Adam T. Barth

Body Area Sensor Networks: Challenges and Opportunities

Body area sensors can enable novel applications in and beyond healthcare, but research must address obstacles such as size, cost, compatibility, and perceived value before networks that use such sensors can become widespread.

Accurate, Fast Fall Detection Using Gyroscopes and Accelerometer-Derived Posture Information

Falls are dangerous for the aged population as they can adversely affect health. Therefore, many fall detection systems have been developed. However, prevalent methods only use accelerometers to isolate falls from activities of daily living (ADL). This makes it difficult to distinguish real falls from certain fall-like activities such as sitting down quickly and jumping, resulting in many false positives. Body orientation is also used as a means of detecting falls, but it is not very useful when the ending position is not horizontal, e.g. falls happen on stairs. In this paper we present a novel fall detection system using both accelerometers and gyroscopes. We divide human activities into two categories: static postures and dynamic transitions. By using two tri-axial accelerometers at separate body locations, our system can recognize four kinds of static postures: standing, bending, sitting, and lying. Motions between these static postures are considered as dynamic transitions. Linear acceleration and angular velocity are measured to determine whether motion transitions are intentional. If the transition before a lying posture is not intentional, a fall event is detected. Our algorithm, coupled with accelerometers and gyroscopes, reduces both false positives and false negatives, while improving fall detection accuracy. In addition, our solution features low computational cost and real-time response.

TEMPO 3.1: A Body Area Sensor Network Platform for Continuous Movement Assessment

This work presents TEMPO (Technology-Enabled Medical Precision Observation) 3.1, a third generation body area sensor platform that accurately and precisely captures, processes, and wirelessly transmits six-degrees-of-freedom inertial data in a wearable, non-invasive form factor. TEMPO 3.1 is designed to be usable to both the wearer and researcher, thereby enabling motion capture applications in body area sensor networks (BASNs). A complete system is designed and developed that includes the following: (1) enabling technologies and hardware design of TEMPO 3.1, (2) a custom real-time operating system (TEMPOS) that manages all aspects of signal acquisition, signal processing, data management, peripheral control, and wireless communication on a TEMPO node, and (3) a custom case design. The system is evaluated and compared to existing BASN hardware platforms. TEMPO 3.1 creates new opportunities for wearable, continuous monitoring applications and extends the research space of current efforts.

Body Sensor Networks: A Holistic Approach From Silicon to Users

Body sensor networks (BSNs) are emerging cyber-physical systems that promise to improve quality of life through improved healthcare, augmented sensing and actuation for the disabled, independent living for the elderly, and reduced healthcare costs. However, the physical nature of BSNs introduces new challenges. The human body is a highly dynamic physical environment that creates constantly changing demands on sensing, actuation, and quality of service (QoS). Movement between indoor and outdoor environments and physical movements constantly change the wireless channel characteristics. These dynamic application contexts can also have a dramatic impact on data and resource prioritization. Thus, BSNs must simultaneously deal with rapid changes to both top-down application requirements and bottom-up resource availability. This is made all the more challenging by the wearable nature of BSN devices, which necessitates a vanishingly small size and, therefore, extremely limited hardware resources and power budget. Current research is being performed to develop new principles and techniques for adaptive operation in highly dynamic physical environments, using miniaturized, energy-constrained devices. This paper describes a holistic cross-layer approach that addresses all aspects of the system, from low-level hardware design to higher level communication and data fusion algorithms, to top-level applications.

Neural Network Gait Classification for On-Body Inertial Sensors

Clinicians have determined that continuous ambulatory monitoring provides significant preventative and diagnostic benefit, especially to the aged population. In this paper we describe gait classification techniques based on data obtained using a new body area sensor network platform named TEMPO 3. The platform and its supporting infrastructure enable six-degrees-of-freedom inertial sensing, signal processing, and wireless transmission. The proposed signal processing includes data normalization to improve robustness, feature extraction optimized for classification, and wavelet pre-processing. The effectiveness of the platform is validated by implementing a binary classifier between shuffle and normal gait. Artificial neural networks and classifiers based on the Cerebellar Model Articulation Controller were tested and yielded classification accuracies (68%-98%) comparable to previous efforts that required more restrictive or intrusive apparatus. These results suggest a viable path to resource-constrained, on-body gait classification.

Body-coupled communication for body sensor networks

Body sensor networks (BSNs) offer a wealth of opportunities for precise, accurate, continuous, and non-invasive sensing of physiological phenomena, but their unique operating environment, the body-area, poses unique technical challenges. Popular communications solutions that utilize 2.4 GHz radio transmission suffer from significant and highly variable path loss in this setting. To compensate for such loss, radio transceivers often transmit at power levels at or above 1 mW -- a reality that limits battery life. We propose the use of body-coupled communication to address this issue, as it presents several distinct advantages over existing solutions, namely: reduced power consumption, minimal interference, and increased privacy. In this paper, we demonstrate a 23 MHz body-coupled channel that supports reliable data transfer with an average received power of 30 dBm over a 2.4 GHz radio frequency link. This scheme reduces power needed for transmission and increases battery life by up to 100%, while maintaining a favorable environment for application-specific quality of service requirements. Finally, we propose a system-level hardware architecture and explore its implications on BSN infrastructure.

Continuous, non-invasive assessment of agitation in dementia using inertial body sensors

Agitated behavior is one of the most frequent reasons that patients with dementia are placed in long-term care settings. These behaviors are indicators of distress and are associated with increased risk of injury to the patients and their caregivers. This study aims to explore the ability of a custom inertial wireless body sensor network (BSN) to objectively detect and quantify agitation, validating against currently accepted subjective clinical measures -- the Cohen-Mansfield Agitation Inventory (CMAI) and the Aggressive Behavior Scale (ABS) -- within the nursing home setting. The ultimate goal is to enable continuous, real-time monitoring of physical agitation in any location over an extended period. Continuous, longitudinal assessment facilitates timely response to agitation events in order to minimize patient distress and risk for injury, to more appropriately titrate pharmacotherapy, and to enable staff (or caregivers) to successfully intervene. Six patients identified as being at high risk for agitated behaviors were enrolled in this pilot study. Patients underwent a series of the above validated tests of memory and agitation. The BSN nodes were applied at three sites on body for three hours while behaviors were annotated simultaneously. This process was subsequently repeated twice for each enrolled subject. The BSN data was then processed using Teager energy analysis, which an earlier study suggested was a promising method for extracting jerky and repetitive movements from inertial data. Results based on construct validity testing for agitation (CMAI) and aggression (ABS) were promising and suggest that additional study with larger sample sizes is warranted.

Holmes: A Comprehensive Anomaly Detection System for Daily In-home Activities

Advances in wireless sensor networks have enabled the monitoring of daily activities of elderly people. The goal of these monitoring applications is to learn normal behavior in terms of daily activities and look for any deviation, i.e., Anomalies, so that alerts can be sent to relatives or caregivers. However, human behavior is very complex, and many existing anomaly detection systems are too simplistic which cause many false alarms, resulting in unreliable systems. We present Holmes, a comprehensive anomaly detection system for daily in-home activities. Holmes accurately learns a residents normal behavior by considering variability in daily activities based not only on a per day basis, but also considering specific days of the week, different time periods such as per week and per month, and collective, temporal, and correlation based features. This approach of learning complicated normal behaviors reduces false alarms. Also, based on resident and expert feedback, Holmes learns semantic rules that explain specific variations of activities in specific scenarios to further reduce false alarms. We evaluate Holmes using data collected from our own deployed system, public data sets, and data collected by a senior safety system provider company from an elderly residents home. Our evaluation shows that compared to state of the art systems, Holmes reduces false positives and false negatives by at least 46% and 27%, respectively.

Portable, non-invasive fall risk assessment in end stage renal disease patients on hemodialysis

Patients with end stage renal diseases (ESRD) on hemodialysis (HD) have high morbidity and mortality due to multiple causes, one of which is dramatically higher fall rates than the general population. The mobility mechanisms that contribute to falls in this population must be understood if adequate interventions for fall prevention are to be achieved. This study utilizes emerging non-invasive, portable gait, posture, strength, and stability assessment technologies to extract various mobility parameters that research has shown to be predictive of fall risk in the general population. As part of an ongoing human subjects study, mobility measures such as postural and locomotion profiles were obtained from five (5) ESRD patients undergoing HD treatments. To assess the effects of post-HD-fatigue on fall risk, both the pre- and post-HD measurements were obtained. Additionally, the effects of inter-HD periods (two days vs. three days) were investigated using the non-invasive, wireless, body-worn motion capture technology and novel signal processing algorithms. The results indicated that HD treatment influenced strength and mobility (i.e., weaker and slower after the dialysis, increasing the susceptibility to falls while returning home) and inter-dialysis period influenced pre-HD profiles (increasing the susceptibility to falls before they come in for a HD treatment). Methodology for early detection of increased fall risk -- before a fall event occurs -- using the portable mobility assessment technology for out-patient monitoring is further explored, including targeting interventions to identified individuals for fall prevention.

Validation of Noninvasive Body Sensor Network Technology in the Detection of Agitation in Dementia

Objective: Agitated behaviors are one of the most frequent reasons that patients with dementia are placed in long-term care settings. This study aims to validate the ability of a custom Body Sensor Network (BSN) to capture the presence of agitation against currently accepted subjective measures, the Cohen-Mansfield Agitation Inventory (CMAI) and the Aggressive Behavior Scale (ABS) and to discriminate between agitation and cognitive decline. Methods: Six patients identified as being at high risk for agitated behaviors were enrolled in this study. The devices were applied at three sites for three hours while behaviors were annotated simultaneously and subsequently repeated twice for each enrolled subject. Results: We found that the BSN was a valid measure of agitation based on construct validity testing and secondary validation using non-parametric ANOVAs. Discussion: The BSN shows promise from these pilot results. Further testing with a larger sample is needed to replicate these results.