★Suffering from dirty strong supersonic attacks

★Suffering from dirty strong supersonic attacks (39ﾚｽ)
上下前次 1-新

9: YAMAGUTIseisei 2019/04/24(水)09:28 ID:5ZbN1Z79Q(8/32) BE AAS
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).
省6

10: YAMAGUTIseisei 2019/04/24(水)09:36 ID:5ZbN1Z79Q(9/32) BE AAS
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.
省11

11: YAMAGUTIseisei 2019/04/24(水)09:36 ID:5ZbN1Z79Q(10/32) BE AAS
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.
省9

12: YAMAGUTIseisei 2019/04/24(水)09:37 ID:5ZbN1Z79Q(11/32) BE AAS
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.
省8

13: YAMAGUTIseisei 2019/04/24(水)09:44 ID:5ZbN1Z79Q(12/32) BE AAS
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
省3

14: YAMAGUTIseisei 2019/04/24(水)09:44 ID:5ZbN1Z79Q(13/32) BE AAS
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.
省4

15: YAMAGUTIseisei 2019/04/24(水)09:45 ID:5ZbN1Z79Q(14/32) BE AAS
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.
省4

16: YAMAGUTIseisei 2019/04/24(水)09:46 ID:5ZbN1Z79Q(15/32) BE AAS
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.
省12

17: YAMAGUTIseisei 2019/04/24(水)09:46 ID:5ZbN1Z79Q(16/32) BE AAS
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.
省10

18: YAMAGUTIseisei 2019/04/24(水)09:50 ID:5ZbN1Z79Q(17/32) BE AAS
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 ID:5ZbN1Z79Q(18/32) BE AAS
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.
省4

20: YAMAGUTIseisei 2019/04/24(水)09:54 ID:5ZbN1Z79Q(19/32) BE AAS
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 ID:5ZbN1Z79Q(20/32) BE AAS
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.
省3

22: YAMAGUTIseisei 2019/04/24(水)09:58 ID:5ZbN1Z79Q(21/32) BE AAS
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
省6

23: YAMAGUTIseisei 2019/04/24(水)09:59 ID:5ZbN1Z79Q(22/32) BE AAS
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.
省9

24: YAMAGUTIseisei 2019/04/24(水)10:00 ID:5ZbN1Z79Q(23/32) BE AAS
(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.
省2

25: YAMAGUTIseisei 2019/04/24(水)10:04 ID:5ZbN1Z79Q(24/32) BE AAS
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.
省4

26: YAMAGUTIseisei 2019/04/24(水)10:16 ID:5ZbN1Z79Q(25/32) BE AAS
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 ID:5ZbN1Z79Q(26/32) BE AAS
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.
省5

28: YAMAGUTIseisei 2019/04/24(水)10:32 ID:5ZbN1Z79Q(27/32) BE AAS
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.

--
省1

上下前次 1-新書関写板覧索設栞歴

あと 11 ﾚｽあります
ｽﾚ情報赤ﾚｽ抽出画像ﾚｽ抽出歴の未読ｽﾚ AAｻﾑﾈｲﾙ

ぬこの手ぬこTOP 0.017s