Public spaces are created for the convenience of visitors, but frequently, their operation does not match individual visitors' needs. We propose instant social control as a new approach for controlling devices deployed in public spaces, envisioning the democratic and inclusive operation of the spaces. It is an approach to embrace individuals in the dynamic and unpredictable situations of public spaces, providing them with a powerful tool of immediate engagement and reflection. This research explores the use of instant social control, focusing on cases where discrepancies and conflicts arise among visitors' preferences for operating public devices. We conducted a field trial by deploying a technology probe to two real-world public spaces: a university auditorium, and a cafeteria. We collected usage logs and surveyed the users' experience with this new way of device control. We further investigated their experience through in-depth interviews with participants. Our field trial revealed a rich set of findings including voting strategies, exploratory device control patterns, users' attempts to communicate with other visitors, considerations of other visitors' discomfort, and acceptance and usefulness of instant social control of public devices.

Public spaces1 are a basis of urban lives. The mode and culture of sharing could be an indicator of the quality of life in the cities. For example, the buses and restaurants should comfort and bring satisfaction to individual visitors, including the vulnerable with special needs. However, their operation mostly occurs in rather a closed and exclusive manner [2]. An inherent limitation to such an inclusive sharing lies in the exclusive modes of traditional device interfaces; a variety of devices, called public devices hereafter, are installed in the public space and determine operational details of the space. As such, the space itself is shared, however, the public devices are controlled in exclusive ways. Could the sharing of the public space be operated in a democratic way?

Public spaces1 are a basis of urban lives. The mode and culture of sharing could be an indicator of the quality of life in the cities. For example, the buses and restaurants should comfort and bring satisfaction to individual visitors, including the vulnerable with special needs. However, their operation mostly occurs in rather a closed and exclusive manner [2]. An inherent limitation to such an inclusive sharing lies in the exclusive modes of traditional device interfaces; a variety of devices, called public devices hereafter, are installed in the public space and determine operational details of the space. As such, the space itself is shared, however, the public devices are controlled in exclusive ways. Could the sharing of the public space be operated in a democratic way?

Public spaces, where we gather, commune, and take a rest, are the essential parts of a modern urban landscape, enriching citizen's everyday life [3]. How we share these spaces are considered an indicator of the quality of life. Public spaces thus have a responsibility to provide comfort and satisfaction to any visitors. However, in most times, the operations of the spaces are managed in rather an exclusive manner.

Public spaces are equipped with 'public actuators', e.g., HVAC, lighting fixtures, speakers, or streaming TV channels to ensure their visitors' comfort. However, many public actuators rarely allow the visitors to adjust their operation, limiting their utility and fairness across the visitors. Also, the social bar is often too high to speak up one's preference and attempt to change an actuator's operation. Social control and use of IoT devices is an underexplored new direction of research even with its huge potential and implication, but comes with high complexity and scale. This paper proposes a novel architecture, namely, Social Control-and-Use Architecture for IoT Devices , which provides a systematic view and an effective tool to handle the complication and intricacy in system design. It also proposes Hivemind , a first-of-a-kind system developed, upon the architecture, for sharing IoT-enabled actuators in a public space. It transforms an exclusively-controlled actuator in a public space into a true public actuator, supporting visitors to instantly participate in the democratic collective control. Also, a myriad of off-the-shelf actuators are easily incorporated without modification to their implementation. The field deployment of Hivemind shows its comprehensive service coverage as well as the users' approval on the democratic collective control of public actuators.

Energy-efficiency is a key performance metric of mobile sensing applications. However, assessment of energy-efficiency is greatly limited in practice. The main difficulty is that it requires assessment of power consumption in various user's real-life situation in the long term. This poster presents DeepPower, a system for assessing energy-efficiency of mobile sensing applications in fast and scalable manner. DeepPower introduces a sensor trace-based power use prediction technique, which significantly reduces the cost of assessing power consumption compared to existing power emulation techniques. Our experiments with three mobile sensing applications and five 1-hour-long sensor traces show that DeepPower can predict hardware usage of 1-hour-long sensor traces in less than a second, achieving average error rate of 4.6%.

Wearable sensors are increasingly becoming the primary interface for monitoring human activities. However, in order to scale human activity recognition (HAR) using wearable sensors to million of users and devices, it is imperative that HAR computational models are robust against real-world heterogeneity in inertial sensor data. In this paper, we study the problem of wearing diversity which pertains to the placement of the wearable sensor on the human body, and demonstrate that even state-of-the-art deep learning models are not robust against these factors. The core contribution of the paper lies in presenting a first-of-its-kind in-depth study of unsupervised domain adaptation (UDA) algorithms in the context of wearing diversity -- we develop and evaluate three adaptation techniques on four HAR datasets to evaluate their relative performance towards addressing the issue of wearing diversity. More importantly, we also do a careful analysis to learn the downsides of each UDA algorithm and uncover several implicit data-related assumptions without which these algorithms suffer a major degradation in accuracy. Taken together, our experimental findings caution against using UDA as a silver bullet for adapting HAR models to new domains, and serve as practical guidelines for HAR practitioners as well as pave the way for future research on domain adaptation in HAR.

Several privacy sensitive apps, e.g., dating apps, and medical counselling apps are equipped with Instant Messaging (IM) features. Messenger features in such apps, let users to chat romantically or as a part of getting personal counselling. However, frequently interacting with the app's messenger service privately, is difficult in public spaces. We term such public spaces as Casual Acquaintance-prone Spaces (CAS). To overcome the limitations associated with interacting with sensitive apps, we propose IMception, a design solution to camouflage sensitive apps' messenger-feature within another app's UI. To conceptualize the design of IMception, we conducted a two-week long survey. Our key findings include that participants felt concerned not only with the content (text messages) from their sensitive apps but also with the appearance of the app from its UI. At last, we explore and discuss the design of IMception and highlight its important design considerations.

In this paper, we introduce inertial signals obtained from an earable placed in the ear canal as a new compelling sensing modality for recognising two key facial expressions: smile and frown. Borrowing principles from Facial Action Coding Systems, we first demonstrate that an inertial measurement unit of an earable can capture facial muscle deformation activated by a set of temporal micro-expressions. Building on these observations, we then present three different learning schemes - shallow models with statistical features, hidden Markov model, and deep neural networks to automatically recognise smile and frown expressions from inertial signals. The experimental results show that in controlled non-conversational settings, we can identify smile and frown with high accuracy (F1 score: 0.85).

Real-time remote interaction has become easier and richer powered by recent advances in mobile computing and communication. A number of research have been explored on enriching family interaction by augmenting an interaction channel with asynchronous communication [6] or additional sensory stimuli [5]. However, it is still far from achieving a sense of living together for family members involuntarily living apart, especially in context-aware impromptu interaction. For families living together, it is trivial to naturally perceive behavioral and situational contexts of the other and initiate a relevant interaction intuitively. For example, a wife starts a casual chat with asking her husband what he is going to cook when she sees him going to the kitchen or hears a simmering sound.

People in work-separated families have been heavily relying on cutting-edge face-to-face communication services. Despite their ease of use and ubiquitous availability, experiences in living together are still far incomparable to those through remote face-to-face communication. We envision that enabling a remote person to be spatially superposed in one's living space would be a breakthrough to catalyze pseudo living-together interactivity. We propose HomeMeld, a zero-hassle self-mobile robotic system serving as a co-present avatar to create a persistent illusion of living together for those who are involuntarily living apart. The key challenges are 1) continuous spatial mapping between two heterogeneous floor plans and 2) navigating the robotic avatar to reflect the other's presence in real time under the limited maneuverability of the robot. We devise a notion of functionally equivalent location and orientation to translate a person's presence into another in a heterogeneous floor plan. We also develop predictive path warping to seamlessly synchronize the presence of the other. We conducted extensive experiments and deployment studies with real participants.

Real-time remote interaction in work-separated families has become easier and richer by recent advances in mobile computing, yet it is still far from achieving a sense of living together. Imagine family members living apart are mutually co-present in each other’s home with their avatars that all the activities and movements are intelligently mirrored in the other’s living space. Such co-presence brings many pseudo living-together experiences, which are incomparable to those of today’s remote face-to-face communication. We develop an initial prototype, HomeMeld, a device-free self-mobile robotic system serving as a real-time, co-present avatar to create an illusion of living together. HomeMeld is built on top of a commercial telepresence robot hardware [1] and a CNN-based computer vision technique, letting a person be device-free at all times as like as she is at home. In this demo, we present the motivation behind our work, the end-to-end operation of HomeMeld, and the vision of giving a sense of living together to the family living apart.

This paper presents a dialog state tracker submitted to Dialog State Tracking Challenge 5 (DSTC 5) with details. To tackle the challenging cross-language human-human dialog state tracking task with limited training data, we propose a tracker that focuses on words with meaningful context based on attention mechanism and bi-directional long short term memory (LSTM). The vocabulary including a plenty of proper nouns is vectorized with a sufficient amount of related texts crawled from web to learn a good embedding for words not existent in training dialogs. Despite its simplicity, our proposed tracker succeeded to achieve high accuracy without sophisticated pre- and post-processing.