Ambient intelligence has a history of focusing on technologies that are integrated into a person's environment. However, ambient intelligence can be found on a person's body as well. In this thematic issue we examine the role of wearable computing in the field of ambient intelligence. In this article we provide an overview of the field of wearable computing and discuss its relationship to the fields of smart environments and ambient intelligence. In addition, we introduce the papers presented in the thematic issue highlighting a number of research projects which are defining the state of the art in wearable computing and ambient intelligence.

One of the major goals of Ambient Intelligence and Smart Environments is to interpret human activity sensed by a variety of sensors. In order to develop useful technologies and a subsequent industry around smart environments, we need to proceed in a principled manner. This paper suggests that human activity can be expressed in a language. This is a special language with its own phonemes, its own morphemes (words) and its own syntax and it can be learned using machine learning techniques applied to gargantuan amounts of data collected by sensor networks. Developing such languages will create bridges between Ambient Intelligence and other disciplines. It will also provide a hierarchical structure that can lead to a successful industry.

The pervasive sensing technologies found in smart environments offer unprecedented opportunities for monitoring and assisting the individuals who live and work in these spaces. As aspect of daily life that is often overlooked in maintaining a healthy lifestyle is the air quality of the environment. In this paper we investigate the use of machine learning technologies to predict CO(2) levels as an indicator of air quality in smart environments. We introduce techniques for collecting and analyzing sensor information in smart environments and analyze the correlation between resident activities and air quality levels. The effectiveness of our techniques is evaluated using three physical smart environment testbeds.

In-home monitoring of gait velocity with passive PIR sensors in a smart home has been shown to be an effective method of continuously and unobtrusively measuring this important predictor of cognitive function and mobility. However, passive measurements of velocity are nonspecific with regard to who generated each measurement or walking event. As a result, this method is not suitable for multi-person homes without additional information to aid in the disambiguation of gait velocities. In this paper we propose a method based on Gaussian mixture models (GMMs) combined with infrequent clinical assessments of gait velocity to model in-home walking speeds of two or more residents. Modeling the gait parameters directly allows us to avoid the more difficult problem of assigning each measured velocity individually to the correct resident. We show that if the clinically measured gait velocities of residents are separated by at least 15 cm/s a GMM can be accurately fit to the in-home gait velocity data. We demonstrate the accuracy of this method by showing that the correlation between the means of the GMMs and the clinically measured gait velocities is 0.877 (p value < 0.0001) with bootstrapped 95% confidence intervals of (0.79, 0.94) for 54 measurements of 20 subjects living in multi-person homes. Example applications of using this method to track in-home mean velocities over time are also given.

Many intelligent systems that focus on the needs of a human require information about the activities that are being performed by the human. At the core of this capability is activity recognition. Activity recognition techniques have become robust but rarely scale to handle more than a few activities. They also rarely learn from more than one smart home data set because of inherent differences between labeling techniques. In this paper we investigate a data-driven approach to creating an activity taxonomy from sensor data found in disparate smart home datasets. We investigate how the resulting taxonomy can help analyze the relationship between classes of activities. We also analyze how the taxonomy can be used to scale activity recognition to a large number of activity classes and training datasets. We describe our approach and evaluate it on 34 smart home datasets. The results of the evaluation indicate that the hierarchical modeling can reduce training time while maintaining accuracy of the learned model.

The public health implications of growing numbers of older adults at risk for dementia places pressure on identifying dementia at its earliest stages so as to develop proactive management plans. The prodromal dementia phase commonly identified as mild cognitive impairment is an important target for this early detection of impending dementia amenable to treatment. In this paper, we propose a method for home-based automatic detection of mild cognitive impairment in older adults through continuous monitoring via unobtrusive sensing technologies. Our method is composed of two main stages: a training stage and a test stage. For training, room activity distributions are estimated for each subject using a time frame of ω weeks, and then affinity propagation is employed to cluster the activity distributions and to extract exemplars to represent the different emerging clusters. For testing, room activity distributions belonging to a test subject with unknown cognitive status are compared to the extracted exemplars and get assigned the labels of the exemplars that result in the smallest normalized Kullbak-Leibler divergence. The labels of the activity distributions are then used to determine the cognitive status of the test subject. Using the sensor and clinical data pertaining to 85 homes with single occupants, we were able to automatically detect mild cognitive impairment in older adults with an score of 0.856. Also, we were able to detect the non-amnestic sub-type of mild cognitive impairment in older adults with an score of 0.958.