Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
3 results
Search Results
Item Network anomaly detection using artificial neural networks optimised with PSO-DE hybrid(Springer Verlag service@springer.de, 2019) Rithesh, K.; Gautham, A.V.; Chandra Sekaran, K.Anomaly Detection is an important field of research in the present age of ubiquitous computing. Increased importance in Network Monitoring and Security due to the growing Internet is the driving force for coming up with new techniques for detecting anomalies in network behaviour. In this paper, Artificial Neural Network (ANN) model optimised with a hybrid of Particle Swarm Optimiser (PSO) and Differential Evolution (DE) is proposed to monitor the behaviour of the network and detect any anomaly in it. We have considered two subsets of 2000 and 10000 dataset size of the NSL KDD dataset for training and testing our model and the results from this model is compared with the traditional ANN-PSO algorithm, and one of the existing variants of PSO-DE algorithm. The performance measures used for the analysis of results are the training time, precision, recall and f1-score. © Springer Nature Singapore Pte Ltd. 2019.Item Anomaly-Based NIDS Using Artificial Neural Networks Optimised with Cuckoo Search Optimizer(Springer Verlag service@springer.de, 2019) Rithesh, K.Anomaly detection in network traffic is one of the major concerns for the researches and the network administrators. Presence of anomalies in network traffic could indicate a possible intrusion on the network, increasing the need for a fast and reliable network intrusion detection system (NIDS). A novel method of using an artificial neural network (ANN) optimised with Cuckoo Search Optimizer (CSO) is developed in this research paper to act as network monitoring and anomaly detection system. Two subsets of the KDD Cup 99 dataset have been considered to train and test our model, one of 2000 instances and the other of 10,000 instances, along with the complete dataset of 61,593 instances and I have compared the result with the BCS-GA algorithm and the fuzzy K-means clustering algorithm optimised with PSO in terms of precision, recall and f1-score, and the training time for the model with the selected database instances. © 2019, Springer Nature Singapore Pte Ltd.Item Prostate Cancer Grading Using Multistage Deep Neural Networks(Springer Science and Business Media Deutschland GmbH, 2023) Bygari, R.; Rithesh, K.; Ambesange, S.; Koolagudi, S.G.Prostate cancer is the second most commonly occurring cancer in men with a high incidence to mortality ratio. Accurate prostate cancer grading is the foremost step in determining the precise treatment process for the patient in preventing mortality of the patient. Currently, the grading is carried out by pathologists, which has limitation of availability super specialist doctors across world to grade it at affordable price, and non-super specialist doctor grading is error prone. This paper evades the need for an expert pathologist by proposing a novel deep learning method for automatic screening of prostate images to detect and assign a grade severity of cancer based on the images. The explainability of classification model imbibed using gradient-weighted class activation mapping (GradCAM) visualization, which generate heatmap of image, which influenced the decision of the model. The proposed method has three stages with ensemble deep neural networks to grade the prostate cancer. Firstly, a UNet is used for the segmentation of the histopathological image. Subsequently, the segmented image is overlaid on the original image, which helps underscore the most critical regions determining the grade of cancer. Finally, the overlaid image is used by an ensemble model consisting of Xception, Resnet-50, EfficientNet-b7 to predict the final grade of the histopathological image. The dataset containing 10,000 histopathological images obtained from Karolinska and Radboud that are made publicly available through the Prostate Cancer Grade Assessment Challenge hosted in Kaggle is used for training and evaluation. This method achieves a classification accuracy of 92.38% and outperforms many state-of-the-art methods. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.