## Description

## 1. Time Series Classification Part 1: Feature Creation/Extraction

An interesting task in machine learning is classification of time series. In this problem,

we will classify the activities of humans based on time series obtained by a Wireless

Sensor Network.

(a) Download the AReM data from: https://archive.ics.uci.edu/ml/datasets/

Activity+Recognition+system+based+on+Multisensor+data+fusion+\%28AReM\

%29 .

The dataset contains 7 folders that represent seven types of activities. In

each folder, there are multiple files each of which represents an instant of a human

performing an activity.1 Each file containis 6 time series collected from activities

of the same person, which are called avg rss12, var rss12, avg rss13, var rss13,

vg rss23, and ar rss23. There are 88 instances in the dataset, each of which contains 6 time series and each time series has 480 consecutive values.

(b) Keep datasets 1 and 2 in folders bending1 and bending 2, as well as datasets 1,

2, and 3 in other folders as test data and other datasets as train data.

(c) Feature Extraction

Classification of time series usually needs extracting features from them. In this

problem, we focus on time-domain features.

i. Research what types of time-domain features are usually used in time series

classification and list them (examples are minimum, maximum, mean, etc).

ii. Extract the time-domain features minimum, maximum, mean, median, standard deviation, first quartile, and third quartile for all of the 6 time series

in each instance.

You are free to normalize/standardize features or use them

directly.2

Your new dataset will look like this:

Instance min1 max1 mean1 median1 · · · 1st quart6 3rd quart6

1

2

3

.

.

.

.

.

.

.

.

.

.

.

.

.

.

. . . .

.

.

.

.

.

.

88

where, for example, 1st quart6, means the first quartile of the sixth time series

in each of the 88 instances.

iii. Estimate the standard deviation of each of the time-domain features you

extracted from the data. Then, use Python’s bootstrapped or any other

method to build a 90% bootsrap confidence interval for the standard deviation

of each feature.

iv. Use your judgement to select the three most important time-domain features

(one option may be min, mean, and max).

2. ISLR 3.7.4

1Some of the data files need very minor cleaning. You can do it by Excel or Python.

2You are welcome to experiment to see if they make a difference.

3. Extra Practice (you do not need to submit the answers): ISLR 3.7.3, 3.7.5.

4. Time Series Classification Part 2: Binary and Multiclass Classification

Important Note: You will NOT submit this part with Homework 3. However, because it uses the features you extracted from time series data in

Homework 3, and because some of you may want to start using your features to build models earlier, you are provided with the instructions of the

next programming assignment.

Thus, you may want to submit the code

for Homework 3 with Homework 4 again, since it might need the feature

creation code. Also, since this part involves building various models, you

are strongly recommended to start as early as you can.

(a) Binary Classification Using Logistic Regression3

i. Assume that you want to use the training set to classify bending from other

activities, i.e. you have a binary classification problem. Depict scatter plots

of the features you specified in 1(c)iv extracted from time series 1, 2, and 6 of

each instance, and use color to distinguish bending vs. other activities. (See

p. 129 of the textbook).4

ii. Break each time series in your training set into two (approximately) equal

length time series. Now instead of 6 time series for each of the training

instances, you have 12 time series for each training instance. Repeat the

experiment in 4(a)i, i.e depict scatter plots of the features extracted from both

parts of the time series 1,2, and 6. Do you see any considerable difference in

the results with those of 4(a)i?

iii. Break each time series in your training set into l ∈ {1, 2, . . . , 20} time series

of approximately equal length and use logistic regression5

to solve the binary

classification problem, using time-domain features.

Remember that breaking

each of the time series does not change the number of instances. It only

changes the number of features for each instance. Calculate the p-values for

your logistic regression parameters in each model corresponding to each value

of l and refit a logistic regression model using your pruned set of features.6

Alternatively, you can use backward selection using sklearn.feature selection

or glm in R. Use 5-fold cross-validation to determine the best value of the pair

(l, p), where p is the number of features used in recursive feature elimination.

Explain what the right way and the wrong way are to perform cross-validation

3Some logistic regression packages have a built-in L2 regularization. To remove the effect of L2 regularization, set λ = 0 or set the budget C → ∞ (i.e. a very large value).

4You are welcome to repeat this experiment with other features as well as with time series 3, 4, and 5 in

each instance.

If you encountered instability of the logistic regression problem because of linearly separable classes,

modify the Max-Iter parameter in logistic regression to stop the algorithm immaturely and prevent from its

instability.

6R calculates the p-values for logistic regression automatically. One way of calculating them in Python

is to call R within Python. There are other ways to obtain the p-values as well.

in this problem.7 Obviously, use the right way! Also, you may encounter the

problem of class imbalance, which may make some of your folds not having

any instances of the rare class. In such a case, you can use stratified cross

validation. Research what it means and use it if needed.

In the following, you can see an example of applying Python’s Recursive

Feature Elimination, which is a backward selection algorithm, to logistic regression.

# R e c u r si v e Fea tu re Elimi na tio n

from s k l e a r n import d a t a s e t s

from s k l e a r n . f e a t u r e s e l e c t i o n import RFE

from s k l e a r n . li n e a r m o d el import L o g i s t i c R e g r e s s i o n

# loa d the i r i s d a t a s e t s

d a t a s e t = d a t a s e t s . l o a d i r i s ( )

# c r e a t e a ba se c l a s s i f i e r used to e v al u a t e a s u b s e t of a t t r i b u t e s

model = L o g i s t i c R e g r e s s i o n ( )

# c r e a t e the RFE model and s e l e c t 3 a t t r i b u t e s

r f e = RFE( model , 3 )

r f e = r f e . f i t ( d a t a s e t . data , d a t a s e t . t a r g e t )

# summarize the s e l e c t i o n of the a t t r i b u t e s

p r i n t ( r f e . s u p po r t )

p r i n t ( r f e . r a n ki n g )

iv. Report the confusion matrix and show the ROC and AUC for your classifier

on train data. Report the parameters of your logistic regression βi

’s as well

as the p-values associated with them.

v. Test the classifier on the test set. Remember to break the time series in

your test set into the same number of time series into which you broke your

training set. Remember that the classifier has to be tested using the features

extracted from the test set. Compare the accuracy on the test set with the

cross-validation accuracy you obtained previously.

vi. Do your classes seem to be well-separated to cause instability in calculating

logistic regression parameters?

vii. From the confusion matrices you obtained, do you see imbalanced classes?

If yes, build a logistic regression model based on case-control sampling and

adjust its parameters. Report the confusion matrix, ROC, and AUC of the

model.

(b) Binary Classification Using L1-penalized logistic regression

i. Repeat 4(a)iii using L1-penalized logistic regression,8

i.e. instead of using pvalues for variable selection, use L1 regularization. Note that in this problem,

you have to cross-validate for both l, the number of time series into which you

7This is an interesting problem in which the number of features changes depending on the value of the

parameter l that is selected via cross validation. Another example of such a problem is Principal Component

Regression, where the number of principal components is selected via cross validation.

8For L1-penalized logistic regression, you may want to use normalized/standardized features

break each of your instances, and λ, the weight of L1 penalty in your logistic

regression objective function (or C, the budget). Packages usually perform

cross-validation for λ automatically.9

ii. Compare the L1-penalized with variable selection using p-values. Which one

performs better? Which one is easier to implement?

(c) Multi-class Classification (The Realistic Case)

i. Find the best l in the same way as you found it in 4(b)i to build an L1-

penalized multinomial regression model to classify all activities in your training set.10 Report your test error. Research how confusion matrices and ROC

curves are defined for multiclass classification and show them for this problem

if possible.11

ii. Repeat 4(c)i using a Na¨ıve Bayes’ classifier. Use both Gaussian and Multinomial priors and compare the results.

iii. Which method is better for multi-class classification in this problem?

9Using the package Liblinear is strongly recommended.

10New versions of scikit learn allow using L1-penalty for multinomial regression.

11For example, the pROC package in R does the job.