I served as Principal of SJCE (Sri Jayachamarajendra College of Engineering), Mysuru and also Principal of JSS Academy of Technical Education, NOIDA. I have close to 37 years of experience in teaching, working in the IT industry as well as research. Guided 9 PhD scholars and have 72 publications. Earlier I was special officer at VTU e-learning and contributed to new technologies such as Video Streaming across campus networks and mobile learning way back in 2010. These have become routine technologies today.
I was a visiting professor at the department of Electronics Engineering , Korea University, SEOUL and visiting foreign Scholar at Hannan University, Osaka, Japan. I have delivered more than 200 talks at various institutions and universities both in India as well as abroad. Served as expert member of National board of accreditation , New Delhi, Member of expert panel to procure Digital Interactive board, NPIU, New Delhi, besides serving as member of academic council of UPTU,
EDUCATION
BE - UoM Mysore
ME - IISC Bangalore
PhD - IISc Bangalore
RESEARCH INTERESTS
Major research focus has been on machine learning algorithms and architectures which I started in 1993 while at IISc. Over the past three decades, I continued to apply new ideas in developing improved dynamic learning algorithms for Radial Basis Function Neural Networks. AI and ML
A Comparative Study of Existing Machine Learning Approaches for Parkinson's Disease Detection Gunjan Pahuja, T. N. Nagabhushan IETE Journal of Research, 2021 Parkinson's disease (PD) has affected millions of people worldwide and is more prevalent in people, over the age of 50. Even today, with many technologies and advancements, early detection of this disease remains a challenge. This necessitates a need for the machine learning-based automatic approaches that help clinicians to detect this disease accurately in its early stage. Thus, the focus of this research paper is to provide an insightful survey and compare the existing computational intelligence techniques used for PD detection. To save time and increase treatment efficiency, classification has found its place in PD detection. The existing knowledge review indicates that many classification algorithms have been used to achieve better results, but the problem is to identify the most efficient classifier for PD detection. The challenge in identifying the most appropriate classification algorithm lies in their application on local dataset. Thus, in this paper three types of classifiers, namely, Multilayer Perceptron, Support Vector Machine and K-nearest neighbor have been discussed on the benchmark (voice) dataset to compare and to know which of these classifiers is the most efficient and accurate for PD classification. The Voice input dataset for these classifiers has been obtained from UCI machine learning repository. ANN with Levenberg–Marquardt algorithm was found to be the best classifier, having highest classification accuracy (95.89%). Moreover, we compared our results with those obtained by Resul Das [“A comparison of multiple classification methods for diagnosis of Parkinson Disease,” Expert Systems and applications, vol. 37, pp 1568–1572, 2010].
Tool Condition Monitoring Using Artificial Neural Network Models Srinivasa P. Pai, Nagabhushana T. N. Research Anthology on Artificial Neural Network Applications, 2021 Tool wear is a major factor that affects the productivity of any machining operation and needs to be controlled for achieving automation. It affects the surface finish, tolerances, dimensions of the workpiece, increases machine down time, and sometimes performance of machine tool and personnel are affected. This chapter deals with the application of artificial neural network (ANN) models for tool condition monitoring (TCM) in milling operations. The data required for training and testing the models studied and developed are from live experiments conducted in a machine shop on a widely used steel, medium carbon steel (En 8) using uncoated carbide inserts. Acoustic emission data and surface roughness data has been used in model development. The goal is for developing an optimal ANN model, in terms of compact architecture, least training time, and its ability to generalize well on unseen (test) data. Growing cell structures (GCS) network has been found to achieve these requirements.
Early detection of parkinson's disease by using SPECT imaging and biomarkers Gunjan Pahuja, T. N. Nagabhushan, Bhanu Prasad Journal of Intelligent Systems, 2020 Precise and timely diagnosis of Parkinson’s disease is important to control its progression among subjects. Currently, a neuroimaging technique called dopaminergic imaging that uses single photon emission computed tomography (SPECT) with 123I-Ioflupane is popular among clinicians for detecting Parkinson’s disease in early stages. Unlike other studies, which consider only low-level features like gray matter, white matter, or cerebrospinal fluid, this study explores the non-linear relation between different biomarkers (SPECT + biological) using deep learning and multivariate logistic regression. Striatal binding ratios are obtained using 123I-Ioflupane SPECT scans from four brain regions which are further integrated with five biological biomarkers to increase the diagnostic accuracy. Experimental results indicate that this investigated approach can differentiate subjects with 100% accuracy. The obtained results outperform the ones reported in the literature. Furthermore, logistic regression model has been developed for estimating the Parkinson’s disease onset probability. Such models may aid clinicians in diagnosing this disease.
Congestion Avoidance and Delay Minimization in Energy Aware Routing of Dynamic ieee 802.11s WMN: Wireless Mesh Networks Under Mobility Conditions S.P. Shiva Prakash, T.N. Nagabhushan, Kirill Krinkin Cognitive Analytics Concepts Methodologies Tools and Applications, 2020 Minimization of delay in collecting the data at any base stations is one of the major concerns in cluster based Wireless Mesh Networks. several researches have proposed algorithms to control congestion considering static nature of a node. Mobility of a node results in high congestion due to frequent link breakages and high energy consumption due to re-establishment of route during routing process. Hence, the authors consider dynamic nodes with single hop inside the static cluster. The proposed model includes four modules namely, Cluster head selection, slot allocation, slot scheduling and data collection process. the cluster head selection is based on the maximum energy, number of links and link duration. Slot allocation is based on the available energy () and the required energy (). Slot scheduling is carried out based on the link duration. Data at the base station will be collected as they are scheduled. Model is tested using Network Simulator-3 (NS3) and results indicate that the proposed model achieves least delay besides reducing the congestion compared to the existing methods.
A curvature-norm based centroid initialized distance regularized level sets for nuclear segmentation in histopathological images P.M. Shivamurthy, T.N. Nagabhushan, Vijaya Basavaraj Biomedical and Pharmacology Journal, 2018 Nuclear pleomorphism is considered to be one of the most significant shape based feature adapted in grading the cancer through the pathological studies of the H&E stained tissue slides. Microscopic study of manually extracting the feature is highly laborious and misleads the pathologists during grading. Digitization of the slides has given rise to various segmentation approaches to extract the nuclei shape to assess the degree of pleomorphism. Here, a novel approach of initializing and evolving the distance regularized level sets (DRLS) for the detection and segmentation of the nuclei has been presented. In this work, two major objectives have been achieved. First, a novel geometric approach has been devised for the detection of centroids of each nuclei in the occluded region and second, a shape prior model has been presented for the extraction of gradient information through morphological operations. The multiple level set implementation of the DRLS contours are initialized using the centroids detected and driven through the gradient computed. The proposed method has been experimented over the images of benign and malignant breast cancer tissue obtained from BeakHis dataset. A quantitative analysis of the results have shown that a 97% of object detection accuracy and 78% of overlap resolution has been achieved through the proposed model. A comparative study with that of geodesic active contours have indicated an improvement in the segmentation accuracy measure of 9-10 pixel difference.
Preface Communications in Computer and Information Science, 2018
Cluster based approach to minimize delay in energy aware routing for ieee 802.11s Wireless Mesh Networks under mobility conditions S. P. Shiva Prakash, T. N. Nagabhushan, Kirill Krinkin Conference of Open Innovation Association Fruct, 2017 Minimization of delay in data collection at base station is one of the major concerns in cluster based Wireless Mesh Network. There exists few other techniques for the cluster head selection in wireless mesh network such as selecting a node with maximum energy as a cluster head. In this work, We consider dynamic nodes with single hop topology with in the static cluster. To minimize the delay that occurs in transmission and reception of data, the proposed model includes four modules namely, Cluster head selection, slot allocation, slot scheduling and data collection process. In proposed model, cluster head selection is based on the maximum energy, number of links and link duration. Link duration is considered in order to avoid the link breakage that occurs before the transmission of data. Slot allocation is based on the available energy [E avail) and the required energy (E req). Slot scheduling is carried out based on the link duration. A node with minimum link duration will be given higher priority to avoid re-transmission that indirectly results in minimization of delay. Data at the base station will be collected as they are scheduled. Mathematical model of the proposed model is presented in this work and it shows that proposed model minimizes delay compared to the existing there by improving network efficiency.
Failure diagnosis and prognosis of rolling-element bearings using artificial neural networks: A critical overview International Journal of COMADEM, 2013
A comparative study of feature projection and feature selection approaches for Parkinson's disease detection and classification using T1-weighted MRI scans G Pahuja, TN Nagabhushan, B Prasad International Journal of Biomedical Engineering and Technology 38 (1), 65-80 , 2022 2022 Citations: 3
A comparative study of existing machine learning approaches for Parkinson's disease detection G Pahuja, TN Nagabhushan IETE Journal of Research 67 (1), 4-14 , 2021 2021 Citations: 205
Tool Condition Monitoring Using Artificial Neural Network Models SP Pai, TN Nagabhushana Handbook of Research on Emerging Trends and Applications of Machine Learning … , 2020 2020 Citations: 2
Congestion Avoidance and Delay Minimization in Energy Aware Routing of Dynamic ieee 802.11 s WMN: Wireless Mesh Networks Under Mobility Conditions SPS Prakash, TN Nagabhushan, K Krinkin Cognitive Analytics: Concepts, Methodologies, Tools, and Applications, 164-193 , 2020 2020 Citations: 2
Early detection of Parkinson’s disease by using SPECT imaging and biomarkers G Pahuja, TN Nagabhushan, B Prasad Journal of Intelligent Systems 29 (1), 1329-1344 , 2019 2019 Citations: 35
Early Detection of Parkinson’s Disease by Using SPECT Imaging and Biomarkers B Prasad, TN Nagabhushan, G Pahuja 2019
A morphologically driven gradient and marker controlled distance regularised level sets for nuclear segmentation in histopathological images PM Shivamurthy, TN Nagabhushan, B Prasad, V Basavaraj International Journal of Signal and Imaging Systems Engineering 11 (5), 300-309 , 2019 2019
A Curvature-Norm Based Centroid Initialized Distance Regularized Level Sets for Nuclear Segmentation in Histopathological Images PM Shivamurthy, TN Nagabhushan, V Basavaraj Biomedical and Pharmacology Journal 11 (3), 1335-1343 , 2018 2018
Cognitive Computing and Information Processing: Third International Conference, CCIP 2017, Bengaluru, India, December 15-16, 2017, Revised Selected Papers TN Nagabhushan, VNM Aradhya, P Jagadeesh, S Shukla, C ML Springer , 2018 2018
A Combined Expectation Maximization and Marker Controlled Watershed Driven Distance Regularized Level Sets for Nuclear Segmentation in Histopathological Images PM Shivamurthy, TN Nagabhushan, V Basavaraj International Journal of Computer Applications 975, 8887 , 2018 2018
Year of Publication: 2018 AR Ulle, TN Nagabhushan, N Manoli 2018
Early detection of Parkinson's disease through multimodal features using machine learning approaches G Pahuja, TN Nagabhushan, B Prasad, R Pushkarna International Journal of Signal and Imaging Systems Engineering 11 (1), 31-43 , 2018 2018 Citations: 16
Cluster based approach to minimize delay in energy aware routing for ieee 802.11 s Wireless Mesh Networks under mobility conditions SPS Prakash, TN Nagabhushan, K Krinkin 2016 19th Conference of Open Innovations Association (FRUCT), 189-195 , 2016 2016 Citations: 1
On improving energy saving in IEEE 802.11 s wireless mesh networks under mobility conditions SPS Prakash, TN Nagabhushan, K Krinkin 2016 Second International Conference on Cognitive Computing and Information … , 2016 2016 Citations: 4
A novel GA-ELM approach for Parkinson's disease detection using brain structural T1-weighted MRI data G Pahuja, TN Nagabhushan 2016 second international conference on cognitive computing and information … , 2016 2016 Citations: 33
An Integrated curvature and Convex Hull based concave point detection in Histopathological images AR Ulle, TN Nagabhushan, N Manoli, V Basavaraj 2016 Second International Conference on Cognitive Computing and Information … , 2016 2016
A foreground marker based centroid initialized Geodesic active contours for histopathological image segmentation PM Shivamurthy, TN Nagabhushan, V Basavaraj 2016 Second International Conference on Cognitive Computing and Information … , 2016 2016 Citations: 4
An ensemble approach to detect exudates in digital fundus images BV Shilpa, TN Nagabhushan 2016 Second International Conference on Cognitive Computing and Information … , 2016 2016 Citations: 9
Automated crop prediction based on efficient soil nutrient estimation using sensor network K Lokesh, J Shakti, S Wilson, MS Tharini, TN Nagabhushan National Conference on Product Design (NCPD 2016) , 2016 2016 Citations: 8
Automated Water flow Control System A Hegde, TS Gopi Kiran, D Deepthi, TN Nagabhushan, SPS Prakash, ... National Conference on Product Design (NCPD 2016) , 2016 2016 Citations: 6
MOST CITED SCHOLAR PUBLICATIONS
A comparative study of existing machine learning approaches for Parkinson's disease detection G Pahuja, TN Nagabhushan IETE Journal of Research 67 (1), 4-14 , 2021 2021 Citations: 205
Failure diagnosis and prognosis of rolling-element bearings using Artificial Neural Networks: A critical overview BKN Rao, PS Pai, TN Nagabhushana Journal of Physics: Conference Series 364 (1), 012023 , 2012 2012 Citations: 58
Flank wear estimation in face milling based on radial basis function neural networks P Srinivasa, TN Nagabhushana, PK Ramakrishna Rao The International Journal of Advanced Manufacturing Technology 20 (4), 241-247 , 2002 2002 Citations: 36
Early detection of Parkinson’s disease by using SPECT imaging and biomarkers G Pahuja, TN Nagabhushan, B Prasad Journal of Intelligent Systems 29 (1), 1329-1344 , 2019 2019 Citations: 35
A novel GA-ELM approach for Parkinson's disease detection using brain structural T1-weighted MRI data G Pahuja, TN Nagabhushan 2016 second international conference on cognitive computing and information … , 2016 2016 Citations: 33
Biometric authentication & identification through behavioral biometrics: A survey G Pahuja, TN Nagabhushan 2015 International Conference on Cognitive Computing and Information … , 2015 2015 Citations: 29
Tool wear estimation using resource allocation network PS Pai, TN Nagabhushana, PKR Rao International Journal of Machine Tools and Manufacture 41 (5), 673-685 , 2001 2001 Citations: 27
Tool condition monitoring using acoustic emission, surface roughness and growing cell structures neural network S Pai, TN Nagabhushana, RBKN Rao Machining science and technology 16 (4), 653-676 , 2012 2012 Citations: 22
Coherency identification using growing self organizing feature maps [power system stability] TN Nababhushana, KT Veeramanju Proceedings of EMPD'98. 1998 International Conference on Energy Management … , 1998 1998 Citations: 22
Early detection of Parkinson's disease through multimodal features using machine learning approaches G Pahuja, TN Nagabhushan, B Prasad, R Pushkarna International Journal of Signal and Imaging Systems Engineering 11 (1), 31-43 , 2018 2018 Citations: 16
Coherency identification using growing self organizing feature maps TN Nagabhushana, KT Veeramanju International conference on energy management and power delivery 19998, 113-116 , 1998 1998 Citations: 11
Power-saving routing algorithms in wireless mesh networks: a survey TN Nagabhushan, SPS Prakash, K Krinkin 2012 11th Conference of Open Innovations Association (FRUCT), 107-115 , 2012 2012 Citations: 10
Radial basis function neural networks for tool wear condition monitoring PS Pai, TN Nagabhushana, PKR Rao, RBKN Rao 2002 Citations: 10
An ensemble approach to detect exudates in digital fundus images BV Shilpa, TN Nagabhushan 2016 Second International Conference on Cognitive Computing and Information … , 2016 2016 Citations: 9
Energy aware power save mode management in wireless mesh networks SPS Prakash, TN Nagabhushan, K Krinkin 14th Conference of Open Innovation Association FRUCT, 122-131 , 2013 2013 Citations: 9
Automated crop prediction based on efficient soil nutrient estimation using sensor network K Lokesh, J Shakti, S Wilson, MS Tharini, TN Nagabhushan National Conference on Product Design (NCPD 2016) , 2016 2016 Citations: 8
Adaptive fault diagnosis of large interconnected power networks using genetic algorithms TN Nagabhushana, HS Chandrasekharaiah Journal of the Indian Institute of Science 77 (1), 95 , 1997 1997 Citations: 7
Automated Water flow Control System A Hegde, TS Gopi Kiran, D Deepthi, TN Nagabhushan, SPS Prakash, ... National Conference on Product Design (NCPD 2016) , 2016 2016 Citations: 6
Fault diagnosis of AC and AC-DC systems using constructive learning RBF neural networks TN Nagabhushana 2012 Citations: 6
Classification of Symbolic Objects Using Adaptive Auto-Configuring RBF Neural Networks TN Nagabhushan, H Ko, J Park, SK Padma, YS Nijagunarya 2007 International Symposium on Information Technology Convergence (ISITC … , 2007 2007 Citations: 5
