Search Results - Software+and+Computing

44 Results

Sort By:

Facial Recognition Based on Converted Spiking Neural Network

Reference #: 01602 The University of South Carolina is offering licensing opportunities for Facial Recognition Based on Converted Spiking Neural Network Background: The current method for facial recognition requires a lot of computing resources (high-performance computers) which is not portable, and the accuracy is very limited. Invention Description: We...

Published: 11/15/2022 | Inventor(s): Yu Qian, Youzhi Tang

Keywords(s): deep learning, Facial recognition, mobile computing, Spiking neural networks

Category(s): Software and Computing

Computer Aided Process Planning Software

Reference #: 01611 The University of South Carolina is offering licensing opportunities for Computer Aided Process Planning Software Background: Automated Fiber Placement (AFP) is an additive manufacturing technique using strips of composite material that is employed in the manufacturing of large aerospace structures. The inherent complexity of the...

Published: 10/24/2022 | Inventor(s): Ramy Harik, Joshua Halbritter, Alex Brasington

Keywords(s): Automated Fiber Placement, Defects, Optimization, Process Planning

Category(s): Software and Computing

Methods and Procedures for Synchronization and Over-the-Air Computation

Reference #: 01615 The University of South Carolina is offering licensing opportunities for Methods and Procedures for Synchronization and Over-the-Air Computation Background: Over-the-air computation (OAC) reduces the communication latency that linearly increases with the number of devices in a wireless network for machine learning applications....

Published: 10/10/2022 | Inventor(s): Alphan Sahin

Keywords(s): federated learning, non-coherent computation, over-the-air computation, software-defined radios, sychronization

Category(s): Software and Computing, Engineering and Physical Sciences

Multimodal Retrieval and Execution Monitoring Using Rich Recipe Representation

Reference #: 01587 The University of South Carolina is offering licensing opportunities for Multimodal Retrieval and Execution Monitoring Using Rich Recipe Representation Background: The content of recipes like for preparing food or assembling furniture exist as textual or image documents which makes it difficult for machines to read, reason and...

Published: 9/14/2022 | Inventor(s): Biplav Srivastava, Vishal Pallagani, Revathy Chandrasekaran Venka, Vedant Khandelwal, Kausik Lakkaraju

Keywords(s): Multimodal representation, Recipe search and recommendation, recipes, Workflows execution

Category(s): Software and Computing

Assigning Trust Rating to AI Services Using Causal Impact Analysis

Reference #: 01617 The University of South Carolina is offering licensing opportunities for Assigning Trust Rating to AI Services Using Causal Impact Analysis Background: Today, it is very difficult for an AI user to know what the AI service is doing. This leads to users not trusting AI and most developers, who are genuine users and reuse others’...

Published: 10/7/2022 | Inventor(s): Biplav Srivastava, Kausik Lakkaraju, Marco Valtorta

Keywords(s): AI, artificial intelligence, black-box testing, causal models, fairness, rating, software testing, trust

Category(s): Software and Computing

A method for assessing disparate impact in internet markets

Reference #: 01605 The University of South Carolina is offering licensing opportunities for A method for assessing disparate impact in internet markets Background: Companies increasingly use computer algorithms to make automatic business decisions (e.g., prices) and personalize these decisions for each consumer. Algorithms, however, may unknowingly...

Published: 10/27/2022 | Inventor(s): Rafael Becerril-Arreola

Keywords(s): Algorithm Auditing, Retail Auditing

Category(s): Software and Computing, Research Tools

Over-the-Air Computation Methods Based on Balanced Number Systems for FEEL

Reference #: 01612 The University of South Carolina is offering licensing opportunities for Over-the-Air Computation Methods Based on Balanced Number Systems for FEEL Background: Federated edge learning (FEEL) is a distributed learning framework that leverages the computational powers of edge devices (EDs) and uses the local data at the EDs without...

Published: 10/24/2022 | Inventor(s): Alphan Sahin

Keywords(s): federated learning, non-coherent computation, over-the-air computation, quantization, signed-digit number system

Category(s): Software and Computing, Engineering and Physical Sciences

Routes Optimization System Based on Railroad and Street Traffic Information

Reference #: 01565 The University of South Carolina is offering licensing opportunities for Routes Optimization System Based on Railroad and Street Traffic Information Background: Current navigation systems, such as Google Maps, Apple Maps, calculates the optimal route based on the street traffic information. But still, the travelers would need to...

Published: 9/3/2022 | Inventor(s): Yu Qian, Yuche Chen

Keywords(s): delay, dynamic programming, optimal route selection, Railroad crossing blockage, street traffic

Category(s): Software and Computing, Engineering and Physical Sciences

Methods for Long-Range Federated Edge Learning with Chirp-Based Over-the-Air Computation

Reference #: 01574 The University of South Carolina is offering licensing opportunities for Methods for Long-Range Federated Edge Learning with Chirp-Based Over-the-Air Computation Background: Federated edge learning (FEEL) deploys federated learning (FL) over a wireless network, in which many edge devices (EDs) participate in training using locally...

Published: 1/3/2023 | Inventor(s): Safi Shams Muhtasimul Hoque, Alphan Sahin

Keywords(s): chirp, DFT-s-OFDM, Distributed learning, federated edge learning, LoRa, orthogonal frequency division multiplexing, over-the-air computation, peak-to-mean envelope power ratio, pulse-position modulation

Category(s): Engineering and Physical Sciences, Software and Computing

Scalable two-phase cooling plates

Reference #: 01575 The University of South Carolina is offering licensing opportunities for Scalable two-phase cooling plates Background: Two-phase cooling usually fails at relatively low heat loads due to the loss of liquid supply. For real applications, two-phase cooling technologies need to match the size of electronic components. However, the...

Published: 11/7/2022 | Inventor(s): Chen Li, Wei Chang, Enrico Santi, Bo Tian

Keywords(s): cold plate, high power device, Thermal management, Two-phase cooling

Category(s): Engineering and Physical Sciences, Software and Computing

1 2 3 4 5