CODEWITHSUNDEEP
machine-learningregression
ummagumma2332
ummagumma2332

Reputation: 29

Combination of classification and regression

The dataset I am working with contains the readings of an 8-sensors gas-sensor-array. The response of a sensor depends on the gas stimuli (methane, ethylene, etc.) and the concentration of the gas (20 ppm, 50 ppm, etc.). The dataset consists of 640 examples and each example is of shape=(6000,8) since there are 8 sensors on the array. (sensor-array response to 100ppm of Methane)

My task is to make a model that will predict the class of the sensor-array reading (from which gas this reading is) and after that, I want to predict the concentration of that gas.

So far I have built a classification model based on 1D convolutional layers which successfully classifies examples into four categories (gases) with 98% accuracy.

How could I predict the concentration value of the gas? Is it possible to perform a regression analysis on the classified examples or should I look for a whole different approach?

Upvotes: 0

Views: 598

Answers (1)

Adarsh Wase
Adarsh Wase

Reputation: 1890

For this task, I would just make a multi output neural network like this:

from tensorflow.keras.layers import Input, Dense
from tensorflow.keras.models import Model

inp = Input(shape=(n_features,))
hidden1 = Dense(20, activation='relu', kernel_initializer='he_normal')(inp)
hidden2 = Dense(10, activation='relu', kernel_initializer='he_normal')(hidden1)

out_reg = Dense(1, activation='linear')(hidden2)
out_class = Dense(n_class, activation='softmax')(hidden2)

model = Model(inputs=inp, outputs=[out_reg, out_class])
model.compile(loss=['mse','sparse_categorical_crossentropy'], optimizer='adam')
model.fit(X_train, [y_train_reg, y_train_class], epochs=150, batch_size=32, verbose=2)

One output for regression and another for classification. Below is the image of neural network architecture:

enter image description here

If you don't know how to create such networks, please read the documentation.

Upvotes: 4

Related Questions