An Intelligent Method for Detecting the Rate of Poverty Level with Reference to Tuberculosis
Sumit Das1, Manas Kumar Sanyal2, Dipansu Mondal3, Debamoy Datta4

1Sumit Das, Assistant Professor, IT, JIS College of Engineering, currently pursuing PhD degree program in AI and Soft Computing in University of Kalyaniy, India.
2Dr. Manas Kumar Sanyal, Professor, Business Administration, University of Kalyani is currently working on IT, AI, ML and Soft Computing, India.
3Dipansu Mondal, Programmer, Centre for Information Resource Management, University of Kalyani, India.
4Debamoy Datta, Student, EE, JIS College of Engineering, India.
Manuscript received on January 02, 2020. | Revised Manuscript received on January 15, 2020. | Manuscript published on January 30, 2020. | PP: 299-306 | Volume-8 Issue-5, January 2020. | Retrieval Number: E4845018520/2020©BEIESP | DOI: 10.35940/ijrte.E4845.018520

Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: This paper represents the factors, which is important for the prediction of the population living below the poverty level as defined by world health organization through reverse engineering. The objective of this research work is to analyze how the tuberculosis detection rate can help us to predict the people living below the poverty line. The feed-forward artificial neural network and Support vector machines used for comparison. The Authors provide physical reasons behind the startling results that we obtained. This work used data collected by the World Health Organization. The data collected consisted of 202 observations of 358 variables and out of these vast numbers of variables; we selected only six variables of interest to build the model. After removing the not available rows, we get only 75 observations out of which we use only 57 observations to build our model. Although the error was a bit high, still with only these few observations both artificial neural networks and support vector machines yielded similar results, confirming our hypothesis. This paper also compares two well-known algorithms for variable importance and finally provides a solution to the problem of poverty by fuzzy cognitive maps. Various concepts related to the economy have been used to develop this model and results are astounding, based on the results solution to the present-day problems has been proposed.
Keywords: Fuzzy Cognitive Maps, Support Vector Machines, Artificial Neural Network, Fuzzy Weight, Tuberculosis.
Scope of the Article: Artificial Intelligent Methods, Models, Techniques.