Hugging Face's logo

Megha31
/
Human_Activity_Recognition_Using_Smartphone

Model card Files Community
Megha31 commited on
Commit
26c25d6
·
1 Parent(s): f43434d

DL

Browse files
Files changed (1) hide show
  1. HAR_Part_3.ipynb +1583 -0
HAR_Part_3.ipynb ADDED
@@ -0,0 +1,1583 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "nbformat": 4,
3
+ "nbformat_minor": 0,
4
+ "metadata": {
5
+ "colab": {
6
+ "provenance": []
7
+ },
8
+ "kernelspec": {
9
+ "name": "python3",
10
+ "display_name": "Python 3"
11
+ },
12
+ "language_info": {
13
+ "name": "python"
14
+ },
15
+ "accelerator": "GPU",
16
+ "gpuClass": "standard"
17
+ },
18
+ "cells": [
19
+ {
20
+ "cell_type": "markdown",
21
+ "source": [
22
+ "# Applying LSTM Models on Raw Data"
23
+ ],
24
+ "metadata": {
25
+ "id": "jUkGXVGfU1xN"
26
+ }
27
+ },
28
+ {
29
+ "cell_type": "code",
30
+ "execution_count": null,
31
+ "metadata": {
32
+ "id": "7USnX2QTSuKt"
33
+ },
34
+ "outputs": [],
35
+ "source": [
36
+ "# Importing Libraries\n",
37
+ "\n",
38
+ "import pandas as pd\n",
39
+ "import numpy as np\n",
40
+ "\n",
41
+ "# Import Keras\n",
42
+ "from keras import backend as K\n",
43
+ "from keras.models import Sequential\n",
44
+ "from keras.layers import LSTM\n",
45
+ "from keras.layers.core import Dense, Dropout\n",
46
+ "from keras.layers import BatchNormalization\n",
47
+ "from keras.regularizers import L1L2"
48
+ ]
49
+ },
50
+ {
51
+ "cell_type": "code",
52
+ "source": [
53
+ "# Activities are the class labels\n",
54
+ "# It is a 6 class classification\n",
55
+ "ACTIVITIES = {\n",
56
+ " 0: 'WALKING',\n",
57
+ " 1: 'WALKING_UPSTAIRS',\n",
58
+ " 2: 'WALKING_DOWNSTAIRS',\n",
59
+ " 3: 'SITTING',\n",
60
+ " 4: 'STANDING',\n",
61
+ " 5: 'LAYING',\n",
62
+ "}"
63
+ ],
64
+ "metadata": {
65
+ "id": "UklmP7-eU9Wm"
66
+ },
67
+ "execution_count": null,
68
+ "outputs": []
69
+ },
70
+ {
71
+ "cell_type": "code",
72
+ "source": [
73
+ "import matplotlib.pyplot as plt\n",
74
+ "import seaborn as sns\n",
75
+ "\n",
76
+ "# function to print the confusion matrix\n",
77
+ "\n",
78
+ "def confusion_matrix(Y_true, Y_pred):\n",
79
+ " \n",
80
+ " Y_true = pd.Series([ACTIVITIES[y] for y in np.argmax(Y_true, axis=1)])\n",
81
+ " Y_pred = pd.Series([ACTIVITIES[y] for y in np.argmax(Y_pred, axis=1)])\n",
82
+ "\n",
83
+ " return pd.crosstab(Y_true, Y_pred, rownames=['True'], colnames=['Pred'])\n",
84
+ "\n",
85
+ " \n",
86
+ " result = confusion_matrix(Y_true, Y_pred)\n",
87
+ "\n",
88
+ " plt.figure(figsize=(10, 8))\n",
89
+ " sns.heatmap(result, \n",
90
+ " xticklabels= list(ACTIVITIES.values()), \n",
91
+ " yticklabels=list(ACTIVITIES.values()), \n",
92
+ " annot=True, fmt=\"d\");\n",
93
+ " plt.title(\"Confusion matrix\")\n",
94
+ " plt.ylabel('True label')\n",
95
+ " plt.xlabel('Predicted label')\n",
96
+ " plt.show() "
97
+ ],
98
+ "metadata": {
99
+ "id": "cG79tQGXVASE"
100
+ },
101
+ "execution_count": null,
102
+ "outputs": []
103
+ },
104
+ {
105
+ "cell_type": "markdown",
106
+ "source": [
107
+ "### Loading Data"
108
+ ],
109
+ "metadata": {
110
+ "id": "dfbEhMvGVG4K"
111
+ }
112
+ },
113
+ {
114
+ "cell_type": "code",
115
+ "source": [
116
+ "# Data directory\n",
117
+ "DATADIR = 'UCI_HAR_Dataset'\n",
118
+ "\n",
119
+ "# Raw data signals\n",
120
+ "# Signals are from Accelerometer and Gyroscope\n",
121
+ "# The signals are in x,y,z directions\n",
122
+ "# Sensor signals are filtered to have only body acceleration\n",
123
+ "# excluding the acceleration due to gravity\n",
124
+ "# Triaxial acceleration from the accelerometer is total acceleration\n",
125
+ "SIGNALS = [\n",
126
+ " \"body_acc_x\",\n",
127
+ " \"body_acc_y\",\n",
128
+ " \"body_acc_z\",\n",
129
+ " \"body_gyro_x\",\n",
130
+ " \"body_gyro_y\",\n",
131
+ " \"body_gyro_z\",\n",
132
+ " \"total_acc_x\",\n",
133
+ " \"total_acc_y\",\n",
134
+ " \"total_acc_z\"\n",
135
+ " ]"
136
+ ],
137
+ "metadata": {
138
+ "id": "W6E6gq2tVJjl"
139
+ },
140
+ "execution_count": null,
141
+ "outputs": []
142
+ },
143
+ {
144
+ "cell_type": "code",
145
+ "source": [
146
+ "# define a function to read the data from csv file\n",
147
+ "def _read_csv(filename):\n",
148
+ " return pd.read_csv(filename, delim_whitespace=True, header=None)\n",
149
+ "\n",
150
+ "# function to load the load\n",
151
+ "def load_signals(subset):\n",
152
+ " signals_data = []\n",
153
+ "\n",
154
+ " for signal in SIGNALS:\n",
155
+ " filename = f'/content/drive/MyDrive/UCI_HAR_Dataset/{subset}/Inertial Signals/{signal}_{subset}.txt'\n",
156
+ " signals_data.append(\n",
157
+ " _read_csv(filename).to_numpy()\n",
158
+ " ) \n",
159
+ "\n",
160
+ " # Transpose is used to change the dimensionality of the output,\n",
161
+ " # aggregating the signals by combination of sample/timestep.\n",
162
+ " # Resultant shape is (7352 train/2947 test samples, 128 timesteps, 9 signals)\n",
163
+ " return np.transpose(signals_data, (1, 2, 0))"
164
+ ],
165
+ "metadata": {
166
+ "id": "Gbp0kyOLVO13"
167
+ },
168
+ "execution_count": null,
169
+ "outputs": []
170
+ },
171
+ {
172
+ "cell_type": "code",
173
+ "source": [
174
+ "def load_y(subset):\n",
175
+ " \"\"\"\n",
176
+ " The objective that we are trying to predict is a integer, from 1 to 6,\n",
177
+ " that represents a human activity. We return a binary representation of \n",
178
+ " every sample objective as a 6 bits vector using One Hot Encoding\n",
179
+ " (https://pandas.pydata.org/pandas-docs/stable/generated/pandas.get_dummies.html)\n",
180
+ " \"\"\"\n",
181
+ " filename = f'/content/drive/MyDrive/UCI_HAR_Dataset/{subset}/y_{subset}.txt'\n",
182
+ " y = _read_csv(filename)[0]\n",
183
+ "\n",
184
+ " return pd.get_dummies(y).to_numpy()"
185
+ ],
186
+ "metadata": {
187
+ "id": "MOXrPORRVRcJ"
188
+ },
189
+ "execution_count": null,
190
+ "outputs": []
191
+ },
192
+ {
193
+ "cell_type": "code",
194
+ "source": [
195
+ "def load_data():\n",
196
+ " \"\"\"\n",
197
+ " Obtain the dataset from multiple files.\n",
198
+ " Returns: X_train, X_test, y_train, y_test\n",
199
+ " \"\"\"\n",
200
+ " X_train, X_test = load_signals('train'), load_signals('test')\n",
201
+ " y_train, y_test = load_y('train'), load_y('test')\n",
202
+ "\n",
203
+ " return X_train, X_test, y_train, y_test"
204
+ ],
205
+ "metadata": {
206
+ "id": "MEf5hg9lVTun"
207
+ },
208
+ "execution_count": null,
209
+ "outputs": []
210
+ },
211
+ {
212
+ "cell_type": "code",
213
+ "source": [
214
+ "# Importing tensorflow\n",
215
+ "np.random.seed(42)\n",
216
+ "import tensorflow as tf\n",
217
+ "tf.random.set_seed(42)"
218
+ ],
219
+ "metadata": {
220
+ "id": "Edexn_grVWug"
221
+ },
222
+ "execution_count": null,
223
+ "outputs": []
224
+ },
225
+ {
226
+ "cell_type": "code",
227
+ "source": [
228
+ "# Initializing parameters\n",
229
+ "epochs = 30\n",
230
+ "batch_size = 16\n",
231
+ "n_hidden = 32"
232
+ ],
233
+ "metadata": {
234
+ "id": "B4dT-A4bVapl"
235
+ },
236
+ "execution_count": null,
237
+ "outputs": []
238
+ },
239
+ {
240
+ "cell_type": "code",
241
+ "source": [
242
+ "#function to count the number of classes\n",
243
+ "def _count_classes(y):\n",
244
+ " return len(set([tuple(category) for category in y]))"
245
+ ],
246
+ "metadata": {
247
+ "id": "5D6pcPuVVbyl"
248
+ },
249
+ "execution_count": null,
250
+ "outputs": []
251
+ },
252
+ {
253
+ "cell_type": "code",
254
+ "source": [
255
+ "# Loading the train and test data\n",
256
+ "X_train, X_test, y_train, y_test = load_data()"
257
+ ],
258
+ "metadata": {
259
+ "id": "VUoSMvSfVga3"
260
+ },
261
+ "execution_count": null,
262
+ "outputs": []
263
+ },
264
+ {
265
+ "cell_type": "code",
266
+ "source": [
267
+ "timesteps = len(X_train[0])\n",
268
+ "input_dim = len(X_train[0][0])\n",
269
+ "n_classes = _count_classes(y_train)\n",
270
+ "\n",
271
+ "print(timesteps)\n",
272
+ "print(input_dim)\n",
273
+ "print(len(X_train))"
274
+ ],
275
+ "metadata": {
276
+ "colab": {
277
+ "base_uri": "https://localhost:8080/"
278
+ },
279
+ "id": "MXby1ubyVjBV",
280
+ "outputId": "8f44a692-57c1-4df3-b11f-251c4979e19e"
281
+ },
282
+ "execution_count": null,
283
+ "outputs": [
284
+ {
285
+ "output_type": "stream",
286
+ "name": "stdout",
287
+ "text": [
288
+ "128\n",
289
+ "9\n",
290
+ "7352\n"
291
+ ]
292
+ }
293
+ ]
294
+ },
295
+ {
296
+ "cell_type": "markdown",
297
+ "source": [
298
+ " 1. Defining the Architecture of 1-Layer of LSTM"
299
+ ],
300
+ "metadata": {
301
+ "id": "m182sLnyVl0K"
302
+ }
303
+ },
304
+ {
305
+ "cell_type": "code",
306
+ "source": [
307
+ "# Initiliazing the sequential model\n",
308
+ "model = Sequential()\n",
309
+ "# Configuring the parameters\n",
310
+ "model.add(LSTM(n_hidden, input_shape=(timesteps, input_dim)))\n",
311
+ "# Adding a dropout layer\n",
312
+ "model.add(Dropout(0.5))\n",
313
+ "# Adding a dense output layer with sigmoid activation\n",
314
+ "model.add(Dense(n_classes, activation='sigmoid'))\n",
315
+ "model.summary()"
316
+ ],
317
+ "metadata": {
318
+ "colab": {
319
+ "base_uri": "https://localhost:8080/"
320
+ },
321
+ "id": "BGD2Lt3MVnK5",
322
+ "outputId": "f7ece6dd-85c8-4d41-a713-540bea33ddf0"
323
+ },
324
+ "execution_count": null,
325
+ "outputs": [
326
+ {
327
+ "output_type": "stream",
328
+ "name": "stdout",
329
+ "text": [
330
+ "Model: \"sequential_3\"\n",
331
+ "_________________________________________________________________\n",
332
+ " Layer (type) Output Shape Param # \n",
333
+ "=================================================================\n",
334
+ " lstm_5 (LSTM) (None, 32) 5376 \n",
335
+ " \n",
336
+ " dropout_5 (Dropout) (None, 32) 0 \n",
337
+ " \n",
338
+ " dense_3 (Dense) (None, 6) 198 \n",
339
+ " \n",
340
+ "=================================================================\n",
341
+ "Total params: 5,574\n",
342
+ "Trainable params: 5,574\n",
343
+ "Non-trainable params: 0\n",
344
+ "_________________________________________________________________\n"
345
+ ]
346
+ }
347
+ ]
348
+ },
349
+ {
350
+ "cell_type": "code",
351
+ "source": [
352
+ "# Compiling the model\n",
353
+ "model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])"
354
+ ],
355
+ "metadata": {
356
+ "id": "MIX8hyRoVrSs"
357
+ },
358
+ "execution_count": null,
359
+ "outputs": []
360
+ },
361
+ {
362
+ "cell_type": "code",
363
+ "source": [
364
+ "# Training the model\n",
365
+ "model.fit(X_train, y_train, batch_size=batch_size, validation_data=(X_test, y_test),epochs=epochs)"
366
+ ],
367
+ "metadata": {
368
+ "colab": {
369
+ "base_uri": "https://localhost:8080/"
370
+ },
371
+ "id": "RxoV_8fdVt7u",
372
+ "outputId": "fc88555b-3bcc-47b6-f10e-1aa6d752887e"
373
+ },
374
+ "execution_count": null,
375
+ "outputs": [
376
+ {
377
+ "output_type": "stream",
378
+ "name": "stdout",
379
+ "text": [
380
+ "Epoch 1/30\n",
381
+ "460/460 [==============================] - 8s 11ms/step - loss: 1.0781 - accuracy: 0.5423 - val_loss: 0.9016 - val_accuracy: 0.6213\n",
382
+ "Epoch 2/30\n",
383
+ "460/460 [==============================] - 4s 10ms/step - loss: 0.7431 - accuracy: 0.6632 - val_loss: 0.6547 - val_accuracy: 0.7255\n",
384
+ "Epoch 3/30\n",
385
+ "460/460 [==============================] - 5s 12ms/step - loss: 0.5874 - accuracy: 0.7629 - val_loss: 0.5316 - val_accuracy: 0.7906\n",
386
+ "Epoch 4/30\n",
387
+ "460/460 [==============================] - 4s 8ms/step - loss: 0.4666 - accuracy: 0.8320 - val_loss: 1.4815 - val_accuracy: 0.6155\n",
388
+ "Epoch 5/30\n",
389
+ "460/460 [==============================] - 4s 8ms/step - loss: 0.3551 - accuracy: 0.8863 - val_loss: 0.4364 - val_accuracy: 0.8483\n",
390
+ "Epoch 6/30\n",
391
+ "460/460 [==============================] - 6s 12ms/step - loss: 0.2936 - accuracy: 0.9067 - val_loss: 0.3727 - val_accuracy: 0.8765\n",
392
+ "Epoch 7/30\n",
393
+ "460/460 [==============================] - 4s 8ms/step - loss: 0.2671 - accuracy: 0.9174 - val_loss: 0.4289 - val_accuracy: 0.8639\n",
394
+ "Epoch 8/30\n",
395
+ "460/460 [==============================] - 4s 8ms/step - loss: 0.2423 - accuracy: 0.9266 - val_loss: 0.3437 - val_accuracy: 0.8711\n",
396
+ "Epoch 9/30\n",
397
+ "460/460 [==============================] - 5s 11ms/step - loss: 0.2158 - accuracy: 0.9293 - val_loss: 0.3924 - val_accuracy: 0.8826\n",
398
+ "Epoch 10/30\n",
399
+ "460/460 [==============================] - 4s 10ms/step - loss: 0.2087 - accuracy: 0.9343 - val_loss: 0.3207 - val_accuracy: 0.8856\n",
400
+ "Epoch 11/30\n",
401
+ "460/460 [==============================] - 4s 10ms/step - loss: 0.1990 - accuracy: 0.9344 - val_loss: 0.3968 - val_accuracy: 0.8704\n",
402
+ "Epoch 12/30\n",
403
+ "460/460 [==============================] - 5s 11ms/step - loss: 0.1726 - accuracy: 0.9376 - val_loss: 0.2942 - val_accuracy: 0.8931\n",
404
+ "Epoch 13/30\n",
405
+ "460/460 [==============================] - 4s 9ms/step - loss: 0.1755 - accuracy: 0.9414 - val_loss: 0.2492 - val_accuracy: 0.9002\n",
406
+ "Epoch 14/30\n",
407
+ "460/460 [==============================] - 4s 10ms/step - loss: 0.1585 - accuracy: 0.9465 - val_loss: 0.3617 - val_accuracy: 0.8904\n",
408
+ "Epoch 15/30\n",
409
+ "460/460 [==============================] - 5s 11ms/step - loss: 0.1629 - accuracy: 0.9468 - val_loss: 0.5414 - val_accuracy: 0.8724\n",
410
+ "Epoch 16/30\n",
411
+ "460/460 [==============================] - 4s 8ms/step - loss: 0.1647 - accuracy: 0.9479 - val_loss: 0.3329 - val_accuracy: 0.8979\n",
412
+ "Epoch 17/30\n",
413
+ "460/460 [==============================] - 4s 8ms/step - loss: 0.1531 - accuracy: 0.9486 - val_loss: 0.3276 - val_accuracy: 0.9043\n",
414
+ "Epoch 18/30\n",
415
+ "460/460 [==============================] - 4s 10ms/step - loss: 0.1623 - accuracy: 0.9459 - val_loss: 0.2336 - val_accuracy: 0.9125\n",
416
+ "Epoch 19/30\n",
417
+ "460/460 [==============================] - 4s 9ms/step - loss: 0.1494 - accuracy: 0.9489 - val_loss: 0.3656 - val_accuracy: 0.9013\n",
418
+ "Epoch 20/30\n",
419
+ "460/460 [==============================] - 4s 8ms/step - loss: 0.1543 - accuracy: 0.9480 - val_loss: 0.3468 - val_accuracy: 0.9016\n",
420
+ "Epoch 21/30\n",
421
+ "460/460 [==============================] - 4s 9ms/step - loss: 0.1398 - accuracy: 0.9490 - val_loss: 0.3211 - val_accuracy: 0.9057\n",
422
+ "Epoch 22/30\n",
423
+ "460/460 [==============================] - 5s 10ms/step - loss: 0.1520 - accuracy: 0.9479 - val_loss: 0.2789 - val_accuracy: 0.9067\n",
424
+ "Epoch 23/30\n",
425
+ "460/460 [==============================] - 4s 8ms/step - loss: 0.1479 - accuracy: 0.9475 - val_loss: 0.2733 - val_accuracy: 0.9074\n",
426
+ "Epoch 24/30\n",
427
+ "460/460 [==============================] - 4s 10ms/step - loss: 0.1425 - accuracy: 0.9493 - val_loss: 0.3381 - val_accuracy: 0.9036\n",
428
+ "Epoch 25/30\n",
429
+ "460/460 [==============================] - 5s 12ms/step - loss: 0.1437 - accuracy: 0.9504 - val_loss: 0.3459 - val_accuracy: 0.8921\n",
430
+ "Epoch 26/30\n",
431
+ "460/460 [==============================] - 4s 8ms/step - loss: 0.1390 - accuracy: 0.9497 - val_loss: 0.3192 - val_accuracy: 0.9074\n",
432
+ "Epoch 27/30\n",
433
+ "460/460 [==============================] - 4s 10ms/step - loss: 0.1361 - accuracy: 0.9520 - val_loss: 0.3324 - val_accuracy: 0.9189\n",
434
+ "Epoch 28/30\n",
435
+ "460/460 [==============================] - 6s 12ms/step - loss: 0.1469 - accuracy: 0.9509 - val_loss: 0.3501 - val_accuracy: 0.9097\n",
436
+ "Epoch 29/30\n",
437
+ "460/460 [==============================] - 5s 10ms/step - loss: 0.1439 - accuracy: 0.9438 - val_loss: 0.2556 - val_accuracy: 0.9308\n",
438
+ "Epoch 30/30\n",
439
+ "460/460 [==============================] - 4s 10ms/step - loss: 0.1434 - accuracy: 0.9486 - val_loss: 0.3141 - val_accuracy: 0.9165\n"
440
+ ]
441
+ },
442
+ {
443
+ "output_type": "execute_result",
444
+ "data": {
445
+ "text/plain": [
446
+ "<keras.callbacks.History at 0x7f78fa564e80>"
447
+ ]
448
+ },
449
+ "metadata": {},
450
+ "execution_count": 52
451
+ }
452
+ ]
453
+ },
454
+ {
455
+ "cell_type": "code",
456
+ "source": [
457
+ "# Confusion Matrix\n",
458
+ "confusion_matrix(y_test, model.predict(X_test))"
459
+ ],
460
+ "metadata": {
461
+ "colab": {
462
+ "base_uri": "https://localhost:8080/",
463
+ "height": 286
464
+ },
465
+ "id": "Pl6Y6R3zVwzE",
466
+ "outputId": "d50b38f5-1af7-4cd8-c5f5-771190191675"
467
+ },
468
+ "execution_count": null,
469
+ "outputs": [
470
+ {
471
+ "output_type": "stream",
472
+ "name": "stdout",
473
+ "text": [
474
+ "93/93 [==============================] - 1s 4ms/step\n"
475
+ ]
476
+ },
477
+ {
478
+ "output_type": "execute_result",
479
+ "data": {
480
+ "text/plain": [
481
+ "Pred LAYING SITTING STANDING WALKING WALKING_DOWNSTAIRS \\\n",
482
+ "True \n",
483
+ "LAYING 511 0 26 0 0 \n",
484
+ "SITTING 1 409 76 4 0 \n",
485
+ "STANDING 0 95 433 4 0 \n",
486
+ "WALKING 0 0 0 480 15 \n",
487
+ "WALKING_DOWNSTAIRS 0 0 0 0 419 \n",
488
+ "WALKING_UPSTAIRS 0 1 0 12 9 \n",
489
+ "\n",
490
+ "Pred WALKING_UPSTAIRS \n",
491
+ "True \n",
492
+ "LAYING 0 \n",
493
+ "SITTING 1 \n",
494
+ "STANDING 0 \n",
495
+ "WALKING 1 \n",
496
+ "WALKING_DOWNSTAIRS 1 \n",
497
+ "WALKING_UPSTAIRS 449 "
498
+ ],
499
+ "text/html": [
500
+ "\n",
501
+ " <div id=\"df-ebce1837-967c-4ffc-872b-b24d45f84c89\">\n",
502
+ " <div class=\"colab-df-container\">\n",
503
+ " <div>\n",
504
+ "<style scoped>\n",
505
+ " .dataframe tbody tr th:only-of-type {\n",
506
+ " vertical-align: middle;\n",
507
+ " }\n",
508
+ "\n",
509
+ " .dataframe tbody tr th {\n",
510
+ " vertical-align: top;\n",
511
+ " }\n",
512
+ "\n",
513
+ " .dataframe thead th {\n",
514
+ " text-align: right;\n",
515
+ " }\n",
516
+ "</style>\n",
517
+ "<table border=\"1\" class=\"dataframe\">\n",
518
+ " <thead>\n",
519
+ " <tr style=\"text-align: right;\">\n",
520
+ " <th>Pred</th>\n",
521
+ " <th>LAYING</th>\n",
522
+ " <th>SITTING</th>\n",
523
+ " <th>STANDING</th>\n",
524
+ " <th>WALKING</th>\n",
525
+ " <th>WALKING_DOWNSTAIRS</th>\n",
526
+ " <th>WALKING_UPSTAIRS</th>\n",
527
+ " </tr>\n",
528
+ " <tr>\n",
529
+ " <th>True</th>\n",
530
+ " <th></th>\n",
531
+ " <th></th>\n",
532
+ " <th></th>\n",
533
+ " <th></th>\n",
534
+ " <th></th>\n",
535
+ " <th></th>\n",
536
+ " </tr>\n",
537
+ " </thead>\n",
538
+ " <tbody>\n",
539
+ " <tr>\n",
540
+ " <th>LAYING</th>\n",
541
+ " <td>511</td>\n",
542
+ " <td>0</td>\n",
543
+ " <td>26</td>\n",
544
+ " <td>0</td>\n",
545
+ " <td>0</td>\n",
546
+ " <td>0</td>\n",
547
+ " </tr>\n",
548
+ " <tr>\n",
549
+ " <th>SITTING</th>\n",
550
+ " <td>1</td>\n",
551
+ " <td>409</td>\n",
552
+ " <td>76</td>\n",
553
+ " <td>4</td>\n",
554
+ " <td>0</td>\n",
555
+ " <td>1</td>\n",
556
+ " </tr>\n",
557
+ " <tr>\n",
558
+ " <th>STANDING</th>\n",
559
+ " <td>0</td>\n",
560
+ " <td>95</td>\n",
561
+ " <td>433</td>\n",
562
+ " <td>4</td>\n",
563
+ " <td>0</td>\n",
564
+ " <td>0</td>\n",
565
+ " </tr>\n",
566
+ " <tr>\n",
567
+ " <th>WALKING</th>\n",
568
+ " <td>0</td>\n",
569
+ " <td>0</td>\n",
570
+ " <td>0</td>\n",
571
+ " <td>480</td>\n",
572
+ " <td>15</td>\n",
573
+ " <td>1</td>\n",
574
+ " </tr>\n",
575
+ " <tr>\n",
576
+ " <th>WALKING_DOWNSTAIRS</th>\n",
577
+ " <td>0</td>\n",
578
+ " <td>0</td>\n",
579
+ " <td>0</td>\n",
580
+ " <td>0</td>\n",
581
+ " <td>419</td>\n",
582
+ " <td>1</td>\n",
583
+ " </tr>\n",
584
+ " <tr>\n",
585
+ " <th>WALKING_UPSTAIRS</th>\n",
586
+ " <td>0</td>\n",
587
+ " <td>1</td>\n",
588
+ " <td>0</td>\n",
589
+ " <td>12</td>\n",
590
+ " <td>9</td>\n",
591
+ " <td>449</td>\n",
592
+ " </tr>\n",
593
+ " </tbody>\n",
594
+ "</table>\n",
595
+ "</div>\n",
596
+ " <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-ebce1837-967c-4ffc-872b-b24d45f84c89')\"\n",
597
+ " title=\"Convert this dataframe to an interactive table.\"\n",
598
+ " style=\"display:none;\">\n",
599
+ " \n",
600
+ " <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
601
+ " width=\"24px\">\n",
602
+ " <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
603
+ " <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
604
+ " </svg>\n",
605
+ " </button>\n",
606
+ " \n",
607
+ " <style>\n",
608
+ " .colab-df-container {\n",
609
+ " display:flex;\n",
610
+ " flex-wrap:wrap;\n",
611
+ " gap: 12px;\n",
612
+ " }\n",
613
+ "\n",
614
+ " .colab-df-convert {\n",
615
+ " background-color: #E8F0FE;\n",
616
+ " border: none;\n",
617
+ " border-radius: 50%;\n",
618
+ " cursor: pointer;\n",
619
+ " display: none;\n",
620
+ " fill: #1967D2;\n",
621
+ " height: 32px;\n",
622
+ " padding: 0 0 0 0;\n",
623
+ " width: 32px;\n",
624
+ " }\n",
625
+ "\n",
626
+ " .colab-df-convert:hover {\n",
627
+ " background-color: #E2EBFA;\n",
628
+ " box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
629
+ " fill: #174EA6;\n",
630
+ " }\n",
631
+ "\n",
632
+ " [theme=dark] .colab-df-convert {\n",
633
+ " background-color: #3B4455;\n",
634
+ " fill: #D2E3FC;\n",
635
+ " }\n",
636
+ "\n",
637
+ " [theme=dark] .colab-df-convert:hover {\n",
638
+ " background-color: #434B5C;\n",
639
+ " box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
640
+ " filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
641
+ " fill: #FFFFFF;\n",
642
+ " }\n",
643
+ " </style>\n",
644
+ "\n",
645
+ " <script>\n",
646
+ " const buttonEl =\n",
647
+ " document.querySelector('#df-ebce1837-967c-4ffc-872b-b24d45f84c89 button.colab-df-convert');\n",
648
+ " buttonEl.style.display =\n",
649
+ " google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
650
+ "\n",
651
+ " async function convertToInteractive(key) {\n",
652
+ " const element = document.querySelector('#df-ebce1837-967c-4ffc-872b-b24d45f84c89');\n",
653
+ " const dataTable =\n",
654
+ " await google.colab.kernel.invokeFunction('convertToInteractive',\n",
655
+ " [key], {});\n",
656
+ " if (!dataTable) return;\n",
657
+ "\n",
658
+ " const docLinkHtml = 'Like what you see? Visit the ' +\n",
659
+ " '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
660
+ " + ' to learn more about interactive tables.';\n",
661
+ " element.innerHTML = '';\n",
662
+ " dataTable['output_type'] = 'display_data';\n",
663
+ " await google.colab.output.renderOutput(dataTable, element);\n",
664
+ " const docLink = document.createElement('div');\n",
665
+ " docLink.innerHTML = docLinkHtml;\n",
666
+ " element.appendChild(docLink);\n",
667
+ " }\n",
668
+ " </script>\n",
669
+ " </div>\n",
670
+ " </div>\n",
671
+ " "
672
+ ]
673
+ },
674
+ "metadata": {},
675
+ "execution_count": 53
676
+ }
677
+ ]
678
+ },
679
+ {
680
+ "cell_type": "code",
681
+ "source": [
682
+ "score = model.evaluate(X_test, y_test)\n",
683
+ "\n",
684
+ "print(\"\\n categorical_crossentropy || accuracy \")\n",
685
+ "print(\" ____________________________________\")\n",
686
+ "print(score)"
687
+ ],
688
+ "metadata": {
689
+ "colab": {
690
+ "base_uri": "https://localhost:8080/"
691
+ },
692
+ "id": "hwFZ64M7V0dN",
693
+ "outputId": "7d42242a-fe62-4172-ca6b-f328c8e9412a"
694
+ },
695
+ "execution_count": null,
696
+ "outputs": [
697
+ {
698
+ "output_type": "stream",
699
+ "name": "stdout",
700
+ "text": [
701
+ "93/93 [==============================] - 0s 5ms/step - loss: 0.3141 - accuracy: 0.9165\n",
702
+ "\n",
703
+ " categorical_crossentropy || accuracy \n",
704
+ " ____________________________________\n",
705
+ "[0.3141055107116699, 0.9165253043174744]\n"
706
+ ]
707
+ }
708
+ ]
709
+ },
710
+ {
711
+ "cell_type": "markdown",
712
+ "source": [
713
+ " 2. Defining the Architecture of 2-Layer of LSTM with more hyperparameter tunning"
714
+ ],
715
+ "metadata": {
716
+ "id": "EFsp0FcXV9HG"
717
+ }
718
+ },
719
+ {
720
+ "cell_type": "markdown",
721
+ "source": [
722
+ "#### 2.1 First Model for 2-Layer of LSTM with more hyperparameter tunning"
723
+ ],
724
+ "metadata": {
725
+ "id": "8p4j41aSV_Uv"
726
+ }
727
+ },
728
+ {
729
+ "cell_type": "code",
730
+ "source": [
731
+ "# Initializing parameters\n",
732
+ "n_epochs = 30\n",
733
+ "n_batch = 16\n",
734
+ "n_classes = _count_classes(y_train)\n",
735
+ "\n",
736
+ "# Bias regularizer value - we will use elasticnet\n",
737
+ "reg = L1L2(0.01, 0.01)"
738
+ ],
739
+ "metadata": {
740
+ "id": "O594yNV2WSRj"
741
+ },
742
+ "execution_count": null,
743
+ "outputs": []
744
+ },
745
+ {
746
+ "cell_type": "code",
747
+ "source": [
748
+ "# Model execution\n",
749
+ "model = Sequential()\n",
750
+ "model.add(LSTM(48, input_shape=(timesteps, input_dim), return_sequences=True,bias_regularizer=reg ))\n",
751
+ "model.add(BatchNormalization())\n",
752
+ "model.add(Dropout(0.50))\n",
753
+ "model.add(LSTM(32))\n",
754
+ "model.add(Dropout(0.50))\n",
755
+ "model.add(Dense(n_classes, activation='sigmoid'))\n",
756
+ "print(\"Model Summary: \")\n",
757
+ "model.summary()"
758
+ ],
759
+ "metadata": {
760
+ "colab": {
761
+ "base_uri": "https://localhost:8080/"
762
+ },
763
+ "id": "17yKQHdAWVWs",
764
+ "outputId": "48627f4b-09b1-465c-d1ab-cd2142af8642"
765
+ },
766
+ "execution_count": null,
767
+ "outputs": [
768
+ {
769
+ "output_type": "stream",
770
+ "name": "stdout",
771
+ "text": [
772
+ "Model Summary: \n",
773
+ "Model: \"sequential_4\"\n",
774
+ "_________________________________________________________________\n",
775
+ " Layer (type) Output Shape Param # \n",
776
+ "=================================================================\n",
777
+ " lstm_6 (LSTM) (None, 128, 48) 11136 \n",
778
+ " \n",
779
+ " batch_normalization_2 (Batc (None, 128, 48) 192 \n",
780
+ " hNormalization) \n",
781
+ " \n",
782
+ " dropout_6 (Dropout) (None, 128, 48) 0 \n",
783
+ " \n",
784
+ " lstm_7 (LSTM) (None, 32) 10368 \n",
785
+ " \n",
786
+ " dropout_7 (Dropout) (None, 32) 0 \n",
787
+ " \n",
788
+ " dense_4 (Dense) (None, 6) 198 \n",
789
+ " \n",
790
+ "=================================================================\n",
791
+ "Total params: 21,894\n",
792
+ "Trainable params: 21,798\n",
793
+ "Non-trainable params: 96\n",
794
+ "_________________________________________________________________\n"
795
+ ]
796
+ }
797
+ ]
798
+ },
799
+ {
800
+ "cell_type": "code",
801
+ "source": [
802
+ "model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])"
803
+ ],
804
+ "metadata": {
805
+ "id": "HfXE9HTbWYMc"
806
+ },
807
+ "execution_count": null,
808
+ "outputs": []
809
+ },
810
+ {
811
+ "cell_type": "code",
812
+ "source": [
813
+ "# Training the model\n",
814
+ "model.fit(X_train, y_train, batch_size=n_batch, validation_data=(X_test, y_test), epochs=n_epochs)"
815
+ ],
816
+ "metadata": {
817
+ "colab": {
818
+ "base_uri": "https://localhost:8080/"
819
+ },
820
+ "id": "TQxn8R_VWbJA",
821
+ "outputId": "b9186f7f-87a8-4e68-f35e-63fd06ca7efb"
822
+ },
823
+ "execution_count": null,
824
+ "outputs": [
825
+ {
826
+ "output_type": "stream",
827
+ "name": "stdout",
828
+ "text": [
829
+ "Epoch 1/30\n",
830
+ "460/460 [==============================] - 14s 17ms/step - loss: 1.5191 - accuracy: 0.6938 - val_loss: 0.9805 - val_accuracy: 0.8310\n",
831
+ "Epoch 2/30\n",
832
+ "460/460 [==============================] - 7s 16ms/step - loss: 0.7182 - accuracy: 0.8690 - val_loss: 0.5508 - val_accuracy: 0.8904\n",
833
+ "Epoch 3/30\n",
834
+ "460/460 [==============================] - 6s 13ms/step - loss: 0.3774 - accuracy: 0.9128 - val_loss: 0.3188 - val_accuracy: 0.8965\n",
835
+ "Epoch 4/30\n",
836
+ "460/460 [==============================] - 8s 17ms/step - loss: 0.2595 - accuracy: 0.9225 - val_loss: 0.4659 - val_accuracy: 0.8405\n",
837
+ "Epoch 5/30\n",
838
+ "460/460 [==============================] - 6s 14ms/step - loss: 0.2368 - accuracy: 0.9187 - val_loss: 0.4207 - val_accuracy: 0.8565\n",
839
+ "Epoch 6/30\n",
840
+ "460/460 [==============================] - 8s 17ms/step - loss: 0.2269 - accuracy: 0.9234 - val_loss: 0.2667 - val_accuracy: 0.9036\n",
841
+ "Epoch 7/30\n",
842
+ "460/460 [==============================] - 6s 14ms/step - loss: 0.1687 - accuracy: 0.9374 - val_loss: 0.2469 - val_accuracy: 0.9125\n",
843
+ "Epoch 8/30\n",
844
+ "460/460 [==============================] - 7s 16ms/step - loss: 0.1691 - accuracy: 0.9387 - val_loss: 0.3808 - val_accuracy: 0.8884\n",
845
+ "Epoch 9/30\n",
846
+ "460/460 [==============================] - 7s 14ms/step - loss: 0.1535 - accuracy: 0.9422 - val_loss: 0.2922 - val_accuracy: 0.9060\n",
847
+ "Epoch 10/30\n",
848
+ "460/460 [==============================] - 7s 16ms/step - loss: 0.1839 - accuracy: 0.9350 - val_loss: 0.3028 - val_accuracy: 0.8935\n",
849
+ "Epoch 11/30\n",
850
+ "460/460 [==============================] - 7s 15ms/step - loss: 0.1648 - accuracy: 0.9408 - val_loss: 0.3396 - val_accuracy: 0.8860\n",
851
+ "Epoch 12/30\n",
852
+ "460/460 [==============================] - 7s 16ms/step - loss: 0.1487 - accuracy: 0.9442 - val_loss: 0.2619 - val_accuracy: 0.9148\n",
853
+ "Epoch 13/30\n",
854
+ "460/460 [==============================] - 8s 18ms/step - loss: 0.1564 - accuracy: 0.9393 - val_loss: 0.2611 - val_accuracy: 0.9131\n",
855
+ "Epoch 14/30\n",
856
+ "460/460 [==============================] - 7s 14ms/step - loss: 0.1492 - accuracy: 0.9418 - val_loss: 0.3017 - val_accuracy: 0.9155\n",
857
+ "Epoch 15/30\n",
858
+ "460/460 [==============================] - 7s 16ms/step - loss: 0.1759 - accuracy: 0.9370 - val_loss: 0.3169 - val_accuracy: 0.9182\n",
859
+ "Epoch 16/30\n",
860
+ "460/460 [==============================] - 7s 14ms/step - loss: 0.1700 - accuracy: 0.9396 - val_loss: 0.3099 - val_accuracy: 0.9030\n",
861
+ "Epoch 17/30\n",
862
+ "460/460 [==============================] - 8s 17ms/step - loss: 0.1506 - accuracy: 0.9403 - val_loss: 0.3593 - val_accuracy: 0.8965\n",
863
+ "Epoch 18/30\n",
864
+ "460/460 [==============================] - 6s 13ms/step - loss: 0.1462 - accuracy: 0.9461 - val_loss: 0.3433 - val_accuracy: 0.9074\n",
865
+ "Epoch 19/30\n",
866
+ "460/460 [==============================] - 8s 17ms/step - loss: 0.1372 - accuracy: 0.9459 - val_loss: 0.2816 - val_accuracy: 0.9206\n",
867
+ "Epoch 20/30\n",
868
+ "460/460 [==============================] - 6s 13ms/step - loss: 0.1436 - accuracy: 0.9429 - val_loss: 0.2907 - val_accuracy: 0.9196\n",
869
+ "Epoch 21/30\n",
870
+ "460/460 [==============================] - 8s 17ms/step - loss: 0.1311 - accuracy: 0.9480 - val_loss: 0.2638 - val_accuracy: 0.9223\n",
871
+ "Epoch 22/30\n",
872
+ "460/460 [==============================] - 6s 13ms/step - loss: 0.1498 - accuracy: 0.9410 - val_loss: 0.3071 - val_accuracy: 0.9030\n",
873
+ "Epoch 23/30\n",
874
+ "460/460 [==============================] - 8s 16ms/step - loss: 0.1399 - accuracy: 0.9472 - val_loss: 0.3322 - val_accuracy: 0.9060\n",
875
+ "Epoch 24/30\n",
876
+ "460/460 [==============================] - 6s 14ms/step - loss: 0.1619 - accuracy: 0.9397 - val_loss: 0.2797 - val_accuracy: 0.9179\n",
877
+ "Epoch 25/30\n",
878
+ "460/460 [==============================] - 7s 16ms/step - loss: 0.1452 - accuracy: 0.9446 - val_loss: 0.2839 - val_accuracy: 0.9148\n",
879
+ "Epoch 26/30\n",
880
+ "460/460 [==============================] - 7s 14ms/step - loss: 0.1296 - accuracy: 0.9494 - val_loss: 0.3043 - val_accuracy: 0.8982\n",
881
+ "Epoch 27/30\n",
882
+ "460/460 [==============================] - 7s 16ms/step - loss: 0.1334 - accuracy: 0.9460 - val_loss: 0.2795 - val_accuracy: 0.9080\n",
883
+ "Epoch 28/30\n",
884
+ "460/460 [==============================] - 7s 14ms/step - loss: 0.1310 - accuracy: 0.9463 - val_loss: 0.2821 - val_accuracy: 0.8945\n",
885
+ "Epoch 29/30\n",
886
+ "460/460 [==============================] - 7s 16ms/step - loss: 0.1253 - accuracy: 0.9489 - val_loss: 0.2743 - val_accuracy: 0.9165\n",
887
+ "Epoch 30/30\n",
888
+ "460/460 [==============================] - 7s 14ms/step - loss: 0.1407 - accuracy: 0.9406 - val_loss: 0.2640 - val_accuracy: 0.9131\n"
889
+ ]
890
+ },
891
+ {
892
+ "output_type": "execute_result",
893
+ "data": {
894
+ "text/plain": [
895
+ "<keras.callbacks.History at 0x7f78fa3f00a0>"
896
+ ]
897
+ },
898
+ "metadata": {},
899
+ "execution_count": 58
900
+ }
901
+ ]
902
+ },
903
+ {
904
+ "cell_type": "code",
905
+ "source": [
906
+ "# Confusion Matrix\n",
907
+ "confusion_matrix(y_test, model.predict(X_test))"
908
+ ],
909
+ "metadata": {
910
+ "colab": {
911
+ "base_uri": "https://localhost:8080/",
912
+ "height": 286
913
+ },
914
+ "id": "abLtI6JsWeM1",
915
+ "outputId": "1e5b55ea-0793-463a-df25-7596e18e36c8"
916
+ },
917
+ "execution_count": null,
918
+ "outputs": [
919
+ {
920
+ "output_type": "stream",
921
+ "name": "stdout",
922
+ "text": [
923
+ "93/93 [==============================] - 2s 7ms/step\n"
924
+ ]
925
+ },
926
+ {
927
+ "output_type": "execute_result",
928
+ "data": {
929
+ "text/plain": [
930
+ "Pred LAYING SITTING STANDING WALKING WALKING_DOWNSTAIRS \\\n",
931
+ "True \n",
932
+ "LAYING 537 0 0 0 0 \n",
933
+ "SITTING 2 419 67 0 0 \n",
934
+ "STANDING 0 128 404 0 0 \n",
935
+ "WALKING 0 0 0 472 19 \n",
936
+ "WALKING_DOWNSTAIRS 0 0 0 2 415 \n",
937
+ "WALKING_UPSTAIRS 0 0 0 11 16 \n",
938
+ "\n",
939
+ "Pred WALKING_UPSTAIRS \n",
940
+ "True \n",
941
+ "LAYING 0 \n",
942
+ "SITTING 3 \n",
943
+ "STANDING 0 \n",
944
+ "WALKING 5 \n",
945
+ "WALKING_DOWNSTAIRS 3 \n",
946
+ "WALKING_UPSTAIRS 444 "
947
+ ],
948
+ "text/html": [
949
+ "\n",
950
+ " <div id=\"df-03249097-2495-4177-b033-477f5b7ebb57\">\n",
951
+ " <div class=\"colab-df-container\">\n",
952
+ " <div>\n",
953
+ "<style scoped>\n",
954
+ " .dataframe tbody tr th:only-of-type {\n",
955
+ " vertical-align: middle;\n",
956
+ " }\n",
957
+ "\n",
958
+ " .dataframe tbody tr th {\n",
959
+ " vertical-align: top;\n",
960
+ " }\n",
961
+ "\n",
962
+ " .dataframe thead th {\n",
963
+ " text-align: right;\n",
964
+ " }\n",
965
+ "</style>\n",
966
+ "<table border=\"1\" class=\"dataframe\">\n",
967
+ " <thead>\n",
968
+ " <tr style=\"text-align: right;\">\n",
969
+ " <th>Pred</th>\n",
970
+ " <th>LAYING</th>\n",
971
+ " <th>SITTING</th>\n",
972
+ " <th>STANDING</th>\n",
973
+ " <th>WALKING</th>\n",
974
+ " <th>WALKING_DOWNSTAIRS</th>\n",
975
+ " <th>WALKING_UPSTAIRS</th>\n",
976
+ " </tr>\n",
977
+ " <tr>\n",
978
+ " <th>True</th>\n",
979
+ " <th></th>\n",
980
+ " <th></th>\n",
981
+ " <th></th>\n",
982
+ " <th></th>\n",
983
+ " <th></th>\n",
984
+ " <th></th>\n",
985
+ " </tr>\n",
986
+ " </thead>\n",
987
+ " <tbody>\n",
988
+ " <tr>\n",
989
+ " <th>LAYING</th>\n",
990
+ " <td>537</td>\n",
991
+ " <td>0</td>\n",
992
+ " <td>0</td>\n",
993
+ " <td>0</td>\n",
994
+ " <td>0</td>\n",
995
+ " <td>0</td>\n",
996
+ " </tr>\n",
997
+ " <tr>\n",
998
+ " <th>SITTING</th>\n",
999
+ " <td>2</td>\n",
1000
+ " <td>419</td>\n",
1001
+ " <td>67</td>\n",
1002
+ " <td>0</td>\n",
1003
+ " <td>0</td>\n",
1004
+ " <td>3</td>\n",
1005
+ " </tr>\n",
1006
+ " <tr>\n",
1007
+ " <th>STANDING</th>\n",
1008
+ " <td>0</td>\n",
1009
+ " <td>128</td>\n",
1010
+ " <td>404</td>\n",
1011
+ " <td>0</td>\n",
1012
+ " <td>0</td>\n",
1013
+ " <td>0</td>\n",
1014
+ " </tr>\n",
1015
+ " <tr>\n",
1016
+ " <th>WALKING</th>\n",
1017
+ " <td>0</td>\n",
1018
+ " <td>0</td>\n",
1019
+ " <td>0</td>\n",
1020
+ " <td>472</td>\n",
1021
+ " <td>19</td>\n",
1022
+ " <td>5</td>\n",
1023
+ " </tr>\n",
1024
+ " <tr>\n",
1025
+ " <th>WALKING_DOWNSTAIRS</th>\n",
1026
+ " <td>0</td>\n",
1027
+ " <td>0</td>\n",
1028
+ " <td>0</td>\n",
1029
+ " <td>2</td>\n",
1030
+ " <td>415</td>\n",
1031
+ " <td>3</td>\n",
1032
+ " </tr>\n",
1033
+ " <tr>\n",
1034
+ " <th>WALKING_UPSTAIRS</th>\n",
1035
+ " <td>0</td>\n",
1036
+ " <td>0</td>\n",
1037
+ " <td>0</td>\n",
1038
+ " <td>11</td>\n",
1039
+ " <td>16</td>\n",
1040
+ " <td>444</td>\n",
1041
+ " </tr>\n",
1042
+ " </tbody>\n",
1043
+ "</table>\n",
1044
+ "</div>\n",
1045
+ " <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-03249097-2495-4177-b033-477f5b7ebb57')\"\n",
1046
+ " title=\"Convert this dataframe to an interactive table.\"\n",
1047
+ " style=\"display:none;\">\n",
1048
+ " \n",
1049
+ " <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
1050
+ " width=\"24px\">\n",
1051
+ " <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
1052
+ " <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
1053
+ " </svg>\n",
1054
+ " </button>\n",
1055
+ " \n",
1056
+ " <style>\n",
1057
+ " .colab-df-container {\n",
1058
+ " display:flex;\n",
1059
+ " flex-wrap:wrap;\n",
1060
+ " gap: 12px;\n",
1061
+ " }\n",
1062
+ "\n",
1063
+ " .colab-df-convert {\n",
1064
+ " background-color: #E8F0FE;\n",
1065
+ " border: none;\n",
1066
+ " border-radius: 50%;\n",
1067
+ " cursor: pointer;\n",
1068
+ " display: none;\n",
1069
+ " fill: #1967D2;\n",
1070
+ " height: 32px;\n",
1071
+ " padding: 0 0 0 0;\n",
1072
+ " width: 32px;\n",
1073
+ " }\n",
1074
+ "\n",
1075
+ " .colab-df-convert:hover {\n",
1076
+ " background-color: #E2EBFA;\n",
1077
+ " box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
1078
+ " fill: #174EA6;\n",
1079
+ " }\n",
1080
+ "\n",
1081
+ " [theme=dark] .colab-df-convert {\n",
1082
+ " background-color: #3B4455;\n",
1083
+ " fill: #D2E3FC;\n",
1084
+ " }\n",
1085
+ "\n",
1086
+ " [theme=dark] .colab-df-convert:hover {\n",
1087
+ " background-color: #434B5C;\n",
1088
+ " box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
1089
+ " filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
1090
+ " fill: #FFFFFF;\n",
1091
+ " }\n",
1092
+ " </style>\n",
1093
+ "\n",
1094
+ " <script>\n",
1095
+ " const buttonEl =\n",
1096
+ " document.querySelector('#df-03249097-2495-4177-b033-477f5b7ebb57 button.colab-df-convert');\n",
1097
+ " buttonEl.style.display =\n",
1098
+ " google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
1099
+ "\n",
1100
+ " async function convertToInteractive(key) {\n",
1101
+ " const element = document.querySelector('#df-03249097-2495-4177-b033-477f5b7ebb57');\n",
1102
+ " const dataTable =\n",
1103
+ " await google.colab.kernel.invokeFunction('convertToInteractive',\n",
1104
+ " [key], {});\n",
1105
+ " if (!dataTable) return;\n",
1106
+ "\n",
1107
+ " const docLinkHtml = 'Like what you see? Visit the ' +\n",
1108
+ " '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
1109
+ " + ' to learn more about interactive tables.';\n",
1110
+ " element.innerHTML = '';\n",
1111
+ " dataTable['output_type'] = 'display_data';\n",
1112
+ " await google.colab.output.renderOutput(dataTable, element);\n",
1113
+ " const docLink = document.createElement('div');\n",
1114
+ " docLink.innerHTML = docLinkHtml;\n",
1115
+ " element.appendChild(docLink);\n",
1116
+ " }\n",
1117
+ " </script>\n",
1118
+ " </div>\n",
1119
+ " </div>\n",
1120
+ " "
1121
+ ]
1122
+ },
1123
+ "metadata": {},
1124
+ "execution_count": 59
1125
+ }
1126
+ ]
1127
+ },
1128
+ {
1129
+ "cell_type": "code",
1130
+ "source": [
1131
+ "score = model.evaluate(X_test, y_test)\n",
1132
+ "\n",
1133
+ "print(\"\\n categorica_crossentropy || accuracy \")\n",
1134
+ "print(\" ____________________________________\")\n",
1135
+ "print(score)"
1136
+ ],
1137
+ "metadata": {
1138
+ "colab": {
1139
+ "base_uri": "https://localhost:8080/"
1140
+ },
1141
+ "id": "sYNMpcu_WjB-",
1142
+ "outputId": "e43835c8-4b1b-4994-9e9e-67cf6f208d59"
1143
+ },
1144
+ "execution_count": null,
1145
+ "outputs": [
1146
+ {
1147
+ "output_type": "stream",
1148
+ "name": "stdout",
1149
+ "text": [
1150
+ "93/93 [==============================] - 1s 6ms/step - loss: 0.2640 - accuracy: 0.9131\n",
1151
+ "\n",
1152
+ " categorica_crossentropy || accuracy \n",
1153
+ " ____________________________________\n",
1154
+ "[0.2640216052532196, 0.9131320118904114]\n"
1155
+ ]
1156
+ }
1157
+ ]
1158
+ },
1159
+ {
1160
+ "cell_type": "markdown",
1161
+ "source": [
1162
+ "#### 2.2 Second Model for 2-Layer of LSTM with more hyperparameter tunning"
1163
+ ],
1164
+ "metadata": {
1165
+ "id": "gPw5BDcNWocp"
1166
+ }
1167
+ },
1168
+ {
1169
+ "cell_type": "code",
1170
+ "source": [
1171
+ "# Model execution\n",
1172
+ "model = Sequential()\n",
1173
+ "model.add(LSTM(64, input_shape=(timesteps, input_dim), return_sequences=True, bias_regularizer=reg))\n",
1174
+ "model.add(BatchNormalization())\n",
1175
+ "model.add(Dropout(0.50))\n",
1176
+ "model.add(LSTM(48))\n",
1177
+ "model.add(Dropout(0.50))\n",
1178
+ "model.add(Dense(n_classes, activation='sigmoid'))\n",
1179
+ "print(\"Model Summary: \")\n",
1180
+ "model.summary()"
1181
+ ],
1182
+ "metadata": {
1183
+ "colab": {
1184
+ "base_uri": "https://localhost:8080/"
1185
+ },
1186
+ "id": "KgIyrMM0WsEY",
1187
+ "outputId": "414d300c-10de-40e0-b5e5-73de5ff3e97f"
1188
+ },
1189
+ "execution_count": null,
1190
+ "outputs": [
1191
+ {
1192
+ "output_type": "stream",
1193
+ "name": "stdout",
1194
+ "text": [
1195
+ "Model Summary: \n",
1196
+ "Model: \"sequential_5\"\n",
1197
+ "_________________________________________________________________\n",
1198
+ " Layer (type) Output Shape Param # \n",
1199
+ "=================================================================\n",
1200
+ " lstm_8 (LSTM) (None, 128, 64) 18944 \n",
1201
+ " \n",
1202
+ " batch_normalization_3 (Batc (None, 128, 64) 256 \n",
1203
+ " hNormalization) \n",
1204
+ " \n",
1205
+ " dropout_8 (Dropout) (None, 128, 64) 0 \n",
1206
+ " \n",
1207
+ " lstm_9 (LSTM) (None, 48) 21696 \n",
1208
+ " \n",
1209
+ " dropout_9 (Dropout) (None, 48) 0 \n",
1210
+ " \n",
1211
+ " dense_5 (Dense) (None, 6) 294 \n",
1212
+ " \n",
1213
+ "=================================================================\n",
1214
+ "Total params: 41,190\n",
1215
+ "Trainable params: 41,062\n",
1216
+ "Non-trainable params: 128\n",
1217
+ "_________________________________________________________________\n"
1218
+ ]
1219
+ }
1220
+ ]
1221
+ },
1222
+ {
1223
+ "cell_type": "code",
1224
+ "source": [
1225
+ "model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])"
1226
+ ],
1227
+ "metadata": {
1228
+ "id": "cJ4wvkh5WycW"
1229
+ },
1230
+ "execution_count": null,
1231
+ "outputs": []
1232
+ },
1233
+ {
1234
+ "cell_type": "code",
1235
+ "source": [
1236
+ "# Training the model\n",
1237
+ "model.fit(X_train, y_train, batch_size=n_batch, validation_data=(X_test, y_test), epochs=n_epochs)"
1238
+ ],
1239
+ "metadata": {
1240
+ "colab": {
1241
+ "base_uri": "https://localhost:8080/"
1242
+ },
1243
+ "id": "VKrGoJiuW3tK",
1244
+ "outputId": "86011b01-e928-434b-a373-102ff9c27ec2"
1245
+ },
1246
+ "execution_count": null,
1247
+ "outputs": [
1248
+ {
1249
+ "output_type": "stream",
1250
+ "name": "stdout",
1251
+ "text": [
1252
+ "Epoch 1/30\n",
1253
+ "460/460 [==============================] - 13s 19ms/step - loss: 1.6734 - accuracy: 0.7078 - val_loss: 1.5870 - val_accuracy: 0.5945\n",
1254
+ "Epoch 2/30\n",
1255
+ "460/460 [==============================] - 6s 14ms/step - loss: 0.7557 - accuracy: 0.8898 - val_loss: 0.4793 - val_accuracy: 0.9179\n",
1256
+ "Epoch 3/30\n",
1257
+ "460/460 [==============================] - 8s 16ms/step - loss: 0.4011 - accuracy: 0.9135 - val_loss: 0.3697 - val_accuracy: 0.8761\n",
1258
+ "Epoch 4/30\n",
1259
+ "460/460 [==============================] - 6s 14ms/step - loss: 0.2216 - accuracy: 0.9287 - val_loss: 0.3722 - val_accuracy: 0.8829\n",
1260
+ "Epoch 5/30\n",
1261
+ "460/460 [==============================] - 8s 17ms/step - loss: 0.1946 - accuracy: 0.9334 - val_loss: 0.4488 - val_accuracy: 0.8446\n",
1262
+ "Epoch 6/30\n",
1263
+ "460/460 [==============================] - 6s 13ms/step - loss: 0.1719 - accuracy: 0.9381 - val_loss: 0.2355 - val_accuracy: 0.9128\n",
1264
+ "Epoch 7/30\n",
1265
+ "460/460 [==============================] - 7s 16ms/step - loss: 0.1631 - accuracy: 0.9399 - val_loss: 0.2094 - val_accuracy: 0.9325\n",
1266
+ "Epoch 8/30\n",
1267
+ "460/460 [==============================] - 6s 13ms/step - loss: 0.1798 - accuracy: 0.9317 - val_loss: 0.2030 - val_accuracy: 0.9189\n",
1268
+ "Epoch 9/30\n",
1269
+ "460/460 [==============================] - 8s 17ms/step - loss: 0.1874 - accuracy: 0.9312 - val_loss: 0.2831 - val_accuracy: 0.9165\n",
1270
+ "Epoch 10/30\n",
1271
+ "460/460 [==============================] - 6s 14ms/step - loss: 0.1565 - accuracy: 0.9387 - val_loss: 0.2430 - val_accuracy: 0.9192\n",
1272
+ "Epoch 11/30\n",
1273
+ "460/460 [==============================] - 7s 16ms/step - loss: 0.1611 - accuracy: 0.9384 - val_loss: 0.2457 - val_accuracy: 0.9080\n",
1274
+ "Epoch 12/30\n",
1275
+ "460/460 [==============================] - 6s 14ms/step - loss: 0.1424 - accuracy: 0.9445 - val_loss: 0.3006 - val_accuracy: 0.8992\n",
1276
+ "Epoch 13/30\n",
1277
+ "460/460 [==============================] - 7s 16ms/step - loss: 0.1442 - accuracy: 0.9440 - val_loss: 0.2308 - val_accuracy: 0.9162\n",
1278
+ "Epoch 14/30\n",
1279
+ "460/460 [==============================] - 6s 13ms/step - loss: 0.1882 - accuracy: 0.9353 - val_loss: 0.2404 - val_accuracy: 0.9199\n",
1280
+ "Epoch 15/30\n",
1281
+ "460/460 [==============================] - 8s 16ms/step - loss: 0.1385 - accuracy: 0.9448 - val_loss: 0.2316 - val_accuracy: 0.9094\n",
1282
+ "Epoch 16/30\n",
1283
+ "460/460 [==============================] - 6s 14ms/step - loss: 0.1704 - accuracy: 0.9393 - val_loss: 0.2102 - val_accuracy: 0.9257\n",
1284
+ "Epoch 17/30\n",
1285
+ "460/460 [==============================] - 7s 16ms/step - loss: 0.1349 - accuracy: 0.9465 - val_loss: 0.2214 - val_accuracy: 0.9165\n",
1286
+ "Epoch 18/30\n",
1287
+ "460/460 [==============================] - 6s 13ms/step - loss: 0.1502 - accuracy: 0.9400 - val_loss: 0.2715 - val_accuracy: 0.9101\n",
1288
+ "Epoch 19/30\n",
1289
+ "460/460 [==============================] - 7s 16ms/step - loss: 0.1281 - accuracy: 0.9472 - val_loss: 0.2358 - val_accuracy: 0.9179\n",
1290
+ "Epoch 20/30\n",
1291
+ "460/460 [==============================] - 6s 14ms/step - loss: 0.1380 - accuracy: 0.9448 - val_loss: 0.2803 - val_accuracy: 0.9080\n",
1292
+ "Epoch 21/30\n",
1293
+ "460/460 [==============================] - 7s 16ms/step - loss: 0.1440 - accuracy: 0.9429 - val_loss: 0.2399 - val_accuracy: 0.9253\n",
1294
+ "Epoch 22/30\n",
1295
+ "460/460 [==============================] - 7s 14ms/step - loss: 0.1608 - accuracy: 0.9416 - val_loss: 0.2226 - val_accuracy: 0.9216\n",
1296
+ "Epoch 23/30\n",
1297
+ "460/460 [==============================] - 7s 16ms/step - loss: 0.1291 - accuracy: 0.9489 - val_loss: 0.2334 - val_accuracy: 0.9257\n",
1298
+ "Epoch 24/30\n",
1299
+ "460/460 [==============================] - 7s 14ms/step - loss: 0.1311 - accuracy: 0.9471 - val_loss: 0.2140 - val_accuracy: 0.9267\n",
1300
+ "Epoch 25/30\n",
1301
+ "460/460 [==============================] - 8s 16ms/step - loss: 0.1324 - accuracy: 0.9475 - val_loss: 0.2815 - val_accuracy: 0.9165\n",
1302
+ "Epoch 26/30\n",
1303
+ "460/460 [==============================] - 6s 13ms/step - loss: 0.1284 - accuracy: 0.9484 - val_loss: 0.2534 - val_accuracy: 0.9325\n",
1304
+ "Epoch 27/30\n",
1305
+ "460/460 [==============================] - 7s 16ms/step - loss: 0.1268 - accuracy: 0.9486 - val_loss: 0.2600 - val_accuracy: 0.9220\n",
1306
+ "Epoch 28/30\n",
1307
+ "460/460 [==============================] - 6s 13ms/step - loss: 0.1290 - accuracy: 0.9501 - val_loss: 0.2439 - val_accuracy: 0.9192\n",
1308
+ "Epoch 29/30\n",
1309
+ "460/460 [==============================] - 8s 17ms/step - loss: 0.1354 - accuracy: 0.9486 - val_loss: 0.5618 - val_accuracy: 0.8320\n",
1310
+ "Epoch 30/30\n",
1311
+ "460/460 [==============================] - 7s 14ms/step - loss: 0.1541 - accuracy: 0.9411 - val_loss: 0.3802 - val_accuracy: 0.9125\n"
1312
+ ]
1313
+ },
1314
+ {
1315
+ "output_type": "execute_result",
1316
+ "data": {
1317
+ "text/plain": [
1318
+ "<keras.callbacks.History at 0x7f78f3474a30>"
1319
+ ]
1320
+ },
1321
+ "metadata": {},
1322
+ "execution_count": 63
1323
+ }
1324
+ ]
1325
+ },
1326
+ {
1327
+ "cell_type": "code",
1328
+ "source": [
1329
+ "# Confusion Matrix\n",
1330
+ "confusion_matrix(y_test, model.predict(X_test))"
1331
+ ],
1332
+ "metadata": {
1333
+ "colab": {
1334
+ "base_uri": "https://localhost:8080/",
1335
+ "height": 286
1336
+ },
1337
+ "id": "65v6IGSdW66a",
1338
+ "outputId": "e9876301-35b6-4a9e-f364-4580cd009f5d"
1339
+ },
1340
+ "execution_count": null,
1341
+ "outputs": [
1342
+ {
1343
+ "output_type": "stream",
1344
+ "name": "stdout",
1345
+ "text": [
1346
+ "93/93 [==============================] - 2s 7ms/step\n"
1347
+ ]
1348
+ },
1349
+ {
1350
+ "output_type": "execute_result",
1351
+ "data": {
1352
+ "text/plain": [
1353
+ "Pred LAYING SITTING STANDING WALKING WALKING_DOWNSTAIRS \\\n",
1354
+ "True \n",
1355
+ "LAYING 537 0 0 0 0 \n",
1356
+ "SITTING 0 407 82 0 0 \n",
1357
+ "STANDING 0 94 438 0 0 \n",
1358
+ "WALKING 0 0 0 447 46 \n",
1359
+ "WALKING_DOWNSTAIRS 0 0 0 1 419 \n",
1360
+ "WALKING_UPSTAIRS 0 2 0 1 27 \n",
1361
+ "\n",
1362
+ "Pred WALKING_UPSTAIRS \n",
1363
+ "True \n",
1364
+ "LAYING 0 \n",
1365
+ "SITTING 2 \n",
1366
+ "STANDING 0 \n",
1367
+ "WALKING 3 \n",
1368
+ "WALKING_DOWNSTAIRS 0 \n",
1369
+ "WALKING_UPSTAIRS 441 "
1370
+ ],
1371
+ "text/html": [
1372
+ "\n",
1373
+ " <div id=\"df-af1f7d68-479a-4380-870e-0e82389a4389\">\n",
1374
+ " <div class=\"colab-df-container\">\n",
1375
+ " <div>\n",
1376
+ "<style scoped>\n",
1377
+ " .dataframe tbody tr th:only-of-type {\n",
1378
+ " vertical-align: middle;\n",
1379
+ " }\n",
1380
+ "\n",
1381
+ " .dataframe tbody tr th {\n",
1382
+ " vertical-align: top;\n",
1383
+ " }\n",
1384
+ "\n",
1385
+ " .dataframe thead th {\n",
1386
+ " text-align: right;\n",
1387
+ " }\n",
1388
+ "</style>\n",
1389
+ "<table border=\"1\" class=\"dataframe\">\n",
1390
+ " <thead>\n",
1391
+ " <tr style=\"text-align: right;\">\n",
1392
+ " <th>Pred</th>\n",
1393
+ " <th>LAYING</th>\n",
1394
+ " <th>SITTING</th>\n",
1395
+ " <th>STANDING</th>\n",
1396
+ " <th>WALKING</th>\n",
1397
+ " <th>WALKING_DOWNSTAIRS</th>\n",
1398
+ " <th>WALKING_UPSTAIRS</th>\n",
1399
+ " </tr>\n",
1400
+ " <tr>\n",
1401
+ " <th>True</th>\n",
1402
+ " <th></th>\n",
1403
+ " <th></th>\n",
1404
+ " <th></th>\n",
1405
+ " <th></th>\n",
1406
+ " <th></th>\n",
1407
+ " <th></th>\n",
1408
+ " </tr>\n",
1409
+ " </thead>\n",
1410
+ " <tbody>\n",
1411
+ " <tr>\n",
1412
+ " <th>LAYING</th>\n",
1413
+ " <td>537</td>\n",
1414
+ " <td>0</td>\n",
1415
+ " <td>0</td>\n",
1416
+ " <td>0</td>\n",
1417
+ " <td>0</td>\n",
1418
+ " <td>0</td>\n",
1419
+ " </tr>\n",
1420
+ " <tr>\n",
1421
+ " <th>SITTING</th>\n",
1422
+ " <td>0</td>\n",
1423
+ " <td>407</td>\n",
1424
+ " <td>82</td>\n",
1425
+ " <td>0</td>\n",
1426
+ " <td>0</td>\n",
1427
+ " <td>2</td>\n",
1428
+ " </tr>\n",
1429
+ " <tr>\n",
1430
+ " <th>STANDING</th>\n",
1431
+ " <td>0</td>\n",
1432
+ " <td>94</td>\n",
1433
+ " <td>438</td>\n",
1434
+ " <td>0</td>\n",
1435
+ " <td>0</td>\n",
1436
+ " <td>0</td>\n",
1437
+ " </tr>\n",
1438
+ " <tr>\n",
1439
+ " <th>WALKING</th>\n",
1440
+ " <td>0</td>\n",
1441
+ " <td>0</td>\n",
1442
+ " <td>0</td>\n",
1443
+ " <td>447</td>\n",
1444
+ " <td>46</td>\n",
1445
+ " <td>3</td>\n",
1446
+ " </tr>\n",
1447
+ " <tr>\n",
1448
+ " <th>WALKING_DOWNSTAIRS</th>\n",
1449
+ " <td>0</td>\n",
1450
+ " <td>0</td>\n",
1451
+ " <td>0</td>\n",
1452
+ " <td>1</td>\n",
1453
+ " <td>419</td>\n",
1454
+ " <td>0</td>\n",
1455
+ " </tr>\n",
1456
+ " <tr>\n",
1457
+ " <th>WALKING_UPSTAIRS</th>\n",
1458
+ " <td>0</td>\n",
1459
+ " <td>2</td>\n",
1460
+ " <td>0</td>\n",
1461
+ " <td>1</td>\n",
1462
+ " <td>27</td>\n",
1463
+ " <td>441</td>\n",
1464
+ " </tr>\n",
1465
+ " </tbody>\n",
1466
+ "</table>\n",
1467
+ "</div>\n",
1468
+ " <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-af1f7d68-479a-4380-870e-0e82389a4389')\"\n",
1469
+ " title=\"Convert this dataframe to an interactive table.\"\n",
1470
+ " style=\"display:none;\">\n",
1471
+ " \n",
1472
+ " <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
1473
+ " width=\"24px\">\n",
1474
+ " <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
1475
+ " <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
1476
+ " </svg>\n",
1477
+ " </button>\n",
1478
+ " \n",
1479
+ " <style>\n",
1480
+ " .colab-df-container {\n",
1481
+ " display:flex;\n",
1482
+ " flex-wrap:wrap;\n",
1483
+ " gap: 12px;\n",
1484
+ " }\n",
1485
+ "\n",
1486
+ " .colab-df-convert {\n",
1487
+ " background-color: #E8F0FE;\n",
1488
+ " border: none;\n",
1489
+ " border-radius: 50%;\n",
1490
+ " cursor: pointer;\n",
1491
+ " display: none;\n",
1492
+ " fill: #1967D2;\n",
1493
+ " height: 32px;\n",
1494
+ " padding: 0 0 0 0;\n",
1495
+ " width: 32px;\n",
1496
+ " }\n",
1497
+ "\n",
1498
+ " .colab-df-convert:hover {\n",
1499
+ " background-color: #E2EBFA;\n",
1500
+ " box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
1501
+ " fill: #174EA6;\n",
1502
+ " }\n",
1503
+ "\n",
1504
+ " [theme=dark] .colab-df-convert {\n",
1505
+ " background-color: #3B4455;\n",
1506
+ " fill: #D2E3FC;\n",
1507
+ " }\n",
1508
+ "\n",
1509
+ " [theme=dark] .colab-df-convert:hover {\n",
1510
+ " background-color: #434B5C;\n",
1511
+ " box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
1512
+ " filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
1513
+ " fill: #FFFFFF;\n",
1514
+ " }\n",
1515
+ " </style>\n",
1516
+ "\n",
1517
+ " <script>\n",
1518
+ " const buttonEl =\n",
1519
+ " document.querySelector('#df-af1f7d68-479a-4380-870e-0e82389a4389 button.colab-df-convert');\n",
1520
+ " buttonEl.style.display =\n",
1521
+ " google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
1522
+ "\n",
1523
+ " async function convertToInteractive(key) {\n",
1524
+ " const element = document.querySelector('#df-af1f7d68-479a-4380-870e-0e82389a4389');\n",
1525
+ " const dataTable =\n",
1526
+ " await google.colab.kernel.invokeFunction('convertToInteractive',\n",
1527
+ " [key], {});\n",
1528
+ " if (!dataTable) return;\n",
1529
+ "\n",
1530
+ " const docLinkHtml = 'Like what you see? Visit the ' +\n",
1531
+ " '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
1532
+ " + ' to learn more about interactive tables.';\n",
1533
+ " element.innerHTML = '';\n",
1534
+ " dataTable['output_type'] = 'display_data';\n",
1535
+ " await google.colab.output.renderOutput(dataTable, element);\n",
1536
+ " const docLink = document.createElement('div');\n",
1537
+ " docLink.innerHTML = docLinkHtml;\n",
1538
+ " element.appendChild(docLink);\n",
1539
+ " }\n",
1540
+ " </script>\n",
1541
+ " </div>\n",
1542
+ " </div>\n",
1543
+ " "
1544
+ ]
1545
+ },
1546
+ "metadata": {},
1547
+ "execution_count": 64
1548
+ }
1549
+ ]
1550
+ },
1551
+ {
1552
+ "cell_type": "code",
1553
+ "source": [
1554
+ "score = model.evaluate(X_test, y_test)\n",
1555
+ "\n",
1556
+ "print(\"\\n categorical_crossentropy || accuracy \")\n",
1557
+ "print(\" ____________________________________\")\n",
1558
+ "print(score)"
1559
+ ],
1560
+ "metadata": {
1561
+ "colab": {
1562
+ "base_uri": "https://localhost:8080/"
1563
+ },
1564
+ "id": "N7i84QfGW9Er",
1565
+ "outputId": "18a8a70f-2896-45a2-a22b-cef28557cfe3"
1566
+ },
1567
+ "execution_count": null,
1568
+ "outputs": [
1569
+ {
1570
+ "output_type": "stream",
1571
+ "name": "stdout",
1572
+ "text": [
1573
+ "93/93 [==============================] - 1s 9ms/step - loss: 0.3802 - accuracy: 0.9125\n",
1574
+ "\n",
1575
+ " categorical_crossentropy || accuracy \n",
1576
+ " ____________________________________\n",
1577
+ "[0.38021206855773926, 0.9124533534049988]\n"
1578
+ ]
1579
+ }
1580
+ ]
1581
+ }
1582
+ ]
1583
+ }