Dr. Gouri Sankar Nayak

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Engineering

Scopus Publications

ENHANCING BRAIN TUMOR CLASSIFICATION THROUGH ADVANCED IMAGE PROCESSING, HYBRID FEATURE EXTRACTION, MRMR FEATURE SELECTION, AND MULTICLASS CLASSIFIERS
Journal of Theoretical and Applied Information Technology, 2025
Optimizing stroke detection with genetic algorithm-based feature selection in deep learning models
Gouri Sankar Nayak, Pradeep Kumar Mallick, Dhaneshwar Prasad Sahu, Avinash Kathi, Rewat Reddy, Jahnavi Viyyapu, Nithina Pabbisetti, Sai Parvathi Udayana, Harika Sanapathi
Applied Neuropsychology Adult, 2025
Brain stroke is a leading cause of disability and mortality worldwide, necessitating the development of accurate and efficient diagnostic models. In this study, we explore the integration of Genetic Algorithm (GA)-based feature selection with three state-of-the-art deep learning architectures InceptionV3, VGG19, and MobileNetV2 to enhance stroke detection from neuroimaging data. GA is employed to optimize feature selection, reducing redundancy and improving model performance. The selected features are subsequently fed into the respective deep-learning models for classification. The dataset used in this study comprises neuroimages categorized into "Normal" and "Stroke" classes. Experimental results demonstrate that incorporating GA improves classification accuracy while reducing computational complexity. A comparative analysis of the three architectures reveals their effectiveness in stroke detection, with MobileNetV2 achieving the highest accuracy of 97.21%. Notably, the integration of Genetic Algorithms with MobileNetV2 for feature selection represents a novel contribution, setting this study apart from prior approaches that rely solely on traditional CNN pipelines. Owing to its lightweight design and low computational demands, MobileNetV2 also offers significant advantages for real-time clinical deployment, making it highly applicable for use in emergency care settings where rapid diagnosis is critical. Additionally, performance metrics such as precision, recall, F1-score, and Receiver Operating Characteristic (ROC) curves are evaluated to provide comprehensive insights into model efficacy. This research underscores the potential of genetic algorithm-driven optimization in enhancing deep learning-based medical image classification, paving the way for more efficient and reliable stroke diagnosis.
Brain image segmentation with fuzzy entropy clustering and PSO-GWO optimization techniques
Gouri Sankar Nayak, Pradeep Kumar Mallick, Neelmadhab Padhi, Manas Ranjan Mohanty, Sachin Kumar, Prasanalakshmi Balaji
Intelligent Decision Technologies, 2024
In the field of brain MRI analysis, image segmentation serves various purposes such as quantifying and visualizing anatomical structures, analyzing brain changes, delineating pathological regions, and aiding in surgical planning and image-guided interventions. Over the past few decades, diverse segmentation techniques with varying degrees of accuracy and complexity have been developed. Real-world brain MRI images often encounter intensity in homogeneity, posing a significant challenge in accurate segmentation. The prevailing image segmentation algorithms, predominantly region-based, typically rely on the homogeneity of image intensities in specific regions of interest. However, these methods often fall short of providing precise segmentation results due to intensity in homogeneity. To address these challenges and enhance segmentation performance, this paper introduce a novel objective function named Fuzzy Entropy Clustering with Local Spatial Information and Bias Correction (FECSB). Additionally, we propose a novel hybrid algorithm that combines Particle Swarm Optimization (PSO) and Grey Wolf Optimization (GWO) to maximize the effectiveness of the FECSB function in MRI brain image segmentation. The proposed algorithm undergoes rigorous evaluation using benchmark MRI brain images, including those from the McConnell Brain Imaging Center (BrainWeb). The experimental results unequivocally demonstrate the superiority of the PSO-GWO clustering method over the traditional Fuzzy C Means (FCM) method. Across various image slices, the PSO-GWO method consistently outperforms FCM in terms of accuracy, showing improvements ranging from 1.28% to 1.46%, approximately achieving 99.37% accuracy.
Deep Learning Approaches for Signal and Image Processing: State-of-the-Art and Future Directions
S Deepan, Jaideep Gera, Anupam Pareek, Sheela Chinchmalatpure, Gouri Sankar Nayak, Jagadeesh Bodapati
Proceedings of International Conference on Contemporary Computing and Informatics Ic3i 2024, 2024
Deep learning has revolutionized signal and image processing by enabling the creation of complex algorithms with many applications. This study examines deep learning signal and image processing optimization and hardware acceleration strategies. Experimentally evaluating stochastic gradient descent (SGD) and Adam optimization algorithms determines their convergence speed and effectiveness. We also examine how GPUs may accelerate model execution and deep learning inference. Our study reveals that deep learning optimization methodologies and platforms provide several practical challenges and trade-offs. This work may help signal and image processing researchers and practitioners design scalable and efficient solutions. Additionally, their methods illuminate deep learning.
State of the art of machine learning techniques: A case study on voting prediction
Role of Iot and Blockchain Techniques and Applications, 2022
Prediction Of Heart Disease and Identification of Severity Level Using Machine Learning Classifier with Android App
Gouri Sankar Nayak, Pradeep Kumar Mallick, Neelmadhab Padhi
Proceedings 2022 IEEE 2nd International Symposium on Sustainable Energy Signal Processing and Cyber Security Isssc 2022, 2022
heart diseases (HD) become one of the most dangerous diseases in the world today and the primary reason for death. In the United States, heart disease is one of the leading causes of mortality for men, women, and members of the majority of racial and ethnic groups. Despite being technologically advanced, America has yet to discover a cure for this deadly disease. Early spotting of people having heart disease may reduce the rate of disease and the mortality rate in a population. In this paper, a smart Android app using machine learning classifiers is proposed for the early detection of heart disease and the determination of its severity level. The proposed android application consists of 7 different aspects for heart disease prediction including login, signup, home, requirement, result, view, and prevention activity. Initially, the patient’s clinical data is gathered, examined, and correlated with their risk for developing clinical symptoms that could indicate heart disease. The application classifies the user's heart disease risk as high, low, or medium based on the risk factors they enter. Analyzing and correlating the data discovered a significant correlation between having heart disease and the application results in the high & low, medium & low, and medium & high categories. K-Nearest Neighbor, Logistic Regression, Random Forest, Decision Tree, Ada Boost, Gradient Boosting, and XGBoost Algorithm are used to classify heart disease. The proposed application obtains the training accuracy 92.0, testing accuracy 87.0, precision 87.0, recall 87.0 and F1-Score 87.0 for Gradient Boosting. This study aims to examine the efficiency of mobile technology in the early risk detection of heart disease.
Heart disease prediction by using novel optimization algorithm: A supervised learning prospective
Sibo Prasad Patro, Gouri Sankar Nayak, Neelamadhab Padhy
Informatics in Medicine Unlocked, 2021
Data analysis in medicine is becoming more and more frequent to clarify diagnoses, refine research methods, and plan appropriate equipment supplies according to the importance of the pathologies that appear. Artificial intelligence offers software solutions that are required to analyze the present data for optimal prediction of results. A system model is capable of several data processing algorithms for the classification of heart disease. This research work is particularly interested in the category of data. The classification allows us to obtain a prediction model from training data and test data. These data are screened by a classification algorithm that produces a new model capable of detailed data, possibly having the same classes of data through the combination of mathematical tools and computer methods. To analyze the present data to predict optimal results, we need to use the optimization technique. This research work aims to design a framework for heart disease prediction by using major risk factors based on different classifier algorithms such as Naïve Bayes (NB), Bayesian Optimized Support Vector Machine (BO-SVM), K-Nearest Neighbors (KNN), and Salp Swarm Optimized Neural Network (SSA-NN). This research is carried out for the effective diagnosis of heart disease using the heart disease dataset available on the UCI Machine Repository. The highest performance was obtained using BO-SVM (accuracy = 93.3%, precision = 100%, sensitivity = 80%) followed by SSA-NN with (accuracy = 86.7%, precision = 100%, sensitivity = 60%) respectively. The results reveal that the proposed novel optimized algorithm can provide an effective healthcare monitoring system for the early prediction of heart disease.
Design & control of low cost solar tree for optimizing a PV system
, Arun Kumar Rath, Gouri Sankar Nayak, , Dr R.K. Jena, and
International Journal of Recent Technology and Engineering, 2019
This concept shows the design and control of a solar tree PV system for charging cell phones, supplying electricity for street lighting on open urban areas and charging of electric bike on the road side when the charge is decaying. Based on the above applications, a 7 feet height-tree was built. It has three section of branches, each branches contains 5 sub stem over which leaves made of acrylic with solar panels on the top (1.5 feet × 1feet) mounted. The energy storage capacity is 30 Amp. It has 2 USB ports to connect mobile devices and two 12V-300 W electrical outlets to connect those devices to the electricity. The solar tree was designed according to the environmental conditions of Gunupur, Odisha and for optimizing the output power a flow chart with programming developed. The result was compared with the C language programme. At the last, the PV system's availability to satisfy the energetic requirements was verified. Due to population growth and energy demands, the solar energy is the 2nd best source of non conventional energy which is cause pollution free in nature. By using the concept of the series and parallel connection of panel with the help of sub branch of the main stem the efficiency of the system can be improved. As compared to normal PV system in area point of view the Solar tree becomes more efficient. There is no systematic stimulation for usage of solar panels, purely relying on individual cases of installation on different types of objects. Solar tree may be very much helpful for creating awareness about solar resource. This concept elaborates the possibility of building a solar tree in GIET campus odisha, India, covering technical, social and economic aspects. Benefits and potential drawbacks are elaborated, while special emphasis is given to the specifics of its utilization due to the geographical position of odisha and corresponding number of sunny hours/days per year.

RECENT SCHOLAR PUBLICATIONS

Enhancing brain tumor classification through advanced image processing, hybrid feature extraction, MRMR feature selection, and multi-class classifiers
GS NAYAK, PK MALLICK, B MARUTIRAO, DR NANCHE, DR NAYAK
Journal of Theoretical and Applied Information Technology 103 (13) , 2025
2025
Citations: 1
Optimizing emergency responses via disaster LSTM algorithm for social media analysis
SB SUDHA, S Dhanalakshmi, MK NAZLI, N MUSTAPHA, TEHNM ARIS, ...
Journal of Theoretical and Applied Information Technology 103 (13), 5406-4519 , 2025
2025
Citations: 1
Optimizing stroke detection with genetic algorithm-based feature selection in deep learning models
GS Nayak, PK Mallick, DP Sahu, A Kathi, R Reddy, J Viyyapu, ...
Applied Neuropsychology: Adult, 1-10 , 2025
2025
Citations: 1
Brain image segmentation with fuzzy entropy clustering and PSO-GWO optimization techniques
GS Nayak, PK Mallick, N Padhi, MR Mohanty, S Kumar, P Balaji
Intelligent Decision Technologies 18 (2), 1319-1336 , 2024
2024
Citations: 3
Prediction Of Heart Disease and Identification of Severity Level Using Machine Learning Classifier with Android App
GS Nayak, PK Mallick, N Padhi
2022 IEEE 2nd International Symposium on Sustainable Energy, Signal … , 2022
2022
Citations: 1
State of the Art of Machine Learning Techniques: A Case Study on Voting Prediction
GS Nayak, R Panigrahi, N Padhy
The Role of IoT and Blockchain, 313-323 , 2022
2022
Heart disease prediction by using novel optimization algorithm: A supervised learning prospective. Informatics in Medicine Unlocked, 26, 100696
SP Patro, GS Nayak, N Padhy
Elsevier , 2021
2021
Citations: 5
Advances in electronics, communication and computing
S Das, MK Swain, G Nayak, S Saxena, PK Mallick, AK Bhoi, GS Chae, ...
Springer, Singapore, , 2021
2021
Citations: 18
Heart disease prediction by using novel optimization algorithm: A supervised learning prospective
SP Patro, GS Nayak, N Padhy
Informatics in Medicine Unlocked 26, 100696 , 2021
2021
Citations: 138
State of the Art of Machine Learning Techniques: A Case Study on Voting Prediction
NP Gouri Sankar Nayak, Rasmita Panigrahi
The Role of IoT and Blockchain Techniques and Applications, Est. 422p w/index , 2021
2021
Design & Control of Low Cost Solar Tree for Optimizing a PV System
RKJ Arun Kumar Rath, Gouri Sankar Nayak
International Journal of Recent Technology and Engineering (IJRTE) 8 (2 … , 2019
2019
Citations: 2
Evaluation of round window accessibility for electrode insertion: validation study from two centers
N Panda, M Kameswaran, SK Patro, S Saran, G Nayak
J Otolaryngol ENT Res 8 (5), 00263 , 2017
2017
Citations: 14

MOST CITED SCHOLAR PUBLICATIONS

Heart disease prediction by using novel optimization algorithm: A supervised learning prospective
SP Patro, GS Nayak, N Padhy
Informatics in Medicine Unlocked 26, 100696 , 2021
2021
Citations: 138
Advances in electronics, communication and computing
S Das, MK Swain, G Nayak, S Saxena, PK Mallick, AK Bhoi, GS Chae, ...
Springer, Singapore, , 2021
2021
Citations: 18
Evaluation of round window accessibility for electrode insertion: validation study from two centers
N Panda, M Kameswaran, SK Patro, S Saran, G Nayak
J Otolaryngol ENT Res 8 (5), 00263 , 2017
2017
Citations: 14
Heart disease prediction by using novel optimization algorithm: A supervised learning prospective. Informatics in Medicine Unlocked, 26, 100696
SP Patro, GS Nayak, N Padhy
Elsevier , 2021
2021
Citations: 5
Brain image segmentation with fuzzy entropy clustering and PSO-GWO optimization techniques
GS Nayak, PK Mallick, N Padhi, MR Mohanty, S Kumar, P Balaji
Intelligent Decision Technologies 18 (2), 1319-1336 , 2024
2024
Citations: 3
Design & Control of Low Cost Solar Tree for Optimizing a PV System
RKJ Arun Kumar Rath, Gouri Sankar Nayak
International Journal of Recent Technology and Engineering (IJRTE) 8 (2 … , 2019
2019
Citations: 2
Enhancing brain tumor classification through advanced image processing, hybrid feature extraction, MRMR feature selection, and multi-class classifiers
GS NAYAK, PK MALLICK, B MARUTIRAO, DR NANCHE, DR NAYAK
Journal of Theoretical and Applied Information Technology 103 (13) , 2025
2025
Citations: 1
Optimizing emergency responses via disaster LSTM algorithm for social media analysis
SB SUDHA, S Dhanalakshmi, MK NAZLI, N MUSTAPHA, TEHNM ARIS, ...
Journal of Theoretical and Applied Information Technology 103 (13), 5406-4519 , 2025
2025
Citations: 1
Optimizing stroke detection with genetic algorithm-based feature selection in deep learning models
GS Nayak, PK Mallick, DP Sahu, A Kathi, R Reddy, J Viyyapu, ...
Applied Neuropsychology: Adult, 1-10 , 2025
2025
Citations: 1
Prediction Of Heart Disease and Identification of Severity Level Using Machine Learning Classifier with Android App
GS Nayak, PK Mallick, N Padhi
2022 IEEE 2nd International Symposium on Sustainable Energy, Signal … , 2022
2022
Citations: 1
State of the Art of Machine Learning Techniques: A Case Study on Voting Prediction
GS Nayak, R Panigrahi, N Padhy
The Role of IoT and Blockchain, 313-323 , 2022
2022
State of the Art of Machine Learning Techniques: A Case Study on Voting Prediction
NP Gouri Sankar Nayak, Rasmita Panigrahi
The Role of IoT and Blockchain Techniques and Applications, Est. 422p w/index , 2021
2021

Publications

Sl. No
Title of a paper Volume & Issue /DOI ISSN / ISBN/ DOI
Indexed Name of the publisher

1 Optimizing stroke detection with genetic algorithm-based feature selection in deep learning models DOI: 10.1080/23279095.2025.2516259
ISSN: 2327-9095 SCIE
Taylor & Francis
(Applied Neuropsychology: Adult)

2 Brain image segmentation with fuzzy entropy clustering and PSO-GWO optimization techniques
Issue (2024) 1319–1336
DOI 10.3233/IDT-230773 SCIE
Intelligent Decision Technologies
(IOS Press)

3 Machine Learning Based Model to Predict the Characteristics of Next
Generation Based on DNA Sequences.

Issue No. 11/2022
Application No.
20221101
3212
PATENT Indian Patent
(Patent Machine Learning Based Model To Predict The Characteristics Of Next Generation Based On Dna Sequences Filed 2022 - Vakilsearch )

4 Advanced Image Deblurring Techniques with Autoencoder-Powered Hybrid Pipelines and NAFNET Integration
Issue No. 05/2025
Application No.
202541003230 PATENT
Indian Patent

5 Enhancing Brain Tumor Classification Through Advanced Image Processing, Hybrid Feature Extraction, MRMR Feature Selection, And Multiclass Classifiers
.

1992-8645 SCOPUS Journal of Theoretical and Applied Information Technology

6 Heart Disease prediction by using novel optimization algorithm: A supervised
learning prospective.

Volume-26
ISSN: 2352-
9148
SCOPUS
Informatics in Medicine Unlocked (Elsevier)

7 Design & Control of Low-Cost Solar Tree for Optimizing a PV

RESEARCH OUTPUTS (PATENTS, SOFTWARE, PUBLICATIONS, PRODUCTS)

1. Advanced Image Deblurring Techniques with Autoencoder-Powered Hybrid Pipelines and NAfNet Integration.
Application no. 202541003230A

2. AI-Powered ensemble approach to skin lesion classification for enhanced dermatological diagnosis. Application no. 202441104752A

3. Innovative few-shot learning model for retinopathy diagnosis using eye check diab scan.
Application

4. Innovative Retinal fundus image analysis for heart attack prediction using deep learning techniques.
Application no. 202541003231 A

5. Innovative U-Net Framework for effective detection and diagnosis of lung cancer
Application no. 202441104219 A

CONSULTANCY

Non-Government Consultancy: HMIES Solution

INDUSTRY EXPERIENCE

Name of the Company
Skylark Information Technologies Pvt. Ltd, Hyderabad
Position Held
Assistant Software Engineer
Period Nov 2015 to Dec 2016