A CNN-based android application for plant leaf classification at remote locations

Shelke, Ankita; Mehendale, Ninad

doi:10.1007/s00521-022-07740-1

Cited by 9 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, some researchers showed that using a single case study may narrow the scope of generalization, while multiple case studies may increase it [61]. We found in the literature that a previous penetration testing thesis also used two case studies with one tester [72,74,81,[117][118][119][120]. More than two test cases were very rare in the penetration testing domain.…”

Section: Generalizationmentioning

confidence: 90%

Overview on Case Study Penetration Testing Models Evaluation

2023

View full text Add to dashboard Cite

Model evaluation is a cornerstone of scientific research as it represents the findings' accuracy and model performance. A case study is commonly used in evaluating software engineering models. Due to criticism in terms of generalization from a single case study and testers, deciding on the number of case studies used for evaluation and the number of testers has been one of the researchers’ challenges. Multiple case studies with multiple testers can be difficult in some domains, such as penetration testing, due to the complexity and time needed to prepare test cases. This study aims to review the literature and examine the evaluation methods used pertaining to the number of case studies and testers involved. This study is beneficial for researchers, students, and penetration testers as it provides case study design steps that are useful to determine the appropriate number of test cases and testers required. The paper's findings and novelty highlight that a single case study with a single tester is enough to evaluate a model. It also strikes a balance between what is enough for the evaluation and the need to reduce criticisms of a single case study by using two case studies with a single tester. Doi: 10.28991/ESJ-2023-07-03-025 Full Text: PDF

show abstract

Section: Generalizationmentioning

confidence: 90%

Overview on Case Study Penetration Testing Models Evaluation

2023

View full text Add to dashboard Cite

show abstract

“…In addition, research on real-time plant disease detection and identification [11], [12], [13] was developed by developing a model that can be used on resource-constrained mobile devices. It can be used more easily and conveniently to including the development to use on mobile devices and work without an internet connection [14]. Currently developing or improving the model of the Convolutional Neural Network (CNN) focuses on reducing the number of parameters and computational costs of the model.…”

Section: Introductionmentioning

confidence: 99%

Improvement Classification Approach in Tomato Leaf Disease using Modified Visual Geometry Group (VGG)-InceptionV3

Thomkaew¹,

Intakosum²

2022

IJACSA

View full text Add to dashboard Cite

This paper presents a new method for optimizing tomato leaf disease classification using Modified Visual Geometry Group (VGG)-InceptionV3. Improved performance of VGG-16 model as a base model with InceptionV3 block reduced the number of convolution layers of VGG-16 from 16 to 10 layers, and added an InceptionV3 block that was improved by adding convolution layer from 3 to 4 layers to increase the accuracy of tomato leaf disease classification and reduce the number of parameters and computation time of the model. The experiments were performed on tomato leaves from the PlantVillage dataset of 10 classes, consisting of nine classes of diseased leaves and one class of healthy leaves. The results showed that the proposed method was able to reduce the number of parameters and computation time with and accuracy of tomato leaf disease classification was 99.27%. Additionally, the proposed approach was compared with state-of-the-art Convolutional Neural Network (CNN) models such as VGG16, InceptionV3, DenseNet121, MobileNetV2, and RestNet50. Comparative results showed that the proposed method had the highest accuracy in the tomato leaf disease classification and required a smaller number of parameters and computational time.

show abstract