BSNs perform long-term, continuous, remote monitoring of physiologic and bio kinematic information. Because of varying computational, storage and communication capabilities at different layers of the BSN, system designers must make design choices that trade-off information quality with resource consumption and battery lifetime. Given these trade-offs there is the possibility that the information provided to the health practitioner may deviate from what was originally sensed, causing the doctor to perform the wrong diagnosis. These trade-offs are based on traditional measures of data quality like RMSE, but those don’t correlate well with the notion of information quality for a particular application. Objective metrics of information distortion and its effect on decision making are necessary to help designers to make more informed trade-off, and to help practitioners understand the kind of information provided by the BSN.
Body area sensor networks (BASN) are emerging cyber-physical systems that promise to improve quality of life through improved health, augmented sensing and actuation for the disabled, independent living for the elderly, and reduced healthcare costs. However, the physical nature of BASNs introduces several new challenges. The human body is a highly dynamic and unpredictable physical environment that creates constantly changing demands on sensing, actuation, and quality of service (QoS). The various locations that users visit, their choice of clothing also adds to the unpredictability of the environment. Thus, BASNs 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 BASN devices, which necessitates a vanishingly small size and therefore extremely limited hardware resources and power budget. This project seeks to develop new principles and techniques for realiable adaptive operation in highly dynamic physical environments, using miniaturized, energy-constrained devices.
Body-Area Sensor Network (BASN) efficacy is predicated by application-oriented, outcome-focused demands, which include strict resource and fidelity requirements in Wireless Health applications. Since a large amount of the energy consumed by a BASN node is due to the wireless radio used to stream data to an aggregator on or off body, significant power reduction can be achieved through the development of scalable, on-node techniques like signal processing and data management, thus dramatically reducing the number of bits to be transmitted. Low power signal processing therefore becomes increasingly important to BASN power efficiency. However, the amount of “information” present in the sensor signals changes over time along with the rate-distortion curve pointing to the need for dynamic management of energy-fidelity tradeoffs in these embedded environments. This work uses embedded hardware and software techniques to dynamically manage the energy-fidelity relationship that exists in many BASN applications thereby enabling smaller, more wearable devices with longer runtimes.
Currently smart homes / assisted living centers are instrumented with different kinds of passive sensors. From these sensors we get a series of sensor firings each of which has a corresponding timestamp. From these lower level data, we want to infer higher level activities. Our goal is to infer which sensors are used for an activity and in which order, typical occurence times and durations of an activity, and typical intervals between the sensor firings of an activity.
We present the real-time 24/7 data-flow architecture for our depression monitoring system. Heterogeneous sensors such as infrared motion sensors, wireless weight scales, accelerometers on the bed, acoustic sensors on a smart phone or in the environment, anonymity-aware cameras, and contact sensors are deployed in a home. The architecture is extensible and new sensor types can be added as needed. Each stream is generated by a device and often preprocessed at the device - (compressing, summarizing, or removing noise) before being sent to and inserted into the main database. In addition to the main database there is an archiving database that is used for saving the original high data-rate periodic raw data. The reason we separate the raw data from the processed data is that filtering and selecting dense data is computationally expensive, and often times, the behavior modules do not need information at that resolution. However, the archived information enables new pre-processing techniques to be applied when advances are made in knowledge discovery from low level patterns or any time when it becomes useful to re-look at the raw data.
This work is devoted to the exploration of Artificial Neural Network Classifiers for use on resource-constrained computing platforms as a mechanism for extending the operational time by preselecting “interesting” data for transmission or storage as opposed to the more conventional practice of simply streaming all incoming data. The execution environment found in microcontrollers of the class typically used in Wearable Body Sensor Network devices or other small, resource constrained data acquisition and control systems is very limited - typical clock speeds are on the order of 10 megahertz, and memory capacities are in the range of 2 to10 kilobytes of random access memory and up to 60 kilobytes of flash. There is no floating point hardware available and the instruction set usually only includes operations for integer add, subtract, and multiply – besides the normal complement of logical, shift, and rotate instructions. A challenge has been to identify classifiers suitable for such a computing environment, and characterize their capabilities.
In this project, a low power wireless ECG sensor is implemented using commercial off the shelf (COTS) components. The resulting system can acquire and process ECG data and send it wirelessly to a basestation such as a handheld device. The picture shows the ECG sensor in operation, with the PDA plotting the real time ECG signal.
This project centers on the development of a custom system-on-chip (SoC)for electrocardiogram (ECG) acquisition and analysis. ECG data is important for medical diagnosis of general health and of many specific conditions, including a variety of cardiac arrhythmias. Existing methods of capturing ECG outside of the clinical setting, such as Holter monitors or event monitors, either have limited lifetimes or non continuous acquisition. This project seeks to develop custom hardware to dramatically extend the lifetime of ECG acquisition circuits by fabricating a custom SoC.
The dynamic nature of BASNs can be leveraged to achieve power efficient, on-node signal processing through dynamic voltage-frequency scaling (DVFS). For example, in tremor analysis, there will be periods of little activity where resource requirements will be lower since data can either be ignored or fewer processing can occur. However, most COTS components that are used on BASN nodes are not specifically designed for DVFS operation. Using DVFS with COTS components allows for low-cost, low-power wireless nodes to adjust operating parameters to application and environment requirements. This work presents techniques for scaling frequency and voltage operation on the TI MSP430, a typical BASN microcontroller found in TEMPO 3.1.