While the potential benefits of smart home technology are widely recognized, a lightweight design is needed for the benefits to be realized at a large scale. We introduce the CASAS “smart home in a box”, a lightweight smart home design that is easy to install and provides smart home capabilities out of the box with no customization or training. We discuss types of data analysis that have been performed by the CASAS group and can be pursued in the future by using this approach to designing and implementing smart home technologies.

Older adults with mild cognitive impairment (MCI) often have difficulty performing complex instrumental activities of daily living (IADLs), which are critical to independent living. In this study, amnestic multi-domain MCI (N = 29), amnestic single-domain MCI (N = 18), and healthy older participants (N = 47) completed eight scripted IADLs (e.g., cook oatmeal on the stove) in a smart apartment testbed. We developed and experimented with a graded hierarchy of technology-based prompts to investigate both the amount of prompting and type of prompts required to assist individuals with MCI in completing the activities. When task errors occurred, progressive levels of assistance were provided, starting with the lowest level needed to adjust performance. Results showed that the multi-domain MCI group made more errors and required more prompts than the single-domain MCI and healthy older adult groups. Similar to the other two groups, the multi-domain MCI group responded well to the indirect prompts and did not need a higher level of prompting to get back on track successfully with the tasks. Need for prompting assistance was best predicted by verbal memory abilities in multi-domain amnestic MCI. Participants across groups indicated that they perceived the prompting technology to be very helpful.

The pervasive sensing technologies found in smart environments offer unprecedented opportunities for monitoring and assisting the individuals who live and work in these spaces. An aspect of daily life that is important for one's emotional and physical health is social interaction. In this paper we investigate the use of smart environment technologies to detect and analyze interactions in smart spaces. We introduce techniques for collect and analyzing sensor information in smart environments to help in interpreting resident behavior patterns and determining when multiple residents are interacting. The effectiveness of our techniques is evaluated using two physical smart environment testbeds.

The temporal nature of data collected in a smart environment provides us with a better understanding of patterns over time. Detecting anomalies in such datasets is a complex and challenging task. To solve this problem, we suggest a solution using temporal relations. Temporal pattern discovery based on modified Allen's temporal relations [5] has helped discover interesting patterns and relations on smart home datasets [10]. This paper describes a method of discovering temporal relations in smart home datasets and applying them to perform anomaly detection process on the frequently-occurring events. We also include experimental results, performed on real and synthetic datasets.

This study evaluates the ability of users to self-install a smart home in a box (SHiB) intended for use by a senior population. SHiB is a ubiquitous system, developed by the Washington State University Center for Advanced Studies in Adaptive Systems (CASAS). Participants involved in this study are from the greater Palouse region of Washington State, and there are 13 participants in the study with an average age of 69.23. The SHiB package, which included several different types of components to collect and transmit sensor data, was given to participants to self-install. After installation of the SHiB, the participants were visited by researchers for a check of the installation. The researchers evaluated how well the sensors were installed and asked the resident questions about the installation process to help improve the SHiB design. The results indicate strengths and weaknesses of the SHiB design. Indoor motion tracking sensors are installed with high success rate, low installation success rate was found for door sensors and setting up the Internet server.

No abstract

Intelligent environment research has resulted in many useful tools such as activity recognition, prediction, and automation. However, most of these techniques have been applied in the context of a single resident. A current looming issue for intelligent environment systems is performing these same techniques when multiple residents are present in the environment. In this paper we investigate the problem of attributing sensor events to individuals in a multiresident intelligent environment. Specifically, we use a naïve Bayesian classifier to identify the resident responsible for a unique sensor event. We present results of experimental validation in a real intelligent workplace testbed and discuss the unique issues that arise in addressing this challenging problem.

Abstract-In smart home environments, it is highly desirable to know who is performing what actions. This knowledge allows the system to accurately build individuals' histories and to take personalized action based on the current resident. Without a good handle on identity, multi-resident smart homes are less effective when used for medical and assistive applications.Most smart home systems either have a single occupancy requirement, or rely on a wireless or video device to identify individuals. These requirements are too burdensome in some situations, which can limit the deployment of smart home technologies in environments that would derive benefits from them. This research work introduces the use of passive sensors and a Hidden Markov Model as a means to identify individuals. The result is a passive, low profile means to attribute individual events to unique residents.For this work, two different pairs of individuals living in a smart home testbed are used to evaluate the tools. The data used is from unscripted, full time occupancy and annotated by the residents themselves for accuracy. Lastly, the Hidden Markov Model approach is compared and contrasted against a prior Naive Bayes solution on the same data sets.