1. We claim, An IoT-enabled deep learning system for real-time detection and classification of maize leaf diseases, comprising: one or more image acquisition units configured to capture images of maize leaves in a field environment; an Internet of Things (IoT) communication module operatively connected to the image acquisition units and configured to transmit the captured images through a wireless network; a processing unit comprising a pre-processing module configured to normalize, filter, and enhance the captured images; a trained deep learning model deployed on at least one of an edge computing device or a cloud computing platform, the deep learning model being configured to automatically detect and classify maize leaf diseases from the pre-processed images; one or more environmental sensors configured to acquire field parameters including temperature, humidity, and soil moisture, wherein the processing unit is further configured to correlate the field parameters with disease occurrence; an output interface configured to provide real-time alerts and disease classification results to a user device along with recommended remedial actions; and wherein the system enables continuous, real-time monitoring and early detection of maize leaf diseases with reduced latency and improved accuracy through integration of IoT-based data acquisition and deep learning-based image analysis.

Description:Title of the Invention
IoT-enabled deep learning system for real-time detection and classification of maize leaf diseases

Field of the invention:
The present invention generally relates to the field of maize leaf diseases, particularly relates to an IoT-enabled deep learning system for real-time detection and classification of maize leaf diseases.

Prior art to the invention:

IN202411008903 – Titled - “Fedmaize: A Method and system for early detection of maize leaf disease using federated learning” discloses a method and a system for early detection of maize leaf disease using Federated Learning comprising the steps of: generating an initial global model training task by the global server specifying the maize crop for disease detection; distributing the generated initial model to a local gateway; selecting a resource-efficient FLClients; forwarding the global model to the selected FLClients; local training of the forwarded global model at the selected FLClients using their raw data; updating the FLClients with the locally trained model; aggregating the FLClients’ locally updated model; receiving by the global server the locally aggregated updates through the local gateways; global aggregation of the received updates at the global server; repeating of steps for several rounds until convergence; and generating of converged data to display on an IoT device of user.

None of the above-mentioned prior arts neither teaches nor discloses about an IoT-enabled deep learning system for real-time detection and classification of maize leaf diseases.

wherein, the present invention is an IoT-enabled deep learning system for real-time detection and classification of maize leaf diseases.

Objects of the invention:
The principle objects of the present invention an IoT-enabled deep learning system for real-time detection and classification of maize leaf diseases.

Summary of the invention:

Thus the basic aspect of the present invention provides an IoT-enabled deep learning system for real-time detection and classification of maize leaf diseases.

Detailed description:

The present invention as herein describes about to an IoT-enabled deep learning system for real-time detection and classification of maize leaf diseases.

The present invention relates to an IoT-enabled deep learning system for real-time detection and classification of maize leaf diseases integrates smart sensing, edge computing, and artificial intelligence to enable early, accurate, and scalable crop health monitoring. In this system, high-resolution images of maize leaves are captured using field-deployed IoT devices such as camera-equipped sensor nodes or smartphones, which are connected through wireless communication protocols (e.g., Wi-Fi, LoRa, or cellular networks) to a central or edge processing unit. The captured images are preprocessed to remove noise, normalize lighting variations, and enhance relevant features before being fed into a deep learning model typically a convolutional neural network (CNN) such as ResNet, MobileNet, or EfficientNet trained to identify and classify common maize diseases like leaf blight, rust, and gray leaf spot. For real-time performance, lightweight models can be deployed on edge devices (e.g., Raspberry Pi or NVIDIA Jetson), reducing latency and dependence on cloud infrastructure, while more complex analysis and model updates can be handled in the cloud. The system can continuously monitor crop conditions, detect early-stage infections, and send instant alerts to farmers via mobile applications, along with recommended remedial actions. Additionally, integration with environmental sensors (temperature, humidity, soil moisture) enables correlation of disease occurrence with field conditions, improving prediction accuracy. Such a system enhances precision agriculture by minimizing crop losses, reducing unnecessary pesticide use, and supporting data-driven decision-making for sustainable maize cultivation.

Embodiments of the present invention will now be described in more detail with reference to the drawings. The following description is for convenience of understanding of the present invention, and the present invention is not limited by this. , Claims:Claims:
1. We claim,
An IoT-enabled deep learning system for real-time detection and classification of maize leaf diseases, comprising:
one or more image acquisition units configured to capture images of maize leaves in a field environment;
an Internet of Things (IoT) communication module operatively connected to the image acquisition units and configured to transmit the captured images through a wireless network;
a processing unit comprising a pre-processing module configured to normalize, filter, and enhance the captured images;
a trained deep learning model deployed on at least one of an edge computing device or a cloud computing platform, the deep learning model being configured to automatically detect and classify maize leaf diseases from the pre-processed images;
one or more environmental sensors configured to acquire field parameters including temperature, humidity, and soil moisture, wherein the processing unit is further configured to correlate the field parameters with disease occurrence;
an output interface configured to provide real-time alerts and disease classification results to a user device along with recommended remedial actions; and
wherein the system enables continuous, real-time monitoring and early detection of maize leaf diseases with reduced latency and improved accuracy through integration of IoT-based data acquisition and deep learning-based image analysis.