MUMBAI, India, Sept. 14 -- Intellectual Property India has published a patent application (202641107657 A) filed by Mohd Zabih Assistant Professordepartment Of Cseaiml; and Dr B V Srinivasulu Associate Professor Department Of Cseaiml on September 08, 2026, for Cognitive Sight: An Adaptive Neuro-Visual Digital Human Framework For Autonomous Visualization Optimization.
Inventors include . Ch Prasanthi Assistant Professor Department Of Cse; Koppula Dennis Assistant Professor Department Of Acse; Kankanala Umalatha Assistant Professor Department Of Cseaiml; Adedla Anilkumar Assistant Professordepartment Of Cseaiml; . Dr Kanigiri Suresh Associate Professor Department Of Cseaiml; Komali Siddamshetti Assistant Professordepartment Of Cse; and G Janardhan Assistant Professor Department Of Cseaiml.
The application for the patent was published on September 11, 2026, under issue no. 37/2026.
Abstract: The increasing complexity of data visualization systems has created a demand for intelligent frameworks capable of understanding human visual cognition and automatically improving visualization quality. This paper introduces CognitiveSight, an adaptive neuro-visual digital human framework that emulates human perception, attention, and cognitive reasoning during visualization assessment. Unlike conventional visualization evaluation techniques that rely on static metrics, the proposed system integrates gaze prediction, cognitive workload estimation, semantic understanding, and reinforcement learning to continuously optimize visual representations. The framework employs a Digital Human Visual Agent (DHVA) that simulates human viewing behavior across multiple iterations of visualization refinement. A hybrid architecture combining Vision Transformers (ViT), Cognitive Attention Networks (CAN), and Deep Reinforcement Learning (DRL) enables the system to predict user attention, identify comprehension bottlenecks, and autonomously redesign visual elements. Experimental evaluation conducted on scientific, business, and healthcare datasets demonstrates improvements in visual clarity, user engagement, information retention, and decision-making accuracy. Results indicate a 21.8% enhancement in visualization comprehension and a 17.4% reduction in cognitive workload compared with existing visualization design approaches
Disclaimer: Curated by HT Syndication.
