Description:Field of Invention
The invention is associated with the discipline of smart farming management, and more specifically an Internet of Things-based control system for intelligent farming administration.
The Objectives of this Invention
The primary goal of the present invention is to leverage the possible applications of artificial intelligence (AI) in the field of analyzing and utilizing intelligence in agricultural automation utilizing data gathered through WSN (Wireless Sensor Network) technologies. Making more intelligent choices could be aided by this. WSN comprises gathering, recording, and analyzing data that can be used to track the actions associated with agriculture and its automated inhabitants. Agriculture automation uses sensors that can gauge humidity, wetness, atmospheric pressure, the PH of water or soil, and other factors.
Background of the Invention
According to (CN2020/111488017A), The invention describes an Internet of Things-based intelligent farming control and administration system that includes a Bluetooth wireless communication module, a data analysis center, a data storage center, an intelligent system for irrigation, a fertilization system, a ventilating and lighting system, a livestock observing system, a meteorological observing system, a soil observing system, a video observing system, a satellite reconnaissance system, and further components. Another type of application invented in (CN2021/113377141A), The invention describes an artificial intelligent agricultural automatic control system that is used to irrigate crops through an automatic irrigation unit automatically, fertilize crops through an autonomous fertilising unit, identify and autonomously kill insects that cause damage to crops through an autonomous insect killing unit, and remove diseases from crops autonomously via an autonomous illness eliminate device. Another method was invented in (CN2016/106358997A), An intelligent hydrology and fertilizer methodology based on cloud computing and an intelligent irrigation and fertilization system are also disclosed. The intelligent irrigation and fertilization system based on cloud computation includes the irrigation and fertilization system, information monitoring system, micro-control unit, cloud server, control terminal, and other components. Utilizing the intelligent irrigated and fertilization system based on cloud computation is the intelligent irrigation and fertilization approach.
According to Chinnasamy et al.'s research (2022 International Conference on Computer Communication and Informatics (ICCCI), Coimbatore, India, 2022, pp. 1-3), In a technological age, agricultural automation is becoming more and more critical. Previously, the data was recorded on a straightforward LCD screen. Still, in this article, we establish a novel idea to keep track of the water level in a particular area while also pumping water and sending it via GSM. The analyzed data can then be sent to a gardener or someone who monitors the area using GSM networks. When no water or water has been filled up in a garden or smart city that uses blockchain technology, smart farming is a device that is intended to help inform someone. The notification system can be utilized as a call for local or emergency agencies to respond in instances of emergency. According to Chinnasamy et al. ((2021), Turkish Journal of Computer and Mathematics Education (TURCOMAT), Vol.16, No.2, pp. 2858-2865), they used blockchain to overcome such security flaws, enabling a decentralized distributed blockchain protocol shared across IoT cluster chiefs. The main objective of this essay is to equip farmlands with smart greenhouses with a transportable blockchain-based infrastructure that ensures integrity and anonymity. In this case, green-house IoT sensor nodes use secure, immutable ledgers to operate as a centrally regulated blockchain to optimize energy use. Additionally, we show a vital solution that uses IoT devices and blockchain technology to provide better secure communications for Smart Greenhouse farming. Hanumann et al (2022, 2022 International Conference on Computer Communication and Informatics (ICCCI), Coimbatore, India, 2022, pp. 1-3), One of the most crucial jobs in any farming or agriculture-based setting is the plant surveillance system, which aids farmers in watering. An automated IOT-based water system uses temperature, moisture, humidity, and brightness of light to track and preserve the farms' approximate soil moisture level. Everyday temperature values can be recorded. Based on the analysis of their sensor results, farmers can choose which farm would work on a given piece of land. The primary objective of this automation is to help the farmer produce more crops, make the best use of the water supply (some locations have drought lands, and they can make excellent use of this technology), and make crop decisions. Their autonomous IOT-based water supply uses resources effectively and produces excellent temperature precision with a working Arduino UNO. Overall, it lowers financial outlay and human interference.
Summary of the Invention
This innovation introduced and discussed using WSN, Cloud Computing, and Machine Learning methods to implement AI (Artificial Neural Network) for comprehensive farm monitoring. The outcomes achieved by the system are encouraging because it can forecast values under unknown conditions.
Detailed Description of the Invention
To examine how agriculture is dynamic, including how the soil, fertility, and other resources are used and when unpredictability arises. With the aid of the Computing extensions (Raspberry Pi), the variety of sensors that gather information from the surrounding environment communicate using the MQTT protocol. The header appropriate for the HTTP protocol combined and transported the material. The sensor data is saved in the cloud whenever the network is used and then shared as informational packets. The Thing-Speak cloud-based system processes intelligent data stored in the cloud and provides insights to streamline machine learning procedures. 60% of the collected data is used to train the GRNN, 30% for testing, and 10% for validation during the training process. The input is windowed to the target value because the GRNN is a supervised method, and the mapping procedure is required to create the optimum network. Since this is an iterative process, the convergence stage is only reached when the input and target layers match perfectly. Because the procedure for learning is continuous, the process keeps transferring the input in the direction of the target. The trained network makes it possible to predict which tactics will work best.
Epoch 2 saw the confirmation plot attain its lowest MSE value of 0.0918, resulting in the best validation effectiveness. Data on increased CO2 from 2000 is used to train neural networks and fed into the procedure. The best network was selected from the training process after it was calibrated 500 times. The effect of each cycle is observed using GRNN for analysis. The next iteration will see an improvement in the false-hit and loss decision rates. The performance of the instructional material determines the learning rate, as mentioned in Regression plots that show network outputs with targets for training, validation, and test sets are also represented by it. The data must lie on a 45° line where the network outputs and targets are equal for the fit to be ideal. This is used to verify the effectiveness of the network. The learning processes that associate all the linked points after each epoch are the focus of this training session. In this instance, the mean square error calculation, which iteratively checks the error, determines the convergence state. The slope of the uncertain polynomial can be increased or decreased depending on the prediction error to improve performance. The user can also choose the number of neurons required in the hidden layer. The number of neurons is determined under certain circumstances, as listed below.
The working of a Smart Agriculture Automatic Monitoring System using Artificial Intelligence involves several interconnected steps that seamlessly combine technology, data, and AI algorithms to enhance farming practices. Here's how the system operates: Sensors and devices, such as weather stations, soil moisture sensors, temperature sensors, humidity sensors, GPS trackers, and even drones, are strategically placed in the agricultural field or environment. These sensors continuously gather data related to various parameters like weather conditions, soil moisture levels, temperature, humidity, crop growth status, and more. The data collected is transmitted to a central database or cloud platform using wireless communication technologies such as Wi-Fi, cellular networks, or dedicated low-power protocols like LoRaWAN. The collected data is stored in a centralized database or cloud server. Data from different sensors and sources are integrated and organized for further analysis. Raw data often requires cleaning and preprocessing to remove noise and inconsistencies. Data normalization and transformation might be performed to ensure uniformity across different data streams. Machine learning algorithms, a subset of AI, are employed to analyze the collected data. The AI models are trained using historical data to recognize patterns, correlations, and anomalies in the data. Different AI techniques like regression, classification, clustering, and time series analysis are used depending on the specific use case. Based on the AI analysis, the system generates actionable insights and predictions. For instance, the system might predict when irrigation is needed based on soil moisture trends, or it might forecast disease outbreaks based on weather conditions and historical disease patterns. The generated insights and predictions are presented to farmers or agricultural managers through user-friendly interfaces like mobile apps or web dashboards. Farmers receive real-time alerts, notifications, and recommendations on the optimal actions to take. Automation can also play a role; for example, irrigation systems can be triggered automatically when soil moisture falls below a certain threshold. The system continually collects new data and updates its AI models to improve accuracy over time. By comparing the predictions with the actual outcomes, the system refines its algorithms and adapts to changing conditions. The system allows farmers to remotely monitor their fields' conditions in real-time, enabling them to make informed decisions even when they are not physically present.
Consider a crop management scenario where an AI-powered smart agriculture system is used to monitor and optimize tomato farming. The system collects data from various sensors placed in the tomato field, such as temperature sensors, humidity sensors, and disease detection cameras. Using AI analysis, the system can predict the risk of fungal infections based on weather conditions and historical disease patterns. If the risk is high, the system sends an alert to the farmer's smartphone app, suggesting the application of a specific fungicide. This helps prevent disease outbreaks and minimizes crop losses. In summary, a Smart Agriculture Automatic Monitoring System using Artificial Intelligence combines data collection, AI analysis, and decision support to provide farmers with real-time insights and predictions, leading to more efficient, productive, and sustainable agricultural practices.
A Smart Agriculture Automatic Monitoring System using Artificial Intelligence (AI) incorporates various technologies to enhance agricultural processes and improve efficiency. Here are the key features of such a system: Integration of sensors, drones, satellites, and IoT devices for real-time data collection on soil moisture, temperature, humidity, crop health, and more. Data is continuously gathered from fields, enabling timely decision-making. AI algorithms analyze historical and real-time data to predict crop yields, disease outbreaks, and optimal planting times. Farmers can plan and adapt their practices based on these predictions. Crop Monitoring and Health Assessment which follows computer vision and machine learning algorithms assess crop health by analyzing images. Detects diseases, pests, nutrient deficiencies, and stress, allowing for early intervention. AI-driven irrigation systems adjust water usage based on real-time weather data, soil moisture, and plant needs. AI models identify pest and disease patterns, enabling targeted treatments and reducing the need for broad-spectrum pesticides. Minimizes chemical usage, promotes eco-friendly practices, and reduces costs. Utilizes AI models to predict growth stages, flowering times, and harvest periods based on environmental conditions. Aids in planning labor, resources, and storage. Integrates weather forecasts with AI models to adapt farming strategies to changing weather conditions. Helps prevent weather-related losses and optimizes resource allocation. AI-driven dashboards and mobile apps provide real-time insights and recommendations to farmers. Supports informed decisions and simplifies monitoring and control. AI-based analysis of soil data helps farmers maintain soil health and fertility. Recommends appropriate fertilization and soil management techniques. Precision techniques minimize overuse of water, pesticides, and fertilizers, leading to sustainable and eco-friendly farming practices. AI systems learn from historical and real-time data, adapting strategies to changing conditions and improving accuracy over time.
A Smart Agriculture Automatic Monitoring System using AI transforms traditional farming into a data-driven, efficient, and sustainable practice, empowering farmers with insights to optimize productivity and make informed decisions.

5 Claims & 1 Figure
Brief description of Drawing
In the figure which are illustrate exemplary embodiments of the invention.
Figure 1, The Process of Proposed Invention , Claims:The scope of the invention is defined by the following claims:

Claim:
1. A system/method for making autonomous system for agriculture using artificial intelligence and WSN, said system/method comprising the steps of:
a) The system connects with array of sensors (1), to microcontroller, that will connect to machine learning (AI) (2), as well as GPS module (3) and wireless transmission module (4).
b) The system monitor all the metrics of land and display the results via display module (5).
2. As mentioned in claim 1, the Raspberry Pi's Computing modules work with an array of sensors to transfer information collected from the surrounding environment via the protocol known as MQTT.
3. According to claim 1, Since the network's infrastructure is being used, sensor-related data is gathered, stored, and transmitted as communication packets.
4. As per claim 1, Intelligent cloud computing handles the data with the Thing- speak cloud computing platform providing statistical analysis to smooth machine learning operations.
5. According to claim 1, The resultant convergence stage is reached if the perfect match of mapping (i.e., Input layer to the Target layer) is achieved. As the learning process is iterative, the process continues to map the input toward the target.