A Comparative Study on Air Quality Analysis Through DNN by SVM, K - Means and Naive Bayes Algorithms

  IJCTT-book-cover
 
International Journal of Computer Trends and Technology (IJCTT)          
 
© 2019 by IJCTT Journal
Volume-67 Issue-11
Year of Publication : 2019
Authors : R.Amulraju, D. Ashok Kumar, T.Vithyaa
DOI :  10.14445/22312803/IJCTT-V67I11P107

MLA

MLA Style:R.Amulraju, D. Ashok Kumar, T.Vithyaa "A Comparative Study on Air Quality Analysis Through DNN by SVM, K - Means and Naive Bayes Algorithms," International Journal of Computer Trends and Technology 67.11 (2019):42-48.

APA Style R.Amulraju, D. Ashok Kumar, T.Vithyaa. A Comparative Study on Air Quality Analysis Through DNN by SVM, K - Means and Naive Bayes Algorithms  International Journal of Computer Trends and Technology, 67(11),42-48.

Abstract
Air Quality may be a major concern round the world. It’s full of a large vary of natural and human influences. The foremost necessary of the natural influences area unit geologic, hydrological and environmental condition, since these have an effect on the standard of Air. To invoke a deep neural network (DNN)-based approach (entitled Deep Air), that consists of a spatial transformation part and a deep distributed fusion network. Considering air pollutants’ spatial correlations, the previous part converts the spatial thin air quality knowledge into a homogenous input to simulate the waste product sources. The latter network adopts a neural distributed design to fuse heterogeneous urban knowledge for at the same time capturing the factors touching air quality, e.g. environmental condition. To Deployed Deep Air in our pollution Prediction system, providing fine-grained air quality forecast. Additionally we tend to confirm the precise results and analysis of the contaminated contents victimization K-Means cluster, SVM Classifier and Naive Bayes. Comparison the contaminated content results with these three processes the K-Means provides the proper result and determines the precise output with facilitate of the datasets. The collected datasets area unit pre-processed and classified to induce the proper results. Finally the results area unit manipulated in associate graph format, that exposes the ends up in associate correct manner.

Reference
[1] D. W. Wong, L. Yuan, and S. A. Perlin, ?Comparison ofspatialinterpo-lation methods for the estimation of air quality data,?Journalof Exposure Science and Environmental Epidemiology, vol. 14, no. 5,, 2004.
[2] R. G. Baraniuk, ?Compressive sensing, sensing,? IEEE Signal Processing Magazine Magazine, vol. 24, no. 4, 2007.
[3] S. S. Haykin, S. S. Haykin, S. S. Haykin, and S. S. Haykin, Neural networks and learning machines. Pearson Education Upper Saddle River, 2009,
[4] J. Schwartz, ?Lung function and chronic exposure to air pollution: A crosscross-sectional analysis of NHANES II, II,? Environmental Research Research, vol. 50,no. 2, pp. 309 – 321, 1989.
[5] Ping-Wei Soh, Adaptive Deep Learning-Based Air Quality Prediction Model Using the Most Relevant Spatial-Temporal Relations, , vol. 50,no. 2, pp. 309 –321, 1989.
[6] L. G. Chestnut, J. Schwartz, D. A. Savitz, and C. M. Burchfiel, ?Pulmo-nary function and ambient particulate matter: epidemiological evidence from NHANES I, I,? Archives of Environmental Health: An International Journal , vol. 46, no. 3, 1991.
[7] D. K. Jha, M. Sabesan , A. Das, N. Vinithkumar , and R. ?Evaluation of interpolation technique for air quality parameters in port blairblair, india ,? Universal Journal of Environmental Research and TechnologyTechnology, vol. 1, no. 3, 2011.
[8] P. Gupta, S. A. Christopher, J. Wang, R. Gehrig, Y. Lee, and N. Kumar, ?Satellite remote sensing of particulate matter and air quality assessment over global cities, cities,? Atmospheric Environment , vol. 40, no. 30, 2006.
[9] X. Yu, Y. Liu, Y. Zhu, W. Feng, L. Zhang, H. F. Rashvand, and V. O. K. Li, ?Efficient sampling and compressive sensing for urban monitoring vehicular sensor networks, networks,? IET Wireless Sensor Systems , vol. 2, 2012.
[10] L. Li, Y. Zheng, and L. Zhang, ?Demonstration abstract: Pimi air box: a costcost-effective sensor for par ticipatory indoor quality monitoring, monitoring,? in Pro- ceedings of the 13th IEEE International Symposium on Information Processing in Sensor Networks , 2014.
[11] D. Basak, S. Pal, and D. C. Patranabis. "Support vector regression." Neu-ral Information Processing-Letters and Reviews 11, no. 10 2007.
[12]Y. Zheng. "Methodologies for cross-domain data fusion:An overview." IEEE transactions on big data 1, no. 1 2015.
[13] Y. Zheng, X. Yi, M. Li, R. Li, Z. Shan, E. Chang, and T. Li. "Forecasting Fine-Grained Air Quality Based on Big Data." 2015.
[14] N. Cressie and C. K. Wikle, Statistics for Spatio-Temporal Data. Wiley, 2011
[15] Y. Saeys, I. Inza, and P. Larranaga, ?A review of feature selection techniques in bioinformatics,? Bioinformatics, vol. 23, no. 19, pp.2507–2517, 2007.

Keywords
Air Quality, K-means, SVM, Naïve Bayes, Precision, Recall, F-Measure