International Conference on Artificial Intelligence, 2001
Most of the existing machine learning algorithms are able to extract knowledge from databases tha... more Most of the existing machine learning algorithms are able to extract knowledge from databases that store discrete attributes (features). If the attributes are continuous, the algorithms can be integrated with a discretization algorithm that transforms them into discrete attributes. The paper describes an algorithm, called CAIM (class-attribute interdependence maximization), for discretization of continuous attributes that is designed to work with
In this paper, we introduce a novel system for recognition of partially occluded and rotated imag... more In this paper, we introduce a novel system for recognition of partially occluded and rotated images. The system is based on a hierarchical network of integrate-and-fire spiking neurons with random synaptic connections and a novel organization process. The network generates integrated output sequences that are used for image classification. The proposed network is shown to provide satisfactory predictive performance given that the number of the recognition neurons and synaptic connections are adjusted to the size of the input image. Comparison of synaptic plasticity activity rule (SAPR) and spike timing dependant plasticity rules, which are used to learn connections between the spiking neurons, indicates that the former gives better results and thus the SAPR rule is used. Test results show that the proposed network performs better than a recognition system based on support vector machines.
International Conference on Machine Learning and Applications, 2002
In today's data-centric world many applications rely on data that comes from multitude of dif... more In today's data-centric world many applications rely on data that comes from multitude of different sources. To integrate that data two major operations are performed: finding semantic mapping between data sources, and transforming structure of the data sources. One of the well-established standards for storing and sharing structured and semantically described data is XML. This paper describes system called XMapper,
Page 1. 2 The Knowledge Discovery Process In this Chapter, we describe the knowledge discovery pr... more Page 1. 2 The Knowledge Discovery Process In this Chapter, we describe the knowledge discovery process, present some models, and explain why and how these could be used for a successful data mining project. 1. Introduction ...
IEEE Transactions on Knowledge and Data Engineering, 2004
... The averaged accuracy of rules generated by the C5.0 algorithm shows that the best results ar... more ... The averaged accuracy of rules generated by the C5.0 algorithm shows that the best results are achieved ... The second best results were achieved by discretizing data using the IEM algorithm and C5.0 with its built-in discretization. ...
Databases and data warehouses provide efficient data retrieval and summarization capabilities, wh... more Databases and data warehouses provide efficient data retrieval and summarization capabilities, which are necessary to prepare and select data for the subsequent steps of the knowledge discovery process. Therefore, prior to presenting data mining methods, we provide an overview of data storage and retrieval technologies.
2007 1st International Conference on Bioinformatics and Biomedical Engineering, 2007
Knowledge of structural classes is useful in understanding folding patterns in proteins. Numerous... more Knowledge of structural classes is useful in understanding folding patterns in proteins. Numerous structural class prediction methods were proposed in the past. Although virtually all state-of-the-art classifiers were already tried, many of these methods use very simple protein sequence representation that often includes amino acid (AA) composition. To this end, we propose a novel sequence representation, which is based on
International Conference on Artificial Intelligence, 2001
Most of the existing machine learning algorithms are able to extract knowledge from databases tha... more Most of the existing machine learning algorithms are able to extract knowledge from databases that store discrete attributes (features). If the attributes are continuous, the algorithms can be integrated with a discretization algorithm that transforms them into discrete attributes. The paper describes an algorithm, called CAIM (class-attribute interdependence maximization), for discretization of continuous attributes that is designed to work with
In this paper, we introduce a novel system for recognition of partially occluded and rotated imag... more In this paper, we introduce a novel system for recognition of partially occluded and rotated images. The system is based on a hierarchical network of integrate-and-fire spiking neurons with random synaptic connections and a novel organization process. The network generates integrated output sequences that are used for image classification. The proposed network is shown to provide satisfactory predictive performance given that the number of the recognition neurons and synaptic connections are adjusted to the size of the input image. Comparison of synaptic plasticity activity rule (SAPR) and spike timing dependant plasticity rules, which are used to learn connections between the spiking neurons, indicates that the former gives better results and thus the SAPR rule is used. Test results show that the proposed network performs better than a recognition system based on support vector machines.
International Conference on Machine Learning and Applications, 2002
In today's data-centric world many applications rely on data that comes from multitude of dif... more In today's data-centric world many applications rely on data that comes from multitude of different sources. To integrate that data two major operations are performed: finding semantic mapping between data sources, and transforming structure of the data sources. One of the well-established standards for storing and sharing structured and semantically described data is XML. This paper describes system called XMapper,
Page 1. 2 The Knowledge Discovery Process In this Chapter, we describe the knowledge discovery pr... more Page 1. 2 The Knowledge Discovery Process In this Chapter, we describe the knowledge discovery process, present some models, and explain why and how these could be used for a successful data mining project. 1. Introduction ...
IEEE Transactions on Knowledge and Data Engineering, 2004
... The averaged accuracy of rules generated by the C5.0 algorithm shows that the best results ar... more ... The averaged accuracy of rules generated by the C5.0 algorithm shows that the best results are achieved ... The second best results were achieved by discretizing data using the IEM algorithm and C5.0 with its built-in discretization. ...
Databases and data warehouses provide efficient data retrieval and summarization capabilities, wh... more Databases and data warehouses provide efficient data retrieval and summarization capabilities, which are necessary to prepare and select data for the subsequent steps of the knowledge discovery process. Therefore, prior to presenting data mining methods, we provide an overview of data storage and retrieval technologies.
2007 1st International Conference on Bioinformatics and Biomedical Engineering, 2007
Knowledge of structural classes is useful in understanding folding patterns in proteins. Numerous... more Knowledge of structural classes is useful in understanding folding patterns in proteins. Numerous structural class prediction methods were proposed in the past. Although virtually all state-of-the-art classifiers were already tried, many of these methods use very simple protein sequence representation that often includes amino acid (AA) composition. To this end, we propose a novel sequence representation, which is based on
Uploads
Papers by Lukasz Kurgan