TNM (Tumor, Lymph Node, Metastasis) is a widely used staging system for predicting the outcome of cancer patients. However, the TNM is not accurate in prediction, pa...
Kai Xing, Donald Henson, Dechang Chen, Li Sheng
ICMLA
2007
13 years 10 months ago
Estimating class probabilities in random forests
For both single probability estimation trees (PETs) and ensembles of such trees, commonly employed class probability estimates correct the observed relative class frequencies in e...
Henrik Boström
ICMLA
2007
13 years 10 months ago
Automatic medical coding of patient records via weighted ridge regression
In this paper, we apply weighted ridge regression to tackle the highly unbalanced data issue in automatic largescale ICD-9 coding of medical patient records. Since most of the ICD...
Jian-Wu Xu, Shipeng Yu, Jinbo Bi, Lucian Vlad Lita...
ICMLA
2007
13 years 10 months ago
Improving gene expression programming performance by using differential evolution
Gene Expression Programming (GEP) is an evolutionary algorithm that incorporates both the idea of a simple, linear chromosome of ï¬xed length used in Genetic Algorithms (GAs) and...
Qiongyun Zhang, Chi Zhou, Weimin Xiao, Peter C. Ne...
ICMLA
2007
13 years 10 months ago
Uncertainty optimization for robust dynamic optical flow estimation
We develop an optical flow estimation framework that focuses on motion estimation over time formulated in a Dynamic Bayesian Network. It realizes a spatiotemporal integration of ...
Volker Willert, Marc Toussaint, Julian Eggert, Edg...