Non-Linear Hybrid Random Projection Techniques for High-Dimensional Data
CoI: Dr.Hasan Masrur
High-dimensional data poses a serious challenge in areas like image monitoring, smart logistics, and AI/ML-based optimization. As the number of features grows, data becomes sparse and computational demands increase, making real-time analysis difficult and often inefficient. Traditional dimensionality reduction methods, such as Principal Component Analysis, struggle to capture the nonlinear patterns present in complex data, while faster alternatives, like Random Projection (RP), may distort important structures. This can negatively affect the performance of downstream tasks such as classification, clustering, and anomaly detection.
To address these issues, we propose a novel method: Nonlinear Hybrid Random Projection (NHRP). By combining the strengths of both linear and nonlinear techniques, NHRP effectively reduces dimensionality while preserving the underlying geometry of the data. This leads to improved efficiency and accuracy, making it ideal for AI-enhanced analytics in Smart Logistics Solutions, including transportation, predictive maintenance, and supply chain optimization.
