Domain Details

Research Domain and Academic Foundation

This page presents the literature background, research gap, problem statement, objectives, methodology, and technologies used in AloeGreen.

Literature Survey

Recent smart agriculture studies highlight the value of integrating sensing, predictive analytics, and mobile interfaces. However, many systems focus on broad crop settings, isolated weather functions, or single-task monitoring. Literature in IoT agriculture, machine learning-based crop prediction, and disease analysis supports the importance of data-driven cultivation support, yet still leaves space for crop-specific platforms tailored to narrower domains such as Aloe vera.

AloeGreen builds on this foundation by treating cultivation support as a connected workflow. It combines real-time monitoring, model-based reasoning, and user-facing insights in a single research-driven environment.

Research Gap

The main gap lies in the fragmentation of current digital agriculture tools. Existing solutions often support only one activity at a time such as weather checking, image classification, generic dashboards, or record keeping. Very few provide an integrated, crop-specific platform dedicated to Aloe vera cultivation.

AloeGreen addresses this gap by proposing one intelligent ecosystem that unifies multiple modules for monitoring, analysis, and decision support.

Research Problem

Aloe vera cultivation still lacks an integrated smart agriculture platform capable of connecting IoT sensing, predictive analytics, disease awareness, nutrient support, and market-oriented insight in one system. As a result, users face difficulty converting raw agricultural data into timely and practical decisions.

Research Objectives

Design a crop-specific AI-IoT platform for Aloe vera cultivation.
Integrate real-time field sensing and cloud-based data flow.
Support yield prediction and environmental forecasting using predictive models.
Provide disease detection, fertilizer recommendation, and price forecasting capabilities.
Deliver research-backed outputs in a usable format for practical decision support.

Methodology

The AloeGreen methodology combines data acquisition, system integration, model development, and evaluation. Field-related inputs are captured through sensing devices and supporting datasets. Information is transmitted through MQTT-based communication, processed by backend services, and interpreted by predictive modules. Outputs are then presented to users through a mobile-ready interface that translates technical results into understandable recommendations.

The platform is evaluated by considering both system integration and model behavior, with performance interpretation used to support the research contribution.

Technologies Used

ESP32-based sensing: field-level data acquisition.
Environmental and agricultural sensors: monitoring soil and climate related conditions.
MQTT / HiveMQ Cloud: reliable communication and cloud data transfer.
FastAPI backend: model serving, orchestration, and API support.
React Native mobile app: accessible user-facing delivery of results.

Research Perspective

AloeGreen demonstrates how an AI-IoT system can move beyond separate experiments and function as a coherent smart agriculture concept. The project is shaped to satisfy academic requirements while remaining grounded in real cultivation needs.