Show simple item record

dc.contributor.advisorChakrabarty, Dr. Amitabha
dc.contributor.authorSiddique, Talha
dc.contributor.authorBarua, Dipro
dc.contributor.authorFerdous, Zannatul
dc.date.accessioned2017-01-19T10:06:03Z
dc.date.available2017-01-19T10:06:03Z
dc.date.copyright2016
dc.date.issued12/14/2016
dc.identifier.otherID 16241001
dc.identifier.otherID 12201029
dc.identifier.otherID 12101045
dc.identifier.urihttp://hdl.handle.net/10361/7626
dc.descriptionCataloged from PDF version of thesis report.
dc.descriptionIncludes bibliographical references (page 65-66).
dc.descriptionThis thesis report is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2016.en_US
dc.description.abstractFarming in Bangladesh is mostly done manually. The automated way of farming here is still not introduced. This research is trying to apply a fundamental approach to inaugurate the automated process in farming in our country. It is an automated farming system designed in android application, which has been implemented to choose the best crop before starting the cultivation process according to the area of the cultivating land. Here, the best crop signifies the crop which will be the most cost effective for that particular land. In this case, the six major crops of Bangladesh – Aus, Aman, Boro, Potato, Wheat and Jute will be considered. This system is also able to prepare a schedule of total cultivation process e.g. the correct time of fertilization and irrigation according to the kind of crop types. The total system is focused on the climate and geographical condition of different areas of Bangladesh. It predicts the best cost effective crop using a prediction based algorithm. The algorithm are aimed to use is multiple linear regression with the association of some independent variables i.e. rainfall, average maximum temperature and average minimum temperature of certain location and give prediction based on yield rate per unit area. Later, KNNR algorithm was used to compare the accuracy and error rate of the predicted yield rate. To describe the functionality of this system; at first, farmer gives the perimeter of land in input area and the district from dropdown menu if he wants the suggestion of best crop. Then best crop name will be shown in the screen. If the suggestive crop is chosen, the entire steps of cultivation will be shown to him. Then the notification of irrigation, fertilization will be shown up timely or in a calendar form. The crop zone is divided according to the division and districts. The data of crops of total seven regions – Bogra, Comilla, Dinajpur, Sylhet, Dhaka, Barisal, Faridpur, Khulna, Rajshahi and Rangpur will be stored in database system. The dataset consists of information on six major crops of Bangladesh; their yield rate, maximum temperature, minimum temperature, year range, region and rainfall. The past twelve years (2000-2011) of Bangladesh have been considered making this dataset to ensure learning and training of the algorithm and increasing the accuracy rate of the prediction and for testing we used three years (2012-2014) for computing accuracy.en_US
dc.description.statementofresponsibilityTalha Siddique
dc.description.statementofresponsibilityDipro Barua
dc.description.statementofresponsibilityZannatul Ferdous
dc.format.extent66 pages
dc.language.isoenen_US
dc.publisherBRAC Universityen_US
dc.rightsBRAC University thesis are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.
dc.subjectMultiple Linear Regression Analysis (MLR)en_US
dc.subjectPredictionen_US
dc.subjectKNNRen_US
dc.subjectAndroid applicationen_US
dc.subjectFertilizer suggestionen_US
dc.subjectDependent variableen_US
dc.subjectIndependent variablesen_US
dc.titleAutomated farming predictionen_US
dc.typeThesisen_US
dc.contributor.departmentDepartment of Computer Science and Engineering, BRAC University
dc.description.degreeB. Computer Science and Engineering


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record