Promoting Energy-Efficient Behavior by Depicting Social Norms in a Recommender Interface

How can recommender interfaces help users to adopt new behaviors? In the behavioral change literature, social norms and other nudges are studied to understand how people can be convinced to take action (e.g., towel re-use is boosted when stating that “75% of hotel guests” do so), but most of these nudges are not personalized. In contrast, recommender systems know what to recommend in a personalized way, but not much human-computer interaction ( HCI ) research has considered how personalized advice should be presented to help users to change their current habits. We examine the value of depicting normative messages (e.g., “75% of users do X”), based on actual user data, in a personalized energy recommender interface called “Saving Aid.” In a study among 207 smart thermostat owners, we compared three different normative explanations (“Global.” “Similar,” and “Experienced” norm rates) to a non-social baseline (“kWh savings”). Although none of the norms increased the total number of chosen measures directly, we show that depicting high peer adoption rates alongside energy-saving measures increased the likelihood that they would be chosen from a list of recommendations. In addition, we show that depicting social norms positively affects a user’s evaluation of a recommender interface.

Comparisons of Sustainability Behaviors Pre- and Early Pandemic Among Botanical Garden Members

The COVID-19 outbreak drastically altered the behaviors of millions of Americans in 2020, including behaviors that contribute to carbon emissions. As many Americans stayed home midyear, environmental groups noted the decrease in driving and transportation-related pollution, theorizing that the pandemic could have a positive impact on the environment by decreasing individuals' carbon emissions. However, it is dubious that individuals will behave in a more eco-friendly manner under the uncertain and stressful conditions of a global pandemic simply because they are more likely to be confined to their homes. We examined sustainability behaviors in 2018 and in the early pandemic in 2020 among a sample of members of a U.S., botanical garden. We surveyed members in May–July 2018, asking whether they had or had not done 11 sustainability behaviors (e.g., used alternative transportation, took shorter showers) in the past month. We resurveyed members about their engagement in those behaviors in April 2020 as well as to recall their engagement in those behaviors pre-pandemic in February 2020. We examined differences in self-reported behaviors among respondents who had taken both the May–July 2018 and April 2020 surveys (matched group n = 227), and then among respondents who had taken either the May–July (n = 1057) or the April 2020 survey (n = 881), but not both. Respondents in the matched group were more likely to report recycling, reducing red meat consumption, eating a plant-based diet, and reducing food waste in April 2020 compared to May–July 2018; they were less likely to compost, check the air in their tires, and use a smart thermostat. However, these differences also emerged when examining recalled behavior in February 2020, suggesting that matched group respondents' self-reports may reflect changes in behavior over time rather than due to the pandemic. The unmatched group was more likely to reduce food waste but less likely to use alternative transportation to commute, check the air in their tires for fuel efficiency, and recycle in April 2020 compared to May–July 2018. Thus, few changes in sustainability behaviors can be attributed to the pandemic, but those that do involve personal travel or home confinement.

Household and Population-Level Behavioural Changes Due to COVID-19 Pandemic: A Smart Thermostat Based Comparative Data Analysis

The World Health Organization declared the coronavirus outbreak as a pandemic on March 11, 2020. To inhibit the spread of COVID-19, governments around the globe, including Canada, have implemented physical distancing and lockdown measures, including a work-from-home policy. Canada in 2020 has developed a 24-Hour Movement Guideline for all ages laying guidance on the ideal amount of physical activity, sedentary behaviour, and sleep (PASS) for an individual in a day. The purpose of this study was to investigate changes on the household and population-level in lifestyle behaviours (PASS) and time spent indoors at the household level, following the implementation of physical distancing protocols and stay-at-home guidelines. For this study, we used 2019 and 2020 data from ecobee, a Canadian smart Wi-Fi thermostat company, through the Donate Your Data (DYD) program. Using motion sensors data, we quantified the amount of sleep by using the absence of movement, and similarly, increased sensor activation to show a longer duration of household occupancy. The key findings of this study were; during the COVID-19 pandemic, overall household-level activity increased significantly compared to pre-pandemic times, there was no significant difference between household-level behaviours between weekdays and weekends during the pandemic, average sleep duration has not changed, but the pattern of sleep behaviour significantly changed, specifically, bedtime and wake up time delayed, indoor time spent has been increased and outdoor time significantly reduced. Our data analysis shows the feasibility of using big data to monitor the impact of the COVID-19 pandemic on the household and population-level behaviours and patterns of change.

Temperature Sensing Optimization for Home Thermostat Retrofit

Most existing residential buildings adopt one single-zone thermostat to control the heating of rooms with different thermal conditions. This solution often provides poor thermal comfort and inefficient use of energy. The current market proposes smart thermostats and thermostatic radiator valves (TRVs) as cheap and relatively easy-to-install retrofit solutions. These systems provide increased freedom of installation, due to the use of wireless communication; however, the uncertainty of the measured air temperature, considering the thermostat placement, could impact the final heating performance. This paper presents a sensing optimization approach for a home thermostat, in order to determine the optimal retrofit configuration to reduce the sensing uncertainty, thus achieving the required comfort level and minimizing the retrofit’s payback period. The methodology was applied to a real case study—a dwelling located in Italy. The measured data and a simulation model were used to create different retrofit scenarios. Among these, the optimal scenario was achieved through thermostat repositioning and a setpoint of 21 °C, without the use of TRVs. Such optimization provided an improvement of control performance due to sensor location, with consequent energy savings of 7% (compared to the baseline). The resulting payback period ranged from two and a half years to less than a year, depending on impact of the embedded smart thermostat algorithms.

WiFi-Enabled User Authentication through Deep Learning in Daily Activities

User authentication is a critical process in both corporate and home environments due to the ever-growing security and privacy concerns. With the advancement of smart cities and home environments, the concept of user authentication is evolved with a broader implication by not only preventing unauthorized users from accessing confidential information but also providing the opportunities for customized services corresponding to a specific user. Traditional approaches of user authentication either require specialized device installation or inconvenient wearable sensor attachment. This article supports the extended concept of user authentication with a device-free approach by leveraging the prevalent WiFi signals made available by IoT devices, such as smart refrigerator, smart TV, and smart thermostat, and so on. The proposed system utilizes the WiFi signals to capture unique human physiological and behavioral characteristics inherited from their daily activities, including both walking and stationary ones. Particularly, we extract representative features from channel state information (CSI) measurements of WiFi signals, and develop a deep-learning-based user authentication scheme to accurately identify each individual user. To mitigate the signal distortion caused by surrounding people’s movements, our deep learning model exploits a CNN-based architecture that constructively combines features from multiple receiving antennas and derives more reliable feature abstractions. Furthermore, a transfer-learning-based mechanism is developed to reduce the training cost for new users and environments. Extensive experiments in various indoor environments are conducted to demonstrate the effectiveness of the proposed authentication system. In particular, our system can achieve over 94% authentication accuracy with 11 subjects through different activities.

From Energy as a Commodity to Energy as a Service—A Morphological Analysis of Smart Energy Services

The Internet of Things penetrates all areas of life and work, giving physical objects the characteristics of digital technologies. Also, in the energy sector, physical products such as photovoltaic systems, battery storage systems, and thermostats are equipped with smart and connectivity components and become smart energy products. Smart energy products enable new types of services that are smart energy services. For example, a smart thermostat can offer an intelligent preheating service based on data collected and analyzed. Against this background, smart energy services offer new business potentials for companies as well as added value for private households. To benefit from this development, companies need an understanding of the characteristics and capabilities of the products and the services building on them. Smart energy services, in particular, appear promising, as services are seen as a bridge to the customer. However, there is little research that supports the design of smart energy services. To close this gap, a morphological analysis of smart energy services along several dimensions is conducted. In highlighting the unique characteristics of smart energy services, the paper provides a more nuanced picture on the nature of smart energy services and their potential in terms of new consumer and business values. Additionally, the phenomenon of consumer-oriented smart energy services will be further conceptualized, and the morphological box can be considered a structured approach for the design of smart energy services.

"Utilization of smart thermostat data at the population level to identify sleep parameters and time spent at home" (Preprint)

BACKGROUND Sleep behaviour and time spent at home are important determinants of human health. Research on sleep patterns has traditionally relied on self-reported data. This methodology suffers from bias and population-level data collection is challenging. Advances in Smart Home technology and the Internet of Things (IoT) have the potential to overcome these challenges to behavioural monitoring. OBJECTIVE The objective of this study is to evaluate the use of smart home thermostat data to evaluate household sleep patterns and the time spent at home, and how these behaviours are influenced by weekday, seasonal and seasonal weekday variations. METHODS The 2018 ecobee "Donate your Data" dataset for 481 North American households was collected for use in this study. Daily sleep cycles were identified based on sensor activation and used to quantify sleep time, wake-up time, sleep duration, and time spent at home. Each household's record was divided into different subsets based on seasonal, weekday, and seasonal weekday scales. RESULTS Overall, our results indicate that sleep parameters (sleep time, wake-up time, and sleep duration) were significantly influenced by the day of the week but were not strongly affected by season. In contrast, time spent at home was dependent on both weekdays and the season. CONCLUSIONS This is the first study to utilize smart home thermostat data to monitor sleep parameters and time spent at home and their dependence on weekdays, seasonal, and seasonal weekday variations at the population level. This type of analysis can influence and report on public health policy at the population level.