Dr. Roozbeh Jafari, assistant professor of electrical engineering at UT Dallas, is developing wearable wireless sensors about the size of a button.
These sensors can be used to detect and possibly even predict falls. A key differentiator for Dr. Jafari’s technology is the unique way it manages and optimizes power consumption throughout the entire system. One way he achieves this goal is by minimizing the collection of unnecessary data, whose processing requires power – a generalizable approach that could open the door to a range of other miniature sensors.
“Roozbeh Jafari has established a very dynamic, innovative laboratory in electrical engineering, that has bridged research challenges in brain-computer interfaces in a remarkable way,” said Dr. John Hansen, associate dean for research in the Erik Jonsson School of Engineering and Computer Science.
For example, when a subject is sitting or laying down and thus at low risk, it may not be necessary to collect as much data as when a person is ambulating. These gains in efficiency allow Jafari to eliminate bulky batteries meant for less adaptable devices, opting instead for lighter and more efficient alternatives. The algorithms used can coordinate, manage, and transmit information from various wearable devices. The amount of energy needed by each bio-sensor could be minimized by collecting just enough to achieve the sensitivity needed for the desired use.
“Signals and events observed from the human body tend to change slowly,” said Jafari, director of the Embedded Systems and Signal Processing Lab and a member of the Texas Analog Center of Excellence (TxACE). “The physics and kinematics of the human body reduce the likelihood of random body signals and movements.”
The final toll on the US health care system related to people falling is estimated to be greater than $50 billion annually. Thus, the value proposition of using wearable sensors to reduce falls is clear. To be beneficial, though, Dr. Jafari and others will have to not only find ways to predict falls but also to intervene to prevent them.
Other potential applications include tracking Parkinson’s patients on their progress with a specific treatment regimen or remote monitoring of elderly patients undergoing outpatient physical therapy.
“Growing demand for health-care monitoring applications requires students, engineers and healthcare professionals to design, develop, deploy and operate wearable systems,” Jafari said. “I am quite pleased to work with my excellent graduate and undergraduate students at UT Dallas to enable the next generation of wearable computers.”
