Search Results - computational+science+and+engineering

27 Results Sort By:
Arterial Pulse Waveform Sensing System with Automatic Bridge-Offset Calibration and Super Class-AB Output Stage
RPI ID: 2019-088-401 Innovation Summary: A system is disclosed for sensing arterial pulse waveforms using a resistive bridge sensor with integrated offset calibration circuitry. The calibration system includes dual current digital-to-analog converters (IDACs), successive approximation registers (SARs), and a comparator that adjusts compensation currents...
Published: 3/10/2026   |   Inventor(s): Yu-Pin Hsu, Zemin Liu, Mona Hella
Keywords(s): arterial pressure, artery pulse waveform, Blood pressure, Blood pressure monitoring, ECG, electrocardiogram, monitor
Category(s): Computational Science and Engineering
Patient Protection and Monitoring System
RPI ID: 2019-052-401 Innovation Summary: This system introduces a sensor module for patient monitoring that uses time-of-flight (TOF) sensors to generate elevation maps of a patient room. These maps are analyzed to determine distance and velocity vectors of room occupants, enabling classification of activities as acceptable or unacceptable. The system...
Published: 3/10/2026   |   Inventor(s): Robert, Jr. Karlicek, Richard Radke, Arunas Tuzikas, Claire Karlicek
Keywords(s): Healthcare Systems, machine-learning, Occupancy, Patient Safety, Privacy, Sensing, Time of Flight
Category(s): Computational Science and Engineering
HOME: High-Order Mixed-Moment-based Embedding for Representation Learning
RPI ID: 2023-002-301, 2023-002-401 Innovation Summary: This technology introduces a novel embedding framework for representation learning that leverages high-order mixed statistical moments to capture complex data relationships. The system enhances feature extraction by encoding richer structural and distributional information from input data. It...
Published: 3/10/2026   |   Inventor(s): Chuang Niu, Ge Wang
Keywords(s): Artificial Intelligence, deep learning, self-supervised reapresentation learning
Category(s): Computational Science and Engineering
Multicopter online rotor fault diagnosis system
RPI ID: 2022-019-301, 2022-019-401 Innovation Summary: This system introduces an online fault diagnosis platform for multicopter rotor systems, enabling real-time detection of rotor anomalies during flight. It utilizes sensor data and diagnostic algorithms to monitor rotor performance and identify faults without interrupting operation. The system is...
Published: 3/10/2026   |   Inventor(s): Airin Dutta, Farhan Gandhi, Fotios Kopsaftopoulos
Keywords(s): aircraft, data-based modeling, fault detection, fault diagnosis, low-cost sensors, machine-learning, multicopters, UAV, VTOL
Category(s): Computational Science and Engineering
Task-Oriented Deep Learning Image Denoising
RPI ID: 2022-015-201 Innovation Summary: A deep learning-based image denoising method tailored to specific tasks such as segmentation or classification. Unlike generic denoising, it preserves features critical to downstream analysis. The model adapts its strategy based on the intended application, improving performance in real-world scenarios. It is...
Published: 3/10/2026   |   Inventor(s): Jiajin Zhang, Hanqing Chao, Ge Wang, Pingkun Yan
Keywords(s): Artificial Intelligence, deep learning, Image Denoising, image quality, medical imaging
Category(s): Computational Science and Engineering
Decorrelation Mechanism and Dual Neck Autoencoders for Deep Learning
RPI ID: 2022-018-201 Innovation Summary: A dual-neck autoencoder architecture is introduced to improve feature separation and reduce redundancy in deep learning models. The decorrelation mechanism embedded in the encoder layers enhances generalization by minimizing overlap in learned representations. This design allows for more effective training in...
Published: 3/10/2026   |   Inventor(s): Christopher Wiedeman, Ge Wang
Keywords(s): Adversarial Attacks, Attack Transferability, computer vision, Decorrelation, deep learning
Category(s): Computational Science and Engineering
Slow-light incorporated Si modulators for RF photonic applications
RPI ID: 2022-020-301, 2022-020-401 Innovation Summary: The disclosed system introduces slow-light photonic modulators that enhance RF photonic signal processing by leveraging engineered dispersion to reduce group velocity within integrated photonic circuits. This slowed propagation increases the interaction time between optical and RF signals, improving...
Published: 3/10/2026   |   Inventor(s): Stephen Anderson, Amir Begovic, Zhaoran Huang
Keywords(s): RF photonics, SFDR, silicon modulator
Category(s): Computational Science and Engineering
Stationary Multi-source AI-powered Real-time Tomography (SMART) for Dynamic Cardiac Imaging
RPI ID: 2022-011-201 Innovation Summary: The SMART system uses 29 fixed source-detector pairs arranged on a circular track to perform real-time tomography without mechanical rotation. AI algorithms reconstruct high-resolution 3D images from simultaneous multi-angle data. This architecture improves temporal resolution and reduces wear compared to rotating...
Published: 3/10/2026   |   Inventor(s): Weiwen Wu, Yan Xi, Ge Wang
Keywords(s): cardiac Imaging, computed tomography (CT), deep learning, image reconstruction, Multi-Source, preclinical imaging, real-time
Category(s): Computational Science and Engineering
Lift Enhanced Wing from Aft Rotor Induced Suction
RPI ID: 2022-052-301 Innovation Summary: An aircraft lift enhancement system is disclosed that integrates airfoils with rotors positioned strategically behind and below the trailing edge of the wing. The rotor placement is optimized to reduce aerodynamic interference and improve lift during VTOL and low-speed flight. The system includes symmetrical...
Published: 3/10/2026   |   Inventor(s): Farhan Gandhi, Richard Healy
Keywords(s): aerospace, eVTOL, Interactional Aerodynamics, Rotorcraft
Category(s): Computational Science and Engineering
Self-Supervised Representation Learning Through Multi-Segmental Discriminative Coding
RPI ID: 2022-058-301, 2022-058-401 Innovation Summary: This invention introduces a self-supervised representation learning (SSRL) system that utilizes multi-segmental informational coding to enhance data representation. The SSRL circuitry includes transformer-based components designed to process input data without requiring labeled examples. By leveraging...
Published: 3/10/2026   |   Inventor(s): Ge Wang, Chuang Niu
Keywords(s): Artificial Intelligence, deep learning, self-supervised reapresentation learning
Category(s): Computational Science and Engineering
1 2 3