Wenyao Xu

Designing a Robust Activity Recognition Framework for Health and Exergaming Using Wearable Sensors

Detecting human activity independent of intensity is essential in many applications, primarily in calculating metabolic equivalent rates and extracting human context awareness. Many classifiers that train on an activity at a subset of intensity levels fail to recognize the same activity at other intensity levels. This demonstrates weakness in the underlying classification method. Training a classifier for an activity at every intensity level is also not practical. In this paper, we tackle a novel intensity-independent activity recognition problem where the class labels exhibit large variability, the data are of high dimensionality, and clustering algorithms are necessary. We propose a new robust stochastic approximation framework for enhanced classification of such data. Experiments are reported using two clustering techniques, K-Means and Gaussian Mixture Models. The stochastic approximation algorithm consistently outperforms other well-known classification schemes which validate the use of our proposed clustered data representation. We verify the motivation of our framework in two applications that benefit from intensity-independent activity recognition. The first application shows how our framework can be used to enhance energy expenditure calculations. The second application is a novel exergaming environment aimed at using games to reward physical activity performed throughout the day, to encourage a healthy lifestyle.

Accelerometer-based on-body sensor localization for health and medical monitoring applications

In this paper, we present a technique to recognize the position of sensors on the human body. Automatic on-body device localization ensures correctness and accuracy of measurements in health and medical monitoring systems. In addition, it provides opportunities to improve the performance and usability of ubiquitous devices. Our technique uses accelerometers to capture motion data to estimate the location of the device on the users body, using mixed supervised and unsupervised time series analysis methods. We have evaluated our technique with extensive experiments on 25 subjects. On average, our technique achieves 89% accuracy in estimating the location of devices on the body. In order to study the feasibility of classification of left limbs from right limbs (e.g., left arm vs. right arm), we performed analysis, based of which no meaningful classification was observed. Personalized ultraviolet monitoring and wireless transmission power control comprise two immediate applications of our on-body device localization approach. Such applications, along with their corresponding feasibility studies, are discussed.

Smart insole: a wearable system for gait analysis

Gait analysis is an important medical diagnostic process and has many applications in rehabilitation, therapy and exercise training. However, standard human gait analysis has to be performed in a specific gait lab and operated by a medical professional. This traditional method increases the examination cost and decreases the accuracy of the natural gait model. In this paper, we present a novel portable system, called Smart Insole, to address the current issues. Smart Insole integrates low cost sensors and computes important gait features. In this way, patients or users can wear Smart Insole for gait analysis in daily life instead of participating in gait lab experiments for hours. With our proposed portable sensing system and effective feature extraction algorithm, the Smart Insole system enables precise gait analysis. Furthermore, taking advantage of the affordability and mobility of Smart Insole, pervasive gait analysis can be extended to many potential applications such as fall prevention, life behavior analysis and networked wireless health systems.

Cluster size optimization in sensor networks with decentralized cluster-based protocols

Network lifetime and energy-efficiency are viewed as the dominating considerations in designing cluster-based communication protocols for wireless sensor networks. This paper analytically provides the optimal cluster size that minimizes the total energy expenditure in such networks, where all sensors communicate data through their elected cluster heads to the base station in a decentralized fashion. LEACH, LEACH-Coverage, and DBS comprise three cluster-based protocols investigated in this paper that do not require any centralized support from a certain node. The analytical outcomes are given in the form of closed-form expressions for various widely-used network configurations. Extensive simulations on different networks are used to confirm the expectations based on the analytical results. To obtain a thorough understanding of the results, cluster number variability problem is identified and inspected from the energy consumption point of view.

A dense pressure sensitive bedsheet design for unobtrusive sleep posture monitoring

Sleep plays a pivotal role in the quality of life, and sleep posture is related to many medical conditions such as sleep apnea. In this paper, we design a dense pressure-sensitive bedsheet for sleep posture monitoring. In contrast to existing techniques, our bedsheet system offers a completely unobtrusive method using comfortable textile sensors. Based on high-resolution pressure distributions from the bedsheet, we develop a novel framework for pressure image analysis to monitor sleep postures, including a set of geometrical features for sleep posture characterization and three sparse classifiers for posture recognition. We run a pilot study and evaluate the performance of our methods with 14 subjects to analyze 6 common postures. The experimental results show that our proposed method enables reliable sleep posture recognition and offers better overall performance than state-of-the-art methods, achieving up to 83.0% precision and 83.2% recall on average.

eCushion: A Textile Pressure Sensor Array Design and Calibration for Sitting Posture Analysis

Sitting posture analysis is widely applied in many daily applications in biomedical, education, and health care domains. It is interesting to monitor sitting postures in an economic and comfortable manner. Accordingly, we present a textile-based sensing system, called Smart Cushion, which analyzes the sitting posture of human being accurately and non-invasively. First, we introduce the electrical textile sensor and its electrical characteristics, such as offset, scaling, crosstalk, and rotation. Second, we present the design and implementation of the Smart Cushion system. Several effective techniques have been proposed to improve the recognition rate of sitting postures, including sensor calibration, data representation, and dynamic time warping-based classification. Last, our experimental results show that the recognition rate of our Smart Cushion system is in excess of 85.9%.

eCushion: An eTextile Device for Sitting Posture Monitoring

Sitting posture analysis is critical for daily applications in biomedical, education and healthcare fields. However, it remains unclear how to monitor sitting posture economically and comfortably. To this end, we presented an eTextile device, called eCushion, in this paper, which can analyze the sitting posture of human being accurately and non-invasively. First, we discussed the implementation of eCushion and design challenges of sensing data, such as scale, offset, rotation and crosstalk. Then, several effective techniques have been proposed to improve the recognition rate of sitting posture. Our experimental results show that the recognition rate of our eCushion system could achieve 92% for object-oriented cases and 79% for general cases.

Co-recognition of Human Activity and Sensor Location via Compressed Sensing in Wearable Body Sensor Networks

Human activity recognition using wearable body sensors is playing a significant role in ubiquitous and mobile computing. One of the issues related to this wearable technology is that the captured activity signals are highly dependent on the location where the sensors are worn on the human body. Existing research work either extracts location information from certain activity signals or takes advantage of the sensor location information as a priori to achieve better activity recognition performance. In this paper, we present a compressed sensing-based approach to co-recognize human activity and sensor location in a single framework. To validate the effectiveness of our approach, we did a pilot study for the task of recognizing 14 human activities and 7 on body-locations. On average, our approach achieves an 87:72% classification accuracy (the mean of precision and recall).

Robust Human Activity and Sensor Location Corecognition via Sparse Signal Representation

Human activity recognition with wearable body sensors receives lots of attentions in both research and industrial communities due to the significant role in ubiquitous and mobile health monitoring. One of the most concerned issues related to this wearable technology is that the sensor signals significantly depends on where the sensors are worn on the human body. Existing research work either extracts location information from the activity signals or takes advantage of the sensor location information as a priori information to achieve better activity recognition performance. In this paper, we present a sparse signal-based approach to corecognize human activity and sensor location in a single framework. Therefore, the wearable sensor is not necessarily constrained to fixed body position and the deployment is much easier although the recognition difficulty becomes much more challenging. To validate the effectiveness of our approach, we run a pilot study in the lab, which includes 14 human activities and seven on-body locations to recognize. The experimental results show that our approach achieves an 87.72% classification accuracy (the mean of precision and recall), which outperforms classical classification methods.

Unobtrusive Sleep Stage Identification Using a Pressure-Sensitive Bed Sheet

Sleep constitutes a big portion of our lives and is a major part of health and well-being. Monitoring the quality of sleep can aid in the medical diagnosis of a variety of sleep and psychiatric disorders and can serve as an indication of several chronic diseases. Sleep stage analysis plays a pivotal role in the evaluation of the quality of sleep and is a proven biometric in diagnosing cardiovascular disease, diabetes, and obesity [32]. We describe an unobtrusive framework for sleep stage identification based on a high-resolution pressure-sensitive e-textile bed sheet. We extract a set of sleep-related biophysical and geometric features from the bed sheet and use a two-phase classification procedure for Wake-Non Rapid Eye Movement-Rapid Eye Movement stage identification. A total of seven all-night polysomnography recordings from healthy subjects were used to validate the proposed bed sheet system and the ability to extract sleep stage information from it. When compared with the gold standard, the described system achieved 70.3% precision and 71.1% recall on average. These results suggest that unobtrusive sleep macrostructure analysis could be a viable option in clinical and home settings in the near future. Compared with existing techniques for sleep stage identification, the described system is unobtrusive, fits seamlessly into the users familiar sleep environment, and has additional advantages of comfort, low cost, and simplicity.