Scribd
Upload
43 views11 pages

Smart Crop Advisor System Using Iot and ML 2

Uploaded by

varunsh245
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
43 views11 pages

Smart Crop Advisor System Using Iot and ML 2

Uploaded by

varunsh245
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 11

Guru Gobind Singh College of Engineering and

Research Center, Nashik.


Department of Computer Engineering
Academic Year: 2023-24

Final Year Project Work


Review 1
Date : 14 Sept 2023

Group ID G-5
Smart Crop Advisor System using Iot and
Project Title
Machine Learning
1. Tejas Amodkar
Team 2. Prajwal Deshmukh
Members 3. Mayur Dhawale
4. Yogesh Jathar

Guide Name Mr. S. A. Gade


1. Problem Definition

• To develop a machine learning model for Suitable Crop Prediction based on


a set of affecting parameters, including temperature, humidity, soil
moisture, weather conditions, and soil nutrients.

• This predictive model aims to assist farmers, agricultural researchers, and


stakeholders in making informed decisions about crop selection for a given
region or agricultural plot.

Guru Gobind Singh College of Engineering, Nashik


2. Motivation

• Enhancing Agricultural Productivity: IoT and ML can significantly


improve crop prediction accuracy, helping farmers to plan better and
maximize their crop yields.

• Empowering Small Farmers: Even small farmers can benefit from these
technologies, which can help them earn a better living.

• Data-Driven Agricultural: Instead of using traditional crop yielding


methods we can use data driven methods to enhance
efficiency of farming.

• Quality Efficiency: To increase the quality and quantity of agricultural


goods at the same time keeping in mind the cost and energy usage.

Guru Gobind Singh College of Engineering, Nashik


3. Objective

• To bridge the digital gap by providing farmers timely information about


crops, weather conditions, soil quality etc.

• To helping farmers make smart choices about their crops to reduce the
chances of crop failures using machine learning techniques.

• To increase the accuracy of suitable crop prediction.

• To digitalizing the whole farming process so that farmers can reap the
benefits of their crops.

Guru Gobind Singh College of Engineering, Nashik


4. Scope

• To improve the productivity and quality of the crops in the agriculture


sector.

• Use of appropriate algorithms on the sensed data can help in


recommendation of suitable crop.

• Helps farmers to better understand the important factors such as water,


topography, aspect, vegetation and soil types.

Guru Gobind Singh College of Engineering, Nashik


5. Process Description:

System Architecture

Guru Gobind Singh College of Engineering, Nashik


5. Process Description:

Flow Diagram
Guru Gobind Singh College of Engineering, Nashik
6. Software- Hardware requirement

• Hardware Requirements

o Controller : ESP8266 CH340


o Sensors – DHT22 (Temperature and Humidity), Capacitive Soil
Moisture
o Base board for ESP8266
o 16x2 LCD
o Cables and Connectors

• Software Requirements

o Programming Language : C, Python


o Libraries : Pandas, Sci-kit Learn,
o Algorithms : Naïve Bays or Decision Tree
o User Application – Android (Flutter)

Guru Gobind Singh College of Engineering, Nashik


7. Strength

• Resource Efficiency: Farmers can make informed decisions on


irrigation, fertilization, and pest control, minimizing environmental
impact.

• Improved Crop Yield: The project's predictive models can lead to


increased crop yield by recommending crops based on optimal
conditions, reducing resource wastage.

• Technology Adoption: Integrating machine learning encourages


technology adoption in agriculture, modernizing practices for greater
efficiency.

• Risk Reduction: Crop failure risks can be mitigated by selecting crops


with higher predicted success rates, safeguarding farmers' livelihoods.

Guru Gobind Singh College of Engineering, Nashik


8. Limitation

• Complexity: Implementing machine learning requires technical expertise


and resources, potentially limiting access for smaller farmers.

• Network Coverage: It requires an unlimited or continuous internet


connection to be successful.

• Maintenance: Models require continuous updating and fine-tuning to


adapt to changing conditions and ensure accurate predictions.

• Adoption Hurdles: Farmers might be hesitant to trust and adopt AI-


based recommendations, preferring traditional knowledge.

Guru Gobind Singh College of Engineering, Nashik


9. References

1. S. Vashisht, P. Kumar and M. C. Trivedi, "Improvised Extreme Learning Machine


for Crop Yield Prediction," 2022 3rd International Conference on Intelligent
Engineering and Management (ICIEM), London, United Kingdom, 2022, pp.
754-757.
2. L. Banda, A. Rai, A. Kansal and A. K. Vashisth, "Suitable Crop Prediction based on
affecting parameters using Naïve Bayes Classification Machine Learning
Technique," 2023 International Conference on Disruptive Technologies (ICDT),
Greater Noida, India, 2023, pp. 43-46.
3. S. Thirumal and R. Latha, "Automated Rice Crop Yield Prediction using Sine
Cosine Algorithm with Weighted Regularized Extreme Learning Machine," 2023
7th International Conference on Intelligent Computing and Control Systems
(ICICCS), Madurai, India, 2023, pp. 35-40, doi:
10.1109/ICICCS56967.2023.10142403.
4. A. K. Sharma and A. S. Rajawat, "Crop Yield Prediction using Hybrid
DeepLearning Algorithm for Smart Agriculture," 2022 Second International
Conference on Artificial Intelligence and Smart Energy (ICAIS), Coimbatore,
India, 2022, pp. 330-335, doi: 10.1109/ICAIS53314.2022.9743001.

Guru Gobind Singh College of Engineering, Nashik

You might also like