Tag Archives: artificial intelligence

Vanderbilt researcher receives $3.9 million in grants to

[ad_1]

A $2.1 million grant from the Nationwide Science Basis and a $1.eight million grant from the U.S. Division of Power will present funding for Vanderbilt researcher Abhishek Dubey, assistant professor {of electrical} engineering and laptop science, to reimagine regional transit techniques utilizing cutting-edge knowledge science strategies via a bunch of tasks referred to as Sensible Transit.

Abhishek Dubey (Vanderbilt College)

Each grants will fund tasks with the Chattanooga Space Regional Transportation Authority and will probably be led by Dubey’s Sensible and resilient Computing for Bodily Environments Lab inside Vanderbilt’s Institute for Software program Built-in Programs.

Dubey’s NSF undertaking, “Mobility for all:  Harnessing rising transit options for underserved communities,” will give attention to growing expertise to design micro-transit techniques to serve areas the place fastened line transit shouldn’t be economical. The system would dynamically generate routes that extra simply allow passengers to entry service from stops based mostly on rider demand, much like trip sharing shuttle or pool service. As well as, the grants present funding for group engagement efforts to know key challenges and talk new options in service adoption.

Change in ridership between pre-COVID (January–February) and post-COVID (Might–June) 2020 per census tract for (left) Nashville and (proper) Chattanooga. (Abhishek Dubey)

Prior to now expertise to ascertain built-in micro-transit techniques has not been profitable as a result of the system-level challenges are too technically troublesome to deal with and confusion amongst passengers results in restricted adoption. To account for these recognized challenges, the undertaking will take a socio-relational method via the enter of Paul Speer, professor and chair of the Division of Human and Organizational Improvement at Peabody School and an professional in group organizing, social energy and group change. His experience will support within the undertaking’s group engagement efforts.

Others concerned in Dubey’s NSF grant embody:

  • Aron Laszka, a cybersecurity professional and assistant professor of laptop science on the College of Houston
  • Lillian Ratliff, an active-learning professional and assistant professor {of electrical} engineering on the College of Washington
  • Samitha Samaranayake, a route planning and dispatch professional and assistant professor in civil and environmental engineering at Cornell
  • Chandra Ward, an city sociology professional and assistant professor of sociology on the College of Tennessee Chattanooga.

“We’re making use of group course of greatest practices to attain broad help for a tech-enabled transit system in Chattanooga,” mentioned Speer. “We intend to attach with group leaders who can then interact their constituents, in order that we now have a transparent understanding of peoples’ mobility wants. With this info, Prof. Dubey and our collaborators can design a really sensible transit system.” The Division of Power undertaking, “AI: Engine for optimizing built-in service in blended fleet transit operations,” seeks to develop extra power environment friendly options to mix individualized transit for folks with disabilities with fixed-route service.

Synthetic intelligence engine map (Abhishek Dubey)

Dubey and his collaborators will use state-of-the-art machine studying and knowledge pushed optimization strategies to deal with the logistics challenges of integrating 21st century transit’s opposing targets – protecting on schedule amid visitors and accommodating dynamic stops – whereas guaranteeing that the service meets strict necessities

Dubey plans to discover strategies that draw upon reinforcement studying and Multiagent Monte Carlo search strategies, an utility of synthetic intelligence that may forecast outcomes based mostly on decision-making elements. For instance, if there are two requests made without delay, the Monte Carlo search technique will run via a number of eventualities till it determines the ‘greatest’ answer to accommodate each. Dubey has utilized these strategies up to now to optimize the operations for ambulances.

A key facet of each tasks would be the capability to design and configure advanced synthetic intelligence algorithms that enhance over time and be taught with new eventualities and conditions. To take action, the staff is constructing a big built-in simulation of Chattanooga’s transit system. “We will probably be questioning easy methods to set the parameters that may lead CARTA to the perfect efficiency throughout its operations, refining our strategies,” Dubey mentioned. “It is a advanced, multidimensional course of that our group is trying ahead to making use of to a real-world problem. After we clear up this, we’ll have helped create a extra power environment friendly and efficient public transit system.” Dubey’s fashions have already resulted in a knowledge dashboard that demonstrates the effectivity benefits of particular routes based mostly on journey routes and timing.

CARTA Energy Consumption dashboard
CARTA Power Consumption dashboard with knowledge offered by CARTA (Abhishek Dubey, Scope Lab)

“We have now some very attention-grabbing challenges to resolve, significantly as we’re doing this work amid a world pandemic,” mentioned Dubey, who can be a senior analysis scientist at Vanderbilt’s Institute for Software program Built-in Programs. “Our aim with these synergistic tasks is to rethink completely the on-demand and fixed-line transit operations to make them extra environment friendly and consumer pleasant for passengers over the subsequent 4 years.”

The DOE grant enhances Dubey’s prior power effectivity undertaking already underway with CARTA.

[ad_2]

Supply hyperlink

Vanderbilt researcher receives $3.9 million in grants to

[ad_1]

A $2.1 million grant from the Nationwide Science Basis and a $1.eight million grant from the U.S. Division of Power will present funding for Vanderbilt researcher Abhishek Dubey, assistant professor {of electrical} engineering and laptop science, to reimagine regional transit programs utilizing cutting-edge information science methods by a bunch of initiatives referred to as Good Transit.

Abhishek Dubey (Vanderbilt College)

Each grants will fund initiatives with the Chattanooga Space Regional Transportation Authority and might be led by Dubey’s Good and resilient Computing for Bodily Environments Lab inside Vanderbilt’s Institute for Software program Built-in Techniques.

Dubey’s NSF mission, “Mobility for all:  Harnessing rising transit options for underserved communities,” will concentrate on growing know-how to design micro-transit programs to serve areas the place fastened line transit is just not economical. The system would dynamically generate routes that extra simply allow passengers to entry service from stops based mostly on rider demand, just like trip sharing shuttle or pool service. As well as, the grants present funding for neighborhood engagement efforts to grasp key challenges and talk new options in service adoption.

Change in ridership between pre-COVID (January–February) and post-COVID (Might–June) 2020 per census tract for (left) Nashville and (proper) Chattanooga. (Abhishek Dubey)

Up to now know-how to ascertain built-in micro-transit programs has not been profitable as a result of the system-level challenges are too technically troublesome to deal with and confusion amongst passengers results in restricted adoption. To account for these recognized challenges, the mission will take a socio-relational method by the enter of Paul Speer, professor and chair of the Division of Human and Organizational Growth at Peabody School and an professional in neighborhood organizing, social energy and neighborhood change. His experience will support within the mission’s neighborhood engagement efforts.

Others concerned in Dubey’s NSF grant embrace:

  • Aron Laszka, a cybersecurity professional and assistant professor of laptop science on the College of Houston
  • Lillian Ratliff, an active-learning professional and assistant professor {of electrical} engineering on the College of Washington
  • Samitha Samaranayake, a route planning and dispatch professional and assistant professor in civil and environmental engineering at Cornell
  • Chandra Ward, an city sociology professional and assistant professor of sociology on the College of Tennessee Chattanooga.

“We’re making use of neighborhood course of finest practices to realize broad help for a tech-enabled transit system in Chattanooga,” stated Speer. “We intend to attach with neighborhood leaders who can then interact their constituents, in order that we now have a transparent understanding of peoples’ mobility wants. With this info, Prof. Dubey and our collaborators can design a really good transit system.” The Division of Power mission, “AI: Engine for optimizing built-in service in combined fleet transit operations,” seeks to develop extra power environment friendly options to mix individualized transit for folks with disabilities with fixed-route service.

Synthetic intelligence engine map (Abhishek Dubey)

Dubey and his collaborators will use state-of-the-art machine studying and information pushed optimization methods to deal with the logistics challenges of integrating 21st century transit’s opposing objectives – protecting on schedule amid site visitors and accommodating dynamic stops – whereas making certain that the service meets strict necessities

Dubey plans to discover strategies that draw upon reinforcement studying and Multiagent Monte Carlo search strategies, an utility of synthetic intelligence that may forecast outcomes based mostly on decision-making components. For instance, if there are two requests made without delay, the Monte Carlo search methodology will run by a number of situations till it determines the ‘finest’ answer to accommodate each. Dubey has utilized these strategies prior to now to optimize the operations for ambulances.

A key facet of each initiatives would be the skill to design and configure advanced synthetic intelligence algorithms that enhance over time and study with new situations and conditions. To take action, the crew is constructing a big built-in simulation of Chattanooga’s transit system. “We might be questioning tips on how to set the parameters that can lead CARTA to one of the best efficiency throughout its operations, refining our methods,” Dubey stated. “It is a advanced, multidimensional course of that our group is wanting ahead to making use of to a real-world problem. Once we resolve this, we’ll have helped create a extra power environment friendly and efficient public transit system.” Dubey’s fashions have already resulted in an information dashboard that demonstrates the effectivity benefits of particular routes based mostly on journey routes and timing.

CARTA Energy Consumption dashboard
CARTA Power Consumption dashboard with information offered by CARTA (Abhishek Dubey, Scope Lab)

“We now have some very fascinating challenges to unravel, notably as we’re doing this work amid a worldwide pandemic,” stated Dubey, who can be a senior analysis scientist at Vanderbilt’s Institute for Software program Built-in Techniques. “Our aim with these synergistic initiatives is to rethink totally the on-demand and fixed-line transit operations to make them extra environment friendly and person pleasant for passengers over the subsequent 4 years.”

The DOE grant enhances Dubey’s prior power effectivity mission already underway with CARTA.

[ad_2]

Supply hyperlink

Algorithm helps improve coronary calcium detection | VUMC Reporter

[ad_1]

 

by Bill Snyder

Dutch computer scientists and colleagues in the United States have achieved a marked improvement in the automatic detection of calcified atherosclerotic plaque in coronary arteries and thoracic aorta using computerized tomography (CT).

Reporting this Feb. 11 in the journal Radiology, they demonstrated that a deep-learning algorithm for artificial intelligence-assisted calcium scoring they developed can accurately determine cardiovascular risk across a range of CT scans and in a racially diverse population.

Deep-learning algorithms are a form of artificial intelligence that enable computers to “learn” from examples to perform a task. This one was developed and evaluated with the help of co-author J. Jeffrey Carr, MD, MSCE, the Cornelius Vanderbilt Chair in Radiology & Radiological Sciences in the Vanderbilt University School of Medicine.

J. Jeffrey Carr, MD

“Coronary calcium has been previously established as an excellent test for reclassifying an individual’s risk for heart disease as either high or low risk,” Carr said. “Developing a fully automated method that can perform the measurement of coronary calcium from CT scans accurately has a lot of value.

“I’m enthusiastic that versions of this could be implemented in (clinical) practice in a relatively few years and thus lower the barriers to identifying those people at high risk for heart disease,” he said.

The algorithm was trained and evaluated by the paper’s senior author, Ivana Išgum, PhD, a world leader in AI and medical imaging, her graduate student and first author, Sanne GM van Velzen, and colleagues at Amsterdam University Medical Center and University Medical Center Utrecht.

The work is based on a calcium scoring algorithm in the National Lung Screening Trial (NLST) that Išgum and graduate student Nikolas Lessmann developed in a collaboration between University Medical Center Utrecht and Radboud University Medical Center in Nijmegen.

The algorithm was built and evaluated using 7,240 CT scans, including nearly 2,900 from the Jackson Heart Study of African Americans in Jackson, Mississippi, 1,400 from patients treated for breast cancer in the Netherlands, and more than 1,000 from the NLST, which was conducted in 2002-2004.

Carr helped plan the study and gained access to the CT scans from the Jackson Heart Study, which is supported by the National Heart, Lung, and Blood Institute (NHLBI) of the National Institutes of Health (NIH), and from the NLST, which was supported by the National Cancer Institute.

“This study demonstrates the growing potential of artificial intelligence-assisted technology to enhance efforts to improve the detection of heart disease, the leading cause of death in this country,” said David Goff, MD, PhD, director of the Division of Cardiovascular Sciences at NHLBI.

“It is part of an ongoing effort by researchers supported by the NHLBI to develop AI tools that can rapidly sift through vast amounts of biomedical data to identify patterns that can help detect disease and hopefully save lives.”

“The American people and NIH have invested in these studies over decades to help us reduce the burden of heart and lung disease,” Carr added. “Thanks to carefully saving the original full fidelity images, we’re now able to use CT images and data volunteered by our participants in some cases more than a decade ago to build and train AI algorithms, techniques that did not exist when the studies began.”

Carr, who came to Vanderbilt in 2013, developed one of the first CT scanners to measure coronary calcium in 1998 while on the faculty of Wake Forest University School of Medicine in Winston-Salem, N.C.

Over the years, CT calcium “scoring” has become an important tool for understanding and determining heart disease risk.

“If you have no coronary calcium, your risk of having a heart attack in the next five years is less than 1%,” Carr said. “But if you have started to develop calcified plaque, even in your 40s and 50s, the risk can jump five- to twentyfold depending on the calcium score.

“We have not done as good a job at identifying and addressing risk factors in some populations in the United States,” he added. “Globally we need to lower barriers (to testing and treatment) to reduce the burden of heart disease worldwide.”

To broaden the application, Ivana Išgum and her colleagues, together with Carr’s input, trained an AI algorithm with CT scans with measurement of coronary calcium from the Jackson Heart Study cohort of African Americans and from the diverse participants in the NLST.

Goff noted that people should also recognize the need for other preventive efforts to fight heart disease, including physical activity, a healthy diet, regular sleep and avoidance of tobacco products.

Carr agreed. “The challenge is identifying people early in life when the prevention methods are likely to be the most effective,” he said. “By identifying individuals with relatively early coronary artery disease before they have any symptoms, we can support and encourage them to make the lifestyle changes and, if appropriate, offer them evidence-based interventions to address diabetes, elevated blood pressure, elevated cholesterol and smoking and effectively prevent or minimize the impact of heart disease.”

Supported by the Dutch Cancer Society, the research was conducted with the cooperation of Jackson Heart Study collaborators Jackson State University, Tougaloo College, the Mississippi State Department of Health and the University of Mississippi Medical Center in Jackson.

[ad_2]

Source link

AP Explains: How Facebook handles speech in ‘secret’ groups

[ad_1]

U.S. Border Patrol agents are under fire for posting offensive messages in a “secret” Facebook group that included sexually explicit posts about U.S. Rep. Alexandria Ocasio-Cortez and dismissive references to the deaths of migrants in U.S. custody. The existence of that group was reported Monday by ProPublica . Prior to that, few people outside the group had ever heard of it.

Facebook enforces complex guidelines against hate speech, abuse and other categories when it comes to users’ posts to their friends or to the public. Here’s a look at how the social network handles similarly offensive material when it’s posted inside the more private corners of the service, in the online gatherings known as “groups.”

WHAT’S A SECRET FACEBOOK GROUP?

Facebook groups are exactly what they sound like — collections of individual users who gather on the company’s platform to discuss hobbies, tell jokes, educate or support one another, plan trips or whatever else strikes their fancy. Joining a group typically requires the approval of a group administrator or an existing member.

Many such groups are public, meaning anyone can search them out, see a list of their members and browse people’s posts without joining — even if they’re not on Facebook. Other groups are “closed.” These boards show up in search, although only members can see posts and the names of other members.

“Secret” groups, by contrast, aren’t visible at all to outsiders; not even their names turn up in searches. Joining one requires being invited by a current member.

Plenty of secret groups aren’t remotely nefarious. For example, people discussing health matters or posting photos of their children to family members and friends often make such groups secret.

Facebook says about 400 million of its users are in what it considers “meaningful” groups, which it defines in a variety of ways, including how much time a person spends in them. The company doesn’t disclose how many of these groups are public, closed or secret.

ARE THE RULES DIFFERENT IN SECRET GROUPS?

Facebook says all groups, including secret ones, are subject to same community standards it applies to individual posts. Among other things, those rules forbid bullying and harassment, hate speech, glorification of violence and “cruel and insensitive” posts that target “victims of serious physical or emotional harm.”

Of course, it might be easier to get away with rule-breaking posts in secret groups, although only to the same extent that someone might get away with sharing objectionable posts only with like-minded friends. While a racist or threatening post in a secret group may be less likely to be reported by other members, Facebook has a variety of tools, including artificial intelligence, that can detect some violations anyway.

The system is far from perfect, though. For example, while Facebook uses AI to proactively find nudity, graphic violence and terrorist propaganda and a host of other things, its systems are not sophisticated enough yet to catch nuance, context and satire.

WHAT IS FACEBOOK DOING ABOUT THE BORDER PATROL GROUP?

Facebook said it is cooperating with federal authorities on their investigation of the matter. It did not respond to questions Tuesday about whether any of the posts on the secret Border Patrol group — called “I’m 10-15” in a reference to Border Patrol code for “aliens in custody” — violated its standards.

The group has roughly 9,500 members, according to ProPublica. It featured a variety of crude and offensive posts.

Some were graphic, doctored images of Ocasio-Cortez, including one that showed a smiling President Donald Trump forcing her head toward his crotch. Other comments referred to Democrats Ocasio-Cortez of New York and U.S. Rep. Veronica Escobar of Texas as “hoes”; one member encouraged agents to throw a “burrito at these bitches” when they visited migrant detention camps.

Others joked about the deaths of migrants in various ways.

But it’s not clear if all the highlighted posts violate Facebook rules. For example, one post that referred to Ocasio-Cortez and Escobar, stating that “there should be no photo ops for these scum buckets,” might be offensive, but it may not count as hate speech or abuse. Nor might another post questioning the authenticity of a photo published in late June by The Associated Press that showed a migrant father and his toddler daughter drowned on the banks of the Rio Grande.

Border Patrol chief Carla Provost called the posts “completely inappropriate” and said that any employees found to have violated standards of conduct would be “held accountable.”

ARE OUTSIDERS TO BLAME?

Some Border Patrol defenders suggested that border agents themselves might not be to blame for all of the posts. In a press release posted to Twitter, the National Border Patrol Council, a union for agents, condemned the 10-15 posts, but took pains to note that the group included “members of the public” as well as current and former agents.

ProPublica said it linked posts within the group with “apparently legitimate Facebook profiles belonging to Border Patrol agents, including a supervisor based in El Paso, Texas, and an agent in Eagle Pass, Texas,” although it was unable to reach those individuals.

It’s not impossible for outsiders to join a secret group, depending on how thoroughly its administrators vet their invitees. Facebook is not involved in that process. It’s not clear how the 10-15 group approved its members.

[ad_2]

Source link