2008 — 2014 |
Dey, Anind |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Career: Supporting the Intelligibility of Context-Aware Applications @ Carnegie-Mellon University
The maturing discipline of ubiquitous computing (ubicomp) has largely ignored usability in lieu the more fundamental quest to simply develop and deploy compelling applications. In these projects usability and social analysis is often post-hoc, one-off, and not accreting into a uniform body of scientific knowledge. This project spotlights the core ubicomp usability challenge as "intelligibility." That is the mapping of mental models, the user's explanations and predictions of a system's expected behavior, to the actual behavior of context-aware ubicomp application. While the use of mental models has been applied to well-understood systems, its application to context-aware systems is novel and promising. It is critical to understand how mental models develop, what sorts of explanations will promote correct mental model formation and what feedback will support users in making correct predictions about application behavior.
Broader Impact: The combination of the fundamental understanding gleaned from the proposed studies with the resulting widely disseminated toolkit, has the potential to enable a new class of context aware applications and related usability metrics. Improved usability of and trust in context-aware applications should reduce the chance of abandonment by making it clear how these applications behave. Easier to understand systems may engage a broader cross-section of end users, advancing the adoption of context-aware systems.
The PI has demonstrated that ubicomp design and evaluation projects such as this engage undergraduates from groups under-represented in computer science research.
|
0.915 |
2009 — 2013 |
Dey, Anind |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Netse: Large: Collaborative Research: Fieldstream: Network Data Services For Exposure Biology Studies in Natural Environments @ Carnegie-Mellon University
This award is funded under the American Recovery and Reinvestment Act of 2009 (Public Law 111-5).
Obtaining physiological/behavioral data from human subjects in their natural environments is essential to conducting ecologically valid social and behavioral research. While several body area wireless sensor network (BAWSN) systems exist today for physiological data collection, their use has been restricted to controlled settings (laboratories, driving/flying scenarios, etc.); significant noise, motion artifacts, and existence of other uncontrollable confounding factors are the often cited reasons for not using physiological measurements from natural environments. In order to provide scientifically valid data from natural environments, a BAWSN system must meet several unique requirements (1) Stringent data quality without sensing redundancy, (2) Personalization to account for wide between person differences in physiological measurements, and (3) Real-time inferencing to allow for subject confirmation and timely intervention.
Intellectual Merit: In this project, a multidisciplinary team of researchers spanning various computing disciplines and behavioral sciences are developing a general purpose framework called FieldStream that will make it possible for BAWSN systems to provide long term unattended collection of objective, continuous, and reliable physiological/behavioral data from natural environments that can be used for conducting population based scientific studies. FieldStream is being incorporated in two real-life projects ? NIH sponsored AutoSense at Memphis and NSF sponsored Urban Sensing at UCLA, to help validate the assumptions, establish the feasibility of developed solutions, and to uncover new requirements.
Broader Impact: By making it possible to obtain scientifically valid objective data from the field, FieldStream promises to help solve several behavioral problems of critical importance to human society that have remained unanswered for lack of such data.
|
0.915 |
2010 — 2016 |
Dey, Anind Sheikh, Yaser (co-PI) [⬀] Kanade, Takeo (co-PI) [⬀] |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Collaborative Research: Computational Behavioral Science: Modeling, Analysis, and Visualization of Social and Communicative Behavior @ Carnegie-Mellon University
Computational Behavioral Science: Modeling, Analysis, and Visualization of Social and Communicative Behavior Lead PI/Institution: James M. Rehg, Georgia Institute of Technology This Expedition will develop novel computational methods for measuring and analyzing the behavior of children and adults during face-to-face social interactions. Social behavior plays a key role in the acquisition of social and communicative skills during childhood. Children with developmental disorders, such as autism, face great challenges in acquiring these skills, resulting in substantial lifetime risks. Current best practices for evaluating behavior and assessing risk are based on direct observation by highly-trained specialists, and cannot be easily scaled to the large number of individuals who need evaluation and treatment. For example, autism affects 1 in 110 children in the U.S., with a lifetime cost of care of $3.2 million per person. By developing methods to automatically collect fine-grained behavioral data, this project will enable large-scale objective screening and more effective delivery and assessment of therapy. Going beyond the treatment of disorders, this technology will make it possible to automatically measure behavior over long periods of time for large numbers of individuals in a wide range of settings. Many disciplines, such as education, advertising, and customer relations, could benefit from a quantitative, data-drive approach to behavioral analysis. Human behavior is inherently multi-modal, and individuals use eye gaze, hand gestures, facial expressions, body posture, and tone of voice along with speech to convey engagement and regulate social interactions. This project will develop multiple sensing technologies, including vision, speech, and wearable sensors, to obtain a comprehensive, integrated portrait of expressed behavior. Cameras and microphones provide an inexpensive, noninvasive means for measuring eye, face, and body movements along with speech and nonspeech utterances. Wearable sensors can measure physiological variables such as heart-rate and skin conductivity, which contain important cues about levels of internal stress and arousal that are linked to expressed behavior. This project is developing unique capabilities for synchronizing multiple sensor streams, correlating these streams to measure behavioral variables such as affect and attention, and modeling extended interactions between two or more individuals. In addition, novel behavior visualization methods are being developed to enable real-time decision support for interventions and the effective use of repositories of behavioral data. Methods are also under development for reflecting the capture and analysis process to users of the technology. The long-term goal of this project is the creation of a new scientific discipline of computational behavioral science, which draws equally from computer science and psychology in order to transform the study of human behavior. A comprehensive education plan supports this goal through the creation of an interdisciplinary summer school for young researchers and the development of new courses in computational behavior. Outreach activities include significant and on-going collaborations with major autism research centers in Atlanta, Boston, Pittsburgh, Urbana-Champaign, and Los Angeles.
|
0.915 |
2010 — 2014 |
Dey, Anind |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Cps: Medium: Collaborative Research: Enabling and Advancing Human and Probabilistic Context Awareness For Smart Facilities and Elder Care @ Carnegie-Mellon University
The objective of this research is to enable cyberphysical systems (CPS) to be context-aware of people in the environment and to use data from real-world probabilistic sensors. The approach is (1) to use radio tomography (RT) and RFID to provide awareness (location and potential identification) of every person in a building or area, and (2) to develop new middleware tools to enable context-aware computing systems to use probabilistic data, thus allowing new applications to exploit sometimes unreliable estimates of the environment.The intellectual merit of the proposal is in the development of new algorithms and models for building-scale RT with low radio densities and across multiple frequencies; the development of efficient multichannel access protocols for rapid and adaptive peer-to-peer measurements; the development of space-time and probabilistic data representations for use in stream-based context awareness systems and for merging ID and non-ID data; (4) and the development of a human context-aware software development toolkit that interfaces between probabilistic data and context-aware applications.
The proposal impacts broadly the area of Cyberphysical systems that reason about human presence and rely on noisy and potentially ambiguous (practical) sensors. The research has additional dramatic impact in: (1) smart facilities which automatically enforce safety, privacy, and security procedures, increasing the ability to respond in emergency situations and prevent accidents and sabotage; (2) elder care, to monitor for physical or social decline so that effective intervention can be implemented, extending the period elders can live in their own home, without pervasive video surveillance.
|
0.915 |
2010 — 2014 |
Dey, Anind Zimmerman, John (co-PI) [⬀] |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Hcc: Small: Learning Routines to Support People's Activities @ Carnegie-Mellon University
People construct routines as they repeatedly perform the same sequence of actions. Routines provide a huge benefit by freeing people?s attention, allowing them to carry out their daily tasks without constantly thinking about every little thing they must do. Problems begin to arise when people must deviate from their routines. Families rely heavily on their routines to address the complex logistics and conflicting agendas of work, school, family, and enrichment activities. However, families often deviate from their routines, and when breakdowns in the plans occur, they feel their lives are out of control.
This research will develop a system that learns the routine movements of family members, and a planning system that leverages this model in order to generate a speculative plan for future days. The system will also predict conflicts with scheduled deviations and detect when plans begin to breakdown, such as when someone forgets to deviate from a routine. A calendar interface that displays the routine movements of family members along with their scheduled deviations and a small set of reminder applications that help people enact their plans and that support them when plans breakdown will form the basis for evaluating the underlying systems. This research is transformative in the novel integration of machine learning and planning techniques, and its application to a real-world and complex problem. Finally, this research provides insights on how intelligent, ubiquitous computing technology influences families? feelings of control and their quality of life.
The proposed work has the potential to significantly improve the quality of life for millions of families by reducing stress caused from breakdowns in plans and routines. Lowering stress can improve the quality of marriages, the quality of parenting, and the physical and mental health of children. We will involve undergraduate and graduate students in our research and will incorporate our findings into our courses on ubiquitous computing, interaction design, and on smart homes. We expect that our focus on a social problem will attract non-science-focused students to science and expose science-focused students to design methods of inquiry.
|
0.915 |
2010 — 2014 |
Dey, Anind |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Socs: Creation of a Framework For Computational Gaming @ Carnegie-Mellon University
Leveraging crowdsourcing to collect data is becoming more common. Human Computation, in particular, has looked at how to use artificial intelligence on data collected from people playing games, to validate that useful data has been collected on a very large scale. This work will investigate a new form of artificial-intelligence based crowdsourced games called Computational Gaming, in which questions will be posed without knowing what the answers are beforehand. Questions that require human judgment will be posed in the context of a game, and machine learning will be used to determine what questions to pose to which players and how to determine whether the responses are valid.
Intellectual Merit. This project will demonstrate the validity of Computational Gaming through two examples in text and image labeling, delineating a set of guiding design principles for building and evaluating future Computational Gaming designs, and producing a toolkit that supports and encourages the use of these design principles for building Computational Gaming systems.
Potential Broader Impacts. The project will create, both more quickly and more cheaply, databases of human-labeled data; it will also do so for a wider variety of problems than currently exists. The framework and toolkit for Computational Gaming will be valuable for game designers, for researchers in many domains that need labeled data, and for the users for whom the research is being conducted.
|
0.915 |
2010 — 2011 |
Dey, Anind |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Workshop: the Doctoral Colloquium At Ubicomp 2010 @ Carnegie-Mellon University
This award supports a Doctoral Colloquium (DC) at the 12th ACM International Conference on Ubiquitous Computing (UbiComp 2010) to be held September 26 - 29, 2010 in Copenhagen, Denmark. The International Conference on Ubiquitous Computing is the premier outlet for novel research contributions that advance the state of the art in the design, development, deployment, evaluation and understanding of ubiquitous computing (ubicomp) systems. The conference is a competitive and interdisciplinary venue of publishing and presenting research that spans and integrates pervasive, wireless, embedded, wearable and/or mobile technologies to bridge the gaps between the digital and physical worlds.
Intellectual interaction with experts and peers will broaden the students? perspective about the future directions of research in a range of topics connected to Ubiquitous Computing. It will also enable the students to network with each other and with the experts. Finally, the focused attention and unique exposure given to the students will in and by itself draw and attract more students to work in the Ubiquitous Computing area. This should hopefully increase the number of graduates in this area, which should drive innovation and generate highly trained workforce working in field of Ubiquitous Computing.
|
0.915 |
2011 — 2012 |
Dey, Anind |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Workshop: the Doctoral Colloquium At Ubicomp 2011 @ Carnegie-Mellon University
This is funding to support a doctoral research symposium (workshop) of approximately 10-15 promising doctoral students, along with 5 high profile faculty and industrial researchers. The event will take place in conjunction with and immediately preceding the 13th ACM International Conference on Ubiquitous Computing (UbiComp 2011), to be held September 17-21, in Beijing, China, and sponsored by the Association for Computing Machinery. The annual UbiComp conference is the premier international forum for the presentation and discussion of cutting edge research relating to both the technical and applied aspects of ubiquitous computing technologies, systems and applications. This is an interdisciplinary field of research and development that utilizes and integrates pervasive, wireless, embedded, wearable and/or mobile technologies to bridge the gaps between the digital and physical worlds. Thus, the conference brings together researchers and practitioners from diverse areas that include human-computer interaction, pervasive computing, distributed and mobile computing, real world modeling, sensors and devices, middleware and systems, programming models and tools, and human-centric validation and experience characterization. More information about the conference may be found at http://www.ubicomp.org/ubicomp2011.
The three goals of the full-day doctoral consortium are to increase the exposure and visibility of the participants' work within the community, to help establish a sense of community among this next generation of researchers, and to help foster their research efforts by providing highly constructive feedback and guidance from senior researchers in a supportive and interactive environment. To these ends, student participants will each make a formal presentation of their work to the group, with ample time allotted for questions and feedback from the faculty panel as well as from the other student participants. The feedback is geared to helping students understand and articulate how their work is positioned relative to other research, whether their topics are adequately focused for thesis research projects, whether their methods are correctly chosen and applied, and whether their results are appropriately analyzed and presented. Additional opportunities for more informal discussion and networking will be during the doctoral consortium's lunch and dinner events. The students will be invited to present their research to a wider audience through posters at the conference, and extended abstracts of their work will be included in the supplemental proceedings which are distributed to all conference attendees.
Broader Impacts: The doctoral colloquium will help expand the participation of young researchers pursuing graduate studies in the various fields associated with ubiquitous computing, by providing them an opportunity to gain wider exposure in the community for their innovative work and to obtain feedback and guidance from senior members of the research community. It will further help foster a sense of community among these young researchers, by allowing them to create a social network both among themselves and with senior researchers at a critical stage in their professional development. Several participants in past UbiComp doctoral consortia have since gone on to high profile research careers. The organizers of this year's event have committed to accept no more than one student from any given institution, and they will make special efforts to attract students who are diverse across a number of dimensions (e.g., research interests, gender and ethnicity), so that the participants' horizons are broadened to the future benefit of the field.
|
0.915 |
2012 — 2017 |
Dey, Anind Bagnell, James [⬀] Hebert, Martial (co-PI) [⬀] |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Nri-Large: Collaborative Research: Purposeful Prediction: Co-Robot Interaction Via Understanding Intent and Goals @ Carnegie-Mellon University
In order for robots to collaborate with humans, they need to be able to accurately forecast human intent and action. People act with purpose: that is, they make sequences of decisions to achieve long-term objectives. For instance, in driving from home to a store, people carefully plan a sequence of roads that will get them there efficiently. In predicting a person's next decision, algorithms must be developed that reflect these purposeful actions.
Currently, robots are unable to anticipate human needs and goals, and this represents a fundamental barrier to their large-scale deployment in the home and workplace. The aim of this project is to develop a new science of purposeful prediction that can be applied to human-robot interaction across a wide variety of domains. The work draws on recent techniques based on Inverse Optimal Control and Inverse Equilibria Theory that enable statistically sound reasoning about observed deliberate behavior. These new methods provide the foundations of a theoretical framework that integrates traditional decision making techniques like optimal control, search and planning with probabilistic methods that reason about uncertainty and hidden information, particularly about goals, utility and intent.
Intellectual merit: The project will provide a general framework that allows robots to anticipate and adapt to the activities of their human co-workers based on perceptual cues. The investigators will develop the theory, a computational toolbox, and, in collaboration with industrial partners, prototype deployments of these new methods for the prediction of peoples' behavior in a diverse set of robotics domains from computer vision to motor control. The project is transformative in that it combines a novel theoretical/algorithmic framework with extensive support in terms of volume of data and validation infrastructure in the context of many applications.
Broader impacts: A revolution in personal robotics in both the home and workplace depends on the ability to forecast human activities and intents; small- and medium- scale manufacturing will make a leap forward through agile robotic systems intelligent enough to understand and assist their co-workers in flexible assembly tasks; and robust models of pedestrian and vehicular traffic flow will enable more effective driver warning systems and safer autonomous mobile robots. Purposeful prediction technology is an important step towards enabling such understanding of actions and intents in these arenas. The research work will involve the training and mentoring of undergraduate, masters and doctoral students as well as post-doctoral fellows in this emerging multi-disciplinary research area at the intersection of computer and cognitive sciences and robotics.
|
0.915 |
2012 — 2013 |
Dey, Anind |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Workshop: the Doctoral Colloquium At Ubicomp 2012 @ Carnegie-Mellon University
This is funding to support a doctoral research symposium (workshop) of approximately 10 promising doctoral students from the United States and abroad (up to 2 international students), along with 5 high profile faculty and industrial researchers. The event will take place in conjunction with and immediately following the 14th ACM International Conference on Ubiquitous Computing (UbiComp 2012), to be held September 5-8, in Pittsburgh, and which is sponsored by the Association for Computing Machinery. The annual UbiComp conference is the premier international forum for the presentation and discussion of cutting edge research relating to both the technical and applied aspects of ubiquitous computing technologies, systems and applications. This is an interdisciplinary field of research and development that utilizes and integrates pervasive, wireless, embedded, wearable and/or mobile technologies to bridge the gaps between the digital and physical worlds. Thus, the conference brings together researchers and practitioners from diverse areas that include human-computer interaction, pervasive computing, distributed and mobile computing, real world modeling, sensors and devices, middleware and systems, programming models and tools, and human-centric validation and experience characterization. More information about the conference may be found at http://www.ubicomp.org/ubicomp2012.
The three goals of the full-day doctoral consortium are to increase the exposure and visibility of the participants' work within the community, to help establish a sense of community among this next generation of researchers, and to help foster their research efforts by providing highly constructive feedback and guidance from senior researchers in a supportive and interactive environment. To these ends, student participants will each make a formal presentation of their work to the group, with ample time allotted for questions and feedback from the faculty panel as well as from the other student participants. The feedback is geared to helping students understand and articulate how their work is positioned relative to other research, whether their topics are adequately focused for thesis research projects, whether their methods are correctly chosen and applied, and whether their results are appropriately analyzed and presented. Additional opportunities for more informal discussion and networking will be during the doctoral consortium's lunch and dinner events. Extended abstracts of the students' work (up to 4 pages in length) will be included in the supplemental proceedings which are distributed to all conference attendees.
Broader Impacts: The doctoral colloquium will help expand the participation of young researchers pursuing graduate studies in the various fields associated with ubiquitous computing, by affording them an opportunity to gain wider exposure in the community for their innovative work and to obtain feedback and guidance from senior members of the research community. It will further help foster a sense of community among these young researchers, by allowing them to create a social network both among themselves and with senior researchers at a critical stage in their professional development. Several participants in past UbiComp doctoral consortia have since gone on to high profile research careers. The event organizers have committed to accept no more than one student from any given institution, and they will make a special effort to attract students who are diverse across a number of dimensions (e.g., research interests, gender and ethnicity), so that the participants' horizons are broadened to the future benefit of the field.
|
0.915 |
2014 — 2017 |
Dey, Anind |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Chs: Medium: Collaborative Research: Intelligent Context-Aware Peer-to-Peer Transaction Brokering @ Carnegie-Mellon University
Peer-to-peer exchange is transforming economic activity, through unprecedented integration of social and practical action. This project will produce a full-scale implementation of a more efficient model of it that can be emulated across many social and economic domains. Peer-to-peer exchange is the direct exchange of goods and services by citizens, mediated by a brokering entity, typically embodied as an information system. It is an emerging paradigm that integrates economic and social interaction, creating many possibilities for innovation. It encompasses diverse services such as ride sharing, everyday tasks, textbook sharing, accommodation sharing , car sharing , sharing parking, local food exchange, sharing household items, exchanging home-cooked meals, sharing workspace and expertise, timebanking, and municipal development . Many of these applications make use of otherwise wasted resources such as parked cars, empty bedrooms, and idle time, increasing the efficiency and sustainability of economic activity. Their number and size have mushroomed; they are now referred to collectively as the "collaborative economy."
Many peer-to-peer exchanges involve sharing goods and services "just in time," that is, sharing precisely when someone needs something and someone else is prepared to provide it. Thus, one key to the success of peer-to-peer exchanges is close coordination of providers/offerers and recipients/requesters. In a recent NSF project, members of the current research team investigated mobile timebanking using smartphone clients, a system in which members of a community can volunteer specific hours of labor they are well prepared to perform, in exchange for hours of labor from other community members, counting each hour equally. A key challenge was a lack of coordination in arranging "just in time" service exchanges.
This new research will investigate computational approaches to coordinating collaborative interactions mediated by contextual intelligence. Also studied will be what sorts of user, task, and interaction information facilitate effective "just in time" service exchanges, and how users appropriate and experience these exchanges. A large field trial will investigate the adoption, usability, and utilization of context-aware peer-to-peer transaction brokering and will provide early reports of results and help a variety of organizations implement techniques that have been shown to work.
The research will extend current understanding of motivations for engaging in helpful economic transactions, the formation of social connections through such transactions, and of how to enhance subjective wellbeing by fostering practical helping behaviors through context-aware technology. A prime objective is to identify strategies for contextually facilitated peer-to-peer exchange that can energize economic exchange activity, and support new kinds of exchange, while enhancing social consequences and concomitants of exchange interactions.
|
0.915 |
2015 — 2018 |
Akinci, Burcu (co-PI) [⬀] Dey, Anind Sinopoli, Bruno [⬀] Rowe, Anthony |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Pfi:Bic - a Cost-Effective Accurate and Resilient Indoor Positioning System @ Carnegie-Mellon University
This Partnerships for Innovation: Building Innovation Capacity project aims at developing a cost effective, accurate, resilient and smart indoor localization service to be used in built environments. Positioning systems have revolutionized how we interact with the world around us. Outdoor mobile devices make use of technologies like Global Positioning System (GPS) to deliver a wide variety of location-based services. Similarly, indoor positioning systems will enable delivery of new services that provide tremendous social and commercial value to humans in residential and commercial built environments. Indoor location services can be used by enterprises to track and manage assets. Building management systems can use indoor location information to enable services for building managers and occupants and first responders, such as effective emergency response, indoor navigation, and perimeter protection. Furthermore, indoor location services will enable implementation of important services such as coordination of people in a disaster scenario (e.g., natural or man-made (public shootings) disasters and navigation services for the blind). Unfortunately, satellite-based approaches, such as GPS, do not work indoors due to weak satellite signals that do not penetrate through building facades. Unlike existing methods, the proposed smart service will achieve high accuracy and robustness with respect to disruptions, while maintaining low installation and maintenance costs. In addition, users will be able to use their mobile device(s), (e.g., smartphone, tablets, smart watches), without the need to carry/wear additional equipment.
The project will develop and combine ultrasound, visible light and Wireless Local Area Network (WLAN)-based positioning techniques with Radio Frequency (RF)-based, magnetic signatures, human ambulation models and building information models (BIMs) for localization, tracking and visualization. The combined use of several independent positioning techniquse not only will dramatically increase the accuracy of positioning over any single technique, but it will add the necessary redundancy to withstand disruption of all but one positioning service, with provably bounded loss of performance. Even in the case of unavailability of all positioning techniques, ambulation models, together with BIM, will be able to provide indoor positioning at a coarser level of granularity. In turn, redundancy can be used to perform maintenance and periodic system calibration on any subsystem without service interruption. The impressive feature of the proposed methodology is that all these properties can be achieved at low installation and maintenance costs, as the system can piggyback on a building's existing audio, lighting, and RF communication capabilities. One unique property of the proposed positioning algorithm will be its modularity and extensibility. Information coming from different sensors will be incorporated seamlessly, allowing the algorithm to work under intermittent failure of one of its subcomponents. The inclusion of ambulation models, together with accelerometer, gyroscope and compass data available on the majority of today's smartphones, will allow the achievement of fine-grain tracking, which will provide smooth trajectories in place of sequence of locations. In the proposed scheme, Multi-sensor localization and BIM play a synergetic role. BIM will contribute to decreasing installation and maintenance costs, by providing precise positioning of the sources of ranging (e.g., light, ultrasound, Wi-Fi antennas) and accurate topological information to develop high fidelity ranging models. Additionally, the semantic information provided by BIM will help with detecting infeasible trajectories. On the other hand, Simultaneous Localization and Mapping (SLAM)-based techniques can help refine BIMs and keep them updated. Dynamic information can enhance BIMs by providing useful information to building managers about traffic patterns and occupancy. Importantly, the design of the smart service needs to be human-centered and to take into account each of the stakeholders, i.e., owner and facilities management team, the service developers, the users of the smart service application program interface (API), who will develop value-added services customized for a particular facility or more generally for many facilities, and, of course, the end-users, the occupants and visitors of the facility, who will use the smart services themselves. To understand the needs and wants of such distinct groups of stakeholders, the project will directly involve them by conducting a series of focus groups. Participatory design is an established technique where a design team works directly with stakeholders to design an artifact or service. Stakeholders will also be engaged in the formal testing of the software service, from installation to maintenance, to application design and to application usage.
At the inception of the project, partners include the lead institution: Carnegie Mellon University, (Departments of Electrical and Computer Engineering, Civil and Environmental Engineering, and the Human-Computer Interaction Institute) Pittsburgh, PA, with primary partners: Bosch RTC Pittsburgh (Pittsburgh, PA, large business) and Sports and Exhibition Authority (Pittsburgh, PA, large business).
|
0.915 |
2017 — 2018 |
Dey, Anind |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Workshop: Joint Doctoral Colloquium At the Ubicomp 2017 and Iswc 2017 Conferences @ Carnegie-Mellon University
This is funding to partially support a joint doctoral research colloquium (workshop) of about 24 promising doctoral students from the United States and abroad (up to 2 international participants to be supported by NSF), to be selected through a peer review process, along with two panels of 4 invited outstanding researchers from both academic and industrial labs. The event will take place in conjunction with the 19th ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) and the 21st ACM International Symposium on Wearable Computing (ISWC), to be collocated in Maui, Hawaii on September 11-15, and sponsored by the Association for Computing Machinery. The ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) is the premier interdisciplinary venue in which leading international researchers, designers, developers, and practitioners in the field present and discuss novel results in all aspects of ubiquitous and pervasive computing. This includes the design, development, and deployment of ubiquitous and pervasive computing technologies and the understanding of human experiences and social impacts that these technologies facilitate. Relevant research topics include, but are not limited to, systems and infrastructures, devices and techniques, applications and experiences, methodologies and tools, and theories and models. More information about the conference may be found at http://www.ubicomp.org/ubicomp2017/. ISWC is a conference dedicated to cutting-edge research in wearable technologies, and is the premier forum for wearable computing and issues related to on-body and worn mobile technologies. Every year, ISWC brings together researchers, product vendors, fashion designers, textile manufacturers, users, and related professionals to share information and advances in wearable computing. The conference typically includes dedicated workshops, a juried design competition, a lively gadget show, and high-quality paper presentation sessions revealing the latest in wearable computing progress. More information about this conference may be found at http://www.iswc.net/iswc17/. The joint ISWC/UbiComp Doctoral Colloquium will help expand the participation of young researchers pursuing graduate studies in the various fields associated with ubiquitous computing, by affording them an opportunity to gain wider exposure in the community for their innovative work and to obtain feedback and guidance from senior members of the research community. It will further help foster a sense of community among these young researchers, by allowing them to create a social network both among themselves and with senior researchers at a critical stage in their professional development. Many participants in past UbiComp doctoral consortia have since gone on to high profile research careers. The event organizers are committed to achieving diversity among the student participants, including in terms of gender and ethnicity. To further support diversity, no more than 2 students will be accepted from any one institution.
The goals of the joint ISWC/UbiComp Doctoral Colloquium are: to provide a forum that will allow senior-level doctoral students to attend the ISWC/UbiComp conferences and take part as contributors to the program, as well as encourage further participation in the future; to give emerging ISWC and UbiComp researchers the opportunity to present their work and receive feedback, guidance, and encouragement from respected researchers to whom they may not have ready access at their home institutions; to provide opportunities for discussion among senior-level doctoral students to expose them to new perspectives on their field and in closely related fields; to foster the building of research relationships that will continue to benefit the students as they progress in their careers; and to expose the diversity and depth of research in the field as being undertaken by junior researchers to the greater UbiComp/ISWC community. To these ends, the format of the doctoral colloquium will facilitate the open exchange of ideas and in-depth discussion among members of the next generation of wearable and ubiquitous computing researchers and established top researchers in the area. The colloquium will begin with a joint session in which all participants will present a 1-minute version of their research. Subsequently, participants will present in-depth in two parallel tracks, attended by the respective conference panels. Students will be encouraged to move freely between the sessions, attending presentations according to their interests. The colloquium will close with a joint career development panel. Meals and breaks will be shared. Presentations will be scheduled with ample time allotted for questions and constructive feedback from the panel and from the other student participants. Particular emphasis will be given to such topics as focusing research questions and ensuring that research activities appropriately address the research questions, the selection and application of fitting and correct methods given the intended contributions of the work, and the appropriate analysis, framing, and communication of findings, results, and contributions. Additional opportunities for more informal discussion and networking will be during the DC lunch and dinner events. Extended abstracts from the DC will be distributed in the conference's supplemental proceedings to all conference attendees, and indexed in the ACM and IEEE digital libraries, offering further exposure. Finally, colloquium participants will also be asked to prepare a poster for a joint ISWC/UbiComp DC poster session as part of the main conference.
|
0.915 |
2018 — 2021 |
Doryab, Afsaneh Dey, Anind |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Chs: Small: Computational Modeling of Human Rhythms to Improve Health and Quality of Life @ Carnegie-Mellon University
According to recent research, balance is a significant contributor to health and well-being. Health challenges are associated with work and personal imbalances, in the form of overload, that exceed human capability to manage their own natural pace. Part of these overloads are due to the imposition of activities and mis-timed or incompatible demands on biological and psychological needs, or lack of attention to synchronization or receptivity of mental and physical states when meeting work and life demands. Advice about life management and health is often generic (for example, have 8 hours sleep a day) rather than tailored to individual lifestyles. This research proposes to improve health and wellbeing in individuals through awareness of their personal rhythms, which are repeated cycles of internal and external events including biological, mental, social, and environmental. The investigators seek to design and evaluate a data analytic and modeling method to make people aware of what they could be doing at any given time to align with their biological clock and to achieve high performance in daily life and work without burning out or developing stress-related disorders.
The research provides an intelligent platform for collecting longitudinal data and modeling human rhythms to enable detection of current, and prediction of future states in each rhythm to provide optimal action recommendations and interventions. The work leverages advances in wearable devices, sensing technology, and online sources to proactively collect and analyze physiological, psychological, behavioral, social, and environmental data to identify personal rhythms, to explore their relationship to positive physical, mental, and behavioral outcomes, and to provide people with tools to reason about these relationships and to improve outcomes. In addition to advancing the state of the art in modeling rhythmic patterns, the research will demonstrate the impact of rhythm-aware technology in changing people?s perceptions and behavior and directing them towards a more balanced and successful life. Integration of personal rhythms in daily lives of individuals will transform societal activities and the overall performance of people and contributes to creating a healthier society.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
|
0.915 |
2020 — 2023 |
Riskin, Eve (co-PI) [⬀] Mankoff, Jennifer Dey, Anind Nurius, Paula (co-PI) [⬀] |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Using Passive Sensing to Assess the Impact of Real-Time Discrimination Against Women and Underrepresented Minorities in Engineering @ University of Washington
Increasing diversity in engineering and computer science has been a goal that remains elusive. Despite significant efforts, underrepresented minorities received only 16.1% and women received only 21.9% of engineering degrees in 2018. The reasons for these low numbers are complex and multifaceted and discrimination is an important factor in why students from these groups leave engineering. The goal of this research is to develop a holistic understanding of the impact of discrimination on historically underrepresented engineering students. In this era of big data and readily available technology such as mobile phones and wearables, a comprehensive change in how data about the college student experience are collected and assessed is possible. One can now move from lab to field, connect action to behavior, and collect longitudinal data. This, in turn, makes it possible to understand bias and its impact on engineering education in new ways: By complementing self-reports with passive data collection, big data can be used to create an image of behavior while learning about specific challenges underrepresented minority and female engineering students face.
The project will result in a uniquely powerful longitudinal data set, which captures real-time changes in student experiences and allows study of the impact of discrimination at scale across a variety of contexts. The project will quantify the scope, direction, and longitudinal impact on behavior and link this to long-term outcomes such as GPA and retention. This ability to connect behavior to experience in the field was lacking in past studies of discrimination. Analytic techniques capable of capturing both individual variance and looking at unequal numbers of observations, such as hierarchical linear modeling, are required due to the large sample (N=200/year) and number of variables. The data are collected at a large public university and will be most applicable to similar programs at similar institutions. The research will support policy making and intervention design in engineering programs. The ultimate goal is to diversify the pool of engineering students, which will be of direct benefit to society by increasing representation and the range of perspectives engaged in the engineering and computer science workforce.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
|
0.915 |