Detection of Plant Leaf-based Diseases Using Machine Learning Approach

Reddy, P. Chaitanya; Chandra, R.; Vadiraj, P; Reddy, M. Ayyappa; Mahesh, T R; Madhuri, G Sindhu

doi:10.1109/csitss54238.2021.9683020

Cited by 23 publications

(14 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SMOTE is used in the initial phase to lessen the impact of data imbalance. Then, the second phase entails classification using Naive Bayes and DT methods (AltDTree, CART, RedEPTree, and RF) [ 33 ]. After that, AdaBoost Ensembles of the aforementioned algorithms are constructed and their performance is evaluated.…”

Section: Proposed Methodologymentioning

confidence: 99%

“…In the next model, all points with greater weights are given more importance. It will continue to train models till a lower error is received [ 33 ].…”

Section: Exploratory Knowledgementioning

confidence: 99%

“…C It is the normalization constant, α It is used to allow the outcome to be generalized and to solve the problem of overfitting and noise sensitive situations [ 33 ]. The real value of α It h It ( x ) is built using a class probability estimate (P).…”

Section: Exploratory Knowledgementioning

confidence: 99%

“…A good classifier should have a precision of 100% (high); only when both numerator and denominator are identical, i.e., TP = TP + FP, can precision become 100% [ 33 ].…”

Section: Performance Evaluationsmentioning

confidence: 99%

See 3 more Smart Citations

AdaBoost Ensemble Methods Using K-Fold Cross Validation for Survivability with the Early Detection of Heart Disease

Mahesh

Kumar

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

As a result of technology improvements, various features have been collected for heart disease diagnosis. Large data sets have several drawbacks, including limited storage capacity and long access and processing times. For medical therapy, early diagnosis of heart problems is crucial. Disease of heart is a devastating human disease that is quickly increasing in developed and also developing countries, resulting in death. In this type of disease, the heart normally fails to provide enough blood to different body parts in order to allow them to perform their regular functions. Early, as well as, proper diagnosis of this condition is very critical for averting further damage and also to save patients’ lives. In this work, machine learning (ML) is utilized to find out whether a person has cardiac disease or not. Both the types of ensemble classifiers, namely, homogeneous as well as heterogeneous classifiers (formed by combining two separate classifiers), have been implemented in this work. The data mining preprocessing using Synthetic Minority Oversampling Technique (SMOTE) has been employed to cope with the imbalance problem of the class as well as noise. The proposed work has two steps. SMOTE is used in the initial phase to reduce the impact of data imbalance and the second phase is classifying data using Naive Bayes (NB), decision tree (DT) algorithms, and their ensembles. The experimental results demonstrate that the AdaBoost-Random Forest classifier provides 95.47% accuracy in the early detection of heart disease.

show abstract

Section: Proposed Methodologymentioning

confidence: 99%

“…In the next model, all points with greater weights are given more importance. It will continue to train models till a lower error is received [ 33 ].…”

Section: Exploratory Knowledgementioning

confidence: 99%

Section: Exploratory Knowledgementioning

confidence: 99%

“…A good classifier should have a precision of 100% (high); only when both numerator and denominator are identical, i.e., TP = TP + FP, can precision become 100% [ 33 ].…”

Section: Performance Evaluationsmentioning

confidence: 99%

See 2 more Smart Citations

AdaBoost Ensemble Methods Using K-Fold Cross Validation for Survivability with the Early Detection of Heart Disease

Mahesh

Kumar

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Regarding metrics for evaluation, image segmentation quality can be measured using a variety of measures, including the Dice coefficient, the Jaccard index, and boundary-based metrics. These metrics aid in quantifying the resemblance of segmented regions to ground truth data [19].…”

Section: Related Workmentioning

confidence: 99%