論文

In this research, we propose a system that allows one to find a hidden spot that is scenic, yet unpopulated, with the intention of improving the satisfaction of one's trip. These hidden spots are not yet noted in the existing tourism services, however can provide a new place for the tourists to discover. We developed an application as a prototype to analyze and pinpoint hidden spots by using venue data from Foursquare [1]. We acquired 19,705 data around Tokyo and calculated the relative hiding spot degree. Thus, we made it possible to provide users with hidden spot information from smartphone application.

Conversational agents are increasingly becoming digital partners of our everyday computing experiences offering a variety of purposeful information and utility services. Although rich on competency, these agents are entirely oblivious to their users’ situational and emotional context today and incapable of adjusting their interaction style and tone contextually. To this end, we present a first-of-its-kind situation-aware conversational agent on kinetic earable that dynamically adjusts its conversation style, tone, volume in response to users emotional, environmental, social and activity context gathered through speech prosody, ambient sound and motion signatures. In particular the system is composed of the following components: • Perception Builder: This component is responsible for building an approximate view of user’s momentary experience by sensing his/her 1) physical activity, 2) emotional state, 3) social context and 4) environmental context using different purpose-built acoustic and motion sensory models [4, 5]. • Conversation Builder: This component enables a user to interact with the agent using a predefined dialogue base, and for this demo, we have used Dialogflow [1] populated with a set of situation-specific dialogues. • Affect Adapter: This component is responsible for guiding the adaptation strategy for the agent’s response corresponding to the user’s context, taking into account the output of the perception builder and a data-driven rule engine. We have devised a set of adaptation rules using multiple quantitative and qualitative studies that describe the prosody, volume and speed to shape agents response. • Text-to-Speech Builder: This component is responsible for synthesising the agent’s response in a voice that accurately reflects a user’s situation using IBM Bluemix Voice service [2]. This synthesis process interplays various voice attributes, e.g., pitch, rate, breathiness, glottal tension etc. to transform agents voice according to the rule of the Affect Adapter.

The information of daily garbage diposal can be used to develop many appealing applications in smart cities. This poster introduces DeepCounter, an automotive sensing system to providing a fine-grained spatio-temporal distribution on the amount of disposed garbage bags. In the system, deep learning based image processing is used to automatically count the number of collected garbage bags from the video taken by a camera mounted on the rear of a garbage truck. A prototype system is implemented and experimental evaluation validates the feasibility of our proposal using realistic garbage collection videos in Fujisawa city, Japan.

We present how crowdsensing with civil officers contribute to collect larger amount of urban data with high spatial-temporal coverage, and enable to understand urban features by analyzing the data. We implemented a crowdsensing system which fits to daily city management, and conducted long-term experiment with garbage section of Fujisawa city, Japan. Based on analysis of collected data, we show that our system provide fine-grained urban data compared to crowdsensing with citizens with improving efficiency of city management. In addition, we analyze our dataset with demographic urban data, and clarified the relationship between pattern of uncollectible garbage thrown and features of resident area.

Increasing hardware resources, such as multi-core and multi-socket CPUs, memory capacity and high-speed NICs, impose significant challenges on Network Function Virtualization (NFV) backends. They increase the potential numbers of per-server NFs or tenants, which requires a packet switching architecture that is not only scalable to large number of virtual ports, but also robust to attacks on the data plane. This is a real problem; a recent study has reported that Open vSwitch, a widely used software switch, had a buffer-overflow bug in its data plane that results the entire SDN domain to be hijacked by worms propagated in the network. In order to address this problem, we propose REdge. It scales to thousands of virtual ports or NFs (as opposed to hundreds in the current state-of-the art), and protect modular, flexible packet switching logic against various bugs, such as buffer overflow and other unexpected operations using static program checking. When 2048 NFs are active and packets are distributed to them based on the MAC or IP addresses, REdge achieves 3.16 Mpps or higher packet forwarding rates for 60 byte packets and achieves the wire rate for 1500 byte packets in the 25 Gbps link.

Many researchers and companies have engaged in estimating users' interests so that an online shopping system can tell what he/she wants now. This paper tackles the next challenge in online shopping, i.e., predicting the times that users go shopping online. To predict the timing of online shopping, we focus on wandering behavior in web search activities and propose a search wandering score (SWS). Online shopping behavior can be categorized into three states: wandering shop-ping, focused shopping, and others. Wandering shopping is a state in which users make purchases in high SWS situations; focused shopping is a state in which users buy things in low SWS situations. Unlike previous studies, our work is based on an analysis of large-scale data containing shopping and search logs produced by approximately 200,000 users of a real web portal site for over a year. The results of an extensive evaluation show that our methodology can predict user's future shopping behavior types with 86% accuracy. This research is the first step towards understanding the relationship between users' mental states and their online shopping behavior.

Conversational agents are increasingly becoming digital partners of our everyday computing experiences offering a variety of purposeful information and utility services. Although rich on competency, these agents are entirely oblivious to their users' situational and emotional context today and incapable of adjusting their interaction style and tone contextually. To this end, we present a mixed-method study that informs the design of a situation-and emotion-aware conversational agent for kinetic earables. We surveyed 280 users, and qualitatively interviewed 12 users to understand their expectation from a conversational agent in adapting the interaction style. Grounded on our findings, we develop a first-of-its-kind emotion regulator for a conversational agent on kinetic earable that dynamically adjusts its conversation style, tone, volume in response to users emotional, environmental, social and activity context gathered through speech prosody, motion signals and ambient sound. We describe these context models, the end-to-end system including a purpose-built kinetic earable and their real-world assessment. The experimental results demonstrate that our regulation mechanism invariably elicits better and affective user experience in comparison to baseline conditions in different real-world settings.

With the advent of 24/7 technology-driven society, there are rising discomforts and increasing concerns over sleep. Quality of sleep critically affects human well-being and everyday performance. A good night’s sleep, therefore, is essential to prepare one’s mind and body for the next day. In this paper, we propose SleepThermo, a system that identifies the affect of in-cloth monitored body temperature change during sleep on human well-being. The primary purpose of this research is to determine the relationship between in-clothing body temperature and mental/physical conditions, and then elicit positive insights to improve sleep quality. Our evaluation proved that there is a potential for body temperature to be used in identifying mental and physical conditions. In addition, personalized models achieved better balanced accuracy than overall models in all subjects.

Collection of information of the events taking place in local neighborhoods along with the emotional statuses of the people involved can enable us to realize an 'affective smart city map', with which, for example, the local authority can review the measures adopted for the local areas and whether their these measure have actually contributed to the quality of life (QoL) and well-being of the people. To realize such an information system having easy-deployability, real-time and secure protection of user's sensitive data, we propose SmileCityReport, a smartphone app-based participatory sensing that can easily capture both the city events and the reporter's emotion-related status based on a novel technique that uses two cameras simultaneously. For our evaluation, we evaluated 15 users over one week and confirmed that the proposed methodology contributes to more activity and (estimated) more positive emotional status of the users, and also that the emotion-related facial expression values constitute valuable data that can be publicly shared.

Mobile Crowd Sensing (MCS) is a method for collecting multiple sensor data from distributed mobile devices for understanding social and behavioral phenomena. The method requires collecting the sensor data 24/7, ideally inconspicuously to minimize bias. Although several MCS tools for collecting the sensor data from an off-the-shelf smartphone are proposed and evaluated under controlled conditions as a benchmark, the performance in a practical sensing study condition is scarce, especially on iOS. In this paper, we assess the data collection quality of AWARE iOS, installed on off-the-shelf iOS smartphones with 9 participants for a week. Our analysis shows that more than 97% of sensor data, provided by hardware sensors (i.e., accelerometer, location, and pedometer sensor), is successfully collected in real-world conditions, unless a user explicitly quits our data collection application.

With the advancements in ubiquitous computing, ubicomp technology has deeply spread into our daily lives, including office work, home and house-keeping, health management, transportation, or even urban living environments. Furthermore, beyond the initial metric of computing, such as “efficiency” and “productivity”, the benefits that people (users) benefit on a well-being perspective based on such ubiquitous technology has been greatly paid attention in the recent years. In our first “WellComp” (Computing for Well-being) workshop, we intensively discuss about the contribution of ubiquitous computing towards users' well-being that covers both physical, mental, and social wellness (and their combinations), from the viewpoints of various different layers of computing. Having strong international organization members in various ubicomp research domains, WellComp 2018 will bring together researchers and practitioners from the academia and industry to explore versatile topics related to wellbeing and ubiquitous computing.

With the advancements in ubiquitous computing, ubicomp technology has deeply spread into our daily lives, including office work, home and house-keeping, health management, transportation, or even urban living environments. Furthermore, beyond the initial metric of computing, such as “efficiency” and “productivity”, the benefits that people (users) benefit on a well-being perspective based on such ubiquitous technology has been greatly paid attention in the recent years. In our second “WellComp” (Computing for Well-being) workshop, we intensively discuss about the contribution of ubiquitous computing towards users’ well-being that covers physical, mental, and social wellness (and their combinations), from the viewpoints of various different layers of computing. Having strong international organization members in various ubicomp research domains, WellComp 2019 will bring together researchers and practitioners from the academia and industry to explore versatile topics related to wellbeing and ubiquitous computing.

With the advancements in ubiquitous computing, ubicomp technology has deeply spread into our daily lives, including office work, home and house-keeping, health management, transportation, or even urban living environments. Furthermore, beyond the initial metric of computing, such as "efficiency"and "productivity", the benefits that people (users) benefit on a well-being perspective based on such ubiquitous technology has been greatly paid attention in the recent years. In our third "WellComp"(Computing for Well-being) workshop, we intensively discuss about the contribution of ubiquitous computing towards users' well-being that covers physical, mental, and social wellness (and their combinations), from the viewpoints of various different layers of computing. After big success of two previous workshops WellComp 2018 and 2019, with strong international organization members in various ubicomp research domains, WellComp 2020 will bring together researchers and practitioners from the academia and industry to explore versatile topics related to well-being and ubiquitous computing.

Background: Obese pregnant women are known to experience poorer pregnancy outcomes and are at higher risk of postnatal arteriosclerosis. Hence, weight control during and after pregnancy is important for reducing these risks. The objective of our planned randomized controlled trial is to evaluate whether the rate of change in body weight in obese women before pregnancy to 12 months postpartum would be lower with the use of an intervention consisting of Internet of Things (IoT) devices and mobile applications during pregnancy to 1 year postpartum compared to a non-intervention group. Methods: Women will be recruited during outpatient maternity checkups at four perinatal care institutions in Japan. We will recruit women at less than 30 weeks of gestation with a pre-pregnancy body mass index ≥ 25 kg/m2. The women will be randomly assigned to an intervention or non-intervention group. The intervention will involve using data (weight, body composition, activity, sleep) measured with IoT devices (weight and body composition monitor, activity, and sleep tracker), meal records, and photographs acquired using a mobile application to automatically generate advice, alongside the use of a mobile application to provide articles and videos related to obesity and pregnancy. The primary outcome will be the ratio of change in body weight (%) from pre-pregnancy to 12 months postpartum compared to before pregnancy. Discussion: This study will examine whether behavioral changes occurring during pregnancy, a period that provides a good opportunity to reexamine one's habits, lead to lifestyle improvements during the busy postpartum period. We aim to determine whether a lifestyle intervention that is initiated during pregnancy can suppress weight gain during pregnancy and encourage weight loss after delivery. Trial registration: UMIN: UMIN (University hospital Medical Information Network) 000,041,460. Resisted on 18th August 2020. https://upload.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000047278.

With the advancements in ubiquitous computing, ubicomp technology has deeply spread into our daily lives, including office work, home and house-keeping, health management, transportation, or even urban living environments. Furthermore, beyond the initial metrics commonly applied in computing, such as "efficiency"and "productivity", the benefits that people (users) benefit on a well-being perspective based on such ubiquitous technology has been greatly emphasized in the recent years. Through the second "WellComp"(Computing for Well-being) workshop, we will intensively discuss about the contribution of ubiquitous computing towards users' well-being that covers both physical, mental, and social wellness (and their combinations), from the viewpoints of various different layers of computing. Having strong international organization members in various ubicomp research domains, WellComp 2021 will bring together researchers and practitioners from the academia and industry to explore versatile topics related to well-being and ubiquitous computing.

Towards wellbeing-awareness in computing, researches for estimating users' emotions using smartphone sensor data have been actively conducted as smartphones are getting more and more ubiquitous. Most studies have constructed emotion estimation models based on machine learning with contextual data from the smartphones and user's self-reporting ground truth label often collected via Experience Sampling Method (ESM). However, snice our emotion changes frequently in our daily lives, trying to collect the ground truth of such volatile emotions leads a storm of ESMs which could be burden to the users. In order to find better ESM methods, we propose and compare 3 ESMs, namely Randomized ESM that executes in randomly timings, Trigger ESM that executes when the user's behavior changes, and Unlocking ESM that sets up ESM on the unlocking screen. We constructed various emotional estimation models with four types of time granularity (1 day, 1/3 day, 3 hours, 1 hour) in four weeks experience with eight persons. As for the response rate, Unlocking ESM was the highest. In addition, it was clear that Unlocking ESM had the highest estimation accuracy in most cases.