def __getitem__(self, index):
assert (index < self._dataset_size)
#if self._is_for_train: # random
# index = random.randint(0, self._dataset_size-1)
# get sample data
data = self._data[index] / 1000
data = list(data)
data_reverse = copy.deepcopy(data)
data_reverse.reverse()
filt_rri1 = list(moving_average(RRi(data), order=1))
filt_rri2 = list(moving_average(RRi(data), order=2))
filt_rri3 = list(moving_average(RRi(data), order=3))
filt_rri1_reverse = copy.deepcopy(filt_rri1)
filt_rri2_reverse = copy.deepcopy(filt_rri2)
filt_rri3_reverse = copy.deepcopy(filt_rri3)
filt_rri1_reverse.reverse()
filt_rri2_reverse.reverse()
filt_rri3_reverse.reverse()
order_data = [filt_rri1, filt_rri2, filt_rri3]
order_data_reverse = [
filt_rri1_reverse, filt_rri2_reverse, filt_rri3_reverse
]
label = int(self._label[index])
subject = self._subject[index]
mean = self._mean_train[index]
sdnn = self._sdnn_train[index]
pnn50 = self._pnn50_train[index]
rmssd = self._rmssd_train[index]
lnrmssd = self._lnrmssd_train[index]
vlf = self._vlf_train[index]
lf = self._lf_train[index]
hf = self._hf_train[index]
rlh = self._rlh_train[index]
features = list(np.stack((mean, sdnn, pnn50, rmssd, lnrmssd, \
vlf, lf, hf, rlh )))
makeup_length = 512 - len(data)
if len(data) > 512:
data = data[:512]
else:
data.extend(0 for _ in range(makeup_length))
return data, data_reverse, order_data, order_data_reverse, label, subject, features
def test_moving_average_order_3(self):
fake_rri = np.array([810, 830, 860, 790, 804])
rri_filt = moving_average(fake_rri, order=3)
expected = [810, 833.33, 826.66, 818, 804]
np.testing.assert_almost_equal(rri_filt, expected, decimal=2)
def test_moving_average_order_5(self):
fake_rri = np.array([810, 830, 860, 790, 804, 801, 800])
rri_filt = moving_average(fake_rri, order=5)
expected = [810, 830, 818.79, 817.0, 811.0, 801, 800]
np.testing.assert_almost_equal(rri_filt, expected, decimal=2)
def preprocess_hr_signal(raw_signal,
fs,
sig_len,
desired_fs: int = 1,
interval: int = 1):
"""
correct sampling bias by making a frequency shift, moving average filter and threshold LPF
:param raw_signal: signal to be preprocessed
:param fs: the raw_signal's sampling frequency
:param sig_len: raw signal's number of samples
:param desired_fs: desired sampling frequency
:param interval: window for moving average filter
:return: processed signal
"""
# interval in hours
signal = Waveforms.frequency_shift(raw_signal, sig_len, fs, desired_fs)
signal = pos_sig(signal)
if np.isnan(signal).all():
return np.nan
signal = RRi(signal)
window = desired_fs * interval * 3600
return threshold_filter(moving_average(signal, window),
threshold='strong')