publications
publications by categories in reversed chronological order.
2025
- Exploring the Design Space of Real-time LLM Knowledge Support Systems: A Case Study of Jargon ExplanationsYuhan Liu , Aadit Shah , Jordan Ackerman , and Manaswi SahaCHI ’25: In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, Yokohama, Japan, 2025
Knowledge gaps often arise during communication due to diverse backgrounds, knowledge bases, and vocabularies. With recent LLM developments, providing real-time knowledge support is increasingly viable, but is challenging due to shared and individual cognitive limitations (e.g., attention, memory, and comprehension) and the difficulty in understanding the user’s context and internal knowledge. To address these challenges, we explore the key question of understanding how people want to receive real-time knowledge support. We built StopGap—a prototype that provides real-time knowledge support for explaining jargon words in videos—to conduct a design probe study (N=24) that explored multiple visual knowledge representation formats. Our study revealed individual differences in preferred representations and highlighted the importance of user agency, personalization, and mixed-initiative assistance. Based on our findings, we map out six key design dimensions for real-time LLM knowledge support systems and offer insights for future research in this space.
@inproceedings{liu2025exploring, author = {Liu, Yuhan and Shah, Aadit and Ackerman, Jordan and Saha, Manaswi}, title = {Exploring the Design Space of Real-time LLM Knowledge Support Systems: A Case Study of Jargon Explanations}, year = {2025}, isbn = {9798400713941}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3706598.3714262}, doi = {10.1145/3706598.3714262}, booktitle = {Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems}, articleno = {633}, numpages = {20}, keywords = {Knowledge Support Systems, Knowledge Representation, Real-time Communication, Large Language Model}, location = {Yokohama, Japan}, series = {CHI '25} }
2024
- Steering AI-Driven Personalization of Scientific Text for General AudiencesTaewook Kim , Dhruv Agarwal , Jordan Ackerman , and Manaswi SahaarXiv preprint arXiv:2411.09969, 2024
Digital media platforms (e.g., social media, science blogs) offer opportunities to communicate scientific content to general audiences at scale. However, these audiences vary in their scientific expertise, literacy levels, and personal backgrounds, making effective science communication challenging. To address this challenge, we designed TranSlider, an AI-powered tool that generates personalized translations of scientific text based on individual user profiles (e.g., hobbies, location, and education). Our tool features an interactive slider that allows users to steer the degree of personalization from 0 (weakly relatable) to 100 (strongly relatable), leveraging LLMs to generate the translations with given degrees. Through an exploratory study with 15 participants, we investigated both the utility of these AI-personalized translations and how interactive reading features influenced users’ understanding and reading experiences. We found that participants who preferred higher degrees of personalization appreciated the relatable and contextual translations, while those who preferred lower degrees valued concise translations with subtle contextualization. Furthermore, participants reported the compounding effect of multiple translations on their understanding of scientific content. Given these findings, we discuss several implications of AI-personalized translation tools in facilitating communication in collaborative contexts.
@article{kim2024steering, title = {Steering AI-Driven Personalization of Scientific Text for General Audiences}, author = {Kim, Taewook and Agarwal, Dhruv and Ackerman, Jordan and Saha, Manaswi}, journal = {arXiv preprint arXiv:2411.09969}, year = {2024}, eprint = {2411.09969}, archiveprefix = {arXiv}, primaryclass = {cs.HC}, url = {https://arxiv.org/abs/2411.09969} } - A Study on Domain Generalization for Failure Detection through Human Reactions in HRIMaria Teresa Parreira , Sukruth Gowdru Lingaraju , Adolfo Ramirez-Aristizabal , Manaswi Saha , Michael Kuniavsky , and Wendy JuarXiv preprint arXiv:2403.06315, 2024
Machine learning models are commonly tested in-distribution (same dataset); performance almost always drops in out-of-distribution settings. For HRI research, the goal is often to develop generalized models. This makes domain generalization - retaining performance in different settings - a critical issue. In this study, we present a concise analysis of domain generalization in failure detection models trained on human facial expressions. Using two distinct datasets of humans reacting to videos where error occurs, one from a controlled lab setting and another collected online, we trained deep learning models on each dataset. When testing these models on the alternate dataset, we observed a significant performance drop. We reflect on the causes for the observed model behavior and leave recommendations. This work emphasizes the need for HRI research focusing on improving model robustness and real-life applicability.
@article{parreira2024study, title = {A Study on Domain Generalization for Failure Detection through Human Reactions in HRI}, author = {Parreira, Maria Teresa and Lingaraju, Sukruth Gowdru and Ramirez-Aristizabal, Adolfo and Saha, Manaswi and Kuniavsky, Michael and Ju, Wendy}, journal = {arXiv preprint arXiv:2403.06315}, year = {2024}, eprint = {2403.06315}, archiveprefix = {arXiv}, primaryclass = {cs.HC}, url = {https://arxiv.org/abs/2403.06315} } - "Bad Idea, Right?" Exploring Anticipatory Human Reactions for Outcome Prediction in HRIMaria Teresa Parreira , Sukruth Gowdru Lingaraju , Adolfo Ramirez-Artistizabal , Alexandra Bremers , Manaswi Saha , Michael Kuniavsky , and Wendy JuROMAN ’24: In Proceedings of the 33rd IEEE International Conference on Robot and Human Interactive Communication, 2024
Humans have the ability to anticipate what will happen in their environment based on perceived information. Their anticipation is often manifested as an externally observable behavioral reaction, which cues other people in the environment that something bad might happen. As robots become more prevalent in human spaces, robots can leverage these visible anticipatory responses to assess whether their own actions might be "a bad idea?" In this study, we delved into the potential of human anticipatory reaction recognition to predict outcomes. We conducted a user study wherein 30 participants watched videos of action scenarios and were asked about their anticipated outcome of the situation shown in each video ("good" or "bad"). We collected video and audio data of the participants reactions as they were watching these videos. We then carefully analyzed the participants’ behavioral anticipatory responses; this data was used to train machine learning models to predict anticipated outcomes based on human observable behavior. Reactions are multimodal, compound and diverse, and we find significant differences in facial reactions. Model performances are around 0.5-0.6 test accuracy, and increase notably when nonreactive participants are excluded from the dataset. We discuss the implications of these findings and future work. This research offers insights into improving the safety and efficiency of human-robot interactions, contributing to the evolving field of robotics and human-robot collaboration.
@inproceedings{parreira2024bad, author = {Parreira, Maria Teresa and Lingaraju, Sukruth Gowdru and Ramirez-Artistizabal, Adolfo and Bremers, Alexandra and Saha, Manaswi and Kuniavsky, Michael and Ju, Wendy}, booktitle = {Proceedings of the 33rd IEEE International Conference on Robot and Human Interactive Communication}, title = {"Bad Idea, Right?" Exploring Anticipatory Human Reactions for Outcome Prediction in HRI}, year = {2024}, volume = {}, number = {}, pages = {2072-2078}, keywords = {Accuracy;Navigation;Human-robot interaction;Machine learning;Predictive models;Data models;Behavioral sciences;Safety;Robots;Videos;robot error;social signals;anticipation;error prevention;computer vision;human-AI collaboration}, doi = {10.1109/RO-MAN60168.2024.10731310}, series = {ROMAN '24} } - Situated Conversational Agents for Task Guidance: A Preliminary User StudyAlexandra W.D. Bremers , Manaswi Saha , and Adolfo G. Ramirez-AristizabalCUI ’24: In Proceedings of the 6th ACM Conference on Conversational User Interfaces, Luxembourg, Luxembourg, 2024
Multimodal large language models have enabled a new generation of Conversational Agents (CA), leveraging language structure in human discourse to encode-decode multimedia formats (e.g., video-to-audio). These next-generation CAs can be useful in task guidance scenarios, where the user’s attention space is limited and verbal instructions can be overwhelming. In this paper, we explore the role of non-verbal conversational cues in identifying and recovering from errors while performing various assembly tasks. Findings from an exploratory Wizard-of-Oz study (N=8) indicate individual differences and preferences for auditory guidance. Combining these initial findings with our early exploration of the task monitoring system, we discuss implications for the emerging area of situated multimodal CAs for physical task guidance, where conversational interactions are based on inputting visual task actions and generating auditory feedback.
@inproceedings{bremers2024situated, author = {Bremers, Alexandra W.D. and Saha, Manaswi and Ramirez-Aristizabal, Adolfo G.}, title = {Situated Conversational Agents for Task Guidance: A Preliminary User Study}, year = {2024}, isbn = {9798400705113}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3640794.3665575}, doi = {10.1145/3640794.3665575}, booktitle = {Proceedings of the 6th ACM Conference on Conversational User Interfaces}, articleno = {51}, numpages = {7}, keywords = {audio augmented reality, conversational agents, multimodal, physical assembly, task guidance}, location = {Luxembourg, Luxembourg}, series = {CUI '24} }
2023
2022
- The Future of Urban Accessibility for People with Disabilities: Data Collection, Analytics, Policy, and ToolsJon E. Froehlich , Yochai Eisenberg , Maryam Hosseini , Fabio Miranda , Marc Adams , Anat Caspi , Holger Dieterich , Heather Feldner , Aldo Gonzalez , Claudina De Gyves , Joy Hammel , Reuben Kirkham, and 16 more authorsASSETS ’22: In Proceedings of the 24th International ACM SIGACCESS Conference on Computers and Accessibility, Athens, Greece, 2022
Inaccessible urban infrastructure creates and reinforces systemic exclusion of people with disabilities and impacts public health, physical activity, and quality of life for all. To improve the design of our cities and to enable more equitable policies and location-centric technology designs, we need new data collection techniques, data standards, and accessibility-infused analytic tools and interactive maps focused on the quality, safety, and accessibility of pathways, transit ecosystems, and buildings. In this workshop, we bring together leading experts in human mobility, urban design, disability, and accessible computing to discuss pressing urban access challenges across the world and brainstorm solutions. We invite contributions from practitioners, transit officials, disability advocates, and researchers.
@inproceedings{froehlich2022future, author = {Froehlich, Jon E. and Eisenberg, Yochai and Hosseini, Maryam and Miranda, Fabio and Adams, Marc and Caspi, Anat and Dieterich, Holger and Feldner, Heather and Gonzalez, Aldo and De Gyves, Claudina and Hammel, Joy and Kirkham, Reuben and Kneisel, Melanie and Labb\'{E}, Delphine and Mooney, Steve J. and Pineda, Victor and Pinh\~{A}O, Cl\'{A}Udia and Rodr\'{I}Guez, Ana and Saha, Manaswi and Saugstad, Michael and Shanley, Judy and Sharif, Ather and Shen, Qing and Silva, Claudio and Sukel, Maarten and Tokuda, Eric K. and Zappe, Sebastian Felix and Zivarts, Anna}, title = {The Future of Urban Accessibility for People with Disabilities: Data Collection, Analytics, Policy, and Tools}, year = {2022}, isbn = {9781450392587}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3517428.3550402}, doi = {10.1145/3517428.3550402}, booktitle = {Proceedings of the 24th International ACM SIGACCESS Conference on Computers and Accessibility}, articleno = {102}, numpages = {8}, location = {Athens, Greece}, series = {ASSETS '22} } - Designing Interactive Data-Driven Tools for Understanding Urban Accessibility at ScaleManaswi SahaUniversity of Washington, Aug 2022PhD Dissertation
Accessibility of urban infrastructure affects the mobility and safety of people, but disproportionately affects people with mobility disabilities. For example, missing curb ramps and uprooted sidewalks can significantly impact the day-to-day travel and safety of wheelchair users. However, there is an immense lack of comprehensive tools to understand and assess urban accessibility and aid decision-making.In this dissertation, I explore the issue of understanding urban accessibility and designing tools for it, with a specific focus on sidewalk accessibility for people with mobility disabilities. I aim to transform how we collect, quantify, visualize, and communicate urban accessibility data through interactive tools. Towards this goal, I have a two-fold vision: (1) mapping the physical accessibility of the world and (2) empowering people with interactive data-driven tools for daily living and urban-scale decision-making. I take a multi-stakeholder approach and characterize urban accessibility as a three-pronged problem: People, Data, and Tools.To address these problems, this dissertation follows three research threads: (1) Socio-Political Environment Analysis [People problem]: Understanding multi-stakeholder interactions and decision-making in a civic ecosystem that leads to inaccessible infrastructure, (2) Scalable Data Collection [Data problem]: Building scalable approaches to address the lack of comprehensive city-wide accessibility datasets, and (3) Interactive Data-driven Decision-Making Tools [Tools problem]: Designing interactive tools for aiding in-situ and remote accessibility decision-making.Across the threads, I bring multiple perspectives from varied stakeholders and diverse decision-making contexts to inform the design of future tools in this space. Specifically, I study five stakeholder groups, namely, policymakers, department officials, accessibility advocates, people with mobility disabilities, and caregivers. Using qualitative studies, online street view imagery, and techniques from crowdsourcing, visualization, and AI, I develop sets of design guidelines and a suite of interactive tools that enable stakeholders to surface underlying causes of inaccessibility, build and raise awareness, and present relevant information for making decisions across daily living, city planning, political advocacy, and policymaking.
@phdthesis{saha2022designing, author = {Saha, Manaswi}, advisor = {Froehlich, Jon E.}, title = {Designing Interactive Data-Driven Tools for Understanding Urban Accessibility at Scale}, month = aug, year = {2022}, isbn = {9798357559746}, school = {University of Washington}, publisher = {University of Washington}, url = {https://www.proquest.com/openview/e4088b197d4f942af13e9c1265e42c13/1?pq-origsite=gscholar&cbl=18750&diss=y}, note = {PhD Dissertation} } - Visualizing Urban Accessibility: Investigating Multi-Stakeholder Perspectives through a Map-based Design Probe StudyManaswi Saha , Siddhant Patil , Emily Cho , Evie Yu-Yen Cheng , Chris Horng , Devanshi Chauhan , Rachel Kangas , Richard McGovern , Anthony Li , Jeffrey Heer , and Jon E. FroehlichCHI ’22: In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, New Orleans, LA, USA, 2022
Urban accessibility assessments are challenging: they involve varied stakeholders across decision-making contexts while serving a diverse population of people with disabilities. To better support urban accessibility assessment using data visualizations, we conducted a three-part interview study with 25 participants across five stakeholder groups using map visualization probes. We present a multi-stakeholder analysis of visualization needs and sensemaking processes to explore how interactive visualizations can support stakeholder decision making. In particular, we elaborate how stakeholders’ varying levels of familiarity with accessibility, geospatial analysis, and specific geographic locations influences their sensemaking needs. We then contribute 10 design considerations for geovisual analytic tools for urban accessibility communication, planning, policymaking, and advocacy.
@inproceedings{saha2022visualizing, author = {Saha, Manaswi and Patil, Siddhant and Cho, Emily and Cheng, Evie Yu-Yen and Horng, Chris and Chauhan, Devanshi and Kangas, Rachel and McGovern, Richard and Li, Anthony and Heer, Jeffrey and Froehlich, Jon E.}, title = {Visualizing Urban Accessibility: Investigating Multi-Stakeholder Perspectives through a Map-based Design Probe Study}, year = {2022}, isbn = {9781450391573}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3491102.3517460}, doi = {10.1145/3491102.3517460}, booktitle = {Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems}, articleno = {413}, numpages = {14}, keywords = {decision-making, geovisual analysis, physical accessibility, sensemaking, urban tech, visualization}, location = {New Orleans, LA, USA}, series = {CHI '22} }
2021
- The Future of Global-Scale Spatial Data Collection and Analyses on Urban (in)Accessibility for People with DisabilitiesJon E. Froehlich , Fabio Miranda , Maryam Hosseini , Nick Bolten , Anat Caspi , Roberto M. Cesar Jr. , Holger Dieterich , Yochai Eisenberg , Victor Pineda , Manaswi Saha , Mikey Saugstad , Andres Sevtsuk, and 3 more authorsSDSS ’21: In 2nd Spatial Data Science Symposium, Virtual, 2021
@inproceedings{froehlich2021future, title = {The Future of Global-Scale Spatial Data Collection and Analyses on Urban (in)Accessibility for People with Disabilities}, author = {Froehlich, Jon E. and Miranda, Fabio and Hosseini, Maryam and Bolten, Nick and Caspi, Anat and Cesar Jr., Roberto M. and Dieterich, Holger and Eisenberg, Yochai and Pineda, Victor and Saha, Manaswi and Saugstad, Mikey and Sevtsuk, Andres and Silva, Claudio T. and Tokuda, Eric K. and Zappe, Sebastian Felix}, booktitle = {2nd Spatial Data Science Symposium}, volume = {2}, year = {2021}, series = {SDSS '21}, location = {Virtual}, }
2020
- Towards Mapping and Assessing Sidewalk Accessibility Across Sociocultural and Geographic ContextsJon E. Froehlich , Michael Saugstad , Manaswi Saha , and Matthew JohnsonAVI ’20: In Proceedings of the 18th International Conference on Advanced Visual Interfaces, 2020
Despite the important role of sidewalks in supporting mobility, accessibility, and public health, there is a lack of high-quality datasets and corresponding analyses on sidewalk existence and condition. Our work explores a twofold vision: first, to develop scalable mechanisms to locate and assess sidewalks in cities across the world, and second, to use this data to support new urban analyses and mobility tools. We report on two preliminary urban science explorations enabled by our approach: exploring geo-spatial patterns and key correlates of sidewalk accessibility and examining differences in sidewalk infrastructure across regions.
@inproceedings{froehlich2020towards, title = {Towards Mapping and Assessing Sidewalk Accessibility Across Sociocultural and Geographic Contexts}, author = {Froehlich, Jon E. and Saugstad, Michael and Saha, Manaswi and Johnson, Matthew}, booktitle = {Proceedings of the 18th International Conference on Advanced Visual Interfaces}, year = {2020}, eprint = {2207.13626}, archiveprefix = {arXiv}, primaryclass = {cs.HC}, url = {https://arxiv.org/abs/2207.13626}, doi = {10.48550/arXiv.2207.13626}, series = {AVI '20} } - Urban Accessibility as a Socio-Political Problem: A Multi-Stakeholder AnalysisManaswi Saha , Devanshi Chauhan , Siddhant Patil , Rachel Kangas , Jeffrey Heer , and Jon E. FroehlichCSCW ’20: In Proceedings of the ACM Computer-Supported Cooperative Work, 2020
Traditionally, urban accessibility is defined as the ease of reaching destinations. Studies on urban accessibility for pedestrians with mobility disabilities (e.g., wheelchair users) have primarily focused on understanding the challenges that the built environment imposes and how they overcome them. In this paper, we move beyond physical barriers and focus on socio-political challenges in the civic ecosystem that impedes accessible infrastructure development. Using a multi-stakeholder approach, we interviewed five primary stakeholder groups (N=25): (1) people with mobility disabilities, (2) caregivers, (3) accessibility advocates, (4) department officials, and (5) policymakers. We discussed their current accessibility assessment and decision-making practices. We identified the key needs and desires of each group, how they differed, and how they interacted with each other in the civic ecosystem to bring about change. We found that people, politics, and money were intrinsically tied to underfunded accessibility improvement projects "without continued support from the public and the political leadership, existing funding may also disappear. Using the insights from these interviews, we explore how may technology enhance our stakeholders" decision-making processes and facilitate accessible infrastructure development.
@inproceedings{saha2020urban, author = {Saha, Manaswi and Chauhan, Devanshi and Patil, Siddhant and Kangas, Rachel and Heer, Jeffrey and Froehlich, Jon E.}, title = {Urban Accessibility as a Socio-Political Problem: A Multi-Stakeholder Analysis}, year = {2020}, issue_date = {December 2020}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, volume = {4}, number = {CSCW3}, url = {https://doi.org/10.1145/3432908}, doi = {10.1145/3432908}, booktitle = {Proceedings of the ACM Computer-Supported Cooperative Work}, articleno = {209}, numpages = {26}, keywords = {advocacy, civic engagement, digital civics, physical accessibility, policymaking, politics, urban technology}, series = {CSCW '20} }
2019
- Closing the Gap: Designing for the Last-Few-Meters Wayfinding Problem for People with Visual ImpairmentsManaswi Saha , Alexander J. Fiannaca , Melanie Kneisel , Edward Cutrell , and Meredith Ringel MorrisASSETS ’19: In Proceedings of the 21st International ACM SIGACCESS Conference on Computers and Accessibility, Pittsburgh, PA, USA, 2019
Despite the major role of Global Positioning Systems (GPS) as a navigation tool for people with visual impairments (VI), a crucial missing aspect of point-to-point navigation with these systems is the last-few-meters wayfinding problem. Due to GPS inaccuracy and inadequate map data, systems often bring a user to the vicinity of a destination but not to the exact location, causing challenges such as difficulty locating building entrances or a specific storefront from a series of stores. In this paper, we study this problem space in two parts: (1) A formative study (N=22) to understand challenges, current resolution techniques, and user needs; and (2) A design probe study (N=13) using a novel, vision-based system called Landmark AI to understand how technology can better address aspects of this problem. Based on these investigations, we articulate a design space for systems addressing this challenge, along with implications for future systems to support precise navigation for people with VI.
@inproceedings{saha2019closing, author = {Saha, Manaswi and Fiannaca, Alexander J. and Kneisel, Melanie and Cutrell, Edward and Morris, Meredith Ringel}, title = {Closing the Gap: Designing for the Last-Few-Meters Wayfinding Problem for People with Visual Impairments}, year = {2019}, isbn = {9781450366762}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3308561.3353776}, doi = {10.1145/3308561.3353776}, booktitle = {Proceedings of the 21st International ACM SIGACCESS Conference on Computers and Accessibility}, pages = {222–235}, numpages = {14}, keywords = {accessibility, blindness, landmarks, wayfinding}, location = {Pittsburgh, PA, USA}, series = {ASSETS '19} } - Project Sidewalk: A Web-based Crowdsourcing Tool for Collecting Sidewalk Accessibility Data At ScaleManaswi Saha , Michael Saugstad , Hanuma Teja Maddali , Aileen Zeng , Ryan Holland , Steven Bower , Aditya Dash , Sage Chen , Anthony Li , Kotaro Hara , and Jon FroehlichCHI ’19: In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, Glasgow, Scotland UK, 2019
We introduce Project Sidewalk, a new web-based tool that enables online crowdworkers to remotely label pedestrian-related accessibility problems by virtually walking through city streets in Google Street View. To train, engage, and sustain users, we apply basic game design principles such as interactive onboarding, mission-based tasks, and progress dashboards. In an 18-month deployment study, 797 online users contributed 205,385 labels and audited 2,941 miles of Washington DC streets. We compare behavioral and labeling quality differences between paid crowdworkers and volunteers, investigate the effects of label type, label severity, and majority vote on accuracy, and analyze common labeling errors. To complement these findings, we report on an interview study with three key stakeholder groups (N=14) soliciting reactions to our tool and methods. Our findings demonstrate the potential of virtually auditing urban accessibility and highlight tradeoffs between scalability and quality compared to traditional approaches.
@inproceedings{saha2019project, author = {Saha, Manaswi and Saugstad, Michael and Maddali, Hanuma Teja and Zeng, Aileen and Holland, Ryan and Bower, Steven and Dash, Aditya and Chen, Sage and Li, Anthony and Hara, Kotaro and Froehlich, Jon}, title = {Project Sidewalk: A Web-based Crowdsourcing Tool for Collecting Sidewalk Accessibility Data At Scale}, year = {2019}, isbn = {9781450359702}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3290605.3300292}, doi = {10.1145/3290605.3300292}, booktitle = {Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems}, pages = {1–14}, numpages = {14}, keywords = {urban informatics, mobility impairments, gis, crowdsourcing, accessibility}, location = {Glasgow, Scotland UK}, series = {CHI '19} }
2018
- Interactively Modeling and Visualizing Neighborhood Accessibility at Scale: An Initial Study of Washington DCAnthony Li , Manaswi Saha , Anupam Gupta , and Jon E. FroehlichASSETS ’18: In Proceedings of the 20th International ACM SIGACCESS Conference on Computers and Accessibility, Galway, Ireland, 2018
Walkability indices such as walkscore.com model the proximity and density of walkable destinations within a neighborhood. While these metrics have gained widespread use (e.g., incorporated into real-estate tools), they do not integrate accessibility-related features such as sidewalk conditions or curb ramps-thereby excluding a significant portion of the population. In this poster paper, we explore the initial design and implementation of neighborhood accessibility models and visualizations for people with mobility impairments. We are able to overcome previous data availability challenges by using the Project Sidewalk API, which provides access to 255,000+ labels about the accessibility and location of DC sidewalks.
@inproceedings{li2018interactively, author = {Li, Anthony and Saha, Manaswi and Gupta, Anupam and Froehlich, Jon E.}, title = {Interactively Modeling and Visualizing Neighborhood Accessibility at Scale: An Initial Study of Washington DC}, year = {2018}, isbn = {9781450356503}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3234695.3241000}, doi = {10.1145/3234695.3241000}, booktitle = {Proceedings of the 20th International ACM SIGACCESS Conference on Computers and Accessibility}, pages = {444–446}, numpages = {3}, keywords = {geo-visualization, mobility impaired, urban accessibility, walkability indices}, location = {Galway, Ireland}, series = {ASSETS '18}, }
2017
- A Pilot Deployment of an Online Tool for Large-Scale Virtual Auditing of Urban AccessibilityManaswi Saha , Kotaro Hara , Soheil Behnezhad , Anthony Li , Michael Saugstad , Hanuma Maddali , Sage Chen , and Jon E. FroehlichASSETS ’17: In Proceedings of the 19th International ACM SIGACCESS Conference on Computers and Accessibility, Baltimore, Maryland, USA, 2017
We present Project Sidewalk, a new online tool that allows anyone-from motivated citizens to government workers-to remotely label accessibility problems by virtually walking through city streets. Basic game design principles such as interactive onboarding, mission-based tasks, and stats dashboards are used to train, engage, and sustain users. We describe the current Project Sidewalk system, present results of a pilot public deployment with 581 users, and discuss open questions and future work.
@inproceedings{saha2017pilot, author = {Saha, Manaswi and Hara, Kotaro and Behnezhad, Soheil and Li, Anthony and Saugstad, Michael and Maddali, Hanuma and Chen, Sage and Froehlich, Jon E.}, title = {A Pilot Deployment of an Online Tool for Large-Scale Virtual Auditing of Urban Accessibility}, year = {2017}, isbn = {9781450349260}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3132525.3134775}, doi = {10.1145/3132525.3134775}, booktitle = {Proceedings of the 19th International ACM SIGACCESS Conference on Computers and Accessibility}, pages = {305–306}, numpages = {2}, keywords = {crowdsourcing, gis, mobility impaired users, urban accessibility}, location = {Baltimore, Maryland, USA}, series = {ASSETS '17} } - Exploring Novice Approaches to Smartphone-based Thermographic Energy Auditing: A Field StudyMatthew Louis Mauriello , Manaswi Saha , Erica Brown Brown , and Jon E. FroehlichCHI ’17: In Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems, Denver, Colorado, USA, 2017
The recent integration of thermal cameras with commodity smartphones presents an opportunity to engage the public in evaluating energy-efficiency issues in the built environment. However, it is unclear how novice users without professional experience or training approach thermographic energy auditing activities. In this paper, we recruited 10 participants for a four-week field study of end-user behavior exploring novice approaches to semi-structured thermographic energy auditing tasks. We analyze thermographic imagery captured by participants as well as weekly surveys and post-study debrief interviews. Our findings suggest that while novice users perceived thermal cameras as useful in identifying energy-efficiency issues in buildings, they struggled with interpretation and confidence. We characterize how novices perform thermographic-based energy auditing, synthesize key challenges, and discuss implications for design.
@inproceedings{mauriello2017exploring, author = {Mauriello, Matthew Louis and Saha, Manaswi and Brown, Erica Brown and Froehlich, Jon E.}, title = {Exploring Novice Approaches to Smartphone-based Thermographic Energy Auditing: A Field Study}, year = {2017}, isbn = {9781450346559}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3025453.3025471}, doi = {10.1145/3025453.3025471}, booktitle = {Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems}, pages = {1768–1780}, numpages = {13}, keywords = {energy efficiency, field study, formative inquiry, mobile devices, sustainable hci, thermography}, location = {Denver, Colorado, USA}, series = {CHI '17} }
2016
- The future role of thermography in human-building interactionMatthew Louis Mauriello , Matthew Dahlhausen , Erica Brown , Manaswi Saha , and Jon FroehlichCHI ’16: In Proceedings of the 34rd Annual ACM Conference Extended Abstracts on Human Factors in Computing Systems, San Jose, California, USA, 2016
@inproceedings{mauriello2016future, title = {The future role of thermography in human-building interaction}, author = {Mauriello, Matthew Louis and Dahlhausen, Matthew and Brown, Erica and Saha, Manaswi and Froehlich, Jon}, booktitle = {Proceedings of the 34rd Annual ACM Conference Extended Abstracts on Human Factors in Computing Systems}, year = {2016}, location = {San Jose, California, USA}, series = {CHI '16}, }
2015
- SensorAct: A Decentralized and Scriptable Middleware for Smart Energy BuildingsPandarasamy Arjunan , Manaswi Saha , Haksoo Choi , Manoj Gulati , Amarjeet Singh , Pushpendra Singh , and Mani B. SrivastavaUIC ’15: In Proceedings of the 12th Intl Conf on Ubiquitous Intelligence and Computing (UIC), 2015
Buildings, with their different subsystems interacting with diverse occupants, constitute a complex Cyber-Physical-Human infrastructure. Monitoring and controlling this complex ecosystem is essential both for efficient and optimized operations of building subsystems and for influencing the occupant behavior. A critical enabling technology in this case is a middleware system for buildings that can provide support for deriving rich inferences by fusing and analyzing intentionally acquired or opportunistically available data from diverse embedded sensors, human feedback, and existing building subsystems. This paper presents Sensor Act, a Scriptable middleware system architecture for energy management applications in buildings. In addition to providing support for managing and integrating heterogeneous sensing and actuation systems in buildings, Sensor Act provides two emerging features: (1) a scripting framework for application developers to extend and automate the various energy management functions of the buildings, and (2) a rule-based sensor data and control sharing mechanism for fine-grained sharing for building owners. We describe the detailed system architecture and design, and provide proof of concept through multiple third party applications built using Sensor Act APIs and deployment in diverse settings across India and United States. Sensor Act is released in open source for community use.
@inproceedings{arjunan2015sensoract, author = {Arjunan, Pandarasamy and Saha, Manaswi and Choi, Haksoo and Gulati, Manoj and Singh, Amarjeet and Singh, Pushpendra and Srivastava, Mani B.}, booktitle = {Proceedings of the 12th Intl Conf on Ubiquitous Intelligence and Computing (UIC)}, title = {SensorAct: A Decentralized and Scriptable Middleware for Smart Energy Buildings}, year = {2015}, volume = {}, number = {}, pages = {11-19}, keywords = {Buildings;Sensors;Monitoring;Actuators;Middleware;Architecture;Engines;Building Management Systems;Middleware;Energy Monitoring;Internet of Things}, doi = {10.1109/UIC-ATC-ScalCom-CBDCom-IoP.2015.27}, series = {UIC '15} }
2014
- WattShare: detailed energy apportionment in shared living spaces within commercial buildingsShailja Thakur , Manaswi Saha , Amarjeet Singh , and Yuvraj AgarwalBuildSys ’14: In Proceedings of the 1st ACM Conference on Embedded Systems for Energy-Efficient Buildings, Memphis, Tennessee, 2014
Increasing energy consumption of commercial buildings has motivated numerous energy tracking and monitoring systems in the recent years. A particular area that is less explored in this domain is that of energy apportionment whereby total energy usage of a shared space such as a building is disaggregated to attribute it to an individual occupant. This particular scenario of individual apportionment is important for increased transparency in the actual energy consumption of shared living spaces in commercial buildings e.g. hotels, student dormitories and hospitals amongst others. Accurate energy accounting is a difficult problem to solve using only a single smart meter. In this paper, we present a novel, scalable and a low cost energy apportionment system called WattShare that builds upon our EnergyLens architecture, where data from a common electricity meter and smartphones (carried by the occupants) is fused, and then used for detailed energy disaggregation. This information is then used to measure the room-level energy consumption. We evaluate WattShare using a week long deployment conducted in a student dormitory in a campus in India. We show that WattShare is able to disaggregate the total energy usage from a single smart meter to individual rooms with an average precision of 96.42% and average recall of 94.96%. WattShare achieves 86.42% energy apportionment accuracy which increases to 94.57% when an outlier room is removed.
@inproceedings{thakur2014wattshare, author = {Thakur, Shailja and Saha, Manaswi and Singh, Amarjeet and Agarwal, Yuvraj}, title = {WattShare: detailed energy apportionment in shared living spaces within commercial buildings}, year = {2014}, isbn = {9781450331449}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/2674061.2674069}, doi = {10.1145/2674061.2674069}, booktitle = {Proceedings of the 1st ACM Conference on Embedded Systems for Energy-Efficient Buildings}, pages = {30–39}, numpages = {10}, keywords = {smartphones, smart meters, personal energy apportionment, energy disaggregation}, location = {Memphis, Tennessee}, series = {BuildSys '14} } - EnergyLens: combining smartphones with electricity meter for accurate activity detection and user annotationManaswi Saha , Shailja Thakur , Amarjeet Singh , and Yuvraj Agarwale-Energy ’14: In Proceedings of the 5th International Conference on Future Energy Systems, Cambridge, United Kingdom, 2014
Inferring human activity is of interest for various ubiquitous computing applications, particularly if it can be done using ambient information that can be collected non intrusively. In this paper, we explore human activity inference, in the context of energy consumption within a home, where we define an "activity" as the usage of an electrical appliance, its usage duration and its location. We also explore the dimension of identifying the occupant who performed the activity. Our goal is to answer questions such as "Who is watching TV in the Dining Room and during what times?". This information is particularly important for scenarios such as the apportionment of energy use to individuals in shared settings for better understanding of occupant’s energy consumption behavioral patterns. Unfortunately, accurate activity inference in realistic settings is challenging, especially when considering ease of deployment. One of the key differences between our work and prior research in this space is that we seek to combine readily available sensor data (i.e. home level electricity meters and sensors on smartphones carried by the occupants) and metadata information (e.g. appliance power ratings and their location) for activity inference. Our proposed EnergyLens system intelligently fuses electricity meter data with sensors on commodity smartphones – the Wifi radio and the microphone – to infer, with high accuracy, which appliance is being used, when its being used, where its being used in the home, and who is using it. EnergyLens exploits easily available metadata to further improve the detection accuracy. Real world experiments show that EnergyLens significantly improves the inference of energy usage activities (average precision= 75.2%, average recall= 77.8%) as compared to traditional approaches that use the meter data only (average precision = 28.4%, average recall = 22.3%).
@inproceedings{saha2014energylens, author = {Saha, Manaswi and Thakur, Shailja and Singh, Amarjeet and Agarwal, Yuvraj}, title = {EnergyLens: combining smartphones with electricity meter for accurate activity detection and user annotation}, year = {2014}, isbn = {9781450328197}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/2602044.2602058}, doi = {10.1145/2602044.2602058}, booktitle = {Proceedings of the 5th International Conference on Future Energy Systems}, pages = {289–300}, numpages = {12}, keywords = {activity detection, energy disaggregation, smart meters, smartphones, user association}, location = {Cambridge, United Kingdom}, series = {e-Energy '14} }
2013
- Sensoract: Design and implementation of fine-grained sensing and control sharing in buildingsPandarasamy Arjunan , Manaswi Saha , Manoj Gulati , Nipun Batra , Amarjeet Singh , and Pushpendra SinghNSDI’13: In the poster track of 10th USENIX Symposium on Networked Systems Design and Implementation, 2013
@inproceedings{arjunan2013sensoract, title = {Sensoract: Design and implementation of fine-grained sensing and control sharing in buildings}, author = {Arjunan, Pandarasamy and Saha, Manaswi and Gulati, Manoj and Batra, Nipun and Singh, Amarjeet and Singh, Pushpendra}, booktitle = {the poster track of 10th USENIX Symposium on Networked Systems Design and Implementation}, series = {NSDI'13}, year = {2013} }
2012
- Bandwidth Management Framework for Multicasting in Wireless Mesh NetworksManaswi Saha and P. Venkata KrishnaInternational Journal of Information and Electronics Engineering, 2012
@article{saha2012bandwidth, title = {Bandwidth Management Framework for Multicasting in Wireless Mesh Networks}, author = {Saha, Manaswi and Krishna, P. Venkata}, journal = {International Journal of Information and Electronics Engineering}, volume = {2}, number = {3}, pages = {421}, year = {2012}, publisher = {IACSIT Press}, }