Goto

Collaborating Authors

Pennsylvania


Toward Reduction in False-Positive Thyroid Nodule Biopsies with a Deep Learning–based Risk Stratification System Using US Cine-Clip Images

#artificialintelligence

The Cine-CNNTrans achieved an average AUC of 0.88 0.10 for classifying benign versus malignant thyroid nodules. The Cine-CNNTrans showed higher AUC than the Static-2DCNN (P .03). For aggregating framewise outputs into nodulewise scores, the Cine-CNNTrans tended toward higher AUC compared with the Cine-CNNAvePool (P .17). Our system tended toward higher AUC than the Cine-Radiomics and the ACR TI-RADS level, though the difference did not achieve statistical significance (P .16


The Global Reach of CMU AI

CMU School of Computer Science

As intractable problems accrue and grow, artificial intelligence is increasingly being called upon as part of the solution. Carnegie Mellon University AI researchers have stepped up to help surmount these obstacles where large data sets must be analyzed and patterns discovered to find answers. Last year, the National Science Foundation teamed up with the U.S. Department of Agriculture, the U.S. Department of Homeland Security, as well as corporate sponsors Accenture, Amazon, Google and Intel to provide $220 million in grants to create 11 new institutes specifically dedicated to AI research across a wide range of sectors. CMU's School of Computer Science and College of Engineering faculty will work with four of these new institutes: the AI Institute for Resilient Agriculture, the AI Institute for Collaborative Assistance and Responsive Interaction for Networked Groups, the AI Institute for Future Edge Networks and Distributed Intelligence, and the USDA-NIFA Institute for Agricultural AI for Transforming the Workforce and Decision Support. Learn more about these institutes and meet the researchers leading the work in our magazine, The Link.


#ICRA2022, the great robotics scicommer – Day 1 video digest

Robohub

The IEEE International Conference on Automation and Robotics, ICRA, is the itinerant flagship conference of the IEEE Robotics and Automation Society, RAS. In its 39th edition, ICRA is being held in the Pennsylvania Convention Center, in Philadelphia, PA, USA, between May 23 and 27, 2022. ICRA started just after the birth of the IEEE Robotics and Automation Society (formerly IEEE Robotics and Automation Council) in 1983. The first edition was held in Atlanta, GA, USA, in 1984. During its first years, the conference showed the growing interest of researchers and industry leaders in the emergent field of robotics.


The IEEE International Conference on Robotics and Automation (ICRA) kicks off with the largest in-person participation and number of represented countries ever

Robohub

The IEEE International Conference on Robotics and Automation (ICRA), taking place simultaneously at the Pennsylvania Convention Center in Philadelphia and virtually, has just kicked off. ICRA 2022 brings together the world's top researchers and most important companies to share ideas and advances in the fields of robotics and automation. This is the first time the ICRA community is reunited after the pandemic, resulting in record breaking attendance with over 7,000 registrations and 95 countries represented. As the ICRA 2022 Co-Chair Vijay Kumar (University of Pennsylvania, USA) states, "we could not be happier to host the largest robotics conference in the world in Philadelphia, and the beginning of the re-emergence from the pandemic after a three year hiatus. Many important developments in robotics and automation have historically been first presented at ICRA, and in its 39th year, ICRA 2022 promises to take this trend one step further.


From The Link: Lessons Learned From the SubT Challenge

CMU School of Computer Science

As the countdown started, a boxy robot with four big wheels carrying a host of cameras, sensors, communication equipment, autonomy software and the computing power to make it all work together rolled down a ramp into a dark tunnel. It did not know where it was, what was ahead of it or where it was going. It was there to explore. Over the next hour, more robots followed: wheeled robots, drones and a dog-like quadruped. Team Explorer deployed eight robots for the final round of the Defense Advanced Research Projects Agency (DARPA) Subterranean, or SubT, Challenge -- a three-year competition during which teams from around the world raced to develop robotic systems that could autonomously operate in underground environments like caves, mines or subway stations for search and rescue missions.


5 Trends in Medical Health Technology in 2022

#artificialintelligence

It is predicted that technologies such as artificial intelligence (AI), cloud computing, extended reality and the Internet of Things (IoT) will be introduced further among related workers, leading to the development and provision of new and better treatments and services. In the months following the outbreak of the COVID-19 outbreak, the proportion of telemedicine consulting has risen sharply from 0.1% to 43.5%, and is expected to rise further in the future, as this trend could save more patients' lives, said Deloitte Accounting Firm analyst. . To achieve this goal, the next-generation portable device, heart rate, stress, and blood oximetry, enables doctors to accurately determine the patient's condition in real time. During the COVID-19 period, doctors built'virtual hospital rooms' in some areas to observe the treatment status of patients in various areas through the central communication infrastructure. The Pennsylvania Emergency Medical Center is developing a high-quality'virtual emergency room'.


Solving Sudoku With AI or Quantum?

#artificialintelligence

Established in Pittsburgh, Pennsylvania, US -- Towards AI Co. is the world's leading AI and technology publication focused on diversity, equity, and inclusion. We aim to publish unbiased AI and technology-related articles and be an impartial source of information. We have thousands of contributing writers from university professors, researchers, graduate students, industry experts, and enthusiasts. We receive millions of visits per year, have several thousands of followers across social media, and thousands of subscribers. All of our articles are from their respective authors and may not reflect the views of Towards AI Co., its editors, or its other writers.


FFCI: A Framework for Interpretable Automatic Evaluation of Summarization

Journal of Artificial Intelligence Research

In this paper, we propose FFCI, a framework for fine-grained summarization evaluation that comprises four elements: faithfulness (degree of factual consistency with the source), focus (precision of summary content relative to the reference), coverage (recall of summary content relative to the reference), and inter-sentential coherence (document fluency between adjacent sentences). We construct a novel dataset for focus, coverage, and inter-sentential coherence, and develop automatic methods for evaluating each of the four dimensions of FFCI based on cross-comparison of evaluation metrics and model-based evaluation methods, including question answering (QA) approaches, semantic textual similarity (STS), next-sentence prediction (NSP), and scores derived from 19 pre-trained language models. We then apply the developed metrics in evaluating a broad range of summarization models across two datasets, with some surprising findings.


Are machine-learning tools the future of healthcare?

#artificialintelligence

Terms like "machine learning," "artificial intelligence" and "deep learning" have all become science buzzwords in recent years. But can these technologies be applied to saving lives? The answer to that is a resounding yes. Future developments in health science may actually depend on integrating rapidly growing computing technologies and methods into medical practice. Cosmos spoke with researchers from the University of Pittsburgh, in Pennsylvania, US, who have just published a paper in Radiology on the use of machine-learning techniques to analyse large data sets from brain trauma patients.


This week in The History of AI at AIWS.net – Deep Blue versus Garry Kasparov

#artificialintelligence

This week in The History of AI at AIWS.net – IBM "Deep Blue" machine defeats Garry Kasparov, the then-reigning World Chess Champion, at chess, in a highly-publicised match on 11 May, 1997. This date was the conclusion of 2 matches, one starting the year before, 1996. The face-off began on February 10, 1996, in Philadelphia, Pennsylvania. Kasparov actually won this match 4-2. A year later in New York City, they would actually rematch, where Deep Blue defeated Kasparov 3.5-2.5.