Yasue Mitsukura

Bio: Yasue Mitsukura is an academic researcher from Keio University. The author has contributed to research in topics: Feature extraction & Face detection. The author has an hindex of 18, co-authored 352 publications receiving 2012 citations. Previous affiliations of Yasue Mitsukura include University of Tokushima & Tokyo University of Agriculture and Technology.

A high-speed brain speller using steady-state visual evoked potentials

Abstract: Implementing a complex spelling program using a steady-state visual evoked potential (SSVEP)-based brain–computer interface (BCI) remains a challenge due to difficulties in stimulus presentation and target identification. This study aims to explore the feasibility of mixed frequency and phase coding in building a high-speed SSVEP speller with a computer monitor. A frequency and phase approximation approach was developed to eliminate the limitation of the number of targets caused by the monitor refresh rate, resulting in a speller comprising 32 flickers specified by eight frequencies (8–15 Hz with a 1 Hz interval) and four phases (0°, 90°, 180°, and 270°). A multi-channel approach incorporating Canonical Correlation Analysis (CCA) and SSVEP training data was proposed for target identification. In a simulated online experiment, at a spelling rate of 40 characters per minute, the system obtained an averaged information transfer rate (ITR) of 166.91 bits/min across 13 subjects with a maximum individual ITR of 192.26 bits/min, the highest ITR ever reported in electroencephalogram (EEG)-based BCIs. The results of this study demonstrate great potential of a high-speed SSVEP-based BCI in real-life applications.

Region detecting method and region detecting apparatus

Abstract: To provide a region detecting method capable of setting a proper threshold independently of a photographing condition and moreover, quickly and accurately detecting a specific region, which uses an image data storing section 10 for storing a sample image 12 and a purposed image 11 , a first computing means 1 for obtaining the extraction-region-identifying threshold data for a plurality of sample images including a common extraction region but having average color values different from each other in accordance with a genetic algorithm and generating a threshold table 8 for the average color values, a second computing means 2 for adaptively computing the extraction-region-identifying threshold data for the purposed image 11 in accordance with the average color value of the purposed image and the threshold table 8 , and a third computing means 3 for detecting an extraction region in accordance with the threshold data computed by the second computing means 12.

A design of self-tuning PID controllers using a genetic algorithm

Abstract: A self-tuning PID controller design scheme is proposed, which is able to deal with systems with unknown or time-varying parameters. The proposed scheme is derived based on the relationship between PID control and generalized minimum variance control (GMVC) laws. Furthermore, a suitable set of some user-specified parameters included in the GMVC criterion is sought by using a genetic algorithm recursively. A numerical simulation example shows the effectiveness of the newly proposed control scheme.

Bimodal BCI Using Simultaneously NIRS and EEG

Abstract: Although noninvasive brain-computer interfaces (BCI) based on electroencephalographic (EEG) signals have been studied increasingly over the recent decades, their performance is still limited in two important aspects. First, the difficulty of performing a reliable detection of BCI commands increases when EEG epoch length decreases, which makes high information transfer rates difficult to achieve. Second, the BCI system often misclassifies the EEG signals as commands, although the subject is not performing any task. In order to circumvent these limitations, the hemodynamic fluctuations in the brain during stimulation with steady-state visual evoked potentials (SSVEP) were measured using near-infrared spectroscopy (NIRS) simultaneously with EEG. BCI commands were estimated based on responses to a flickering checkerboard (ON-period). Furthermore, an “idle” command was generated from the signal recorded by the NIRS system when the checkerboard was not flickering (OFF-period). The joint use of EEG and NIRS was shown to improve the SSVEP classification. For 13 subjects, the relative improvement in error rates obtained by using the NIRS signal, for nine classes including the “idle” mode, ranged from 85% to 53 %, when the epoch length increase from 3 to 12 s. These results were obtained from only one EEG and one NIRS channel. The proposed bimodal NIRS-EEG approach, including detection of the idle mode, may make current BCI systems faster and more reliable.

Generating visual flickers for eliciting robust steady-state visual evoked potentials at flexible frequencies using monitor refresh rate.

Abstract: In the study of steady-state visual evoked potentials (SSVEPs), it remains a challenge to present visual flickers at flexible frequencies using monitor refresh rate. For example, in an SSVEP-based brain-computer interface (BCI), it is difficult to present a large number of visual flickers simultaneously on a monitor. This study aims to explore whether or how a newly proposed frequency approximation approach changes signal characteristics of SSVEPs. At 10 Hz and 12 Hz, the SSVEPs elicited using two refresh rates (75 Hz and 120 Hz) were measured separately to represent the approximation and constant-period approaches. This study compared amplitude, signal-to-noise ratio (SNR), phase, latency, scalp distribution, and frequency detection accuracy of SSVEPs elicited using the two approaches. To further prove the efficacy of the approximation approach, this study implemented an eight-target BCI using frequencies from 8-15 Hz. The SSVEPs elicited by the two approaches were found comparable with regard to all parameters except amplitude and SNR of SSVEPs at 12 Hz. The BCI obtained an averaged information transfer rate (ITR) of 95.0 bits/min across 10 subjects with a maximum ITR of 120 bits/min on two subjects, the highest ITR reported in the SSVEP-based BCIs. This study clearly showed that the frequency approximation approach can elicit robust SSVEPs at flexible frequencies using monitor refresh rate and thereby can largely facilitate various SSVEP-related studies in neural engineering and visual neuroscience.

Machine learning

Abstract: Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

The Self-Organizing Map

Abstract: An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article.

A particle swarm optimization approach for optimum design of PID controller in AVR system

Abstract: In this paper, a novel design method for determining the optimal proportional-integral-derivative (PID) controller parameters of an AVR system using the particle swarm optimization (PSO) algorithm is presented. This paper demonstrated in detail how to employ the PSO method to search efficiently the optimal PID controller parameters of an AVR system. The proposed approach had superior features, including easy implementation, stable convergence characteristic, and good computational efficiency. Fast tuning of optimum PID controller parameters yields high-quality solution. In order to assist estimating the performance of the proposed PSO-PID controller, a new time-domain performance criterion function was also defined. Compared with the genetic algorithm (GA), the proposed method was indeed more efficient and robust in improving the step response of an AVR system.