Informatics Publishing Limited

V. Britto Prabhu ¹, N. Venkatanathan ², S. Krishna Anand ¹

Affiliations
1 School of Computing, SASTRA University, Thanjavur - 613401, Tamil Nadu, IN
2 School of Electrical and Electronics Engineering, SASTRA University, Thanjavur - 613401, Tamil Nadu, IN

Abstract

By analysing the previous earthquakes in Sumatra region the long term earthquake prediction may help the Government and NGOs for necessary emergency preparedness. In order to predict chaotic behaviour of nature K-Means clustering algorithm is employed over the previous earthquake data for clustering the regions based on the coordinates of the earthquakes occurred places and Laws of Haversine is used further to compute the distance between the main earthquakes and secondary shocks. The 14 years of earthquake data of 8400 samples were collected from various sources. Each cluster results in different radius of the cluster. Based on the laws of Haversine results the data were loaded and analysed. The analysis results show the pattern of earthquakes and its changes. It gives the information about next larger earthquake pattern and place of occurrence.

Keywords

Aftershock, Cluster, Earthquake, Foreshock, Laws of Haversine, Seismic Event

Full Text

   

S. Krishna Anand ¹, T. G. Raman ², S. Subramanian ¹

Affiliations
1 SKCET, Coimbatore, IN
2 Seshasayee Paper & Boards Ltd, IN

Abstract

The ways of maximization of net steam output from Chemical Recovery Boilers has been a puzzle over the years. To lend support to the same, a type 2 fuzzy expert system has been designed which takes into account a large number of parameters. The composition of Black liquor solids ( fuel) is dependent on a large number of factors right from raw materials like wood and bagasse down through chemicals used for Paper manufacture and pulping since it is the source of heat and power for producing paper of quality at high productivity level. The choice of parameters playing a significant role in the same has to be determined. Pruning is carried out by performing sensitivity analysis. It has been observed that Boiler Liquor solids flow, Moisture content in fuel and Gross Calorific value are found to be more sensitive while parameters like flue gas outlet temperature hardly makes an impact in the process. These apart, apportioning of combustion air at three levels does play a part in productivity. The parameters with a larger impact have been grouped together using c-means clustering. It has been observed in the real world that some measurements are being omitted owing to carelessness of the operators. C-Means clustering could deal with missing data The existing system gives emphasis to operator’s experience and specialists expertise. A temporary lack of focus or the absence of a specialist can lead to major consequences. There arises a need for designing a Type 2 Fuzzy logic system to ensure better performance at all times of operation.

Keywords

Fuzzy Expert System, Backpropogation Neural Network, C-Means Clustering, Superheater, Type 2 Fuzzy Logic, Supervisory Learning, Sensitivity Analysis.

Full Text

     

U. Nivedhitha ¹, S. Krishna Anand ¹

Affiliations
1 School of Computing, SASTRA University, Thirumalaisamudram, Thanjavur − 613401, Tamil Nadu, IN

Abstract

Objectives: A wide variety of disasters occur across the globe, prediction of such disaster is the requisite for early precaution and evacuation process. Prediction of earthquake could be achieved using precursors or seismographic data but all such methods can be carried out only by the domain experts (seismologist). Methods: Data mining methods have been used in a wide variety of applications and in various domains. It allows prediction of performance and expected progression which enables derivation of rational decisions. Anticipating earthquake using previous earthquake history data can be achieved using data mining concepts. In this paper, a prediction model is proposed for anticipating earthquakes by applying clustering and association rule mining on earthquake history data. Initially, the data is collected and they are clustered, this clustered data is passed to next phase where frequent patterns are obtained by applying association rule mining, finally by using the obtained pattern, the upcoming earthquakes are predicted by performing rule matching. Findings: This paper describes a predictive model employing significant earthquake data and mining techniques which predicts the fore coming earthquake. Applications: This prediction model can be used to predict various seismic events and also they can be used for making prediction in other fields by employing appropriate dataset.

Keywords

Association Rule Mining, Clustering, Data Mining, Earthquake Prediction, Frequent Pattern.

Full Text

   

L. Jayasurya ¹, S. Krishna Anand ¹

Affiliations
1 School of Computing, SASTRA University, Thanjavur - 613401, Tamil Nadu, IN

Abstract

Objectives: The feature selection is one category of principally used information analysis algorithms on microarray information or any related to high dimensional information. The goal of the feature selection algorithms is to separate out a little set of informative options that best explains experimental variations. This work really investigates the feature selection drawback for microarray information with tiny samples and variant correlation. Most existing algorithms sometimes need expensive machine effort, particularly beneath thousands of cistron (Gene) conditions. Usually citron (Gene) selection methodology searches for associate best or close to best set of genes with relevance a given analysis. Methods: The main objective of this project is to effectively choose the foremost informative options from microarray data, whereas creating the machine expenses reasonable. This can be achieved by proposing Fuzzy Forest using Weighted Gene Correlation Network Analysis (WGCNA) that makes use of interaction between the features (or Genes). Necessary representative features (or Genes) selection measure designated from every enriched feature partition to make the reduced gene area. Findings: Finally, by shaping a correct regression context, the planned methodology are often simply implement to utilize the MapReduce paradigm, that considerably reduces machine load and additionally resulting in lower prediction error rates (OOB) with variable importance compared to different existing approaches. Thus, it is necessary to know the performance of random forest with microarray data and its potential use for gene selection. Applications: Some the major applications of WGCNA based Fuzzy Forest are genomic data analysis (including microarray data), neuroscience, bioinformatics, DNA methylation data analysis (16s rRNA gene sequencing), cancer, yeast genetics analysis, analysis of brain imaging data (functional MRI data analysis).

Keywords

Feature Selection, Fuzzy Forest, MapReduce, Microarray Data, Module Eigen Gene, Random Forest, Rhadoop, WGCNA.

Full Text