“REINFORCEMENT LEARNING WITH SPATIAL APPLICATIONS”
Smart cities offer more and more real-time information
provided by sensor networks and traffic cameras. This information can be
very valuable for transportation planing and analysing user behaviour.
For instance, knowing which parking spots are currently available close
to my destination is very valuable in order to reduce the travel time
and thus, maximize the resource usage and minimize the traffic load. The
future development of this information is usually uncertain (i.e.
non-deterministic). However, algorithms for routing applications should
consider that new information will become available during travelling
along the computed path. In order to exploit the provided information to
a full extend, it is not sufficient to compute a static route or travel
plan because the optimality of the plan might degrade as the state of
the environment might consistently change.
In order to plan transportation and understand observed trajectories in
smart environments, it is necessary to compute action policies instead
of static routes. A policy provides the most promising action for all
situations and in particular, the encountered situations. Analogously,
it makes sense to understand human behaviour based on the sequence of
decisions in the encountered situations. To compute and analyse
policies, the field of reinforcement learning already provides a rich
set of tools.
Matthias Schubert’s Bio:
Matthias Schubert is a professor for Computer Science at the LMU
Munich. He is one of the founders of the Data Science Lab @LMU Munich
and a member of the Munich Competence Center for Machine Learning. His
research interests comprise spatial information systems, representation
learning and artificial intelligence in non-deterministic environments.
With the proliferation of location-aware mobile devices and the emergence of everyday analytics, geospatial technology now spans every market, crosses national boundaries, and affects every trending issue. There is no doubt that cloud-based solutions are increasing in demand, requiring next generation, customizable technology to harness multisource data and transform it into focused solutions to be consumed by users of every level. The M.App Portfolio platform is designed to create smart, lightweight, customized market applications that address unique business and industry problems by combining geospatial analytics with cloud technology, as well as enterprise-level deployment environments. These applications, known as Hexagon Smart M.Apps, link sophisticated analytics and spatial models to geospatially relevant information, conveying data about solutions through intuitive, customizable, interactive and innovative displays. In this presentation, you will see several Smart M.Apps in action to better understand how this platform is changing the way we visualize, interpret, and interact with spatial information. Learn how Hexagon Geospatial has teamed with the World Antiquities Coalition to use Smart M.App technology to track missing and stolen cultural artifacts. See how the Green Space Analyzer provides a new way for decision makers to influence policy. Understand how a Smart M.App helps count endangered species in Africa. See how Smart M.Apps address the problems of refugee camps and can be used in country-wide census. Hexagon Geospatial’s technology provides the ability to address the challenge of linking business information with multisource multi-sensor data, in near real-time to answer questions and make decisions about our dynamically changing Earth.
“Industry 4.0” is shorthand for what the World Economic Forum calls “the Fourth Industrial Revolution.” The invention of the steam engine and construction of railroads brought the first industrial revolution in the 18th century. A second industrial revolution began in the 19th century with the advent of mass production. Digital computers heralded a third industrial revolution beginning in the 1960s. Today, the drivers of Industry 4.0 include “a ubiquitous and mobile internet, smaller, cheaper, and more powerful sensors, and artificial intelligence and machine learning.” Industry 4.0 is manifest in an Internet of Things that’s connecting billions of devices, and is likely to attract trillions in spending, in the coming decade. Many IoT devices “know where they are can act on their locational knowledge.” Foresman’s and Luscombe’s proposed Second Law of Geography claims that spatially enabled things have increased financial and functional utility. This increased utility, they argue, creates the basis for a spatially enabled economy.
However, other thought leaders worry that the Fourth Industrial Revolution may threaten many of today’s workers with “technological unemployment.” Not just the IoT, but international finance, social media, other human activities generate an unprecedented and ever-increasing volume, velocity and variety of data. Some foresee that human analysts and their employers will rely increasingly on machine learning and artificial intelligence to cope with the data deluge. Many already do. A body of research by economists, tech leaders, and forward-looking historians anticipates fundamental disruption of traditional employment by increasingly capable machines. This presentation will consider the implications of the IoT, and broader trends in data-driven discovery, for GIS work and workforce development.
Currently in the United States, 15-20% of our students have dyslexia, yet our elementary school reading curriculum is not appropriate for these learners due to the fact that they, “…simply are not able to categorize the sounds of language or connect sound to meaning in the same way as other students.” (Marshall, 2013) In the early grades especially, the curriculum takes up the majority of learning time, The average elementary school spends 520 minutes per week on Language Arts, and only 352 minutes per week on math instruction. (McMurrer, 2008). This leaves students with dyslexia feeling isolated and unintelligent, ultimately losing confidence and the joy of learning. Faced with less than ideal prospects, these students are denied access to so many pathways to success and in some cases turn to a life of crime evident in the fact that 48% of our current prison population is dyslexic.
Simultaneously, these students are not exposed to subjects that many of them would excel in, namely science, math, engineering and technology, or STEM. Moskal (2014) states, “some researchers speculate that these brain differences, which result in challenges to language development, may provide dyslexic students with an advantage in STEM.” Referencing Davis and Braun (2010) in “The Gift of Dyslexia”, Moskal explains the difference between two-dimensional and three-dimensional reasoning, the latter used by many dyslexic students in problem solving. Dyslexic students are more flexible in their ability to look at problems from different angles without changing their own position, a skill which is helpful in physical science but creates reading challenges in that a change in angles quickly turns a “b” into a number of other letters.
So, what if instead of shuttling these students through the door leading to poverty, limited opportunity, and in some cases prison, we slid that door closed and opened one leading to a life filled with following their passion? Come learn how we can change the tide for these students not only so they can reach their full potential but also so that all of us can benefit. We will discuss briefly what dyslexia is before moving onto how we can better teach students from K to Workforce and do our part here in Northern Virginia to create alternative pathways to STEM excellence.
Krista K. Gauthier is the founder and Executive Director of Sliding Doors STEM & Dyslexia Learning Center, an innovative after-school program for children with dyslexia in grades 1-5. Krista first conceived of Sliding Doors (or SDSquared for short) when, as a parent of a child with dyslexia, she noticed that the access she was able to provide her daughter in both remediation and STEM enrichment was denied to so many for a variety of reasons. Also, in taking this journey with her daughter, Krista realized that people with dyslexia are uniquely suited to excel in STEM fields. She knew that helping ALL children with dyslexia reach their full potential could help us all by funneling them onto STEM pathways and encouraging them to take their place as our future innovators.
Krista has over 10 years of experience in education, both as a teacher and as a researcher in educational theory and curriculum. Krista holds a Bachelor’s Degree in Literature from Boston College and a Master’s Degree in Literature from Northeastern University. Krista used those degrees in her role as a high school English teacher in Denver Colorado and then began a PhD in Educational Anthropology at the University of Colorado Boulder with a focus on gender issues in education. At Boulder, Krista was the lead researcher on a National Science Foundation grant to help middle and high school girls pursue engineering. After taking time to raise her two daughters, Krista served as a development director for a NOVA Catholic School and most recently worked as the STEM Programs Director for a non-profit called RoboNation. Krista has taken this myriad of experiences to found and build Sliding Doors.
Title: Cloud solutions for Earth Observation in the era of Fat Data
Yonah Bromberg Gaber
Platform Developer Community Associate
Radiant Earth Foundation
Radiant Earth Foundation is a non-profit organization seeking to address the massive problem of EO data. We are actively working to aggregate the world’s open Earth imagery and provide access and education on its use to the global development community. At the center of Radiant Earth Foundation is an open technology platform that will help people discover and analyze the vast resources of Earth imagery, accelerating improved decision-making and fueling new solutions, discoveries and innovations. In support of this user-driven platform, Radiant Earth Foundation offers an integrated and robust community development program to guide people in the use of imagery, geospatial data sets and tools. This includes insights into the commercial marketplace and related policies.
With so many EO satellites in orbit today, we have far more data than users can look at with their eyes. Spaceborne imagery is a prime example of “big data” and has traditionally been processed locally on machines operated by specialists. However, the cost of cloud storage and computing has fallen dramatically in recent years. This has initiated an explosion in the use of EO data by companies and a growth in startups innovating to deliver new insights about the world around us. These large volumes of EO data and the ability to process it quickly, is changing our world. The open Radiant Earth platform allows the development of EO-based applications for users without any expertise in remote sensing or geospatial technologies.
This seminar will address cloud-based EO, the technologies being developed, and practical options for doing cloud-based remote sensing.
ASPRS Mason is hosting a drone clinic for anyone interested in learning about and how to fly drones. The clinic is free and no experience is necessary!
Dress warmly! We will have coffee, tea and hot chocolate available, along with some light refreshments.
For more info, follow ASPRS Mason on Facebook, Twitter and Instagram.