first review rougb.pptxMinna no Nihongo Shokyuu 1 - Choukai

Minna no Nihongo Shokyuu 1 - ChoukaiMinna no Nihongo Shokyuu 1 - ChoukaiMinna no Nihongo Shokyuu 1 - ChoukaiMinna no Nihongo Shokyuu 1 - Choukai

1. Title IoT-Enabled Dynamic Nutrient Microdosing System for Precision Hydroponics Bharath Reddy 1MS20ET013 Parth Navale 1MS21ET403 Puneeth S L 1MS21ET404 Punith H M 1MS21ET405 Project Guide Dr. Arvind Kumar G Assistant Professor Electronics and Telecommunication Engineering 1

2. Aim of the Project To design and develop a remotely accessible hydroponics system that empowers individuals to cultivate plants in their gardens and backyards effortlessly, without the need for constant manual oversight, we are incorporating IoT (Internet of Things) and ML (Machine Learning) technologies to automate the growth process.

3. Introduction 3

4. Objectives 4

5. Methodology 1.Define System Architecture: Identify hardware components: plant sensors, actuators, Raspberry Pi microcontroller, NodeMCU ESP8266 pH controller, EC sensor, WiFi module, grow lights, pH solutions, peristaltic pump using relay module, and power supply. Determine communication protocols and establish connectivity architecture. 2.Hydroponics Setup and Plant Growth: Specify the hydroponic setup using cocopeat for growing tomato cherry plants. Integrate grow lights for optimized plant growth. 3.Peristaltic Pump Setup: Implement a peristaltic pump using a relay module for precise nutrient dosing. Ensure proper power supply for all components. 4.pH Controller Integration: Incorporate NodeMCU ESP8266 pH controller into the microcontroller's circuit. Establish communication between the main microcontroller and the pH controller. Configure the pH controller to adjust pH levels based on pH sensor readings. Integrate pH solutions for calibration.

6. 5 .Blynk App Development: Create a Blynk app interface with widgets for pH adjustment, nutrient adjustment, pH control, EC sensor readings, and control for grow lights. Implement virtual pins for communication between the microcontroller and the Blynk app. 6.Algorithm Implementation : Develop CNN and machine learning algorithms for tomato plant nutrient deficiency using data from pH sensors, nutrient solution EC sensors, and other relevant sensors. Incorporate decision-making rules based on plant health indicators to dynamically adjust nutrient dosing, pH levels, and EC. 7.System Testing and Validation: Conduct comprehensive testing of the integrated system's functionality, including nutrient dosing, pH control, grow lights, and remote monitoring. Simulate various scenarios to validate the algorithm's responsiveness to changing plant conditions.

7. Block Diagram of the System Fig 1:Block diagram of the System design RPI MI & AI Algorithm Camera pH sensor EC Sensor Arduino WIFI UP Pump Down Pump IoT Display IoT Cloud

8. HARDWARE REQUIRED Raspberry Pi 5 Camera pH Sensor EC Sensor Peristaltic Pump Relay Arduino UNO RENO 3 pH Solutions pH and EC meter 8

9. Software Requirement Embedded C Python Open CV Rembg Visual Studio Code Arduino IDE IoT Cloud

10. Dataset Processing using Rembg Original Image Black background Image Without Background Image

11. Project Schedule

12. Literature Review [1] A Review On Nutrient Deficiency Symptoms And Effects On Tomato Plant The paper examines nutrient deficiency in tomato plants, focusing on Nitrogen, Phosphorus, Potassium, Calcium, Zinc, and others. Key symptoms include stunted growth, leaf curling, tip burn, chlorosis, and abnormal foliage. External factors like excessive soil moisture and high salinity contribute to deficiencies. Management practices involve applying nutrient-containing compounds and specific fertilizers. The study highlights the impact on yield and quality, discussing physiological responses and genetic modifications. Emphasizing the need to address deficiencies, the research underscores their significance in successful tomato cultivation . [2]Automatic Detection of Tomato Leaf Deficiency and its Result of Disease Occurrence through Image Processing The paper underscores the economic importance of agricultural productivity and critiques existing plant disease detection methods. It emphasizes the need for early identification and proposes an automatic deficiency detection system for tomato leaves using image processing. The method includes leaf area measurement, edge and vein segmentation, and color feature extraction. The authors stress the impact of nutrient deficiencies on plant health and advocate for accurate disease detection to prevent crop loss. Referring to related research on machine learning and image processing, the paper highlights successful detection of various nutrient deficiencies in tomatoes and predicts disease occurrence based on these deficiencies .

13. Literature Review [3]Hydroponic Solutions for Soilless Production Systems: Issues and Opportunities in a Smart Agriculture Perspective The research paper underscores the significance of hydroponic solutions in mitigating soil degradation and water scarcity, addressing challenges posed by population growth and diminishing fertile soil. It emphasizes optimal nutrient management, incorporating nanoparticles, beneficial microorganisms, and Industry 4.0 technologies. The advantages include controlled, automated processes, leveraging IoT, and enhancing productivity, quality, and environmental sustainability. Focus areas encompass nutrient management, crop quality improvement, and emerging technologies. The authors advocate for smart agriculture strategies through consistent information system design to overcome limitations in soilless cultivation. [4]Automated pH Controller System for Hydroponic Cultivation The paper discusses the development of an automated pH controller system for deep water culture (DWC) hydroponic cultivation using an Arduino Mega 2560 microcontroller. The system aims to automatically maintain the pH level in the water solution for DWC to ensure optimal plant growth . The research includes experiments to measure the amount of pH adjusting solution dropped by the actuator , the changing pH value in the main tank with different pH sensors , and the effects of pH up and down solutions on the pH value. The results show that the system successfully maintains the pH level in the water solution and transfers it to the hydroponics container at the desired level. The experiments provide insights into the relationship between motor rotation and pH adjuster amount, pH value variation over time, and the effects of pH up and down solutions on pH levels. The paper ultimately demonstrates the successful development of the automated pH controller system for DWCs hydroponic cultivation.

14. [5]Design of Automatic pH Level Prototype Using Microcontrol Nodemcu Esp8266 Based on IoT Technology The study developed an automatic water pH control system using NodeMCU ESP8266 and IoT technology for enhanced safety and pH maintenance. Utilizing pH and water level sensors, and adjusting diaphragm pump speed through Sugeno Fuzzy logic, the system controlled water pH effectively. A smartphone app facilitated monitoring, and successful pH control for an 8-liter water capacity was demonstrated. The study covered hardware and software design, employing Arduino IDE and Blynk application. Testing confirmed successful pH control within set standards, with suggestions for potential future enhancements. [6]Detection and classification of nutrient deficiencies in plants using machine learning The research paper discusses the development of an artificial neural network model to detect and classify nutrient deficiencies in tomato plants based on leaf characteristics. The study highlights the significance of nutrients in plant growth and the detrimental effects of nutrient deficiencies on crop yield . Different segmentation schemes, including hue and threshold based schemes, are compared to assess their impact on the performance of the system. The influence of various activation functions in the artificial neural network is also examined. The results demonstrate that the proposed model can accurately identify nutrient deficiencies in tomato plants. The paper emphasizes the importance of early detection of nutrient deficiencies to enhance plant productivity . Additionally, it provides insights into the nutrient requirements of tomato plants, deficiency symptoms, and fertilization techniques. The study suggests potential future directions, including the inclusion of fruit images in the dataset and exploring convolutional neural networks for improved deficiency detection .

15. [7]Raspberry Pi-Embedded Intelligent Control System for Irrigation and Fertilization Based on deep learning The paper presents the development of a Raspberry Pi-embedded intelligent control system for irrigation and fertilization based on deep learning models. The system aims to improve water and fertilizer utilization efficiency in agriculture. This is achieved by using deep learning models to make decisions for irrigation and fertilization based on leaf images. The system includes sensors, image acquisition, control parts, and remote control. The deep learning model is compressed on the Raspberry Pi, reducing its size and decision-making time while maintaining accuracy. The paper also discusses the hardware selection, environment deployment, and model compression process. The study shows that pruning the deep learning model can reduce its size and improve its computation speed without significantly sacrificing accuracy. The paper highlights the potential for further research on deep learning models for different crops and fertilizer deficiencies. [8]Tomato Fruit Detection and Counting in Greenhouses Using Deep Learning This research paper discusses the use of deep learning algorithms, specifically the MaskRCNN algorithm, to detect and count tomatoes in images taken in a greenhouse using RealSense cameras. The paper highlights the importance of automating the processes of fruit detection and counting in agriculture, particularly for crops like tomatoes. It compares the results of using MaskRCNN with earlier work and classical segmentation methods, demonstrating that MaskRCNN outperforms in detecting both ripe and unripe tomatoes with higher precision and recall. The results show that deep learning-based methods have the potential to automate and improve fruit detection in challenging agricultural environments. The paper also discusses practical applications and future directions for integrating fruit detection results with harvested yield and improving depth-based input for the algorithm. The study was a collaborative effort involving researchers from Wageningen University and Research and Enza Zaden .

16. Conclusion Effortless Garden, Anywhere:  Remotely monitor & control your plants, ditching constant manual work. AI-Powered Nutrition:  Sensors & AI adjust nutrients microdosing for optimal plant health. Automated pH Balance:  Built-in controller maintains perfect pH for thriving plants. Sustainable & Resource-Efficient:  Less water usage compared to traditional methods, minimizing environmental impact. Scalable Design:  Accommodate future growth by easily adding more plants or expanding your garden. Cost-Effective & Accessible:  Affordable design brings the benefits of smart hydroponics to a wider audience.

17. References Journals: 1. Arvind Kumar G, Sowmya N, Vanitha K. M, Sharan Reddy., “Continuous Monitoring of Lettuce Growth in Hydroponic System” Mathematical Statistician and Engineering Applications., Vol. 71 No. 4 (2022), ISSN: 2094-0343 2. Kumar, Arvind. (2021). Agricultural Resource Sharing and Crop Management. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 12(12), 1656-1661. 3. Design, Construction and Testing of IoT-Based Automated Indoor Vertical Hydroponics Farming Test-Bed in Qatar https://doi.org/10.3390/s20195637. https://www.mdpi.com/1424-8220/20/19/5637 4. Cost-Effective Smart Hydroponic Monitoring and Controlling System Using IoT. https://www.scirp.org/journal/paperinformation.aspx?paperid=95969 5. Hydroponic Farm Monitoring System Using IoT. https://www.irejournals.com/formatedpaper/1702234.pdf 6. IoT-Based Hydroponics Approach for Soil-less Farming. https://iarjset.com/wp- content/uploads/2020/10/IARJSET.2020.7917.pdf 7. Hydroponics System based on IoT. https://www.annalsofrscb.ro/index.php/journal/article/download/3712/3023 8. IoT-based Indoor Hydroponics System https://www.researchgate.net/publication/356664868_IoT_based_Indoor_Hydroponics_System . 9. IoT-Based Automated Hydroponic Cultivation System https://www.ripublication.com/ijaerspl2019/ijaerv14n11spl_23.pdf 10. IoT-Based Automated Hydroponic System. https://www.mathaelectronics.com/iot-based-automated-hydroponic-system