1
vote
1answer
20 views

Using selected features from a wrapper algorithm to train another model

I was wondering if it can be useful to use selected features from a wrapper algorithm (for example SVM-RFE) to train another classification model like k-NN or Linear regression.
0
votes
0answers
41 views

HOG Feature Implementation with SVM in MATLAB

I would like to do classification based on HOG Features using SVM. I understand that HOG features is the combination of all the histograms in every cell (i.e. it becomes one aggregate histogram). ...
0
votes
0answers
39 views

HIstogram of oriented gradients (HOG) features descriptor theoretical problems

I'm going to implement HOG as my features descriptor. But there are some things that make me confused: For example: If we have an image with size of 10 x 20 If we want to compute the HOG of that ...
1
vote
0answers
31 views

What are some classic examples of feature selection in classification?

Is there a classic example showing the importance of good feature selection in classification? The ideal example would be simple, and very easy to understand. I've been volunteered/instructed to put ...
0
votes
1answer
30 views

What is parameter fine tuning means in SVM?

I got this sentence in one of paper, but I dont understand what does it mean?? " Training a learningbased classifier such as an SVM on an imbalanced dataset often requires parameter fine-tuning, ...
0
votes
0answers
18 views

Detecting noisy patterns in document images

I am looking for features to extract to distinguish between text objects and arbitrary noisy patterns in degraded document images. This is an example of a document with some parts of noise, I have ...
0
votes
1answer
72 views

Good algorithms for feature extraction from images?

I am searching for some algorithms for feature extraction from images which I want to classify using machine learning . I have heard only about [scale-invariant feature transform][1] (SIFT), I have ...
0
votes
1answer
36 views

How to compare features and classifiers which achieve perfect accuracy?

So I'm looking to compare different combinations of features and classifiers. But I'm getting a lot of combinations that achieve 100% cross validation accuracy. I'm trying to figure out how I would ...
2
votes
3answers
21 views

How to compare features and classifiers which achieve perfect accuracy?

So I'm looking to compare different combinations of features and classifiers. But I'm getting a lot of combinations that achieve 100% cross validation accuracy. I'm trying to figure out how I would ...
2
votes
1answer
45 views

Feature selection while retaining a specified feature

Pardon if this question is very basic, but I am not able to find any solution for my problem. I am trying to run a feature selection scheme on N features for my classification model, however I want ...
1
vote
0answers
36 views

Music classification into genres

I need to classify music (songs) into genres (rock, french house, trash metal, etc). My idea was to extract features from the songs (bmp, zero crossing, etc) and then apply known classification ...
1
vote
0answers
40 views

Classifier predicts only one class

I was trying myself in kaggle CIFAR competition, I trained lots of classifiers but get the same result/fail (don't know how to treat them), maybe someone could help me figure what i'm doing wrong. ...
3
votes
1answer
162 views

Understanding the output of C5.0 classification model using the CARET package

The C5.0 classification model was used in this 4-class problem data with $N_{train}$=165, $P$=11, using caret R-package by ...
1
vote
0answers
25 views

Estimating confidence of a prediction

Given a set of features vectors $X=\{\vec{x}_1,..,\vec{x}_n\}$, binary ground truth data $Y=\{y_1,..,y_n\}$ and continuous prediction $\bar{Y} = \{\bar{y}_1,..,\bar{y}_n\}\in [0,1]$, I want to perform ...
1
vote
0answers
33 views

Feature selection methods comparison

I recently run a project that involves a feature selection step before further pattern recognition. The number of features for our data set is very large and instead of running greedy ...
2
votes
1answer
121 views

How to interpret this cross-validated sparse LDA figure using CARET package?

Training data with $p$ =11 predictors and $n$ =165 with 4-class problem was cross-validated (5 times repeated 10-fold CV) using the sparse LDA (aka SDA) using caret ...
2
votes
2answers
80 views

Selecting a feature modeling approach for text classification

I am new to text processing. Currently I am trying to determine which type of feature vector I need for a classification problem. I am mainly deciding between binary feature modeling and ...
0
votes
2answers
53 views

Choosing the best featureset for prediction

I have this N sets of features F each with $F_i$ number of features. All the feature sets have 20000 examples and we have 20,000 labels for them. Lets say feature set $F_1$ has 10 features and ...
2
votes
2answers
92 views

improve precision in text classification

I am working on binary text classification using sklearn: The length of each sample is not high (~ 200-500 characters) I use TF-IDF to get important words as TfidfVectorizer(sublinear_tf=False, ...
1
vote
0answers
45 views

Inferring dimension weight in a mapping from a triangle to a distribution over its vertices

I have a dataset $(y_i, \mathbf{X}_i)$, where $\mathbf{X}_i$ is a $3 \times n$ matrix of reals and $y_i$ takes a value in $\{1, 2, 3\}$. Essentially, $y_i$ represents a "selection" of the row vector ...
0
votes
3answers
87 views

Classification performance and the feature set selection

I am now working on a classification problem. The generated feature set can be separated into two group. I did a comparison study: use all of the features; use the features of group 1 only; and use ...
0
votes
0answers
7 views

How to find entropy of vocabulary terms in multilabel document classification problem?

I have 5 million of document s with varying number of labels for each. I intent to find entropy value for selecting discriminative terms to degrade the size of vocab. However, having that multiple ...
1
vote
0answers
60 views

How to explain difference of importance between feature selection and model quality?

I have a data collection with a mixed feature set consisting of both numerical features and text features. The number of numerical features is quite small, i.e., 6, comparing to the number of text ...
0
votes
0answers
97 views

Time series classification

I am classifying a set of time series inputs after creating independent features from every $n$ samples and running machine learning algorithms. I get good accuracy based on many error metrics on the ...
0
votes
0answers
115 views

Weak Classifiers weights/contribution in Adaboost and Real adaboost?

In Adaboost according to SAMME implementation, the $\alpha$ determines the contribution of the weak classifier. Here is the Adaboost algorithm $\alpha$ is in step 2. (c) Now in RealAda boost I ...
2
votes
1answer
94 views

Number of samples vs Number of features

I've got a set of two classes with 4000 observations total. I've a set of 63 features to construct a predictor. My question is, is there a relation that would prevent overfiting for having too much ...
1
vote
0answers
29 views

How to use reservoir states for readout and training?

I’m trying to make a Liquid State Machine, I have a spiking neural network as the liquid, and a feedforward neural network that should learn to map the reservoir’s states to the output. I’ve read ...
8
votes
4answers
2k views

Test accuracy higher than training. How to interpret?

I've a dataset containing at most 150 examples (split into training & test), with many features (higher than 1000). I need to compare classifiers and feature selection methods which perform well ...
3
votes
1answer
328 views

Can we use random forest for classification in combination with distance matrix between classes?

With a colleague, we are working on a dataset containing ~5000 continuous variables for 120 individuals belonging to 8 classes. We want to estimate the relative importance of each variable to explain ...
2
votes
1answer
207 views

Features selection using F-score for multiclass classification

I'm going to implement a feature selection algorithm, and I plan to use the F-score for because of its simplicity. The problem is that, the F-score is used for binary classification. How can it be ...
1
vote
1answer
38 views

Finding similar users

I am working on a problem in the online advertising space. I am trying to identify consumers similar to the set of consumers who have bought a product in the past (have 'converted'). If I can identify ...
1
vote
0answers
82 views

True and false discovery rate in variable selection

I have a question about how I can calculate true and false positive rate in a simulation study? I have seen some articles and thesis by different definitions. One of them is the following one: ...
2
votes
0answers
38 views

Why do correlations matter in simulating data to compare classifiers when p >> N?

In genomics and computational biology, expression data sets contain a much larger number of features (p) than the number of observations (N). I wanted to simulate data where p>>N to compare the ...
2
votes
1answer
70 views

A buggy but effective feature?

Through error analysis I found that a quite effective feature actually has bugs in its implementation. Correcting the bugs actually decreased the classifier's performance. What do you do? Correct the ...
7
votes
4answers
775 views

Features for time series classification

I consider the problem of (multiclass) classification based on time series of variable length $T$, that is, to find a function $$f(X_T) = y \in [1..K]\\ \text{for } X_T = (x_1, \dots, x_T)\\ ...
1
vote
0answers
108 views

Number of features and accuracy/f-measure - Who can explain this results?

I'm performing a binary sentiment classification (positive/negative) based on a Naive Bayes classificator and a SVM. To select top k features I use the MRMR algorithm. The model is trained using a ...
0
votes
3answers
288 views

Classifier feature importance

If I train a GNB/LDA/kNN/other classifier I would like to know, in the model built, how important are features to classify or which feature(s) drives the classifier. For example in SVM models the ...
2
votes
0answers
169 views

time series with different length: feature extraction and classification [on hold]

I have a binary classification problem, where each data point is multi-channel time-series, which can be represented as a matrix $T \times F$, where $T$ is the time-series length, and $F$ as the ...
2
votes
1answer
137 views

Determining conserved features using a Bayesian approach

I would like to perform some sort of binary classification, and my data set consists of 100 examples (for each class), which are vectors with 2500 elements. Ideally, I would like to determine which ...
1
vote
0answers
208 views

Feature importance

The extremely randomized trees classifier (scikitlearn) provides a (multivariate) feature importance measurement Ensemble methods/feature importance evaluation. For each feature, the classifier ...
2
votes
1answer
170 views

Multiclass classification with SVM a question about the feature vectors

I was told I had to direct my machine learning questions to this site. So here it goes. I'm trying to do Multiclass classification with SVM. I have 7 classes. Now I was wondering if the following is ...
3
votes
2answers
85 views

Random search for the optimal number of input features and optimal number of hidden layers for a MLP?

I've performed a random search in hypothesis space $$\{(c,h)| c \in U[1,256]; h\in U[1,100];c \in \mathrm{Z} \text{ and } h \in \mathrm{Z}\}$$ that defines the parameters of a standard multilayer ...
2
votes
1answer
155 views

Selecting optimal number of input features and optimal number of hidden layers for a MLP?

What is the best way to select parameters for a binary neural network classifier? More specifically I have 265 features ranked according to Mutual Information Criterion. I have to determine the ...
1
vote
1answer
155 views

highly correlated features and high ranking

I am classifying different texts and I wondering about some features that are highly correlated. I have 49 features. Some features are absolute counters (integers) but most features are relative ...
4
votes
2answers
202 views

Why does increasing the number of features reduce performance?

I'm trying to gain an intuition as to why increasing the number of features could reduce performance. I'm currently using an LDA classifier which performs better bivariately among certain features ...
0
votes
0answers
144 views

What are the good algorithms for feature extraction for large dataset?

I have KDD dataset for detecting fraud actions on networks but it has millions of lines and >20 feature columns. Thus it is not viable to process all these on my personal computer. I am thinking about ...
3
votes
2answers
219 views

How to do feature selection for learning from positive and unlabeled examples?

I have a binary classification task for German webpages for which I only have positive examples. That is why I use learning from positive and unlabeled examples as described on this page, also known ...
7
votes
4answers
1k views

Low classification accuracy, what to do next?

So, I'm a newbie in ML field and I try to do some classification. My goal is to predict the outcome of a sport event. I've gathered some historical data and now try to train a classifier. I got around ...
2
votes
1answer
134 views

What properties of a text makes it a spam/bad question?

I'm trying to identify numeric properties of a text message that make it a spam or, more specifically, a bad question on sites like this one. For example, would things like capital letter density ...
0
votes
1answer
153 views

R package for feature set algorithm selection

I want to train a binary classification NN and part of this will require data pre-processing. However, I have a choice of which pre-processing algorithm to use. Of course I'd like to choose that one ...