Collaborating Authors


How We Learned To Break Down Barriers To Machine Learning - AI Summary


This article is the first in a short series of pieces that will recap each of the day's talks for the benefit of those who weren't able to travel to DC for our first conference. Dr. Sephus came to AWS via a roundabout path, growing up in Mississippi before eventually joining a tech startup called Partpic. When asked, she identified access as the biggest barrier to the greater use of AI/ML--in a lot of ways, it's another wrinkle in the old problem of the digital divide. A core component of being able to utilize most common AI/ML tools is having reliable and fast Internet access, and drawing on experience from her background, Dr. Sephus pointed out that a lack of access to technology in primary schools in poorer areas of the country sets kids on a path away from being able to use the kinds of tools we're talking about. Dr. Sephus said that AWS has been hiring sociologists and psychologists to join its tech teams to figure out ways to tackle the digital divide by meeting people where they are rather than forcing them to come to the technology.

Lightning bolt extending across 3 US states sets global record

Al Jazeera

A lightning bolt that stretched for 768 kilometres (477.2 miles) across the southern United States in 2020 is the new world record holder for the longest single flash, according to the World Meteorological Organization (WMO). The mega flash extended across the states of Texas, Louisiana and Mississippi on April 29, 2020, beating the previous record set on October 31, 2018, in Brazil of 709km (440.6 miles), the United Nations agency said on Tuesday. Reporting a separate record, the WMO said a single lightning flash over Uruguay and northern Argentina on June 18, 2020, lasted 17.1 seconds, eclipsing the old-time record of 16.7 seconds. WMO has verified 2 new world records for a lightning #megaflash Longest distance single flash of 768 km (477.2 miles) across southern #USA – 60 kilometres MORE than old record Greatest duration of 17.102 seconds over #Uruguay and northern #Argentina The findings by WMO's Committee on Weather and Climate Extremes were published in the Bulletin of the American Meteorological Society.

Network and Physical Layer Attacks and countermeasures to AI-Enabled 6G O-RAN Artificial Intelligence

Abstract--Artificial intelligence (AI) will play an increasing role in cellular network deployment, configuration and management. This paper examines the security implications of AI-driven 6G radio access networks (RANs). While the expected timeline for 6G standardization is still several years out, pre-standardization efforts related to 6G security are already ongoing and will benefit from fundamental and experimental research. The Open RAN (O-RAN) describes an industry-driven open architecture and interfaces for building next generation RANs with AI control. Considering this architecture, we identify the critical threats to data driven network and physical layer elements, the corresponding countermeasures, and the research directions. The steady increase in the number of connected devices and the heterogeneous types of communications performance demands have driven the wireless business and research and development (R&D) efforts.

TIS STTR Press Release


Entitled "Trusted Sensor Integration", the Phase I STTR focuses on building both analytical/statistical and Machine Learning based models of the static and dynamic behavior of individual sensors and systems. The proposed solution uses the imperfections of the sensor in translating the physical input to a numeric output to derive a fingerprint. It will stimulate a simple cyber-physical system, e.g. an engine, to measure the sensor output, and to feed both stimulation signals and sensor outputs into an RNN. A realistic training here depends on the realistic stimulation. As stated in the original solicitation titled "Cyber Resilience of Condition Based Monitoring Capabilities", The project, carried out in collaboration between ObjectSecurity LLC and subcontractor Mississippi State University, aims for successful technology development and transition that will result in a secure CBM sensor node that can minimize human intervention and reduce the number of machinery overhauls, shorten time spent in depot for repairs, and optimize maintenance logistics by at least 50%.

US coronavirus cases surge to new heights amid youth disregard

Al Jazeera

Coronavirus hospitalisations and caseloads hit new highs in more than a half-dozen states as signs of the virus' resurgence mounted, with newly confirmed infections nationwide back near their peak level of two months ago. After trending downward for six weeks, the US caseload has been growing again for more than a week, particularly in southern and western states. Some 34,700 new cases were reported nationwide Tuesday, according to the count kept by Johns Hopkins University. The number was higher than any other day except April 9 and the record-setting date of April 24, when 36,400 cases were logged. While new cases have been declining steadily in early US hot spots, such as New York and New Jersey, several other states set single-day case records Tuesday, including Arizona, California, Mississippi, Nevada and Texas.

Artificial intelligence improves seismic analyses


The challenge to analyze earthquake signals with optimum precision grows along with the amount of available seismic data. At the Karlsruhe Institute of Technology (KIT), researchers have deployed a neural network to determine the arrival-time of seismic waves and thus precisely locate the epicenter of the earthquake. In their report in the Seismological Research Letters journal, they point out that Artificial Intelligence is able to evaluate the data with the same precision as an experienced seismologist. For precisely locating an earthquake event, it is critical to determine the exact arrival-time of the majority of seismic waves at the seismometer station (the so-called phase arrival). Without this knowledge, further accurate seismological evaluations are not possible.

How AI will impact state governments -- GCN


Why: With 58 percent of respondents to a 2018 NASCIO survey expecting artificial intelligence and machine learning to be the most impactful emerging technologies over the next three to five years, NASCIO investigates how the technology is currently being used by state governments. Findings: A recent Deloitte report outlines four uses of automation: relieving humans of day-to-day tasks; splitting up tasks to allow computers do so some work and humans to supervise; replacing work done by humans; and augmenting work to make humans more efficient or effective at their jobs. Robotic process automation is making inroads in both back-office and front-office functions, the NASCIO study finds, saving between 40 and 70 percent on labor costs and completing work with near zero error rates. The North Carolina Innovation Center, for example, is using chatbots to split up some of its help desk work, and Mississippi's citizen-facing chatbot can respond to over 100 inquiries. The Minnesota Pollution Control Agency is using AI to import real-time weather information, crunch the numbers and develop basic analysis that meteorologists review.

LiDAR and Camera Detection Fusion in a Real Time Industrial Multi-Sensor Collision Avoidance System Machine Learning

Collision avoidance is a critical task in many applications, such as ADAS (advanced driver-assistance systems), industrial automation and robotics. In an industrial automation setting, certain areas should be off limits to an automated vehicle for protection of people and high-valued assets. These areas can be quarantined by mapping (e.g., GPS) or via beacons that delineate a no-entry area. We propose a delineation method where the industrial vehicle utilizes a LiDAR {(Light Detection and Ranging)} and a single color camera to detect passive beacons and model-predictive control to stop the vehicle from entering a restricted space. The beacons are standard orange traffic cones with a highly reflective vertical pole attached. The LiDAR can readily detect these beacons, but suffers from false positives due to other reflective surfaces such as worker safety vests. Herein, we put forth a method for reducing false positive detection from the LiDAR by projecting the beacons in the camera imagery via a deep learning method and validating the detection using a neural network-learned projection from the camera to the LiDAR space. Experimental data collected at Mississippi State University's Center for Advanced Vehicular Systems (CAVS) shows the effectiveness of the proposed system in keeping the true detection while mitigating false positives.

A Framework and Method for Online Inverse Reinforcement Learning Artificial Intelligence

Inverse reinforcement learning (IRL) is the problem of learning the preferences of an agent from the observations of its behavior on a task. While this problem has been well investigated, the related problem of {\em online} IRL---where the observations are incrementally accrued, yet the demands of the application often prohibit a full rerun of an IRL method---has received relatively less attention. We introduce the first formal framework for online IRL, called incremental IRL (I2RL), and a new method that advances maximum entropy IRL with hidden variables, to this setting. Our formal analysis shows that the new method has a monotonically improving performance with more demonstration data, as well as probabilistically bounded error, both under full and partial observability. Experiments in a simulated robotic application of penetrating a continuous patrol under occlusion shows the relatively improved performance and speed up of the new method and validates the utility of online IRL.

ClickSoftware Enables Predictive Field Service - DATAVERSITY


A recent press release states, "ClickSoftware, the leading provider of field service management software, today announced significant new capabilities for Field Service Edge, its cloud-based, mobile workforce management platform designed to meet the needs of the most demanding field service organizations. This latest offering introduces new strategic capabilities that will greatly improve field service efficiency and effectiveness. Major features are: (1) Predictive field service powered by ClickSoftware's Machine Learning Cloud, which identifies data patterns to make predictions and automatically improve valuable KPIs, (2) New demand forecasting capabilities to support more accurate resource planning and schedule optimization and provide richer insights to support proper staffing.