An Associated Representation Method for Defining Agricultural Cases in a Case-Based Reasoning System for Fast Case...

Area of Science:

• Artificial Intelligence
• Smart Agriculture
• Decision Support Systems

Background:

• Case-based reasoning (CBR) is vital for intelligent systems in smart agriculture, offering farming operation management advice.
• Traditional case representation methods (textual, attribute-value, ontological) can be inefficient for large datasets.
• Efficient case retrieval is crucial for practical CBR applications in agriculture.

Purpose of the Study:

• To propose and evaluate an associated case representation method for faster case retrieval in smart agriculture.
• To address the inefficiency of traditional methods in handling large agricultural datasets.
• To enhance the performance of CBR systems for farming decision support.

Main Methods:

• Developed an associated case representation where cases are interconnected with similar and dissimilar ones.
• Implemented a similarity measurement strategy that prioritizes associated cases over exhaustive comparison.
• Conducted experiments comparing the associated method against traditional methods using retrieval metrics.

Main Results:

• The associated case representation method demonstrated significantly faster case retrieval.
• The proposed method achieved promising accuracy while visiting fewer cases.
• Experimental results confirmed improved retrieval efficiency compared to traditional approaches.

Conclusions:

• The associated case representation method offers a superior approach for efficient case retrieval in smart agriculture.
• This innovation enhances the practical applicability of CBR systems for farmers.
• The findings highlight the potential of associated case representation for large-scale intelligent agricultural systems.