Browsing by Author "Jepkoech, J."

Now showing 1 - 4 of 4

A Backward Regressed Capsule Neural Network for Plant Leaf Disease Detection
(Science Publications, 2022) Jepkoech, J.; Kenduiywo, B. K.; Mugo, D. M.; Too, E. C.
This study investigated the introduction of backward regression coupled with DenseNet features in a Capsule Neural Network (CapsNet) for plant leaf disease classification. Plant diseases are considered one of the main factors influencing food production and therefore fast crop disease detection and recognition are important in enhancing food security interventions. CapsNets have successfully been adopted for plant leaf disease classification however, backpropagation of signals to preceding layers is still a challenge due to low gradient flow. In addition, parameter and computational complexities exist due to complex features. Therefore, this study implemented a loop connectivity pattern to improve gradient flow in the convolution layer and backward regression for feature selection. We observed a 99.7% F1 score with backward regression and 87% F1 score without backward regression accuracy on testing our framework based on the standard Plant Village (PV) dataset comprising ten tomato classes with 9080 images. Additionally, CapsNet with backward regression showed relatively higher and stable accuracy when sensitivity analysis was performed by varying testing and training dataset percentages. In comparison Support Vector Machines (SVM), Artificial Neural Networks (ANN), AlexNet, ResNet, VGGNet, Inception V3, and VGG 16 deep learning approaches scored 84.5, 88.6, 99.3, 97.87, 99.14, and 98.2%, respectively. These findings indicate that the introduction of backward regression of features in the CapsNet model may be a decent and, in most cases superior and less expensive alternative for phrase categorization models based on CNNs and RNNs. Therefore, the accuracy of plant disease detection may be enhanced even further with the aid of the fusion of several classifiers and the integration of a backward regressed capsule neural network.
Exploring Entropy Pruning Coupled with Capsule Neural Network (Caps net) For Leaf Disease Classification.
(2022) Jepkoech, J.; Too, E. C.; Mugo, D.
In an attempt to detect plant leaf diseases faster, accurately, and more efficiently, researchers have adopted deep learning methods using models like CNN and CapsNet with some success. However, there is a need for improvement as the current models are computationally expensive in terms of time and model complexity. Our work improves the Capsule Neural Network(CapsNet) model by adding convolutional layers to collect enough data and prune using the Entropy-based method. Entropy-based pruning reduces the number of characters in the model by getting rid of useless features and retaining only the useful features for detection. This considerably reduces the parameter size and reduces model complexities in terms of time and computation. We used F1, F5, and varying folds to assess accuracy in pruned mode against normal models. We tested our idea using 9080 images of tomatoes from PlantVillage and on three models, namely; ResNet-50, VGG-16, and CapsNet. CapsNet was the best among the pruned models with 98.9% followed by ResNet-50 with 93% and VGG-16 at 89.99%. We observed that pruning might be a Superior and less computationally expensive method than VGG-16 and ResNet-50. This implies that the accuracy of such models can be improved through the introduction of pruning.
Exploring Entropy pruning coupled with Capsule Neural Network(CapsNet) for leaf disease classification
(2022-03) Jepkoech, J.; Mugo, D.; Too, E.C.; ; ;
In an attempt to detect plant leaf diseases faster, accurately, and more efficiently, researchers have adopted deep learning methods using models like CNN and CapsNet with some success. However, there is a need for improvement as the current models are computationally expensive in terms of time and model complexity. Our work improves the Capsule Neural Network(CapsNet) model by adding convolutional layers to collect enough data and prune using the Entropy-based method. Entropy-based pruning reduces the number of characters in the model by getting rid of useless features and retaining only the useful features for detection. This considerably reduces the parameter size and reduces model complexities in terms of time and computation. We used F1, F5, and varying folds to assess accuracy in pruned mode against normal models. We tested our idea using 9080 images of tomatoes from PlantVillage and on three models, namely; ResNet-50, VGG-16, and CapsNet. CapsNet was the best among the pruned models with 98.9% followed by ResNet-50 with 93% and VGG-16 at 89.99%. We observed that pruning might be a Superior and less computationally expensive method than VGG-16 and ResNet-50. This implies that the accuracy of such models can be improved through the introduction of pruning.
The Effect of Adaptive Learning Rate on the Accuracy of Neural Networks
(2021) Jepkoech, J.; Too, E. C.; Kenduiywo, B. K.; Mugo, D. M.
Learning rates in gradient descent algorithms have significant effects especially on the accuracy of a Capsule Neural Network (CNN). Choosing an appropriate learning rate is still an issue to date. Many developers still have a problem in selecting a learning rate for CNN leading to low accuracies in classification. This gap motivated this study to assess the effect of learning rate on the accuracy of a developed (CNN). There are no predefined learning rates in CNN and therefore it is hard for researchers to know what learning rate will give good results. This work, therefore, focused on assessing the effect of learning rate on the accuracy of a CNN by using different learning rates and observing the best performance. The contribution of this work is to give an appropriate learning rate for CNNs to improve accuracy during classification. This work has assessed the effect of different learning rates and came up with the most appropriate learning rate for CNN plant leaf disease classification. Part of the images used in this work was from the PlantVillage dataset while others were from the Nepal database. The images were pre-processed then subjected to the original CNN model for classification. When the learning rate was 0.0001, the best performance was 99.4% on testing and 100% on training. When the learning rate was 0.00001, the highest performance was 97% on testing and 99.9% on training. The lowest performance observed was 81% accuracy on testing and 99% on training when the learning rate was 0.001. This work observed that CNN was able to achieve the highest accuracy with a learning rate of 0.0001. The best Convolutional Neural Network accuracy observed was 98% on testing and 100% on training when the learning rate was 0.0001.