Papers by Keiichi Yasumoto
2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), 2018
It has been intensively demonstrated that physical activity can enhance the mental and physical h... more It has been intensively demonstrated that physical activity can enhance the mental and physical health of practitioners. In recent years, fitness activities became the most common way to engage in physical activities. In this paper, we propose a smart-glove based fitness activity tracking system that can detect athletes activities in any indoor fitness facility, with no need of attaching multiple sensors on the athlete’s body. The system adopts force sensitive resistor (FSR) sensors to identify the type of exercise by analyzing the pressure distribution in the hand palm during fitness activities. To evaluate the performance of our proposed system, we ran a pilot study with 10 healthy participants over 10 common fitness activities. The experimental results showed an overall recognition accuracy rate of 87%. We believe the promising results would contribute to the works on personal assisted coaching systems and create enjoyable experiences when performing fitness activities.
2022 ACM/IEEE 13th International Conference on Cyber-Physical Systems (ICCPS)
Modern smart cities are focusing on smart transportation solutions to detect and mitigate the eff... more Modern smart cities are focusing on smart transportation solutions to detect and mitigate the effects of various traffic incidents in the city. To materialize this, roadside units and ambient transportation sensors are being deployed to collect vehicular data that provides real-time traffic monitoring. In this paper, we first propose a real-time data-driven anomaly-based traffic incident detection framework for a city-scale smart transportation system. Specifically, we propose an incremental region growing approximation algorithm for optimal Spatio-temporal clustering of road segments and their data; such that road segments are strategically divided into highly correlated clusters. The highly correlated clusters enable identifying a Pythagorean Mean-based invariant as an anomaly detection metric that is highly stable under no incidents but shows a deviation in the presence of incidents. We learn the bounds of the invariants in a robust manner such that anomaly detection can generalize to unseen events, even when learning from real noisy data. We perform extensive experimental validation using mobility data collected from the City of Nashville, Tennessee, and prove that the method can detect incidents within each cluster in real-time.
! " #%$'&'(*),+ . / 01+ 2 $ 3 45+6+ 7 8 9 :5+ 2 ; < =,+>+?+ @ A B C,+6+D+ ... more ! " #%$'&'(*),+ . / 01+ 2 $ 3 45+6+ 7 8 9 :5+ 2 ; < =,+>+?+ @ A B C,+6+D+ E F G 45+ H IKJMLON PRQ SKT UWV X Y Z [ L \ ] ^`_baRc`d eMf g h ikj LOTOS l m nRoKprq _ S I s truwvOx p y{z S |K} l~
K `lMOrk O nR b`n `nK I JML LOTOS ~K U ¡ nw¢ N`PQ SbJM£ vb¤ v 1 ¥blk¦ UWZ ̈§© «a v n ¬b¥bl ¦ UWZ ̈§© {a vOx N`PRQKS JW®° ̄ lK±M2 x LOTOS aR3 ́b_ U`μ°§\ ] ^ S¶W· 1 ̧o «M» U 1⁄4K1⁄2 uwv nW 3⁄4 ̈a v°x RkK¿ J £ vO¤ v Z ̈§R© a v°x ¦ ¿À I
uRv n Á Ubμk§Ã U Ä`·wQ `ÅRÆ 1⁄2
° j e aÇ`È«a vOx ~ «É x μ ÊËKÌ Í ÎO`nw Ï ·{Ð Ñ bqbÒo x N`PQ S T l \K] ^O_ aRc d μ Ó O n xKÔ L d`P ÖÕ × SØÐ Ù x Ú ]rÛ ÜÞÝ } Öß o ào x H UWá°â Mã äKå ærz S | }Y ç è ̧°z S | } jOé lWp yrz S | } sKt L Î êo x aR3K ́ _ U`μk§ 3⁄4oa vOx Þk
xWëKì L _ í · N`P{Ðî ́ í a ïRj°é l Ù ð U JMñ p òKó U Í ÎO n°k oô e õ ê I ö nbÁ ÷ ø x
Many research efforts have been made on human context recognition, especially activity recognitio... more Many research efforts have been made on human context recognition, especially activity recognition using sensors such as accelerometers embedded in smartphones. However, few studies are conducted for recognizing human context while operating smartphones (smartphone operating context or socontext in short). Examples of so-contexts are smoking or eating while operating smartphones and playing a game while in the train. Estimating so-contexts will bring new services such as notification timing optimization and user interface optimization. In this paper, aiming to provide a tool toward so-context estimation, we propose a system that monitors, recognizes and outputs user's touch operations on Android phones. To realize so-context estimation, the system needs to satisfy three requirements: (1) it should work on any android device, (2) it should run in the background of any application, and (3) it should identify touch operations in high-level format and output the identified operation...
Adjunct Proceedings of the 2021 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2021 ACM International Symposium on Wearable Computers, 2021
For the COVID-19 Contact Confirming Application (COCOA) to be fully effective, it is important th... more For the COVID-19 Contact Confirming Application (COCOA) to be fully effective, it is important that many people install COCOA on their smartphones. However, because the current COCOA implements only a minimum number of functions, it is difficult to motivate people to install it. Therefore, we focus on an extrinsic approach that motivates the installation of COCOA by adding fun functions through interaction with a ubiquitous system on the environment side. In this paper, we introduce an interactive system that nudges users to install COCOA by reframing the act of installing COCOA as getting a ticket to participate in fun experiences. CCS CONCEPTS • Human-centered computing → Interaction design.
Sensors and Materials, 2021
In recent years, street parking in prohibited areas has become a social problem, especially in ur... more In recent years, street parking in prohibited areas has become a social problem, especially in urban and tourist areas. In addition, because street parking can cause traffic congestion and accidents, real-time detection is required. The detection of street parking has been previously implemented on the basis of comparisons of videos recorded by fixed-point cameras. However, this approach has a limited detection area and low accuracy. To overcome these problems, this study aims towards a real-time street parking detection system that uses dashboard camera videos. We propose a machine learning method based on the characteristics of on-street parked vehicles derived by transforming images into text. The object detection model YOLOv3 was used to analyze videos. We created a dataset based on the coordinate information of 1765 vehicles and the recording vehicle information. We also created a model using random forest and logistic regression algorithms and evaluated it using the holdout and stratified 5-fold validation methods. F-measure values of up to 92% and 89% were obtained for the two types of model, respectively. These results confirm the effectiveness of the proposed street parking detection method based on bounding boxes and recording vehicle data.
In this paper, we propose a technique to implement communication protocols as hardware circuits u... more In this paper, we propose a technique to implement communication protocols as hardware circuits using a model of concurrent EFSMs with multi-way synchronization. Since use of multi-way synchronization enables simple and comprehensible specifications of recent communication protocols which frequently use complicated mechanisms such as mutual exclusion and dynamic job assignment, the proposed model is expected to reduce development cost in designing/developing such protocols. We implement specifications described in the model so that EFSMs work synchronously with the same clock, and that the synchronization mechanism for checking executability of each tuple of synchronizing transitions is implemented as a combinational logic circuit. Through some experiments, we have confirmed that the proposed technique can synthesize hardware circuits with relatively good performances for practical use. General Terms high-level synthesis, concurrent EFSMs, multi-way synchronization, LOTOS, communica...
Proceedings of the 18th Conference on Embedded Networked Sensor Systems
In recent years, many studies and development of Cyber Physical Systems (CPS) have been carried o... more In recent years, many studies and development of Cyber Physical Systems (CPS) have been carried out to feed back analysis results to human users in a physical space by using machine learning, aiming to analyze a huge amount of information obtained from physical space in a cyber space. To apply CPS to sports, a lot of studies have been conducted on sensing and recognizing actions and movements of athletes using machine learning. In this study, we focus on fishing as a sport, and propose a fishing CPS that recognizes anglers' actions in real-time and provides information on the past useful actions that are linked to fishing results depending on time and place as a decision support when the anglers do not make catch. In addition, this paper reports on the development of an IoT (Internet of Things) device that acquires positional information, acceleration and gyroscope information, and a web system that displays results of real-time activity recognition along with the place and time by animation for realizing the fishing CPS. We have evaluated the developed IoT device and web system from the viewpoint of practical use. As a result, we have confirmed that the GPS and acceleration sensors, in the actual breakwater environment, were constantly transmitting data to a server via UDP communication for 4 hours and 40 minutes.
Journal of Information Processing
Many network services are utilized in different fields and becoming indispensable to everyday lif... more Many network services are utilized in different fields and becoming indispensable to everyday life activities as Internet of Things (IoT) emerged as a communication network that connects almost everything. In addition to traditional one-to-one and oneto-many communications such as telephone, e-mail and web services, various communication forms and sophisticated processing such as social network services, big data utilization and artificial intelligence provide "places" and "knowledge" in cyber spaces for service users. To support the evolution of network services, a wide variety of cross-disciplinary and forward-thinking studies will be required in addition to studies to advance computing and networking technologies. More specifically, future studies to improve network services should include: recommendation engine, collaboration environments, machine learning techniques, network infrastructure in severe environments as in deep mountains and sea areas. It is essential to discuss social and technological tasks, and their solutions over the above issues in combinations of traditional network technologies, including all levels of implementation from the physical-through application-layers. Based on this background, we planned a special issue entitled "Network Services and Distributed Processing" in 2018. This special issue solicited submissions about research that collateralizes the existing distributed processing, not only network research but also embryonic research, research across boundaries in the application field, technical research for new service provision, safety, and research of new fundamental technology. Mainly the committee members from Special Interest Group on Distributed Processing System (IPSJ SIG-DPS) formed the editorial committee of the special issue as below. The Editorial Committee re
International Journal of Multimedia Data Engineering and Management, 2016
Emerging Internet of Things (IoT) technologies will allow spectators in a sport game to produce v... more Emerging Internet of Things (IoT) technologies will allow spectators in a sport game to produce various video streams from various angles. With existing technologies, however, it is difficult to process massive and various data streams for multi-channel contents in real-time. To solve this problem, we aim to construct a software agent (called “Curator”) that compiles video contents automatically according to his/her values. In this paper, we propose a system to automatically switch multiple video streams that general sports spectators have taken using Random Forests classifier. Meta data such as image feature data and game progress data is extracted for each video scene as the input of the classifier. For evaluation, we constructed a camera switching timing estimation model using the live TV broadcast of some baseball game data. A video of another baseball game was curated with the constructed model. As a result, our system predicted the camera switching timing with accuracy (F-meas...
2013 IEEE Region 10 Humanitarian Technology Conference, 2013
In this paper, we propose a Java-based middleware for group communication in wireless ad hoc netw... more In this paper, we propose a Java-based middleware for group communication in wireless ad hoc networks. The pro- posed middleware provides facilities for establishing multi- way synchronization channels among multiple agents (pro- cesses executed in mobile hosts) based on their locations. Through multi-way synchronization channels, agents can ex- ecute events on the same channel synchronously to exchange data. Through some
This paper presents a cost-efficient video multi- cast method for live video streaming to heterog... more This paper presents a cost-efficient video multi- cast method for live video streaming to heterogeneous mobile terminals over a content delivery network (CDN), where CDN consists of a video server, several proxies with wireless access points, and overlay links among the server and proxies. In this method, the original video sent from the server is converted into multiple versions with various qualities by letting proxies execute transcoding services based on the users' requirements, and delivered to mobile terminals along video delivery paths. To suppress the required computation and transfer costs in CDN, we propose an algorithm to calculate cost-efficient video delivery paths which minimizes the sum of the computation cost for proxies and the transfer cost on overlay links. Our basic idea for deriving cost-efficient delivery paths is to place transcoding service on different proxies in load-balancing manner, and to construct a minimal Steiner tree from all transcoding points ...
Due to the recent progress of the Internet, we need high-speed net- work monitors which can obser... more Due to the recent progress of the Internet, we need high-speed net- work monitors which can observe millions of packets per second. Since several types of network attacks occur, we need to modify monitoring facilities and their capacities depending on monitoring items and network speed. In this paper, we propose (1) a methodology for designing and implementing such network mon-
2008 Ieee International Conference on Multimedia and Expo, 2008
The 3D tele-immersive (3DTI) environments are emerging as the next generation technique for tele-... more The 3D tele-immersive (3DTI) environments are emerging as the next generation technique for tele-communication. In this paper, we present a novel and generic interface for view control in 3D environments. The interface uses Wii Remote, a wireless controller for a video game console. It allows the user to manipulate the virtual camera and 3D objects intuitively with buttons and through motions (pitch and roll). We conducted user studies to evaluate the interface with a professional dancer and average audiences. The results demonstrate that the Wii Remote interface is much better suited to view control in 3DTI environments since it is much easier to use, more effective, and more accurate than the conventional mouse-based interfaces.
2000 Ieee International Conference on Multimedia and Expo Icme2000 Proceedings Latest Advances in the Fast Changing World of Multimedia, Feb 1, 2000
ABSTRACT We propose a language called QOS-SMIL where some QoS guarantee statements are added to a... more ABSTRACT We propose a language called QOS-SMIL where some QoS guarantee statements are added to a subclass of SMIL, and give its implementation technique. In QOS-SMIL, in addition to standard facilities of SMIL, dynamic media-scaling of each multimedia object and explicit inter-media synchronization among objects, can be specified. In the proposed implementation technique, we use real-time LOTOS as an intermediate language so that we convert a given QOS-SMIL description to the corresponding real-time LOTOS specification, and implement it with our real-time LOTOS compiler. Through some experiments, we have confirmed that our approach has some advantages w.r.t. development cost of multimedia systems with QoS control
2010 7th IEEE Consumer Communications and Networking Conference, 2010
In Vehicular Ad Hoc Networks (VANETs), delivering messages to a specific location is difficult du... more In Vehicular Ad Hoc Networks (VANETs), delivering messages to a specific location is difficult due to the high mobility of vehicles. In this paper, we propose a method for efficient message delivery in VANETs utilizing the route information in car navigation systems. In the proposed method, each car periodically exchanges the information on its current position and scheduled route in the car navigation system with neighboring cars within radio range. By referring to the exchanged information, each car forwards messages to the neighboring car that will most closely approach the destination. Through simulations, we confirm that the proposed method achieves a better delivery rate with low bandwidth usage than a Geocast-based method and Epidemic routing.
Uploads
Papers by Keiichi Yasumoto