Turning Data into Intelligent Decisions

Bridging Quantum Computing and NLP: A Novel Framework for Advanced Bias Detection with Next-Generation Computing

Processing (NLP) to address one of the most critical challenges in AI—bias detection. Traditional bias detection methods often struggle to identify subtle, context-dependent biases embedded within large-scale textual data. To overcome these limitations, the proposed Quantum Bias Detection (QBD) framework integrates quantum machine learning techniques with classical NLP models. By leveraging quantum state embeddings and quantum kernel methods, the system enhances the detection of both explicit and hidden biases with improved accuracy, precision, and sensitivity. Experimental evaluation demonstrates that the hybrid quantum-classical approach significantly outperforms conventional techniques, particularly in identifying nuanced and context-aware biases. This work highlights the transformative potential of quantum computing in building fair, transparent, and ethically responsible AI systems, contributing to the future of bias-aware NLP applications.

LogiX: AI-Driven Secure Login System with Quantum-Resistant Algorithms and Multi-Factor Authentication

LogiX is a next-generation AI-driven authentication framework designed to secure digital identities against both modern and emerging quantum-era cyber threats. The system integrates post-quantum cryptographic algorithms, including Kyber (key exchange), Dilithium (digital signatures), and NTRU (encryption), ensuring long-term resilience against quantum attacks. Beyond cryptographic security, LogiX leverages intelligent machine learning models for real-time anomaly detection, credential-sharing analysis, phishing detection, and adaptive multi-factor authentication (MFA). By combining quantum-resistant security protocols with AI-driven behavioral monitoring, the system enables proactive threat detection and dynamic risk-based authentication. Designed with scalability and cloud compatibility in mind, LogiX provides a future-proof, intelligent security architecture capable of protecting sensitive user data across distributed environments. This research demonstrates the effectiveness of integrating post-quantum cryptography with AI to build secure, adaptive, and next-generation authentication systems.

Classification Using Neural Network and Genetic Algorithm

Explores a hybrid AI approach combining neural networks and genetic algorithms to optimize model structure and weights. Addresses limitations of traditional backpropagation by improving convergence speed and classification accuracy through evolutionary optimization.

Email

abirbarman@proton.me

Phone

+91 8670321835

Location

Bengaluru, India

Response Time

Within 24 hours