scholarly journals Design and Implementation of Various Regression Models for Yield Prediction

2020 ◽  
Vol 9 (5) ◽  
pp. 1280-1284
Keyword(s):  
Random Forest ◽  
Predictive Models ◽  
Regression Models ◽  
Tamil Nadu ◽  
Research Work ◽  
Uttar Pradesh ◽  
Yield Prediction ◽  
Indian States ◽  
Design And Implementation ◽  
Yield Value

Agriculture is the backbone of India. In order to support farmers in India, this research is focused on the design of various predictive models that are used to predict the yield value for a specific crop in Indian states. This research work considers Rice, Wheat, and Bajra crops in Tamil-Nadu, Rajasthan, Uttar Pradesh states respectively. The various regression models such as Linear, Multiple, C4.5 and Random Forest are considered in this work. R squared value is used to evaluate the performance of the regression models. The result of this work shows that Random Forest model is better in performance.

scholarly journals Evolution of COVID-19 Pandemic in India

2020 ◽  
Author(s):  
Ali Asad ◽  
Siddharth Srivastava ◽  
Mahendra K. Verma
Keyword(s):  
Power Law ◽  
Mathematical Analysis ◽  
Predictive Models ◽  
Growth Pattern ◽  
Tamil Nadu ◽  
Linear Growth ◽  
Uttar Pradesh ◽  
Indian States ◽  
Effective Governance ◽  
Second Wave

AbstractA mathematical analysis of patterns for the evolution of COVID-19 cases is key to the development of reliable and robust predictive models potentially leading to efficient and effective governance against COVID-19. Towards this objective, we study and analyze the temporal growth pattern of COVID-19 infection and death counts in various states of India. Our analysis up to June 16, 2020 shows that several states (namely Maharashtra, Tamil Nadu, Delhi, Uttar Pradesh) have reached t2 power-law growth, while some others like Gujarat, Rajasthan, and Madhya Pradesh have reached linear growth. Karnataka and Kerala are exhibiting a second wave. In addition, we report that the death counts exhibit similar behaviour as the infection counts. These observations indicate that Indian states are far from flattening their epidemic curves.

scholarly journals Incidence of treatment for postabortion complications in India, 2015

2020 ◽  
Vol 5 (7) ◽  
pp. e002372
Author(s):  
Susheela Singh ◽  
Rubina Hussain ◽  
Chander Shekhar ◽  
Rajib Acharya ◽  
Melissa Stillman ◽  
...  
Keyword(s):  
Tamil Nadu ◽  
Large Scale ◽  
National Level ◽  
Uttar Pradesh ◽  
Primary Source ◽  
Reproductive Age ◽  
Legal Abortion ◽  
Indian States ◽  
Medication Abortion ◽  
Postabortion Care

Abortion has been legal under broad criteria in India since 1971. However, access to legal abortion services remains poor. In the past decade, medication abortion (MA) has become widely available in India and use of this method outside of health facilities accounts for over 70% of all abortions. Morbidity from unsafe abortion remains an important health issue. The informal providers who are the primary source of MA may have poor knowledge of the method and may offer inadequate or inaccurate advice on use of the method. Misuse of the method can result in women seeking treatment for true complications as well as during the normal processes of MA. An estimated 5% of all abortions are done using highly unsafe methods and performed by unskilled providers, also contributing to abortion morbidity. This paper provides new representative abortion-related morbidity measures at the national and subnational levels from a large-scale 2015 study of six Indian states—Assam, Bihar, Gujarat, Madhya Pradesh, Tamil Nadu and Uttar Pradesh. The outcomes include the number and treatment rates of women with complications resulting from induced abortion and the type of complications. The total number of women treated for abortion complications at the national level is 5.2 million, and the rate is 15.7 per 1000 women of reproductive age per year. In all six study states, a high proportion of all women receiving postabortion care were admitted with incomplete abortion from use of MA—ranging from 33% in Tamil Nadu to 65% in Assam. The paper fills an important gap by providing new evidence that can inform policy-makers and health planners at all levels and lead to improvements in the provision of postabortion care and legal abortion services—improvements that would greatly reduce abortion-related morbidity and its costs to Indian women, their families and the healthcare system.

scholarly journals Weather prediction using random forest machine learning model

2021 ◽  
Vol 22 (2) ◽  
pp. 1208
Author(s):  
R. Meenal ◽  
Prawin Angel Michael ◽  
D. Pamela ◽  
E. Rajasekaran
Keyword(s):  
Machine Learning ◽  
Wind Speed ◽  
Random Forest ◽  
Solar Radiation ◽  
Regression Models ◽  
Tamil Nadu ◽  
Weather Prediction ◽  
Learning Model ◽  
Statistical Regression ◽  
Machine Learning Model

The complex numerical climate models pose a big challenge for scientists in weather predictions, especially for tropical system. This paper is focused on presenting the importance of weather prediction using machine learning (ML) technique. Recently many researchers recommended that the machine learning models can produce sensible weather predictions in spite of having no precise knowledge of atmospheric physics. In this work, global solar radiation (GSR) in MJ/m2/day and wind speed in m/s is predicted for Tamil Nadu, India using a random forest ML model. The random forest ML model is validated with measured wind and solar radiation data collected from IMD, Pune. The prediction results based on the random forest ML model are compared with statistical regression models and SVM ML model. Overall, random forest machine learning model has minimum error values of 0.750 MSE and R2 score of 0.97. Compared to regression models and SVM ML model, the prediction results of random forest ML model are more accurate. Thus, this study neglects the need for an expensive measuring instrument in all potential locations to acquire the solar radiation and wind speed data.

scholarly journals Crop Yield Prediction using XG Boost Algorithm

2020 ◽  
Vol 8 (5) ◽  
pp. 3516-3520
Keyword(s):  
Crop Yield ◽  
Tamil Nadu ◽  
Crop Yields ◽  
Absolute Error ◽  
Climatic Conditions ◽  
Support Vector ◽  
Yield Prediction ◽  
Indian States ◽  
South Indian ◽  
Proposed Model

The main objective of this research is to predict crop yields based on cultivation area, Rainfall and maximum and minimum temperature data. It will help our Indian farmers to predict crop yielding according to the environment conditions. Nowadays, Machine learning based crop yield prediction is very popular than the traditional models because of its accuracy. In this paper, linear regression, Support Vector Regression, Decision Tree and Random forest is compared with XG Boost algorithm. The above mentioned algorithms are compared based on R2 , Minimum Square Error and Minimum Absolute Error. The dataset is prepared from the data.gov.in site for the year from 2000 to 2014. The data for 4 south Indian states Andhra Pradesh, Karnataka, Tamil Nadu and Kerala data alone is taken since all these states has same climatic conditions. The proposed model in this paper based on XG Boost is showing much better results than other models. In XG Boost R2 is 0.9391 which is the best when compared with other models.

Inclusiveness and the Progress of Indian States: Evidence from Inclusive Development Index Between 2011 and 2018

2021 ◽  
pp. 097370302110086
Author(s):  
Suresh Chand Aggarwal
Keyword(s):  
Principal Component Analysis ◽  
Tamil Nadu ◽  
Uttar Pradesh ◽  
Principal Component ◽  
Inclusive Development ◽  
Indian States ◽  
Development Index ◽  
Policy Initiatives ◽  
Low Performance ◽  
Simple Average

This article examines the progress of the Indian states in inclusiveness between 2011 and 2018, based on the “Inclusive Development Index” (IDI), which includes many important aspects of the economy and people. The study has followed the broad guidelines of the Organisation for Economic Co-operation and Development—OECD (2008) to construct IDI, and it is based on two pillars of growth—the process and the outcome. The index includes 26 sub-pillars represented by 104 indicators. The weights of the indicators are obtained separately for 2011 and 2018 by applying the principal component analysis at the indicator level, and then a simple average has been computed at the sub-pillar and pillar levels to obtain the composite IDI for the 19 major Indian states. The composite IDI shows that in 2018, while the most inclusive states are Himachal Pradesh, Tamil Nadu, Maharashtra, Karnataka, Gujarat, Chhattisgarh and Kerala, the least inclusive are the states of Rajasthan, Uttar Pradesh (UP), Madhya Pradesh (MP), Assam, Jharkhand and Bihar. The performance of the states, however, varies among pillars, sub-pillars and indicators in both 2011 and 2018. The study may help the states to identify their spheres of “low” performance and learn from their “front-runner” peers, so as to take the necessary policy initiatives.

scholarly journals Does Causation hold for Panel Data in between SDP and NTR among Indian States?

2014 ◽  
Vol 10 (1) ◽  
pp. 3-15
Author(s):  
Alok Kumar Pandey
Keyword(s):  
Growth Rate ◽  
Panel Data ◽  
Tamil Nadu ◽  
Panel Cointegration ◽  
Uttar Pradesh ◽  
Domestic Product ◽  
Tax Revenue ◽  
Federal System ◽  
Indian States ◽  
Indian Economy

Inadequate revenue sources, uncontrolled growth of current expenditures and failure of central transfers to grow as fast as the states ‘own revenues’ have been the major sources of fiscal imbalance at states level. The existence of nexus in between NTR and SDP can be examined in several ways like growth rates relating to SDP and NTR, proportion of NTR to SDP, several policies relating to accelerate SDP and NTR, etc. So far as inter-state non-tax revenue and state domestic product in India is concerned, limited studies have been done. Present study tries to explore the stationarity and cointigration between Non Tax Revenue and State Domestic Product of twenty major states of Indian federal system in panel data structure for the period 1980-81 to 2011-12.The objectives of the study are: to test the panel stationary of Domestic Production and Non Tax Revenue of the major states of the Indian federal system for the period 1980-81 to 2011-12 in terms of total and growth rate and to test the panel cointegration in between SDP and NTR for the Indian federal system of twenty major states state for the period 1980-81 to 2011-12 in terms of total and growth rate. In the present study data has been taken from Handbook of Statistics on Indian Economy and State Finance for twenty major states; Andhra Pradesh, Assam, Bihar, Gujarat, Haryana, Himachal Pradesh, Jammu & Kashmir, Karnataka, Kerala, Madhya Pradesh, Maharashtra, Manipur, Nagaland, Orissa, Punjab, Rajasthan, Tamil Nadu, Tripura and Uttar Pradesh (Handbook of Statistics on Indian Economy 2011-12).In the present study, LLC (2002) and IPS (2003) tests of stationarity have been used. Kao (1999) test of panel cointegration shows that the SDP and NTR and NTR and SDP for the twenty states for the period under study are cointegrable. The results of the study suggest that state domestic product of the states are causing the non tax revenue of the states  and  the non tax revenue of the states  are also causing state domestic product of the states for Indian federal system.

scholarly journals Temporal evolution of COVID-19 in the states of India using SIQR Model

2020 ◽  
Author(s):  
Alok Tiwari
Keyword(s):  
Tamil Nadu ◽  
Temporal Evolution ◽  
Reproduction Number ◽  
Uttar Pradesh ◽  
National Average ◽  
Indian Government ◽  
Indian States ◽  
Steady Rate ◽  
Entire Nation ◽  
Second Wave

ABSTRACTCOVID 19 entered during the last week of April 2020 in India has caused 3,546 deaths with 1,13,321 number of reported cases. Indian government has taken many proactive steps, including strict lockdown of the entire nation for more than 50 days, identification of hotspots, app-based tracking of citizens to track infected. This paper investigated the evolution of COVID 19 in five states of India (Maharashtra, UP, Gujrat, Tamil Nadu, and Delhi) from 1st April 2020 to 20th May 2020. Variation of doubling rate and reproduction number (from SIQR) with time is used to analyse the performance of the majorly affected Indian states. It has been determined that Uttar Pradesh is one of the best performers among five states with the doubling rate crossing 18 days as of 20th May. Tamil Nadu has witnessed the second wave of infections during the second week of May. Maharashtra is continuously improving at a steady rate with its doubling rate reaching to 12.67 days. Also these two states are performing below the national average in terms of infection doubling rate. Gujrat and Delhi have reported the doubling rate of 16.42 days and 15.49 days respectively. Comparison of these states has also been performed based on time-dependent reproduction number. Recovery rate of India has reached to 40 % as the day paper is written.

scholarly journals Principles and Practices of Making Agriculture Sustainable: Crop Yield prediction using Random Forest

2020 ◽  
Vol 21 (4) ◽  
pp. 591-599
Author(s):  
Syed Muzamil Basha ◽  
Dharmendra Singh Rajput ◽  
Janet J ◽  
Rama Subbareddy Somula ◽  
Sajeev Ram
Keyword(s):  
Random Forest ◽  
Best Management Practices ◽  
Food Production ◽  
Management Practices ◽  
Research Work ◽  
Absolute Error ◽  
High Rate ◽  
Yield Prediction ◽  
Best Management ◽  
Adequate Food

Agriculture has advanced tremendously over the last 100 years. In fact it is been keeping up with food production at a very high rate. In fact, some scientists feel that agriculture already produces enough food to feed the world, but of course there are issues and problems with food availability, agricultural production practices, preservation and transportation, and probably more that one can think of that hinder many people in this world from getting adequate food. The basic challenge is to provide food for the needy people. This need can be fulfilled with the help of the farmers taking responsibility in increasing the food production by 50% by the year 2050. The objective of the present work is to increase this food production, protecting the environmentwith managing natural resources. Mainly focusing on water, nutrients and other inputs to produce foods without degrading the environment. The Goal is to develop the social, environmental, and the economic aspects of possible solutions to minimize the agricultural footprint, and become more sustainable. The dataset considered in our experiment is used in yield prediction based on historic yield and weather information. Implemented both the versions of Thomson model and compared the result with segmentation model, Random Forest (RF). Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) are used as evaluation metrics in estimating the performance of models implements and stated that Random forest algorithm is providing 0.07 (RMSE). The outcome of the present research work helps farmers in adopting best management practices and trying to give them the economical and technical support in making easier for them to adopt best management practices.

scholarly journals Prediction of Diabetics using Machine Learning

2020 ◽  
Vol 8 (5) ◽  
pp. 1119-1124
Keyword(s):  
Random Forest ◽  
Tamil Nadu ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Indian States ◽  
Data Set ◽  
Mean Values ◽  
Bayes Algorithm ◽  
Independent Features ◽  
Individual Trees

Around 50.9 Million People in India suffer from diabetics and Tamil Nadu stands second in the list of Indian states. The main objective of this paper is to develop prediction modeling of the given medical data of patients with and without diabetics. Through this paper, we aim to create hybrid models that can be easily used by doctors to treat patients with diabetics. Naïve Bayes and Random forest algorithms are used to predict whether a person having diabetics or not, by keeping his health conditions in mind. Thus this process enables doctors to easily group, classify and categorize the disease type accordingly treatment can be given to them. We split the Dataset into 1) Training set and 2) Testing Set and perform analysis on them. The Pima Indian dataset was used to study and analyze the data, alongside with data mining techniques. It is the data obtained from the National Institute for Diabetics patients which contains n number of medical predictor variables and one target variable. Initially, we replace the null values that are there in the dataset with the mean values of the respective columns. We then split the dataset into different ways to perform analysis on them: 85/15, 80/20, 70/30, 60/40. After procuring the data set, we apply Naïve Bayes and Random Forest algorithms on this. The Naïve Bayes algorithm is used here to find the probability of the independent features/columns. The data set is given as an input and the prediction takes place according to the NB Model. The Random Forest algorithm is used here in order to perform feature selection. It takes n inputs from the dataset and builds numerous uncorrelated decision trees during the time of training. It then displays the class that is the mode of all of the class outputs by individual trees.

scholarly journals Preliminary Analysis of Excess Mortality in India During the Covid-19 Pandemic (Update August 4, 2021).

2021 ◽  
Author(s):  
Christopher T Leffler ◽  
Joseph D. Lykins ◽  
Edward Yang
Keyword(s):  
Tamil Nadu ◽  
Andhra Pradesh ◽  
Excess Mortality ◽  
West Bengal ◽  
Uttar Pradesh ◽  
Madhya Pradesh ◽  
Systems Science ◽  
Mortality Data ◽  
Indian States ◽  
All Cause Mortality

Background. As both testing for SARS Cov-2 and death registrations are incomplete or not yet available in many countries, the full impact of the Covid-19 pandemic is currently unknown in many world regions. Methods. We studied the Covid-19 and all-cause mortality in 18 Indian states (combined population of 1.26 billion) with available all-cause mortality data during the pandemic for the entire state or for large cities: Gujarat, Karnataka, Kerala, Maharashtra, Tamil Nadu, West Bengal, Delhi, Madhya Pradesh, Andhra Pradesh, Telangana, Assam, Bihar, Odisha, Haryana, Rajasthan, Himachal Pradesh, Punjab, and Uttar Pradesh. Excess mortality was calculated by comparison with available data from years 2015-2019. The known Covid-19 deaths reported by the Johns Hopkins University Center for Systems Science and Engineering for a state were assumed to be accurate, unless excess mortality data suggested a higher toll during the pandemic. Data from Uttar Pradesh were not included in the final model due to anomalies. Results. In several regions, fewer deaths were registered in 2020 than expected. The excess mortality in Mumbai (in Maharashtra) in 2020 was 137.0 / 100K. Areas in Tamil Nadu, Kolkata (in West Bengal), Delhi, Madhya Pradesh, Karnataka, Haryana, and Andhra Pradesh saw spikes in mortality in the spring of 2021. Conclusions. The pandemic-related mortality through June 30, 2021 in 17 Indian states was estimated to be 132.9 to 194.4 per 100,000 population. If these rates apply to India as a whole, then between 1.80 to 2.63 million people may have perished in India as a result of the Covid-19 pandemic by June 30, 2021. This per-capita mortality rate is similar to that in the United States and many other regions.

Sign in / Sign up

Export Citation Format

Share Document