Adriana M. Adami

Detection of Movement in Bed Using Unobtrusive Load Cell Sensors

Quality of sleep is an important attribute of an individuals health state and its assessment is therefore a useful diagnostic feature. Changes in the patterns of motor activities during sleep can be a disease marker, or can reflect various abnormal physiological and neurological conditions. Presently, there are no convenient, unobtrusive ways to assess quality of sleep outside of a clinic. This paper describes a system for unobtrusive detection of movement in bed that uses load cells installed at the corners of a bed. The system focuses on identifying when a movement occurs based on the forces sensed by the load cells. The movement detection approach estimates the energy in each load cell signal over short segments to capture the variations caused by movement. The accuracy of the detector is evaluated using data collected in the laboratory. The detector is capable of detecting voluntary movements in bed while the subjects were awake, with an average equal error rate of 3.22% (±0.54). Its performance is invariant with respect to the individuals characteristics, e.g., weight, as well as those of the bed. The simplicity of the resulting algorithms and their relative insensitivity to the weight and height of the monitored individual make the approach practical and easily deployable in residential and clinical settings.

Unobtrusive monitoring of sleep patterns

Disrupted sleep is a common problem in the elderly, due to age-related changes in health, lifestyle, and the physiological aspects of sleep. Severe sleep disturbances lead to impaired functioning, reduced quality of life, and increased health care costs. Therefore, monitoring of sleep patterns in the elderly is important. However, current methods for monitoring sleep are inadequate. In this paper, we use load cells for unobtrusive continuous monitoring of sleep patterns. Load cells are placed under a bed, and sleep characteristics such as bedtime, wake up time, and number and duration of naps are inferred from the load cell data. Using information from each load cell individually, we can also identify a persons position in bed, and, consequently, detect position shifts. We describe the algorithms for computation of the sleep characteristics and for assessment of the persons position in bed. We conclude by discussing the limitations in our approach, and the work we intend to pursue in the future.

Detection and Classification of Movements in Bed using Load Cells

The quality of our life is tied to the quality of our sleep. People with sleep deficits may experience impaired performance, irritability, lack of concentration, and daytime drowsiness. Increased mobility in bed can be a sign of disrupted sleep. Therefore, body movements in bed represent an important behavioral aspect of sleep. In this paper, we propose a method for detection and classification of movement that uses load cells placed at each corner of a bed. The detection of movements is based on short-term analysis of the mean-square differences of the load cell signals. Movement classification is based on features extracted from a wavelet-based multiresolution analysis (MRA) to classify the type of movement into two classes: small and large. A linear classifier is trained on each level of the MRA, and the decisions of the 4 classifiers are combined using a Bayesian combination rule. The method is evaluated on load cell data collected from 6 subjects. Each subject performed 5 trials composed of 20 pre-defined movements including small shifts of position to large movements of torso and limbs. The performance measure for the detection problem is the equal error rate (EER). We show that the detection method achieves a 2.9% EER and that the classification method has a classification error of 4%

A visual modality for the augmentation of paper

In this paper we describe how we have enhanced our multimodal paper-based system, Rasa, with visual perceptual input. We briefly explain how Rasa improves upon current decision-support tools by augmenting, rather than replacing, the paper-based tools that people in command and control centers have come to rely upon. We note shortcomings in our initial approach, discuss how we have added computer-vision as another input modality in our multimodal fusion system, and characterize the advantages that it has to offer. We conclude by discussing our current limitations and the work we intend to pursue to overcome them in the future.

Unobtrusive classification of sleep and wakefulness using load cells under the bed

Poor quality of sleep increases the risk of many adverse health outcomes. Some measures of sleep, such as sleep efficiency or sleep duration, are calculated from periods of time when a patient is asleep and awake. The current method for assessing sleep and wakefulness is based on polysomnography, an expensive and inconvenient method of measuring sleep in a clinical setting. In this paper, we suggest an alternative method of detecting periods of sleep and wake that can be obtained unobtrusively in a patients own home by placing load cells under the supports of their bed. Specifically, we use a support vector machine to classify periods of sleep and wake in a cohort of patients admitted to a sleep lab. The inputs to the classifier are subject demographic information, a statistical characterization of the load cell derived signals, and several sleep parameters estimated from the load cell data that are related to movement and respiration. Our proposed classifier achieves an average sensitivity of 0.808 and specificity of 0.812 with 90% confidence intervals of (0.790, 0.821) and (0.798, 0.826), respectively, when compared to the “gold-standard” sleep/wake annotations during polysomnography. As this performance is over 27 sleep patients with a wide variety of diagnosis levels of sleep disordered breathing, age, body mass index, and other demographics, our method is robust and works well in clinical practice.

A method for classification of movements in bed

Sleep is characterized by episodes of immobility interrupted by periods of voluntary and involuntary movement. Increased mobility in bed can be a sign of disrupted sleep that may reduce sleep quality. This paper describes a method for classification of the type of movement in bed using load cells installed at the corners of a bed. The approach is based on Gaussian Mixture Models using a time-domain feature representation. The movement classification system is evaluated on data collected in the laboratory, and it classified correctly 84.6% of movements. The unobtrusive aspect of this approach is particularly valuable for longer-term home monitoring against a standard clinical setting.

A subject state detection approach to determine rest-activity patterns using load cells

A patients sleep/wake schedule is an important step underlying clinical evaluation of sleep-related complaints. Aspects related to timing of a persons sleep routine provide important clues regarding diagnosis and treatments. Solutions for sleep complaints may sometimes rely solely on changes in habits and life style, based on what is learned from daily rest-activity patterns. This paper describes an approach for determining two states, in-bed and out-of-bed, using load cells under the bed. These states are important because they can help characterize rest-activity patterns at nighttime or detect bed exits in hospitals or nursing homes. The information derived from the load cells is valuable as an objective and continuous measure of daily patterns, and it is particularly valuable in sleep studies in populations who would not be able to remember specific hours to complete sleep diaries. The approach is evaluated on data collected in a laboratory experiment, in a sleep clinic, and also on data collected from residents of an assisted-living facility.

A System for Unobtrusive Monitoring of Mobility in Bed

Accurate assessment of mobility in bed presents challenges to clinicians and researchers alike. It is traditionally performed by either overnight polysomnograph recording or wrist-actigraphy. A different approach is instrumenting the bed itself rather than the sleeping subject. This paper describes an alternative system for unobtrusive monitoring of mobility in bed that uses load sensors installed at the corners of a bed. This work is focused on the detection and classification of the type of movements based on the forces sensed by load cells. The accuracy of the system is evaluated using data collected in a laboratory, although the methodology can be employed in home and community settings. The system is capable of detecting voluntary movement with an average equal error rate of 3.22% (plusmn 0.54). The approach for movement classification is based on Gaussian mixture models using a time-domain feature representation that correctly classified 84.6% of movements. Because the system allows both quantification and specification of movement, it has great potential for clinical use.

Comparison of load cells and wrist-actigraphy for unobtrusive monitoring of sleep movements

Accurate assessment of mobility in bed presents challenges to clinicians and researchers alike. Mobility is traditionally assessed by either overnight polysomnograph recording or wrist actigraphy. This paper describes an alternative system for unobtrusive and continuous monitoring of sleep movements that uses load sensors installed at the corners of a bed. This work is focused on the detection and classification of clinically relevant types of movement based on the forces sensed by load cells. The accuracy of the system for detecting movement has been evaluated using data collected in a laboratory setting. We also present a comparison of the proposed system with wrist-actigraphy.

Gaussian model for movement detection during Sleep

Quality of sleep is an important attribute of an individuals health state and its assessment is therefore a useful diagnostic feature. Changes in the patterns of mobility in bed during sleep can be a disease marker or can reflect various abnormal physiological and neurological conditions. This paper describes a method for detection of movement in bed that is evaluated on data collected from patients admitted for regular polysomnography. The system is based on load cells installed at the supports of a bed. Since the load cell signal varies the most during movement, the approach uses a weighted combination of the short-term mean-square differences of each load cell signal to capture the variations in the signal caused by movement. We use a single univariate Gaussian model to represent each class: movement versus non-movement. We assess the performance of the method against manual annotation performed by a sleep clinic technician from seventeen patients. The proposed detection method achieved an overall sensitivity of 97.9% and specificity of 98.7%.