Approaches to Training Multi-Class Semantic Image Segmentation of Damage in Concrete
This paper addresses the problem of creating a large quantity of high-quality training image segmentation masks from scanning electron microscopy (SEM) images of concrete samples that exhibit progressive amounts of degradation resulting from alkali-silica
Prevention of Cooktop Ignition Using Detection and Multi-Step Machine Learning Algorithms
This paper presents a study to examine the potential use of machine learning models to build a real-time detection algorithm for prevention of kitchen cooktop fires. Sixteen sets of time- dependent sensor signals were obtained from 60 normal/ignition
Reinforcement Learning-Based Control and Networking Co-design for Industrial Internet of Things
Industrial Internet-of-Things (I-IoT), also known as Industry 4.0, is the integration of Internet of Things (IoT) technology into the industrial manufacturing system so that the connectivity, efficiency, and intelligence of factories and plants can be
Symposium on Federally Funded Research on Cybersecurity of Electric Vehicle Supply Equipment (EVSE)
Electric vehicles are becoming common on the Nation's roads, and the electric vehicle supply equipment infrastructure (EVSE) is being created to support that growth. The NIST Information Technology Lab (ITL) hosted a one-day symposium to showcase federally
Cybercrime Losses: An Examination of U.S. Manufacturing and the Total Economy
Cybercrime puts America's competitive edge and economic future at risk; however, there is some debate as to the extent that this activity is impacting economic activity. This report examines a selection of the current estimates of U.S. losses due to
While mode selection has been envisioned as the most cost-effective way to address the interference issue in Device-to-Device (D2D) communications, existing works have been largely conducted without consideration of the energy depletion of devices. In this
Narrow Spectrum Software Testing Addressing Complexity and Trust
Combination coverage based testing supplements basic structural coverage based test selection. This provides a sound test engineering method with defensible, quantitative measures of test completeness.
Simulation Testbed for Railway Infrastructure Security and Resilience Evaluation
The last decade has seen an influx of digital connectivity, operation automation, and remote sensing and control mechanisms in the railway domain. The management of the railway operations through the use of distributed sensors and controllers and with
The More the Merrier: Adding Hidden Measurements for Anomaly Detection and Mitigation in Industrial Control Systems
Industrial Control Systems (ICS) collect information from a variety of sensors throughout the process, and then use that information to control some physical quantities. Control engineers usually have to pick which measurements they are going to use and
Streaming Batch Gradient Tracking for Neural Network Training
Faster and more energy efficient hardware accelerators are critical for machine learning on very large datasets. The energy cost of performing vector-matrix multiplication and repeatedly moving neural network models in and out of memory motivates a search
Strategic Roadmap for Interoperable Public Safety Video Analytics
Since 9/11, the Department of Homeland Security has provided over $16 billion dollars in grant assistance to secure cities and non-profit organizations against terrorist and disaster incidents. In order to meet the threat demands, public safety
Attractor selection based limited feedback hybrid precoding for uplink V2I communications
As an essential part of vehicle networks, the Vehicle to Infrastructure (V2I) needs the support of millimeter wave and massive MIMO technologies to enable high data rate applications, such as automated driving, real-time high-quality multimedia services
Auto-tuning of double dot devices it in situ with machine learning
The current practice of manually tuning quantum dots (QDs) for qubit operation is a relatively time- consuming procedure that is inherently impractical for scaling up and applications. In this work, we report on the \it in situ} implementation of a
Summary: Workshop on Machine Learning for Optical Communication Systems
Optical communication systems are expected to find use in new applications that require more intelligent and automated functionality. Optical networks are needed to address the high speeds and low latency of 5G wireless networks. The analog nature of