Children naturally transform everyday objects into play equipment, but studying these spontaneous interactions using real products poses significant safety and analytical challenges. As a new methodology of environmental design and interaction science, this paper proposes the "Playfication" framework to quantitatively model and predict how children interact with environments based on pure 3D geometry and physical scale. First, Non-negative Matrix Factorization (NMF) is applied to a large-scale 3D dataset on everyday objects to extract fundamental geometric patterns ("Basis Shapes"). The authors fabricated these shapes as safe, soft blocks and conducted a free-play observational study with 31 children to capture interaction distributions. By integrating 3D point clouds and absolute scale data, a PointNet++ model was trained to predict interaction probabilities (e.g., "sit," "stand," "crawl"). An evaluation using unseen commercial furniture demonstrated the model's accuracy in predicting physical affordances. This approach serves as an exploratory proof-of-concept for understanding child-object interactions and designing safer, more engaging environments.

An inclusive society has a growing demand for support systems that can accommodate the diversity of human physical and mental functions and the diversity of living environments. This study focuses on preventing home accidents involving young children as a concrete example of methodologies for observing, modeling, and controlling "living situations," which are complex systems composed of people and their environments, where interactions between people and environments change over time. Although previous research has proposed technologies for recognizing children’s behaviors and detecting environmental risks, few have integrated behavior and environment to predict accident pathways and time to occurrence. In this study, the authors propose a system that integrates home data scanned in three dimensions acquired through smartphones, child position data obtained using posture recognition technology, and epidemiological accident databases (N=358,715 cases) collected by the Tokyo Fire Department in Japan. The system estimates accident risks based on the relative positions of furniture and children, and visualizes the predicted paths and expected arrival time to high-risk objects in real-time. The evaluation based on national accident statistics confirmed that the system’s object recognition covers approximately 70% of furniture types involved in serious accidents. By conducting experiments for a six-year-old child and 55 three-dimensional scanned data obtained in actual living environments, the authors also demonstrate the feasibility of risk visualization considering the individuality and dynamic nature of living environments.

Falls among older adults are a serious global challenge. The World Health Organization strongly recommends gait, balance, and functional training, Tai Chi, or home assessment and modification to prevent falls among older people, but these strategies have not changed over the past few decades. The purpose of the present study is to propose an innovative approach to fall prevention naturally embedded in the environment. We first suggest new methods for simplifying and understanding the relationship between falls and everyday life, and describe this relationship as a knowledge graph using emergency transport data on falls among the aged. As a result of a cluster analysis using knowledge graphs, we identified whole-body balance as a key factor and living environmental determinant of falls. We then propose the concept of a homeostatic spatial system and discuss our development of seven homeostatic products as a proof of concept. Finally, we develop an evaluation system to visualize specific locations in a defined area where people maintain whole-body balance using their hands or other body parts. Our findings confirm that the system is useful for evaluating how people change their behaviors to maintain whole-body balance based on homeostatic products and the living environment as a whole.

We propose a Convolutional Neural Network (CNN)-based model "RotationNet," which takes multi-view images of an object as input and jointly estimates its pose and object category. Unlike previous approaches that use known viewpoint labels for training, our method treats the viewpoint labels as latent variables, which are learned in an unsupervised manner during the training using an unaligned object dataset. RotationNet uses only a partial set of multi-view images for inference, and this property makes it useful in practical scenarios where only partial views are available. Moreover, our pose alignment strategy enables one to obtain view-specific feature representations shared across classes, which is important to maintain high accuracy in both object categorization and pose estimation. Effectiveness of RotationNet is demonstrated by its superior performance to the state-of-the-art methods of 3D object classification on 10- and 40-class ModelNet datasets. We also show that RotationNet, even trained without known poses, achieves comparable performance to the state-of-the-art methods on an object pose estimation dataset. Furthermore, our object ranking method based on classification by RotationNet achieved the first prize in two tracks of the 3D Shape Retrieval Contest (SHREC) 2017. Finally, we demonstrate the performance of real-world applications of RotationNet trained with our newly created multi-view image dataset using a moving USB camera.

We propose a Convolutional Neural Network (CNN)-based model "RotationNet," which takes multi-view images of an object as input and jointly estimates its pose and object category. Unlike previous approaches that use known viewpoint labels for training, our method treats the viewpoint labels as latent variables, which are learned in an unsupervised manner during the training using an unaligned object dataset. RotationNet is designed to use only a partial set of multi-view images for inference, and this property makes it useful in practical scenarios where only partial views are available. Moreover, our pose alignment strategy enables one to obtain view-specific feature representations shared across classes, which is important to maintain high accuracy in both object categorization and pose estimation. Effectiveness of RotationNet is demonstrated by its superior performance to the state-of-the-art methods of 3D object classification on 10- and 40-class ModelNet datasets. We also show that RotationNet, even trained without known poses, achieves the state-of-the-art performance on an object pose estimation dataset.

Lacerations occur frequently in numerous common environments, but the mechanisms by which they are generated remain unclear. This makes it difficult for designers to create products that can prevent such injuries. Although a significant number of studies have dealt with injury prevention from the standpoint of avoiding bone fractures, lacerations have yet to be thoroughly investigated and a scientific approach to laceration prevention is urgently required. In this paper, we describe a system for analyzing the dynamic characteristics of human-skin like materials, such as pigskin, in an effort to understand laceration generation mechanisms. The system consists of a high speed camera and a drop impact device. Additionally, we developed a finite element model (FEM) for use in determining the inner behavior of materials via computer simulation. According to statistical analysis using injury surveillance data, a typical situation involves a collision between a victim's head and the edge of an object, such as a table, chair, bathtub, or other such item. Accordingly, we conducted experiments aimed at determining the dynamic characteristic of pigskin, which is a substitute for human skin, when it collides with various materials. This paper reports our experimental results and discusses laceration generation mechanisms in order to obtain scientific knowledge that can be used when designing product safety features.

We've known for a while that the Internet has ossified as a result of the race to optimize existing applications or enhance security. NATs, performance-enhancing-proxies,firewalls and traffic normalizers are only a few of the middleboxes that are deployed in the network and look beyond the IP header to do their job. IP itself can't be extended because "IP options are not an option". Is the same true for TCP?

Many injures during childhood are related to the use of playground equipment. Until recently, scientific data of how children actually use playground equipment were scarce. Childhood injury cases were not examined thoroughly from the perspective of how equipment can be modified for improving safety without ruining its attraction to children. To design age-appropriate and safer playground equipment, it is essential that scientific data on the interaction between children and this equipment be accumulated. Herein we report on studies to develop new playground equipment by applying sensor technology to examine the science behind children's interaction with playground equipment. We developed a rock-climbing wall equipped with force sensors to record the physical behavior of children while on the wall, thus allowing measurement of these behaviors in a more natural environment. Fifty force sensors installed in the developed rock-climbing wall are able to collect a large amount of data while children are playing with the equipment. The behavior data of 623 children were recorded in the present study. Herein, we also report on a child behavior prediction model created from the collected data.

Migration between different wireless access networks often involves disconnected period, which is caused by passing an area of bad wireless coverage and potential overhead to switch the network on the network interface to connect to. The disconnected period can cause extra transmission delay due to the timer-driven retransmission behavior in the transport protocols, such as TCP and SCTP. We propose a new retransmission scheme to achieve better migration performance in SCTP, which is a newer connection-oriented and reliable transport protocol that is becoming popular. Our scheme minimizes the extra transmission delay by leveraging address reconfiguration operation in SCTP without involving other layers. It decreases the delay more than 5 seconds compared to the original SCTP when migration involves approximately ten-second disconnected period. The implementation of our scheme is already imported in FreeBSD.

PR-SCTP provides a timeliness transport service. When the lifetime of the data specified by the application expires, the sender PR-SCTP gives up retransmitting the data, and transmits a Forward TSN chunk to make the receiver advance the Cumulative ACK point. However, on the mobile communication, connectivity of the nodes is intermittent. PRSCTP does not work properly in this case, thereby the timeliness transmission is impaired. In order to address this issue, we propose a new algorithm that transmits a Forward TSN triggered by readdressing events in SCTP associations. Our scheme allows PR-SCTP to restart transmission of data with lifetime smoothly regardless of duration of the connectivity disruption.

This paper presents an improvement of position estimation of the ultrasonic 3D tag system developed by the authors. We are involved in a joint project of developing an omnidirectional autonomous mobile robot system and our ultrasonic 3D tag system was employed as an indoor GPS system to the robot. However, the position estimation error of current system is not enough to support the mobile robot, that is, position estimation error of the system is about 50mm by using the currently implemented robust estimation methods. By employing a new estimator based on a nonparametric filter, the estimation error was reduced to less than 20mm on average. Moreover, the new method is much robuster than the previous methods. This paper introduces an overview of the system and experimental results of simulations.

This paper reports on the development of a mobile robot system for operation within a house equipped with a ubiquitous sensor network.Human robot interaction is achieved through the combination of on-robot audio and laser range sensing and additional audio sensors mounted in the ceiling of the ubiquitous environment. The ceiling mounted microphone arrays can be used to summon a mobile robot from a location outside the robot's range of hearing. After the robot autonomously navigates to the desired location, the on-board microphone array can be used to locate the sound source and to recognise a series of greetings and commands.

This paper describes a mobile robot for home service purpose together with ubiquitous ceiling ultrasonic locator and microphone array. User call can be detected by those ubiquitous devices and then mobile robot navigates toward given location. After reaching to the given location, the robot tries to find out user location by using stereo camera, laser and onbody microphone array. We implemented those system at our experimental house "Rokko Holone". System components and experimental results are shown.

Many handover techniques in the Internet have been introduced with the development of mobile computing technologies. Although many proposed handover schemes utilize multiple interfaces, having multiple interfaces can increase power consumption, device installation space and hardware costs of mobile devices. Therefore, we have been studying handover schemes for mobile nodes with a single wireless network interface. To achieve seamless and efficient handover, we focus on stream control transmission protocol (SCTP) which offers message-oriented, reliable and connection-oriented delivery transport service. Unlike other transport protocols such as TCP, SCTP can provide an end-to-end handover mechanism with a multi-homing feature. However, the handover mechanism in the current SCTP causes large handover delay especially when a mobile node has only one single wireless network interface. In this paper, we have investigated the current issues in the SCTP handover mechanism and propose a new handover scheme based on SCTP, which identifies a communication path as a pair of source and destination address. We also propose new data retransmission feature for smooth handover.

This paper describes the recent development of new optical torque sensor in order to replace expensive strain gauge sensor attached at the tip of the anthropomorphic robot arm and realize local impedance control in each joint

This paper describes a mobile robot for home service purpose together with ceiling attached ultrasonic locator and microphone array. User call can be detected by those ceiling devices and then mobile robot navigates toward given location. After reaching to the given location, the robot tries to find out user location by using stereo camera, laser and triconcentric microphone array. We implemented those system at our experimental house "Rokko Holone". System components and experimental results are shown

This paper proposes a learning-by-doing (LBD) system for assisting learners of English as a foreign language, by providing educational content generated based on real-world behaviors in a sensorized environment. The LBD system consists of an ultrasonic location sensing system developed by the authors and an educational content server. The location of the student is monitored by ultrasonic sensors embedded around the learning room. The system voices English verbs related to objects around the student so that the student can obtain the language skills for expressing various activities of everyday life in English by performing real-world behaviors. The system was implemented experimentally in an English language school. Six subjects participated in an experiment evaluating the educational efficacy of the proposed system. Recall rates of learned verbs were compared among three methodologies, "learning by text," "learning by pictures and text," and "learning by doing". Recall rates were measured at the following intervals: soon after the learning task, 2 days after, 4 days after, 7 days after, and 14 days after the learning task. The results indicate that the proposed LBD system increased the recall rate of learned words by 113% 14 days after the learning task. Overall, the system significantly increased the average recall rate by 102% in comparison to the other learning methodologies.

In this paper, we focus on the overhead caused by the conflict between TCP/IP and IEEE 802.11 technologies and propose two schemes: partial retransmission and ACK suppression to alleviate this issue. Our schemes can improve communication performance and error resiliency simultaneously in TCP/IP communication over 802.11 networks. Because our schemes require modification only to the IEEE 802.11 DCF and do not require any modification in IP or higher layers, users can use these schemes by replacing the 802.11 interfaces or device drivers of mobile machines and 802.11 access points. This means that the deployment issue of our scheme will be minor compared to the other solutions that require modifications of TCP/IP protocols or applications. Furthermore, the design of our schemes are quite simple so that they can be used in low CPU power devices, which is an important factor for mobile devices.

This paper describes a method for robustly detecting and efficiently recognizing daily human behavior in the real world. The proposed method involves real-world sensorization using ultrasonic tags to robustly observe behavior, real-world virtualization to create a virtual environment by modeling real objects using a stereovision system, and virtual sensorization of virtualized objects in order to quickly register the handling of objects in the real world and efficiently recognizing specific human behavior. A behavior-to-speech system created based on this recognition method is also presented as a new application of this technology.

This paper proposes a system for quickly realizing a function for robustly detecting daily human activity events in handling objects in the real world. The system has three functions: 1) robustly measuring 3D positions of the objects; 2) quickly calibrating a system for measuring 3D positions of the objects; 3) quickly registering target activity events; and 4) robustly detecting the registered events in real time. As for 1), the system realizes robust measurement of 3D positions of the objects using an ultrasonic 3D tag system, which is a kind of a location sensor, and robust estimation algorithm known as random sample consensus (RANSAC). The paper evaluates the robustness by comparing RANSAC with a least-squares optimization method. As for 2), the system realizes quick calibration by a calibrating device having three or more ultrasonic transmitters. Quick calibration enables the system to be portable. As for 3), quick registration of target activity events is realized by a stereoscopic camera with ultrasonic 3D tags and interactive software for creating 3D shape model, creating virtual sensors based on the 3D shape model, and associating the virtual sensors with the target events. The system makes it possible to quickly create object-shaped sensors to which a new function for detecting activity events are added while maintaining the original functions of the objects.

This paper describes a middleware which the authors developed to implement distributed sensor networks. The authors have been developing sensorized environments which have hundreds of sensors and can monitor human daily activities in real time. All sensors in the environment should be connected and organized into a sensor network because no single sensor can cover the whole environment. The middleware developed by the authors supports easy implementation of such sensor network. The design and implementation of the middleware, especially the generic programming and pattern-oriented approach for I/O device handlers, are presented in this paper.

This paper describes an ultrasonic tagging system developed for robustly observing human activity in a living area. Using ultrasonic transmitter tags with unique identifiers, the system is shown through experimental application to be able to track the three-dimensional motion of tagged objects in real time with high accuracy, resolution and robustness to occlusion. The use of an ultrasonic system is desirable because of its low cost and use of commercial components, and the proposed system achieves high accuracy and robustness through the use of many redundant sensors. The system employs multilateration to locate tagged objects using one of two estimation algorithms, a least-squares optimization method or a random sample consensus method.

This paper presents a position estimation method for multiple ultrasonic emitters which are activated simultaneously. Locations of ultrasonic emitters are generally calculated from distance data obtained at receivers, but the emitters must be activated one after another to avoid crosstalk. Thus, the sampling rate for each emitter decreases as the number of emitters increases. The authors solved this problem by activating multiple emitters simultaneously and applying a newly developed position estimation algorithm. This paper presents the theoretical analysis and the results of simulations and experiments.

This paper describes the network implementation for SELF, Sensorized Environment for Life, which the authors are developing. SELF is an experimental sensorized environment to support healthcare. All sensors are embedded in the environment cleverly so human in SELF may not care for being monitored from the environment. To construct such an environment and make use of the information from sensors, every sensor should be connected with the others and, consequently, they should form a sensor network. In this paper, the outline of SELF itself is described briefly but not discussed in detail. The focus of this paper is the aspects of this sensor network in SELF.

This paper describes an intelligent environmental system, SELF (Sensorized Environment for Life), that enables a person to maintain his or her health through "self-communication." The system externalizes a "self" by storing personal data such as physiological status, analyzing it, and reporting useful information to assist the person, in maintaining his or her health. To establish the methodology to create such a system, this study analyzes and re-defines the self as an object of information processing. Self-communication is nothing but understanding ourselves objectively. It is not easy to put into practice because it requires a visualized or numerized representation of oneself. As an example of an externalized self, this study focused on the physiological status of a person. The physiological status is obtained as follows: SELF observes the person's behavior with distributed sensors invisibly embedded in the daily environment, extracts physiological parameters from it, analyzes the parameters, and accumulates the results. The accumulated results are used for reporting useful information to maintain the person's health. The authors constructed a model room for SELF consisting of a bed with pressure sensor array, a ceiling lighting dome with a microphone, and a washstand with a display. Fundamental results of self-externalization using SELF are presented.

The authors describes a concept and an implementation of a networked and sensorized environment which they are developing. They call this environment SELF, named after Sensorized Environment for Life. The main objective of SELF is to construct an environment which can support healthcare of not only aged but healthy people with the information accumulated by surrounding sensors installed in it. To equip such capabilities with the system, all sensors should be embedded in the environment and systematically form a sensor network. This paper outlines the concept of SELF and shows its current implementations.

This paper proposes a new method for monitoring normal breath sounds in a daily environment where many kinds of noises exist. In a typical conventional breath monitor, a thermistor, an accelerometer, or a contact-type microphone must be attached directly to a person's body such as a part around the nose and the mouth, or a part over the chest wall and the trachea. This paper focuses on key issues stemming from a factor of the environment: extraction of breath sounds from sensor signals contaminated by environmental noise; and realization of a monitoring system suitable for our homes. Features of normal breath sounds are clarified by frequency analysis. Based on the features, a method for extracting normal breath sounds is discussed. This paper also describes a ceiling dome microphone which is a kind of a parabolic sound concentrator. It realizes a function of detecting normal breathing sounds with high sensitivity while keeping a room's appearance natural. The gain obtained by such a concentrator is analyzed theoretically from the acoustic point of view. Experimental results proved the feasibility of the proposed method.

We develop a body parts position and posture estimation system. This system consists of a pressure sensor distributed bed and body parts position and posture estimation software. The computer constructs many pressure distribution images based on the simple human models and accumulates these images to its memory, called the model-based pressure image templates. The pressure distribution image through is compared with model-based pressure image templates to find out the most matched pressure image template. The model-based pressure image templates contain body parts positions and joint angles information, so the body parts position contacting with the bed can easily be estimated by using the most matched model-based pressure image template. Finally, an estimated posture is displayed as a 3D computer graphics image. An experimental result reveals that the system not only can display the estimated lying human posture intuitively, but can also estimate the lying human's body parts position accurately where the body parts contacts with bed.

The transmission control protocol (TCP) adopts some techniques that use network resources efficiently by estimating the characteristics and condition of the network. The slow-start algorithm is the primary technique for effective resource usage. The goal of slow-start is to establish a TCP connection in an optimum state for the network path quickly unless giving an excessive load to the network. However, in large-bandwidth with long-delay links such as satellite links, the slow-start algorithm does not work properly and causes substantial performance degradation. In this paper, we describe the problem of the current slow-start algorithm in large-bandwidth with long-delay networks. We propose a new slow-start algorithm that can increase network transfer performance for large bandwidth with long delay networks. We also implemented this algorithm on a network simulator for evaluation and it resulted in over a 60% efficiency compared to a normal slow start algorithm.

This paper proposes a function for monitoring a patient's respiration and posture in sleep using a human symbiosis system in a sickroom. The novel features of the system function lie in noninvasive and unrestrained monitoring to ensure the symbiosis with the human. Noninvasive monitoring eliminates the need for monitoring needles or catheters to invade the patient's body; sensors thus do not impose a physiological burden such as pain on the patient. In unrestrained monitoring, sensors and their electrical cords do not limit degrees of freedom of the patient's movement. Unrestrained sensing therefore does not impose a psychological burden caused by the limitations on the patient. A "robotic bed", which is a system to realize the functions stated above, is a bed-shaped system with 221 pressure sensors for monitoring the patient's respiration and posture without preventing doctors and nurses from performing their tasks. The sensors are set 5 cm from each other on the bed and surround the patient. Experiments to monitor respiration and posture in sleep demonstrate that the proposed function is feasible for monitoring for over 6 hours.

Understanding human intention is an essential function for a robot which can offer adequate support to human beings. It requires smooth communication between the human and the robot. Human behavior is an expressive media of communication. This paper proposes a new function of "active under standing of human intentions" by a robot through monitoring of human behavior. The unique feature of the proposed function lies in the fact that it utilizes multi-communication channels in parallel. i.e., human intentions are understood not only through conscious behavior but also through unconscious behavior. The paper also proposes a robot architecture to realize the function. The following points are the key features of the architecture: a robot possesses multi-sensors which surround the human; and information processing is carried out by dual loops-a loop for information exchange between the human and the robot and a loop for human intention understanding. As an example of a robot with human intention understanding functions, the authors constructed a micro-teleoperation robot. It can automatically understand an operator's intention through such unconscious behavior of touching a desk with an operator's hand. The understood result is utilized to change the control mode of a master-slave manipulation system from fine motion to rough motion and vice versa. The experimental results prove that the proposed function is effective in making the operation of the system easier. Consequently the system is friendly to the operator.>