Dr. G. Narasimha Rao

https://doi.org/10.64823/ijter.2503030

The proliferation of Internet of effects bias has introduced significant cybersecurity vulnerabilities compounded by their essential interconnectedness and resource limitations. This paper proposes a robust cybersecurity frame designed to guard IoT ecosystems. Our result integrates an Autoencoder for effective point birth and anomaly discovery Deep Neural Networks(DNNs) for sophisticated deep literacy- grounded attack bracket and Decision Trees for rapid-fire, interpretable real- time trouble identification. By assaying live data from IoT bias, the system effectively detects anomalies and directly classifies different cyber pitfalls including Denial of Service(DoS) attacks and unauthorized access attempts. This multi-layered approach leverages the Autoencoder's capability to learn normal data patterns and highlight diversions while DNNs use these uprooted features to fete intricate attack autographs with high perfection. The addition of Decision Trees ensures nippy and transparent bracket critical for nimble trouble response. This intertwined system significantly improves trouble discovery capabilities and accelerates response times thereby strengthening the overall security posture of IoT networks. The proposed result offers an adaptive and visionary defense against the dynamic and evolving diapason of cyber pitfalls in the expanding IoT geography which decreasingly includes criticalcyber-physical systems(CPS) like Industrial IoT(IIoT) bias within sectors similar as heads and mileage shops integral to the dependable operation of artificial control systems(ICS) including SCADA, DCS, PLCs, and Modbus protocols.

https://doi.org/10.64823/ijter.2503025

Skin cancer remains one of the most prevalent and potentially fatal forms of cancer worldwide, highlighting the urgent need for early, accurate, and scalable diagnostic methods. This project proposes a deep learning-based solution for automated skin cancer classification using Convolutional Neural Networks (CNNs) trained on the HAM10000 dataset—a benchmark collection of dermatoscopic images representing seven distinct skin lesion types, including melanoma, basal cell carcinoma, and benign nevi. The framework incorporates robust image preprocessing techniques and a customized CNN architecture designed to optimize feature extraction and classification performance across diverse lesion categories. To further enhance model generalization and address potential class imbalance, the project explores data augmentation strategies tailored for medical imagery. A user-friendly interface, developed using Streamlit, enables real-time inference and accessibility for both clinical and non-specialist use. Experimental results demonstrate high classification accuracy and strong differentiation between malignant and benign lesions, supporting the system’s utility as a reliable, cost-effective, and accessible diagnostic aid. This work underscores the significant role of AI-powered tools in augmenting dermatological decision-making, especially in resource-constrained environments where timely diagnosis can substantially impact patient outcomes.