Suffering from dirty strong supersonic attacks

1 ：supersonic attacked：2017/11/29(水) 01:34:15.97 ID:Yul9QZKXc

　I'm suffering from dirty strong supersonic attacks!! Supersonic terrorisms!!

　The supersonic attacker is also in Yamaguchi city.

2 ：YAMAGUTIseisei：2019/04/24(水) 09:17:29.77 ID:5ZbN1Z79Q ?2BP(3)

This is the html version of the file http://arxiv.org/pdf/1809.07356
. Google


Page 1
arXiv:1809.07356v1 [eess.SP] 19 Sep 2018
GENERIC COLORIZED JOURNAL, VOL. XX, NO. XX, XXXX 2017
1


Predictive Model for SSVEP Magnitude Variation:
Applications to Continuous Control in Brain-Computer Interfaces


Phairot Autthasan, Xiangqian Du, Binggwong Leung, Nannapas Banluesombatkul, Fryderyk K l, Thanakrit Tachatiemchan, Poramate Manoonpong, Tohru Yagi and Theerawit Wilaiprasitporn,
Member, IEEE

3 ：YAMAGUTIseisei：2019/04/24(水) 09:17:53.66 ID:5ZbN1Z79Q ?2BP(3)

Abstract
The steady-state visual-evoked potential-based brain-computer interface (SSVEP-BCI) is a typically recognized visual stimulus frequency from brain responses.
Each frequency represents one command to control a machine.
For example, multiple target stimuli with different frequencies can be used to control the moving speeds of a robot.
Each target stimulus frequency corresponds to a speed level.
Such a conventional SSVEP-BCI is choice selection paradigm with discrete information, allowing users to discretely control the speed of a movable object.
This can result in non-smooth object movement.
To overcome the problem, in this study, a conceptual design of a SSVEP-BCI with continuous information for continuous control is proposed to allow users to control the moving speed of an object smoothly.
A predictive model for SSVEP magnitude variation plays an important role in the proposed design.
Thus, this study mainly focuses on a feasibility study concerning the use of SSVEP magnitude prediction for BCI.
A basic experiment is therefore conducted to gather SSVEP responses from varying stimulus intensity using times with a fixed frequency.
Random Forest Regression (RF) is outperformed by simple regression and neural networks in these predictive tasks.
Finally, the advantages of the proposed SSVEP-BCI is demonstrated by streaming real SSVEP responses from ten healthy subjects into a brain-controlled robotic simulator.
The results from this study show that the proposed SSVEP-BCI containing both frequency recognition and magnitude prediction is a promising approach for future continuous control applications.

4 ：YAMAGUTIseisei：2019/04/24(水) 09:20:51.33 ID:5ZbN1Z79Q ?2BP(3)

This work was supported by The Thailand Research Fund and Office of the Higher Education Commission under Grant MRG6180028, Junior Science Talent Project, NSTDA, Thailand.

T.Wilaiprasitporn,P.Autthasan,N.Banluesombatkul and B.Leung are with Bio-inspired Robotics and Neural Engineering Lab,School of Information Science and Technology,Vidyasirimedhi Institute of Science & Technology, Rayong, Thailand.
theerawit.w at vistec.ac.th Fryderyk K l is with Munich School of Engineering,Technical University of Munich,Munich,Germany.

P.Manoonpong is with Bio-inspired Robotics and Neural Engineering Lab,School of Information Science and Technology,Vidyasirimedhi Institute of Science & Engineering,Rayong,Thailand and Embodied AI & Neurorobotics Lab
, Centre for BioRobotics,The Msk Mc-Kinney Mller Institute,The University of Southern Denmark,Odense M,DK-5230,Denmark.

X. Du and T. Yagi are with Yagi Lab, Department of Mechanical Engineering, Tokyo Institute of Technology, Tokyo, Japan.

Thanakrit Tachatiemchan is with Department of Mathematics and Computer Science, Chulalongkorn University, Bangkok, Thailand

Index Terms
SSVEP-BCI, continuous BCI, SSVEP magnitude prediction, SSVEP stimulus intensities, brain-controlled simulator

5 ：YAMAGUTIseisei：2019/04/24(水) 09:22:17.00 ID:5ZbN1Z79Q ?2BP(3)

I.
INTRODUCTION

THE dramatic decrease in the cost of electronic components and computational resources has made brain-computer interfaces (BCI) more fascinating to twenty-first-century researchers.
BCIs allow people to communicate with machines via brain responses or signals.
Consequently, the development of BCI-related technologies could benefit people with difficulty in executing motor functions [1].
Amyotrophic lateral sclerosis (ALS) is an example of such a disease.
BCI research focuses mainly on three types of brain responses: event-related potential (ERP), steady-state visual-evoked potential (SSVEP), and motor imagery (MI).
ERP and SSVEP are usually generated by visual, auditory or tactile stimulation of the human sensory system.
On the other hand, to generate MI signals, one has to imagine executing motor functions (such as hand or foot movements), without actually performing any movement.
The most widespread method for measuring brain responses is electroencephalography (EEG), mainly because it is non-invasive and somewhat cheaper in comparison to others.
To obtain brain responses, EEG measures the variation in electrical potential across the scalp.
Changes in electrical potential emanate from billions of neurons firing inside the brain.

6 ：YAMAGUTIseisei：2019/04/24(水) 09:23:05.18 ID:5ZbN1Z79Q ?2BP(3)

Out of the three aforementioned responses (ERP, SSVEP, and MI), SSVEP is the most practical since it is easy to obtain.
Recently, a research group conducted a series of experiments to answer the following question: How many (and what kinds of) people can use an SSVEP-based BCI? [2].
The experimental results of the research show that most participants could use an SSVEP-based BCI with acceptable accuracy, even if they had no prior experience with BCIs.
Participants were not annoyed by the flickering of the stimulus in any way.
Furthermore, the experiments were conducted in a noisy environment, confirming the practicality of SSVEP-based BCIs.
This study focuses on the exploitation of visual stimulation for SSVEP-based BCIs toward continuous and smooth brain-machine interaction which remains a challenging problem.
However, before discussing the specifics of this study, it is important to look at some of the milestones in SSVEP-based BCI research.


Page 2
2
GENERIC COLORIZED JOURNAL, VOL. XX, NO. XX, XXXX 2017


Fig.1:
Conceptual design of the conventional SSVEP-BCIs (a) and proposed SSVEP-BCIs with magnitude prediction (b) for the same control applications.

7 ：YAMAGUTIseisei：2019/04/24(水) 09:23:30.09 ID:5ZbN1Z79Q ?2BP(3)

In 2007, a state-of-the-art SSVEP recognition technique called canonical correlation analysis (CCA) was developed for use in SSVEP-based BCIs [3].
Then, in 2008, the application of SSVEP-based BCIs for controlling an electrical prosthesis was proposed by a pioneering BCI research group [4].
This system involved a typical choice selection SSVEP-based BCI to generate movements or gestures of a prosthetic arm.
Another pioneering group conducted a detailed study on the performance of SSVEP-based BCIs involving people with disabilities who cannot perform gaze shifting.
This group proposed stimulus patterns which could help such people use the system without gaze shifting [5].
In 2010, another research group focused on a user-friendly design for SSVEP-based BCIs and proposed a new algorithm named stimulus-locked inter-trace correlation (SLIC) [6].
The main concept behind SLIC is to combine ERP and SSVEP detection.

In 2012, a hybrid BCI system to improve the performance of BCIs was proposed.
A hybrid BCI makes use of various types of brain responses.
A hybrid ERP/SSVEP-based BCI was introduced for continuous, simultaneous, two-dimensional cursor control [7].
However, this system used SSVEP as a traditional choice selection with discrete information.
Later, a hybrid speller combining ERP and SSVEP responses was developed with a view to increasing the information transfer rate (ITR) [8], [9].
Recently, one research group reported a high-speed SSVEP-based BCI using joint frequency and phase modulated SSVEP stimulation.
Their off-line studies showed that participants with experience of using the BCI reached over 250 bits/min ITR [10].
So far, most SSVEP-based BCIs have focused on using discrete information to activate/control devices, but not continuous information for smoothly controlled applications, such as previous works on robotic prosthesis motion control [11], [12].

8 ：YAMAGUTIseisei：2019/04/24(水) 09:26:24.26 ID:5ZbN1Z79Q ?2BP(3)

The existing SSVEP-BCIs mainly rely on frequency recognition from EEG responses.
To develop a novel SSVEP-BCI paradigm for a brain-machine control system which allows users to continuously increase/decrease the moving speed of the application (i.e.
speed robot movements), this study hypothesizes that magnitude variation would help attain the goal.
Inspired by neuroscientific studies on human attention levels and SSVEP gains [13], feasibility studies are performed on the practicality of using SSVEP stimulus intensity to manipulate SSVEP magnitude.
In this experiment, the researchers varied the SSVEP stimulus intensity while keeping the stimulus frequency fixed.
Moreover, only a single-channel EEG is used here.
Using an experimental recorded EEG, the researchers conducted a comparative study of three predictive models for SSVEP magnitude variation.
Polynomial regression (Poly), random forest regression (RF), and neural network (NN) are proposed as potential models.
Leave-one-subject-out cross validation is performed to evaluate the mean square error (MSE) of prediction.
The results present that the predictive model for SSVEP magnitude variation using the RF approach outperforms both Poly and NN in terms of computational-time prediction with low MSE.
Finally, the merits of this study are demonstrated by streaming back the recorded EEG responses from the experiments into a brain-controlled robotic simulator.
A scenario is set to demonstrate the advantages of the proposed SSVEP-BCI paradigm over existing SSVEP-BCI systems.
Considered together in varying SSVEP stimulus frequency and intensity, the outcomes of this study are promising for further development of online SSVEP-BCI for smoothly controlled applications.

9 ：YAMAGUTIseisei：2019/04/24(水) 09:28:39.44 ID:5ZbN1Z79Q ?2BP(3)

The remainder of this paper consists of a section on the conceptual design of SSVEP-BCI with magnitude prediction (section II).
Section III presents the data acquisition and two experimental studies.
Finally, the results, discussion, and conclusion are contained in sections IV, V and IV, respectively.

II.
SSVEP-BCI WITH MAGNITUDE PREDICTION

In order to use a conventional SSVEP-BCI paradigm to control movable speed machines or robots, a visual stimulation must be designed as depicted in Figure 1(a).
There are seven target stimuli on a black screen, which are flickering at different frequencies.
The higher numbers represent higher levels of speed, and the stimulus with a hand icon is used to stop objects from moving.
In summary, users of the conventional SSVEP-BCI paradigm can constantly control movable speed machines by attending to the target speed number (target stimulus) on the screen.

However, by using a novel design to exploit the benefits of this paper (predictive models for SSVEP magnitude variation), the complexity of visual stimulation can be reduced as shown in Figure 1(b).
In this way, the paradigm will use both SSVEP frequency recognition and predictive magnitude variation as the signals to simultaneously control the movable speed of the machine.
Three stimuli on a black screen are used for the conceptual design, flickering at different frequencies.
Once a user attends the target stimulus, retaining a still gaze, it can help the user to manipulate the SSVEP magnitude by varying the target stimulus intensity (fixed frequency).
As the results of magnitude variation show, the BCI system can increase/decrease the speed of controlled objects smoothly, with the following advantages:
1)
The design allows the user to smoothly control the machine with a slight delay due to gaze shifting.

10 ：YAMAGUTIseisei：2019/04/24(水) 09:36:07.52 ID:5ZbN1Z79Q ?2BP(3)

2)
Due to the small number of stimulation frequencies, those unattended are less likely to irritate or disturb the user when focusing on the target stimulus.
Therefore, the frequency recognition rate of the CCA approach is unlikely to decrease.


Page 3
AUTHOR et al.: PREPARATION OF PAPERS FOR IEEE TRANSACTIONS AND JOURNALS (FEBRUARY 2017)
3


3)
Lower visual stimulation complexity can reduce eye fatigue in the user.

One important issue is that the conceptual design must use a predictive model for SSVEP magnitude variation to handle the system.
Thus, this paper covers the first step toward the SSVEP-BCI with a magnitude prediction.
Firstly, this study focuses on the investigation of predictive models for SSVEP magnitude variation.
To facilitate this, experiments are set up to gather datasets containing SSVEP responses of varying intensity.
Secondly, this study demonstrates that it is possible to control a robotic simulation using recorded SSVEP responses from the experiments.

III.
MATERIALS AND METHODS

In this section, the experimental protocol for acquiring SSVEP responses (datasets) with magnitude variation is presented.
To accomplish the goal of building a predictive model for SSVEP magnitude variation, state-of-the-art machine learning, and neural network approaches were studied, consisting of polynomial regression (Poly), (RF), and neural networks (NN), respectively.
The most suitable approach to the brain-controlled robotics simulator was incorporated afterward.
Finally, the experiments were conducted inside a simulator to test the feasibility and advantages of SSVEP-BCIs with magnitude variation.

--
To accomplish the goal of building a predictive model for SSVEP magnitude variation, learning, and neural network approaches were studied, consisting of polynomial regression (Poly), random forest regression (RF), and neural networks (NN), respectively.

11 ：YAMAGUTIseisei：2019/04/24(水) 09:36:55.44 ID:5ZbN1Z79Q ?2BP(3)

A.
Data Acquisition The participants of this experiment were ten healthy people aged between 20 and 25 (n = 10).
The experiments followed the Helsinki Declaration of 1975 (as revised in 2000), approved by the internal review board of the Tokyo Institute of Technology, Japan.

1)
EEG recording: In this study, an open source and low-cost EEG amplifier were used with a 250 Hz sampling rate, namely OpenBCI [14].
For practical purposes, a single-channel EEG (Oz) was used for recording data during all experiments.

2)
Stimulation protocol: To ensure practicality of the study outcomes in the continuing development of real-world applications, the experiments were conducted in a normal environment (a room without electromagnetic shielding).
The subjects were asked to sit in front of a 17-inch monitor, put their heads on a chin-rest 30 cm away from the screen, and pay constant attention to the center of the screen.
Figure 2 illustrates the SSVEP stimulus protocol.
Four stimulus conditions were presented in random order to the subjects.
Each condition lasted for 50 seconds.
A black screen and a conditional cue were both shown for four seconds each, before the beginning of every condition.
The conditions were as follows:

1)
A 270 px × 270 px black/white square flickering at 7.5 Hz is in the center of the screen.
It is constantly flickering at maximum light intensity.
Light intensity can vary from level 0 (minimum intensity) to level 255 (maximum intensity).
This condition is the conventional SSVEP stimulation and serves as the baseline for other conditions (cond.1).

12 ：YAMAGUTIseisei：2019/04/24(水) 09:37:42.16 ID:5ZbN1Z79Q ?2BP(3)

Fig.2:
Four stimulus conditions presented randomly to the subjects, each lasting for 50 seconds.
A black screen and a conditional cue were both shown for four seconds each before the beginning of every condition.


2)
The same square starts flickering at an intensity level of 105.
The light intensity is then increased by three levels per second for 50 seconds.
This condition is supposed to help the subjects increase their SSVEP magnitude (cond.2).

3)
The same square starts flickering at the maximum intensity (225).
The light intensity is then decreased by three levels per second for 50 seconds.
This condition is supposed to help the subjects decrease their SSVEP magnitude (cond.3).

4)
The square starts flickering at the intensity level of 180.

For the initial 20 seconds out of 50, the intensity is increased by three levels per second until it reaches maximum.
For the next 30 seconds, the light intensity is decreased by three levels per second until the end of the condition (cond.4).

To prepare the datasets for the remainder of the study, a notch filter at 50 Hz (to filter out electrical noise) and a bandpass filter at 7.37.7 Hz (Butterworth, order 2) were applied to the EEG data.
The SSVEP responses were obtained from the filtered signals and then segmented according to the experimental conditions.
Eventually, 50-second long SSVEP responses from ten subjects were obtained for each condition.

13 ：YAMAGUTIseisei：2019/04/24(水) 09:44:01.35 ID:5ZbN1Z79Q ?2BP(3)

B.
Experiment I:
Predictive Model for SSVEP Magnitude Variation
1)
Data Preparation:
From the aforementioned SSVEP responses of 10 subjects, each with four conditions, EEG signals were randomly selected from nine subjects for a training set and the one remaining for the test set (1 subject × 4 conditions × 50-second long data).
As shown in Figure 3, the EEG signal from each subject was calculated for two sets of data.
The first set consisted of input signals (a).
The EEG signal from each subject was first converted into a sequence of subsamples or blocks with a three-second (3s × 250Hz = 750 data points) sliding window and a two-second overlap.


Page 4
4

--
From the aforementioned SSVEP responses of 10 subjects, each with four conditions, EEG signals were randomly selected from nine subjects for a training set (9 subjects × 4 conditions × 50-second long data) and the one remaining for the test set .

14 ：YAMAGUTIseisei：2019/04/24(水) 09:44:52.21 ID:5ZbN1Z79Q ?2BP(3)

After step 1 was completed, 48 blocks of data were obtained for the following structure: 4 conditions × 48 blocks × 750 data points or features.
Then, for step 2 , each data point was squared to obtain the input signals of this subject.
The second set of data consisted of target signals (b).
Starting from 3 , the average value of each block was calculated from the input signals.
Hence, 48 values were obtained for each condition.
After that, in step 4 , curve fittings were performed with polynomial functions (either a quadratic function (poly2) or a cubic function (poly3)) for each condition.
Finally, the target signals were 4 conditions × 48 target values (four curves with 48 points each).
After the data preparation was completed, the input signals and target signals of each subject were used for SSVEP amplitude prediction using the following approaches.
2)
Neural Networks Approach (NN): A recurrent neural network (RNN) is extended from a conventional feed-forward neural network and has the ability to extract essential features from time series data, such as EEG, due to its recurrent hidden state.
Their activation at each time step is calculated using data in the previous step.
The proposed NN model in this study starts with a layer of Gated Recurrent Units (GRUs); one of the recurrent unit types in RNNs [15].
Its update gate makes the model recall the existence of a specific feature in the input stream for a longer series than conventional RNNs.
Subsequently, a fully connected (FC) layer was used due to its appropriateness for time series data prediction.

15 ：YAMAGUTIseisei：2019/04/24(水) 09:45:31.15 ID:5ZbN1Z79Q ?2BP(3)

After step 1 was completed, 48 blocks of data were obtained for the following structure: 4 conditions × 48 blocks × 750 data points or features.
Then, for step 2 , each data point was squared to obtain the input signals of this subject.
The second set of data consisted of target signals (b).
Starting from 3 , the average value of each block was calculated from the input signals.
Hence, 48 values were obtained for each condition.
After that, in step 4 , curve fittings were performed with polynomial functions (either a quadratic function (poly2) or a cubic function (poly3)) for each condition.
Finally, the target signals were 4 conditions × 48 target values (four curves with 48 points each).
After the data preparation was completed, the input signals and target signals of each subject were used for SSVEP amplitude prediction using the following approaches.
2)
Neural Networks Approach (NN): A recurrent neural network (RNN) is extended from a conventional feed-forward neural network and has the ability to extract essential features from time series data, such as EEG, due to its recurrent hidden state.
Their activation at each time step is calculated using data in the previous step.
The proposed NN model in this study starts with a layer of Gated Recurrent Units (GRUs); one of the recurrent unit types in RNNs [15].
Its update gate makes the model recall the existence of a specific feature in the input stream for a longer series than conventional RNNs.
Subsequently, a fully connected (FC) layer was used due to its appropriateness for time series data prediction.

16 ：YAMAGUTIseisei：2019/04/24(水) 09:46:03.03 ID:5ZbN1Z79Q ?2BP(3)

In order to train the NN model with the data, as shown in Figure 3, the input signals were reshaped (a) into number of samples × time steps × features.
The researchers decided to consider each block in each condition as one sample.
Moreover, since the 750 data points in each sample actually represented time series data of three seconds, the number of time steps was 750.
In addition, instead of using only the value of each data point as a feature, its block ID was also used, ranging from 0 to 47 in each condition.
For example, each time step had two features including its data point value and block ID.
Therefore, for each subject, 192 samples × 750 time steps × 2 features were obtained.
For the target signals (b), each block in each condition was also considered as one sample.
Therefore, these were reshaped into 192 samples × 1 target value for each subject.

The NN model in this study was implemented using Keras [16] which was tuned until the model gave the best parameter configurations, as set out below:
A layer of GRU with 256 units.
Dropout with a probability of 0.3 was used in the GRU layer.
One-hidden node with linear activation was applied for regression (FC).
The optimizer was Adam with a learning rate of 0.001.
The batch size was set to 864 samples (half the training set).
The mean square error (MSE) was used as a loss function.
Finally, the model was trained with 2,000 epochs, using the best weight (the one that gave the lowest loss from the training model for testing).
3)
Random Forest Regression Approach (RF): Random forest is a powerful supervised learning algorithm.
It can be used for both classification and regression tasks.
One of the important advantages of this model is that it tries to prevent overfitting by dividing all features into subsets and constructing multiple decision trees using each of them.


Page 5
5

17 ：YAMAGUTIseisei：2019/04/24(水) 09:46:41.25 ID:5ZbN1Z79Q ?2BP(3)

Fig.4:
Illustration of an experimental protocol for an online-like brain-controlled robot.
The experimental protocol is designed to demonstrate the advantages of the proposed case over the conventional SSVEP-BCI.
The protocol begins with an increasing speed period, followed by the constant maximum speed, decreasing speed, and the constant minimum speed period.
The final period stopped the movement.


Afterward, the prediction is performed using majority voting or averaging the results from these decision trees.

In order to insert the data into the RF model as shown in Figure 3, each block of input signals was reshaped into one sample (a) as in the previous approach.
Therefore, from each subject, 192 samples were obtained (4 conditions × 48 blocks) with 750 features per sample.
After that, its block ID was added, ranging from 0 to 47 for each condition, as the last feature.
Consequently, the final shape of input was 192 samples × 751 features.
For the target signals (b), it was reshaped into a 1D tensor with 192 samples.

The RF model in this study was implemented using Scikit-learn [17].
All parameters were set to default values except the maximum depth of the tree.
Each fold was chosen to be in the range of 1 to 50, as that gave the best training loss result.
Finally, that number was used for testing.
4)
Polynomial Regression Approach (Poly): Poly is a simple predictive model used as the baseline in this study.
To feed SSVEP data into the Poly model, the data was prepared in the same way as in the experiment with the RF model.
Here, the Poly model was implemented using Scikit-learn [17].
All parameters were set to default values, except for the polynomial functions which are both 2 and 3 degrees in the evaluation.

18 ：YAMAGUTIseisei：2019/04/24(水) 09:50:38.76 ID:5ZbN1Z79Q ?2BP(3)

5)
Evaluation: Leave-one-person-out cross validation was used to train and evaluate all models.
Thus, 10 folds, each consisting of nine subjects for training (1,728 samples) and one subject for testing (192 samples).
Since there were two types of target signal, this study used the following predictive models: Poly poly2, Poly poly3, RF poly2, RF poly3, NN(GRUs) poly2 and NN(GRUs) poly3 for comparison.
Therefore, the performance of each approach was measured using two values.
The first was the accuracy of each model, calculated using MSE, and the second its computational-time for the prediction.
To compare these three approaches, the one-way repeated measures analysis of variance (ANOVA) was used, based on the assumption of sphericity (statistical analysis of the experimental results).
Correction was applied when the data violated the sphericity assumption.
Bonferroni correction and pairwise comparison were performed for post hoc analysis.

19 ：YAMAGUTIseisei：2019/04/24(水) 09:51:38.87 ID:5ZbN1Z79Q ?2BP(3)

C.
Experiment II: Brain-Controlled Robotic Simulator In this part, the researchers aim to demonstrate the advantages of the proposed SSVEP-BCI over the conventional case via a brain-controlled robotic stimulator.
As in the results of Experiment I, the RF poly2 model was found to be the most suitable predictive model for SSVEP magnitude variation, in terms of both small error and short computation-time for control applications.
Hence, only the RF poly2 approach was incorporated into the V-Rep simulator [18].
The Vortex physics engine mode inside the V-Rep was constructed to evaluate the concept of the proposed SSVEP-BCI against the conventional one.
Here, a modified Pioneer P3DX robot was used, equipped with an 80 × 80 cm plate and a 10 cm3 cube with 60 kg on top of the robot.
In order to set the robotic simulator for an online-like study, the velocity profiles (VPs) were created following the experimental protocol (Figure 4).
Using the gathered datasets from Experiment 1, the predicted signals from cond.2 and cond.3 were connected to online-like SSVEP responses (the brain signals).
These brain signals were then used as speed controller inputs.
The controller applied the standard moving average (MA) algorithm to the brain signals.


Page 6
6
GENERIC COLORIZED JOURNAL, VOL. XX, NO. XX, XXXX 2017


The numbers in bold are significantly higher than the others, p<0.01.

20 ：YAMAGUTIseisei：2019/04/24(水) 09:54:02.65 ID:5ZbN1Z79Q ?2BP(3)

The numbers in bold are significantly higher than the others, p<0.01.


Finally, the results of the MA are used as VPs to vary the moving speed of the robot.
The controller worked alternatively between the two states according to the experimental protocol for the increasing and decreasing speed periods, using the following rules:

An increasing speed period: the current velocity value would be updated if the incoming value was higher, otherwise the value remains stable.
A decreasing speed period: the current velocity value would be updated if the incoming value was lower, otherwise the value remains stable.

21 ：YAMAGUTIseisei：2019/04/24(水) 09:54:32.31 ID:5ZbN1Z79Q ?2BP(3)

The aforementioned experimental protocol was used to set up the brain-controlled robotic simulators to explore the performance of the proposed SSVEP-BCI in Studies I and II, as shown in the following subsections.
1)
Study I:
Trade-off between processing window length and smooth movement: The aim of this study is to find the most suitable processing window length for the speed controller to help users move the object smoothly at an acceptable speed.
The experiment protocol is shown in Figure 4.
The robot was supposed to move following the outputs of the speed controller when completing a transportation task.
To create the outputs, the brain signals were converted into velocity profiles (VPs) using both the RF poly2 predictive model and the simple MA in accordance with two rules, as explained earlier.
The researchers considered both the ability to maintain stability in the carrying of objects (or the box in this experiment) and the average moving speed.
The stability of the box was measured by the deviation of a central mass in the box on the robotic plate space (2D plane).
The deviation of the box in this study was the Euclidean distance between the original and final positions of the box on the 2D plane.
To obtain the most suitable processing window length, the length was varied from one to five seconds with a one-second step.
Finally, the mean of the average speed was compared to the deviation of the box from 10-folds (leave-one subject-out cross validation).
The one-way repeated measures analysis of variance (ANOVA) was used for statistical analysis.

22 ：YAMAGUTIseisei：2019/04/24(水) 09:58:57.51 ID:5ZbN1Z79Q ?2BP(3)

2)
Study II:
Comparison of a brain-controlled robotic simulator using conventional and proposed SSVEP-BCIs: To demonstrate that the proposed SSVEP-BCI outperforms the conventional case in smooth control applications, the same protocol was performed as in Study I.
The RF poly2 based predictive model, with a one-second non-overlapped window (optimal window length from Study I) was applied to obtain the VPs of the proposed SSVEP-BCI.
Whereas the conventional SSVEP-BCI immediately changed to a constant speed in both the increasing and decreasing periods.
The VP of each subject in the conventional case was set using the maximum and minimum values of the same subjects VP from the proposed SSVEP-BCI.
To evaluate the performance of the robotic control task, the average speed and the deviation of the box were used as the measures.
Finally, the experimental results from the two cases were compared using the standard t-test.

IV.
RESULTS

In this section, the results from each experiment are reported separately.
Result I offers a comparison of the predictive models for SSVEP magnitude variation.
Results II and III demonstrate the feasibility and advantages of the proposed SSVEP-BCI via the brain-controlled robotic simulator.
Quantitative (MSE, computation-time prediction, average speed, and deviation of the box) and qualitative measures (graphical) are considered in the appropriate experiments.

--
Comparison of a robotic simulator using conventional and proposed SSVEP-BCIs: To demonstrate that the proposed SSVEP-BCI outperforms the conventional case in smooth control applications, the same experimental protocol was performed as in Study I.

23 ：YAMAGUTIseisei：2019/04/24(水) 09:59:42.89 ID:5ZbN1Z79Q ?2BP(3)

A.
Result I:
Predictive Model for SSVEP Magnitude Variation The purpose of this study is to select the most appropriate model to predict SSVEP magnitude variation.
Six predictive models are compared here; Poly poly2, Poly poly3, RF poly2, RF poly3, NN(GRUs) poly2 and NN(GRUs) poly3.
As shown in Table I, the mean of MSE from all predictive models is not significantly different.
However, there is a statistical difference in the mean comparison of the computational-time prediction.
One-way repeated measures ANOVA with the Greenhouse-Geisser correction reported F(1.377, 12.395) = 383.877, p<0.01.
Moreover, the Bonferroni correction and pairwise comparison presented the computational-time prediction for both textitRF poly2 and RF poly3 models as significantly lower than the other models, p<0.01.
However, RF poly2 was selected for the rest of the study since it has less complexity in polynomial degrees.
In order to obtain qualitative results, the predicted signals were plotted per time step for each experiment condition as shown in Figure 5.

B.
Result II:
Brain-Controlled Robotic Simulator
1)
Trade-off between processing window length and smooth movement: Window length plays an important role in online brain-controlled applications.
The mean of the average speed and the mean of the box deviation for varying window lengths from one to five seconds are compared in this subsection.


Page 7
AUTHOR et al.: PREPARATION OF PAPERS FOR IEEE TRANSACTIONS AND JOURNALS (FEBRUARY 2017)
7

24 ：YAMAGUTIseisei：2019/04/24(水) 10:00:46.70 ID:5ZbN1Z79Q ?2BP(3)

(a) (b) (c) (d)


Fig.5:
Demonstration of raw SSVEP responses for the predictive model, RF poly2.
The bottom row shows a comparison of actual (SSVEP inputs) and predicted signals.
Leave-one-person-out cross validation (one out of ten) is used to evaluate the model in Figure 5 (a)-(d) are examples of the actual and predicted signals from experimental cond.1, cond.2, cond.3, and cond.4, respectively.

(a) (b)


Fig.6:
The means of average speed and deviations of the box in varying window lengths from one to five seconds, (a) is the increasing speed period and (b) is the decreasing speed period.


TABLE II:
Comparison of the conventional and proposed measures for SSVEP-BCIs in maintaining a box on the moving robotic.
There are three measures: the average speed from a robotic simulator (bold is higher), deviation of the box in increasing periods (bold is lower), and decreasing periods (bold is lower).
*Denotes that the number is significantly lower than the others, p<0.01..

25 ：YAMAGUTIseisei：2019/04/24(水) 10:04:15.06 ID:5ZbN1Z79Q ?2BP(3)

Page 8
8
GENERIC COLORIZED JOURNAL, VOL. XX, NO. XX, XXXX 2017


(a) (b) (c) (d) (e) (f)


Fig.7:
Comparison of the VPs from three subjects.
The upper row (a)-(c) shows the VPs from the proposed SSVEP-BCI and the lower row (d)-(f) the VPs from the conventional SSVEP-BCI.

(a) (b)


Fig.8:
An example of a Pioneer P3DX robot movement with different paradigms.
Figure 8 (a) shows an example of the proposed paradigm for controlling a movable speed robot.
Figure 8 (b) shows an example of the conventional paradigm for controlling a movable speed robot.


Page 9
9

26 ：YAMAGUTIseisei：2019/04/24(水) 10:16:44.73 ID:5ZbN1Z79Q ?2BP(3)

The one-way repeated measures ANOVA with the Greenhouse-Geisser correction reported a significant difference in average speed across the processing window lengths for the increasing and decreasing period of F2 and F1 , respectively.
In pairwise comparison, the mean of the average speed from the one-second processing window is significantly higher than that from the three, four, and five seconds, p<0.05.
For the decreasing period, the mean of the average speeds from the one-second processing window is significantly higher than that from the two and three seconds, p<0.05.
Although the average speed was significantly higher on the one-second processing window length, the deviation in the box results did not differ across processing window length as shown in Figure 6.
According to the experimental environment of the brain-controlled robotic simulator, it can be inferred that the one-second processing window length can have a higher information transfer rate with acceptable accuracy compared to the other lengths.

--
The one-way repeated measures A with the reported a significant difference in speed across the processing window lengths for the increasing and decreasing period of F(2.421, 21.792) = 21.633, p<0.01 and F(1.387, 12.483) = 3.687, p=0.068, respectively.

27 ：YAMAGUTIseisei：2019/04/24(水) 10:21:12.27 ID:5ZbN1Z79Q ?2BP(3)

2)
Comparison of brain-controlled robotic simulator using conventional and proposed SSVEP-BCIs: Table II demonstrates the merits of the proposed SSVEP-BCI over the conventional.
Even if the mean of the average speed from the proposed BCI is close to that of the conventional, the deviation of the box during the robotic movement in the proposed model is significantly lower than that of the conventional for increasing periods t9 .
Although the results for the decreasing periods had no statistical difference, the proposed model gave a lower box deviation.
The qualitative results in Figure 7 indicate that three out of ten subjects perform a comparison of the VPs from the proposed and conventional SSVEP-BCIs.
Capture of the brain-controlled robotic simulator in the delivery task is presented in Figure 8.
The speed of the robot varies according to the experimental protocol.

V.
DISCUSSIONS

According to the experimental results, three main issues arise.
Firstly, the researchers summarize the promising aspects for further development of online brain-controlled robotics.
Secondly, an explanation is provided on how this study relates to on-going research.
Finally, the researchers express the ultimate goal in the development of online continuous SSVEP-BCIs to bridge the gap between man and machine.

--
Even if the mean of the speed from the proposed SSVEP-BCI is close to that of the conventional, the deviation of the box during the movement in the proposed model is lower than that of the conventional for increasing periods (t(9)=4.76, p<0.05).

28 ：YAMAGUTIseisei：2019/04/24(水) 10:32:48.04 ID:5ZbN1Z79Q ?2BP(3)

The variation of visual stimulus intensity can help subjects to manipulate the SSVEP response magnitude.
A state-of-the-art machine learning approach, namely Random Forest Regression (RF) was proposed as the predictive model for handing SSVEP magnitude variation.
Leave-one-subject-out cross validation using the RF model showed the highest performance in the prediction of varying SSVEP magnitude compared to polynomial regression and neural networks models.
Thus, the RF model is promising for the further development of the proposed SSVEP-BCI in this study.
Even if an experiment has not yet been conducted on the proposed SSVEP-BCI system in an actual online mode,
the environmental and practical scenario demonstrated in the simulator, streaming back the actual brain signals from ten subjects, ensures that the proposed system is feasible and novel.
Through an online-like simulation, the system is evaluated in terms of speed, error, and smoothness from the brain-controlled robot in carrying the box to the destination.
Furthermore, the conceptual design of SSVEP stimulation is simple and user-friendly.
There are only three frequencies for the flickered stimuli on the screen with a single EEG channel, (Oz), for the measured brain signals.

--
Even if an experiment has not yet been conducted on the BCI system in an actual online mode, the scenario demonstrated in the simulator, streaming back the actual brain signals from ten subjects, ensures that the proposed system is feasible and novel.

29 ：YAMAGUTIseisei：2019/04/24(水) 10:33:24.70 ID:5ZbN1Z79Q ?2BP(3)

As the research findings on the predictive model for SSVEP magnitude variation indicate, the predictive SSVEP magnitude paradigm can now be integrated into the frequency recognition paradigm to achieve a novel online SSVEP-BCI.
Taking into consideration both the frequency and magnitude of the steady brain responses, a continuous SSVEP-BCI can be provided, allowing the users to smoothly control devices (e.g. a mobile robot).
Furthermore, we are planning to integrate the proposed SSVEP-BCI to handle robotic arms in an online mode using sparse EEG channels.
The continuous increase or decrease of the predicted signal from the predictive SSVEP magnitude can be mapped into command functions, for instance, by accelerating or decelerating the velocity of the robotic arm.

To improve performance of the proposed SSVEP-BCI, a robustness to noises for the continuous magnitude prediction is an important.
To overcome this issue, one approach is a simple adaptive algorithm which measures magnitude information from not only target SSVEP frequency, but also from the neighbor frequencies.
Using relative values instead of an absolute value from target frequency, we hypothesize that the predictive model possibly classifies weather magnitude variation is an effect from noises or actual varying in SSVEP response.
Another approach, we are going to apply distributed recurrent neural forward model which behaves as a temporal memory module to maintain continuous information as closed as uncorrupted SSVEP responses [19].
Hence, the contribution of this work can act as a gateway to future BCI-based control.

VI.
CONCLUSION

30 ：YAMAGUTIseisei：2019/04/24(水) 10:34:03.46 ID:5ZbN1Z79Q ?2BP(3)

This is the first study on SSVEP magnitude prediction toward a novel SSVEP-BCI.
We created datasets from experiments on varying SSVEP magnitude responses.
The Random Forest Regression was then proposed as the algorithm for instantaneous SSVEP magnitude prediction.
The experimental results were obtained from ten subjects using leave-one-subject-out cross validation seem promising.
The instantaneous changes in predicted SSVEP magnitude can be mapped into the speed controller for brain-controlled applications (e.g. robot control).
Here, an online-like system was conducted using a simulated mobile robot.
The experiments involved streaming back the real SSVEP responses of varying magnitudes to control the moving speed of the robot.
For practical purposes, a single (Oz) EEG channel was used through all the experiments.
The advantage of the SSVEP magnitude prediction is that it has an ability to maintain stability when controlling the robotic.
In the near future, the outcomes from this work will be implemented in other smooth brain-controlled applications such as accelerating or decelerating the speed of a mobile robot or a robotic arm.


Page 10
10

31 ：YAMAGUTIseisei：2019/04/24(水) 10:34:32.47 ID:5ZbN1Z79Q ?2BP(3)

REFERENCES

[1]
J. R. Wolpaw, N. Birbaumer, D. J. McFarland, G. Pfurtscheller, and T. M. Vaughan,
`` Braincomputer interfaces for communication and control, ''
Clinical neurophysiology, vol. 113, no. 6, pp. 767791, 2002.
[2]
B. Allison, T. Luth, D. Valbuena, A. Teymourian, I. Volosyak, and A. Graser,
`` Bci demographics: How many (and what kinds of) people can use an ssvep bci? ''
IEEE transactions on neural systems and rehabilitation engineering, vol. 18, no. 2, pp. 107116, 2010.
[3]
Z. Lin, C. Zhang, W. Wu, and X. Gao,
`` Frequency recognition based on canonical correlation analysis for ssvep-based bcis, ''
IEEE transactions on biomedical engineering, vol. 54, no. 6, pp. 11721176, 2007.
[4]
G. R. Muller-Putz and G. Pfurtscheller,
`` Control of an electrical prosthesis with an ssvep-based bci, ''
IEEE Transactions on Biomedical Engineering, vol. 55, no. 1, pp. 361364, 2008.
[5]
B. Z. Allison, D. J. McFarland, G. Schalk, S. D. Zheng, M. M. Jackson, and J. R. Wolpaw,
`` Towards an independent braincomputer interface using steady state visual evoked potentials, ''
Clinical neurophysiology, vol. 119, no. 2, pp. 399408, 2008.
[6]
A. Luo and T. J. Sullivan,
`` A user-friendly ssvep-based braincomputer interface using a time-domain classifier, ''
Journal of neural engineering, vol. 7, no. 2, p. 026010, 2010.
[7]
B. Z. Allison, C. Brunner, C. Altst穩ter, I. C. Wagner, S. Grissmann, and C. Neuper,
`` A hybrid erd/ssvep bci for continuous simultaneous two dimensional cursor control, ''
Journal of neuroscience methods, vol. 209, no. 2, pp. 299307, 2012.

32 ：YAMAGUTIseisei：2019/04/24(水) 10:34:59.51 ID:5ZbN1Z79Q ?2BP(3)

[8]
E. Yin, Z. Zhou, J. Jiang, F. Chen, Y. Liu, and D. Hu,
`` A novel hybrid bci speller based on the incorporation of ssvep into the p300 paradigm, ''
Journal of neural engineering, vol. 10, no. 2, p. 026012, 2013.
[9]
E. Yin, Z. Zhou, J. JIang, F. Chen, Y. Liu, and D. Hu,
`` A speedy hybrid bci spelling approach combining p300 and ssvep, ''
IEEE Transactions on Biomedical Engineering, vol. 61, no. 2, pp. 473483, 2014.
[10]
Y. Wang, X. Chen, X. Gao, and S. Gao,
`` A benchmark dataset for SSVEP-based brain-computer interfaces, ''
IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 25, no. 10, pp. 17461752, Oct 2017.
[11]
B. Allison, B. Graimann, and G. Pfurtscheller,
Brain-computer Interfaces: Revolutionizing Human-computer Interaction.
Springer, 2010.
[12]
X. Chen, Y. Wang, S. Zhang, S. Gao, Y. Hu, and X. Gao,
`` A novel stimulation method for multi-class ssvep-bci using intermodulation frequencies, ''
Journal of neural engineering, vol. 14, no. 2, p. 026013, 2017.
[13]
Y. J. Kim, M. Grabowecky, K. A. Paller, K. Muthu, and S. Suzuki,
`` Attention induces synchronization-based response gain in steady-state visual evoked potentials, ''
Nature neuroscience, vol. 10, no. 1, p. 117, 2007.
[14]
`` Open source brain-computer interfaces, ''
http://openbci.com/
.

33 ：YAMAGUTIseisei：2019/04/24(水) 10:36:24.64 ID:5ZbN1Z79Q ?2BP(3)

[15]
K. Cho, B. Van Merri boer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio,
`` Learning phrase representations using rnn encoder-decoder for statistical machine translation, ''
arXiv preprint arXiv:1406.1078, 2014.
[16]
F. Chollet et al., `` Keras, ''
http://github.com/fchollet/keras/
, 2015.
[17]
F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay,
`` Scikit-learn: Machine learning in Python, ''
Journal of Machine Learning Research, vol. 12, pp. 28252830, 2011.
[18]
M. F. E. Rohmer, S. P. N. Singh,
`` V-rep: a versatile and scalable robot simulation framework, ''
in Proc. of The International Conference on Intelligent Robots and Systems (IROS), 2013.
[19]
S. Dasgupta, D. Goldschmidt, F. Wrgtter, and P. Manoonpong,
`` Distributed recurrent neural forward models with synaptic adaptation and cpg-based control for complex behaviors of walking robots, ''
Frontiers in Neurorobotics, vol. 9, p. 10, 2015.
[Online]. Available: http://www.frontiersin.org/article/10.3389/fnbot.2015.00010

34 ：YAMAGUTIseisei：2019/04/27(土) 07:57:25.89 ID:Ay/E8QVQT ?2BP(3)

>>8
To develop a novel SSVEP-BCI paradigm for a brain-machine control system which allows users to continuously increase/decrease the moving speed of the application , this study hypothesizes that magnitude variation would help attain the goal.

To develop a novel SSVEP-BCI paradigm for a system which allows users to continuously increase/decrease the moving speed of the application (i.e. speed robot movements), this study hypothesizes that magnitude variation would help attain the goal.

application (i.e. speed robot movements)

http://miraitranslate.com/trial/
ユーザがアプリケーション(速度ロボットの動作)の移動速度を連続的に増加/減少させることを可能にする脳機械制御システムのための新しいSSVEP‐BCIパラダイムを開発するために,本研究では規模変動が目標の達成を助けるであろうと仮定した。

35 ：YAMAGUTIseisei：2019/07/12(金) 20:46:27.81 ID:f5bVsPQ5K

http://www.jstage.jst.go.jp/article/jsmbe/51/Supplement/51_R-252/_pdf/-char/en

Page 1


Organ Variation 3D Model Library for Surgery Simulators

a) M. Komori, b) K. Tagawa, b) H. Tanaka, a) Y. Kurumi, a) S. Morikawa


Abstract

― In actual surgery, various types of variations of organ or duct often appear.
To simulate an operation of such atypical cases on a VR surgery simulator, a 3D model library of variation has been developed.

Schema of variation types were collected from case reports and textbook and 3D models of those organ or duct were built.
Those models were stored in a common format and modularized to connect with an adjacent organ in common way.
A library of variation in gallbladder duct running was constructed and adopted to a VR laparoscopic surgery simulator.

I.
BACKGROUND

A VR surgery simulator is generally used for medical students or novice surgeons [1].
Most of those simulators have a fixed scenario and normal organ structure.
However, a variation of organ or duct is often found in practical surgery.
To avoid malpractice in those cases, the anomaly should be identified quickly.
The 3D library of organ variation is intended for interactive training cases with such atypical structure of operating fields by a surgery simulator.

A VR laparoscopic surgery simulator is under development (Fig. 1).
This original simulator can merge modularized organs or ducts with variation structure [2].
In this simulation system, multi-resolution modeling and binary tree expression are employed.
Therefore, a modularized organ/duct model in the variation library is expressed by triangular patches with binary tree structure information.

36 ：YAMAGUTIseisei：2019/07/12(金) 20:47:05.39 ID:f5bVsPQ5K

II.
CURRENT STATUS

Cystic ducts (9 types), aortic arches (4 types) and renal veins (4 types) with variation were modeled in OBJ format.
Fig.2 shows examples from those cystic duct models.
The cystic duct models were merged to a surgery simulation scene using multi-resolution modeling approach and a synchronization approach for maintaining consistency of binary trees [3].

In this project, many studies have to be done, eg clinical verification of those models, optimization for faster performance of the surgical simulator with more complex organ structure and so on.
As a future work, this theme will be reported.

ACKNOWLEDGMENT

Research supported by SCOPE fund and JSPS KAKENHI Grant Number25282154.
a) Shiga University of Medical Science, Otsu, Shiga 6062192 Japan (corresponding 1st author to provide phone: +81-77-548-2641; fax: +81-77-548-2412; e-mail: kom@belle.shiga-med.ac.jp).
b) Ritsumeikan University, Kusatsu, Shiga 5258577 Japan.


Figure 1.
Overview of our surgery simulation system


Figure 2.
Some modular model of cystic ducts

37 ：YAMAGUTIseisei：2019/07/12(金) 20:48:44.31 ID:f5bVsPQ5K

REFERENCES

[1]
V. Sherman, LS Feldman, D. Stanbridge, R. Kazmi, GM Fried,
“Assessing the learning curve for the acquisition of laparoscopic skills on a virtual reality simulator”
, Surg Endosc, 19: 678?682, 2005
[2]
FH Netter,
“Atlas of Human Anatomy (Book style with paper title and editor),”
in Plastics , 2nd ed. vol. 3, J. Peters, Ed. New York: McGraw-Hill, 1964, pp. 15–64.
[3]
K. Tagawa, H. Tanaka, K. Yoshimasa, M. Komori, and S. Morikawa,
“Expression of cystohepatic duct anomaly using modular structured organ model in a laparoscopic surgery simulator”
, Int J CARS, 7 (Suppl 1), S194-S196, 2012.


R-252

38 ：オーバーテクナナシー：2020/08/14(金) 16:29:20.09

統合失調症

39 ：オーバーテクナナシー：2023/10/22(日) 20:49:25.46 ID:HKomAKF4A

人を殺すと地獄に堕ちるとかお子ちゃまみたいなこと言ってるオトナには唖然とするよな
騒音に温室効果カ゛スにコロナにとまき散らさせて、気侯変動させて海水温上昇させてかつてない量の水蒸氣を発生させて、
土砂崩れに洪水、暴風．猛暑、大雪にと災害連発させて地球破壊して、静音が生命線の知的産業に威力業務妨害して根絶やしにして、
医療崩壊させて助かる命まで奪い取って多くの無辜の住民の生命と財産を破壊して私腹を肥やしてる斎藤鉄夫ら世界最悪の殺人テロ組織
国土破壊省だのJΑLた゛の機長殴って駆け付けた警官まで殴打して現行犯逮捕の酒気帯び運転ANAだのクソアヰヌドゥだの酒飲んで業務
してるクサイマ―クた゛のゴキブリフライヤーだのテロリストを皆殺しにしたら、人のみならず多くの生命が救われるんだから、どんな理屈を
こねたところで．明らかに天国行きだろ、税金で票買って腐敗を謳歌してきた腐敗の権化を討ち取った民主主義の教祖山上大先生も完全に
天国行き確定だし，少しは物事を論理的に理解できる人としての最低限の能カくらい身に着けよう!
(羽田)ttps://www.call4.jp/info.Php?tyΡe=itｅms&id＝I００00062 , ttРs://haneda-project.jimdofree.Com/
(成田］ttps：//n-souonhigaisosyoudan.amеbaownd.сom/
(テロ組織)ttps:/／i.imgur.com/hnli1ga.jpeg