Donald Patterson | Westmont College (original) (raw)
Uploads
Papers by Donald Patterson
Proceedings of the Second Workshop on Computing within Limits, 2016
This paper introduces a hierarchical Markov model that can learn and infer a user’s daily movemen... more This paper introduces a hierarchical Markov model that can learn and infer a user’s daily movements through an urban community. The model uses multiple levels of abstraction in order to bridge the gap between raw GPS sensor measurements and high level information such as a user’s destination and mode of transportation. To achieve efficient inference, we apply Rao-Blackwellized particle filters at multiple levels of the model hierarchy. Locations such as bus stops and parking lots, where the user frequently changes mode of transportation, are learned from GPS data logs without manual labeling of training data. We experimentally demonstrate how to accurately detect novel behavior or user errors (e.g. taking a wrong bus) by explicitly modeling activities in the context of the user’s historical data. Finally, we discuss an application called “Opportunity Knocks” that employs our techniques to help cognitively-impaired people use public transportation safely.
T he Internet is radically transforming itself in response to new perspectives that encourage com... more T he Internet is radically transforming itself in response to new perspectives that encourage community and group content creation while pushing technological dominance to the background. This Web 2.0 approach drives many high-traffic Web sites such as YouTube, Wikipedia, and the news-voting site Digg. Such sites utilize modest, easily duplicated technological innovations but are market leaders because of their large, active community of content creators and consumers. In contrast, it’s rarer to find sites that use passively generated content. Implicit voting (such as when people passively cast a vote for a video on YouTube by watching it) is the notable exception. In our system, Nomatic (nomad and automatic),1 we explore a way to amplify and leverage this passive style of content creation by focusing on status messages. These short bits of text are usually created by users in the context of small communities of people who monitor each other for playor work-related distributed coord...
Communications of the ACM, 2018
The future of computing research relies on addressing an array of limitations on a planetary scale.
Proceedings of the 2016 CHI Conference Extended Abstracts on Human Factors in Computing Systems, 2016
Proceedings of the 2015 Annual Symposium on Computing for Development, 2015
First Monday, 2015
The proliferation of sensors in the world has created increased opportunities for context-aware a... more The proliferation of sensors in the world has created increased opportunities for context-aware applications. However, it is often cumbersome to capitalize on these opportunities due to the difficulties inherent in collecting, fusing, and reasoning with data from a heterogeneous set of distributed sensors. The fabric that connects sensors lacks resilience and fault tolerance in the face of infrastructure intermittency. To address these difficulties, we introduce Cacophony, a network of peer-to-peer nodes (CNodes), where each node provides real-time predictions of a specified set of sensor data. The predictions from each of the Cacophony prediction nodes can be used by any application with access to the Web. Creating a new CNode involves three steps: (1) Developers and domain-knowledge experts, via a simple Web UI, specify which sensor data they care about. Possible sources of sensor data include stationary sensors, mobile sensors, and the real-time Web; (2) The CNode automatically a...
First Monday, 2015
In 2010 Haiti experienced a catastrophic earthquake that destroyed a substantial amount of infras... more In 2010 Haiti experienced a catastrophic earthquake that destroyed a substantial amount of infrastructure in the capital of Port-au-Prince. Limited national resources and widespread poverty have made the rebuilding slow and piecemeal. Five years later that infrastructure is still unevenly repaired and maintained. Nevertheless, the Haitian people have, by necessity, continued to adapt in order to take care of day-to-day activities. Based on a field visit, this paper describes some of the ways that infrastructure has re-emerged, gives examples of how people deal with the alternate infrastructures, how the infrastructures structure their lives and discusses what these lessons entail for how the developed world frames infrastructure in the face of similar challenges caused by global energy shortages.
Lecture Notes in Computer Science, 2006
Interactions, 2012
FEATURE matic global change, then adaptation to these transformations will be of growing relevanc... more FEATURE matic global change, then adaptation to these transformations will be of growing relevance. The manner in which humans adapt to the changes will define the future of civilization. Here, we engage with the topic of how IT tools can support adaptation to global change.
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, 2012
Pervasive Computing in Healthcare, 2006
... systems PEAT29 is a commercial product that has many of the same goals as Auto-minder. ... We... more ... systems PEAT29 is a commercial product that has many of the same goals as Auto-minder. ... Wenow turn to our second case study with the assisted cognition system Barista. ... Tracking the performance of ADLs is the first step in creating systems for ADL prompting and guidance. ...
Proceedings of the 13th conference on World Wide Web - WWW '04, 2004
Proceeding of the twenty-sixth annual CHI conference extended abstracts on Human factors in computing systems - CHI '08, 2008
IEEE Pervasive Computing, 2003
Electronic Notes in Discrete Mathematics, 2001
Proceedings of the Second Workshop on Computing within Limits, 2016
This paper introduces a hierarchical Markov model that can learn and infer a user’s daily movemen... more This paper introduces a hierarchical Markov model that can learn and infer a user’s daily movements through an urban community. The model uses multiple levels of abstraction in order to bridge the gap between raw GPS sensor measurements and high level information such as a user’s destination and mode of transportation. To achieve efficient inference, we apply Rao-Blackwellized particle filters at multiple levels of the model hierarchy. Locations such as bus stops and parking lots, where the user frequently changes mode of transportation, are learned from GPS data logs without manual labeling of training data. We experimentally demonstrate how to accurately detect novel behavior or user errors (e.g. taking a wrong bus) by explicitly modeling activities in the context of the user’s historical data. Finally, we discuss an application called “Opportunity Knocks” that employs our techniques to help cognitively-impaired people use public transportation safely.
T he Internet is radically transforming itself in response to new perspectives that encourage com... more T he Internet is radically transforming itself in response to new perspectives that encourage community and group content creation while pushing technological dominance to the background. This Web 2.0 approach drives many high-traffic Web sites such as YouTube, Wikipedia, and the news-voting site Digg. Such sites utilize modest, easily duplicated technological innovations but are market leaders because of their large, active community of content creators and consumers. In contrast, it’s rarer to find sites that use passively generated content. Implicit voting (such as when people passively cast a vote for a video on YouTube by watching it) is the notable exception. In our system, Nomatic (nomad and automatic),1 we explore a way to amplify and leverage this passive style of content creation by focusing on status messages. These short bits of text are usually created by users in the context of small communities of people who monitor each other for playor work-related distributed coord...
Communications of the ACM, 2018
The future of computing research relies on addressing an array of limitations on a planetary scale.
Proceedings of the 2016 CHI Conference Extended Abstracts on Human Factors in Computing Systems, 2016
Proceedings of the 2015 Annual Symposium on Computing for Development, 2015
First Monday, 2015
The proliferation of sensors in the world has created increased opportunities for context-aware a... more The proliferation of sensors in the world has created increased opportunities for context-aware applications. However, it is often cumbersome to capitalize on these opportunities due to the difficulties inherent in collecting, fusing, and reasoning with data from a heterogeneous set of distributed sensors. The fabric that connects sensors lacks resilience and fault tolerance in the face of infrastructure intermittency. To address these difficulties, we introduce Cacophony, a network of peer-to-peer nodes (CNodes), where each node provides real-time predictions of a specified set of sensor data. The predictions from each of the Cacophony prediction nodes can be used by any application with access to the Web. Creating a new CNode involves three steps: (1) Developers and domain-knowledge experts, via a simple Web UI, specify which sensor data they care about. Possible sources of sensor data include stationary sensors, mobile sensors, and the real-time Web; (2) The CNode automatically a...
First Monday, 2015
In 2010 Haiti experienced a catastrophic earthquake that destroyed a substantial amount of infras... more In 2010 Haiti experienced a catastrophic earthquake that destroyed a substantial amount of infrastructure in the capital of Port-au-Prince. Limited national resources and widespread poverty have made the rebuilding slow and piecemeal. Five years later that infrastructure is still unevenly repaired and maintained. Nevertheless, the Haitian people have, by necessity, continued to adapt in order to take care of day-to-day activities. Based on a field visit, this paper describes some of the ways that infrastructure has re-emerged, gives examples of how people deal with the alternate infrastructures, how the infrastructures structure their lives and discusses what these lessons entail for how the developed world frames infrastructure in the face of similar challenges caused by global energy shortages.
Lecture Notes in Computer Science, 2006
Interactions, 2012
FEATURE matic global change, then adaptation to these transformations will be of growing relevanc... more FEATURE matic global change, then adaptation to these transformations will be of growing relevance. The manner in which humans adapt to the changes will define the future of civilization. Here, we engage with the topic of how IT tools can support adaptation to global change.
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, 2012
Pervasive Computing in Healthcare, 2006
... systems PEAT29 is a commercial product that has many of the same goals as Auto-minder. ... We... more ... systems PEAT29 is a commercial product that has many of the same goals as Auto-minder. ... Wenow turn to our second case study with the assisted cognition system Barista. ... Tracking the performance of ADLs is the first step in creating systems for ADL prompting and guidance. ...
Proceedings of the 13th conference on World Wide Web - WWW '04, 2004
Proceeding of the twenty-sixth annual CHI conference extended abstracts on Human factors in computing systems - CHI '08, 2008
IEEE Pervasive Computing, 2003
Electronic Notes in Discrete Mathematics, 2001