http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Condition Monitoring of Railway Vehicle Suspension Using Adaptive Multiple Model Approach
Hitoshi Tsunashima,Hirotaka Mori 제어로봇시스템학회 2010 제어로봇시스템학회 국제학술대회 논문집 Vol.2010 No.10
This paper demonstrates the possibility to detect suspension failures of railway vehicles using a multiple-model approach from on-board measurement data. The railway vehicle model used includes the lateral and yaw motions of the wheelsets and bogie, and the lateral motion of the vehicle body, with sensors measuring the lateral acceleration and yaw rate of the bogie, and lateral acceleration of the body. The detection algorithm is formulated based on the Interacting Multiple-Model (IMM) algorithm adding a method updating estimation model. The IMM method has been applied for detecting faults in vehicle suspension systems in a simulation study. The mode probabilities and states of vehicle suspension systems are estimated based on a Kalman filter (KF). This algorithm is evaluated in simulation examples. Simulation results indicate that the algorithm effectively detects on-board faults of railway vehicle suspension systems in realistic situation.
Evaluation of pleasant and unpleasant emotions evoked by visual stimuli using NIRS
Kazuki Yanagisawa,Hitoshi Tsunashima 제어로봇시스템학회 2015 제어로봇시스템학회 국제학술대회 논문집 Vol.2015 No.10
A relation between a level of brain activity and pleasant and unpleasant emotions has been studied using Near-infrared Spectroscopy (NIRS). In this study, the relation between the brain activity and the pleasant and unpleasant emotions was evaluated using International Affective Picture System (IAPS) and NIRS. Based on the NIRS recording for 21 participants, the effect of pleasant and unpleasant emotion on the brain activity was measured. The detection of pleasant and unpleasant emotion from NIRS signal was conducted using Neural Network. It was shown that the pleasant and unpleasant emotion can be detected with the accuracy of 96% (the highest) and 75% (average).
Multichannel Temporal Data Classification of Motor Imagination Using fNIRS
Sei Takahashi,Hideo Nakamura,Hitoshi Tsunashima 제어로봇시스템학회 2010 제어로봇시스템학회 국제학술대회 논문집 Vol.2010 No.10
We describe classification of functional near-infrared spectroscopy (fNIRS) data acquired during finger tapping imagery tasks performed by a human subject, using an artificial neural network designed for image sequence recognition. Our goal is to develop a brain-computer interface that can handle various intentions of users. We used an fNIRS system to collect neural information from brain activity. For discrimination of the fNIRS data, we used our previously proposed neural network model called the Neocognitron-type Image Sequence Recognition Model (Neo-ISRM), which is suitable for analyzing multichannel temporal patterns. Finger tapping imagery of both left and right hands was used as the mental tasks to be discriminated with Neo-ISRM. The model gave good discrimination results for each category of tasks from data for the motor area, the prefrontal area, and the frontal lobe. In all experiments, we confirmed that the discrimination results for the frontal lobe had fewer discrimination errors compared with the results for both the motor and prefrontal areas.
Development of NIRS-BCI system Using Perceptron
Kazuki Yanagisawa,Hideyuki Sawai,Hitoshi Tsunashima 제어로봇시스템학회 2012 제어로봇시스템학회 국제학술대회 논문집 Vol.2012 No.10
Brain Computer Interface (BCI) is a system that controls machines and devices by extracting neural information from human brain activity and it is expected for nursing robot such as an artificial hand. The present study focuses on BCI that uses near-infrared spectroscopy (NIRS). But signal processing methods for NIRS signals have not yet been established. For these reasons, it is difficult obtain highly accurate control operations. This study proposes BCI systems that can control a robot using NIRS which measures neural information from human brain activity. In this study propose a new brain activity judgment method that uses dispersion ratio and perseptron, to achieve highly accurate on/off operations is developed. Brain activity during actual grasping tasks and imagined grasping tasks are measured to demonstrate the validity of the proposed BCI system. Experimental results showed that the operation results can be greatly improved with the proposed method by both tasks.
Classication of fNIRS Data Using an Articial Neural Network for Image Sequence Recognition
Sei Takahashi,Nagako Saito,Hideo Nakamura,Hitoshi Tsunashima 대한전자공학회 2009 ITC-CSCC :International Technical Conference on Ci Vol.2009 No.7
We describe classication of functional near-infrared spectroscopy (fNIRS) data acquired during finger tapping and motor imagery tasks performed by a human subject, using an articial neural network for image sequence recognition. Our goal is to develop a brain-computer interface. We used an fNIRS system to collect neural information from brain activity. For discrimination of fNIRS data, we used our previously proposed neural network model called the Neocognitron-type Image Sequence Recognition Model (Neo-ISRM), which is suitable for multichannel temporal patterns. Finger tapping and its motor imagery were used as the motion and mental tasks to be discriminated using Neo-ISRM. The model gave good discrimination results for each category of tasks.
Brain-Computer Interface using Near-Infrared Spectroscopy for Rehabilitation
Kazuki Yanagisawa,Kyohei Asaka,Hideyuki Sawai,Hitoshi Tsunashima,Takafumi Nagaoka,Takeo Tsujii,Kaoru Sakatani 제어로봇시스템학회 2010 제어로봇시스템학회 국제학술대회 논문집 Vol.2010 No.10
This study proposes a new method for detecting brain activity level for brain-computer interface (BCI) using a near-infrared spectroscopy (NIRS) which is applicable for rehabilitation. NIRS detects the radiated near-infrared rays, and measures relative variations of oxygenated hemoglobin (oxy-Hb) and deoxygenated hemoglobin (deoxy-Hb) based on those absorbencies. The proposed method detects the brain activity level using oxy-Hb and the differential value of oxy-Hb. Results with grasping task show that the proposed method is effective for the detecting of brain activity level.