Welcome to the Research Roundup: a collection of highlights from Husker’s latest research and creative pursuits.
Picking up good vibes
In the United States, nearly one-fifth of commercially raised piglets die within about three weeks of birth – the period during which a litter suckles from its mother before being weaned off its milk. Farmers and researchers are collectively studying how to better monitor sows and their litters to reduce this mortality rate. Although effective, video surveillance requires adequate lighting, as well as digital processing and storage capabilities, which makes it difficult to implement on a large scale. Wearable sensors, on the other hand, face the challenges of durability, battery life, and other issues.
Tami Brown-Brandl, Raj Sharma and Asya Macon of Nebraska, all from the Department of Biological Systems Engineering, joined colleagues from the University of Michigan, Stanford University and Carnegie Mellon University to explore another option. The team placed sensors under several pens to test whether vibrations could help identify a sow’s posture (lying down, sitting/kneeling or standing) and the feeding activity of the sow and her piglets.
Using machine learning, the vibration-sensitive system accurately classified a sow’s posture in the vast majority of cases: 95.5% sitting/kneeling, 99.9% lying and 100% standing position. It also correctly classified feeding a sow 96% of the time and nursing a pegged piglet 91.3% of the time.
The results suggest that vibration sensors could prove to be a reliable and practical way of signaling the factors – piglet size and disease, sow injuries – that tend to put piglets at risk.
Spill the blood
Peripheral arterial disease arises from the plaque-related narrowing or blockage of blood vessels, which limits blood flow to the extremities, usually the legs. While the resulting lack of oxygen can lead to periodic leg pain, peripheral arterial disease can also develop painlessly, delaying treatments and potentially leading to more serious long-term health problems. And diagnosing peripheral arterial disease can be especially difficult in the elderly, who sometimes suffer from health conditions with symptoms similar to those of BUFFER.
Unfortunately, the gold standard diagnostic procedure for BUFFER is expensive and requires specialized training. Fadi Alsaleem, Mohammad Ali Takallou and Ali Hazem Al Ramini of Nebraska Engineering contributed to a recent study aimed at developing a simpler and less expensive screening technique. Led by the University of Nebraska at Omaha, the study applied machine learning to data collected from 270 adults – 227 with BUFFER43-year-old Sans – who walked a path lined with force-measuring plates while wearing reflective markers captured by high-speed cameras.
By identifying certain biomechanical and pressure-related signatures, two types of machine learning models successfully distinguished between adults with and without BUFFER in about 89% of cases. Even relying solely on so-called ground reaction forces – the forces exerted on a foot when a foot applies a force to the ground – one of the model types still achieved an accuracy of 87%.
Applying the study’s proof-of-concept to wearable sensors, including those built into shoes, could eventually help alert doctors to the onset of BUFFERthe team said.
The poll says…
In late 2020, the university’s Office of Sociological Research interviewed a random sample of 2,775 Nebraskans. The survey came amid aftershocks from two seismic events: the start of the covid-19 pandemic and nationwide protests over the killing of George Floyd by a former Minneapolis police officer.
As a researcher who has studied the intersections between public health, crime, policing and politics, Lisa Kort-Butler of the Department of Sociology decided to analyze the results of this survey. She was particularly interested in whether the general anxieties and insecurities spurred by the ongoing discord might influence attitudes toward public policy and those in authority.
Perceive covid-19 as a serious threat, whether this threat is considered an economic or health problem, corresponded to a greater concern with crime. And the Nebraskans who saw covid-19 as a health threat were also more likely to avoid areas where they felt unsafe. But those who know someone who has contracted covid-19 were actually less likely to avoid these areas – a seemingly paradoxical finding that nonetheless echoes national surveys.
Around 20% of respondents said their communities spent too little on law enforcement. According to the survey, Nebraskanians who so generally believed also:
- Perceived covid-19 as a threat to the economy more than to public health
- Confidence expressed in political leaders, but distrust in health officials, on issues related to covid-19
- Believed that race relations in the United States were deteriorating
Overall, Kort-Butler said, the survey data supported the idea that uncertainty and insecurity stemming from periods of upheaval can be channeled into support for criminal justice policies that promise a return. to normal.
#Research #Overview #November