No abstract

No abstract

Ovaries play a vital role in the female reproductive system as they are responsible for the production of egg or ovum required during the fertilization. The female ovaries very often get affected with cyst. An enlarged ovarian cyst can lead to torsion, infertility and even cancer. Therefore, it is very important to diagnose it as soon as possible. For the diagnosis of an ovarian cyst, ultrasound test is conducted. We collected the sample ultrasound images of ovaries of different women and detected whether ovarian cyst is present or not. The proposed work employs the traditional VGG-16 model fine-tuned with our very own dataset of ultrasound images. A VGG-16 model is a 16-layer deep learning neural network trained on ImageNet dataset. Fine-tuning is done by modifying the last four layers of VGG-16 network. Our model is able to determine whether the ultrasound images shows ovarian cyst or not. An accuracy of 92.11% is obtained. The accuracy and loss curves are also plotted for the proposed model.

Sugarcane, belonging to the grass family Poaceae, is rich in sugar sucrose, thereby used for making white sugar, jaggery and other by-products like molasses and bagasse. However, a diseased sugarcane plant is of no use, so it needs to be detected as soon as possible. A novel deep learning framework approach is proposed in this paper to detect whether a sugarcane plant is diseased or not by analyzing its leaves, stem, color, etc. The study comprises three scenarios based on different feature extractors namely Inception v3, VGG-16 and VGG-19. These are the pertained models on which different classifiers are trained. The state-of-the-art algorithms (SVM, SGD, ANN, naive Bayes, KNN and logistic regression) are compared with deep learning algorithms like neural network and hybrid AdaBoost. Several statistical measures such as accuracy, precision, specificity, AUC and sensitivity are calculated using Orange software, and the scenario having the highest accuracy is chosen. The receiver operating characteristic curve is computed in order to assess accuracy. An AUC of 90.2% is obtained using VGG-16 as the feature extractor and SVM as the classifier.

No abstract