Questions tagged [feature-extraction]

Variables (used for prediction or explication) used in regression or regression-like models (like clustering, discrimination). Use this tag for questions about constructing such variables or selecting the best among them.

Filter by
Sorted by
Tagged with
23
votes
2answers
11k views

Feature Transformation on Input data

I was reading about the solution to this OTTO Kaggle challenge and the first place solution seems to use several transforms for the input data X, for example Log(X+1), sqrt( X + 3/8), etc. Is there a ...
0
votes
1answer
1k views

Image Feature Vectors

I have downloaded a dataset from Amazon. http://jmcauley.ucsd.edu/data/amazon/ Dataset involves feature vectors of images. There are around 1.5 M feature vectors. Dataset consists of 10 characters (...
5
votes
1answer
120 views

Why is duplicating inputs bad?

I am trying to predict an output value based on several continuously-valued inputs using a regression model. I am not sure what approach is appropriate to scale/transform the input data for the ...
26
votes
3answers
17k views

Why do we convert skewed data into a normal distribution

I was going through a solution of the Housing prices competition on Kaggle (Human Analog's Kernel on House Prices: Advance Regression Techniques) and came across this part: ...
1
vote
1answer
326 views

Inception/ResNet doing worse than SIFT in feature extraction

We are doing our Thesis on multimodal retrieval. it's basically searching different modalities (multimedia ex: text, video, images ...) with other modalities. i.e. searching a database of images with ...
5
votes
1answer
4k views

How to transform raw data to fixed-frequency time series?

How to transform raw data to fixed-frequency time series? For example I have the following raw data in DataFrame ...
1
vote
2answers
555 views

How to quantify a tokenized user agent string for a neural network?

I am currently experimenting with user agent strings. My current plan is to tokenize the user agent string and split it in its important parts. Like OS, Browser Name, etc. After that, does it make ...
7
votes
2answers
5k views

What is the rationale for discretization of continuous features and when should it be done?

Continous feature discretization usually leads to lose of information due to the binning process. However most of the Top solutions for Kaggle Titanic are based on discretization(age,fare). When ...
4
votes
1answer
307 views

What is representation in optical character recognition?

I am learning OCR and reading this book The authors define 8 processes to implement OCR that follow one by one (2 after 1, 3 after 2 etc): Optical scanning Location segmentation Pre-processing ...
3
votes
1answer
322 views

Extracting sub features from inside a df cell?

I have a dataframe containing several features of form: ...
0
votes
2answers
501 views

Scalar entities for k means clustering

I am trying to understand kmeans clustering and I read a article where kmeans is used for clustering the features generated in network logs. This clustering is followed by a supervised classification. ...
1
vote
3answers
595 views

Detecting outlier with combining two vectors

I want to combine the following vectors in a way that just the red point (number 7) becomes inconsistent with other points( become an outlier and become distant from other points) and other points ...
1
vote
1answer
75 views

unsupervised learning in medical systems and intelligent systems?

I have a dataset which belongs to a hospital. It contains data about patients and healthy people. The problem is separating healthy ones from patients. I add some new features to dataset to solve this ...
39
votes
6answers
26k views

Encoding features like month and hour as categorial or numeric?

Is it better to encode features like month and hour as factor or numeric in a machine learning model? On the one hand, I feel numeric encoding might be reasonable, because time is a forward ...
5
votes
1answer
657 views

Time Series pattern recognition and classification problem

I have some labeled sensor data. Now, I would like to know how to extract features from time series using DFT, DWT, and HAAR transforms. I know that the transformations above transform a signal to ...
7
votes
3answers
34k views

Extracting Features Using TensorFlow CNN

I'm trying to extract features of set of images. I'm using CNN from this site. Can anyone please tell me how to do feature extraction of images using CNN? I looked for various places. But nowhere it'...
13
votes
3answers
5k views

How to use GAN for unsupervised feature extraction from images?

I have understood how GAN works while two networks (generative and discriminative) compete with each other. I have built a DCGAN (GAN with convolutional discriminator and de-convolutional generator) ...
1
vote
0answers
229 views

HIgher Order Interaction Variables. How to use them in model? [closed]

http://stats.idre.ucla.edu/stata/webbooks/logistic/chapter2/ This above website gives an example about using interaction effect between variables. Interacting variables are multiplied and used in the ...
1
vote
0answers
385 views

Feature extraction in ConvNNs - layers progression

This is a bit of a confusion I have and I never saw any explanation of it, so I have to ask the question. Whenever I see the discussion on how a ConvNNs extracts features, I see something like this: ...
9
votes
1answer
303 views

How does a convolutional ply differ from an ordinary convolutional network?

I am currently working on recreating the results of this paper. In the paper they describe a method for using CNN for features extraction, and have a acoustic model that is Dnn-hmm and pretrained ...
0
votes
1answer
82 views

Feature Selection Algorithm for Attributes with Logical Relationships (like “AND”)

I'm looking at datasets where the the attributes and the target class have a logical relationsships. All attributes and the target class are binary. Here's an example: Neither ...
2
votes
1answer
121 views

Generating data that look alike my original data

If I have a set of N data, each individual data has 4 features. I do not know a priori the relations that could exist (or don't exist) between the features. Is it possible to generate new data from ...
3
votes
2answers
405 views

Modern Feature Selection Review/Resources

I found this review paper by Guyon and Elisseeff in a 2003 JMLR publication but, although not outdated, it is quite old. Is there a more recent review or resource on the topic of feature selection? ...
0
votes
2answers
387 views

Feature extraction from web browsing history of one website

I have a dataset of web browsing histories for users visiting a particular website over a period of time (say the last 90 days). Each user has a unique ID and several records showing when he/she ...
0
votes
3answers
76 views

Feature usage for machine learning algorithm

Given a list of software installed by users as features, e.g., Microsoft_VC80_DebugCRT_x86_x64 1.0.0; Microsoft_VC80_DebugCRT_x86 1.0.0; ;Windows UPnP Browser 0.1.01;Adobe Acrobat Professional 10; I ...
1
vote
1answer
303 views

Feature extraction - wavelet transformation + autoregression

I am working on a feature extraction problem (ECG signal). Within my literature review I stumbled across the following text: "The wavelet transform is used to extract the coefficients of the ...
2
votes
1answer
3k views

Boruta feature selection in R with custom importance (xgboost feature importance)

According to the documentation - CRAN Boruta is an all relevant feature selection wrapper algorithm, capable of working with any classification method that output variable importance measure (VIM); ...
1
vote
1answer
2k views

Image feature extraction Python skimage blob_dog

I am trying to extract features from images using: ...
4
votes
1answer
6k views

Use TSFRESH-library to forecast values

Have some issue with understanding how to use TSFERSH-library (version 0.4.0) to forecast next N-values of particular series. Below my code: ...
0
votes
1answer
3k views

Feature extraction for sentiment analysis

I am working on a group project for my capstone course and we have been tasked with creating a sentiment analysis tool with Python business logic and (L/W)AMP everything else. We have good feedback ...
2
votes
1answer
655 views

Feature Selection, Machine learning and Time Series analysis, for large financial timeseries

I have m( around O(millions) ) of rows of type timestamp | val | ind1 | ind2 | ind3 | .... k entries My task is to predict the value of "val" for any future ...
2
votes
2answers
291 views

Feature Engineering

I have a data frame with around 37,000 rows and 54 columns. Out of these 54 columns, two columns namely 'user_id' and 'mail_id' are provided in a very creepy format as shown below: ...
0
votes
1answer
3k views

Using scikit-learn FeatureHasher

I have a huge data set with one of the columns named 'mail_id'. The mail_id is given in a very creepy format as shown below: ...
1
vote
1answer
415 views

Multiple binary dummy features Vs Multi-values single feature

I found a script on Kaggle's titanic competion in wich the creator convert Multi-values single feature (namely Pclass = {1,2,3}) to 3 binary features. What are the pro/cons of such a conversion? Does ...
0
votes
2answers
131 views

Which features can help to differentiate these two density?

I'm wondering that is there any features that can help in differentiating the following two images. I mean differentiating in related numbers.
3
votes
1answer
373 views

How many features should I take out of 515 features?

In continuation to this question, I have a conceptual question. If I am not using the 'nfeatures' then I am getting 7 features from a feature set of 515 features. If I use the 'nnfeatures' tag (this ...
2
votes
2answers
142 views

Different runs of feature selection algorithm giving different set of selected feature. How to choose the best set among them?

I am using the forward feature selection algorithm from MATLAB. The code is as follows: ...
2
votes
1answer
74 views

extracting information in presence of noise

Assume I have a vector of displacements, when I calculate the derivative I obtain velocity. The problem is, there are so many noisy points and I am looking for one number as a velocity. What do you ...
15
votes
2answers
16k views

List of feature engineering techniques

Is there any resource with a list of feature engineering techniques? A mapping of type of data, model and feature engineering technique would be a gold mine.
0
votes
2answers
448 views

Features from images using opencv in Python

I want to start with image processing (image classification). I installed opencv and plan to use it with Python. Being starter at this, I am looking for references regarding trivial ...
3
votes
1answer
5k views

Choosing the right parameters to train a Tf-Idf vectoriser

I'm very new to the DS world, so please bear with my ignorance. I'm trying to analyse user comments in Spanish. I have a somewhat small dataset (in the 100k's -- is that small?), and when I run the ...
0
votes
1answer
64 views

Advance Methods of Understanding Significance of Customer Behaviors

I currently own a couple of websites and lately I've been implementing some feature changes - I've noticed some changes in website traffic and I was wondering what some of the more sophisticated ways ...
3
votes
1answer
194 views

how to determine hashing bit length for multiple categorical features?

Say I have $N$ categorical features $f_i$ $i\in(1,N)$ each of which of different alphabet size $n_i$. How can I efficiently optimize the hashing trick on that feature vector? Should I enumerate hash ...
1
vote
1answer
1k views

Feature Extraction - calculate slope

Having a bit of a mind-blank at the moment and am looking for some advice. I am extracting features from time series data for input into a classification algorithm, for example I'm extracting ...
4
votes
3answers
2k views

Categorizing Customer Emails

I am working on a project for a company which needs to categorize customer e-mails regarding loans and insurance. The e-mails are labeled uniquely from set of 13 category labels. The number of records ...
1
vote
1answer
291 views

Ground-truth and feature extraction for predictive modelling

I have a dataset of users, each user has has daily information about his activities (numerical values representing some measurements of his physical activities). In addition, each user in each day ...
0
votes
1answer
399 views

Time-stamp for linear model

How can we extract information from time-stamp variable for modelling? I have a variable with format mm-dd-yyyy hh:mm:ss I want to predict an outcome variable using time-stamp as input variable. I do ...
1
vote
1answer
1k views

Feature selection - QR code localization

I just started learning about machine learning recently and have a project where I have to develop a program for QR code localization so that a QR code can be detected and read at any angle of ...
8
votes
2answers
1k views

Averaging two Word2vec vectors to obtain a unified representation for single word

I have been working on a trained data for Word2vec algorithm. Since we need words to stay as original we don't make them lowercase at the preprocessing phase. Thus there are words with different ...
1
vote
1answer
451 views

xgboost performance with predicted values as input

I have predicted the probability of loss using different features. Now when I used this with a non-important feature to predict the probability of loss. The first one is very close. logloss was close ...

1
3 4 5
6
7