Monica Tentori

Activity Recognition for the Smart Hospital

Although researchers have developed robust approaches for estimating, location, and user identity, estimating user activities has proven much more challenging. Human activities are so complex and dynamic that its often unclear what information is even relevant for modeling activities. Robust approaches to recognize user activities requires identifying the relevant information to be sensed and the appropriate sensing technologies. In our effort to develop an approach for automatically estimating hospital-staff activities, we trained a discrete hidden Markov model (HMM) to map contextual information to a user activity. We trained the model and evaluated it using data captured from almost 200 hours of detailed observation and documentation of hospital workers. In this article, we discuss our approach, the results, and how activity recognition could empower our vision of the hospital as a smart environment.

MOSOCO: a mobile assistive tool to support children with autism practicing social skills in real-life situations

MOSOCO is a mobile assistive application that uses augmented reality and the visual supports of a validated curriculum, the Social Compass, to help children with autism practice social skills in real-life situations. In this paper, we present the results of a seven-week deployment study of MOSOCO in a public school in Southern California with both students with autism and neurotypical students. The results of our study demonstrate that MOSOCO facilitates practicing and learning social skills, increases both quantity and quality of social interactions, reduces social and behavioral missteps, and enables the integration of children with autism in social groups of neurotypical children. The findings from this study reveal emergent practices of the uses of mobile assistive technologies in real-life situations.

Mobility in hospital work: towards a pervasive computing hospital environment

Handheld computers are increasingly being used by hospital workers. With the integration of wireless networks into hospital information systems, handheld computers can provide the basis for a pervasive computing hospital environment; to develop this designers need empirical information to understand how hospital workers interact with information while moving around. To characterise the medical phenomena we report the results of a workplace study conducted in a hospital. We found that individuals spend about half of their time at their base location, where most of their interactions occur. On average, our informants spent 23% of their time performing information management tasks, followed by coordination (17.08%), clinical case assessment (15.35%) and direct patient care (12.6%). We discuss how our results offer insights for the design of pervasive computing technology, and directions for further research and development in this field such as transferring information between heterogeneous devices and integration of the physical and digital domains.

Privacy-Aware Autonomous Agents for Pervasive Healthcare

Hospitals are convenient settings for deploying pervasive computing technology, but they also raise important privacy concerns. Hospital work imposes significant demands on staff, including high availability, careful attention to patients, confidentiality, rapid response to emergencies, and constant coordination with colleagues. These demands shape the way hospital workers experience and understand privacy. In addition, healthcare professionals experience a high level of mobility because they must collaborate with colleagues and access information and artifacts distributed throughout the premises. Autonomous agents can help developers design privacy-aware systems that handle the threats raised by pervasive technology

Ambient Awareness to Strengthen the Family Social Network of Older Adults

Social networking sites (SNSs) provide ambient awareness of the interests and activities of friends and relatives helping them sustain and strengthen their social ties. Older adults who are not adopting SNSs might however feel like outsiders within their own families who increasingly rely on these services to socialize. Previous research has shown that situated displays can provide appropriate interfaces for older adults to use digital services. In this paper we explore how situated displays can intuitively provide ambient awareness to strengthen the family social network of older adults. We designed and developed Tlatoque, a situated display, to seamlessly integrate older adults into the SNS used by their relatives. The results of a 21-week deployment study of an initial version of Tlatoque in one extended family showed that the older adult became more conscious of relatives’ activities, which also enriched in-person encounters. However, relatives expected the older adult to reply to their posts in the SNS and Tlatoque lacked mechanisms for the older adult to provide feedback. We re-designed Tlatoque to incorporate means for enabling the older adult to share information back to the SNS. We conducted a second 21-week deployment study with another extended family to evaluate the use of this new version of the system. Our results indicate that the second design was successful in providing ambient awareness to the older adult as well as to her relatives. We conclude that situated displays that provide SNS services can assist the integration of older adults to their social network and contribute to enhance asymmetric relations between the older adult and younger relatives.

Hidden Markov Models for Activity Recognition in Ambient Intelligence Environments

This paper presents a process for the development of a model-driven architecture (MDA) tool for the construction of service-oriented component-based applications. The process is used in the construction of a tool for one particular domain, but can be easily adapted to other domains. The tool in itself simplifies the development of components using a MDA approach, in which modeling is at the core of the development activities. After components are modeled, the tool validates the correctness of the design of the model based in a specification that is embedded inside the tool. Once the model has been validated, the tool is capable of creating the skeletons of the code for the components which are then executed inside the OSGi platform.Context-aware computing offers several advantages for human computer interaction by augmenting ambient intelligence environments with computational artifacts that can be responsive to the needs of users. One of the main challenges in context-aware computing is context recognition. While some contextual variables, such as location, can be easily recognized, others, such as activity are more complex to estimate. This paper describes an approach to estimate activities in a working environment. The approach is based on information gathered from a workplace study, in which 196 hours of detailed observation of hospital workers were recorded. This data is used to train a Hidden Markov Model to estimate user activity. The results indicate that the user activity can be correctly estimated 92.6% of the time. We compare our results with the use of neuronal networks and human observers familiar with those work practice. We discuss how these results can be used for context-aware applications.

Using Augmented Reality to Help Children with Autism Stay Focused

Children with autism have difficulty sustaining their selective attention during therapy sessions. Attention management techniques involve the use of verbal and visual prompting, annotated on top of the physical objects used during therapies. Here, the authors explore how augmented reality helps integrate the physical and digital worlds, mimicking current strategies for attention management in autism. They describe their design decisions when developing the Mobile Object Identification System (Mobis), a mobile augmented reality application that lets teachers superimpose digital content on top of physical objects. The results of a five-week deployment study demonstrate that Mobis is useful and easy to use, increases the sustained and selective attention of children with autism, and elicits positive emotions during therapies. This article is part of a special issue on managing attention.

Pervasive Computing for Hospital, Chronic, and Preventive Care

An emerging area of great impact and significance is the application of pervasive computing technologies in healthcare. Pervasive healthcare refers to the set of technologies designed to seamlessly integrate health education, interventions, and monitoring technology into our everyday lives, regardless of space and time. This approach can increase both the coverage and quality of care. Over the last decade, pervasive computing solutions for healthcare have become increasingly prevalent in both research and commercial efforts. This survey analyzes a variety of research projects and commercial solutions devoted to understanding, designing, and implementing pervasive healthcare applications in support of preventive care, hospital care, and chronic care. Taking into account the working conditions of clinicians and the needs of patients, pervasive computing offers a variety of attractive solutions for many of the challenges to care delivery in these domains. The work of clinicians is intrinsically tied to the physical domain of the patient, not to digital material available in computer systems; clinicians as well as other non-clinical caregivers continually switch between different caregiving contexts. Furthermore, their work is characterized by high mobility, ad hoc collaboration, and interruptions. At the same time, patients and family members frequently demonstrate poor adherence to both behavioral and pharmaceutical interventions and experience inadequate communication with those providing care. The use of health education to promote motivation, reinforcement, advice, and tools for capturing and tracking health information supporting self-monitoring can help patients to overcome these challenges. Pervasive computing offers solutions for clinicians, patients, and a variety of other caregivers to assist them with these problems including applications and mechanisms to: • ease the recording, tracking, and monitoring of health information; • allow communication, collaboration, and coordination among the varied stakeholders; • encourage clinical adherence and disease prevention; • support the nomadic work of clinicians and seamless integration of the physical and digital worlds; and • enable the development of novel medical devices. In this survey, we present an overview of the history of pervasive healthcare research as a human-centered vision driven by a healthcare model that includes preventive, hospital, and chronic care. We then summarize the research in this space, outlining research challenges, current approaches, results, and trends. Finally, we discuss future research directions as a springboard for new focus in pervasive healthcare. This survey is based on analysis of the literature as well as our own research experiences and those of many of our colleagues.

Seamless interaction among heterogeneous devices in support for co-located collaboration

In some working environments users experience a high level of mobility while requiring collaborating and coordinating their activities with colleagues involving the exchange and analysis of documents distributed in space or time. Medical workers stand out among others by the demands imposed by hospital work. These new forms of interaction pose new challenges for the design of pervasive computing environments aimed at seamlessly integrating heterogeneous devices. Based on workplace studies conducted in a hospital, we designed and implemented a mobile collaborative system aimed at supporting co-located collaboration, proximity-based application-sharing, and the remote control of heterogeneous devices. The results of a preliminary evaluation show that users perceive the services provided by the application to be useful and efficient, even though the manipulation of the remote display through the PDA was less efficient than with the keyboard and mouse.

A social cloud-based tool to deal with time and media mismatch of intergenerational family communication

Social media services are increasingly used to support social interaction among young people and adults. Older adults however, are often reluctant to use social media services, and prefer to socialize through face-to-face meetings or telephone conversations. Moreover, the time periods that family members have for socializing can be different, as they may have a different schedule for conducting activities and commitments during the day. These differences in media preferences and scheduling times for socializing generate a communication asymmetry that socially isolates older adults and negatively impacts their physical and mental health. Based on the analysis of a dataset from two 21-weeks deployment studies and nine semi-structured interviews, we conducted an in-depth formative study trying to understand the communication asymmetry among older adults and their relatives. The results were used to improve the design and implementation of SocialConnector, a cloud-based application that enables older adults to conduct synchronous and asynchronous social interactions with their relatives. The usability of the new system was evaluated to determine if its services contribute to address the stated communication asymmetry. The obtained results provide evidence that the system can successfully help to alleviate the communication breakdowns led by asymmetries in media and time preferences among family members. Differences in preferred media obstruct social interaction with older adults.A mismatch in interaction rhythms also makes difficult the communication with elders.SocialConnector bridges this gap by connecting the elderly with their families.Older adults perceive low effort for socializing when using SocialConnector.