Description:
Reference #: 01651
The University of South Carolina is offering licensing opportunities for Sleep Disruptions Identification from Millimeter-Wave Wireless Systems.
Background:
Millimeter-wave (mmWave) wireless-based solutions can enable fine-grained disruption monitoring from wireless signal reflections. The core idea is to leverage cross-correlation between successive mmWave reflected signals and a Hidden Markov Model (HMM) to identify the sleep disruptions, such as toss-turn patterns, to provide insight into the impact of sleep on the overall functioning of adults and future cognitive development of infants. MmWave transceivers are poised to soon become ubiquitous in all 5G-and-beyond devices, such as access points, enabling the opportunity for bringing private, non-invasive sleep disruption monitoring to the masses at-home.
Invention Description:
A lightweight two-states Hidden Markov Model (HMM) was designed to improve the detection accuracy and timing estimations of sleep disruptions. The two states are rest and toss-turn, and the emissions are different levels of envelope values. To build the HMM, several datasets involving multiple volunteers tossing and turning during their sleep and formulate the state transition matrices by estimating the four conditional probabilities were collected: p(Rest|Rest), p(Rest|Toss-Turn), p(Toss-Turn|Rest), and p(Toss-Turn|Toss-Turn). Then, the emission matrix by estimating the conditional probabilities for discrete envelope values were formulated: p(e <1|Rest), p(e<2|Rest),p(e<1|Toss-Turn),p(e<2|Toss-Turn), and so on. Finally, run-time, ArgoSleep (ArgoSleep applies a cross-correlation between successive frames of the reflected signals, and estimates the rate of change (i.e., time-derivative) in the peak correlation output) first calculates the envelope from the reflected mmWave signals, and then uses the state transition and emission matrices and a Viterbi decoder to predict the binary states, corresponding to rest and toss-turn.
Potential Applications:
Sleep is a critical aspect of human health and well-being, particularly for children’s neurological development and adult well-being. Existing works using parent report shows that disrupted sleep in early infancy is related to atypical neurodevelopment. Therefore, studying sleep disruptions, such as toss-turn patterns, can provide insight into the impact of sleep on the overall functioning of adults and future cognitive development of infants. Millimeter-wave (mmWave) enables fine-grained disruption monitoring from wireless signal reflections. The core idea is to leverage cross-correlation between successive mmWave reflected signals and a Hidden Markov Model (HMM) to identify the sleep and disruptions period.
Advantages and Benefits:
Currently, the method sleep disruptions have severe limitations – it is incredibly physically invasive, complicated to set up in-home, and, critically, can disrupt the infant’s natural sleeping pattern and often lead to rashes, burns, and injuries. Thus, there is a significant need for non-invasive and contactless approaches that estimate sleep disruptions without compromising comfort and safety. Millimeter-wave (mmWave) wireless-based solutions can overcome these challenges by bringing private, non-invasive sleep disruption monitoring to the masses at-home.