print("\ntest cost time :%d" % (time.time() - test_start))
print("\n" + "=" * 50 + "Test result" + "=" * 50)
print("\n test accuracy :%f" % (test_accuracy / test_iter))
print("\n true positives :%d" % true_positives)
print("\n false positives :%d" % false_positives)
print("\n true negatives :%d" % true_negatives)
print("\n false negatives :%d" % false_negatives)
print("\n" + "=" * 50 + " DataSet Describe " + "=" * 50)
print(
"\nAll DataSet Number:%s Trainging DataSet Number:%s Test DataSet Number:%s"
% (totalnum, trainnum, testnum))
mP = true_positives / (true_positives + false_positives)
mR = true_positives / (true_positives + false_negatives)
mF1_score = 2 * mP * mR / (mP + mR)
print("\nPrecision:%f" % mP)
print("\nRecall:%f" % mR)
print("\nF1-Score:%f" % mF1_score)
conmat = confusion_matrix(mlabel, preLabel)
print("\nConfusion Matraics:")
print(conmat)
from Visualization import Visual
matrix = Visual()
matrix.cm_plot(mlabel, preLabel, ['Benign', 'Attack'], '1DCNN_LSTM_2_1')
print('finish image confusion')
print('train time:', duarion)
# ------------------------------------------------------------------------------------------
vis.plot(desired_force, PAM_goal, env.object_goal, PAM_path_predicted,
object_path_actual, object_path_planned, PAM_path_actual,
PAM_path_planned)
if __name__ == '__main__':
rospy.init_node('high_level_controller', anonymous=True)
desiredInput = rospy.Publisher('controlInput', controlInput, queue_size=10)
rospy.Subscriber('feedback',
feedback,
callback,
queue_size=1,
buff_size=2**24)
vis = Visual()
desired_force = force()
object_path_actual = Path()
object_path_actual.header.frame_id = 'frame_0'
PAM_path_actual = Path()
PAM_path_actual.header.frame_id = 'frame_0'
object_path_planned = Path()
PAM_path_planned = Path()
old_walker_state = state()
old_bed_state = state()
old_blue_chair_state = state()
env = environment()
env.example_2()
# object parameters : Rho(4), Omega(3), width(1), length(1) #Rho[0,1,2,3]=[mass, inertia, x_c, y_c]
walker_params = [
print("\n false negatives :%d" % false_negatives)
print("\n" + "=" * 50 + " DataSet Describe " + "=" * 50)
print(
"\nAll DataSet Number:%s Trainging DataSet Number:%s Test DataSet Number:%s"
% (totalnum, trainnum, testnum))
mP = true_positives / (true_positives + false_positives)
mR = true_positives / (true_positives + false_negatives)
mF1_score = 2 * mP * mR / (mP + mR)
print("\nPrecision:%f" % mP)
print("\nRecall:%f" % mR)
print("\nF1-Score:%f" % mF1_score)
conmat = confusion_matrix(mlabel, preLabel)
print("\nConfusion Matraics:")
print(conmat)
# print(len(mlabel))
from Visualization import Visual
matrix = Visual()
matrix.cm_plot(
mlabel, preLabel,
['Benign', 'Bot', 'DDoS', 'DoS', 'Patator', 'PortScan', 'WebAttack'],
'1DCNN_LSTM_7_1')
print('finish image confusion')
print('train time:', duarion)
# ------------------
#
# ------------------------------------------------------------------------
print("\n test accuracy :%f" % (test_accuracy / test_iter))
print("\n true positives :%d" % true_positives)
print("\n false positives :%d" % false_positives)
print("\n true negatives :%d" % true_negatives)
print("\n false negatives :%d" % false_negatives)
print("\n" + "=" * 50 + " DataSet Describe " + "=" * 50)
print("\nAll DataSet Number:%s Trainging DataSet Number:%s Test DataSet Number:%s" % (
totalnum, trainnum, testnum))
mP = true_positives / (true_positives + false_positives)
mR = true_positives / (true_positives + false_negatives)
mF1_score = 2 * mP * mR / (mP + mR)
print("\nPrecision:%f" % mP)
print("\nRecall:%f" % mR)
print("\nF1-Score:%f" % mF1_score)
conmat = confusion_matrix(mlabel, preLabel)
print("\nConfusion Matraics:")
print(conmat)
print(len(mlabel))
from Visualization import Visual
matrix = Visual()
label12=['Benign','Bot','DDoS','DoSGoldenEye','DoSHulk','DoSSlowhttptest','DoSslowloris','FTPPatator','PortScan','SSHPatator','WebAttackBruteForce','WebAttackXSS']
matrix.cm_plot(mlabel,preLabel,label12,'1DCNN_12_1')
print('finish image confusion')
print('train time:',duarion)
# ------------------------------------------------------------------------------------------
print("\ntest cost time :%d" % (time.time() - test_start))
print("\n" + "=" * 50 + "Test result" + "=" * 50)
print("\n test accuracy :%f" % (test_accuracy / test_iter))
print("\n true positives :%d" % true_positives)
print("\n false positives :%d" % false_positives)
print("\n true negatives :%d" % true_negatives)
print("\n false negatives :%d" % false_negatives)
print("\n" + "=" * 50 + " DataSet Describe " + "=" * 50)
print("\nAll DataSet Number:%s Trainging DataSet Number:%s Test DataSet Number:%s" % (
totalnum, trainnum, testnum))
mP = true_positives / (true_positives + false_positives)
mR = true_positives / (true_positives + false_negatives)
mF1_score = 2 * mP * mR / (mP + mR)
print("\nPrecision:%f" % mP)
print("\nRecall:%f" % mR)
print("\nF1-Score:%f" % mF1_score)
conmat = confusion_matrix(mlabel, preLabel)
print("\nConfusion Matraics:")
print(conmat)
print(len(mlabel))
from Visualization import Visual
matrix = Visual()
label12=['Benign','Bot','DDoS','DoSGoldenEye','DoSHulk','DoSSlowhttptest','DoSslowloris','FTPPatator','PortScan','SSHPatator','WebAttackBruteForce','WebAttackXSS']
matrix.cm_plot(mlabel,preLabel,label12,'LSTM_12_1')
print('finish image confusion')
print('train time:',duarion)