Learn more about UC TechAlerts – Subscribe to categories and get notified of new UC technologies

Browse Category: Computer > Software


[Search within category]

Pain Assessment Method And Apparatus For Patients Unable To Self Report Pain

Though pain assessment is a crucial part of many medical treatment plans, most physicians rely on patients self-reporting their own pain levels. This self-reporting strategy may be convenient to some patients trying to determine whether the patient should get to a doctor, but in some situations, especially where a patient is non-communicative or incapacitated, these patients may be unable to clearly express themselves to a medical professional. As such, researchers at UCI have developed a novel device that automatically and objectively monitors a patient’s pain levels by tracking/monitoring subconscious facial movements in real-time.

“EchoCV”: A Web-Based Fully Automated Echocardiogram Interpretation System

Echo-CV is a novel, fully-automated system for analyzing images obtained from an echocardiogram that can be deployed on the web.

System and Method for Flexible Low-Energy Membrane-Based Liquid Purification

UCLA researchers in the Department of Chemical and Biomolecular Engineering have developed a platform and method for membrane-based water purification and desalination that combines operational flexibility with energy efficiency, allowing effective treatment and desalination of raw feed water over a wider range of solute concentrations and product recovery.

Automatic Recognition Of Anatomical Coverage In Medical Images

UCLA researchers in the Department of Radiology have developed an algorithm for automated processing of medical images.

Boundary Learning Optimization Tool

UCLA researchers in the Department of Mechanical Engineering have developed a computational tool that rapidly identifies material designs with optimal performance.

Local Binary Pattern Network (LBPN)

Convolutional Neural Networks (CNN) have had a notable impact on many applications. Modern CNN architectures such as AlexNet, VGG, GoogLetNet, and ResNet have greatly advanced the use of deep learning techniques into a wide range of computer vision applications. These gains have surely benefited from the continuing advances in computing and storage capabilities of modern computing machines. Memory and computation efficient deep learning architectures are an active area of research in machine learning and computer architecture. Model size reduction and efficiency gains have been reported by selectively using binarization of operations in convolutional neural networks that approximate convolution by reducing floating point arithmetic operations. 

DeepSign: Digital Rights Management in Deep Learning Models

As society becomes more and more complicated, we have also developed ways to analyze and solve some of these complexities via the convergence of the fields of artificial intelligence, cognitive science and neuroscience. What has emerged is the development of machine learning, which allows computers to improve automatically through experience. Thus, developers working on artificial intelligence (AI) systems have come forth to align AI with machine-learning algorithms to cover a wide variety of machine-learning problems. The most advanced of these are called supervised learning methods which form their predictions via learned mapping, which can include decision trees, logistic regression, support vector machines, neural networks and Bayesian classifiers. More recently, deep networks have emerged as multilayer networks involved in a number of applications, such as computer vision and speech recognition. A practical concern in the rush to adopt AI as a service is the capability to perform model protection: AI models are usually trained by allocating significant computational resources to process massive amounts of training data. The built models are therefore considered as the owner’s intellectual property (IP) and need to be protected to preserve the competitive advantage.

Automated Activity Classification Of Video From Body Worn Cameras

UCLA researchers in the Department of Mathematics have developed an approach to classify different ego-motion categories from body-worn video.

Closure-Tree: An Index Structure for Graph Queries

A graph comparison technique that can support both subgraph and similarity queries.

Virtual Reality Training Tasks Used For Stroke Rehabilitation

UCLA researchers in the Department of Mechanical and Aerospace Engineering have developed a set of virtual reality training tasks that can be used for rehabilitation for post-stroke patients.

Trainable Filter Emulator For Real-Time Control Systems

Researchers led by Dr. Cong from the Department of Computer Science at UCLA have developed an algorithm that enables real-time control in brain-machine interface applications.

Provably Secure Virus Detection

Professor Rafail Ostrovsky in the Department of Computer Science, in collaboration with researchers at Georgia Institute of Technology, has developed a provably secure defense against software viruses that can be deployed on computers without any additional hardware requirements.

An Implantable Electrocorticogram (ECoG)-Brain-Computer Interface System for Restoring Lower Extremity Movement and Sensation

A fully implantable brain-computer interface (BCI) with onboard processing to control a robotic gait exoskeleton as a walking aid for individuals with chronic spinal cord injury (SCI). This technology would alleviate SCI patient’s dependence on wheel chairs, reducing the risk of secondary medical complications that account for an estimated $50 billion/year in healthcare costs.

Automatic Personal Daily Activity Tracking

Researchers at UCI have developed an entirely unobtrusive method for chronicling and analyzing an individual’s daily activities over time, which relies on tracking user activity via their smartphone. This technology has important applications in health and behavior monitoring, where it can be used to signal the early stages of various diseases and disorders.

Automated Debugging for Data-Intensive Scalable Computing

UCLA researchers in the Department of Computer Science have developed BIGSIFT, a new faulty data localization approach that combines insights from automated fault isolation in software engineering and data provenance in database systems to find a minimum set of failure-introducing inputs.

Cloud based platform for display and analysis of image time series

Current microscopy systems commonly used in biomedical research labs and companies generate large amounts of large data, known as image stacks. There is currently no easy, streamlined way to store, organize and analyze these datasets on a cloud. Researchers at UCI have developed a software consisting of a cloud-based data management and analysis platform that make visualization and analysis of large image stacks simpler and faster.

Anisotropic Elastoplasticity For Codimensional Frictional Contact

UCLA researchers in the Department of Mathematics and Department of Computer Science have developed a novel hybrid Lagrangian/Eulerian approach to simulate frictional contact in thin codimensional elastic objects, such as cloth, hair, and knit. It allows a more smooth and vivid animation of those objects with faster speed and higher robustness.

Platform for predicting a compound’s cardioactivity

The invention is a platform that combines a screening system and machine learning algorithms to investigate and report the cardio-activity related information of a certain compound. Through screening cardiac tissue strips, the platform determines whether a compound is cardio-active or not, as well as the associated cardio-active mechanism based on a drug library that is automatically developed. Such information is crucial for the drug development process, especially for evidence based decisions.

A simple, accurate and inexpensive device pointing system using head tilt gesturing

Current device pointing systems, which control the movement of cursors on screens, suffer from several drawbacks which often preclude their use by individuals with special needs or medical conditions. This UCI invention describes a simple, inexpensive “head mouse” that, in combination with proprietary software, tracks the position of the head relative to the body, allowing for full control of a pointing device.

Predictive Optimization Of Pharmeceutical Efficacy

UCLA researchers in the Department of Mechanical and Aerospace Engineering have developed a machine learning platform to virtually screen combinatorial drug therapies.

Reducing Computational Complexity of Training Algorithms for Artificial Neural Networks

Researchers at UCLA have developed a novel mathematical theorem to revolutionize the training of large-scale artificial neural networks (ANN).

GPS-Based Miniature Oceanographic Wave Measuring Buoy System

Oceanic monitoring helps coastal communities, economies, and ecosystems thrive. The coastlines and open oceans prove to be very important to maritime countries for recreation, mineral and energy exploitation, shipping, weather forecasting and national security. As solar power, GPS, and telecomm improvements have been made, directional wave buoys have emerged and set the standard in wave monitoring. Non-directional and directional wave measurements are of high interest to users because of the importance of wave monitoring for successful marine operations. Wave data and climatological information derived from the data are also used for a variety of engineering and scientific applications.

Automated Reconstruction Of The Cardiac Chambers From MRI

This is a fast, fully automated method to accurately model a patient’s left heart ventricle via machine learning algorithms.

ParBreZo - a rapid, high-resolution flood inundation modeling software

By mid-century, flooding is predicted to cause annual losses of $52 billion. The ParBreZo v.8.0 software developed at UCI can predict flood inundation at better than 30 feet resolution, and within a short span of time. These predictions will help plan and prepare for future floods, respond intelligently to on-going flooding, and learn from past floods.

Anchor Based Sequence Clustering Algorithm for Efficient & Accurate Motif Discovery

A new strategy for speeding up motif discovery, an anchor based sequence clustering algorithm (ASC) that works significantly faster and with greater accuracy than current motif finding algorithms.

  • Go to Page: