Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
14 results
Search Results
Item Feature selection using fast ensemble learning for network intrusion detection(Springer Verlag service@springer.de, 2020) Pasupulety, U.; Adwaith, C.D.; Hegde, S.; Patil, N.Network security plays a critical role in today’s digital system infrastructure. Everyday, there are hundreds of cases of data theft or loss due to the system’s integrity being compromised. The root cause of this issue is the lack of systems in place which are able to foresee the advent of such attacks. Network Intrusion detection techniques are important to prevent any system or network from malicious behavior. By analyzing a dataset with features summarizing the method in which connections are made to the network, any attempt to access it can be classified as malicious or benign. To improve the accuracy of network intrusion detection, various machine learning algorithms and optimization techniques are used. Feature selection helps in finding important attributes in the dataset which have a significant effect on the final classification. This results in the reduction of the size of the dataset, thereby simplifying the task of classification. In this work, we propose using multiple techniques as an ensemble for feature selection. To reduce training time and retain accuracy, the important features of a subset of the KDD Network Intrusion detection dataset were analyzed using this ensemble learning technique. Out of 41 possible features for network intrusion, it was found that host-based statistical features of network flow play an import role in predicting network intrusion. Our proposed methodology provides multiple levels of overall selected features, correlated to the number of individual feature selection techniques that selected them. At the highest level of selected features, our experiments yielded a 6% increase in intrusion detection accuracy, an 81% decrease in dataset size and a 5.4× decrease in runtime using a Multinomial Naive Bayes classifier on the original dataset. © Springer Nature Switzerland AG 2020.Item Designing Scalable Intrusion Detection Systems with Stacking Based Ensemble Learning(Springer Science and Business Media Deutschland GmbH, 2022) Sujan Reddy, A.S.; Akashdeep, S.; Kamath S․, S.; Rudra, B.Network Intrusion Detection Systems monitor the network traffic and reports any malicious activity. In this paper, a combination of feature engineering techniques and Ensemble Learning is proposed to build an effective Intrusion Detection System. The zero importance feature selection method is used to extract 23 features. Random forests, Feed Forward Neural Networks and Auto encoders are used as the base models and the predictions from these base models are combined using Extreme Gradient Boosting (XGB). To ensure that the proposed ensemble model is scalable as well, parallel programming is used for parallel computation of class probabilities from each model of the ensemble. The NSL-KDD dataset is used to train our models. To test our models, we use KDD+test dataset. Experimental results show that the proposed ensemble model outperforms several state-of-the-art works. The proposed parallel programming approach decreases the average prediction time of the model ensuring that the model is scalable. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.Item Fake News Detection Using Genetic Algorithm-Based Feature Selection and Ensemble Learning(Springer Science and Business Media Deutschland GmbH, 2022) Nikitha, K.M.; Rozario, R.; Pradeep, C.; Ananthanarayana, V.S.Since its conception roughly 40 years ago, the Internet has always been an unpoliced area of human interaction. This lawlessness has since been curbed with legislation, making nefarious activities on the web constitutionally punishable. However, in the case of fake news and disinformation campaigns, the responsibility of verification is placed on the reader and the publisher, and there is no easily executable legal recourse for wrongdoers. This lack of policing combined with the power of controlling popular opinion for uses such as election manipulation, slander as a form of blackmail, stock manipulation for insider trading, shielding corporate wrong-doing makes it clear that this is a problem worth solving. Furthermore, we believe that automating the process is crucial as the task requires processing a massive amount of information whilst also being free of all biases, which is not possible by a human team. This paper explores different text properties that can indicate if a newspaper article is likely to be false or real. Our novel approach makes use of an ensemble learner created using weak learners. The weak learners are further trained on selective features to make them moderate learners. Our study shows that training individual models on different sets of features extracted using genetic algorithms performs better than models trained on all features. These become moderate learners and surpass the weak learners on performance. Further, when we ensemble these moderate learners, we achieve superior results than normal ensemble learners. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.Item Machine Learning based COVID-19 Mortality Prediction using Common Patient Data(Institute of Electrical and Electronics Engineers Inc., 2022) Agrawal, S.; Patil, N.COVID-19 was declared a pandemic in 2020, and it caused havoc worldwide. The fact that it is unpredictable adds to its lethality. The world has already seen various COVID-19 infection waves, subsequent waves being even more deadly. Many patients are asymptomatic initially but suddenly develop breathing problems. More than four million people have died due to COVID-19. It is necessary to forecast a patient's likelihood of dying so that appropriate precautions can be implemented. In this study, a COVID-19 mortality prediction model which uses machine learning is proposed. Most of the current research work requires several patient features and lab test results to predict mortality. However, we suggest a simpler and more efficient technique that relies solely on X-rays and basic patient information such as age and gender. Several ensemble-based models were evaluated and compared using a variety of metrics, and the best method was able to achieve a classification accuracy of 92.6% and AUPRC of 0.95. © 2022 IEEE.Item Ensemble Learning Approach for Short-term Energy Consumption Prediction(Association for Computing Machinery, 2022) Sujan Reddy, A.; Akashdeep; Harshvardhan; Kamath S․, S.Predicting electricity consumption accurately is crucial for garnering insights and potential trends into energy consumption for effective resource management. Due to the linearity/non-linearity in usage patterns, electricity consumption prediction is challenging and cannot be adequately solved by using a single model. In this paper, we propose ensemble learning based approaches for short-term electricity consumption on an open dataset. The ensemble model is built on the combined predictions of supervised machine learning and deep learning base models. Experimental validation showed that the proposed ensemble model is more accurate and decreases the training time of the second layer of the ensemble by a factor close to ten, compared to the state-of-the-art. We observed a reduction of approximately 34% in the Root mean squared error for the same size of historical window. © 2022 Owner/Author.Item Automatic Abnormality Detection in Musculoskeletal Radiographs Using Ensemble of Pre-trained Networks(Springer Science and Business Media Deutschland GmbH, 2023) Verma, R.; Jain, S.; Saritha, S.K.; Dodia, S.Musculoskeletal disability (MSDs) defined as the injuries that affect the movement or musculoskeletal system of the human body. Over the worldwide, it is the second most cause of physical disability. Musculoskeletal disability worsens over time and can result in long-term discomfort and severe disability. As a result, early detection and diagnosis of these anomalies is essential. But the diagnosis process is very time consuming, error prone and required diagnostic professional. Deep learning algorithms have recently been applied in medical imaging that provides a robust platform with very reliable outcomes. The development of Computer Aided Detection (CAD) system extensively speed up the diagnosis process. In this paper, a weighted ensemble model has been proposed, which is the combination of three pre-trained models (DenseNet169, MobileNet, and XceptionNet). The weighted ensemble model is tested on MURA dataset, a large public dataset provided by Stanford ML Group. Our model achieved a cohen’s kappa score 0.739 with precision of 0.885 and recall of 0.854, which is higher than many existing approaches such as densenet169 and ensemble200 model. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.Item Cardiovascular Diseases Divination using Artificial Neural Network with Ensemble Models(Institute of Electrical and Electronics Engineers Inc., 2023) Pabitha, B.; Sanshi, S.; Karthik, N.Health is wealth, but nowadays, wealth is health, where humans keep running their day-to-day activities without caring about their health for various reasons. Every human being in this world suffers from one or other diseases. Recently, cardiovascular diseases like heart attacks are prevalent in all age groups. Addressing cardiovascular diseases is essential before the disease reaches a crucial stage. Nowadays, artificial intelligence algorithms have been used to detect diseases in their early stages. In this piece of writing, a model of an artificial neural network is utilised to analyze, detect and predict the likelihood of cardiovascular disease in the early stages. In this proposed work, feed forward propagation, forward the input data to learn and map the relationships between inputs and outputs, and backward propagation is used to reduce the errors in the data. Further, an ensemble learning stacked model is used to achieve high accuracy in the prediction of diseases. To verify the correctness of the model, ensemble learning to stack is executed with three different models, namely Model 1, Model 2, and Model 3, with varying sets of feature selections. The experiment results show an accuracy rate of 93% in their predictions. © 2023 IEEE.Item Dialect Identification Using Spectral and Prosodic Features on Single and Ensemble Classifiers(Springer Verlag, 2018) Chittaragi, N.B.; Prakash, A.; Koolagudi, S.G.In this paper, investigation of the significance of spectral and prosodic behaviors of speech signal has been carried out for dialect identification. Spectral features such as cepstral coefficients, spectral flux, and entropy are extracted from shorter frames. Prosodic attributes such as pitch, energy, and duration are derived from longer frames. IViE (Intonational Variations in English) speech corpus covering nine dialectal regions of British Isles has been considered, to evaluate the proposed approach. Since corpus is available in both read and semi-spontaneous modes, the influence of spectral and prosodic behavior over these datasets is distinguishably articulated. Further, two distinct classification algorithms, namely support vector machine (SVM) and an ensemble of decision trees along with the SVM are used for identification of nine dialects. Dialect discriminating information captured from both features are used for constructing feature vectors. Experiments have been conducted on individual and combinations of features. A better dialect recognition performance is observed with ensemble methods over a single independent SVM. © 2017, King Fahd University of Petroleum & Minerals.Item ELBA-NoC: Ensemble learning-based accelerator for 2D and 3D network-on-chip architectures(Inderscience Publishers, 2020) Kumar, A.; Talawar, B.Network-on-chips (NoCs) have emerged as a scalable alternative to traditional bus and point-to-point architectures, it has become highly sensitive as the number of cores increases. Simulation is one of the main tools used in NoC for analysing and testing new architectures. To achieve the best performance vs. cost trade-off, simulators have become an essential tool. Software simulators are too slow for evaluating large scale NoCs. This paper presents a framework which can be used to analyse overall performance of 2D and 3D NoC architectures which is fast and accurate. This framework is named as ensemble learning-based accelerator (ELBA-NoC) which is built using random forest regression algorithm to predict parameters of NoCs. On 2D, 3D NoC architectures, ELBA-NoC was tested and the results obtained were compared with extensively used Booksim NoC simulator. The framework showed an error rate of less than 5% and an overall speedup of up to 16 K×. © © 2020 Inderscience Enterprises Ltd.Item A Deep Ensemble Learning-Based CNN Architecture for Multiclass Retinal Fluid Segmentation in OCT Images(Institute of Electrical and Electronics Engineers Inc., 2023) Rahil, M.; Anoop, B.N.; Girish, G.N.; Kothari, A.R.; Koolagudi, S.G.; Rajan, J.Retinal Fluids (fluid collections) develop because of the accumulation of fluid in the retina, which may be caused by several retinal disorders, and can lead to loss of vision. Optical coherence tomography (OCT) provides non-invasive cross-sectional images of the retina and enables the visualization of different retinal abnormalities. The identification and segmentation of retinal cysts from OCT scans is gaining immense attention since the manual analysis of OCT data is time consuming and requires an experienced ophthalmologist. Identification and categorization of the retinal cysts aids in establishing the pathophysiology of various retinal diseases, such as macular edema, diabetic macular edema, and age-related macular degeneration. Hence, an automatic algorithm for the segmentation and detection of retinal cysts would be of great value to the ophthalmologists. In this study, we have proposed a convolutional neural network-based deep ensemble architecture that can segment the three different types of retinal cysts from the retinal OCT images. The quantitative and qualitative performance of the model was evaluated using the publicly available RETOUCH challenge dataset. The proposed model outperformed the state-of-the-art methods, with an overall improvement of 1.8%. © 2013 IEEE.