Knowledge Extraction from Artificial Neural Networks and Applications

Application of neural networks is investigated for the prediction of avalanches on ChowkibalTangdhar road axis in Jammu and Kashmir. The networks are developed and trained monthwise using the past snow and weather parameters recorded at the Stage-II Observatory on the axis to generate an assessment of avalanche and non-avalanche activities. Two approaches have been considered for training the network. In the first approach, only avalanche activities observed in the axis were taken for training, and in the second approach, along with the observed activities, the opinion of expert forecasters were also considered. The performance of the networks varies from 67 to 82 per cent for correct predictions. Winter data for [2001][2002] has been used to validate the network performance.

show abstract

“…Neural network utilises mathematical expression and the nodes are valued with numerical weights [11][12][13] .…”

Section: Methodsmentioning

confidence: 99%

Application of Neural Networks for Avalanche Forecasting

Pant

Ganju

2006

DSJ

View full text Add to dashboard Cite

show abstract

“…Distances between weight vectors are often analyzed in order to give an objective border between clusters. The U-matrix (unified distance matrix) representation 29,30 is one of the well-known criteria for this purpose, yet the U-matrix we applied to this problem did not give a clear border (data not shown). We, thus, employed another approach to get proper clusters.…”

Section: Constitution Of Sommentioning

confidence: 99%

“…One reasonable method to ensure the reliability of clustering is to provide meaningful borders among clusters based on distances between weight vectors of neurons. The U-matrix method 29,30 is one of them. Another approach to the classification is to employ known families of training data as a label of each neuron.…”

Section: Representation Of Gpcrmentioning

confidence: 99%

Alignment-Free Classification of G-Protein-Coupled Receptors Using Self-Organizing Maps

Otaki

Mori

Itoh

et al. 2006

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Proteins are classified mainly on the basis of alignments of amino acid sequences. Drug discovery processes based on pharmacologically important proteins such as G-protein-coupled receptors (GPCRs) may be facilitated if more information is extracted directly from the primary sequences. Here, we investigate an alignment-free approach to protein classification using self-organizing maps (SOMs), a kind of artificial neural network, which needs only primary sequences of proteins and determines their relative locations in a two-dimensional lattice of neurons through an adaptive process. We first showed that a set of 1397 aligned samples of Class A GPCRs can be classified by our SOM program into 15 conventional categories with 99.2% accuracy. Similarly, a nonaligned raw sequence data set of 4116 samples was categorized into 15 conventional families with 97.8% accuracy in a cross-validation test. Orphan GPCRs were also classified appropriately using the result of the SOM learning. A supposedly diverse family of olfactory receptors formed the most distinctive cluster in the map, whereas amine and peptide families exhibited diffuse distributions. A feature of this kind in the map can be interpreted to reflect hierarchical family composition. Interestingly, some orphan receptors that were categorized as olfactory were somatosensory chemoreceptors. These results suggest the applicability and potential of the SOM program to classification prediction and knowledge discovery from protein sequences.

show abstract

“…Each cluster can then be characterized by using a list of the most important variables and their descriptive statistics. Another frequently employed method is to form characterizing rules [19,18] to describe the values in each cluster:…”

Section: Cluster Characterizationmentioning

confidence: 99%

“…To form the characterizing rules -in effect to select the low and high limits of the range -one can use statistics of the values in the clusters [19]. Another approach is to optimize the rules with respect to their significance.…”

Section: Cluster Characterizationmentioning

confidence: 99%

An Automated Report Generation Tool for the Data Understanding Phase

Vesanto

Hollmén

2002

Hybrid Information Systems

View full text Add to dashboard Cite

To successfully prepare and model data, the data miner needs to be aware of the properties of the data manifold. In this chapter, the outline of a tool for automatically generating data survey reports for this purpose is described. Such a report is used as a starting point for data understanding, acts as documentation of the data, and can easily be redone if necessary. The main focus is on describing the cluster structure and the contents of the clusters. The described system combines linguistic descriptions (rules) and statistical measures with visualizations. Whereas rules and mathematical measures give quantitative information, the visualizations give qualitative information on the data sets, and help the user to form a mental model of the data based on the suggested rules and other characterizations.

show abstract

Knowledge Extraction from Artificial Neural Networks and Applications

Cited by 11 publications

References 4 publications

Application of Neural Networks for Avalanche Forecasting

Application of Neural Networks for Avalanche Forecasting

Alignment-Free Classification of G-Protein-Coupled Receptors Using Self-Organizing Maps

An Automated Report Generation Tool for the Data Understanding Phase

Contact Info

Product

Resources

About