Please enable JavaScript.
Coggle requires JavaScript to display documents.
PDD1 - Coggle Diagram
PDD1
BACKGROUND
-
-
-
-
-
-
-
STUDY SIGNIFICANCE
-
provide insights into the relevance and importance of classification models, particularly advanced deep learning models.
LR
DL
(CNN), has shown remarkable improvements in plant disease detection.
-
deep learning models and advanced classification techniques has the potential to greatly benefit agriculture
-
Deep learning has gained attention, but further research is needed to explore future trends and advancements in the classification process.
ML
-
-
-
88% for SVM, 97% for KNN, and 99.6% for CNN.
MOST IMP
previous manual image processing and diagnosis methods have several drawbacks in the
determination process
Therefore, an advanced approach based on classification models is discussed which shows a higher accuracy level and feasibility in plant disease detection and classification aspects.
Since the study focuses on aligning knowledge on the reliability of deep learning models in this detection process, the focus needs to be extensive and thus requires further research and justification as to how deep learning models can be efficient in the plant disease detection process.
-
METHODOLOGY
DATA PRE-PROCESSING
cleaning, normalization,
extraction of characteristics, and sampling
-
-
-
-
-