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.
In the advancing world, it is very crucial to protect our environment. Many incidents of man-made and natural disasters were happening around the world. Forest fires are one such catastrophe for environment. Once the fire inside deep forest starts, it burns and destroys everything and spreads everywhere within the forest. Such forest fires disasters should be curbed in order to protect fauna and flora habitats in the forest. The objective of this work is to design and implement an IoT based system which is self-sustaining and would predict and detect the forest fires and sends the exact location to concerned officials which would help firefighting personnel to extinguish the fire in the location where it starts slowly.
Weather forecasting plays a major role in various fields such as agriculture, transportation etc., It is also essential in prediction of natural disasters like Flood, storm etc., So in order to prevent the damages from such natural disorders, accurate weather prediction is essential. IoT topology is a combination of both hardware and wireless communication network utilized for real-time data analysis. Hence, this proposed topology formulated an IoT based weather monitoring using artificial neural network (ANN) for prediction. The main objective of this designed topology system is monitoring weather parameters such as temperature/humidity/pressure/rainfall etc., IoT is organized to collect data from sensors and is communicated through Wi-Fi network. ANN is tailored for weather prediction. The analysis proves that the proposed architecture shows better efficiency in weather prediction than the conventional methods.
Agriculture the backbone of our nation as well many nations is essential to feed the people and smart farming is the much-needed disruptive technology to help the farmers increase their yield. Airborne vehicles and relays supplement the automation system to monitor the growth of the plants, individually and record the observations to estimate the level of pesticides and herbicides to be applied. However, there are no simulation platforms designed to help these farmers to collect and process the data gathered. The proposed work consists of a sensor fusion framework that will give the user a complete farming scenario which is focused on data gathering with airborne UAV or relay mechanism, line of sight deployment, coverage area, identify sensor placement, and usage of fog computing paradigm as a backend computing support. The paper focuses on providing an evaluation benchmark for energy consumption, system resource usage, packet delivery ratio and transmission delay.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.