著者
Theerawit Wilaiprasitporn Alexandru Popovici Tohru Yagi
出版者
一般社団法人 電気学会
雑誌
電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)
巻号頁・発行日
vol.136, no.9, pp.1312-1317, 2016-09-01 (Released:2016-09-01)
参考文献数
8

In this study, we propose a hybrid brain/blink computer interface based on a single-channel electroencephalography (EEG) amplifier. Eyelid closing and hard blink were selected as two possible inputs for control of the interface. A 2-min calibration was required before starting to use the interface. An algorithm for feature extraction and classification was developed for EEG signals from eyelid closing, hard blink, and resting. To evaluate the performance of the interface, we incorporated it into a personal identification number (PIN) application, in both visual and auditory modes. Experiments with 5 healthy participants revealed that the PIN application based on the interface achieved a mean accuracy of 97.40%. In conclusion, we expect that our investigation will contribute to hybrid brain-computer interface research and technologies in the near future.
著者
Theerawit Wilaiprasitporn Tohru Yagi
出版者
一般社団法人 電気学会
雑誌
電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)
巻号頁・発行日
vol.136, no.9, pp.1277-1282, 2016-09-01 (Released:2016-09-01)
参考文献数
24
被引用文献数
2

Here we report the development of a personal identification number (PIN) application using a P300-based brain-computer interface (BCI). We focused on visual stimulation design for increasing the evoked potential in the brain. Single-channel electroencephalography and a computationally inexpensive algorithm were used for P300 detection. Experimental results showed that our proposed stimulus induced higher P300 amplitude than did a conventional stimulus. For a performance evaluation, we compared two versions of the proposed application, which were based on our ‘original P300 BCI’ and ‘adaptive P300 BCI’. In the adaptive P300 BCI, we introduced a novel algorithm for P300 detection to improve the information transfer rate while maintaining acceptable accuracy. Experiments with 10 healthy participants revealed that the original P300 BCI achieved mean accuracy of 83.50% at 11.40 bits/min and the adaptive version achieved mean accuracy of 86.00% at 18.63 bits/min.
著者
福田 敏男 湧田 雄基 長谷川 泰久 新井 史人 川口 三夫 野田 明子
出版者
一般社団法人 電気学会
雑誌
電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)
巻号頁・発行日
vol.125, no.1, pp.43-49, 2005 (Released:2005-04-01)
参考文献数
45
被引用文献数
1 9

In this paper, we propose an algorithm to estimate sleep quality based on a heart rate variability using chaos analysis. Polysomnography(PSG) is a conventional and reliable system to diagnose sleep disorder and to evaluate its severity and therapeatic effect, by estimating sleep quality based on multiple channels. However, a recording process requires a lot of time and a controlled environment for measurement and then an analyzing process of PSG data is hard work because the huge sensed data should be manually evaluated. On the other hand, it is focused that some people make a mistake or cause an accident due to lost of regular sleep and of homeostasis these days. Therefore a simple home system for checking own sleep is required and then the estimation algorithm for the system should be developed. Therefore we propose an algorithm to estimate sleep quality based only on a heart rate variability which can be measured by a simple sensor such as a pressure sensor and an infrared sensor in an uncontrolled environment, by experimentally finding the relationship between chaos indices and sleep quality. The system including the estimation algorithm can inform patterns and quality of own daily sleep to a user, and then the user can previously arranges his life schedule, pays more attention based on sleep results and consult with a doctor.
著者
平田 貴臣 呉本 尭 大林 正直 間普 真吾 小林 邦和
出版者
一般社団法人 電気学会
雑誌
電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)
巻号頁・発行日
vol.136, no.3, pp.348-356, 2016-03-01 (Released:2016-03-01)
参考文献数
16
被引用文献数
2

Since 1970s, linear models such as autoregressive (AR), moving average (MA), autoregressive integrated moving average (ARIMA), etc. have been popular for time series data analyze and prediction. Meanwhile, artificial neural networks (ANNs), inspired by connectionism bio-informatics, have been showing their powerful abilities of function approximation, pattern recognition, dimensionality reduction, and so on since 1980s. Recently, deep belief nets (DBNs) which use multiple restricted Boltzmann machines (RBMs) and multi-layered perceptron (MLP) are proposed as time series predictors. In this study, a hybrid prediction method using DBNs and ARIMA is proposed. The effectiveness of the proposed method was confirmed by the experiments using CATS benchmark data and chaotic time series data.
著者
宇野 達也 小圷 成一 平田 廣則
出版者
一般社団法人 電気学会
雑誌
電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)
巻号頁・発行日
vol.116, no.10, pp.1183-1187, 1996-09-20 (Released:2008-12-19)
参考文献数
11

It is difficult to decide the optimal neural network structure for a particular problem. We propose a solution to this problem, a new constructive learning algorithm based on division of a given learning problem. The proposed method first decomposes the original learning problem into small pieces and constructs a set of small networks which independently learn one of decomposed problems. It constructs a large network which learns the given learning problem by combining the small networks in a bottom-up manner. We demonstrate the efficiency of our learning algorithm by applying it to XOR, 3-bits parity, a non-liner function approximation, and two-spirals problem. Experimental results show that our learning algorithm can construct networks which have higher learning convergence rate and better generalization capability within less computation time than the standard back-propagation algorithms.
著者
神谷 昭基 小野 功 小林 重信
出版者
一般社団法人 電気学会
雑誌
電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)
巻号頁・発行日
vol.117, no.7, pp.829-836, 1997-06-20 (Released:2008-12-19)
参考文献数
13

Start-up scheduling is aimed at minimizing the start-up time while limiting turbine rotor stresses to an acceptable level. This scheduling problem has a wide search space. In order to improve the search efficiency and robustness and to establish an adaptive search model, we propose to integrate evolutionary computation, based on Genetic Algorithms (GA), with reinforcement learning. The strategies with our proposal include: multi-boundary-based enforcement operator and multi-elitist plan. By setting a second boundary, located right outside the existing boundary containing those feasible schedules, we extend our proposed enforcement operator and the conventional elitist plan into the multi-boundary-based enforcement operator and multi-elitist plan. These two strategies work together to focus the search along the boundary, around which the optimal schedule is supposed to exist, so as to increase the search efficiency as well as its robustness. During a search process, GA guides the reinforcement learning to concentrate its learning on those promising areas instead of the entire space. In return, reinforcement learning can generate a good schedule, in the earlier stage of the search process. We obtain encouraging test results. In this paper, we propose the GA-based search model with these strategies and discuss the test results.
著者
宇野 達也 小圷 成一 平田 廣則
出版者
一般社団法人 電気学会
雑誌
電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)
巻号頁・発行日
vol.118, no.3, pp.326-332, 1998-03-01 (Released:2008-12-19)
参考文献数
15

We propose a new ANN learning algorithm based on hierarchical clustering of training data. The proposed algorithm first constructs a tree of sub-learning problems by hiearchically clustering given learning patterns in a bottom-up manner and decides a corresponding network structure. The proposed algorithm trains the whole network giving teacher signals of the original learning problem to the output units, and trains sub-networks giving teacher signals of the divided sub-learning problems to the hidden units simultaneously. The hidden units which learn sub-learning problems become feature detectors, which promote the learning of the original learning problem. We demonstrate the advantages of our learning algorithm by solving N-bits parity problems, a non-liner function approximation, iris classification problem, and two-spirals problem. Experimen-tal results show that our learning algorithm obtains better solutions than the standard back-propagation algorithms and one of constructive algorithms in terms of the learning speed and the convergence rate.
著者
小林 隆 薦田 憲久
出版者
一般社団法人 電気学会
雑誌
電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)
巻号頁・発行日
vol.124, no.5, pp.1068-1075, 2004 (Released:2004-08-01)
参考文献数
13
被引用文献数
1 4 7

The traditional business process design methods, in which the usecase is the most typical, have no useful framework to design the activity sequence with. Therefore, the design efficiency and quality vary widely according to the designer’s experience and skill.  In this paper, to solve this problem, we propose the business events and their state transition model (a basic business event model) based on the language/action perspective, which is the result in the cognitive science domain. In the business process design, using this model, we decide event occurrence conditions so that every event synchronizes with each other. We also propose the design pattern to decide the event occurrence condition (a business event improvement strategy). Lastly, we apply the business process design method based on the business event model and the business event improvement strategy to the credit card issue process and estimate its effect.
著者
Atsushi Shimada Vincent Charvillat Hajime Nagahara Rin-ichiro Taniguchi
出版者
一般社団法人 電気学会
雑誌
電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)
巻号頁・発行日
vol.133, no.1, pp.142-149, 2013-01-01 (Released:2013-01-01)
参考文献数
9

Clickable Real World is a new framework to realize an intuitive information search with a mobile terminal. To achieve the goal, we tackle two challenging tasks. One is landmark detection from an observing scene. Our approach detects a landmark based on an image prior. The prior is not given manually. Instead, it is generated automatically from the training samples collected from photo sharing website. Another challenging task is image annotation assisted by geolocation. We use the location of a user who uses a mobile terminal, and geolocation where the training sample images were taken. Two probabilistic models are generated to achieve image annotation. One is image-based labeling which utilizes the co-occurrence between image features and label features. The other is label-based localization which uses the consensus about the label given around the geolocation among photographers. We combine two probabilistic approaches to improve the accuracy of image annotation. We demonstrate this approach for 87 scenes in the world.
著者
上平 裕太 大山 航 若林 哲史 木村 文隆
出版者
一般社団法人 電気学会
雑誌
電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)
巻号頁・発行日
vol.134, no.12, pp.1809-1816, 2014 (Released:2014-12-01)
参考文献数
15

This paper proposes a signature verification technique called combined segmentation-verification based on off-line features and on-line features. We use three different off-line feature vectors extracted from full name Japanese signature image and from the sub-images of the first name and the last name. The Mahalanobis distance for each off-line feature vector is calculated for signature verification. The on-line feature based technique employs dynamic programming (DP) matching technique for time series data of the fullname signature and first name and last name. The final decision (verification) is performed by SVM (Support Vector Machine) based on the three Mahalanobis distances and three dissimilarity of the DP matching. In the evaluation test the proposed technique achieved 3.35% EER (Equal Error Rate) with even FRR (False Acceptance Rate) and FAR (False Rejection Rate), which is 3.10% lower than the best EER obtained by the individual technique. This result shows that the proposed combined segmentation-verification approach improves Japanese signature verification accuracy significantly.
著者
綿貫 卓也 野澤 昭雄
出版者
一般社団法人 電気学会
雑誌
電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)
巻号頁・発行日
vol.134, no.10, pp.1551-1556, 2014 (Released:2014-10-01)
参考文献数
12
被引用文献数
2 4

In this research, mode of viewing, preference, and excitement-calm to TV contents were estimated from the hemodynamics parameter to create the estimation model. As physiology indices, the cardiovascular system was assessed by mean blood pressure (MP), heart rate (HR), stroke volume (SV), cardiac output (CO), and total peripheral resistance (TPR). Comfortable, arousal, vigor, preference and concentration to TV contents were assessed by visual analog scale (VAS) for mental indices. Psychological excitement-calm to TV was assessed by up and down arrow key of a keyboard in real time. Based on the above indices, the estimation model was created by using the neural network. As a conclusion, the distinction rate of the preference and the mode of viewing were each obtained to 83.3% and 75.0% at the maximum. The average error of the excitement-calm was obtained to 17%。
著者
小池 将史 内田 雅文 野澤 昭雄
出版者
一般社団法人 電気学会
雑誌
電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)
巻号頁・発行日
vol.134, no.10, pp.1531-1536, 2014 (Released:2014-10-01)
参考文献数
24

The aim of this research was development of emotion still camera. Emotion still camera is used to record the image of KANSEI of the photographer at the moment of shooting a photograph. Physiological and psychological measurements of the photographer were performed at the moment of the photography. Three situations where photographer generally took a photograph were defined. The three situations had the time factor, the spatial factor and the psychological factor. Blink and peripheral skin temperature (PST) and heart rate (HR) and pupil diameter were measured with camera operation. KANSEI was evaluated by the physiological - psychological indices.  There was more the number of blinks in the time factor than general number of blinks. The average of PST in the time factor fell in comparison with the usual PST of the photographer. The average of HR in the time factor was increased in comparison with others. It was thought that the result was caused by the sympathicotonia of photographer strained by the time factor.
著者
水田 孝信 和泉 潔 八木 勲 吉村 忍
出版者
一般社団法人 電気学会
雑誌
電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)
巻号頁・発行日
vol.133, no.9, pp.1694-1700, 2013-09-01 (Released:2013-09-01)
参考文献数
15

We built an artificial market model and compared effects of price variation limits, short sell regulations and up-tick rules. In the case without the regulations, the price fell to below a fundamental value when economic bubble bursts occurred. On the other hand, in the case with the regulations, this over-shooting did not occur and the market was more effective. However, the short sell regulation and the up-tick rule caused the trading prices to be higher than the fundamental value. To summarize these points, the price variation limits have the potential to make the market more effective. We also surveyed an adequate limitation price range and an adequate limitation time span for the price variation limit and found a parameters' condition of the price variation limit to prevent the over-shoots.
著者
新井 康平 矢島 健郎
出版者
一般社団法人 電気学会
雑誌
電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)
巻号頁・発行日
vol.128, no.11, pp.1679-1686, 2008-11-01 (Released:2008-11-01)
参考文献数
31
被引用文献数
5 9

A communication aid with human eyes only is proposed. A set of candidate character is displayed onto computer screen of relatively small and light Head Mount Display: HMD that is mounted on glasses of which user wears on. When user looks at a candidate character with his/hers left eye while right eye picture is taken with small and light web camera that also is mounted on the glasses. The proposed system can selects 81 characters with two layers of 9 by 9 character candidate image. Other than these there is another selective image including control keys and frequently use of sentences. By using image matching between previously acquired template image for each candidate character and the currently acquired image, the proposed system realizes that which character in the candidates is selected. By using blinking and fix one's eye on combine together, the proposed system recognizes that user determines the selected key from the candidates. The blinking detection method employs a morphologic filter to avoid misunderstanding of dark eye detection due to eyebrows and shadows. Thus user can input sentences. User also may edit the sentences and then the sentences are read with Text to Speech: TTS software tool. Thus the system allows support conversations between handicapped and disabled persons without voice and the others peoples because only the function required for conversation is human eyes. Also the proposed system can be used as an input system for wearable computing systems. Test results by the 6 different able persons show that the proposed system does work with acceptable speed, around 1.5 second / character.
著者
岩倉 友哉 岡本 青史 淺川 和雄
出版者
一般社団法人 電気学会
雑誌
電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)
巻号頁・発行日
vol.130, no.1, pp.83-91, 2010-01-01 (Released:2010-01-01)
参考文献数
26
被引用文献数
2

AdaBoost is a method to create a final hypothesis by repeatedly generating a weak hypothesis in each training iteration with a given weak learner. AdaBoost-based algorithms are successfully applied to several tasks such as Natural Language Processing (NLP), OCR, and so on. However, learning on the training data consisting of large number of samples and features requires long training time. We propose a fast AdaBoost-based algorithm for learning rules represented by combination of features. Our algorithm constructs a final hypothesis by learning several weak-hypotheses at each iteration. We assign a confidence-rated value to each weak-hypothesis while ensuring a reduction in the theoretical upper bound of the training error of AdaBoost. We evaluate our methods with English POS tagging and text chunking. The experimental results show that the training speed of our algorithm are about 25 times faster than an AdaBoost-based learner, and about 50 times faster than Support Vector Machines with polynomial kernel on the average while maintaining state-of-the-art accuracy.
著者
鈴木 新 劉 和輝 金井 伸行
出版者
一般社団法人 電気学会
雑誌
電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)
巻号頁・発行日
vol.131, no.9, pp.1559-1563, 2011-09-01 (Released:2011-09-01)
参考文献数
16

This paper proposes a method for estimation of a body temperature by using a relation between the upper arm temperature and the atmospheric temperature. Conventional method has measured by armpit or oral, because the body temperature from the body surface is influenced by the atmospheric temperature. However, there is a correlation between the body surface temperature and the atmospheric temperature. By using this correlation, the body temperature can estimated from the body surface temperature. Proposed method enables to measure body temperature by the temperature sensor that is embedded in the blood pressure monitor cuff. Therefore, simultaneous measurement of blood pressure and body temperature can be realized. The effectiveness of the proposed method is verified through the actual body temperature experiment. The proposed method might contribute to reduce the medical staff's workloads in the home medical care, and more.
著者
小野 眞 岩田 尚史 馬場 毅 金子 俊一
出版者
一般社団法人 電気学会
雑誌
電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)
巻号頁・発行日
vol.130, no.8, pp.1404-1410, 2010-08-01 (Released:2010-08-01)
参考文献数
21

Control charts are widely applied to monitoring quality variation from stable status to instable status in many manufacturing lines. Large-scale integrated circuit(LSI) manufacturing requires to monitor thin film thicknesses, circuit pattern dimensions, particle count on a wafer and so on. This paper proposes a new monitoring method for particles on a wafer. If particles induce random location based on Poison distribution, the c-chart is applicable. However, actual particle generation is not dependent of Poison distribution and then the c-chart indicates many false alarms. The proposed method predicts particle-limited yield to apply the p-chart to monitoring particle data. The method uses data outputted by a particle inspection tool such as a particle location and a scattered light intensity with respect to each particle. Experiments show that the method reduces false alarms.
著者
安井 一真 宇都宮 陽一 奥田 隆史
出版者
一般社団法人 電気学会
雑誌
電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)
巻号頁・発行日
vol.143, no.12, pp.1145-1153, 2023-12-01 (Released:2023-12-01)
参考文献数
25

Outdoor play is important for children because it is fun, improves communication, and provides adequate exercise. In addition, the environment and conditions for traditional play have changed due to the coronavirus pandemic, making it necessary to consider new rules of play. In this study, we focus on tag, one of the games, and consider rules that can reduce the differences in physical advantage and disadvantage due to foot speed. In this study, we consider three rules. (1) the “number selection behavior” rule (R1-1), in which the chaser actively pursues the runner who has been the chaser less frequently; (2) the “replacement condition A” (R2-1), in which the replacement condition between the chaser and the runner is multiple touches; and (3) the “replacement condition B” (R2-2), in which the replacement condition between the chaser and the runner is one touch and a rock-paper-scissors victory by the chaser. We analyze the effects of these three conditions on the game of tag using multi-agent simulation.
著者
三好 孝典 加藤 勇夫 松本 勉
出版者
一般社団法人 電気学会
雑誌
電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)
巻号頁・発行日
vol.143, no.11, pp.1056-1061, 2023-11-01 (Released:2023-11-01)
参考文献数
10

Control systems such as factory production systems and mobility systems require countermeasures to prevent serious physical damage from cyber-attacks. Although there have been reported cases of attacks such as installation of unauthorized devices in internal networks and physical tampering with vehicle networks, sufficient countermeasures have not yet been taken in the control systems currently in operation. In this paper, we propose a method to detect network route tampering by adding calculation and communication functions for network tampering detection to devices and components that make up bus-type networks commonly used in field networks. The proposed method makes it possible to detect anomalies caused by network route tampering without changing the specifications of field devices and with minimal impact on communication performance on the field network.