Diane J. Cook - US grants

9355110 Lewis The purpose of this project is to provide traineeships for Ph.D. students to work with the Controls Group and the Intelligent Systems Group at the University of Texas at Arlington. The students who are selected to participate in this program will benefit from the collaboration between faculty and Electrical Engineering and in Computer Science and Engineering to further the state-of-the-art in robot planning and control. Students will also have the opportunities to perform their research at the University of Texas Automation and Robotics Research Institute (ARRI), and will have extensive interaction with representatives from international and industrial research labs. The University of Texas at Arlington is committed to increasing the participation of ethnic minorities and females in engineering careers. The proposed program continues these efforts to recruit minority and female engineers. As described in this proposal, we have established strong ties with the University of Texas at Brownsville and Grambling State University, and one of the principal investigators serves as the faculty advisor for the local chapter of the Society of Women Engineers and as a co-advisor for the local chapter of the Society of Hispanic Engineers. We propose to coordinate with these predominantly Hispanic, African-American, and women-based groups to recruit top students into our program. ***

The development of intelligent robot planning techniques is an essential element of future underwater and space exploration and industrial automation. These technologies find application in autonomous underwater and planetary rovers, autonomous rendezvous and docking, operation and maintenance of a nuclear power plant, extravehicular activity, autonomous landers, robotic and telerobotic control and automation, and in the general construction and operation of a laboratory, ship or industrial site. The purpose of this project is to increase the efficiency and effectiveness of robot planning by making use of parallel hardware and machine learning techniques. The project is made up to two component parts, each of which contributes independently and collectively to the automation of robotic activity. The first subproject focuses on developing parallel algorithms for heuristic search, which is a fundamental component in robot planning. The second subproject focuses on incremental modification and reuse of plans by searching for similarities between old and new plans. These two projects have been developed and tested on several search and planning problems. We propose to extend the existing research by improving the parallel search algorithms, developing parallel planning algorithms, and applying dynamic graph match to allow reuse of plans in a dynamically changing environment.//

9413923 Lewis This award provides funds for a robotics assembly cell and mobile vehicle testbed. The equipment will be dedicated to the advancement of robotics intelligent material handling technology. The equipment consists of two Silicon Graphics servers, a MIMD parallel processing computer, robotics equipment for the intelligent materials handling cell, a mobile platform with arm, a real-time digital control system, and distributed control equipment. This equipment will comprise the completion of two next generation systems ready for technology transfer to industry: the Intelligent Material Handling Development Cell and the Real-Time Digital Control System. The objective of the research to be performed using this equipment is to develop intelligent material handling technology in unstructured environments. The technology may improve United States global competitiveness by providing robotics systems that do not need to be explicitly retaught and reprogrammed as a result of minor changes in environments or tasks. This research represents across-disciplinary effort that is con-sponsored by industry, whichs will work with the university to steer the research and commercialize the result.

The objective of this project is to scale up the applicability of planning algorithms developed in the field of Artificial Intelligence. The basic research component of the project is to first investigate techniques for improving scalability of planning using parallel techniques, then to explore machine learning techniques for reusing and refining generated plans. Industrial applications of AI planning algorithms have been limited largely by the computational complexity of the planning task. The significant speedup that can be obtained using parallel hardware and machine learning techniques can bridge the gap between research and a wide variety of industrial applications. To demonstrate the power of the techniques developed here, they will not only be formally verified but will be applied to such applications as automated assembly and cooperative planning of unmanned ground vehicles. The CAREER project will also impact graduate and undergraduate education. Existing seminar courses in Parallel AI and in Planning and Robotics will be refined. An industrial team will be formed to suggest topics and to oversee class projects. All course materials developed for these classes will be packaged and available for general dissemination over the Internet.

CDA-9529561 Cook, Diane J. Shirazi, Behrooz A. Kavi, Krishna M. University of Texas- Arlington Design of a Distributed Computing Environment Using Power PC Micro Kernel The goal of this project is to investigate, design, and develop a unique distributed computing environment using a cluster of 12 networked PowerPcs. The uniqueness of the proposed research is based on the development of a set of tailor-made, PowerPC micro kernel routines to efficiently manage the overall system for a specific, large-scale AI application: parallel knowledge discovery from large complex databases. The main objectives are: (1) Developing a set of new and unique load balancing schemes for management of distributed systems. The schemes will be tailored for AI applications and implemented using the PowerPC micro kernel routines. (2) Developing a new distributed system for parallel knowledge discovery from large complex databases. The application will be carried out using the computing facility and proposed load balancing environment.

9724497 Lewis New developments in telecommunications systems, wireless networks, flexible manufacturing systems, etc. place severe demands on the design of decision-making supervisory controllers. On the other hand, new developments in advanced machinery, manufacturing tooling, lightweight and mobile robots, etc. place high demands on the design of real-time device-level motion controllers. The objective of this project is to design a controller with both multi-agent decision-making and machine-level motion control functions. To achieve this objective, new pieces of equipment are required for the development of an intelligent material handling cell (for multi-agent supervisory control), the development of a real-time control system (for machine-level control), and the development of a FMS/Machine Tool Controller (including both supervisory and real-time motion control functions). The equipment is essential for the development of a new class of controllers which have both multi-agent decision-making and machine-level motion control functions. The project benefits from the collaborative relationship of the investigators with companies such as Simis Labs and Caterpiller Inc.

9820440
Shirazi, Behrooz
University of Texas, Arlington

CISE REU: Research Experiences for Undergraduates in Dynamic Distributed Real-Time Systems

This Research Experiences for Undergraduates (REU) Site project supports six students per year in programs carried out during the summers for three years. The students work on projects in the area of dynamic distributed real-time systems including aspects of Quality of Service specification and management and benchmarking of such systems. Although the students are recruited nationwide, the program focuses on students from minority and women's institutions and from institutions lacking research facilities in the southwest region of the country. The student projects are related to a large, multi-year DARPA-funded research project. However, in addition to their participation in these projects, the students will be involved in literature searching, technical writing and making technical presentations.

Recent advances in computer and network technologies and storage, the explosion of publishing, and the vast increase in data availability from sources such as the Internet and satellites, that have enabled the emergence of an unprecedented number of new computer applications, present a new challenge to the ways data and information are used and managed. This challenge will shape both the research agenda as well as the technology to be developed for the 21st century. The objective of this workshop is to bring together the PIs and Co-PIs currently funded by the Information and Data Management Program (IDM) of the National Science Foundation to: (1) cooperatively analyze and focus on the research and development issues of problems that are fundamental in making progress towards this new challenge; (2) share, provide demonstrations and interact with each other on the objectives, contributions and challenges of major research activities funded by the IDM and explore fruitful collaboration and synergism; and (3) provide an opportunity to NSF program officers, other foundations and funding agencies, and industry representatives to learn more about the current research efforts and successes of projects funded by IDM, and for such officers to share their program highlights and concerns.

The workshop will generate a proceedings on all projects currently funded by IDM in both hard copy and electronic form. The workshop will also generate a report detailing future directions of research and will suggest promising modalities of research with an aim to foster innovation and technology transfer. The proceedings will provide project information searchable by different criteria and provide connections between discoveries and their use to society. The workshop website (http://itlab.uta.edu/idm01) will also include links to other relevant material.

EIA-0115885
Diane J. Cook
University of Texas at Arlington

MRI: Instrumentation for Intelligent Agent and Wireless Computing Research

This is a proposal for equipment acquisition under the Major Research Instrumentation (MRI) program to support research and student training on intelligent agents in a mobile environment. The Wireless Intelligent Simulator Environment being established will integrate software agents, human agents, and robot agents, so that physically distributed interacting agents can perform a variety of tasks cooperatively or competitively.

The MavHome project views a smart home as an intelligent agent, which is able to perceive its environment through the use of sensors and act upon the environment through the use of actuators. The home has overall goals, such as minimizing the cost of maintaining the home and maximizing the comfort and productivity of its inhabitants. In order to meet these goals, the house must be able to reason about and adapt to information using knowledge about databases, machine learning, multiagent systems, robotics, smart sensors, wireless mobile computing, and multimedia computing. Smart homes can potentially minimize home operating costs in a time when utilities fees are becoming prohibitive, and can assist individuals with disabilities to lead independent lives. Through the university visitor program, minority recruitment, course development, and dissemination of results, the project will impact research and education in the area of "smart space technologies."

With the increasing amount and complexity of today's data, there is an urgent need to accelerate the development of knowledge discovery and concept learning methods for mining large databases. Furthermore, much of this data is structural in nature, or is composed of entities and relationships between those entities. Hence, there exists a need to develop scalable methods for discovering new knowledge in structural databases. The main objective of this project is to investigate and implement new methods for performing knowledge discovery and concept learning on structural databases represented as graphs. This work builds upon existing methods for graph-based knowledge discovery implemented in the Subdue structural discovery system. The graph-based discovery algorithm is extended to perform structural concept learning and structural, hierarchical conceptual clustering. To achieve greater scalability, database management techniques are integrated into the graph-based discovery and learning processes. One targeted application is the use of Subdue as the core of a structural Web seach engine. Domain experts provide guidance and feedback on applications to molecular biology, geology, telecommunications, and software engineering. Achievement of the above objectives impacts the ability to automatically extract useful knowledge from the ever-increasing amount of data. By disseminating the Subdue discovery algorithm, databases, and discovered results over the Internet, scientists in all areas benefit from similar analyses of their own databases. Through integration of our research ideas into classes taught at UTA and into student research, this project impacts education at UTA and at other universities.

EIA- 0086260
Cook, Diane J.
University of Texas at Arlington

CISE Educational Innovation: Integrating Intelligent Agent and Wireless Computing Research into the Undergraduate Curriculum

The research-base for this project is Artificial Intelligence (AI), in particular, rational agent development. The project provides undergraduate students with access to a large-scale distributed mobile agent laboratory containing both real and simulated agents. The focus of the project is new curriculum material for AI, mobile computing, multimedia, and robotics courses that allow students to test their knowledge in a real and virtual environment as well as new courses in human-computer interaction and wireless-multimedia computing. The PIs have demonstrated successful research and development of AI simulators that provide students with environments for testing agent design ideas in decision making, multi-agent cooperation, and learning. The PIs expanded agent environment includes real-world tasks involving distributed decision-making, cooperation with both human and computer agents, and wireless communication. The project increases students' interest and expertise in this area through hands-on experiences with physical and simulated collaborative environments. In particular, the project uses a wireless communication system, called Wireless Intelligent Simulator Environment (WISE), in this institution's Computer Science area that permits human, software, and robot agents to interact over a distributed environment. The WISE environment, in addition to supporting new features of this university's existing courses (in AI, Mobile Networking and Computing, Multimedia, Robotics, and Senior Capstone Design Courses), supports new courses in Human-Computer Interaction and Wireless Multimedia Computing.

0203499
Manfred Huber
University of Texas Arlington
"An Active, Collaborative Learning Program in Smart Home Technologies"

This project provides opportunities for students, through the transfer of knowledge advances from research in Smart Home technologies, to engage in educational experiences that prepare them for the workforce in the expanding area of embedded, smart systems. The project focuses on the upper-level undergraduate and beginning graduate curricula at the University of Texas at Arlington (UTA) and Texas Christian University (TCU). The curriculum developments enabled by this project draw from expertise in the computer science and the engineering departments of both institutions and are also used to augment courses within various engineering disciplines. New course elements developed in this project incorporate state-of-the-art advances in fields such as Machine Learning, Requirements Modeling, Product Development Processes, Mobile robotics, and Multi-agent systems. Smart Home technology provides a vehicle to investigate and integrate these diverse topics and thus represents an environment suitable for cross-disciplinary team projects in which students with different expertise learn to cooperate to address a task. A Smart Home lab at UTA and a similar lab (Smart Frog Condo) at TCU are equipped with a variety of sensors and devices to provide hands-on experiences for students. These two similar labs permit experiments to be largely interchangeable to ensure the most efficient use of resources and available expertise at the two universities.

This project addresses homeland security, an issue of the highest national priority, with a goal of monitoring, preventing, and recovering from natural and inflicted disasters. In particular, in collaboration with team from UT Arlington, Penn State University and the University of Kentucky, the project will create a novel technology-enabled security framework, called Pervasively Secure Infrastructures (PSI), that will make use of such advanced technologies as smart sensors, wireless networks, pervasive computing, mobile agents, data mining, and profile-based learning in an integrated, collaborative and distributed manner. The uniqueness of this multi-disciplinary, multi-university proposal lies in the synergistic combination of the proposed research in (i) efficient data collection and aggregation from heterogeneous sensors and monitors; (ii) novel techniques for real-time, secured, authenticated information transmission and sharing, and (ii) intelligent situation awareness (e.g., threat detection and security services) through new learning, data mining, and knowledge discovery techniques. The project will mainly focus on authentication and secure data transmission in wireless networks. The project will integrate these research efforts in the novel paradigm of pervasive community computing that can efficiently handle dynamically changing information, adapt to changing situations, and provide scalability in terms of the number of users, devices, and data sizes.

Automated analysis of public health data represents a critical need, but effective analysis must look beyond individual data points. Much of the data that is collected is structural, consisting not only of entities but also of relationships (e.g., spatial,temporal) between the entities. As a result, a need exists to develop methods for discovering knowledge and learning concepts specifically for this type of structural data. A graph-based data mining technique that can perform pattern discovery, concept learning, and hierarchical clustering on data represented as graphs. This approach, implemented in the Subdue system, has demonstrated success in a numbeof scientific and industrial databases. The proposed effort will investigate the viability ofgraph-based data mining approach as a foundation for representing and ministructural data found in public health databases and related applications.

The effort will contribute 1) an analysis of public health data that explores data
points, relationships between the data points, and integration of data from related
domains to strengthen the results, 2) design of a graph-based mining system that can handle streaming data in an online fashion, 3) development of a new approach to concept learning that processes training examples embedded n a single interconnected graph, and 4) construction of a toolset that can provide early detection and assessment of epidemics and other public health crises.
The project depends on a strong partnership between computer scientists and an expert in public health. A collaboration between the University of Texas at Arlington and the University of North Texas Health Science Center has already received initial support from the two schools The collaboration will be fostered through monthly seminars and research meetings. The results of this project will thus have an impact on the computerscience community and an equal, if not greater, impact on the domain community The code and data will be available for general dissemination over the Internet, and results will be integrated into the classroom and into a book on graph-based data mining.

DESCRIPTION (provided by applicant): The number of Americans unable to live independently in their homes due to cognitive or physical impairments is rising significantly due to the aging of the population. There is a currently a fundamental gap in the knowledge base concerning how to apply machine learning technologies to improve health monitoring and how to harness these technologies to implement interventions designed to sustain independent living. The long-term objective of this work is to improve human health and impact health care delivery by developing smart environments that aid with health monitoring and intervention. The objective of this particular application is to design, implement, and evaluate technologies for assessing everyday functional limitations and for providing automated intervention strategies for persons with early-stage dementia. To most people home is a sanctuary, yet today those who need special care, predominantly older adults, must leave home to meet clinical needs. The central hypothesis is that many older adults with cognitive impairment can lead independent lives in their own homes with the aid of automated assistance and health monitoring. The rational for the proposed work is that smart environment technologies can improve quality of life and health care for older adults who require assistance with everyday functional activities and reduce the emotional and financial burden for caregivers and society. Guided by strong preliminary data and a partnership between computer science and clinical neuropsychology researchers, our central hypothesis will be tested by pursuing the following specific aims: (1) Design software algorithms that use smart environment data to recognize complex everyday activities in real-world settings, (2) Use smart environments to automate functional health assessment and to examine the ecological validity of laboratory-based measures, (3) Design automated reminder and prompting-based interventions to aid with everyday activity completion, and (4) Analyze correlations between everyday behavioral patterns and physiological data. The proposed work is innovative because it defines methods of detecting and coping with aging, early dementia and disabilities in our most personal environments: our homes. The proposed work is significant because it provides the basis for automated, robust functional assessment of individuals with cognitive limitations and of intervention strategies designed to improve functional independence for these individuals. Rather than relying on self-reporting by the patient or by an informant who may or may not spend extended time with the patient, smart home technologies will allow us to identify functional deficits that impede a patient's ability to maintain independence in their home as they begin to occur, and to extend independent living at home by intervening in a real world setting.

DESCRIPTION (provided by applicant): The world's population is aging and the resulting prevalence of chronic illnesses is a challenge that our society must address. Our vision is to address this challenge by designing smart environment technologies that keep older adults functioning independently in their own homes as long as possible. Smart environments have been used as the basis of monitoring activities for residents with health conditions. However, there is currently a lack of large scale, longitudinal research to identify early markers of dementia and other health status changes and to predict functional decline. The objective of this project is to perform a 5-year longitudinal study of older adults performing daily activities in thir own smart homes. By tracking residents' daily behavior over a long period of time our intelligent software can perform automated functional assessment and identify trends that are indicators of acute health changes (e.g., infection, injury) and slower progressive decline (e.g., dementia). By implementing prompt-based interventions that support functional independence and promote healthy lifestyle behaviors (e.g., social contact, exercise, regular sleep), we can improve overall health and well- being. We hypothesize that smart home technologies can be used to detect and predict functional change, to slow functional change and extend functional independence, and to improve quality of life in elderly individuals who are at risk of transitioning to MCI and t dementia. This hypothesis has been formulated on the basis of preliminary data produced by the applicants which supports the efficacy of using smart home technologies for both functional status assessment and for prompting the initiation and completion of activities in individuals with MCI and dementia. The rationale of the proposed work is that understanding the natural history of functional change between aging and dementia will lead to early prevention and proactive interventions that will slow functional change, thereby delaying nursing home placement and cost of care to society. We plan to pursue the following specific aims: (1) Characterize the daily lifestyle of smart environment residents through minimal-supervision activity recognition and activity discovery, (2) Design software algorithms that detect trends in behavioral data, and (3) Evaluate the efficacy of activity-aware automated prompting technology for extending functional independence and improving quality of life. The proposed work is innovative because it will track a large number of individuals longitudinal in their own homes and determine whether this technology can be used to promote healthy lifestyle behaviors and detect health care changes that may lead to early interventions, improved quality of life, and decreased health care utilization. The project is significant because it will introduce new technologies for activity discovery and tracking that require minimal- supervision, contribute algorithms that predict cognitive decline and signal more acute health status change, and demonstrate for the first time that activity-aware automated prompting technologies can be used to support and/or slow functional change and to increase quality of life in elderly individuals.

DESCRIPTION (provided by applicant): The world's population is aging and the increasing number of elderly who cannot maintain functional independence in their own homes is a challenge our society must address. While the idea of smart environments is now a reality, gaps in our knowledge base concerning how to scale and validate activity recognition and health assessment technologies currently limit clinical translation of smart environments for real-time health monitoring and intervention. The long-term objective of this project is to improve human health and impact health care delivery by developing smart environments that aid with health monitoring and intervention. The objective of this renewal application is to design, evaluate and validate software algorithms that recognize daily activities, provide automated health assessment and support real-time interventions. To most people home is a sanctuary, yet today those who need special care, predominantly older adults, must leave home to meet clinical needs. We hypothesize that many older adults who require support completing everyday activities can lead independent lives in their own homes with the aid of automated assistance and health monitoring. The rational for the proposed work is that smart environment technologies can improve quality of life and health care for older adults who require assistance with everyday functional activities and reduce the emotional and financial burden for caregivers and society. Building on our pioneering prior work and a partnership between computer science and clinical neuropsychology researchers, our central hypothesis will be tested by pursuing the following specific aims: (1) expand and validate software algorithms that recognize daily activities and provide automated functional assessment to encompass a greater number of behaviors and more diverse older adult population; (2) develop and validate software algorithms that provide automated health assessment by partnering actigraphy and ecological momentary assessment with in-home smart home data; (3) develop technologies to provide data-driven context-aware automated prompts; and (4) investigate methods for visualizing and integrating clinically-relevant smart home health data into personal and electronic health records. The proposed work is innovative because it partners real-time methodologies and defines methods of detecting and coping with aging and disabilities in our most personal environments: our homes. This work is significant because it provides the basis for technologies that will keep older adults with functional impairment in their homes and monitor frail older individuals from afar. The outcome of this work will result in automated health assessments that make use of smart technology, recommendations for improving the ecological validity of office-based clinical assessments, automated real-time intervention methods that can help support preventative health care measures, and clinically-relevant, user-friendly interfaces for integration of smart home data into health records.

DESCRIPTION (provided by applicant): The world's population is aging and the resulting prevalence of chronic illnesses is a challenge that our society must address. Our vision is to address this challenge by designing a curriculum for undergraduates in MSTEM fields that provides them the needed research skills to address this looming problem. Undergraduates in nursing, psychology, sociology, computer science, engineering (MSTEM) programs as well as those in healthcare-related disciplines need a strong multi-disciplinary background to be truly prepared for research in applying technology to gerontology issues. The objective of this project is to develop training programs for undergraduate participants in the fields of gerontology, and technology-based assistive environments. This will be done through course work, summer research programs, internships in the field, and professional workshops to help other institutions develop similar programs. The ultimate goal is to bring up a generation of new graduate student researchers and innovators who understand the need of continued work in the field for addressing the aging population issues and begin their research careers prepared for gerontechnology oriented research. We hypothesize that by developing a these new programs for training both undergraduates and fellow educators in the issues surrounding the aging problem, multi-disciplinary MSTEM approaches to tackling these tough issues, and supporting undergraduates in becoming prepared for graduate programs we can provide gerontechnology-related research groups across the nation with highly qualified applicants. The rationale of the proposed work is that there are few well integrated MSTEM programs for undergraduates and a lack of training in related research programs for new undergraduates available. Our group's research centers on this field, and our research team is interested in developing generations of qualified graduate students who come prepared for this highly complex field of research. To accomplish this, we plan to pursue the following specific aims: (1) Develop an undergraduate two semester (one academic year) multi-disciplinary MSTEM Gerontechnology course series, (2) Establish a summer research and internship experience program for highly qualified undergraduates, (3) Support senior capstone projects in MSTEM fields, especially for those students who wish to continue their work from the Gerontechnology course, (4) Integrate the Gerontechnology course into the existing Minor in Aging offered at the institution, giving it its first technology related course. We will also create a certificate of accomplishment for all students who have completed the Gerontechnology course and who have completed additional field experience related to gerontology, and (5) Lead and run two workshops for others interested in learning about the latest research in the field, plus training for other educators in the field of Gerontechnology so they can bring similar programs online at their institutions. The proposed work is innovative because Gerontechnology related undergraduate programs with a true multi-disciplinary core are rare. The combination of serving both the local student body, summer students from other programs, and to also bring our faculty's experience to other institutions through workshops is a compelling and energetic approach to bolstering the quantity of highly prepared upcoming graduate researchers. The project is significant because it will introduce many undergraduates to the issues faced by our society in the coming decades, as well as prepare many of them to help develop new approaches to health care through melding technology with traditional medical approaches.

? DESCRIPTION (provided by applicant): The long-term objective of this project is to improve human health and impact health care delivery by developing intelligent technologies that aid with health monitoring and intervention. Our immediate objective is to design, evaluate and validate machine learning-based software algorithms that recognize daily activities, provide activity-aware medicine reminder interventions and provide insights on intervention timings that yield successful compliance. We hypothesize that many individuals with needs for medicine intervention can be more compliant with their medicine regimen if prompts are provided at the right times and in the right context. We plan to accomplish these objectives by 1) enhancing and validating software algorithms that recognize daily activities and activity transitions, 2) developing and validating activity-aware medicine prompting interventions for mobile devices, and 3) designing technologies to analyze medicine reminder successes and failures. We are well positioned to significantly advance the clinical translation of mobile device-based medicine reminders for use by heart failure patients. The proposed work represents a natural extension of our prior research and is innovative because it will partner real-time methodologies for validation and algorithmic development with smart phone data, utilize novel activity discovery algorithms, and employ activity recognition and prediction algorithms in the development of activity-aware prompting.

PROJECT SUMMARY/ABSTRACT Our society faces significant challenges in providing quality health care that is accessible by each person and is sensitive to each person's individual lifestyle and individual health needs. Due to recent advances in sensing technologies that have improved in accuracy, increased in throughput, and reduced in cost, it has become relatively easy to gather high resolution behavioral and individualized health data at scale. The resulting big datasets can be analyzed to understand the link between behavior and health and to design healthy behavior interventions. In this emerging area, however, very few courses are currently available for teaching researchers and practitioners about the foundational principles and best practices behind collecting, storing, analyzing, and using behavior- based sensor data. Teaching these skills can help the next generation of students thrive in the increasingly digital world. The goal of this application is to design online courses that train researchers and practitioners in sensor-based behavioral health. Specifically, we will offer training in responsible conduct, collection and understanding of behavioral sensor data, data exploration and statistical inference, scaling behavioral analysis to massive datasets, and introducing state of the art machine learning and activity learning techniques. The courses will be offered in person to WSU faculty and staff, offered with staff support through MOOCs, and available to the general public from our web page. Course material will be enhanced and driven by specific clinical case studies. Additionally, the courses will be supplemented with actual datasets that students can continue to use beyond the course. This contribution is significant because not only large research groups but even individual investigators can create large data sets that provide valuable, in-the-moment information about human behavior. They need to be able to handle the challenges that arise when working with sensor- based behavior data. Because students will receive hands-on training with actual sensor datasets and analysis tools, they will know how to get the best results from available tools and will be able to interpret the significance of analysis results. Our proposed online course program, called AHA!, builds on the investigators' extensive experience and ongoing collaboration at Washington State University on the development of smart home and mobile health app design, activity recognition, scalable biological data mining, and the use of these technologies for clinical applications. Our approach will be to design online course modules to train individuals in the analysis of behavior-based sensor data using clinical case studies (Aim 1). We will design an educational program that involves students from diverse backgrounds and that is findable, accessible, interoperable, and reusable (Aim 2). Finally, we will conduct a thorough evaluation to monitor success and incrementally improve the program (Aim 3). All of the materials will be designed for continued use beyond the funding period of the program.

PROJECT SUMMARY/ABSTRACT The world's population is aging and the increasing number of older adults with chronic health conditions is a challenge our society must address. While the idea of smart environments is now a reality, there remain gaps in our knowledge about how to scale smart homes technologies for use in complex settings and to use machine learning and activity learning technologies to design automated health assessment and intervention strategies. The long-term objective of this project is to improve human health and impact health care delivery by developing smart environments that aid with health monitoring and intervention. The primary objective of this application is to design a ?clinician in the loop? smart home to empower individuals in managing their chronic health conditions by automating health monitoring, assessment, and evaluation of intervention impact. Building on our prior work, the approach will be to generate analytics describing an individual's behavior routine using smart homes, smart phones, and activity learning (Aim 1). Our trained clinicians will use the analytics to perform health assessment and detection of health events (Aim 2). In addition, we will introduce brain health interventions to support sustainable improvement of brain health (Aim 3). Finally, we train machine learning algorithms from the clinical observations to automate assessment of health and intervention impact (Aim 4). The use of these technologies is expected to improve and extend the functional health and wellbeing of older adults, lead to more proactive and preventative health care, and reduce the caregiver burden of health monitoring and assistance. By understanding situational factors that impact prompt adherence, adherence situations can be increased. The approach is innovative because it will explore and validate new machine learning techniques for activity learning and health assessment based on clinical ground truth. These contributions are significant because they can extend the health self-management of our aging society through proactive health care and real-time intervention, and reduce the emotional and financial burden for caregivers and society. Given nursing home care costs, the impact of family-based care, and the importance that people place on staying at home, technologies that increase functional independence and thus support aging in place while improving quality of life for both individuals and their caregivers are of significant value to both individuals and society.

PROJECT SUMMARY/ABSTRACT The world's population is aging and the increasing number of older adults with Alzheimer's disease and related dementias (ADRDs) is a challenge our society must address. While the idea of smart environments is now a reality, there remain gaps in our knowledge about how to scale smart homes technologies for use in complex settings and to use machine learning and activity learning technologies to design automated health assessment and intervention strategies. The primary objective of the parent study is to design a ?clinician in the loop? smart home to empower individuals in managing their chronic health conditions by automating health monitoring, assessment, and evaluation of intervention impact. This supplement extends our design to monitor, assess, and intervene for individuals with ADRDs and their caregivers. Building on our prior work, the approach will be to generate analytics describing an individual's behavior routine using smart homes, smartwatches, and activity learning (Aim 1). Our trained clinicians will use the analytics to train algorithms for health assessment (Aim 2). In addition, we will introduce brain health interventions to extend brain health and objectively capture intervention both adherence and caregiver support (Aim 3). Clinician guidance is used to train machine learning algorithms to automatically recognize health events (Aim 4). Given the unique challenges that will arise when we include individuals with ADRDs, we also introduce novel methods to track multiple residents in smart environments (Aim 5) and compare behaviors between individuals with ADRDs and the original sample of older adults with chronic health conditions (Aim 6). These contributions are significant because they can extend the health self-management of our aging society through proactive health care and real-time intervention, and reduce the emotional and financial burden for caregivers and society. Given nursing home care costs, the impact of family-based care, and the importance that people place on staying at home, technologies that increase functional independence and thus support aging in place while improving quality of life for both individuals and their caregivers are of significant value to both individuals and society.

PROJECT SUMMARY/ABSTRACT The world's population is aging. The resulting prevalence and ability to provide quality care for older individuals with Alzheimer's disease and related dementias (ADRDs) and other chronic illnesses is a challenge our society must address. Our vision is to address this challenge by providing a diverse body of undergraduate students with the scientific, clinical, and research experience needed to understand health-assistive technology and design technological solutions that aid with the challenges of aging and improve human health. Undergraduates in neuroscience, psychology, sociology, computer science, and engineering (MSTEM) programs as well as those in healthcare-related disciplines need a strong multi-disciplinary background to be truly prepared for research in applying technology to gerontology issues. The objective of this renewal application is to continue to enhance and lead a research training program for undergraduate students in the fields of gerontology and technology-based assistive environments. This will be done through course work, summer research programs, online materials and professional symposia to help other institutions develop similar programs. The ultimate goal is to bring up a diverse generation of new graduate student researchers and innovators who understand the need of continued work in the field for addressing the aging population issues and begin their research careers prepared for gerontechnology oriented research. To accomplish our goal, we will refine and offer a gerontechnology class that is geared toward multidisciplinary undergraduate students (Aim 1). We will also refine and offer a gerontechnology-focused summer undergraduate research experience (GSUR) program that will provide a team-based research opportunity for highly-qualified students (Aim 2). To broaden the impact of the training program, we will offer mentoring support for senior capstone projects and independent and clinical training projects related to gerontechnology (Aim 3). Finally, we will broaden the impact of our program by disseminating training materials through online classes, Youtube videos, and podcasts, and presenting methods and results of the training program at high-visibility gerontology and technology meetings (Aim 4). In all of these efforts we will recruit and involve a diverse student body, including women in STEM, minorities, persons with disabilities and individuals from disadvantaged backgrounds. The proposed program is innovative because Gerontechnology-related undergraduate programs with a true multi- disciplinary core are rare. The combination of serving both the local student body, summer students from other programs, and individuals from outside the university through online materials, open seminars, and workshops will bolster the quality, quantity, and diversity of highly prepared upcoming graduate researchers. The project is significant because it will introduce many undergraduates to the issues faced by our society in the coming decades, as well as prepare many of them to help develop new approaches to health care through melding technology with traditional medical approaches.

PROJECT SUMMARY / ABSTRACT The world's population is aging and the increasing number of older adults with Alzheimer's disease and related dementias (ADRDs) is a challenge our society must address. While the future of healthcare availability and quality of services seems uncertain, at the same time advances in pervasive computing and intelligent embedded systems provides innovative strategies to meet these needs. One particular need which technology can help address is assessment and assistance with a person's functional performance. The long-term goal of this work is to develop technologies that will improve the independent functioning and quality of life of individuals with functional limitations (particularly individuals with ADRDs) and reduce their reliance on caregivers. The primary objective of this application is to develop a multi-modal sensor-based approach to automate functional health assessment and assistance with everyday activities. Building on our prior collaborative work, our approach will be to collect and fuse multi-modal functional performance data from ambient sensors, mobile sensors, free text, and assessment apps (Aim 1). This fused ?human behaviorome? will provide a basis, together with observation-based ground truth, for automated functional assessment and validation of each component technology, including the use of compensatory strategies, through in-person observation and through video recording of typical daily activities and strategies (Aim 2). Finally, using iterative, user-centered assessment of prompt-based assistance, we will evaluate the ability of activity segmentation and forecasting techniques to provide automated support for activity initiation and accurate completion of everyday activities (Aim 3). The proposed contributions are significant because they will provide insights on functional health revealed within a person's everyday environment that have not been investigated in prior work. The results can also help to extend functional independence through real-time assistance, while the outcomes can assist family planning, provision of care, and design of real-world and lab-based measures of functional performance. This work is important because of the increasing number of older individuals experiencing cognitive and functional limitations due to chronic health conditions. Furthermore, they address the need for individuals to remain functionally independent as long as possible in their own homes, thereby improving quality of life and reducing health care costs.

PROJECT SUMMARY / ABSTRACT Advances in machine learning and low-cost, wearable sensors offer a practical method for understanding, assessing, and intervening for Alzheimer's Disease and Related Dementias (ADRDs) in everyday spaces. We propose to create a Behaviorome research program that will create ground-breaking methods for building health-predictive models from wearable sensor data by mapping patterns of behavior using machine learning and pervasive computing technologies. This program will create innovative multidisciplinary ideas to address NIH ADRD Milestone 11.c, Embed wearable technologies/pervasive computing in existing and new clinical research. Our research program builds on a history of interdisciplinary research contributions in areas including human behavior modeling from longitudinal sensor data and design of novel assessment and intervention mechanisms. We propose to design and validate methods for mapping a human behaviorome ?in the wild?, automatically assessing cognitive and functional health from behavior markers, scaling technologies through machine learning, linking health and behavior with their influences, and closing the loop with automated interventions. Similarly, our mentoring program builds on experience training students and early- career investigators to become leaders in the field of gerontechnology. We will recruit and train graduate students and early-stage researchers, including those from underrepresented groups, to grow an institutional multidisciplinary Behaviorome research program and to establish new research programs that contribute to the targeted Milestone. We will scale the impact of mentoring by establishing a webinar series and creating youtube videos that highlight and explain breakthroughs in the design and application of Behaviorome research. Results of this program will include scripts and templates to construct a behaviorome with resource- limited wearable devices, scale data and models to large diverse populations, integrate data with multiple information sources (e.g., genetics), automate health assessment and intervention, and create understandable explanations of data and models. These will contribute to existing clinical studies such as the clinician-in-the- loop smart home, digital memory notebook, and pervasive computing measures of functional performance. Furthermore, they will lead to new clinical studies that formalize connections between health and its influences, exploration of the impact of ethnicity and the built environment on health, and the design of ADRD interventions for medication adherence, task prompting, and negative interaction de-escalation. The proposed contributions are significant because they will provide insights on detecting and assessing ADRDs within a person's everyday environment using wearable sensing and pervasive computing methods that have not been investigated in prior work. Additionally, the mentoring steps will pave the way for a new generation of researchers to offer improved methods of addressing the need to understand, assess, and intervene for ADRDs in everyday settings, thereby improving quality of life and reducing health care costs.