Papers by Narendra Kumar Rao
Detection of Partially Occluded Area in Images Using Image Segmentation Technique
Lecture notes in networks and systems, 2024
Brain Interaction Assessment Using EEG Source Localization
Advances in medical diagnosis, treatment, and care (AMDTC) book series, May 31, 2024
Demystifying explainable artificial intelligence (EAI)
Institution of Engineering and Technology eBooks, Nov 15, 2023
Speech Emotion Recognizer Using CNN
Facial Landmarks Detection System with OpenCV Mediapipe and Python using Optical Flow (Active) Approach
2023 3rd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE)
Convolutional Neural Network Model for Traffic Sign Recognition
2023 3rd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE)
Sparsely Supervised Learning for Medical Image Classification on Noisy Heterogeneous Data
2023 3rd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE)
A Wellness Mobile Application for Smart Health
IGI Global eBooks, Jun 30, 2023
Neural Networks based Object Detection Techniques in Computer Vision
2022 4th International Conference on Inventive Research in Computing Applications (ICIRCA)
EAI Endorsed Transactions on Pervasive Health and Technology
The early detection of Alzheimer's disease, a neurodegenerative ailment that affects both cog... more The early detection of Alzheimer's disease, a neurodegenerative ailment that affects both cognitive and social functioning, can be accomplished using deep learning technology. Deep learning is more accurate and efficient than human diagnosis in detecting functional connectivity and changes in the brain networks of people with MCI. Early detection of Mild Cognitive Impairment (MCI) can reduce the disease's development. However, achieving high accuracy levels is difficult due to the dearth of reliable biomarkers. The dataset was picked up from the Kaggle database. It contains magnetic resonance images of the brain, each image being unique and in different stages of the disease for classification purpose for our project, as it was most suitable for our project’s needs. We developed a deep learning model using learning AZ net, Dense net, Resnet, Efficient Net and Inception Net with a maximum accuracy of 99.96% for classifying Alzheimer's disease stages and early detection us...
ML Approaches to Detect Email Spam Anamoly
2022 International Conference on Data Science, Agents & Artificial Intelligence (ICDSAAI)
Email Spamming has been recognized as one of the most dangerous cyber-attacks these days. As emai... more Email Spamming has been recognized as one of the most dangerous cyber-attacks these days. As email is more encouraging platform for the communication mechanism these days, it is accessible to everyone across the world with the help of internet. Hence it has to be protected in order to reduce the cyber-attacks which involve loss of organizational property. The previous spam-filtering technologies include humanly detection of certain keywords and blocking the spam-sending domains which are recognizable. Spamming of emails is on the rise as the number of internet users grows, resulting in the leakage of personal information from users. Thus, detecting these email spams is critical in order to reduce illegal and unethical behavior, as well as phishing and fraud. As a result, ongoing research into email spam detection has been conducted utilizing a variety of machine learning algorithms with varying levels of accuracy. Using the required techniques of machine learning in this project, the regular words which are used in spam emails are easily identified using the preoccupied data set called stop-words. This proposed system tries to recognize a recurrent word group which are used mostly that are classed as spam using machine learning techniques. The machine learning model that has been using is an earlytrained model with feedback that can tell the difference between a correct and an ambiguous output.
Virtual Alphabet Recognition using Deep Convolution Neural Networks
2022 4th International Conference on Inventive Research in Computing Applications (ICIRCA)
Movie Recommendation System using Machine Learning
2022 4th International Conference on Inventive Research in Computing Applications (ICIRCA)
Fine-tuning for Transfer Learning of ResNet152 for Disease Identification in Tomato Leaves
Smart innovation, systems and technologies, Nov 14, 2022
Text Recognition from Images Using Deep Learning Techniques
Smart innovation, systems and technologies, Nov 14, 2022
Object detection techniques for real-time applications
Institution of Engineering and Technology eBooks, Sep 8, 2022
An Unbiased Privacy Sustaining Approach Based on SGO for Distortion of Data Sets to Shield the Sensitive Patterns in Trading Alliances
Smart Intelligent Computing and Applications, 2018
Distribution of data in the organizations which are having cooperative business is a common scena... more Distribution of data in the organizations which are having cooperative business is a common scenario for getting the benefits in the business. Modern technology in data mining has permitted to extract the unknown patterns from the repositories of enormous data. On the other hand, it raises problem of revealing the confidential patterns when the data is shared to the others. Privacy-preserving data mining is an emerging area for the research in the domain of security to deal with the need privacy for concerns of confidential patterns. The original database is to be transformed to conceal the confidential patterns. Along with concealing the confidential patterns, another important parameter that is to be addressed is attaining the balance between privacy and utility of the database which are generally inversely proportional to each other. Another challenging aspect in the transformation process is reducing the side effects, miss cost, and false rules that may occur by mining the transformed database. In this paper, a new method has been projected for concealing of association rules that are sensitive by carefully selecting the transactions for transformation using computational intelligence technique social group optimization. The outcome of the proposed approach is measured against the existing techniques based on computational intelligence methods to demonstrate the comparison of side effects with the proposed method.
Automated Detection of Skin Lesions Using Back Propagation Neural Network
Smart innovation, systems and technologies, Nov 14, 2022
International Journal of Innovative Technology and Exploring Engineering, 2019
A printed circuit board without connecting with any components called as a bare PCB. Consider a P... more A printed circuit board without connecting with any components called as a bare PCB. Consider a PCB as a basic part which has been settled with more electronic units. In order to display the manufacturing process, the drawbacks have been taken by PCB individually. The reflection of this separation process impacts the performance of the circuits. Also, we have examined about classification methodologies as well as referential based PCB detection. From the input images, the needed and related information has been pulled out using image processing methodologies by the referential based PCB detection. Comparing with the un-defected PCB images, this was used to find out the defects. To meet the goal of the PCB defect detection, several feature extraction and pre-processing methods are derived in this article. The PCB defects have been classified by those features using the machine learning algorithms. Moreover, several types of machine learning algorithms are derived in this article. Thi...
Improved Precision in Regression Testing through Ranking of Program Execution Sequence Items in Clustering Based Test Suite Selection
Uploads
Papers by Narendra Kumar Rao