Learning from a learning thermostat: lessons for intelligent systems for the home
The DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
Abstract
Everyday systems and devices in the home are becoming smarter. In order to better understand the challenges of deploying an intelligent system in the home, we studied the experience of living with an advanced thermostat, the Nest. The Nest utilizes machine learning, sensing, and networking technology, as well as eco-feedback features. We conducted interviews with 23 participants, ten of whom also participated in a three-week diary study. Our findings show that while the Nest was well-received overall, the intelligent features of the Nest were not perceived to be as useful or intuitive as expected, in particular due to the system's inability to understand the intent behind sensed behavior and users' difficulty in understanding how the Nest works. A number of participants developed workarounds for the shortcomings they encountered. Based on our observations, we propose three avenues for future development of interactive intelligent technologies for the home: exception flagging, incidental intelligibility, and constrained engagement.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
The Computer for the 21st Century
Weiser, M. (1991) · Scientific American · doi:10.1038/scientificamerican0991-94 · Cited by 10,017
The Duality of Technology: Rethinking the Concept of Technology in Organizations
Orlikowski, W. J. (1992) · Organization Science · doi:10.1287/orsc.3.3.398 · Cited by 4,957
(2006) · Cited by 2,256
The Aware Home: A Living Laboratory for Ubiquitous Computing Research
Kidd, C. D., Orr, R., Abowd, G. D., Atkeson, C. G., Essa, I. A., MacIntyre, B., Mynatt, E., Starner, T. E., & Newstetter, W. (1999) · Lecture Notes in Computer Science · doi:10.1007/10705432_17 · Cited by 1,035 · cited 2×
“, [9,10]), or with prototypes in experimental settings (e.”
The design of eco-feedback technology
Froehlich, J., Findlater, L., & Landay, J. (2010) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1753326.1753629 · Cited by 813 · cited 2×
“, [7]), which will, in turn, motivate people to save more energy.”
(1935) · Economic Record · doi:10.1111/j.1475-4932.1935.tb02774.x · Cited by 712
Why and why not explanations improve the intelligibility of context-aware intelligent systems
Lim, B. Y., Dey, A. K., & Avrahami, D. (2009) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1518701.1519023 · Cited by 552 · cited 1×
“been done into how to design interfaces that render system behavior more intelligible [1,12,24], such research has yet”
BackgroundAt Home with Ubiquitous Computing: Seven Challenges
Edwards, W. K., & Grinter, R. E. (2001) · Cited by 535
MavHome: an agent-based smart home
Cook, D. J., Youngblood, M., Heierman, E. O., Gopalratnam, K., Rao, S., Litvin, A., & Khawaja, F. (2004) · Proceedings of the First IEEE International Conference on Pervasive Computing and Communications, 2003. (PerCom 2003). · doi:10.1109/percom.2003.1192783 · Cited by 525 · cited 1×
“, [3,9,10,15]), but few such projects have provided insight into the lived experience of occupants.”
Intelligibility and Accountability: Human Considerations in Context-Aware Systems
Bellotti, V., & Edwards, K. (2001) · Human–Computer Interaction · doi:10.1207/s15327051hci16234_05 · Cited by 471 · cited 2×
“been done into how to design interfaces that render system behavior more intelligible [1,12,24], such research has yet”
Research works printed but not linked: 4
- Dey A.K., 2009, Workshop on Intelligence and Interaction: IJCAI
- 10.5555/647987.741327 · doi:10.5555/647987.741327
- U.S. Energy Information Administration Annual Energy Review September 27 2012 U.S. Energy Information Administration Annual Energy Review September 27 2012
- 10.5555/645969.674887 · doi:10.5555/645969.674887
Cited by
Items 101–200 of 267
Yang, R., Pisharoty, D., Montazeri, S., Whitehouse, K., & Newman, M. (2016) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/2971648.2971698 · Cited by 25
Self-citationA Mobile Augmented Reality App for Creating, Controlling, Recommending Automations in Smart Homes
Mattioli, A., & Paternò, F. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3604242 · Cited by 20
Shared Language and the Design of Home Healthcare Technology
Burrows, A., Gooberman‐Hill, R., & Coyle, D. (2016) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/2858036.2858496 · Cited by 22
From Artifacts to Architecture
Alavi, H. S., Churchill, E. F., Kirk, D. S., Bier, H., Verma, H., Lalanne, D., & Schnädelbach, H. M. (2018) · ACM Conference Companion Publication on Designing Interactive Systems (DIS Companion) · doi:10.1145/3197391.3197393 · Cited by 20
Technology paternalism and smart products: Review, synthesis, and research agenda
Rochi, M. (2023) · Technological Forecasting and Social Change · doi:10.1016/j.techfore.2023.122557 · Cited by 24
Snow, S., Auffenberg, F., & schraefel, M. C. (2017) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3025453.3025578 · Cited by 22
“However the ability of the thermostat to learn preferences was complicated by too much or too little input from users, which led to a mutual misunderstanding between the users and the system [32].”
BackgroundInfluentialChallenges and Opportunities in Designing Smart Spaces
Sahni, Y., Cao, J., & Shen, J. (2017) · Internet of things · doi:10.1007/978-981-10-5861-5_6 · Cited by 18
Wu, T.-W., Chien, Y.-L., Lee, H.-P., & Chang, Y.-J. (2021) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445209 · Cited by 19
“efect [36], whereby engagement with an intelligent system gradually decreases [81].”
BackgroundGenie: a longitudinal study comparing physical and software thermostats in office buildings
Balaji, B., Koh, J., Weibel, N., & Agarwal, Y. (2016) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/2971648.2971719 · Cited by 22
“[51, 52] study long term use of Nest thermostat and show automated learning fails to capture rich behavioral context and poor mental models lead to user misconceptions.”
BackgroundMethodInfluentialSeeing (Movement) is Believing: The Effect of Motion on Perception of Automatic Systems Performance
García García, P., Costanza, E., Verame, J., Nowacka, D., & Ramchurn, S. D. (2021) · Human–Computer Interaction · doi:10.1080/07370024.2018.1453815 · Cited by 17
An Analysis of (Non-)Use Practices and Decisions of Internet of Things
Garg, R. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-29390-1_1 · Cited by 19
“Only a few studies discuss the challenges [54] or smart voice assistants [35], and they do not specifically discuss users’ (non-)use practices and decisions.”
A Conversational Agent for Creating Flexible Daily Automation
Gallo, S., & Paternò, F. (2022) · International Conference on Advanced Visual Interfaces (AVI) · doi:10.1145/3531073.3531090 · Cited by 16
“They may obtain mixed results (see for example [19]), because they may generate actions that do not match the real user needs or people may have difficulties in understanding the automatically generated automations.”
BackgroundThe everyday enactment of interfaces: a study of crises and conflicts in the more-than-human home
van Beek, E., Giaccardi, E., Boess, S. U., & Bozzon, A. (2023) · Human-Computer Interaction · doi:10.1080/07370024.2023.2283536 · Cited by 25
“For example, a study with the Nest learning thermostat found that an occasional visit from relatives who prefer lower temperatures is already enough to surface a conflict between assumed and situated needs (Yang & Newman, 2013).”
Development of an embedded system course to teach the Internet-of-Things
Rao, A. R., Clarke, D. J. B., Bhadiyadra, M., & Phadke, S. (2018) · IEEE Integrated STEM Education Conference (ISEC) · doi:10.1109/isecon.2018.8340468 · Cited by 16
“Though details of the algorithm have not been released, it is known that Nest takes about a week to generate its initial schedule and thereafter continuously adapts the scheduling to temperature adjustments made by a user [21].”
BackgroundTracking the Consumption of Home Essentials
Fuentes, C., Porcheron, M., Fischer, J. E., Costanza, E., Malik, O., & Ramchurn, S. D. (2019) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300869 · Cited by 19
“Regardless of the approach taken, predicting the needs of end-users is demonstrably an unresolved challenge, even with existing commercial systems [60], and is complicated by the multi-person, multi-activity collaborative environments such technologies are destined for, such as the home [42].”
BackgroundNon-intrusive estimation and prediction of residential AC energy consumption
Jain, M., Singh, A., & Chandan, V. (2016) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom.2016.7456509 · Cited by 15
“A previous study [5] has shown that the energy saving features of Nest such as Auto-Schedule and Auto-Away failed to make any impact.”
BackgroundVerame, J. K. M., Costanza, E., & Ramchurn, S. D. (2016) · Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems · doi:10.1145/2858036.2858369 · Cited by 15
A Data Analysis Technique to Estimate the Thermal Characteristics of a House
Tabatabaei, S. A., van der Ham, W., Klein, M. C. A., & Jan Treur, A. (2017) · Energies · doi:10.3390/en10091358 · Cited by 15
Kumar, P., & Chouhan, L. (2020) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.3993 · Cited by 17
Operation Strategy of Smart Thermostats That Self-Learn User Preferences
Li, Y., Yan, Z., Chen, S., Xu, X., & Kang, C. (2019) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2019.2891508 · Cited by 15
“In addition, AI-based thermostats, such as the deep-learningbased Nest [17], can hardly provide a clear relation between user inputs and temperature outputs [18], which may make users confused and unsure about how to further modify the AI-recommended schedules.”
BackgroundThe Normal Natural Troubles of Virtual Reality in Mixed-Reality Performances
Rostami, A., & McMillan, D. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3502139 · Cited by 16
Developing occupant-centric smart home thermostats with energy-saving and comfort-improving goals
Luo, M., Zheng, Q., Zhao, Y., Zhao, F., & Zhou, X. J. (2023) · Energy and Buildings · doi:10.1016/j.enbuild.2023.113579 · Cited by 14
Agrawal, H., Leigh, S.-W., & Maes, P. (2015) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/2750858.2805850 · Cited by 14
“Solutions like the Nest thermostat [7] and other commercial solutions [28] offer capabilities like auto scheduling and occupancy sensing to reduce physical and mental effort of users.”
BackgroundHome Worlds: Situating Domestic Computing in Everyday Life Through a Study of DIY Home Repair
Wolf, C. T., Ringland, K. E., & Hayes, G. R. (2019) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3359263 · Cited by 17
“The learning thermostats examined in number of works [19, 36, 37, 43, 78] and available in popular home improvement stores must deal with the inevitable exceptions in home life (e.”
BackgroundFortClash: Predicting and Mediating Unintended Behavior in Home Automation
Coppers, S., Vanacken, D., & Luyten, K. (2022) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3532204 · Cited by 13
“As discussed in the introduction, this user might not have sufficient information, know-how or willingness to perform the necessary edits, especially in case of rare unintended behavior [14, 24, 45, 53, 74, 75].”
BackgroundLearning from the Veg Box: Designing Unpredictability in Agency Delegation
Verame, J. K. M., Costanza, E., Fischer, J., Crabtree, A., Ramchurn, S. D., Rodden, T., & Jennings, N. R. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3174021 · Cited by 13
“With a few exceptions, which have studied off-the-shelf products such as the Nest Thermostat [47, 48] and the Roomba [17, 43], prior studies around autonomous systems in the home have focused on research prototypes.”
BackgroundInfluentialHabit detection within a long-term interaction with a social robot
Rivoire, C., & Lim, A. (2016) · doi:10.1145/3005338.3005342 · Cited by 13
My smart home: an auto-ethnography of learning to live with smart technologies
Aagaard, L. K., Christensen, T. H., & Gram‐Hanssen, K. (2023) · Personal and Ubiquitous Computing · doi:10.1007/s00779-023-01725-0 · Cited by 18
To Do and Not to Do: Constrained Scenarios for Safe Smart House
Guilly, T. L., Smedegård, J. H., Pedersen, T. G., & Skou, A. (2015) · International Conference on Intelligent Environments (IE) · doi:10.1109/ie.2015.11 · Cited by 12
Exploiting known vulnerabilities of a smart thermostat
Moody, M., & Hunter, A. (2016) · Conference on Privacy, Security and Trust · doi:10.1109/pst.2016.7906936 · Cited by 12
“While the advantages of such appliances are well-known[6], [8], there are also established concerns related to security [3].”
BackgroundSmart Thermostats: An Experimental Facility to Test Their Capabilities and Savings Potential
Bustamante, S., Castro, P., Laso, A., Mañana, M., & Arroyo, A. (2017) · Sustainability · doi:10.3390/su9081462 · Cited by 12
“Also, the general perception from the user’s answers in the surveys and interviews shows the difficulty of knowing the real savings coming from the use of smart thermostats [9,11].”
BackgroundProgressive Disclosure: Designing for Effective TransparencyPreprint
Springer, A., & Whittaker, S. (2018) · arXiv.org · doi:10.48550/arxiv.1811.02164 · Cited by 24
“Providing system explanations may also undermine user perceptions when users lack the attentional capacity to process complex explanations, for example while they are executing a demanding task [12,81].”
BackgroundKim, H., & Lim, Y.-K. (2021) · Designing Interactive Systems Conference · doi:10.1145/3461778.3462141 · Cited by 17
Gong, J., Yang, X., Seyed, T., Davis, J. U., & Yang, X.-D. (2018) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3242587.3242662 · Cited by 13
“…and manipulation have enormous potential in small wearable (e.g., smartwatches) or IoT devices (e.g., Amazon Echo, Nest Thermostat, Cortana Home Assistant), where input to these devices is generally difficult due to smaller form factors and the lack of effective input modalities [19, 31, 50, 56].”
BackgroundBock, Y. D., Auquilla, A. R., Kellens, K., Vandevenne, D., Nowé, A., & Duflou, J. R. (2016) · Ecoproduction · doi:10.1007/978-981-10-0471-1_60 · Cited by 10
How Relevant are Incidental Power Poses for HCI?
Jansen, Y., & Hornbæk, K. (2018) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3173588 · Cited by 10
Hyland, L., Crabtree, A., Fischer, J. E., Colley, J., & Fuentes, C. (2018) · Computer Supported Cooperative Work (CSCW) · doi:10.1007/s10606-018-9314-4 · Cited by 12
“The answer is they don ’ t, which is why they are experienced as problematic in practice, especially in multi-user settings as Yang and Newman (2013) unpack.”
BackgroundSmart Thermostats for Home Automation Systems and Energy Savings from Smart Thermostats
Ayan, O., & Türkay, B. E. (2018) · International Conference on Control, Engineering & Information Technology · doi:10.1109/ceit.2018.8751790 · Cited by 10
Ruyck, O. D., Conradie, P. D., Marez, L. D., & Saldien, J. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-29384-0_33 · Cited by 12
Avdic, M., & Vermeulen, J. (2020) · Australian Conference on Human-Computer Interaction (OzCHI) · doi:10.1145/3441000.3441068 · Cited by 14
“through proxemic dimensions [25], or gaze as in Tama [41]) to ofer incidental intelligibility [73] and reveal action possibilities to recover from these breakdowns.”
BackgroundPolicing the smart home: The internet of things as ‘invisible witnesses’1
Urquhart, L., Miranda, D., & Podoletz, L. (2022) · Information Polity · doi:10.3233/ip-211541 · Cited by 17
“Smart home user studies highlight how the initial novelty of interfaces like smart thermostats become ‘mundane’ once these systems integrate into the users’ life and work (Yang & Newman, 2013).”
BackgroundKittley-Davies, J., Alqaraawi, A., Yang, R., Costanza, E., Rogers, A., & Stein, S. (2019) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300273 · Cited by 12
““noisy backgrounds” and camera focus) and unrealistic user expectations [28] can all negatively impact user experience - making it difficult for users to reason about unexpected outcomes and in general how best to interact.”
Self-citationIn Control or Being Controlled? Investigating the Control of Space Heating in Smart Homes
Larsen, S. P. A. K., Gram‐Hanssen, K., & Madsen, L. V. (2023) · Sustainability · doi:10.3390/su15129489 · Cited by 10
New horizons for the IoT in everyday life
Fischer, J. E., Colley, J., Luger, E. A., Golembewski, M., Costanza, E., Ramchurn, S. D., Viller, S., Oakley, I., & Froehlich, J. E. (2016) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/2968219.2968347 · Cited by 9
“However, user studies of nascent proactive IoT devices show that they lack intelligibility and controllability, which has led to users being frustrated and wasting time and money, which may ultimately lead to abandoning the technology [12].”
BackgroundReal-time work environment optimization using multimodal media and body sensor network
Zhao, N., Seitinger, S., Richer, R., & Paradiso, J. A. (2020) · Smart Health · doi:10.1016/j.smhl.2020.100164 · Cited by 9
“Failure often happens because of poor understanding of technical limitations and reasoning behind system decisions [8].”
BackgroundWHISPER: Wireless Home Identification and Sensing Platform for Energy Reduction
Jacoby, M., Tan, S. Y., Katanbaf, M., Saffari, A., Saha, H., Kapetanovic, Z., Garland, J., Florita, A. R., Henze, G. P., Sarkar, S., et al. (2021) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan10040071 · Cited by 11
“Users also report frustration with the operation of these thermostats and say that they are generally not as good at learning as hoped [62].”
BackgroundEmbedding intelligent eco-aware systems within everyday things to increase people’s energy awareness
Casado–Mansilla, D., López-de-Armentia, J., Ventura, D., Garaizar, P., & López–de–Ipiña, D. (2015) · Soft Computing · doi:10.1007/s00500-015-1751-0 · Cited by 12
“This work emphasises the need to assist or facilitate the real-time decision-making process necessary to reduce energy consumption on everyday activities at work, since it is a promising approach to reduce consumption (Fischer 2008; Yang and Newman 2013)”
BackgroundInfluentialPrototyping a voice-controlled smart home hub wirelessly integrated with a wearable device
Wilde, A., Ojuroye, O., & Torah, R. N. (2015) · International Conference on Sensing Technology · doi:10.1109/icsenst.2015.7438367 · Cited by 9
“For the successful deployment of smart homes, there is a need for unobtrusive, simple, human-computer interfaces that function by responding to environmental cues [3].”
BackgroundZhong, S., Lalanne, D., & Alavi, H. S. (2021) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445524 · Cited by 10
“Specifcally, HCI’s contributions to IEQ have been fourishing in the last decade concerted with the proliferation of domotics as well as the introduction of iconic commercial products such as Nest Thermostat [88].”
BackgroundThe energy saving potential of retrofitting a smart heating system: A residence hall pilot study
Bock, Y. D., Auquilla, A. R., Bracquené, E., Nowé, A., & Duflou, J. R. (2021) · Sustainable Computing Informatics and Systems · doi:10.1016/j.suscom.2021.100585 · Cited by 9
“Such intelligent heating systems have been extensively researched and a number of smart thermostats are commercially available, such as the Nest,1 Heat Genius2 and Anna3 solutions, but their intelligent features are not always well-received [9] These systems typically rely on motion sensors to infer occupancy schedule…”
BackgroundSmart Thermostats in Rental Housing Units: Perspectives from Landlords and Tenants
Koupaei, D. M., & Cetin, K. S. (2021) · Journal of Architectural Engineering · doi:10.1061/(asce)ae.1943-5568.0000516 · Cited by 10
Promote Energy Conservation in Automatic Environment Control
Rau, P. P., Gong, Y., Dai, Y.-B., & Cheng, C. (2015) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/2702613.2732869 · Cited by 9
“[8] pointed out that user could accept being less comfortable when they had clear motivation to save energy.”
BackgroundInfluentialOccupancy Sensing and Prediction for Automated Energy Savings
Kleiminger, W. (2015) · Repository for Publications and Research Data (ETH Zurich) · doi:10.3929/ethz-a-010450096 · Cited by 9
“If the occupants do not feel in control of the system, they are likely to turn it off completely [186].”
BackgroundInfluentialAccounting for User Diversity in the Design for Sustainable Behaviour in Smart Offices
Irizar-Arrieta, A., Casado–Mansilla, D., & Retegi, A. (2018) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.3674991 · Cited by 11
CHASE: checklist to assess user experience in IoT environments
Almeida, R. L. A., Andrade, R. M. C., Darin, T., & Paiva, J. O. V. (2020) · IEEE/ACM International Conference on Software Engineering: New Ideas and Emerging Results (ICSE-NIER) · doi:10.1145/3377816.3381737 · Cited by 12
How We Use Together: Coordinating Individual Preferences for Using Shared Devices at Home
Lee, Y., & Lim, Y.-K. (2024) · Designing Interactive Systems Conference · doi:10.1145/3643834.3661634 · Cited by 9
“…within a household, it has been commonly observed that the values or preferences among members difer across various areas: including indoor temperature preferences [31, 69, 89], lighting adjustments [54, 59], energy conservation [36, 37], and concerns related to safety and privacy [82, 91].”
BackgroundManaging energy tariffs with agents
Alan, A., Ramchurn, S. D., Rodden, T. A., Costanza, E., Fischer, J. E., & Jennings, N. R. (2015) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/2800835.2801626 · Cited by 8
“Examples of the latter include “smart” thermostats that take into account our whereabouts and learn our preferences [7, 15].”
BackgroundReef: Exploring the Design Opportunity of Comfort-Aware Eco-Coaching Thermostats
Huang, C.-C., Liang, S.-Y., Wu, B.-H., & Newman, M. (2017) · Designing Interactive Systems Conference · doi:10.1145/3064663.3064685 · Cited by 13
“Balancing Comfort & Convenience We knew from prior work that leaving users in control is essential, yet in a situation like thermostat scheduling, people appreciate some degree of automation [1,32].”
BackgroundMethodInfluentialSelf-citationIoT End User Programming Models
Reiss, S. P. (2019) · doi:10.1109/serp4iot.2019.00008 · Cited by 8
“Others have noted that it is important in the user interface to deal with unusual situations (i.e. deviations from the routine) [12,31,50].”
BackgroundDesigning the Expressivity of Multiple Smart Things for Intuitive and Unobtrusive Interactions
Chuang, Y. (2020) · Designing Interactive Systems Conference · doi:10.1145/3357236.3395450 · Cited by 8
“On the other hand, when something unexpected happens, users often feel frustrated because they do not know why the problem occurred [29, 44].”
BackgroundUser Perceptions of Privacy in Smart Homes.Preprint
Zheng, S., Chetty, M., & Feamster, N. (2018) · arXiv (Cornell University) · Cited by 10
Katzburg, O., Roimi, M., Frenkel, A., Ilan, R., & Bitan, Y. (2024) · JMIR Human Factors · doi:10.2196/56924 · Cited by 12
Sun, L., Li, Z., Zhou, Z., Lou, S., Li, W., & Zhang, Y. (2023) · Artificial intelligence for engineering design analysis and manufacturing · doi:10.1017/s0890060422000270 · Cited by 10
“…could have the autonomy to make decisions independently or assist humans in Challenges: avoid users ’ unrealistic expectations of products ’ capability; better understand the intentions of stakeholders (Yang and Newman, 2013); manage the uncertainty of automatic ability and improve reliability.”
BackgroundBarathi, A. S., Manapragada, N. V. S. K., Kumar, P., Shukla, S., & Shukla, A. K. (2024) · Advances in geographical and environmental sciences · doi:10.1007/978-981-97-1685-2_4 · Cited by 7
Rule and theme discovery in human interactions with an 'internet of things'
Cervantes-Solis, J. W., Baber, C., Khattab, A., & Mitch, R. (2015) · British HCI Conference · doi:10.1145/2783446.2783565 · Cited by 8
“The impact and problems with interacting of such a system have been analysed [20] to show the user’s expectations don’t necessarily adhere to the designed functionality of the system.”
BackgroundEUD4SH: A EUD Model for the Smart Home
Caivano, D., Cassano, F., Fogli, D., & Piccinno, A. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-01746-0_10 · Cited by 7
Agrawal, H., Leigh, S.-W., & Maes, P. (2015) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/2800835.2800848 · Cited by 7
“thermostat [7] and other commercial solutions [28] offer capabilities like auto scheduling and occupancy sensing to”
BackgroundrIoT: Enabling Seamless Context-Aware Automation in the Internet of Things
Hua, J., Liu, C., Kalbarczyk, T., Wright, C., Roman, G.-C., & Julien, C. (2019) · IEEE International Conference on Mobile Ad-Hoc and Sensor Systems (MASS) · doi:10.1109/mass.2019.00035 · Cited by 8
“Although some manufacturers allow users to define personalized automation based on primitive context information like time, they cannot leverage sensor data provided by other manufacturers [6], and as a result, they fail to fully respond to a user’s more subtle intentions due to lack of context [41].”
BackgroundThe potential of physical motion cues: changing people's perception of robots' performance
Garcia, P. G., Costanza, E., Ramchurn, S. D., & Verame, J. K. M. (2016) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/2971648.2971697 · Cited by 7
“Recently, researchers have investigated the usefulness of existing IoT products, such as the Nest thermostat [25] and vacuum cleaning robots (e.”
BackgroundExplaining smart heating systems to discourage fiddling with optimized behavior
Stumpf, S., Skrebe, S., Aymer, G., & Hobson, J. (2018) · Enlighten: Publications (University of Glasgow) · Cited by 13
An investigation of transfer learning for deep architectures in group activity recognition
Casserfelt, K., & Mihailescu, R. (2019) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomw.2019.8730589 · Cited by 6
“This can range from controlling things like heating, lighting, or ventilation in order to increase user satisfaction ( [8], [21]), to more complex scenarios, where a dynamic set of devices, with their functionalities and services, cooperate temporarily to achieve a user goal ( [2], [10]).”
BackgroundViaene, E., Kuijer, L., & Funk, M. (2021) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2021.707562 · Cited by 6
“As mentioned above, the communication and shared autonomy between the learning system and the inhabitant expose the majority of issues that the integration of learning systems in everyday life raises (Yang and Newman, 2013).”
BackgroundInfluentialUser Involvement in Training Smart Home Agents: Increasing Perceived Control and Understanding
Sieger, L. N., Hermann, J., Schomäcker, A., Heindorf, S., Meske, C., Hey, C.-C., & Doğangün, A. (2022) · International Conference on Human-Agent Interaction (HAI) · doi:10.1145/3527188.3561914 · Cited by 8
“Finally, one can question the assumption that users would be too unmotivated to invest work into a smart home system with supervised learning [57].”
BackgroundRau, P. P., Gong, Y., Huang, H.-J., & Wen, J. (2016) · Buildings · doi:10.3390/buildings6020019 · Cited by 7
“It should distinguish which adjustment is a regular input and what is an exceptional case [3,19].”
BackgroundImplicit Interaction Through Machine Learning: Challenges in Design, Accountability, and Privacy
McMillan, D. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-70284-1_27 · Cited by 6
“Systems based on machine learning may be unable to show understanding of users ’ intent, leading them to be perceived as useless and unintuitive [22], and in studies of self-driving vehicles human behaviour has been shown to be responsive to real and perceived levels of control [4].”
BackgroundOn the Temporality of Adaptive Built Environments
Alavi, H. S., Verma, H., Mlynář, J., & Lalanne, D. (2019) · Springer series in adaptive environments · doi:10.1007/978-3-319-70875-1_2 · Cited by 7
Merabet, G. H., Essaaidi, M., Haddou, M. B., Qolomany, B., Qadir, J., Anan, M., Al‐Fuqaha, A., Abid, M. R., & Benhaddou, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.02214 · Cited by 6
“In this context, research works have been oriented at more advanced building control systems based on Artificial Intelligence (AI), taking into account several aspects such as the user preference over time [7].”
BackgroundDesigning the Expressive Point Lights to Enhance User's Situated Awareness of Smart Systems
Liu, Y., Lee, Y.-H., Chuang, Y., Liang, R., & Chen, L.-L. (2017) · ACM Conference Companion Publication on Designing Interactive Systems (DIS Companion) · doi:10.1145/3064857.3079187 · Cited by 6
“However, when something unexpected happens, users usually feel frustrated because they do not know why the error occurred and how to fix it [5, 10].”
BackgroundToward Theory-Based End-User Software Engineering
Burnett, M., Kulesza, T., Oleson, A., Ernst, S., Beckwith, L., Cao, J., Jernigan, W., & Grigoreanu, V. (2017) · Springer eBooks · doi:10.1007/978-3-319-60291-2_10 · Cited by 7
“As Yang and Newman found when studying users of smart home thermostat systems (which learn from their users to predictively adjust the home’s temperature) [Yang and Newman 2013], a system that appears to disregard user feedback deters users from continuing to provide feedback.”
BackgroundSmart Services und ihr Einfluss auf die Wertschöpfung und Geschäftsmodelle von Unternehmen
Paukstadt, U., Strobel, G., Eicker, S., & Becker, J. (2020) · Springer eBooks · doi:10.1007/978-3-658-17291-6_83 · Cited by 9
PEREIRA, D. S. E., Castro, R. M. G., & Adão, P. (2021) · Intelligent Buildings International · doi:10.1080/17508975.2021.1985418 · Cited by 4
“…Mathews Correlation Coefficient (MCC) were used as main criteria, since they complement each other and were used in similar works (Lu et al. 2010; Yang and Newman 2013). accuracy is defined as a balanced performance metric for classification problems, that can be computed by dividing the number…”
BackgroundMethodYue, S. (2024) · Innovations in Systems and Software Engineering · doi:10.1007/s11334-024-00591-0 · Cited by 12
“It refers to a phenomenon of harnessing data from heterogeneous sources to achieve a better understanding of some target data or make a more precise decision by reasoning those data from mul-timodalities.”
Measuring the effectiveness of zonal heating control for energy saving
Ibrahim, M. F., Mohamed, M., & Far, B. H. (2016) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2016.7844231 · Cited by 5
“thermostat [15, 16] was introduced in late 2011 to the market and media gave it a great attention.”
BackgroundSensemaking in the autonomic smart-home
Despouys, R., Sharrock, R., & Demeure, I. M. (2014) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/2638728.2641553 · Cited by 5
“We can recall a study conducted by Yang et al. about Nest [8]: ” the intelligent features of the Nest were not perceived to be as useful or intuitive as expected”.”
MethodAnticipatory Reasoning for a Proactive Context-Aware Energy Saving System
Wu, C.-L., Chen, W.-C., Tseng, Y.-S., Fu, L., & Lu, C.-H. (2014) · IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) · doi:10.1109/ithings.2014.41 · Cited by 5
k-SpecNET: Localization and classification of indoor superimposed sound for acoustic sensor networks
Wang, W., Seraj, F., & Havinga, P. (2020) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops48775.2020.9156174 · Cited by 5
“Indoor human activity information is important because it can be applied to many real-life human-centric problems from health-care of the inhabitants to energy saving in smart buildings [1], [2].”
Background"I had a solid theory before but it's falling apart": Polarizing Effects of Algorithmic TransparencyPreprint
Springer, A., & Whittaker, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.02163 · Cited by 16
Irwin, G. (2017) · doi:10.1145/3038450.3038454 · Cited by 4
Evaluating Smart Home Services and Items: A Living Lab User Experience Study
Seo, E., & Yang, W. (2023) · Buildings · doi:10.3390/buildings13010263 · Cited by 4
“First, studies do not typically consider the multidimensionality of the concept of the smart home, leading to a one-sided representation of its implications, services, and user segments [4,19–21].”
BackgroundLATEST: a learning-based automated thermal environment control system
von Frankenberg, N., Ruoff, P., Bruegge, B., & Loftness, V. (2020) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/3410530.3414591 · Cited by 4
“Furthermore, none of the formerly mentioned approaches address the explainability of their predictions, although occupants have expressed the desire to understand the basis of control decisions [30].”
BackgroundIntelligent occupancy-driven thermostat by dynamic user profiling
Bock, Y. D., Auquilla, A. R., Kellens, K., Nowé, A., & Duflou, J. R. (2016) · Electronics Goes Green · doi:10.1109/egg.2016.7829813 · Cited by 4
“revealed that its intelligent features, such as auto-away which switches the heating off when the room is vacant, were not well received [5].”
BackgroundSavouring Slow Gifts: Reflection from the Field Study of Hybrid Gifting
Kwon, H. S., Benford, S., & Koleva, B. N. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714048 · Cited by 5
ARena of Privacy: Exploring Augmented Reality in Enhancing Smart Home Privacy Awareness and Control
Zhao, H., Yi, X., Chen, L., Zhang, Z., Ren, W., Shi, X., Liu, B., & Cao, J. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2564276 · Cited by 4
“They have explored different methodologies, such as user studies, prototyping, and iterative design, to understand user needs, evaluate designs, and address usability issues (Purington et al., 2017; Ur et al., 2016; Yang & Newman, 2013).”
Data driven feedback for optimized and efficient usage of decentralized air conditioners
Jain, M. (2016) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomw.2016.7457082 · Cited by 3
“But the poor interface (programmable thermostat) and inaccurate learning (Nest) increased the AC energy consumption in some scenarios [7], [8].”
BackgroundPaternò, F. (2023) · Springer eBooks · doi:10.1007/978-3-319-27648-9_37-1 · Cited by 3
Using simple predictive models to improve control of complex building systems
Evins, R., & David, N. (2017) · ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys) · doi:10.1145/3137133.3137159 · Cited by 3
“features are not appreciated in a domestic setting [11], and that it may have security vulnerabilities [4].”
BackgroundIntegration of Smart Home technologies for district heating control in Pervasive Smart Grids
Mihailescu, R., & Davidsson, P. (2017) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomw.2017.7917616 · Cited by 4
Designing the Expressiveness of Point Lights for Bridging Human-IoT System Communications
Liu, Y., Liang, R., Lee, Y.-H., Chuang, Y., & Chen, L.-L. (2017) · InTech eBooks · doi:10.5772/intechopen.71131 · Cited by 3
“However, when something unexpected happens, users usually feel frustrated because they do not know how the problem occurred [2, 3].”
BackgroundAdvanced Planning of Home Appliances with Consumer’s Preference Learning
Bazenkov, N. I., & Goubko, M. (2018) · Communications in computer and information science · doi:10.1007/978-3-030-00617-4_23 · Cited by 3
New Directions for the IoT: Automate, Share, Build, and Care
Fuentes, C., Porcheron, M., Fischer, J. E., Costanza, E., Verdezoto, N. X., Herskovic, V., Zuckerman, O., & Takayama, L. A. (2019) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3290607.3299000 · Cited by 4
“For example, a study by Yang and Newman reflects on how a commercial “Learning Thermostat” to control heating does not take into account the collaborative practices at home, leading to a lack of understanding of how the system works, and to negative user perceptions [24].”
Metadata
- Authors
- Yang, R., & Newman, M. W.
- Affiliations
- University of Michigan (US)
- Venue
- Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing
- Publisher
- ACM
- Published
- 2013-09-08
- Pages
- 93-102
- OpenAlex
- W2133270667
- Cited by
- 268
- References
- 28
- Citations by year
- 2026: 9 · 2025: 7 · 2024: 12 · 2023: 15 · 2022: 13 · 2021: 15 · 2020: 25 · 2019: 34 · 2018: 33 · 2017: 41 · 2016: 34 · 2015: 21 · 2014: 9
- FWCI
- 16.81
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) (publishedVersion)
- Funders
- University of Michigan
- Topics
- Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
- Physical Sciences › Engineering › Electrical and Electronic Engineering › IoT-based Smart Home Systems
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Keywords
- smart home devices, smart home technology, user experience, eco-feedback, user intent understanding, workarounds
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.