Xianping Tao

epSICAR: An Emerging Patterns based approach to sequential, interleaved and Concurrent Activity Recognition

Recognizing human activities from sensor readings has recently attracted much research interest in pervasive computing. This task is particularly challenging because human activities are often performed in not only a simple (i.e., sequential), but also a complex (i.e., interleaved and concurrent) manner in real life. In this paper, we propose a novel Emerging Patterns based approach to Sequential, Interleaved and Concurrent Activity Recognition (epSICAR). We exploit Emerging Patterns as powerful discriminators to differentiate activities. Different from other learning-based models built upon the training dataset for complex activities, we build our activity models by mining a set of Emerging Patterns from the sequential activity trace only and apply these models in recognizing sequential, interleaved and concurrent activities. We conduct our empirical studies in a real smart home, and the evaluation results demonstrate that with a time slice of 15 seconds, we achieve an accuracy of 90.96% for sequential activity, 87.98% for interleaved activity and 78.58% for concurrent activity.

A Pattern Mining Approach to Sensor-Based Human Activity Recognition

Recognizing human activities from sensor readings has recently attracted much research interest in pervasive computing due to its potential in many applications, such as assistive living and healthcare. This task is particularly challenging because human activities are often performed in not only a simple (i.e., sequential), but also a complex (i.e., interleaved or concurrent) manner in real life. Little work has been done in addressing complex issues in such a situation. The existing models of interleaved and concurrent activities are typically learning-based. Such models lack of flexibility in real life because activities can be interleaved and performed concurrently in many different ways. In this paper, we propose a novel pattern mining approach to recognize sequential, interleaved, and concurrent activities in a unified framework. We exploit Emerging Pattern-a discriminative pattern that describes significant changes between classes of data-to identify sensor features for classifying activities. Different from existing learning-based approaches which require different training data sets for building activity models, our activity models are built upon the sequential activity trace only and can be applied to recognize both simple and complex activities. We conduct our empirical studies by collecting real-world traces, evaluating the performance of our algorithm, and comparing our algorithm with static and temporal models. Our results demonstrate that, with a time slice of 15 seconds, we achieve an accuracy of 90.96 percent for sequential activity, 88.1 percent for interleaved activity, and 82.53 percent for concurrent activity.

An unsupervised approach to activity recognition and segmentation based on object-use fingerprints

Human activity recognition is an important task which has many potential applications. In recent years, researchers from pervasive computing are interested in deploying on-body sensors to collect observations and applying machine learning techniques to model and recognize activities. Supervised machine learning techniques typically require an appropriate training process in which training data need to be labeled manually. In this paper, we propose an unsupervised approach based on object-use fingerprints to recognize activities without human labeling. We show how to build our activity models based on object-use fingerprints, which are sets of contrast patterns describing significant differences of object use between any two activity classes. We then propose a fingerprint-based algorithm to recognize activities. We also propose two heuristic algorithms based on object relevance to segment a trace and detect the boundary of any two adjacent activities. We develop a wearable RFID system and conduct a real-world trace collection done by seven volunteers in a smart home over a period of 2 weeks. We conduct comprehensive experimental evaluations and comparison study. The results show that our recognition algorithm achieves a precision of 91.4% and a recall 92.8%, and the segmentation algorithm achieves an accuracy of 93.1% on the dataset we collected.

Managing Quality of Context in Pervasive Computing

Context-awareness plays a key role in a paradigm shift from traditional desktop styled computing to emerging pervasive computing. Many context-aware systems have been built to achieve the vision of pervasive computing and alleviate the human attention bottleneck; however, these systems are far from real world applications. Quality of context is critical in reducing the gap between existing systems and real-life applications. Aiming to provide the support of quality of context, in this paper, we propose a novel quality model for context information and a context management mechanism for inconsistency resolution. We also build a prototype system to validate our proposed model and mechanism, and to assist the development of context-aware applications. Through our evaluations and case study, context-aware applications can be built with the support of quality of context

Recognizing multi-user activities using wearable sensors in a smart home

The advances of wearable sensors and wireless networks offer many opportunities to recognize human activities from sensor readings in pervasive computing. Existing work so far focuses mainly on recognizing activities of a single user in a home environment. However, there are typically multiple inhabitants in a real home and they often perform activities together. In this paper, we investigate the problem of recognizing multi-user activities using wearable sensors in a home setting. We develop a multi-modal, wearable sensor platform to collect sensor data for multiple users, and study two temporal probabilistic models-Coupled Hidden Markov Model (CHMM) and Factorial Conditional Random Field (FCRF)-to model interacting processes in a sensor-based, multi-user scenario. We conduct a real-world trace collection done by two subjects over two weeks, and evaluate these two models through our experimental studies. Our experimental results show that we achieve an accuracy of 96.41% with CHMM and an accuracy of 87.93% with FCRF, respectively, for recognizing multi-user activities.

A hierarchical approach to real-time activity recognition in body sensor networks

Real-time activity recognition in body sensor networks is an important and challenging task. In this paper, we propose a real-time, hierarchical model to recognize both simple gestures and complex activities using a wireless body sensor network. In this model, we first use a fast and lightweight algorithm to detect gestures at the sensor node level, and then propose a pattern based real-time algorithm to recognize complex, high-level activities at the portable device level. We evaluate our algorithms over a real-world dataset. The results show that the proposed system not only achieves good performance (an average utility of 0.81, an average accuracy of 82.87%, and an average real-time delay of 5.7 seconds), but also significantly reduces the networks communication cost by 60.2%.

FTrack: Infrastructure-free floor localization via mobile phone sensing

Mobile phone localization plays a key role in the fast-growing Location Based Applications domain. Most of the existing localization schemes rely on infrastructure support such as GSM, WiFi or GPS. In this paper, we present FTrack, a novel floor localization system to identify the floor level in a multi-floor building on which a mobile user is located. FTrack uses the mobile phones accelerometer only without any infrastructure support. It does not require any prior knowledge of the building such as floor height. By capturing user encounters and analyzing user trails, FTrack finds the mapping from the traveling time (when taking the elevator) or the step counts (when walking on the stairs) between any two floors to the number of floor levels. The mapping can then be used for mobile users to pinpoint their current floor levels. We conduct both simulation and field studies to demonstrate the effectiveness of FTrack. Our field trial in a 10-floor building shows that FTrack achieves an accuracy of over 90% after two hours in our experiment.

Sensor-Based Human Activity Recognition in a Multi-user Scenario

Existing work on sensor-based activity recognition focuses mainly on single-user activities. However, in real life, activities are often performed by multiple users involving interactions between them. In this paper, we propose Coupled Hidden Markov Models (CHMMs) to recognize multi-user activities from sensor readings in a smart home environment. We develop a multimodal sensing platform and present a theoretical framework to recognize both single-user and multi-user activities. We conduct our trace collection done in a smart home, and evaluate our framework through experimental studies. Our experimental result shows that we achieve an average accuracy of 85.46% with CHMMs.

FollowMe: on research of pluggable infrastructure for context-awareness

Pervasive computing is to enhance the environment by embedding many computers that are gracefully integrated with human users. To achieve this, the key research thrust is to create a smart context-awareness environment which should enclose various users and satisfy different needs of the users. Building such smart environments is still difficult and complex due to lacking a uniform infrastructure that can adapt to diverse smart domains. To address this problem, we propose a context-aware computing infrastructure, called FollowMe. Our infrastructure integrates an ontology based context model and a workflow based application model with the OSGi framework. By plugging different domain contexts and applications, FollowMe can be customized to various domains.

Concurrent Event Detection for Asynchronous consistency checking of pervasive context

Contexts, the pieces of information that capture the characteristics of computing environments, are often inconsistent in the dynamic and uncertain pervasive computing environments. Various schemes have been proposed to check context consistency for pervasive applications. However, existing schemes implicitly assume that the contexts being checked belong to the same snapshot of time. This limitation makes existing schemes do not work in pervasive computing environments, which are characterized by the asynchronous coordination among computing devices. The main challenge imposed on context consistency checking by asynchronous environments is how to interpret and detect concurrent events. To this end, we propose in this paper the Concurrent Events Detection for Asynchronous consistency checking (CEDA) algorithm. An analytical model, together with corresponding numerical results, is derived to study the performance of CEDA. We also conduct extensive experimental evaluation to investigate whether CEDA is desirable for context-aware applications. Both theoretical analysis and experimental evaluation show that CEDA accurately detects concurrent events in time in asynchronous pervasive computing environments, even with dynamic changes in message delay, duration of events and error rate of context collection.