(Press-News.org) HOUSTON – (Nov. 20, 2023) – Picture a swarm of drones capturing photos and video as they survey an area: What would enable them to process the data collected in the most rapid and effective manner possible?
Rice University’s Santiago Segarra and Ashutosh Sabharwal have won a grant from the Army Research Office, a directorate of the U.S. Army Combat Capabilities Development Command Army Research Laboratory, to develop a machine learning framework that improves military communication networks’ decision-making processes. The research could also help inform applications such as self-driving vehicles and cyber intrusion detection.
“Distributed decision-making is crucial in military networks,” said Sabharwal, who is a co-investigator on the grant. “In high-stakes, fast-paced environments, relying solely on a centralized decision-making process can result in delays, bottlenecks and vulnerabilities. Spreading decision and execution responsibilities across the network enables a rapid response to changing situations and adaptability to unforeseen circumstances.”
The main challenge for effective distributed network control is that the individual units that make up a network — nodes — have to find the best way to aggregate local information and distill it into actionable knowledge. In the drone example, to perform a machine learning task like object recognition on visual data collected in real time, the individual nodes — or, in our example, drones — have to follow designated protocols that specify where the information is to be processed.
“This can be done either in the drone — with its limited battery and computational capacity — or can be offloaded to headquarters through wireless connections with the associated communication latency,” Segarra said.
The optimal decision depends on multiple factors, such as the size and sensitivity of the data, the complexity of the task and the congestion level of the communication network. Rigid decision-making protocols that pre-specify how information is to be aggregated can delay or impede the network’s ability to react. Sabharwal and Segarra aim to develop a novel distributed machine learning architecture that would enable nodes to combine local data in the most effective manner.
“Our goal is for the swarm of drones to make jointly optimal offloading decisions in a distributed manner — that is, in the absence of a central agent that tells every drone what to do,” Segarra said.
To achieve this, the researchers will develop a deep learning framework where two graph neural networks interact in an actor-critic setting: The actor neural network makes offloading decisions while the critic assesses their quality. By training both neural networks in an iterative fashion, the goal is to obtain a versatile actor whose decisions translate into rapid, adaptive action across a broad range of scenarios.
Segarra is an assistant professor of electrical and computer engineering and statistics. Sabharwal is Rice’s Ernest Dell Butcher Professor of Engineering and chair of the Department of Electrical and Computer Engineering.
Project title: Distributed Machine Learning for Tactical Networks
Award number: W911NF-24-2-0008
CAPTION: Ashutosh Sabharwal (left) and Santiago Segarra
(Credit: Photo courtesy of Rice University)
George R. Brown School of Engineering: https://engineering.rice.edu/
Department of Electrical and Computer Engineering: https://eceweb.rice.edu/
Ashutosh Sabharwal website: http://ashu.rice.edu/
Santiago Segarra website: http://segarra.rice.edu/
National Security Research Accelerator: https://runsra.rice.edu/
Wireless Open-Access Research Platform: http://warpproject.org/trac
Reconfigurable Eco-system for Next-generation End-to-end Wireless: https://renew-wireless.org/
Scalable Health Labs: http://sh.rice.edu/
See Below the Skin: http://www.seebelowtheskin.org/
Saving Lives Through Transformative Health Technologies: https://pathsup.org/
Grant backs research on teaching networks to make better decisions
Rice researchers to develop machine learning framework for improved distributed network control
ELSE PRESS RELEASES FROM THIS DATE:
72% of Thai women persuade partners to seek genetic counseling if they are thalassemia carriers | BGI Insight
According to Thailand's Ministry of Public Health, approximately 18-24 million or 30-40 percent of the Thai population carries the thalassemia gene, with moderately severe thalassemia patients requiring regular treatment, including blood transfusion and chelation therapy to remove excess iron from the blood. To facilitate greater understanding of this hereditary hemoglobinopathy, BGI Genomics released its State of Thalassemia Awareness Report. This report assesses the level of knowledge and attitudes related to the associated ...
In many major crop regions, workers plant and harvest in spiraling heat and humidity
A global study of major crops has found that farmworkers are being increasingly exposed to combinations of extreme heat and humidity during planting and harvest seasons that can make it hard for them to function. Such conditions have nearly doubled across the world since 1979, the authors report, a trend that could eventually hinder cultivation. The most affected crop is rice, the world’s number one staple, followed closely by maize. As temperatures rise, the trend has accelerated in recent years, with some regions seeing 15-day per-decade increases in extreme humid heat during ...
Understanding children’s views on the perfect school | Bentham Science
Young Voices Unheard: Children’s Views from Scotland and Greece on Education is a new book published by Bentham Science that attempts to explore the question of how young children view the concepts of Children’s rights. Giving children an opportunity to voice their ideas on their education is necessary, if we do not want to deprive children of their right to be consulted and their opinions to be listened to and be seriously considered when decisions are made affecting children’s lives (article 12 of the Convention). The book attempts to give a voice to children aged 5 to ...
Bentham Science announces release of "Amazon Web Services: The Definitive Guide for Beginners and Advanced Users"
In a world driven by digital transformation, Amazon Web Services (AWS) has emerged as a powerhouse, providing on-demand cloud computing platforms and APIs to individuals, companies, and governments. Bentham Science is delighted to unveil "Amazon Web Services: The Definitive Guide for Beginners and Advanced Users," a comprehensive text that simplifies the complexities of AWS, making it accessible to graduate students, professionals, and academic researchers in computer science, engineering, and information technology. Key Features: Hands-On Approach for Beginners: The book adopts a practical, hands-on approach, ensuring that beginners can dive into AWS ...
Redefining the quest for artificial intelligence: What should replace the Turing test?
In a paper published Nov. 10 in Intelligent Computing, Philip Nicholas Johnson-Laird of Princeton University and Marco Ragni of Chemnitz University of Technology propose a novel alternative to the Turing test, a milestone test developed by computing pioneer Alan Turing. The paper suggests that it is time to shift the focus from whether a machine can mimic human responses to a more fundamental question: "Does a program reason in the way that humans reason?" The Turing test, which has long been a cornerstone of AI evaluation, involves a human evaluator attempting to distinguish between human and machine ...
Suboptimal follow-up, prevention in geriatric fall-related head trauma
Falls are the leading cause of both fatal and nonfatal injuries in the United States for adults ages 65 and older. With 1 in 4 older adults falling annually, 27,000 deaths, 8 million emergency department (ED) visits, and 800,000 hospitalizations have occurred. Follow-up after an ED-related fall visit is essential to initiate preventive strategies in these patients who are at very high risk for recurrent falls. Currently, it is unclear how frequently follow up occurs and whether preventive strategies are implemented. Researchers from Florida Atlantic University’s Schmidt College of Medicine and collaborators explored this issue by investigating ...
Over a third of Americans worry about getting the flu, RSV, or COVID-19
PHILADELPHIA – Over a third of American adults are worried that they or someone in their family will get the seasonal flu, Covid-19, or RSV (respiratory syncytial virus) in the next three months, according to a new health survey from the Annenberg Public Policy Center (APPC) of the University of Pennsylvania. Those three viral illnesses made up the “tripledemic” of respiratory illnesses that overwhelmed some health care facilities last winter. Although RSV typically peaks later in the year, this month hospitals in parts of Texas are already seeing emergency ...
State-of-the-art nanomaterial enabling ecofriendly removal of fine dust precursors
Over the past decade, fine dust conditions in Korea have worsened, as perceived by the general public, with an increase in the number of days per year featuring high-concentration fine dust. Additionally, the previous maximum fine-dust concentration level has been surpassed. In response, the Korean government has expanded its financial investment in efforts aimed at addressing fine-dust issues. Fine dust consists of particles that are too small to be seen with the naked eye. When these particles enter the human body through the skin and respiratory system, they can cause various diseases. According to a survey conducted by the Korea Environment Institute, three in ten people ...
AI-powered crab gender identification: revolutionizing fishery management and conservation
When winter comes to Japan, fishermen in the northern regions set out to capture one of the most anticipated seasonal delicacies: the horsehair crab. Known locally as “kegani” and bearing the scientific name Erimacrus isenbeckii, this species of crustacean is highly sought after throughout the country. To protect the horsehair crab population from overfishing, the Japanese and prefectural governments have implemented various restrictions on their capture. For example, in Hokkaido, where kegani is abundant, capturing females for consumption is strictly prohibited. To ...
Gambling addiction may increase the risk of long-term sick leave
Gambling addiction can increase the risk of long-term sick leave for several years, according to a new study published in Psychological Medicine. Researchers from Karolinska Institutet behind the study point to the need to detect people with gambling addiction in time to avoid financial and health problems. Gambling addiction is a psychiatric condition characterized by prolonged and problematic gambling that leads to negative financial, health and social consequences. 1.3 percent of the Swedish population, corresponding to 105,000 Swedes, have gambling problems or an increased risk of gambling problems, but the number ...
LAST 30 PRESS RELEASES:
Leukemia cells activate cellular recycling program
Argonne and Idaho National Laboratories partner with CMBlu Energy for innovative long-duration energy storage project
CCNY researchers publish optical data storage breakthrough in Nature Nanotechnology
Diet has a major impact on risk of Alzheimer’s disease
Study shows how ethical brands fare in a recession
New technique efficiently offers insight into gene regulation
U of M Medical School study finds visions of nonphysical world are common among cognitively healthy Ojibwe individuals
Consistency key to corporate expressions of racial solidarity
How mountains affect El Niño-induced winter precipitation
ECHO research examines nutrition data's value from pregnancy to adolescence in understanding child health
Training the immune system to prevent cancer – NextGen researchers discover paradigm-shifting approach
Snail-inspired robot could scoop ocean microplastics
Georgia State professor granted $5 million to identify and characterize objects in space
Immune protein may induce dementia unrelated to high blood pressure
Q&A: How can Canada best meet its commitment to protecting 30% of its land by 2030?
Eating disorder hospitalizations on the rise, affecting 'atypical' groups the most
Brains of newborns aren't underdeveloped compared to other primates
Mortality and morbidity among individuals with hypertension receiving a diuretic, ace inhibitor, or calcium channel blocker
Types of on-screen content and mental health in kindergarten children
Maternal prenatal depressive symptoms and fetal growth during the critical rapid growth stage
About 20% of patients listed as alive in their electronic health records were actually deceased according to California data
Dietary environmental factors shape the immune defense against Cryptosporidium infection
New study maps ketamine's effects on brain
Studies help explain why some prostate cancers become resistant to hormone therapy
Hard to drug: Protein droplets reveal new ways to inhibit transcription factors in an aggressive form of prostate cancer
MD Anderson’s Katy Rezvani, M.D., receives 2023 Honorific Award from the American Society of Hematology
Salty immune cells surrounding the brain linked to hypertension-induced dementia
Dark galactic region nicknamed "The Brick" explained with Webb telescope findings
Awareness, accessibility, and affordability are crucial for the early detection of thalassemia
Complications from flu largely preventable with annual flu vaccine[Press-News.org] Grant backs research on teaching networks to make better decisions
Rice researchers to develop machine learning framework for improved distributed network control