In the paper "A Survey on Behaviour Recognition Using WiFi
Channel State Information" you have given that you have also applied HMM on the extracted features using STFT and use the MATLAB toolbox for HMM training. Can I get that matlab code if possible.

Thanks for sharing this project, this is great!
But What is the purpose of the document named "cross_vali_input_data"?

hi,
could you elaborate the sentence above.
and where is the dataset one?
thanks a lot.

I am planning to visualize the data as spectrogram to explore it. If you had converted the data to spectrogram from .csv files, would you mind sharing me the code to convert it? However, if you don't have the spectrogram, would you mind sharing me the original .dat file that you have before you converted it to .csv files?

Hello, thank you for your sharing. I try to run the coding, but there is always an index error that I cannot handle. Could you please help me with that? I would appreciate it.

The error is as follows:

IndexError Traceback (most recent call last)
/var/folders/5x/3g67fwns0mb68s__c_3fk4wr0000gn/T/ipykernel_43899/857709293.py in
10 outputfilename2 = "./input_files/yy_" + str(window_size) + "" + str(threshold) + "" + label + ".csv"
11
---> 12 x, y = dataimport(filepath1, filepath2)
13 with open(outputfilename1, "w") as f:
14 writer = csv.writer(f, lineterminator="\n")

/var/folders/5x/3g67fwns0mb68s__c_3fk4wr0000gn/T/ipykernel_43899/1109332674.py in dataimport(path1, path2)
84 y[k/slide_size,:] = np.array([0,0,0,0,0,0,0,1])
85 else:
---> 86 y[k/slide_size,:] = np.array([2,0,0,0,0,0,0,0])
87 k += slide_size
88

IndexError: only integers, slices (:), ellipsis (...), numpy.newaxis (None) and integer or boolean arrays are valid indices

Thank you for the dataset, which is really helpful to me. Here I have some questions about the dataset.
I found the phase_calibration file in your repositories. May I ask if the phase information in the CSV files is calibrated or not?
What do you do to deal with the raw phase data?

Thanks for sharing this data, this is great! I have a quick question: is the data shared here raw? Has it been preprocessed in any way?

Thanks for your time!

Do you have the code for the test set?

I couldn't find details about the location of the activity (e.g. room A or B) in the csv files.
Do you have this information?

Regards,
Abdo

Hi, I am planning to make some prediction about the CSI data collected by myself. Now I have restored a model graph from those three files, model.ckpt.data-00000-of-00001，model.ckpt.index，model.ckpt.meta. But I don't know how to make prediction. Can you give me some direction? Here is my code:

Hi,

I run your code smoothly until facing the following error:

`
in dataimport(path1, path2)
77 y[k/slide_size,:] = np.array([0,0,0,0,0,0,0,1])
78 else:
---> 79 y[k/slide_size,:] = np.array([2,0,0,0,0,0,0,0])
80 k += slide_size
81

IndexError: only integers, slices (:), ellipsis (...), numpy.newaxis (None) and integer or boolean arrays are valid indices
`
should I use integer division here?

Hi,

I noticed that your team collected data with 1000 samples per second.
could you explain how to achieve this ?

Thanks a lot.

Hello, while I was trying to run cross_vali_data_convert_merge.py, the process of reading the csv files starts with 'input_' is okay, but error occurs when reading the csv files starts with 'annotation'. The details of this error is shown below, thank you in advance if you could help me out! All the best!

input_file_name= ./Dataset/Data/input_bed_170309_1201_19.csv
input_file_name= ./Dataset/Data/input_bed_170321_1325_20.csv
annotation_file_name= ./Dataset/Data/annotation_bed_170308_1405_01.csv
Traceback (most recent call last):
File "cross_vali_data_convert_merge.py", line 106, in
x, y = dataimport(filepath1, filepath2)
File "cross_vali_data_convert_merge.py", line 88, in dataimport
y[k/slide_size,:] = np.array([2,0,0,0,0,0,0,0])
IndexError: only integers, slices (:), ellipsis (...), numpy.newaxis (None) and integer or boolean arrays are valid indices.

I noticed that you sort the input* and annotation* data to make input-output correspondence between the files for creating windows in "cross_vali_data_convert_merge.py" but if I print out the sorted data, there seems to be a discrepancy due to there being no numbers (161219) in sankalp and siamak annotation files names but being present in the input file names. (I am using google colab)

The sorted data is as follows:

#List the sorted data and make sure data has same naming scheme in both Annotation and Input
import glob
sorted(glob.glob("./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed.csv"))
sorted(glob.glob("./drive/My Drive/WifiActivityRecognition/Dataset/input_bed.csv"))

['./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170308_1405_01.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170308_1406_02.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170308_1407_03.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170308_1408_04.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170308_1409_05.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170308_1410_06.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170308_1411_07.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170308_1412_08.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170308_1413_09.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170308_1414_10.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170308_1415_11.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170308_1416_12.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170308_1417_13.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170308_1418_14.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170308_1419_15.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170308_1420_16.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170308_1421_17.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170308_1422_18.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170308_1423_19.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170308_1424_20.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1114_01.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1118_02.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1118_03.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1118_04.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1118_05.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1121_06.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1121_07.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1122_08.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1123_09.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1124_10.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1124_11.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1124_12.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1124_13.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1127_14.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1128_15.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1128_16.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1132_17.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1132_18.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1133_19.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1138_01.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1139_02.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1140_03.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1141_04.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1142_05.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1148_06.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1149_07.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1150_08.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1151_09.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1152_10.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1153_11.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1154_12.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1155_13.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1156_14.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1157_15.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1158_16.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1159_17.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1200_18.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170309_1201_19.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_bed_170321_1325_20.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_sankalp_bed_1.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_sankalp_bed_10.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_sankalp_bed_2.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_sankalp_bed_3.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_sankalp_bed_4.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_sankalp_bed_5.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_sankalp_bed_6.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_sankalp_bed_7.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_sankalp_bed_8.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_sankalp_bed_9.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_siamak_bed_1.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_siamak_bed_10.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_siamak_bed_2.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_siamak_bed_3.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_siamak_bed_4.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_siamak_bed_5.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_siamak_bed_6.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_siamak_bed_7.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_siamak_bed_8.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/annotation_siamak_bed_9.csv']

['./drive/My Drive/WifiActivityRecognition/Dataset/input_161219_sankalp_bed_1.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_161219_sankalp_bed_10.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_161219_sankalp_bed_2.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_161219_sankalp_bed_3.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_161219_sankalp_bed_4.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_161219_sankalp_bed_5.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_161219_sankalp_bed_6.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_161219_sankalp_bed_7.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_161219_sankalp_bed_8.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_161219_sankalp_bed_9.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_161219_siamak_bed_1.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_161219_siamak_bed_10.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_161219_siamak_bed_2.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_161219_siamak_bed_3.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_161219_siamak_bed_4.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_161219_siamak_bed_5.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_161219_siamak_bed_6.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_161219_siamak_bed_7.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_161219_siamak_bed_8.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_161219_siamak_bed_9.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170308_1405_01.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170308_1406_02.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170308_1407_03.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170308_1408_04.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170308_1409_05.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170308_1410_06.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170308_1411_07.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170308_1412_08.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170308_1413_09.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170308_1414_10.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170308_1415_11.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170308_1416_12.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170308_1417_13.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170308_1418_14.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170308_1419_15.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170308_1420_16.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170308_1421_17.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170308_1422_18.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170308_1423_19.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170308_1424_20.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1114_01.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1118_02.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1118_03.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1118_04.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1118_05.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1121_06.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1121_07.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1122_08.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1123_09.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1124_10.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1124_11.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1124_12.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1124_13.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1127_14.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1128_15.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1128_16.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1132_17.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1132_18.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1133_19.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1138_01.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1139_02.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1140_03.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1141_04.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1142_05.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1148_06.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1149_07.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1150_08.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1151_09.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1152_10.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1153_11.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1154_12.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1155_13.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1156_14.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1157_15.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1158_16.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1159_17.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1200_18.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170309_1201_19.csv',
'./drive/My Drive/WifiActivityRecognition/Dataset/input_bed_170321_1325_20.csv']

I execute "cross_vali_recurrent_network_wifi_activity.py" and I got some error
λ python cross_vali_recurrent_network_wifi_activity.py C:\Users\ks812\Anaconda3\lib\site-packages\h5py\__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from floattonp.floatingis deprecated. In future, it will be treated asnp.float64 == np.dtype(float).type`.
from ._conv import register_converters as _register_converters
WARNING:tensorflow:From cross_vali_recurrent_network_wifi_activity.py:79: softmax_cross_entropy_with_logits (from tensorflow.python.ops.nn_ops) is deprecated and will be removed in a future version.
Instructions for updating:

Future major versions of TensorFlow will allow gradients to flow
into the labels input on backprop by default.

See @{tf.nn.softmax_cross_entropy_with_logits_v2}.

csv file importing...
bed finished... xx= (657, 500, 90) yy= (657, 8)
fall finished... xx= (443, 500, 90) yy= (443, 8)
pickup finished... xx= (495, 500, 90) yy= (495, 8)
run finished... xx= (1209, 500, 90) yy= (1209, 8)
sitdown finished... xx= (404, 500, 90) yy= (400, 8)
standup finished... xx= (304, 500, 90) yy= (304, 8)
walk finished... xx= (1465, 500, 90) yy= (1465, 8)
bed = 657 fall= 443 pickup = 495 run= 1209 sitdown= 404 standup= 304 walk= 1465
Traceback (most recent call last):
File "cross_vali_recurrent_network_wifi_activity.py", line 102, in
x_sitdown, y_sitdown = shuffle(x_sitdown, y_sitdown, random_state=0)
File "C:\Users\ks812\Anaconda3\lib\site-packages\sklearn\utils_init_.py", line 343, in shuffle
return resample(*arrays, **options)
File "C:\Users\ks812\Anaconda3\lib\site-packages\sklearn\utils_init_.py", line 258, in resample
check_consistent_length(*arrays)
File "C:\Users\ks812\Anaconda3\lib\site-packages\sklearn\utils\validation.py", line 204, in check_consistent_length
" samples: %r" % [int(l) for l in lengths])
ValueError: Found input variables with inconsistent numbers of samples: [404, 400]`

My Tensorflow (GPU) version is 1.10.0

As you mentioned，92nd - 181st column shows (30 subcarrier * 3 antenna) phase.
But why is the phase value of all subcarriers almost all greater than 2pi?
For example, in "input_161219_sankalp_bed_1.csv", the phase values of all subcarriers are almost between 10 and 15 from 8.5099s to 11.5s, but isn't the value range of phase from 0 to 2pi?

Thank you for sharing the data and code,it's really great! I have a simple question.
The data I saw in the paper are six kinds of activities, but there are seven kinds of activities in the dataset. There is no " lie down" activity. Is bed corresponding to this activity? So pick up is a later activity?
And i also want to know what do the Numbers in the name of the input _filies in the original dataset mean?
The paper says six people did the activity, did six people do each activity or did each activity have different Numbers of participants?
Do each activity for 20 seconds and repeat each activity 20 times. How is the specific file stored?
I would appreciate it if you could give me an answer.
Thank you for your time!

Time series data should never be split randomly as you have done. Sliding windows ensure most of the validation set is at least 80% similar to the training set. You can see this from the validation loss which continues to decrease despite 2000 epochs. Cross validation should be done subject-wise.

i cant find this file in the repo

Is there any way to have access to this dataset?

Thanks!

I really appreciate your work and really want to run the code.
However, when I run cross_vali_data_convert_merge.py, data sitdown class prevent me from training a model. Specificly, the shape of xx and yy are ((7195, 90000), (7187, 8)), the dimension of other classes however match perfectly.

Is there any problem in your collected data? Or something wrong with me.

Hi, there,
I'm recently working on the network using csi data. And I followed https://dhalperi.github.io/linux-80211n-csitool/#publications to create the csi data which is a dat file.
And I'm wondering how to create a csv file like your dataset from a raw data(dat file).

It would be very thankful if somebody answer me.

just one example,
in filepath1 , we sorted the result list, like below

in filepath2 , we also sorted the result list, like below

After generating xx and yy, they are not aligned.
Who knows is there some problem?

What are the purposes of setting the following parameters?

window_size = 1000
threshold = 60
slide_size = 200

Many thanks!

您好，我想请问一下原始 CSI 幅度数据，是一个100090的数据，这个 90 维矢量是由3 个天线和 30 个子载波组成的，请问是否可以把100090数据改为1000303，即将90按顺序划分为30*3？
希望您能看到我的提问，我将感激不尽！

Hi,
Can you show me how did you get *.csv from *.dat file?
And also since your link to the dataset is broken, could you somehow kindly share me your data?
My email address is: [email protected]

Thanks a lot!

Hi, thank you for sharing the code. I'm trying to implement CARM and your code helps a lot.

I'm a little bit confused about the data processing codes in PCA_STFT_visualize.ipynb. Does the data processing method in this script totally equal to the method in CARM paper? np.convolve is used to calculate the constant offset in the script , while the paper says it is calculated by average CSI amplitude for 4 seconds, so I think it refers to simply averaging the amplitude for 4 sec? Besides the H matrix in the paper is built by chunks obtained in 1-second interval which are cut from CSI streams, while the script used another np.convolve whose window_size is 0.1s to build this matrix (or maybe just to smooth the signal, I'm not sure). Could you help explain why these np.convolve are used? Thanks a lot.

I was quite surprised that some value in the columns of 'BG' is negative?
For example,
File name 'input_161219_sankalp_fall_5'
column: BG
row: 267
value: -1.0395

I download the dataset .
when I exec "python3 cross_vali_data_convert_merge.py" I got some error:

annotation_file_name= ../old_version/Dataset/annotation_bed_170308_1405_01.csv
Traceback (most recent call last):
File "cross_vali_data_convert_merge.py", line 107, in
x, y = dataimport(filepath1, filepath2)
File "cross_vali_data_convert_merge.py", line 44, in dataimport
y = np.zeros(((len(tmp2) + 1 - 2 * window_size)/slide_size+1,8))
TypeError: 'float' object cannot be interpreted as an integer

I try fix that ,convert float to int
y = np.zeros(((len(tmp2) + 1 - 2 * window_size)/slide_size+1,8))
to
y = np.zeros((int((len(tmp2) + 1 - 2 * window_size)/slide_size+1),8))

and I got this error

annotation_file_name= ../old_version/Dataset/annotation_bed_170308_1405_01.csv
Traceback (most recent call last):
File "cross_vali_data_convert_merge.py", line 107, in
x, y = dataimport(filepath1, filepath2)
File "cross_vali_data_convert_merge.py", line 89, in dataimport
y[k/slide_size,:] = np.array([2,0,0,0,0,0,0,0])
IndexError: only integers, slices (:), ellipsis (...), numpy.newaxis (None) and integer or boolean arrays are valid indices

I am a novice in machine learning. After running the code, I want to know how to write the calling function.
Thank you for your time.

Hi,
Thank you for the new dataset. Unfortunately, somehow I got "xx = np.concatenate((xx,x2),axis=0) MemoryError" when converting your dataset. I have tried with different window_size and slide_size but the error persist. My machine has 16GB of RAM. Do you have any idea of resolving this?
Thanks a lot!

I am trying to use this dataset to train lstm model. I need some clarity on dataset used for training.

1. Dataset has Noactivity annotations but is there a reason for not including it in lstm classifier?
2. Is Mexico files in dataset are collected at a single building using similar CSI capture setup?

Thanks

Just to make sure that I'm doing this right:
I switched this:

To this:

Since I was getting this error message:

Also, do I need to run this code in order to see your data 'PCA_STFT_visualize.ipynb' in jupyter notebook or can I already visualize it? Any help is appreciated, Thanks!

Dear authors,

Firstly, thanks for sharing the dataset and the code. While running the file "cross_vali_data_convert_merge", it reads the input files but it returns the following error when reading the annotation files.

`cross_vali_data_convert_merge.py', wdir='H:/traces/wlan-csi-stanford')
input_file_name= ./Dataset\input_161219_siamak_bed_1.dat.csv
input_file_name= ./Dataset\input_161219_siamak_bed_10.dat.csv
input_file_name= ./Dataset\input_161219_siamak_bed_2.dat.csv
input_file_name= ./Dataset\input_161219_siamak_bed_3.dat.csv
input_file_name= ./Dataset\input_161219_siamak_bed_4.dat.csv
input_file_name= ./Dataset\input_161219_siamak_bed_5.dat.csv
input_file_name= ./Dataset\input_161219_siamak_bed_6.dat.csv
input_file_name= ./Dataset\input_161219_siamak_bed_7.dat.csv
input_file_name= ./Dataset\input_161219_siamak_bed_8.dat.csv
input_file_name= ./Dataset\input_161219_siamak_bed_9.dat.csv
annotation_file_name= ./Dataset\annotation_siamak_bed_1.csv
Traceback (most recent call last):

File "", line 1, in
runfile('H:/traces/wlan-csi-stanford/cross_vali_data_convert_merge.py', wdir='H:/traces/wlan-csi-stanford')

File "C:\Users\Muhammad\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 710, in runfile
execfile(filename, namespace)

File "C:\Users\Muhammad\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 101, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)

File "H:/traces/wlan-csi-stanford/cross_vali_data_convert_merge.py", line 107, in
x, y = dataimport(filepath1, filepath2)

File "H:/traces/wlan-csi-stanford/cross_vali_data_convert_merge.py", line 43, in dataimport
y = np.zeros(((len(tmp2) + 1 - 2 * window_size)/slide_size+1,8))

TypeError: 'float' object cannot be interpreted as an integer`

Hi, I am looking for the .dat files from which CSV in Dataset are generated, Could you please share the link?

Hi Hirokazu Narui, I notice there are some error files after downloading your data set as follows: https://drive.google.com/file/d/1DwCGKJmqf2Vajliow8rTqVWpIusjuui7/view?usp=sharing
Please re-check and update a better and fuller version of the data set. Thank you very much !!!

Hi,

I am trying to look the the practical aspect of using CSI. To this end, I separated the NoActivity data from the given activities and trained the RNN model to classify 8 activities (including NoActivity) and made it work in real time. Although the performance on the dataset in quite good, in practical environment, it does not perform well. The type of environment and disturbances outside the LOS of the transmitter and Receiver also cause the output to change.

I do not know how exactly your 'sitdown', 'standup' or 'fall' activities were performed or how your environment was, but if I try doing these in my room, it can hardly classify them correctly.

I am going to try using directional antennas and changing other aspects (like increasing frequency back to 1kHz and decreasing the number of activities to classify). Can you suggest something else to make it more robust in practical environments?

Just what the title says. I checked that file in my "Dataset" folder and seems to match the same file that is linked in the repository. Any help would be appreciated. Thanks!

Traceback (most recent call last):
File "./test_wu/cross_vali_data_convert_merge.py", line 108, in
x, y = dataimport(filepath1, filepath2)
File "./test_wu/cross_vali_data_convert_merge.py", line 33, in dataimport
xx = xx.reshape(len(xx),-1)
ValueError: cannot reshape array of size 0 into shape (0,newaxis)

How can I solve this problem?

Thanks a lot!

Thanks for your data. I have a few questions on settings of the CSI tool
First, what is the exact centre frequency for 2.4Ghz and 5Ghz since each band has multiple channels.
For example, channel 44 is about 5.25Ghz.
Second, since Intel5300 NIC has three antennas , for each antennas which channel it works on.
For example ,the collected data has 181 columns. Data from 1 to 90 are assigned to three antennas. 1 to 30 is antenna one that works on 2.4Ghz

I am looking forward to your reply.

The data set download result is DataSet.tar_2,Run the program, the result is an error， what should I do?