Big Data

New scalable computing technique will make analyzing Big Data easier

Teresa Donnellan — Tue, 17 Sep 2024 20:23:22 +0000

New scalable computing technique will make analyzing Big Data easier Teresa Donnellan Tue, 09/17/2024 - 16:23

In This Story

With the advancement of data collection techniques, there has been an exponential increase in the availability and complexity of datasets, particularly spatiotemporal data; finding the computing power to analyze such Big Data, however, has remained a challenge for many researchers in various fields. Through a collaborative research project funded by the National Science Foundation, ��AV statistics professor Lily Wang hopes to change that.

Professor Lily Wang, Department of Statistics, College of Engineering and Computing. Photo by Creative Services

Wang and the Chair of the Department of Statistics at The George Washington University, Huixia Judy Wang, are developing a form of scalable, distributed computing that could lessen the power demand on any single computer by distributing the analysis across a network of computers.

“In the past, we knew there were insights hidden in the data, but due to computing limitations, we couldn’t access them,” said Lily Wang. “Now, with scalable quantile learning techniques, we can gain a deeper understanding of the entire data distribution and extract insights into variability, outliers, and tail behavior, which are critical for more informed decision-making.”

Spatial and temporal data are increasingly being used in such research areas as climate study and health care, among others, noted Lily Wang.

“This data richness presents a lot of opportunities for getting deep insights into dynamic patterns over time and space; but it also brings many, many challenges,” said Wang. Large datasets often exhibit heterogeneous and dynamic patterns, requiring new approaches to capture meaningful relationships.

This project uses two large datasets: the National Environmental Public Health Tracking Network database from the Centers for Disease Control and Prevention and the outdoor air quality data repository from the Environmental Protection Agency.

“Both datasets have been challenging to analyze in the past due to their size and complexity,” explained Wang. “But through scalable and distributed learning techniques, we’re now able to handle large-scale heterogeneous data across the entire United States.”

One of the project's major innovations is the use of distributed computing to divide the data into smaller, manageable regions. Each region is analyzed separately, and the results are efficiently aggregated to form a comprehensive understanding of the entire dataset.

“You can think of it like dividing the U.S. into small regions, analyzing each one separately, and then combining the results to create a comprehensive national analysis,” Wang said. “This method allows us to analyze millions of data points simultaneously without the need for supercomputers.”

Beyond its goals for technical advancements, the project also emphasizes training the next generation of data scientists. Graduate students at George Mason and The George Washington will gain hands-on experience working with real-world data, helping to develop new computational methods.

The project began on September 1, 2024, and is expected to last three years. It has already garnered attention, including recognition from the office of Congressman Gerry Connolly (D-VA).

The potential applications of this research are far-reaching, from improving air quality predictions to understanding public health trends and beyond. Wang explained, "This work empowers researchers and policymakers to leverage vast amounts of data to address rising societal issues more effectively.”

Topics

Department of Statistics

Statistics Faculty

Computational statistics

Big Data

big data analytics

Research Interests: Nonstationary Time Series Analysis; Spectral Analysis; Nonparametric Statistics; Big Data; Bayesian Data Analysis; Applications in Medicine

Research

Professor applies statistics and AI to land use modeling and real estate pricing

Teresa Donnellan — Wed, 29 May 2024 16:18:12 +0000

Professor applies statistics and AI to land use modeling and real estate pricing Teresa Donnellan Wed, 05/29/2024 - 12:18

In This Story

Abolfazl Safikhani

��AV statistics professor Abolfazl Safikhani recently applied his cutting-edge, interdisciplinary research to analyzing land use dynamics and property pricing shifts over time, work that underscores the transformative potential of data-driven insights, especially in urban planning and real estate.

Safikhani earned bachelor’s and master’s degrees in mathematics before earning a doctorate in statistics.

“I decided to do a PhD in statistics because throughout the master’s I had become more and more interested in connecting real world problems to data. And I'm very happy that I made that decision,” he said.

Abolfazl Safikhani

Along with a former colleague at the University of Florida in the urban planning department, Safikhani applied machine learning techniques to a dataset comprising millions of land parcels in Florida. The two endeavored to decipher the intricate dynamics of land use transformations over time and predict future developments with unprecedented accuracy. Their predictions surpassed 98% accuracy.

But the team didn't stop with successful predictions. They recognized the importance of understanding the underlying mechanisms driving these predictions. With the addition of a new collaborator, Tianshu Feng in George Mason’s Systems Engineering and Operations Research Department, the researchers aim to present their land use analysis software as explainable artificial intelligence (XAI). By elucidating the black box of machine learning algorithms, Safikhani hopes local government decision-makers and urban planners can confidently leverage the software to optimize resource allocation effectively.

Another of Safikhani’s projects considers land use and value specifically concerning the price of residential real estate. Safikhani’s own experience buying real estate in Fairfax County, Virginia, in 2022, inspired this project. When he asked his real estate agent to estimate a fair price of a certain house, the agent came back with an estimate based on the price of three comparable local properties that had recently sold. Ever a “quant guy,” Safikhani said, he thought there could be a better way: applying the idea of transfer learning.

“The big idea of transfer learning is, within your big data set, try to find areas that have similar dynamics to your area of interest. And then use that similarity to improve your prediction,” Safikhani explained. “So, imagine that there is a little neighborhood somewhere in DC or somewhere in Maryland or somewhere in California that has dynamics very similar to the specific neighborhood where you want to buy a house in Northern Virginia. Once you account for some changes, let's say, regulations and things that are different, then the remaining dynamics are their similarities.”

He continued, “If you only use your neighborhood, you can have three data points. If you use another, similar neighborhood, it's going to be 20. If you use neighborhoods from other places over the 50 states of the U.S., you may end up getting a thousand data points.”

Safikhani is working with a colleague from the University of California – Los Angeles to bring in funding to develop this pricing software. Their preliminary results show the benefit of their proposed model versus current pricing systems.

Safikhani's research is poised to revolutionize sectors like urban planning and real estate. In fact, his research has attracted the attention of startups keen to translate his findings into real estate–disrupting tools.

“It seems there's actually a growing interest in having such AI tools that would understand land use development and then really match it with pricing,” he said. “And sooner or later, this [technology] is going to come out. Platforms like Zillow are doing a good job, but there's much more that can be done.”

Topics

Applied Statistics

Department of Statistics

Statistics Faculty

Computational statistics

Big Data

big data analytics

real estate entrepreneurship

Artificial Intelligence

Research

Big data may lead to safer roadways, lower emissions

Teresa Donnellan — Mon, 23 Oct 2023 16:26:19 +0000

Big data may lead to safer roadways, lower emissions Teresa Donnellan Mon, 10/23/2023 - 12:26

In This Story

Shanjiang Zhu

Anand Vidyashankar

Once, transportation officials made decisions based on household surveys performed roughly once per decade, which asked selected households to record their travel behavior on a given day. With the advent of smartphones, similar data became available roughly every few minutes. Now, with an increasing number of connected vehicles on the road, that data is available in nearly real time. CEIE professor Shanjiang Zhu is embracing this shift, exploring the capabilities of researchers with this massive amount of data.

With funding from the Virginia Department of Transportation (VDOT), Zhu and his research team, Anand N. Vidyashankar from the department of statistics and Chenfeng Xiong from the Civil and Environmental Engineering department at Villanova University, will reconcile the travel data from three different sources—surveys, smartphones, and connected vehicles—into invaluable travel information.

"In the past, we tried to understand travel behavior, which is critical for future investment decisions and also transportation policy, based on survey data,” Zhu explained. “Based on that, you understand, on average, where people have traveled, in what mode, with whom, and spent how much time there, uh what is the purpose for the trip, etc. Using that information, you can develop a model that basically can predict future scenario, like how congested the network could be in 2040; and that drives all the investment decisions and policy debates.” This method introduces problems of timeliness, as it can skip major events such as the COVID-19 pandemic, and human error, as people would not necessarily remember every detail of their travel on a given day.

The introduction of widespread smartphone use about ten years ago made the available data much denser, said Zhu, resulting in about one data point every three to five minutes. Each time a person’s smartphone app calls for location service, their location is automatically registered. Nevertheless, this method introduced a bias problem, as not everyone owns a smartphone and not everyone uses them often.

About a year ago, Zhu’s team won a competition hosted by VDOT to make the best possible use of connected vehicle data, basically newer vehicles like those with an “SOS” button installed. One drawback to the data currently is connected vehicles currently make up a relatively small share of vehicles on the road.

“But we have ways to make corrections from a statistical perspective, and then this gives you a much more accurate picture of traffic on the road,” said Zhu, adding “On average, it's one data point every three seconds. With such data, the accuracy and timeliness of travel demand models could be greatly improved.” Zhu noted his colleague Vidyashankar will be reviewing the data fusion to ensure a rigorous statistical approach.

The new data also opens the door for new safety studies, Zhu said, adding safety studies are currently based mainly on police reports after an accident has occurred. By using alternate data, such as how often a car’s brake deceleration rate exceeds a certain threshold or how hard a driver turns the steering wheel, dangerous locations might be addressed before an accident occurs. Zhu is interested in exploring the topic further using the dataset resulting from his current project.

Zhu foresees data from connected vehicles becoming increasingly important as more and more people adopt the technology. He said, “Now we are investing in the methodology part and seeing how we can make this connection more productive, to improve the driving environment, to make our roads safer, to make the driving experience better, and also to reduce our energy consumption and emissions."

Topics

Department of Civil Environmental and Infrastructure Engineering (CEIE)

transportation engineering

Big Data

big data analytics

Transportation Policy Operations and Logistics

Research

CEC faculty research

NSF CAREER Award funds faculty member’s mission to expand cloud’s capabilities

Anonymous — Tue, 15 Jun 2021 13:03:49 +0000

NSF CAREER Award funds faculty member’s mission to expand cloud’s capabilities Anonymous (not verified) Tue, 06/15/2021 - 09:03

In This Story

Yue Cheng

Social media platforms and dozens of other web and mobile apps generate countless amounts of data. And with a constant flux of data comes a continuous need for high-performance and highly scalable ways to store and access this data. Yue Cheng, an assistant professor in the Department of Computer Science, won a National Science Foundation CAREER Award to meet the needs of the big data industry.

Cheng and his research team will use the nearly $580,000 award “Harnessing Serverless Functions to Build Highly Elastic Cloud Storage Infrastructure” to develop a scalable and cost-effective cloud computing storage system using serverless computing.

“We are researching new ways of using emerging serverless computing capabilities to build a high-performance cloud storage infrastructure,” says Cheng. “Serverless computing is the next generation of cloud.”

Cheng’s new infrastructure, InfiniStore, will reduce the cost and need for manual storage management, says Cheng.

Conventional cloud computing uses virtual machines (VM) that are rented out to cloud users. “The user pays for whatever resources they need, and while it gives great flexibility, the VM-based model isn’t the most effective nor elastic. Cloud service providers still charge for space and capacity that is reserved but not in use. Cloud users also must manually start or stop virtual machines to best suit their needs.”

Serverless computing is the solution to cost and resource issues under the conventional VM model. Because of its inherent elasticity, it can scale up and down autonomously. Since it doesn’t require a space reservation, like with VMs, Cheng can implement a new cloud storage pricing model based on usage.

“Let’s say at one point in time there are no requests, and no cloud function is launched. And a later point in time, there is a huge spike in data access requests. The elastic storage would automatically trigger thousands of cloud functions, each serving as a tiny little data storage unit, to serve this spike of data access requests, and the cloud user is only charged when the data stored in cloud functions are accessed,” says Cheng.

Cheng’s project includes collaborations with industry leaders like NetApp and IBM Research and fellow researchers at Mason. In addition to the development of InfiniStore, the grant also consists of an educational plan centered around teaching serverless computing and increasing access for undergraduate students to participate in leading research.

“We will design a new cloud service called InfiniCloud, which is a digital and interactive notebook service that allows students and educators to implement, write, and deploy serial and parallel Python programs at any scale,” says Cheng. “We will also start an outreach plan to promote diversity in computing and engage undergraduate students in computing research.”

Cheng stresses the importance of advancing computing capabilities and allowing students and educators access too. “This project will support big data storage, which is extremely important, but I am also committed to introducing undergrad students to this state-of-the-art field in cloud computing,” says Cheng.

“Yue’s NSF CAREER Award comes at a time of nearly universal reliance on cloud services to support critical enterprise functions. His research will realize significant improvements in the ways that cloud resources are allocated to end-users, through innovations in cloud storage technology,” says Department of Computer Science Chair David Rosenblum. “And the educational plan he has devised will give Mason students significant hands-on learning opportunities with this important area of computing technology.”

Topics

cloud computing

Big Data

Awards

Mason offers new Data Analytics Credential to prepare students for careers in big data

Anonymous — Thu, 11 Mar 2021 16:47:33 +0000

Mason offers new Data Analytics Credential to prepare students for careers in big data Anonymous (not verified) Thu, 03/11/2021 - 11:47

In This Story

Liza Wilson Durant

Brett Hunter

��AV is offering a new Data Analytics Credential to help undergraduates hone their skills in handling big data.

The new credential is the second one offered in partnership with the Greater Washington Partnership’s Capital CoLAB. Mason launched the Digital Technology Credential in 2019 to support additional skills in data analysis, visualization, and cybersecurity for non-engineers. More than 150 students are currently enrolled in that program.

“The new Data Analytics Credential will enable hundreds of Mason students to offer their specialized data analytics skills to employers who are seeking to meet the talent shortfall in data science and analytics,” says Liza Wilson Durant, associate dean for strategic initiatives and community engagement for the Volgenau School of Engineering.

Liza Wilson Durant says the new credential is an exciting showcase of our industry partners engaging with students from multiple disciplines. Photo by Evan Cantwell.

The credential focuses on data storage and management and will make students more marketable, including for jobs as data analysts and data scientists, says Brett Hunter, associate chair of the Department of Statistics.

The credential is designed for undergraduates in statistics, computing, information technology, and data science who want to acquire the data analytics skills needed by high-profile employers in the metropolitan areas of Baltimore, Washington, D.C., and Richmond.

Developed with the Greater Washington Partnership’s Capital CoLAB, the credential equips students across disciplines with the specialized data analytics skills that the Greater Washington Partnership employers have specified to be most important to their operations. The Capital CoLAB (Collaborative of Leaders in Academia and Business) is an action-oriented partnership of employers and academic institutions that executes initiatives to develop the talent needed for the jobs of today and tomorrow.

By enrolling in either the Digital Technology Credential or Data Analytics Credential programs, students will have direct access to opportunities and engagement with some of the largest employers in the region, including Amazon, Capital One, and Northrop Grumman.

“It is exciting to see our industry partners directly engaged with our students and reinforcing the demand for the skills they are acquiring by offering them internships and other experiential learning opportunities,” says Durant.

Many students in statistics, computational data science, computer science, and information science and technology will only need to take one to three additional undergraduate courses to earn the credential, Hunter says. They can use some of their elective courses to do that.

“The credential is not another degree, but essentially a badge you can put on your LinkedIn profile or electronic resume,” he says. “I think most statistics undergraduates will take advantage of the opportunity to communicate their skills in this new way.”

The badge associated with the Data Analytics Credential also represents an innovation for students and employers. “Micro-credentials like the Data Analytics badge reflect the ‘new currency’ in denoting skill achievement and helps our students move more easily from college to career,” says Marc Austin, Executive Director of Professional Development and Academic Ventures who leads Mason’s Continuing and Professional Development unit which administers the new digital badge.

More than 50 students have already enrolled in the new Data Analytics Credential program.

Students who are working towards earning the credential will receive several exclusive benefits from area companies, including:

Access to a student portal with paid internship and event opportunities.
Invitations to participate in annual internship fairs with employers looking to recruit students.
Access to professional development webinars and other ad-hoc opportunities.

Mason students can learn more and enroll in the new Data Analytics Credential here.

Topics

data analytics

Digital Technology Credential Program

Biostatistics

Big Data

Statistics seniors receive award at American Statistical Association national data challenge

Martha Bushong — Thu, 21 Jan 2021 12:09:10 +0000

Statistics seniors receive award at American Statistical Association national data challenge Martha Bushong Thu, 01/21/2021 - 07:09

Topics

Volgenau School of Engineering

Four seniors majoring in statistics––Emily Litzenberg, Kate Lang, Nate Mulugeta, and Shannon Connor––received an honorable mention for the best use of external data at the American Statistical Association’s (ASA) Fall Data Challenge 2020.

For the national competition, called Get Out the Vote, teams of high school and undergraduate students submitted their recommendations on how to increase voter turnout using voting behavior data from the Census Bureau and the Bureau of Labor Statistics. High school and undergraduate students were judged separately.

Mason’s team looked at the data from 2000 to 2016 to see if there was an increase in registered voters who didn’t vote because they didn’t like either candidate in the presidential race. “We found there was a rise in people who didn’t vote over the years because of dislike for the candidates,” Connor says.

The group was then tasked with coming up with a way to improve voter turnout, and they suggested ranked-choice voting in which voters rank candidates by preference on their ballots, she says.

Connor says the project gave the students a chance to work closely on a statistical analysis. “I learned a lot about how to go from start to finish with a statistical group project.”

Elizabeth Johnson, an associate professor of statistics and the group’s sponsor, says, “This national competition allows students to work in teams to investigate current issues using real data, They experience the whole research process of creating a research question before collecting, analyzing, and reporting on data. I am very proud of their accomplishment in a very competitive field."

Four senior students from the Department of Statistics received an honorable mention for the best use of external data at the American Statistical Association’s (ASA) Fall Data Challenge 2020. Pictured from the left are Shannon Connor, Nate Mulugeta, and Emily Litzenberg. Kate Lang is not pictured.

Photo credit:

Photos provided

New Screening Tool Can Tell the Difference Between COVID-19 and the Flu, and It’s Evidence-Based and Free

dhawkin — Thu, 02 Jul 2020 20:51:31 +0000

New Screening Tool Can Tell the Difference Between COVID-19 and the Flu, and It’s Evidence-Based and Free dhawkin Thu, 07/02/2020 - 16:51

Data analytics work finds keys to music, murder

Martha Bushong — Wed, 06 Sep 2017 17:22:24 +0000

Data analytics work finds keys to music, murder Martha Bushong Wed, 09/06/2017 - 13:22

Data Analytics Adds Classes in Arlington

dallen21 — Mon, 03 Nov 2014 20:12:26 +0000

Data Analytics Adds Classes in Arlington dallen21 Mon, 11/03/2014 - 15:12

To increase access and availability for our students, we will be offering classes at Mason's Arlington Campus for students enrolled in the MS in Data Analytics Engineering. Beginning in January 2015 we will offer AIT 580, OR 531, and STAT 515 in Arlington. The campus is located on Fairfax Blvd. and is convenient to the Metro's Virginia Square (GMU) station on the Orange and Silver Lines. To register for classes visit our website.

Mason Aims to Fill Jobs Need with Data Analytics Master’s Program

dallen21 — Wed, 22 Jan 2014 20:33:20 +0000

Mason Aims to Fill Jobs Need with Data Analytics Master’s Program dallen21 Wed, 01/22/2014 - 15:33