CROP YEILD PREDICTION IOT

ABSTRACT:-

                Agriculture aided through IoT is known as Smart Agriculture and it offers rise to precision farming. Soil Monitoring blended with Internet of Things (IoT) technology aids withinside the enhancement of agriculture through growing yield via gauging the precise soil traits along with Moisture, Temperature, Humidity, PH, and Nutrition content/Fertility. This data is then gathered in cloud garage and with the suitable records operations; it enabled us to optimize farming techniques and helped create a fashion analysis. This, then, lets in us to exactly make use of sources and steer the farming techniques in prudent approaches to optimize yield. The proposed IoT gadget is composed of pH sensors, Humidity and temperature sensors, Soil moisture sensors, soil nutrient sensors (NPK) probes, Raspberry pi geared up with WiFi and Cloud garage. When the sensors are implemented, they degree the corresponding traits and transmit time-stamped live records to the cloud server. These sensors work collectively and offer healthy records to the analyst. For the recommending gadget, the SVM and Decision Tree set of rules is proposed to get the crop appropriate for the given soil records and allows to decorate the boom the use of an optimized farming process.

PROPOSED SYSTEM:-

The structure for soil conduct evaluation and advocated the crop. Below Figure indicates the analyses of the soil datasets which integrates all modules. The pre-processing stage includes 3 major procedures particularly statistics cleansing and lacking statistics computation. The gadget structure offers a precise waft of every technique of a conceptual version that defines the structure, conduct, and more. The illustration of the gadget with processing dating to every different in the surroundings to be executed for the crop prediction and advice to be calculated. The statistics mining method became used to are expecting the crop yield for maximizing crop productivity. The proposed methodology, the pre-processed statistics became clustered the usage of SVM and Decision Tree set of rules. The crop yield became expected primarily based totally at the generated rules. The district and crop are enter to the prediction version and the SVM and Decision Tree set of rules recommends the crop to the user. By Comparing those algorithms, accuracy is calculated and in comparison and generated the graph.

MODULES:

• User Register and Login: User have to register and login to check which elements (NPK) are suitable for soil and which crop will grow based on soil moisture and humidity. Also farmer can manage temperature, water level, moisture from home
• NPK Prediction: We use crop dataset which is open-source to trained models (Adaboost) and predict NPK values.
• Crop Prediction: Feeding NPK values to trained machine learning models such as Random forest, SVM, Decision tree to predict crop. Algorithm also recommend fertilizers to the user based on crop prediction.
• Crop yield prediction: Based on user district ,season area and crop algorithm will predict yield and also recommend crop.

1. SUPPORT VECTOR MACHINES

Algorithm 1explains the entire scenario of the guide vector system. The guide vector gadget begins offevolved via way of means of selecting the form of soil. Then the crop that may be grown in that soil is extracted from the database. Next, the extent of water selected via way of means of the farmer is in comparison with the plants. Those plants which suit the soil are observed. Now the plants are separated as in step with the user needs. Now relying upon the want of the customers the acre degree of the farmer is determined and the land is split into parts. Based at the fee of the crop recommended.

1. DECISION TREE ALGORITHM

Algorithm 2 explains the entire situation of the selection tree. The selection tree begins offevolved through deciding on the kind of soil. Then the crop that may be grown in that soil is extracted from the database. The identical steps had been observed as given in SVM. Now relying upon the want of the customers the acre degree of the farmer is discovered and the land is split into parts. The proportional land is given to the farmers for his or her cultivation. And discover the precision and calculate the measures with a selection tree to endorse the crop with accuracy.

HARDWARE AND SOFTWARE REQUIREMENTS

HARDWARE:

• Processor: Intel Core i3 or more.
• Hard disk: 250 GB or more.
• DHT11 Sensor
• Soil moisture Sensor
• Mq2 Gas Sensor
• LDR Sensor
• Raspberry pi
• Arduino

SOFTWARE:

• Operating System : Windows 10, 7, 8.
• Python
• Anaconda
• Spyder, Jupyter notebook, Flask.

MYSQL.