scispace - formally typeset
Search or ask a question
Institution

Kongu Engineering College

About: Kongu Engineering College is a based out in . It is known for research contribution in the topics: Cluster analysis & Control theory. The organization has 2001 authors who have published 1978 publications receiving 16923 citations.


Papers
More filters
Journal ArticleDOI
TL;DR: In this paper, different contourlet frame based feature extraction techniques for remote sensing images are proposed Principal component analysis (PCA) method is used to reduce the number of features Gaussian Kernel fuzzy C-means classifiers uses these features to improve the classification accuracy Accuracy assessment based on field visit data and cluster validity measures are used to measure the accuracy of the classified data.
Abstract: Conventional classification algorithms makes the use of only multispectral information in remote sensing image classification Wavelet provides spatial and spectral characteristics of a pixel along with its neighbours and hence this can be utilized for an improved classification The major disadvantage of wavelet transform is the non availability of spatial frequency features in its directional components The contourlet transform based laplacian pyramid followed by directional filter banks is an efficient way of extracting features in the directional components In this paper different contourlet frame based feature extraction techniques for remote sensing images are proposed Principal component analysis (PCA) method is used to reduce the number of features Gaussian Kernel fuzzy C-means classifiers uses these features to improve the classification accuracy Accuracy assessment based on field visit data and cluster validity measures are used to measure the accuracy of the classified data The experimental result shows that the overall accuracy is improved to 173 % (for LISS-II), 181 % (for LISS-III) and 195 % (for LISS-IV) and the kappa coefficient is improved to 0933 (for LISS-II), 00103 (for LISS-III) and 00214 (for LISS-IV) and also the cluster validity measures gives better results when compared to existing method

8 citations

Proceedings ArticleDOI
15 Mar 2019
TL;DR: Jupyter Notebook is the data mining tool used to predict the crop production and precipitation, temperature, reference crop, evapotranspiration, area, production and yield for the season from January to December for the years 2000 to 2018.
Abstract: Agriculture is an important application in India. The modern technologies can change the situation of farmers and descision making in agricultural field in a better way. Python is used as a front end for analysing the agricultural data set. Jupyter Notebook is the data mining tool used to predict the crop production. The parameter includes in the dataset are precipitation, temperature, reference crop, evapotranspiration, area, production and yield for the season from January to December for the years 2000 to 2018. The data mining techniques like K-Means Clustering, KNN, SVM, and Bayesian network algorithm where high accuracy can be achieved.

8 citations

Proceedings ArticleDOI
01 Jan 2017
TL;DR: An algorithm named as DSOS with Local search (DSOSLS), in DSOSLS the local search technique has been applied to the solution which is obtained from the DSOS algorithm, and the experimental analysis shows that the DS OSLS algorithm reduces the make span at a higher level.
Abstract: In Cloud computing applications, data and computing resources are provided as a service to the clients over the Internet. Task scheduling plays a vital role in assigning the tasks to different virtual machines in cloud computing. The ultimate goal of cloud task scheduling is to curtail the make span. Discrete Symbiotic Organism Search (DSOS) is a meta heuristic algorithm which provides optimal solution to cloud scheduling problems. Local search procedure will move from one solution to another improved solution. In this paper we propose an algorithm named as DSOS with Local search (DSOSLS). In DSOSLS the local search technique has been applied to the solution which is obtained from the DSOS algorithm. DSOSLS algorithm moves the task from the high make span virtual machine to low make span virtual machine. The experimental analysis shows that the DSOSLS algorithm reduces the make span at a higher level.

8 citations

Proceedings Article
30 Mar 2012
TL;DR: In this article, the free vibration analysis of hybrid-composite beams has been carried out on the hybrid composite beams having different fiber orientation angles (θ) from 0° to 90° and aspect ratios (L/h) from 45 to 120 with different boundary conditions by using numerical analysis software.
Abstract: This study deals with the free vibration analysis of hybrid-composite beams The combinations for hybrid composites used in the analysis are Carbon/epoxy and Glass/epoxy The Hybrid-Composite beams have superior material properties than ordinary composites (having fiber and matrix) due to synergistic effect The free vibration analysis has been carried out on the hybrid composite beams having different fiber orientation angles (θ) from 0° to 90° and aspect ratios (L/h) from 45 to 120 with different boundary conditions by using numerical analysis software (FEA-ANSYS 120) In the present work the effects of fiber orientation angles and aspect ratios on natural frequencies and mode shapes of the hybrid composite beams are investigated

8 citations

Journal ArticleDOI
TL;DR: For detecting and classifying breast cancer in breast cytology videos, deep learning frameworks are suggested and the suggested system will outperform CNN and DenseNet in the diagnosis and classification of breast tumors from histological photographs.

8 citations


Authors
Network Information
Related Institutions (5)
Anna University
19.9K papers, 312.6K citations

89% related

VIT University
24.4K papers, 261.8K citations

89% related

National Institute of Technology, Rourkela
10.7K papers, 150.1K citations

88% related

SRM University
11.7K papers, 103.7K citations

88% related

Thapar University
8.5K papers, 130.3K citations

87% related

Performance
Metrics
No. of papers from the Institution in previous years
YearPapers
202221
2021572
2020234
2019121
2018143
2017136