Lawrence K. Au

MEDIC: Medical embedded device for individualized care

OBJECTIVE Presented work highlights the development and initial validation of a medical embedded device for individualized care (MEDIC), which is based on a novel software architecture, enabling sensor management and disease prediction capabilities, and commercially available microelectronic components, sensors and conventional personal digital assistant (PDA) (or a cell phone). METHODS AND MATERIALS In this paper, we present a general architecture for a wearable sensor system that can be customized to an individual patients needs. This architecture is based on embedded artificial intelligence that permits autonomous operation, sensor management and inference, and may be applied to a general purpose wearable medical diagnostics. RESULTS A prototype of the system has been developed based on a standard PDA and wireless sensor nodes equipped with commercially available Bluetooth radio components, permitting real-time streaming of high-bandwidth data from various physiological and contextual sensors. We also present the results of abnormal gait diagnosis using the complete system from our evaluation, and illustrate how the wearable system and its operation can be remotely configured and managed by either enterprise systems or medical personnel at centralized locations. CONCLUSION By using commercially available hardware components and software architecture presented in this paper, the MEDIC system can be rapidly configured, providing medical researchers with broadband sensor data from remote patients and platform access to best adapt operation for diagnostic operation objectives.

The SmartCane system: an assistive device for geriatrics

Falls are currently a leading cause of death from injury in the elderly. The usage of the conventional assistive cane devices is critical in reducing the risk of falls and is relied upon by over 4 million patients in the U.S.. While canes provide physical support as well as supplementary sensing feedback to patients, at the same time, these conventional aids also exhibit serious adverse effects that contribute to falls. The falls due to the improper usage of the canes are particularly acute in the elderly and disabled where reduced cognitive capacity accompanied by the burden of managing cane motion leads to increased risk. This paper describes the development of the SmartCane assistive system that encompasses broad engineering challenges that will impact general development of individualized, robust assistive and prosthetic devices. The SmartCane system combines advances in signal processing, embedded computing, and wireless networking technology to provide capabilities for remote monitoring, local signal processing, and real-time feedback on the cane usage. This system aims to reduce risks of injuries and falls by enabling training and guidance of patients in proper usage of assistive devices.

MicroLEAP: Energy-aware Wireless Sensor Platform for Biomedical Sensing Applications

Extended system lifetime is a critical requirement for wearable sensor platforms. However, these platforms must also accommodate local data processing, data storage, and broadband wireless communications. Since compact battery storage capacity is constrained, there exists a fundamental tradeoff between energy optimization and performance. Furthermore, biomedical transducers may also demand high peak power dissipation during active operations. Energy management, therefore, must be introduced through new hardware architecture and enabled through software in the overall system design. To effectively optimize energy dissipation for biomedical sensing applications, a new wearable sensor platform, MicroLEAP, has been developed. The MicroLEAP platform supports per-task real-time energy profiling to permit adaptive applications that select platform components to best match dynamically-varying measurement requirements. MicroLEAP design, implementation, and example of energy-aware operation are demonstrated.

SmartFall: an automatic fall detection system based on subsequence matching for the SmartCane

Fall-induced injury has become a leading cause of death for the elderly. Many elderly people rely on canes as an assistive device to overcome problems such as balance disorder and leg weakness, which are believed to have led to many incidents of falling. In this paper, we present the design and the implementation of SmartFall, an automatic fall detection system for the SmartCane system we have developed previously. SmartFall employs subsequence matching, which differs fundamentally from most existing fall detection systems based on multi-stage thresholding. The SmartFall system achieves a near perfect fall detection rate for the four types of fall conducted in the experiments. After augmenting the algorithm with an assessment on the peak impact force, we have successfully reduced the false-positive rate of the system to close to zero for all six non-falling activities performed in the experiment.

Context-aware Sensing of Physiological Signals

Recent advancement in microsensor technology permits miniaturization of conventional physiological sensors. Combined with low-power, energy-aware embedded systems and low power wireless interfaces, these sensors now enable patient monitoring in home and workplace environments in addition to the clinic. Low energy operation is critical for meeting typical long operating lifetime requirements. Some of these physiological sensors, such as electrocardiographs (ECG), introduce large energy demand because of the need for high sampling rate and resolution, and also introduce limitations due to reduced user wearability. In this paper, we show how context-aware sensing can provide the required monitoring capability while eliminating the need for energy-intensive continuous ECG signal acquisition. We have implemented a wearable system based on standard widely-used handheld computing hardware components. This system relies on a new software architecture and an embedded inference engine developed for these standard platforms. The performance of the system is evaluated using experimental data sets acquired for subjects wearing this system during an exercise sequence. This same approach can be used in context-aware monitoring of diverse physiological signals in a patients daily life.

Episodic sampling: Towards energy-efficient patient monitoring with wearable sensors

Energy efficiency presents a critical design challenge in wireless, wearable sensor technology, mainly because of the associated diagnostic objectives required in each monitoring application. In order to maximize the operating lifetime during real-life monitoring and maintain sufficient classification accuracy, the wearable sensors require hardware support that allows dynamic power control on the sensors and wireless interfaces as well as monitoring algorithms to control these components intelligently. This paper introduces a context-aware sensing technique known as episodic sampling – a method of performing context classification only at specific time instances. Based on Additive-Increase/Multiplicative-Decrease (AIMD), episodic sampling demonstrates an energy reduction of 85 percent with a loss of only 5 percent in classification accuracy in our experiment.

Active guidance towards proper cane usage

The usage of conventional assistive cane devices is critical in reducing the risk of falls, which are particularly detrimental to the elderly and disabled. Individuals that experience the greatest risks rely on cane devices for support of ambulation. Results of many studies, however, have shown that incorrect cane usage is prevalent among cane users. The original SmartCane assistive system has been developed to provide a method for acquiring detailed motion data from cane usage. The cane itself, however, lacks any type of programmability as well as real-time data processing algorithms to provide feedback to the cane user. This paper describes the development of a real-time sensor information processing algorithm that provides direct detection of cane usage characteristics. Specifically, it supports direct feedback to the cane user, permitting guidance for proper cane usage and reducing the risk of falls. This paper also aims to improve upon the existing system by incorporating MicroLEAP, an energy-aware embedded computing platform. The new system provides local data processing capability by classifying whether an individual is executing a stride with proper cane motion and applied forces.

Demonstration of Active Guidance with SmartCane

The usage of conventional assistive cane devices is critical in reducing the risk of falls, which are particularly detrimental for the elderly and disabled. Many of the individuals that experience the greatest risk of falling rely on cane devices for support of ambulation. However, the results of many studies have shown that incorrect cane usage is prevalent among cane users. The original SmartCane assistive system has been developed to provide a method for acquiring detailed motion data from cane usage. The cane itself, however, lacks any type of programmability as well as real-time data processing algorithms to provide feedback to the cane user. In this demonstration, we have incorporated an embedded computing platform into SmartCane and developed a real-time sensor information processing algorithm that provides direct detection of cane usage characteristics. The new system provides local data processing capability by classifying whether an individual is executing a stride with proper cane motion and applied forces. It also provides direct feedback information to the individual, thereby guiding the subject towards proper cane usage and reducing the risk of falls.

Energy-Efficient Context Classification With Dynamic Sensor Control

Energy efficiency has been a longstanding design challenge for wearable sensor systems. It is especially crucial in continuous subject state monitoring due to the ongoing need for compact sizes and better sensors. This paper presents an energy-efficient classification algorithm, based on partially observable Markov decision process (POMDP). In every time step, POMDP dynamically selects sensors for classification via a sensor selection policy. The sensor selection problem is formalized as an optimization problem, where the objective is to minimize misclassification cost given some energy budget. State transitions are modeled as a hidden Markov model (HMM), and the corresponding sensor selection policy is represented using a finite-state controller (FSC). To evaluate this framework, sensor data were collected from multiple subjects in their free-living conditions. Relative accuracies and energy reductions from the proposed method are compared against naïve Bayes (always-on) and simple random strategies to validate the relative performance of the algorithm. When the objective is to maintain the same classification accuracy, significant energy reduction is achieved.

CARER: Efficient dynamic sensing for continuous activity monitoring

Advancement in wireless health sensor systems has triggered rapidly expanding research in continuous activity monitoring for chronic disease management or promotion and assessment of physical rehabilitation. Wireless motion sensing is increasingly important in treatments where remote collection of sensor measurements can provide an in-field objective evaluation of physical activity patterns. The well-known challenge of limited operating lifetime of energy-constrained wireless health sensor systems continues to present a primary limitation for these applications. This paper introduces CARER, a software system that supports a novel algorithm that exploits knowledge of context and dynamically schedules sensor measurement episodes within an energy consumption budget while ensuring classification accuracy. The sensor selection algorithm in the CARER system is based on Partially Observable Markov Decision Process (POMDP). The parameters for the POMDP algorithm can be obtained through standard maximum likelihood estimation. Sensor data are also collected from multiple locations of the subjects body, providing estimation of an individuals daily activity patterns.