MUMBAI, India, Aug. 10 -- Intellectual Property India has published a patent application (202641090672 A) filed by St. Peters Engineering College on July 25, 2026, for Ai-Enhanced Signal Processing System For Real-Time Data Analysis And Adaptive Optimization.
Inventors include Mrs. M. Usha, Assistant Professor In Department Of Cse, St Peters; Mr. A Raj Kumar, Assistant Professor In Department Of Cse, St Peters Engineering College, Opposite Ts Forest Academy, Kompally Road; Ms. Panjala Chandana, Assistant Professor In Department Of Cse, St; Ms. Arukonda Srujana, Assistant Professor In Department Of; Mrs. Paidi Rajitha, Assistant Professor In Department Of Cseaiml, St; and Mr. Sai Varma, Assistant Professor In Department Of Cse, St Peters Engineering College, Opposite Ts Forest Academy Kompally Road, Dullapally, Maisammaguda, Medchal, Hyderabad, Telangana.
The application for the patent was published on July 31, 2026, under issue no. 31/2026.
Abstract: The present invention relates to an AI-Enhanced Signal Processing System for Real-Time Data Analysis and Adaptive Optimization, developed to improve the accuracy, efficiency, and adaptability of signal processing in dynamic and data-intensive environments. Conventional signal processing techniques primarily rely on static algorithms and manually configured parameters, which often result in reduced performance when processing noisy, non-stationary, and heterogeneous signal streams. The proposed invention overcomes these limitations by integrating artificial intelligence (AI), advanced digital signal processing (DSP), deep learning, and adaptive optimization into a unified framework capable of intelligent real-time signal acquisition, processing, analysis, and decision-making. The proposed system comprises a signal acquisition module, an adaptive preprocessing module, an AI-based feature extraction engine, a real-time analytics module, an adaptive optimization engine, a decision support module, and a continuous learning framework. The preprocessing module performs adaptive noise suppression, signal enhancement, normalization, and synchronization to improve signal quality. The feature extraction engine employs deep learning models, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), long short-term memory (LSTM) networks, and transformer architectures, to automatically learn meaningful temporal, spectral, and statistical features. The analytics module performs classification, anomaly detection, pattern recognition, and predictive analysis, while the adaptive optimization engine continuously refines processing parameters using machine learning-based optimization techniques to maintain robust performance under varying operational conditions. Furthermore, the invention incorporates a hybrid cloud–edge computing architecture that efficiently distributes computational tasks between edge devices and cloud servers, thereby minimizing latency, communication overhead, bandwidth consumption, and energy usage. The continuous learning framework enables autonomous model updates using newly acquired data without interrupting system operation. Consequently, the proposed invention provides a scalable, intelligent, and self-optimizing signal processing platform that significantly enhances real-time analytical accuracy, operational reliability, and decision-making efficiency across applications such as industrial automation, healthcare, IoT, smart grids, autonomous systems, wireless communications, and intelligent surveillance.
Disclaimer: Curated by HT Syndication.
