Arun Nagaraja

Arun Nagaraja

Auto-generated profile, based on publicly available information

Arun Nagaraja

Jain University, Bangalore, India

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 April 2022 in Computational Intelligence and Neuroscience
Verified
Journal Article
Open access
PDF file
MRMahesh T R
Mahesh T R
VKV. Dhilip Kumar
V. Dhilip Kumar
MAMuhammad Junaid Asghar
Muhammad Junaid Asghar
Oana GEMANOana GEMAN
Oana GEMAN
AGArulkumaran G
Arulkumaran G
NAN. Arun
N. Arun
As a result of technology improvements, various features have been collected for heart disease diagnosis. Large data sets have several drawbacks, including limited storage capacity and long access and processing times. For medical therapy, early diagnosis of heart problems is crucial. Disease of heart is a devastating human disease that is quickly increasing in developed and also developing countries, resulting in death. In this type of disease, the heart normally fails to provide enough blood to different body parts in order to allow them to perform their regular functions. Early, as well as, proper diagnosis of this condition is very critical for averting further damage and also to save patients’ lives. In this work, machine learning (ML) is utilized to find out whether a person has cardiac disease or not. Both the types of ensemble classifiers, namely, homogeneous as well as heterogeneous classifiers (formed by combining two separate classifiers), have been implemented in this work. The data mining preprocessing using Synthetic Minority Oversampling Technique (SMOTE) has been employed to cope with the imbalance problem of the class as well as noise. The proposed work has two steps. SMOTE is used in the initial phase to reduce the impact of data imbalance and the second phase is classifying data using Naive Bayes (NB), decision tree (DT) algorithms, and their ensembles. The experimental results demonstrate that the AdaBoost-Random Forest classifier provides 95.47% accuracy in the early detection of heart disease.

21 February 2020 in IEEE Access
Verified
Journal Article
Open access
ANArun Nagaraja
Arun Nagaraja
UBUma Boregowda
Uma Boregowda
KKKhalaf Khatatneh
Khalaf Khatatneh
Radha KrishnaRadha Krishna
Radha Krishna
Rajasekhar NuvvusettyRajasekhar Nuvvusetty
Rajasekhar Nuvvusetty
VKV. Sravan Kiran
V. Sravan Kiran
The fundamental objective behind any network intrusion detection system is to automate the detection process whenever intrusions occur in the network. The problem of the network anomaly detection is to determine, if the network incoming traffic is legitimate (or) anomalous. Automated detection systems designed to identify incoming anomalous traffic patterns usually apply widely used machine learning techniques. However, irrespective of any system model which is developed to identify anomalous traffic, all these models requires comparing anomalous and normal traffic patterns. Such comparisons implicitly depend on the ability of the underlying machine learning model to gauge the similarity between a known legitimate observation and the target. The efficiency of any network anomalous detection system depends on the use of distance (or) similarity measures and how they are actually applied. A novel distance function which can be applied to determine the similarity between two conditional feature pattern vectors is an important contribution of present research. Feature dimensionality is another important issue for any machine learning algorithm. In the present work, feature reduction is achieved using the proposed feature transformation technique. However, our approach for feature transformation uses the proposed gaussian distance function to achieve dimensionality reduction to represent the original input dataset in the new transformation space. We have also proposed new computation expressions for determining equivalent deviation and threshold in gaussian space. Experiments are performed on KDD and NSL-KDD datasets by considering widely applied classifier algorithms in various state-of-art research contributions. For performance validation of machine learning models, k-fold cross validation is applied by setting k to 10 through considering evaluation parameters such as accuracy, precision and recall. Experiment results have proved that our approach for anomaly detection that applies the proposed feature transformation technique proved comparatively better to detection methods CANN, GARUDA, and UTTAMA addressed in the recent research literature.

5 March 2019 in Foundations of Science
Verified
Journal Article
Closed access
PDF file
ANArun Nagaraja
Arun Nagaraja
BUB. Uma
B. Uma
GKGunupudi Rajesh Kumar
Gunupudi Rajesh Kumar

1 October 2018
Verified
Conference Paper
Open access
PDF file
ANArun Nagaraja
Arun Nagaraja
SAShadi Aljawarneh
Shadi Aljawarneh
PSPrabhakara H. S
Prabhakara H. S