One-class document classification via Neural Networks

Authors:
Larry Manevitz;Malik Yousef
Affiliations:
Department of Computer Science, University of Haifa, Haifa, Israel and Department of Experimental Psychology, Institute of Mathematics, Oxford University, Oxford, UK;Department of Computer Science, University of Haifa, Haifa, Israel and Wistar Institute, University of Pennsylvania, Philadelphia, Pennsylvania, USA
Venue:
Neurocomputing
Year:
2007

Citing 19
Cited 11

Learning and Revising User Profiles: The Identification ofInteresting Web Sites

Machine Learning - Special issue on multistrategy learning
Characteristic concept representations

Characteristic concept representations
Inductive learning algorithms and representations for text categorization

Proceedings of the seventh international conference on Information and knowledge management
Supervised versus unsupervised binary-learning by feedforward neural networks

Machine Learning
Information Retrieval

Information Retrieval
Introduction to Modern Information Retrieval

Introduction to Modern Information Retrieval
Predicate Invention and Learning from Positive Examples Only

ECML '98 Proceedings of the 10th European Conference on Machine Learning
Text Categorization with Suport Vector Machines: Learning with Many Relevant Features

ECML '98 Proceedings of the 10th European Conference on Machine Learning
A Comparative Study on Feature Selection in Text Categorization

ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
Learning from Positive Data

ILP '96 Selected Papers from the 6th International Workshop on Inductive Logic Programming
One-class svms for document classification

The Journal of Machine Learning Research
Extreme re-balancing for SVMs: a case study

ACM SIGKDD Explorations Newsletter - Special issue on learning from imbalanced datasets
A web navigation system based on a neural network user-model trained with only positive web documents

Web Intelligence and Agent Systems
Nonlinear Autoassociation Is Not Equivalent to PCA

Neural Computation
The Diabolo Classifier

Neural Computation
A novelty detection approach to classification

IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 1
Syskill & webert: Identifying interesting web sites

AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1
A kernel autoassociator approach to pattern classification

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
A statistical approach to the representation of uncertainty in beliefs using spread of opinions

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans

Minimum spanning tree based one-class classifier

Neurocomputing
One-Class Genetic Programming

EuroGP '09 Proceedings of the 12th European Conference on Genetic Programming
Using duo output neural network to solve binary classification problems

ACS'10 Proceedings of the 10th WSEAS international conference on Applied computer science
Towards one-class pattern recognition in brain activity via neural networks

MICAI'10 Proceedings of the 9th Mexican international conference on Artificial intelligence conference on Advances in soft computing: Part II
Loop-closing: A typicality approach

Robotics and Autonomous Systems
Can a good offense be a good defense? Vulnerability testing of anomaly detectors through an artificial arms race

Applied Soft Computing
DBFS: An effective Density Based Feature Selection scheme for small sample size and high dimensional imbalanced data sets

Data & Knowledge Engineering
Recognition of word collocation habits using frequency rank ratio and inter-term intimacy

Expert Systems with Applications: An International Journal
Diversity measures for one-class classifier ensembles

Neurocomputing
Clustering-based ensembles for one-class classification

Information Sciences: an International Journal
Review: A review of novelty detection

Signal Processing

Quantified Score

Hi-index	0.01

Visualization

Abstract

Automated document retrieval and classification is of central importance in many contexts; our main motivating goal is the efficient classification and retrieval of ''interests'' on the internet when only positive information is available. In this paper, we show how a simple feed-forward neural network can be trained to filter documents under these conditions, and that this method seems to be superior to modified methods (modified to use only positive examples), such as Rocchio, Nearest Neighbor, Naive-Bayes, Distance-based Probability and One-Class SVM algorithms. A novel experimental finding is that retrieval is enhanced substantially in this context by carrying out a certain kind of uniform transformation (''Hadamard'') of the information prior to the training of the network.