An approach to categorize chest X-ray images using sparse categorical cross entropy

The Coronavirus disease (COVID-19) pandemic is the most recent threat to global health. Reverse transcription-polymerase chain reaction (RT-PCR) testing, computed tomography (CT) scans, and chest X-ray (CXR) images are being used to identify Coronavirus, one of the most serious community viruses of the twenty-first century. Because CT scans and RT-PCR analyses are not available in most health divisions, CXR images are typically the most time-saving and cost-effective tool for physicians in making decisions. Artificial intelligence and machine learning have become increasingly popular because of recent technical advancements. The goal of this project is to combine machine learning, deep learning, and the health-care sector to create a categorization technique for detecting the Coronavirus and other respiratory disorders. The three conditions evaluated in this study were COVID-19, viral Pneumonia, and normal lungs. Using X-ray pictures, this research developed a sparse categorical cross-entropy technique for recognizing all three categories. The proposed model had a training accuracy of 91% and a training loss of 0.63, as well as a validation accuracy of 81% and a validation loss of 0.7108.

The Rate and Pattern of the Spatio-Temporal Expansion of Rangpur City Corporation, Rangpur, Bangladesh

Analyzing the spatio-temporal growth of the built-up areas of any urban place is incredibly much vital for the proper planning and development of the urban areas. The present study emphasizes on determining the rate and pattern of spatio-temporal growth of Rangpur City Corporation (RpCC) for the year of 1989, 2000, 2010, and 2017 through Shannon's Entropy with the help of GIS and remote sensing techniques. The Shannon's Entropy technique was adopted in order to determining the dispersion or compactness in the pattern of the built-up areas in the study area. In the present study, Lands at Operational Land Imager (OLI), Lands at Thematic Mapper (TM) and Lands at Enhanced Thematic Mapper plus (ETM+) satellite images on the year of 1989, 2000, 2010, and 2017 were analyzed for certain interpretations. The changes of the built-up areas in RpCC were identified and determined through supervised classification using ArcMap10.5 software. The study indicated that spatio-temporal growth of the built-up areas have been in RpCC was existed during 1989-2017. The built-up areas increased by 5.89 Sq.km. during 1989 -2000, 32.23 Sq.km. during 2000- 2010 and 18.85 Sq.km. during 2010-2017 and the expansion rate of the built-up areas was 8.02%, 25.64% and 6.01% during 1989-2000, 2000-2010 and 2010-2017 respectively. The relative entropy value of 1989, 2000, 2010 and 2017 was found 0.17, 0.24, 0.47 and 0.53 which interprets that the expansion of the built-up areas was existed in RpCC and the pattern of expansion was dispersed. However, the outcomes of this study will be very helpful to formulate perfect planning and management system regarding the expansion of the built-up areas the built-up areas expansion of RpCC.

A comprehensive evaluation of county economies in the Beijing-Tianjin-Hebei Region based on entropy TOPSIS analysis

Although the economy of a county that is linked to surrounding towns and rural areas constitutes a multiple basic economic unit within China's national economy, it usually exhibits independent characteristics and functions. Consequently, a county's economy plays a critical role in the overall economic development of a country's national economy. We created an evaluation index system based on entropy Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) to carry out a comprehensive evaluation of county economy across the entire Beijing-Tianjin-Hebei region. We found serious imbalances in the development of these counties, with county economies within Beijing and Tianjin being more advanced than those in Hebei Province. Furthermore, there were marked differences between county economies within prefecture-level cities of Hebei Province. The developmental level of counties in cities like Langfang, Tangshan and Chengde was relatively high. Conversely, the level of development of counties in Hengshui, Baoding, Xingtai and Handan was lower. Moreover, there were imbalances among cities in relation to county economic development, especially in Langfang, with smaller differences being found in Hengshui and Qinhuangdao. We analysed and identified the factors influencing differences between counties before providing recommendations.

An Integrated Entropy-TOPSIS Methodology for Evaluating Green Energy Sources

This research aims to select the optimum green energy sources for sustainable planning from a given set of alternatives. The study presents an integrated multi-criteria decision-making analysis—the entropy-technique for order of preference by similarity to ideal solution (TOPSIS)—to evaluate the energy sources: coal, oil, gas, carbon capture; and storage: nuclear fission/power, large hydro, small hydro, wind, solar photovoltaic, concentrating solar, geothermal, and biomass. Information related to energy parameters are always imprecise; thus, to address the impreciseness of eliciting judgments in the preferences of criteria, the entropy method is used. TOPSIS method is then utilized to select the optimum sources. Results show that solar-photovoltaic is the optimum green energy source having the highest score value, and annual generation is the most prioritized criterion. Sensitivity analysis also demonstrates the robustness of the selection methodology.