3 SYSTEM DEVELOPMENTThis system has been developed using


This system has been developed using WinPython which includes the packages such as: NumPy, SciPy, Pandas, Theano , Sklearn, Matplotlib and OpenCV. The overview of the algorithm for the system is as given below. Then the temperature class together with Max and Min are used to predict the suitable crop. Algorithm explains the functioning of the entire recommendation system.

Prediction of crop production using regression model and ANN: Recently, Researchers have developed several forecasting and prediction models of various crop yields in relation to different parameters as influencing factors by applications of artificial neural networks and by combining ANN and statistical techniques such as linear regression technique.

In this section, a number of related works dealing with the applications of neural network models, comparison with linear regression techniques and some combined models for the prediction and forecasting of crop yields has been reviewed. Since, the performance of a particular technique in comparison to other techniques, depends on a number of factors like the volume of the data, selection of model or technique, the methods of validation of results, the measure used for comparison and whether significant difference exists in the results etc.

Get quality help now
Bella Hamilton
Verified writer

Proficient in: Data Analysis

5 (234)

“ Very organized ,I enjoyed and Loved every bit of our professional interaction ”

+84 relevant experts are online
Hire writer

, therefore, attempt has been made to carry out the review on these points. The ANNs have largely impressed the agricultural researchers, as they are able to overcome the difficulties to many extents of traditional statistical approaches.

Statistical models that can be expressed in neural network form are regression, discriminant, density estimation and graphical interaction models such as simple linear regression, projection pursuit regression, polynomial regression, non-parametric regression, logistic regression, linear discriminant functions, classification trees, finite mixture models, kernel regression and smoothing splines compared several methods for predicting crop yield based on soil properties.

Get to Know The Price Estimate For Your Paper
Number of pages
Email Invalid email

By clicking “Check Writers’ Offers”, you agree to our terms of service and privacy policy. We’ll occasionally send you promo and account related email

"You must agree to out terms of services and privacy policy"
Write my paper

You won’t be charged yet!

3.1. System design:

Figure.3.1.1. Proposed System Design

There is no existing system which recommends crops based on multiple factors such as Nitrogen, Phosphorus and Potassium nutrients in soil and weather components which include temperature and rainfall. The proposed system suggests an android based application, which can precisely predict the most profitable crop to the farmer. The user location is identified with the help of GPS. According to user location, the feasible crops in the respective location is identified from the soil and weather database. These soils are compared with past year production database to identify the most profitable crop in the current location. After this processing is done at server side, the result is sent to the user’s android application. The previous production of the crops is also taken into account which in turn leads to precise crop proposition. Depending on the numerous scenarios and additional filters according to the user requirement the most producible crop is suggested.

Crop yield prediction using machine learning:

A research group investigated the utilization of various information mining methods which will foresee rice crop yield for the data collected from the state of Maharashtra, India. A total of 27 regions of Maharashtra were selected for the assessment and the data was collected related to the principle rice crop yield influencing parameters such as different atmospheric conditions and various harvest parameters i.e Precipitation rate, minimum, average, maximum and most extreme temperature, reference trim cultivable area, evapotranspiration, and yield for the season between June to November referred as Kharif, for the years to 2002 from the open source, Indian Administration records.

WEKA a Java based dialect programming for less challenging assistance with information data sets, assigning design outcomes tool was applied for dataset processing and the overall methodology of the study includes, (1) pre-processing of dataset (2) Building the prediction model utilizing WEKA and (3) Analyzing the outcomes. Cross validation study is carried out to scrutinize how a predictable information mining method will execute on an ambiguous dataset. Study applied 10-fold higher cross validation study design to assess the data subsets for screening and testing. Identified and collected information was randomly distributed into 10 sections where in one data section was used for testing while all other data sections were utilized for the preparation information. Study reported that the method applied was supportive in the precise estimation of rice crop yield for the state of Indonesian J Elec Eng & Comp Sci ISSN: 2502-4752 ? Agriculture Data Analytics in Crop Yield Estimation: A Critical Review (B M Sagar) 1089 Maharashtra, India. The precise quantification of the rice productivity in various climatic conditions can help farmer to understand the optimum condition for the higher rice crop yield [8]. Agriculture is one of the major revenue producing sectors of India and a source of survival.

Various seasonal, economic and biological factors influence the crop production but unpredictable changes in these factors lead to a great loss to farmers. These risks can be measured when suitable mathematical and statistical model designs are applied on data related to soil, weather and past yield. With the advent of data mining, crop yield can be predicted by deriving useful insights from these agricultural data that aids farmers to decide on the crop they would like to plant for the forthcoming year leading to maximum profit. There are various systems that use diverse data mining technologies to manipulate data to derive insights and help in decision making for farmers. The present data mining systems and algorithms used were focus either on one crop and predict or forecast any one parameter like either yield or price. A research presents a survey on the various algorithms used for crop yield prediction, study used to forecast the yield .

The data and predicted output are accessible for the farmers through a web application. This aids farmer to decide on the crop they would like to plant for the forthcoming year. In addition, the web application also provides a forum for the farmers to goods the products without middlemen which help them to obtain maximum price for their products.

Crop yield prediction using data mining techniques:

India is a country where farming and agriculture based industries are the major resource of economy. It is also one of the country which suffer from major natural calamities like drought or flood which damages the crop which cause huge financial loss for the farmers and economic stability of the country. Predicting the crop yield well in advance prior to its harvest can help the farmers and Government organizations to make appropriate planning like storing, selling, fixing minimum support price, importing/exporting etc.

Predicting a crop well in advance requires a systematic study of huge data coming from various variables like soil quality, pH, essential elements quantity etc. As Prediction of crop deals with large set of database thus making this prediction system a perfect candidate for application of data mining methodologies which majorly helps in acquiring a knowledge to achieve higher crop yield. The success of any crop yield prediction system heavily relies on how accurately the features have been extracted and how appropriately classifiers have been employed. Study summarizes the results obtained by various algorithms which are being used by various authors for crop yield prediction, with their accuracy and recommendation .

Weeds and pests were the major crop damaging biotic agents and the farmers are need to be well- informed in accessing the various data mining technologies to acquire a knowledge on applications of effective weed and pest control strategies and managing techniques to reduce crop damage. Collection of data related to the various weeds and pest, modeling of the data to prepare for the mining, selection of appropriate methodology, interpretation and sharing the information become the major challenges in weed and pest control to protect the crop damage. A study was conducted to evaluate the major challenges and noteworthy opportunities and applications of Big Data in controlling the weed and pest damage and hence to achieve higher crop yield. Study reported that the form of the data collected, type of the assessment method and tools applied are the major influencing factors in understanding the role of crop damaging agents such as weed and pest, which provides the knowledge on using improved crop management strategies and crop yield prediction. Big Data cargo space and questioning incurs intense challenges, in respect to allocate the data across numerous technologies, and also continuously evolving data from diverse sources.

When the selected data was from the different sources, semantic methodologies play a vital role in the assessment, which preliminarily detect the factors possess potential agricultural importance and developing relationships between data items in terms of meanings and units. Study presented a success story from the Netherlands in using the information from the Big Data analytics, with numerical algorithms in controlling the crop damage and reported the higher crop yield. Study concluded that, the utility and the applications and of Big data analytics for weed and pest control is very large and particularly for invasive, parasitic and herbicide-resistant weeds. Also imported the need of collaboration of agricultural scientists with data scientists to implement the methodologies for the benefit of agricultural practices [6]. Data mining plays a pivotal role for decision making on different concerns with respect to agriculture practices.

The objective of the data mining methods is to mine knowledge from an accessible data set and convert it into a comprehensible format for some significant application of the Agri process. Crop management of certain agriculture region is depending on the climatic conditions of that region because climate can make huge impact on crop productivity. Real time weather data can help to achieve the good crop management. Effective utilization of mined agricultural based information and communications expertise enables automation of retrieving useful data in an effort to acquire knowledge, which provides opportunity to easier data acquisition from electronic sources directly, transfer to secure electronic system of ? ISSN: 2502-4752 Indonesian J Elec Eng & Comp Sci, Vol. 12, No. 3, December 2018 : 1087 – 1093 1090 documentation and reduces manual tasks.

Automation strategies reduce the overall production cost, hence support for higher crop yield and higher market price. Also identified that how the data mining helps to analyze and predict the useful pattern from huge and dynamically changed climatic data. In the field of agricultural bioengineering, scientist and engineers in collaboration have developed and discussed the application of mathematical model designs like fuzzy logic designs in optimization of the crop yield, artificial neural networks in validation studies, genetic algorithms designs in accessing the fitness of the model applied, decision trees, as well as support vector machines to assess soil, climate conditions and availability of water resources related to crop growth and pest management in agriculture. Study summarizes the application of data mining technologies i.e Neural Networks, Support Vector Machine, Big Data analysis and soft computing in the assessment of agriculture field based on weather conditions [5].

Cite this page

3 SYSTEM DEVELOPMENTThis system has been developed using. (2019, Dec 05). Retrieved from https://studymoose.com/3-system-developmentthis-system-has-been-developed-using-example-essay

👋 Hi! I’m your smart assistant Amy!

Don’t know where to start? Type your requirements and I’ll connect you to an academic expert within 3 minutes.

get help with your assignment