We analyzed one year’s device usage log data collected from Smart TVs launched in the US to uncover and understand user-preferred picture quality previously unknown. Through K-means cluster analysis, we first clustered similar users into groups based on their historical picture setting activities on TVs. We then performed K-prototypes clustering upon data instances from a specific group of users, who were reasonably active in customizing picture quality, to discover new picture setting configurations distinguished from the factory default. Lastly, we conducted mixed effects modeling on the collected datasets to determine contextual factors impacting the user preferences towards the discovered picture settings. The analysis yielded several implications for the consumer electronics industry in providing users with the picture quality best suited for their current situation and personal characteristics.

We discover user-preferred picture settings on smart TVs and investigate whether it is possible to predict the users’ picture setting preferences through machine learning methods. We first perform K-means clustering on large-scale smart TV usage log data to understand how users fine-tune the factory default picture settings. Clustering results recognize 3–4 user groups who have reasonably different preferences toward the default settings. By characterizing these user preferences, we come up with new user-preferred picture settings. We perform an in-depth analysis of the newly discovered picture settings regarding diverse TV device characteristics. We also perform lab experiments to demonstrate how these new settings deliver different picture quality than the default. Next, we construct a deep learning-based classifier that learns and predicts the picture setting preferences of the users. The final trained model shows 86% accuracy in predicting users’ decisions to choose a specific picture setting out of four available options.

Researchers are building Internet of Things (IoT) systems that aim to raise users’ privacy awareness, so that these users can make informed privacy decisions. However, there is a lack of empirical research on the practical implications of informed privacy decision-making in IoT. To gain deeper insights into this question, we conducted an online study ( N = 488) of people’s privacy decision-making as well as their levels of privacy awareness toward diverse IoT service scenarios. Statistical analysis on the collected data confirmed that people who are well aware of potential privacy risks in a scenario tend to make more conservative and confident privacy decisions. Machine learning (ML) experiments also revealed that individuals overall privacy awareness is the most important feature when predicting their privacy decisions. We verified that ML models trained on privacy decisions made with confidence can produce highly accurate privacy recommendations for users (area under the ROC curve (AUC) of 87%). Based on these findings, we propose functional requirements for privacy-aware systems to facilitate well-informed privacy decision-making in IoT, which results in conservative and confident decisions that enjoy high consistency.

With the advent of the Internet of Things (IoT), users are more likely to have privacy concerns since their personal information could be collected, analyzed, and utilized without notice by the networked IoT devices and services. Users may want to control all such activities by explicitly expressing their privacy preferences. However, it is becoming increasingly difficult for users to do so, not only because of the cognitive burden of continuously making privacy decisions for IoT services, but also because IoT devices have no, or only very restricted, user interfaces. Intelligent software helping users make better privacy decisions will be an important component of privacy-preserving IoT environments. In order to construct such a component, we aim to verify whether it will be possible to computationally model and predict users' privacy preferences in IoT. To that end, we survey 172 participants in a simulated campuswide IoT environment about their privacy preferences regarding hypothetical personal information tracking scenarios. Then, we cluster the scenarios based on the survey responses, arriving at four clusters with distinct associated privacy preferences. Based on the clustering results, we uncover contextual factors that induce privacy violations in IoT. Finally, we build machine learning models to predict users' privacy decisions, using both contextual information and the corresponding cluster membership as training data. The final trained model shows 77% accuracy in predicting users' decisions whether or not to allow the respective IoT scenario.

With the widespread use of smartphones, users tend to use their smartphone for a long period of time in unhealthy postures; bending forward the neck and watching the relatively small screen closely with concentration. If users keep such unhealthy postures for a long time, they are susceptible to musculoskeletal disorders and eye problems such as cervical disc and myopia, respectively. To prevent users from having these diseases, we propose a new methodology to monitor the posture of smartphone users with built-in sensors. The proposed mechanism estimates various values representing user postures like the tilt angle of the neck, viewing distance, and gaze condition of the user, by analyzing sensor data from a front-faced camera, 3-axis accelerometer, orientation sensor, or any combination thereof, and warns the user if estimated values are maintained within the abnormal range over the pre-defined time. As a proof of concept, we developed an Android application named Smart Pose which estimates the user's neck tilt angle from analysis of the facial image, shakiness and tilt angle of the smartphone, and then notifies the user when her/his neck tilt angle is maintained in an unusual range during the smartphone operation. Also, we validated the result of our system by the comparison with measurements from 3D posture imaging equipment in our research facility. Via the proposed mechanism, a participant was able to be aware of his unhealthy postures, and then try to correct them.

With the widespread use of smartphones, users tend to use their smartphone for a long period of time in unhealthy postures; bending forward the neck and watching the relatively small screen closely with concentration. If users keep such unhealthy postures for a long time, they are susceptible to musculoskeletal disorders and eye problems such as cervical disc and myopia, respectively. To prevent users from having these diseases, we propose a new methodology to monitor the posture of smartphone users with built-in sensors. The proposed mechanism estimates various values representing user postures like the tilt angle of the neck, viewing distance, and gaze condition of the user, by analyzing sensor data from a front-faced camera, 3-axis accelerometer, orientation sensor, or any combination thereof, and warns the user if estimated values are maintained within the abnormal range over the pre-defined time. As a proof of concept, we developed an Android application named Smart Pose which estimates the user's neck tilt angle from analysis of the facial image, shakiness and tilt angle of the smartphone, and then notifies the user when her/his neck tilt angle is maintained in an unusual range during the smartphone operation. Also, we validated the result of our system by the comparison with measurements from 3D posture imaging equipment in our research facility. Via the proposed mechanism, a participant was able to be aware of his unhealthy postures, and then try to correct them.

With the widespread use of smartphones, users tend to use their smartphone for a long period of time in unhealthy postures; bending forward the neck and watching the relatively small screen closely with concentration. If users keep such unhealthy postures for a long time, they are susceptible to musculoskeletal disorders and eye problems such as cervical disc and myopia, respectively. To prevent users from having these diseases, we propose a new methodology to monitor the posture of smartphone users with built-in sensors. The proposed mechanism estimates various values representing user postures like the tilt angle of the neck, viewing distance, and gaze condition of the user, by analyzing sensor data from a front-faced camera, 3-axis accelerometer, orientation sensor, or any combination thereof, and warns the user if estimated values are maintained within the abnormal range over the pre-defined time. As a proof of concept, we developed an Android application named Smart Pose which estimates the user's neck tilt angle from analysis of the facial image, shakiness and tilt angle of the smartphone, and then notifies the user when her/his neck tilt angle is maintained in an unusual range during the smartphone operation. Also, we validated the result of our system by the comparison with measurements from 3D posture imaging equipment in our research facility. Via the proposed mechanism, a participant was able to be aware of his unhealthy postures, and then try to correct them.

Awareness of the emotion of those who communicate with others is a fundamental challenge in building affective intelligent systems. Emotion is a complex state of the mind influenced by external events, physiological changes, or relationships with others. Because emotions can represent a user's internal context or intention, researchers suggested various methods to measure the user's emotions from analysis of physiological signals, facial expressions, or voice. However, existing methods have practical limitations to be used with consumer devices, such as smartphones; they may cause inconvenience to users and require special equipment such as a skin conductance sensor. Our approach is to recognize emotions of the user by inconspicuously collecting and analyzing user-generated data from different types of sensors on the smartphone. To achieve this, we adopted a machine learning approach to gather, analyze and classify device usage patterns, and developed a social network service client for Android smartphones which unobtrusively find various behavioral patterns and the current context of users. Also, we conducted a pilot study to gather real-world data which imply various behaviors and situations of a participant in her/his everyday life. From these data, we extracted 10 features and applied them to build a Bayesian Network classifier for emotion recognition. Experimental results show that our system can classify user emotions into 7 classes such as happiness, surprise, anger, disgust, sadness, fear, and neutral with a surprisingly high accuracy. The proposed system applied to a smartphone demonstrated the feasibility of an unobtrusive emotion recognition approach and a user scenario for emotion-oriented social communication between users.

With the widespread use of a smartphone, users tend to use their smartphone for a long period of time in unhealthy postures; bending forward the neck and watching the relatively small screen closely with concentration. If users keep such unhealthy postures for a long time, they are susceptible to musculoskeletal disorders and eye problems such as cervical disc and myopia, respectively. To prevent users from having these diseases, we propose a new methodology to monitor the posture of smartphone users with built-in sensors. The proposed mechanism estimates various values representing user postures like the tilt angle of the neck, viewing distance, and gaze condition of the user, by analyzing sensor data from a front-faced camera, 3-axis accelerometer, orientation sensor, or any combination thereof, and warns the user if estimated values are maintained within the abnormal range over the allowed time. Via the proposed mechanism, users are able to be aware of their unhealthy postures, and then try to correct their postures.

We present an ontology-based reasoning approach for saving energy in a smart home setting where a mobile phone can serve as a generic sensor which can collect the inhabitant's contextual data. The paper details an ontology that describes the smart home domain and a prototype to test the system. Finally, we conclude with lessons learned from our work in developing an energy-aware smart home prototype and suggestions for future work.

We developed a user interface prototype for t he Android smartphone w hich recommends a number of applications to bes t m atch th e user's cont ext. To consider the user's context of use, we utilized 5 prototypical variables; time, location, weather, emotion, and activities. The developed system derives the best three recommended applications based on the results of supervised learning from such data sets. To consider the history of past context information, in addition to the current one, we developed a novel and effective probabilistic learning and inference algorithm named “Spatiotemporal Structure Learning”. By extending Naïve Bayesian Classifier, the spatiotemporal structure learning can create a probability model which represents relationship between time-series contextual variables. We implemented a prototype system which shows the current context and the inferred recommendation of applications. For the prototype system, w e developed an Android widget application for the user interface and a Java-based server application which learns structure from training data and provides inference results in real-time. To gather training d ata and evaluate proposed system, w e conducted a pilot stud y which showed 69% of accuracy in predicting the user's application usage. The prototype demonstrated the feasibility of an adaptive user interface applied to a state of the art smartphone. We also believe that the suggested spatiotemporal structure learning can be applied to number of application areas including healthcare or energy problems.