Detection and classification of breast cancer types using VGG16 and ResNet50 deep learning techniques Ashwini P., Suguna N., Vadivelan N. International Journal of Electrical and Computer Engineering, 2024 Breast cancer has become a major worldwide health issue, accounting for a large portion of the mortality rate among women. As a result, the need for early detection techniques to enhance prognosis is increasing. Many techniques are being used to detect breast cancer early, and treatment outcomes are frequently favorable when the disease is detected early. Mammography is a commonly used and very successful method for identifying breast cancer among these modalities. Through additional image processing operations like resizing and normalizing, this technology allows the detection of malignant spots from mammography pictures of the affected area. The goal of our research is to improve breast cancer detection and diagnosis speed and accuracy. In this study, we investigate the use of deep learning methods, particularly the visual geometry group (VGG16) and ResNet50 models, for mammography-based breast cancer detection. We assess the performance of the VGG16 and ResNet50 models by training and testing on a mammogram dataset that consists of 322 images from the mammographic image analysis society (MIAS) dataset. The suggested models aim to classify these images into normal, benign, and malignant groupings. Our results show better performance when compared to existing approaches. The proposed methods VGG16 and ResNet50 show promising results, achieving a classification accuracy of 91.23% and 99.01% respectively.
Secure internet of battlefield from malicious software using deep eigenspace learning K. Bhargavi, N. Vadivelan, Sarangam Kodati, M. Nalini Aip Conference Proceedings, 2022 In military cases, the Internet of Things (IoT) is normally made of a variety and nodes for the Internet (e.g. Portable military jackets as well as diagnostic equipment). This IoT system and network is an important target for malicious, especially for individuals funded by the state or indeed the political entity. Malware usage is a popular access point. This paper introduces a method of huge information to install malicious on the Internet of Battlefield Items (IoBT) or the internet of military things(IoMT) through the OpCode sequence of both the system. They transform OpCodes in a vector field and implement a profound methodology for studying to distinguish hazardous and successful software. The specificity of certain suggested malware analysis strategy and the sustainable development towards injection of garbage software threats are indeed demonstrated. Finally, we have our Github malicious analysis, that they believe will help ongoing studies (e.g. to promote assessment of potential contributor to malware detection).
Detection of cyber attacks using machine learning N. Vadivelan, K. Bhargavi, Sarangam Kodati, M. Nalini Aip Conference Proceedings, 2022 Cyber security professionals pay greater regard to risk evaluation and propose techniques for mitigating. Throughout the area of cyber defense, designing successful strategies was a plan set. Machine learning also increasingly become an important concern in data protection although machine learning is successful in cyber defense. The rapid expansion in Cloud Computing, networking and evolutionary computation has been the result of unprecedented developments in computing, storage and computational technology. The planet is rapidly being digitizested - there is a growing want of comprehensive and sophisticated information security and privacy issues And Strategies to fight security threats, which are becoming more complicated. Cyber terrorism is spreading worldwide using all kinds of computer weakness. Machine learning algorithms were used to address global computer security threats such as malware detection, ransom ware recognition, fraud detection and spoofing identification. It research analyzes how cyber training is used in defense as well as offence, providing details about cyber threats on machine learning techniques and The much more popular kinds of cyber security risks are evaluated using machine learning algorithms which describe how machine learning is used for computer defence such as the identification and avoidance of attacks, vulnerability scanning and recognition and public internet risk assessment.
Covertids-an optimal intrusion detection system for covert communication International Journal of Applied Engineering Research, 2015
A multi stage security mechanism with finite automation for high secured communication in WSN International Journal of Applied Engineering Research, 2015
