Naoaki ITAKURA (板倉 直明)

Offer Organization: 日本学術振興会, System Name: 科学研究費助成事業, Category: 基盤研究(C), Fund Type: -, Overall Grant Amount: - (direct: 3600000, indirect: 1080000)
本研究の目的は、携帯端末利用時の生理的振戦から、呈示画面情報に対する興味度を推定し、その情報を収集するシステムを開発することである。携帯端末等で情報を取得する機会が増加した現在、個人特定に繋がらない生理的振戦で興味度推定が実現できれば、その利用価値は大きい。また、携帯端末を用いて、様々な状況や姿勢において生理的振戦を測定する研究は、アルコールや薬などの摂取が人間の運動制御系へ与える問題など、人の運動制御系を評価する新たな応用研究に繋がる。
令和５年度においては、最初に、生理的振戦とスマートフォンの画面操作の両方を用いて、興味度推定が出来るかを検討した。その結果、生理的振戦においてピーク周波数の最大振幅値が小さい時に興味あるページと答えた割合が80.6％となった。一方、画面操作において、スワイプ移動距離の変化割合が少ない時に興味あるページと答えた割合が76.5％となった。両者とも一致した割合は72.1％であり、より確実に興味あるページを抽出できる可能性を示した。また、画面操作が生理的振戦の測定結果に影響を与えているかを、画面操作ありの場合となしの場合で比較した結果、生理的振戦の測定値には影響を与えていないことも確認した。
次に、スマートフォンの持ち方により、得られる生理的振戦の特徴が変化するかも検討した。比較した持ち方として、肘を体に付けて肘から先を角度0度と45度にした場合、肘を机に付けて肘から先を角度0度と45度にした場合で比較した。肘を体に付けた状態では、生理的振戦のピーク周波数は変わらないがその最大振幅は、角度0度は角度45度の平均約1.7倍となった。一方、肘を机に付けた状態では、生理的振戦のピーク周波数は、角度0度は角度45度の平均約2.3倍となり、最大振幅値は僅かに角度0度の方が大きくなった。

Offer Organization: Japan Society for the Promotion of Science, System Name: Grants-in-Aid for Scientific Research, Category: Grant-in-Aid for Scientific Research (C), Fund Type: -, Overall Grant Amount: - (direct: 3000000, indirect: -)
In this study, we developed the road traffic simulator "MITRAM" for the analysis of traffic congestion by employing fuzzy reasoning, and carried out simulation analysis for four problems.
First, we verified the driving model with the theoretical values of traffic engineering and field data, and obtained reasonable results. The driving model consists of vehicle-following model, right-turn model and signal-intersection model. Moreover, we also verified that when a large number of vehicles are generated, the MITRAM offers general traffic rules and characteristics.
Next, we applied the MITRAM to the following research applications.
1.In order to feed the sensor data from real traffic directly into the MITRAM, we constructed an intersection network model. We applied the model to the MITRAM and simulated the traffic of a relatively large area modeling the 41 intersections in the city area of Kochi-shi. It is confirmed that the simulation results are accurate and reproducible. In addition, we quantitatively verified that flatting the traffic demand due to off-peak is effective for reducing the congestion.
2.We added the function of emission estimation of NO_x (oxides of nitrogen) and CO_2 from the traffic data in the MITRAM. We carried out road traffic simulation for the city area of Chofu-shi and obtained the amount of air pollution emission at the several points of the city area. The result showed that it is possible to understand the relationships between the amount of emission and traffic signal control by using the function.
3.It is a significant problem that railway crossings in city areas hinder surrounding road traffic. One solution for this is to install traffic signals. We carried out simulation analysis for the railway crossing area of the first Keihin national road near Kamata station of Keihin express. We confirmed that the installation of traffic signals increased the traffic capacity by 60% ; thus, it is very effective for reducing the congestion.
4.We added the function of route choice into vehicles. We carried out simulation analysis to examine whether providing traffic information to each vehicle is effective for reducing the congestion and causes a new congestion in the surrounding area. The result showed that traffic information significantly affected the traffic flow. We confirmed that traffic information is useful for reducing congestion while it propagates some congestion to the surrounding roads.

Offer Organization: Japan Society for the Promotion of Science, System Name: Grants-in-Aid for Scientific Research, Category: Grant-in-Aid for Scientific Research (C), Fund Type: -, Overall Grant Amount: - (direct: 3700000, indirect: -)
1.The effects of breathing exercise : Breathing exercise were carried out once a week.
Exercise time was one and half hours. It continued five years. The heart rate and blood pressure were measured almost every times. The flexibility, body fat, stature, bone density were measured several times in a year. Stature grew taller than before exercise and the difference was statistically significant. Flexibility increased after exercise, it was high significant. Bone density was not significant.
2.The breathing of shooting : we analyzed breathing at the time of shooting of Lanny Bassham who are world and Olympic champion.
3.Swimming and breathing, Dance and breathing, Gymnastic and breathing
4.On the influence of breathing method on change of center of gravity of body during standing posture
5.Questionary survey about an effects of breathing method to perform before a class
6.Education of Breathing : Kataoka give some lectures at 4^ International Summer Course for P.E.Teachers in Estonia, 5^ International Seminar for P.E.Teacheres in Finland(2004), 5^ International Summer Course for P.E.Teachers in Estonia(2005)

Offer Organization: Japan Society for the Promotion of Science, System Name: Grants-in-Aid for Scientific Research, Category: Grant-in-Aid for Scientific Research (C), Fund Type: -, Overall Grant Amount: - (direct: 3500000, indirect: -)
The research was performed to develop the artificial neural network models for explaining and resolving the mammalian brain function. We proposed the covariance field neural network model which is a natural extension of the classical analogue neural network model, and gives a mean field approximation to Markov random fields. The covariance field neural network can represent the covariance of spike timing as the phase difference, which is important in brain information processing, and can perform information processing based on spike timing. As a mean field approximation it gives much better approximation accuracy for Markov random fields even for the large weight strength compared with the naive mean field model. We performed computer experiments to support this. We also applied this model to image segmentation, and confirmed the segmentation capability with phase-difference. We proposed the mean field learning for Boltzmann machine, and performed some fundamental experiments to confirm the quick training speed for the phase.
On the other hand, we proposed the efficient learning methods for neural netoworks, especially for the recently highlighted support vector machine(SVM). We extended SVM learning to the efficient multi-class algorithm, and apply the second order cone programming method to SVM learning. In addition we proposed the maximal margin classifier based on the geometric method, which behaves faster than the quick SVM known as SMO. Finally we proposed a new learning machine based on the kernel PCA, which can automatically determine the kernel parameter so that it can realize the no free parameter learning machine.

Offer Organization: Japan Society for the Promotion of Science, System Name: Grants-in-Aid for Scientific Research, Category: Grant-in-Aid for Scientific Research (C), Fund Type: -, Overall Grant Amount: - (direct: 3000000, indirect: -)
As a new methodology of intelligent system, we have proposed an pattern information based active learning method (PBALM), which has a non-exact processing nature without complex computational formulas. The PBALM is formed on the basis of fuzzy concepts, striving for human-like information processing. Typical fuzzy rules. On the other hand, the PBALM features are ambiguous pattern processings. This simulates human brain nature in the modeling of processing information in pattern-like images rather than utilizing numerical interpretations, when humans acquire knowledge from complex targets.
The PBALM has plural processing units called IDS's, which are tasked with extracting useful information from a system subject to modeling. In order to realize an PBALM system which is capable of performing complex, large scale modeling with an excellent fault tolerant architecture, dedicated hardware for IDS is indispensable. For the purpose of developing such an intelligent hardware system, we tentatively designed an IDS hardware unit using an evaluation board available on the market, and verified how effective it would be.
Because we confirmed the effectiveness of dedicated IDS hardware with the evaluation board, we developed a new IDS processing unit called 'HIDS'. We designed a printed circuit board on which an IDS controller which ran at 100MHz, were mounted. In performance test results, in spite of the parallelization of only four HIDS boards, the performance of HIDS was far superior in the processing time in comparison to that of the software-based PBALM. By using HIDS units that we developed in this project, the PBALM system would be applied to modeling and control applications under demanding realtime conditions.