Human-building relationships impact everyone in industrialized society. We spend approximately 90% of our lives in the built environment. Buildings have a large impact on the environment; consuming 20% of worldwide energy (40% of U.S. energy) annually. Buildings are complex systems, yet architecture, engineering, and construction (AEC) professionals often perform their work without considering the human factors that affect the operational performance of the building system. The AEC industry currently employs a linear design and delivery approach, lacking verified performance standards and real-time feedback once a certificate of occupancy is issued. We rely on static monthly utility bills that lag and mask occupant behavior. We rely on lawsuits and anecdotal business development trends as our feedback mechanisms for the evaluation of a complex, system-based product. The omission of human factors in the design and delivery of high performance building systems creates risk for the AEC industry. Neglecting an iterative, human-centered design approach inhibits our ability to relinquish the building industry's position as the top energy consuming sector. Therefore, this research aims to explore, identify, and propose optimizations to critical human-building relationships in the multifamily housing system. This work is grounded in Sociotechnical Systems theory (STS). STS provides the most appropriate theoretical construct for this work because 1) human-building interactions (HBI) are fundamentally, human-technology interactions, 2) understanding HBI will improve total system performance, and 3) the interrelationships among human-building subsystems and the potential for interventions to effect the dynamics of the system are not currently well understood. STS was developed in the 1940's as a result of work system design changes with coal mining in the United Kingdom. STS consists of four subsystems and provides a theoretical framework to approach the joint optimization of complex social and technical problems. In the context of this work, multidisciplinary approaches were leveraged from human factors engineering and building construction to explore relationships among the four STS subsystems. An exploratory case study transformed the work from theoretical construct toward an applied STS model. Data are gathered from each STS subsystem using a mixed-methods research design. Methods include Systematic Review (SR), a descriptive case study of zero energy housing, and the Macroergonomics Analysis and Design (MEAD) of three builder-developers. This work contributes to bridging the bodies of knowledge between human factors engineering and the AEC industry. An output of this work is a framework and work system recommendations to produce human-centered, adaptive buildings. This work specifically examined the system inputs and outputs of multifamily housing in the United States. The findings are supportive of existing scientific society, government, and industry standards and goals. Relevant standards and goals include the Human Factors and Ergonomics Society (HFES) Macroergonomics and Environmental Design Technical Groups, International Energy Agency's Energy in Buildings ANNEX 79 Occupant Behavior-Centric Building Design and Operation, the U.S. Department of Energy's Building America Research to Market Plan and zero energy building goals of the American Society of Heating Refrigeration and Air-Conditioning Engineers (ASHRAE). / Doctor of Philosophy / We spend approximately 90% of our lives in the built environment. Buildings have a large impact on the environment; consuming 20% of worldwide energy (40% of U.S. energy) annually. As we work to reduce energy use in buildings, new challenges have emerged. As buildings become more complex, the architecture, engineering, and construction industry (AEC) must adapt. The industry historically employs a linear design and delivery approach, lacking verified performance standards and real-time feedback once a certificate of occupancy is issued. We rely on static monthly utility bills that lag and mask occupant behavior. We rely on lawsuits and anecdotal business development trends as our feedback mechanisms for the evaluation of a complex, system-based product. The omission of human factors in the design and delivery of high-performance building systems creates risk for the industry and occupants. To better understand that risk, a comparative analysis of zero energy housing explores the relationship between humans and the buildings of the future. A second case study explores the work systems of builder-developers by using the Macroergonomic Analysis and Design method. The work reports risks and barriers in the system, as well as opportunities to create human-centered, adaptive housing. Specifically, this project enhances our understanding of 1) high performance housing, 2) their occupants, and 3) the builder-developers that produce high performance housing.

We inhabit space. This means our deepest mental and emotional understanding of the world is tied intimately to our experiences as we perceive them in a physical context. Just like a book or film may induce a sense of presence, so too may our modern sensor drenched infrastructures and mobile information spaces. With the recent development of personal and ubiquitous computing devices that we always carry with us, and increased connectivity and robustness of wireless connections, there is an increasing tie between people and things around them. This also includes the space people inhabit. However, such enhanced experiences are usually limited to a personal environment with a personal smartphone being the central device. We would like to bring such technology enhanced experiences to large public spaces with many occupants where their movement patterns, and interactions can be shared, recorded, and studied in order to improve the occupants' efficiency and satisfaction. Specifically, we use sensor networks and ubiquitous computing to create smart built environments that are seamlessly aware of and responsive to the occupants. Human sensing system is one of the key enabling technologies for smart built environments. We present our research findings related to the design and deployment of an indoor human sensing system in large public built spaces. We use a case study to illustrate the challenges, opportunities, and lessons for the emerging field of human building interaction. We present several fundamental design trade-offs, applications, and performance measures for the case study. / Master of Science / The recent advances in mobile technologies, like smart phones and enhanced wireless communication, allow people to experience added comfort and convenience brought by these devices. For example, smart lighting and air conditioning control can be set remotely, before people arrive at their homes. However, these personal experiences are usually limited to personal spaces and tied to a specific personal smart phone. When it comes to public spaces, we seldom see such technological advancement being utilized. In reality, the concept of smart public spaces is still limited to technologies like opening / closing a door automatically. We discuss the reasons that cause such difference between personal and public spaces. We argue that Human Building Interactions should be shaped around non-intrusive indoor human sensing technologies. We present discussions, considerations and implementation of a system that uses a low cost camera network for indoor human sensing. We also describe several applications based on the developed system. We demonstrate how to bring technology enhanced experiences to public built spaces and provide smart built environments.

<p>Commercial buildings not only have significant impacts on occupants’ well-being, but also contribute to more than 19% of the total energy consumption in the United States. Along with improvements in building equipment efficiency and utilization of renewable energy, there has been significant focus on the development of advanced heating, ventilation, and air conditioning (HVAC) system controllers that incorporate predictions (e.g., occupancy patterns, weather forecasts) and current state information to execute optimization-based strategies. For example, model predictive control (MPC) provides a systematic implementation option using a system model and an optimization algorithm to adjust the control setpoints dynamically. This approach automatically satisfies component and operation constraints related to building dynamics, HVAC equipment, etc. However, the wide adaptation of advanced controls still faces several practical challenges: such approaches involve significant engineering effort and require site-specific solutions for complex problems that need to consider uncertain weather forecast and engaging the building occupants. This thesis explores smart building operation strategies to resolve such issues from the following three aspects. </p> <p>First, the thesis explores a stochastic model predictive control (SMPC) method for the optimal utilization of solar energy in buildings with integrated solar systems. This approach considers the uncertainty in solar irradiance forecast over a prediction horizon, using a new probabilistic time series autoregressive model, calibrated on the sky-cover forecast from a weather service provider. In the optimal control formulation, we model the effect of solar irradiance as non-Gaussian stochastic disturbance affecting the cost and constraints, and the nonconvex cost function is an expectation over the stochastic process. To solve this optimization problem, we introduce a new approximate dynamic programming methodology that represents the optimal cost-to-go functions using Gaussian process, and achieves good solution quality. We use an emulator to evaluate the closed-loop operation of a building-integrated system with a solar-assisted heat pump coupled with radiant floor heating. For the system and climate considered, the SMPC saves up to 44% of the electricity consumption for heating in a winter month, compared to a well-tuned rule-based controller, and it is robust, imposing less uncertainty on thermal comfort violation.</p> <p>Second, this thesis explores user-interactive thermal environment control systems that aim to increase energy efficiency and occupant satisfaction in office buildings. Towards this goal, we present a new modeling approach of occupant interactions with a temperature control and energy use interface based on utility theory that reveals causal effects in the human decision-making process. The model is a utility function that quantifies occupants’ preference over temperature setpoints incorporating their comfort and energy use considerations. We demonstrate our approach by implementing the user-interactive system in actual office spaces with an energy efficient model predictive HVAC controller. The results show that with the developed interactive system occupants achieved the same level of overall satisfaction with selected setpoints that are closer to temperatures determined by the MPC strategy to reduce energy use. Also, occupants often accept the default MPC setpoints when a significant improvement in the thermal environment conditions is not needed to satisfy their preference. Our results show that the occupants’ overrides can contribute up to 55% of the HVAC energy consumption on average with MPC. The prototype user-interactive system recovered 36% of this additional energy consumption while achieving the same overall occupant satisfaction level. Based on these findings, we propose that the utility model can become a generalized approach to evaluate the design of similar user-interactive systems for different office layouts and building operation scenarios. </p> <p>Finally, this thesis presents an approach based on meta-reinforcement learning (Meta-RL) that enables autonomous optimal building controls with minimum engineering effort. In reinforcement learning (RL), the controller acts as an agent that executes control actions in response to the real-time building system status and exogenous disturbances according to a policy. The agent has the ability to update the policy towards improving the energy efficiency and occupant satisfaction based on the previously achieved control performance. In order to ensure satisfactory performance upon deployment to a target building, the agent is trained using the Meta-RL algorithm beforehand with a model universe obtained from available building information, which is a probability measure over the possible building dynamical models. Starting from what is learned in the training process, the agent then fine-tunes the policy to adapt to the target building based on-site observations. The control performance and adaptability of the Meta-RL agent is evaluated using an emulator of a private office space over 3 summer months. For the system and climate under consideration, the Meta-RL agent can successfully maintain the indoor air temperature within the first week, and result in only 16% higher energy consumption in the 3^rd month than MPC, which serves as the theoretical upper performance bound. It also significantly outperforms the agents trained with conventional RL approach. </p>

Indoor Localization Systems (ILS), also known as Indoor Positioning Systems (IPS), has been created to determine the position of individuals and other assets inside facilities. Indoor Localization Systems have been implemented for monitoring individuals and objects in a variety of sectors. In addition, ILS could be used for energy and sustainability purposes. Energy management is a complex and important challenge in the Built Environment. The indoor localization market is expected to increase by 33.8 billion in the next 5 years based on the 2016 global survey report (Marketsandmarkets.com). Therefore, this thesis focused on exploring and investigating "depth sensors" application in detecting occupants' indoor positions to be used for smarter management of energy consumption in buildings. An interconnected passive depth-sensor-based system of occupants' positioning was investigated for human-building interaction applications. This research investigates the fundamental requirements for depth-sensing technology to detect, identify and track subjects as they move across different spaces. This depth-based approach is capable of sensing and identifying individuals by accounting for the privacy concerns of users in an indoor environment. The proposed system relies on a fixed depth sensor that detects the skeleton, measures the depth, and further extracts multiple features from the characteristics of the human body to identify them through a classifier. An example application of such a system is to capture an individuals' thermal preferences in an environment and deliver services (targeted air conditioning) accordingly while they move in the building. The outcome of this study will enable the application of cost-effective depth sensors for identification and tracking purposes in indoor environments. This research will contribute to the feasibility of accurate detection of individuals and smarter energy management using depth sensing technologies by proposing new features and creating combinations with typical biometric features. The addition of features such as the area and volume of human body surface was shown to increase the accuracy of the identification of individuals. Depth-sensing imaging could be combined with different ILS approaches and provide reliable information for service delivery in building spaces. The proposed sensing technology could enable the inference of people location and thermal preferences across different indoor spaces, as well as, sustainable operations by detecting unoccupied rooms in buildings. / Master of Science / Although Global Positioning System (GPS) has a satisfactory performance navigating outdoors, it fails in indoor environments due to the line of sight requirements. Physical obstacles such as walls, overhead floors, and roofs weaken GPS functionality in closed environments. This limitation has opened a new direction of studies, technologies, and research efforts to create indoor location sensing capabilities. In this study, we have explored the feasibility of using an indoor positioning system that seeks to detect occupants’ location and preferences accurately without raising privacy concerns. Context-aware systems were created to learn dynamics of interactions between human and buildings, examples are sensing, localizing, and distinguishing individuals. An example application is to enable a responsive air-conditioning system to adapt to personalized thermal preferences of occupants in an indoor environment as they move across spaces. To this end, we have proposed to leverage depth sensing technology, such as Microsoft Kinect sensor, that could provide information on human activities and unique skeletal attributes for identification. The proposed sensing technology could enable the inference of people location and preferences at any time and their activity levels across different indoor spaces. This system could be used for sustainable operations in buildings by detecting unoccupied rooms in buildings to save energy and reduce the cost of heating, lighting or air conditioning equipment by delivering air conditioning according to the preferences of occupants. This thesis has explored the feasibility and challenges of using depth-sensing technology for the aforementioned objectives. In doing so, we have conducted experimental studies, as well as data analyses, using different scenarios for human-environment interactions. The results have shown that we could achieve an acceptable level of accuracy in detecting individuals across different spaces for different actions.

With the ever-growing concerns of environmental and climate concerns for energy consumption in our society, it is crucial to develop novel solutions that improve the efficient utilization of distributed energy resources for energy efficiency and demand response (DR). As such, there is a need to develop targeted energy programs, which not only meet the requirement of energy goals for a community but also take the energy use patterns of individual households into account. To this end, a sound understanding of the energy behavior of customers at the neighborhood level is needed, which requires operational analytics on the wealth of energy data from customers and devices. In this dissertation, we focus on data-driven solutions for customer energy behavior characterization with applications to distributed energy management and flexibility provision. To do so, the following problems were studied: (1) how different customers can be segmented for DR events based on their energy-saving potential and balancing peak and off-peak demand, (2) what are the opportunities for extracting Time-of-Use of specific loads for automated DR applications from the whole-house energy data without in-situ training, and (3) how flexibility in customer demand adoption of renewable and distributed resources (e.g., solar panels, battery, and smart loads) can improve the demand-supply problem. In the first study, a segmentation methodology form historical energy data of households is proposed to estimate the energy-saving potential for DR programs at a community level. The proposed approach characterizes certain attributes in time-series data such as frequency, consistency, and peak time usage. The empirical evaluation of real energy data of 400 households shows the successful ranking of different subsets of consumers according to their peak energy reduction potential for the DR event. Specifically, it was shown that the proposed approach could successfully identify the 20-30% of customers who could achieve 50-70% total possible demand reduction for DR. Furthermore, the rebound effect problem (creating undesired peak demand after a DR event) was studied, and it was shown that the proposed approach has the potential of identifying a subset of consumers (~5%-40% with specific loads like AC and electric vehicle) who contribute to balance the peak and off-peak demand. A projection on Austin, TX showed 16MWh reduction during a 2-h event can be achieved by a justified selection of 20% of residential customers. In the second study, the feasibility of inferring time-of-use (ToU) operation of flexible loads for DR applications was investigated. Unlike several efforts that required considerable model parameter selection or training, we sought to infer ToU from machine learning models without in-situ training. As the first part of this study, the ToU inference from low-resolution 15-minute data (smart meter data) was investigated. A framework was introduced which leveraged the smart meter data from a set of neighbor buildings (equipped with plug meters) with similar energy use behavior for training. Through identifying similar buildings in energy use behavior, the machine learning classification models (including neural network, SVM, and random forest) were employed for inference of appliance ToU in buildings by accounting for resident behavior reflected in their energy load shapes from smart meter data. Investigation on electric vehicle (EV) and dryer for 10 buildings over 20 days showed an average F-score of 83% and 71%. As the second part of this study, the ToU inference from high-resolution data (60Hz) was investigated. A self-configuring framework, based on the concept of spectral clustering, was introduced that automatically extracts the appliance signature from historical data in the environment to avoid the problem of model parameter selection. Using the framework, appliance signatures are matched with new events in the electricity signal to identify the ToU of major loads. The results on ~1500 events showed an F-score of >80% for major loads like AC, washing machine, and dishwasher. In the third study, the problem of demand-supply balance, in the presence of varying levels of small-scale distributed resources (solar panel, battery, and smart load) was investigated. The concept of load complementarity between consumers and prosumers for load balancing among a community of ~250 households was investigated. The impact of different scenarios such as varying levels of solar penetration, battery integration level, in addition to users' flexibility for balancing the supply and demand were quantitatively measured. It was shown that (1) even with 100% adoption of solar panels, the renewable supply cannot cover the demand of the network during afternoon times (e.g., after 3 pm), (2) integrating battery for individual households could improve the self-sufficiency by more than 15% during solar generation time, and (3) without any battery, smart loads are also capable of improving the self-sufficiency as an alternative, by providing ~60% of what commercial battery systems would offer. The contribution of this dissertation is through introducing data-driven solutions/investigations for characterizing the energy behavior of households, which could increase the flexibility of the aggregate daily energy load profiles for a community. When combined, the findings of this research can serve to the field of utility-scale energy analytics for the integration of DR and improved reshaping of network energy profiles (i.e., mitigating the peaks and valleys in daily demand profiles). / Doctor of Philosophy / Buildings account for more than 70% of electricity consumption in the U.S., in which more than 40% is associated with the residential sector. During recent years, with the advancement in Information and Communication Technologies (ICT) and the proliferation of data from consumers and devices, data-driven methods have received increasing attention for improving the energy-efficiency initiatives. With the increased adoption of renewable and distributed resources in buildings (e.g., solar panels and storage systems), an important aspect to improve the efficiency by matching the demand and supply is to add flexibility to the energy consumption patterns (e.g., trying to match the times of high energy demand from buildings and renewable generation). In this dissertation, we introduced data-driven solutions using the historical energy data of consumers with application to the flexibility provision. Specific problems include: (1) introducing a ranking score for buildings in a community to detect the candidates that can provide higher energy saving in the future events, (2) estimating the operation time of major energy-intensive appliances by analyzing the whole-house energy data using machine learning models, and (3) investigating the potential of achieving demand-supply balance in communities of buildings under the impact of different levels of solar panels, battery systems, and occupants energy consumption behavior. In the first study, a ranking score was introduced that analyzes the historical energy data from major loads such as washing machines and dishwashers in individual buildings and group the buildings based on their potential for energy saving at different times of the day. The proposed approach was investigated for real data of 400 buildings. The results for EV, washing machine, dishwasher, dryer, and AC show that the approach could successfully rank buildings by their demand reduction potential at critical times of the day. In the second study, machine learning (ML) frameworks were introduced to identify the times of the day that major energy-intensive appliances are operated. To do so, the input of the model was considered as the main circuit electricity information of the whole building either in lower-resolution data (smart meter data) or higher-resolution data (60Hz). Unlike previous studies that required considerable efforts for training the model (e.g, defining specific parameters for mathematical formulation of the appliance model), the aim was to develop data-driven approaches to learn the model either from the same building itself or from the neighbors that have appliance-level metering devices. For the lower-resolution data, the objective was that, if a few samples of buildings have already access to plug meters (i.e., appliance level data), one could estimate the operation time of major appliances through ML models by matching the energy behavior of the buildings, reflected in their smart meter information, with the ones in the neighborhood that have similar behaviors. For the higher-resolution data, an algorithm was introduced that extract the appliance signature (i.e., change in the pattern of electricity signal when an appliance is operated) to create a processed library and match the new events (i.e., times that an appliance is operated) by investigating the similarity with the ones in the processed library. The investigation on major appliances like AC, EV, dryer, and washing machine shows the >80% accuracy on standard performance metrics. In the third study, the impact of adding small-scale distributed resources to individual buildings (solar panels, battery, and users' practice in changing their energy consumption behavior) for matching the demand-supply for the communities was investigated. A community of ~250 buildings was considered to account for realistic uncertain energy behavior across households. It was shown that even when all buildings have a solar panel, during the afternoon times (after 4 pm) in which still ~30% of solar generation is possible, the community could not supply their demand. Furthermore, it was observed that including users' practice in changing their energy consumption behavior and battery could improve the utilization of solar energy around >10%-15%. The results can serve as a guideline for utilities and decision-makers to understand the impact of such different scenarios on improving the utilization of solar adoption. These series of studies in this dissertation contribute to the body of literature by introducing data-driven solutions/investigations for characterizing the energy behavior of households, which could increase the flexibility in energy consumption patterns.

Virtual Reality has been growing in popularity and demand as technology has been substantially improved and become more readily available to the general public in the recent years. Similarly, the Architecture, Engineering and Construction industries have benefited from these advances and extensive research has been performed to adopt and streamline its utilization. An example of this adoption has been the use of Immersive Virtual Environments (IVE) as a representation of the built environment for different purposes such as building design and occupant behavior studies in the post construction stage – i.e., Human Building Interaction. This research has investigated a workflow for different alternatives of reality-capturing-based technologies that have been tested to generate a more realistic representation of the built environment regarding HBI. One of these alternatives considered was 360-image based IVEs. This alternative in particular was tested and compared by the means of a preliminary user study in order to evaluate whether it is an adequate representation of the built environment regarding HBI, and how it is compared to commonly used benchmarked Graphical based IVEs. Ultimately, participants of this user study reported a strong feeling of immersion and presence in the 360-image based IVE and showed a better performance in cognitive tasks such as reading speed and comprehension. In contrast, participants showed a better performance in object identification and finding in the Graphical based IVE. The results of our preliminary user study indicate that 360-image based IVEs could potentially be an adequate representation in the study of Human Building Interaction based on these metrics. Further research with a larger sample size should be done in performed in order to generalize any findings. / Master of Science / Virtual Reality has been growing in popularity and demand as technology has substantially improved and become more available to the general public in the recent years. Similarly, the Architecture, Engineering and Construction industries have benefited from these advances and extensive research has been performed to utilize this technology. An example of this adoption has been the use of Immersive Virtual Environments (IVE) as a representation of a building for different purposes such as design and understanding of the way occupants interact with a building. IVEs rely on using special digital goggles (called head mounted displays or HMDs) that help users immerse in a virtual environment and experience it. For this reason, our research has sought to explore different alternatives to possibly generate a more realistic immersive virtual environment that relies on immersive image-based technologies to test how humans behave, respond, and interact with a building. One of these alternatives considered was 360-degree cameras and their associated images. We sought to study whether these technologies provide an improved experience for users compared to the environments that are created through computer graphics. This thesis explains the processes that were investigated to understand the creation of an IVE, and the different alternatives available in the market to generate a 360-degree image based IVE. Then, one of these alternatives was tested and compared to a classic IVE through an experiment in order to evaluate whether 360-degree image based IVEs can be an adequate representation for building occupant interaction studies.

The IoT-embedded smart homes have a high level of home automation and could change many aspects of the residents' daily lives, such as control, convenience, comfort, and energy-saving. The rise of voice-based virtual assistants like Amazon's Alexa, Google assistants in the past five years has brought new potentials to provide occupants with a convenient and intuitive interface to interact with smart homes through conversations. However, the one-way communications in the form of user commands to control building systems does not result in the optimal course of actions. As such, in this thesis, we proposed the concept of proactive smart home assistants and explored the occupants' perception towards smart home assistants proactively providing suggestions to adapt them into energy-saving behaviors. We also investigated the impact of occupants' personal features on their intention in taking energy-saving behaviors. A comprehensive data collection was conducted through online surveys, in which 307 valid responses with participant's personal profile information, their perceptions of smart home assistants, and their feedback to our designed messages were collected. The first manuscript compared participants' responses to traditional plain-text energy-saving suggestions and suggestions provided by smart home assistants. The nudging effect of smart home assistants was justified to be significant in affecting occupant's energy-saving behaviors. Occupant's thermal comfort range, smart home device previous experience, values and beliefs were then proved to have significant impact on their intention in taking the smart home assistant's suggestions. The second manuscript fitted 21 personal characteristics features in machine learning models (SVM, Random Forest, Logistic Regression) to predict occupant's intention and attitude towards energy-saving suggestions. The results indicated that occupant's beliefs about interests in taking actions and beliefs about energy expenses, occupant's education level, residence occupancy type, thermal comfort ranges, and smart home device experiences are important features in occupants' energy-saving behavior intention prediction. This research demonstrates the effect of proactive smart home assistants in human-building interaction as well as the impact of personal characteristic features on occupant's energy-saving behaviors, paving a path to the future development of bi-directional human-building communication. / Master of Science / With the technology development in the fields of the Internet of Things (IoT), smart homes have made it possible to help occupants conserve energy in an efficient way without sacrificing the occupants' comfort. The rise of voice-based virtual assistants like Amazon's Alexa, Google assistants accompany the proliferation of smart speaker products in the past five years has brought new potentials to provide occupants with a convenient and intuitive interface to interact with smart homes through conversations. Based on IoT, the virtual assistants are able to control a broad range of Wi-Fi connected home devices like thermostats, lighting systems, and security systems. As such, through the simple wake words (e.g., "Alexa", "Hey, Google"), occupants can easily control the home environment with their voice commands. Despite the potentials brought by these voice-based virtual assistants, it has been shown that users might not know about all the supported features and limit their interaction with smart home assistants to simple daily tasks. The one-way communications in the form of user commands to control building systems do not result in the optimal course of actions. Therefore, in this study, we have envisioned that these virtual assistants, coupled with their corresponding smart home ecosystems could act proactively as a bridge to facilitate human-building interaction and achieve goals like nudging occupants to adopt sustainable and healthy behaviors. A comprehensive data collection was conducted through online surveys, in which 307 valid responses with participant's personal profile information, their perceptions of smart home assistants, and their feedback to our designed messages were collected. The first manuscript compared participants' responses to traditional plain-text energy-saving suggestions and suggestions provided by smart home assistants. The nudging effect of smart home assistants was justified to be significant in affecting occupant's energy-saving behaviors. Occupant's thermal comfort range, smart home device previous experience, values and beliefs were then proved to have significant impact on their intention in taking the smart home assistant's suggestions. The second manuscript fitted 21 personal characteristics features in machine learning models (SVM, Random Forest, Logistic Regression) to predict occupant's intention and attitude towards energy-saving suggestions. The results indicated that occupant's beliefs about interests in taking actions and beliefs about energy expenses, occupant's education level, residence occupancy type, thermal comfort ranges, and smart home device experiences are important features in occupants' energy-saving behavior intention prediction. This research demonstrates the effect of proactive smart home assistants in human-building interaction as well as the impact of personal characteristic features on occupant's energy-saving behaviors, paving a path to the future development of bi-directional human-building communication.