We present acoustic event identification by integration of sound source separation and deep learning based on a convolutional neural network for extremely noisy acoustics signals captured with a 16 ch microphone array embedded in an Unmanned Aerial Vehicle (UAV).We showed that the proposed method can identify over 98% sound sources correctly for a 10 class classification task using 16 ch recorded sound data with a microphone array embedded in a quadrotor.

抄録全体を表示

I made attention to “crowd funding and micro investment” to support affected SMEs, after the Great East Japan Earthquake, and analyzed its system and the situation of the enterprise. It is useful to give encouragement (mentally) as well as to alleviate economic burden (economically). Participation by citizens and social contribution by the private company are also emphasized.

抄録全体を表示

This paper introduces the Romanian Host Town Project of Musashino City, Tokyo, aproject specially organized for the Tokyo 2020 Olympic and Paralympic Games. I report on my experience of visiting and acting as a cultural exchange delegate in Brasov,Romania, in order to shed light on Musashino’s ‘Romanian Host Town Project’, especially established for the 2020 Tokyo Olympic and Paralympic Games, and examine the current efforts and potential of the project. For this purpose, the paper looks back on the history of the relationship between Musashino in Japan and Brasov in Romania, which was originally established based on cultural exchange. I will show how Musashino intercultural exchange activities are often supported by its citizens, non-profit organizations, private-sector enterprises and schools. My observations and arguments are based on the power of ‘grassroots activities’ to reach out to citizens to obtain their understanding and support; this is the basis of Musashino municipal intercultural activities. I argue that the consortium among industry, government and academia is functioning effectively, especially in cultural exchange activities. In order to determine the extent to which citizens are aware and supportive of the project, I rely upon the municipal opinion poll. The opinion poll indicates promising results among the younger generations, but the project has yet to obtain wider recognition and support by the citizens for its intended purpose in 2020 and thereafter.

抄録全体を表示

This study applies behavior setting theory, and conducts an observation survey at ten-minute intervals of behavior mapping records by tracing the behavioral contents, interaction conditions and activity types of the elderly, trying to break down behavioral characteristics and an activity scale into two mixed-care day service centers (DSCs). Remarkable behavioral characteristics noted are as follows: Participants have various interests, particularly some less frail elderly whose interaction patterns are regarded as "active", and they are not satisfied with staying in one limited space all day long and require diverse activities. Participants with dementia, however, have interaction patterns that are "passive" and are often in a daze and do nothing when activities are held, showing a requirement for a place for wandering. Five items are presented as suggestions for the design of a mixed-care DSC: (1) Reducing the distance between user spaces when planning floor layouts; (2) Considering and offering the possibility of different activities and an activity scale held at the same time in the day room; (3) Designing in a manner that answers the need for wandering; (4) Providing ample and barrier-free spaces in corridors, passages and the courtyards, and (5) Providing plural toilets with easy access.

抄録全体を表示

This paper is concerned with an experimental modal analysis of a loudspeaker system. Based on Frequency Response Functions (FRFs) measured in about 500 points uniformly spaced on the front panel of the loudspeaker system several vibrations modes of the loudsneaker membranes have been found. Then, the vibrations of the loudspeaker membranes were compared with vibrations of the of the loudspeaker system. It has been shown that the vibrations of the loudspeaker case were very small relative to the vibration of the loudspeaker membranes. Thus, the loudspeaker , which may be considered as a set of vibrating plates, is rather a source of a very weak sound and may be neglected. It does not influence significantly on the acoustics field radiated by the loudspeaker system.

抄録全体を表示

This paper addresses bird song scene analysis based on semi-automatic annotation. Research in animal behavior, especially in birds, would be aided by automated or semi-automated systems that can localize sounds, measure their timing, and identify their sources. This is difficult to achieve in real environments, in which several birds at different locations may be singing at the same time. Analysis of recordings from the wild has usually required manual annotation. These annotations may be inaccurate or inconsistent, as they may vary within and between observers. Here we suggest a system that uses automated methods from robot audition, including sound source detection, localization, separation and identification. In robot audition, these technologies are assessed separately, but combining them has often led to poor performance in natural setting. We propose a new Spatial-Cue-Based Probabilistic Model (SCBPM) for their integration focusing on spatial information. A second problem has been that supervised machine learning methods usually require a pre-trained model, which may need a large training set of annotated labels. We have employed a semi-automatic annotation approach, in which a semi-supervised training method is deduced for a new model. This method requires much less pre-annotation. Preliminary experiments with recordings of bird songs from the wild revealed that our system outperformed the identification accuracy of a method based on conventional robot audition.^*

^* This paper is an extension of a proceeding of IROS2015.

抄録全体を表示

Background: Sedentary behaviors are prevalent among children and can have a detrimental effect on their health. Little is known about the influence of parental time on children’s sedentary behavior. This study examined the association between parental working hours and children’s sedentary time.

Methods: Cross-sectional data were drawn from the Japanese Study on Stratification, Health, Income, and Neighborhood (J-SHINE) in 2010 and 2011. Participants were 886 children aged 7–18 years and their parents. The primary outcome was self-reported sedentary time after school that comprised screen time and non-screen time. The main explanatory variable was parental working hours. We used multiple regression analysis adjusting for sociodemographic factors.

Results: Children’s mean sedentary time was 222 (standard deviation [SD], 123) min/day; 144 (SD, 108) min/day screen time and 78 (SD, 65) min/day non-screen time. Children whose mothers worked ≥20 hours/week had 28 (95% CI, 9 to 48) min/day longer sedentary time than children of homemakers (240 min/day vs 214 min/day). The longer maternal working hours, the longer sedentary time (P for trend <0.01). In contrast, children whose fathers worked ≥48 hours/week had 82 (95% CI, −156 to −7) min/day shorter sedentary time than children of non-working fathers (179 min/day vs 264 min/day). When limited to children whose fathers worked, there was no statistically significant association between children’s sedentary time and paternal working hours.

Conclusions: Children with mothers who work long hours or fathers not working tend to sit more. Supplementing the shortages in resources for childcare may be necessary among those families.

抄録全体を表示

This paper addresses Acoustic Event Identification (AEI) of acoustic signals observed with a microphone array embedded in a quadrotor that is flying in a noisy outdoor environment. In such an environment, noise generated by rotors, wind, and other sound sources is a big problem. To solve this, we propose the use of a combination of two approaches that have recently been introduced: Sound Source Separation (SSS) and Sound Source Identification (SSI). SSS improves the Signal-to-Noise Ratio (SNR) of the input sound, and SSI is then performed on the SNR-improved sound. Two SSS methods are investigated. One is a single channel algorithm, Robust Principal Component Analysis (RPCA), and the other is Geometric High-order Decorrelation-based Source Separation (GHDSS-AS), known as a multichannel method. For SSI, we investigate two types of deep neural networks namely Stacked denoising Autoencoder (SdA) and Convolutional Neural Network (CNN), which have been extensively studied as highly-performant approaches in the fields of automatic speech recognition and visual object recognition. Preliminary experiments have showed the effectiveness of the proposed approaches, a combination of GHDSS-AS and CNN in particular. This combination correctly identified over 80% of sounds in an 8-class sound classification recorded by a hovering quadrotor. In addition, the CNN identifier that was implemented could be handled even with a low-end CPU by measuring the prediction time.

抄録全体を表示

Reducing energy consumption in the residential sector is crucial for addressing global warming. This study aims to evaluate the reduction in residential energy consumption owing to changes in residents′ awareness and lifestyle. First, the power consumption of home electronics and the low-impact lifestyle recommended in 2010 were reviewed, and the annual reduction in electricity consumption by practicing low-impact lifestyle was defined as low-impact lifestyle point. Second, a questionnaire survey was conducted in Tokyo′s Meguro Ward to investigate the relation between the residents′ lifestyle and energy consumption. Results showed that the annual energy consumption decreased as the lifestyle points of the households increased. Finally, the effect of the Great East Japan Earthquake on residents′ awareness regarding energy was examined. More than 85% of the respondents were found to have experienced a change in their awareness toward energy and the average reduction rate was found to be 13%.

抄録全体を表示

High expectations are placed on the use of unmanned aerial vehicles (UAVs) in such tasks as rescue operations, which require a system that makes use of visual or auditory information to recognize the surrounding environment. As an example of such a system, this study examines the recognition of the environment using a helicopter mounted with a microphone array. Because the rotors of a helicopter generate high noise during operation, it is necessary to reduce the effects of this noise and those from other sources to record the audio signals coming from the ground with onboard microphones. In particular, because of helicopter body control, the rotor speed changes continuously and causes an unsteady rotor noise, which implies that it would be effective to arrange the microphones at a sufficient distance from the rotors. When a large microphone array is employed, however, the array weight may alter the helicopter’s flight characteristics and increase the noise, presenting a dilemma. This paper presents a model of rotor noise that takes into account the effect of the microphone array on the helicopter’s dynamic characteristics and proposes a method of evaluating the optimality of the array configuration, which is necessary for design. The validity of the proposed method is investigated using a multirotor helicopter mounted with a microphone array previously developed by the authors. In addition, an application example for locating sound sources on the ground using this helicopter is presented.

抄録全体を表示

We have studied on robot-audition-based sound source localization using a microphone array embedded on a UAV (unmanned aerial vehicle) to locate people who need assistance in a disaster-stricken area. A localization method with high robustness against noise and a small calculation cost have been proposed to solve a problem specific to the outdoor sound environment. In this paper, the proposed method is extended for practical use, a system based on the method is designed and implemented, and results of sound source localization conducted in the actual outdoor environment are shown. First, a 2.5-dimensional sound source localization method, which is a two-dimensional sound source localization plus distance estimation, is proposed. Then, the offline sound source localization system is structured using the proposed method, and the accuracy of the localization results is evaluated and discussed. As a result, the usability of the proposed extended method and newly developed three-dimensional visualization tool is confirmed, and a change in the detection accuracy for different types or distances of the sound source is found. Next, the sound source localization is conducted in real-time by extending the offline system to online to ensure that the detection performance of the offline system is kept in the online system. Moreover, the relationship between the parameters and detection accuracy is evaluated to localize only a target sound source. As a result, indices to determine an appropriate threshold are obtained and localization of a target sound source is realized at a designated accuracy.

抄録全体を表示

本研究の目的は，カナダの家庭科における多文化共生教育に関する学習指導について明らかにするこ とである。また，その結果を踏まえ，日本の中学校技術・家庭科家庭分野において多文化共生教育を実 践するための配慮点を把握することも目的とした。調査対象は，カナダ，ブリテッシュ・コロンビア州 の中等教育学校で家庭科を担当する教員６名である。授業観察と半構造化インタビュー調査を実施した。 その結果，家庭科において多文化共生教育を実践する上で，以下のような配慮点が示唆された。 家庭科（主に食生活の内容）の授業における配慮点： １．基本的食物としては，地域の食材や，個々の生徒が大切にしている家庭料理を取り上げる。 ２．世界に存在する共通の食べ物を教材とし，それらの類似点や相違点，相違点を生む要因を考察する。 ３．生徒が多様な文化に関する自分の知識や経験を話せる時間を設ける。 ４．文化の多様性を理解し合う機会をつくる。 ５．将来的にも多様性に対する開かれた目を持つことを目標とする。 他の国から来て間もない生徒に対する配慮点： １．異なる文化背景をもつ生徒がなじみやすく，在校する生徒も受け入れやすい授業環境づくりをする。 ２．転校してきた生徒には，世話係となる生徒をつける。 ３．翻訳教材や視覚教材を準備する。 ４．多様な学習活動や評価方法を取り入れ，新しく来た生徒が授業に積極的に関われる機会をつくる。 ５．語学援助教員と協働する。

抄録全体を表示

Predicting how the electric vehicle market will develop from now on is a very important issue for not only countries that have led the car market such as Japan but also for countries that are going to develop. Then, in order to predict the diffusion of electric vehicles, the diffusion speed and price transition of former cars was analyzed quantitatively, and research which clarifies the prediction method of the diffusion rate of a car was performed. The universal relation about the sale and diffusion of cars became clear by considering a technical element in it. Conventionally, the demand forecast of a new product was carried out after the sale start. Past experience and a specialist's opinion were adopted in part. In a prior study, it was shown clearly that there was great influence by the leading role of engineering development and production and sale of a key device in each product. The relationship means whether the process of technology development and production sales is initiated by the device manufacturer only or through collaboration with the product manufacturer. In this paper, the results could be extended to the auto industry and so the same tendency was observed. Furthermore, the results were applied to predicting diffusion and the price of an electric vehicle, and if the problems, which were the interference of the present diffusion, can be solved, the earliness of diffusion and transition of the price of an electric vehicle could be decided by the development speed of the battery. The problems were both the short mileage from one charge and the more expensive price in comparison a common vehicle. According to the result of consumer electronics apparatus, the case was that 20 % of diffusion will be carried out in about 5 years after sales start, and the prices at that time are 50 % or less compared with a start price.

抄録全体を表示

The "National Council on Educational Reform" was set up as an ad hoc advisory committee to the Prime Minister. The Council's purpose is to propose measures to meet the needs of a highly developed information society of the 21st century. Educational reform is in progress at each level from kindergarten to graduate school in Japan based on the report of the Council. The main aim of the reports of the National Council on Educational Reform is transforming Japanese education from that which centers on formal education at schools to one that will continue on into life-long study. The idea of the intelligent school was proposed by the Council as the school of the future. An intelligent school aims that: (1) School equipment should be appropriate for a highly developed information society. (2) Education in schools should be transformed from teacher-centered education to learner-centered education. (3) Facilities and equipment at schools are to be shared by those receiving formal school education and those in life-long study. This paper describes the outline of the intelligent school as written in the report of the National Council on Educational Reform. This paper will also give a brief outline of Namerikawa lower secondary school in Toyama Prefecture, which is the first intelligent school in Japan constructed following the guidelines set by the National Council on Educational Reform.

抄録全体を表示

No discussion of play and leisure in Japan would be complete without acknowledging the place of pachinko, a game so popular that it dominates the leisure economy in a way no other medium does, not even videogames. Even in decline, pachinko generates more revenue in Japan than any other leisure pursuit and yet it is rarely discussed in game studies in the West or even in the Japanese literature around game culture. This is largely because of the gambling associated with pachinko and because it is unique to Japan – a national industry with no export potential. Pachinko is at the disreputable edge of gaming—economically, culturally, and mechanically. Above all, pachinko machines stand out as monstrous hybrids that combine the electro-mechanical apparatus of a pinball machine with the digital screen of a slot machine in a curious mixed interface that seems to be an anachronism of a pre-computing era. And that is what this paper is about – the hybrid interface of pachinko.

抄録全体を表示

It is becoming clear that simulated outings in virtual reality (VR) can help alleviate psychiatric symptoms and improve cognitive function in adult patients and the aged. However, conventional VR simulated experiences using head-mounted displays, which are goggle-type devices, have a major issue in that they can only be experienced by one person and do not allow communication with others. Therefore, in this study, we developed a sharing system for VR simulated experiences that incorporates an element of communication with familiar people and created VR content including memorable places for hospitalized patients. We then investigated how hospitalized patients react when experiencing the content of their own memorable places. As a result, conversations about recalling the past were generated during the experience, indicating that the system and content developed in this study may help prevent dementia and improve the negative symptoms associated with schizophrenia.

抄録全体を表示

The infection control measures taken by the Japanese government due to the COVID-19 pandemic have severely affected events organizations. Based on an online survey conducted from March 16 to 19, 2021, this paper discusses the behavior and consciousness of event participants under Japan’s infection control measures of “self-restraint”. The survey targeted the period between the first declaration of the state of emergency and the end of the second declaration in Japan. We analyzed the varying effects of calls for self-restraint on participation in different events at each stage of the pandemic policy, and the factors influencing continued participation in face-to-face events. Event management is a typical case where ordinary people react to and challenge the government’s infection control measures. Our survey revealed the effects of the government’s requests for “self-restraint”. However, its impact differed among different types of events. The effectiveness of the request for “selfrestraint” varies with the degree to which people were committed to event participation.

抄録全体を表示