Questions tagged [classification]

Statistical classification is the problem of identifying the sub-population to which new observations belong, where the identity of the sub-population is unknown, on the basis of a training set of data containing observations whose sub-population is known. Therefore these classifications will show a variable behavior which can be studied by statistics.

2,257 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
0
votes
0answers
243 views

Two tails or one tail McNemar's test in a binary classification problem. Which one should i choose?

I'm using McNemar's test for compare two designed models in a binary classification problem. As you know we have two kinds of this test. ...
0
votes
1answer
86 views

Regression/classification, how to accommodate the missing columns of data?

I would like to apply any regression methods, such as the ones available using WEKA libraries (for example, SVMs, NNs, Random Trees,...) . However, I am getting very low results since I am missing the ...
0
votes
0answers
47 views

In search of a proper similarity function

I'm trying to find the most similar sample between a candidate and a bag of samples. Consider you have a knowledge corpus as follows: ...
0
votes
1answer
79 views

Is this a case of semi-supervised classification?

This is a question about proper terminology related with what is understood with "Semi-Supervised Classification". This is my context: I have a rule-based classifier. I know for sure I can classify ...
0
votes
0answers
77 views

How many samples do I need to prove that a classification algorithm is better than another?

I have two algorithms A and B, used to automatically classify each of N elements into K categories, N and K both being in the millions. Neither A or B is perfect, but it is relatively easy for a human ...
0
votes
0answers
689 views

How many features can be used for classification?

Asked a similar question the other day without an answer Link. I think maybe the question there is too big. Here I want to ask a specific one: 2 Class labels (Binary classification labelled with ...
0
votes
1answer
81 views

Evolution strategies in libsvm

I'm working on a protein multi-classification problem, using libsvm and the edit distance kernel. This kernel depends on a parameter $\gamma$. I'm able to get the best parameters ($\gamma$ and $C$) ...
0
votes
0answers
47 views

Approach for credit scoring for an agricultural products/chemicals company

I am currently working on a project for a large agri-business company. We currently have a credit policy that gives scores and classifies the debtors of the company into 5 segments - VLR (Very low ...
0
votes
0answers
63 views

Understand the parameters for multiple regression - question based on the notations in a given algorithm

I've set up a regression model but am not sure if I'm doing it right. I'm using multiple regression to help do multi-class classification. So far I feel like I've understood the theory, but I'm ...
0
votes
1answer
32 views

How to cluster direction of traffic data?

I have data on many trips (same route). The trip content: latitude, longitude, and ...
0
votes
2answers
47 views

How to score detector

I'm developing a classifier system to detect objects of interest in images. I want to report a score, but I'm a bit lost as to what the most fair and informative number is. Sensitivity and ...
0
votes
0answers
38 views

Probablistic counterpart for decision trees

We know if Gaussian Mixture Model is a probablistic counterpart of k-means algorithm. Is there a probablistic counterpart for decision-trees? UPDATE: I know that branching in DT can be probablistic. ...
0
votes
1answer
49 views

Standardising the weights generated from feedforward back propagation NN

I have binary data input to NN. The weights generated by NN are not normalized, i.e., the weights are not the same for every run of the algorithm. How to standardize these weights?
0
votes
0answers
399 views

How to make the most of a Gaussian mixture assumption in a model?

I have a dataset with 100 columns and approximately 100000 lines. I have a variable to predict that is Y (0,1 so it's a classification problem). I have an other categorical variable with two values ...
0
votes
0answers
82 views

How can i add a weight correctly in a classification algorithm created by me of handwritten sign?

I have 150 images of handwritten signs (like cross, star, circle, tridents), i extracted from them the number of branched point, ent-point and "close" a s feaetures (Having said that features are not ...
0
votes
0answers
58 views

Impact of biased sampling on classifier training ?

Let's imagine I have a very unbalanced dataset with 99.99% of 0 and 0.01% of 1 on the target variable. What I want to do is make a classifier for this target. Now imagine that this dataset is very ...
0
votes
0answers
25 views

Choose canonical values from clusters of erroneous ones

I suspect this is a statistical problem, but it may be just an algorithmic one. So, more formally: Given: a set C of unknown ‘canonical' values an error window e a set V of known values, s.t. ...
0
votes
0answers
49 views

Procedure for finding boundaries

I have a data set of two variables as class and test score. Where class is a classification made by experts and test score ranges 0-10. The data set looks like: ...
0
votes
0answers
758 views

SVM with overlapping classes

Following my earlier post, I have successfully run linear svm on some datasets, however for other datasets, it is failing. These are the datasets where range of one class lies within that of the next ...
0
votes
0answers
2k views

How to use Gaussian mixture model for multivariate pattern classification

I am new to statistical pattern recognition and trying to learn.To begin with I am trying to work with two class problems and trying to classify motion activities as mentioned in the paper "Object ...
0
votes
0answers
495 views

Alternative to LDA

Is there an alternative to using LDA and regression models to classify data where the response variable is assumed to have a linear relationship with the predictor? Essentially I am trying to find ...
0
votes
0answers
724 views

How to classify different types of fingerprints using svm two class problem in matlab?

Here I am working on fingerprint recognition. I am using SVM for fingerprint feature verification and classification. I want to classify fingerprint images using two class problem of SVM that means in ...
0
votes
0answers
268 views

How to utilize the output probabilities from a probabilisitic classifier?

Can anybody please explain that in simple words: how can we correctly use probabilities given by some classifiers along with the predicted class values? Let us consider some implementation of a Naive ...
0
votes
0answers
177 views

Significance index of unlabeled data prediction

I have a training set used to train an SVM classifier, the model found is used to predict a dataset of several unlabeled examples. I would like to know how to extract an index of the goodness of the ...
0
votes
0answers
505 views

Can RBMs be used for feature selection / reduction?

I have a data set that's ~ 150R X 2000C and was curious if an RBM is appropriate in situation with this type of imbalance. It's a microarray and I'm looking at a 0/1 classification problem. I'd be ...
0
votes
0answers
203 views

Best way to classify hierarchical data

First of all, I want to be clear that I am new to AI, although I've learned a bit about classification. Let's say I have a hierarchical sets of words: ...
0
votes
0answers
139 views

Adding training examples to Bayesian classifier reduces accuracy

I'm working on a problem to predict/classify overall sentiment of a large amount of text, which I can verify on the next day. Each data point is a day and is composed of multiple articles. I bin the ...
0
votes
0answers
515 views

CART with rpart and a 12 level factor

I have a 12-level factor variable (month) in my dataset and I wanted to fit a CART tree with rpart(). Would you split the 12-level factor variable into 12 dummy variables? If I fit the model with one ...
0
votes
0answers
197 views

Problem with classifying new observations with discriminant analysis

I have a data set of 40,000 individuals which I clustered using k-means. I used 30 variables, each ordinal from 1=minimum to ...
0
votes
0answers
945 views

LMNN: Simple Algorithm Description

B"H Hello, I understand the principles of LMNN (Large-Margin Nearest Neighbor) classification very well, but not all that well Weinberger's pseudo-code for its implementation. Can anyone simply (but ...
0
votes
0answers
745 views

What is the appropriate method to use to calculate customer lifetime value?

I'd like to figure out what the potential lifetime value of a customer may be based on their purchasing patterns with our products. I have transactional data that tells me what a customer purchased, ...
0
votes
1answer
38 views

Should Learning Curves be Plotted only on Train or the Entire Dataset?

In order to compare a few models to start my ML project, first I split the dataset into train and test, and then performed nested CV on the training set only and got my fair estimate of true risk on ...
0
votes
1answer
610 views

Best Suitable feature selection method for ordinal logistic regression

I have 33 variables my dataset, I need to omit some less significant features then, which is the "best suitable feature selection method " for the Ordinal Logistic Regression?
0
votes
1answer
311 views

One class of Ordinal DV values has too few observations - best way to address

I am doing an ordinal classification using glmnet, with 3 level class DV: 1 (bad), 2(ok), 3(good). I am trying to fit a model to this ordinal DV, and find best features. The problem is that one of the ...
0
votes
1answer
85 views

Anomaly detection

I am trying to categorize the functionality of batteries in one kind of device. I am using linear models to find the functionality of batteries over time (considering other variables in the device ...
0
votes
1answer
3k views

Interpreting log-loss as percentage

I know that log-loss penalises models that are confident with the wrong predicted classes. Can this be translated to percentage accuracy? If not, then how do I report the error or compare it to other ...
0
votes
1answer
39 views

which of these 2 classification models is best

The difference between the two models is the label, which is slightly differently defined for the 2nd model. So for model 2 there are less data that fall in class 1.0 (87161 versus 155915). Which of ...
0
votes
1answer
503 views

converting discrete values to buckets to perform predictions

I have a set of continuous discrete values, which I would like to convert to a classification task. Say, my scores in an exam are anything between 0-100. I want to convert my scores in the next exam ...
-1
votes
0answers
31 views

The feature space with different shapes for the training and the testing phases

I use a supervised learning algorithm to classify a set of items $E=\{e_1, e_2, ... e_n\}$ into two categories: $\{0,1\}^n$. The features generated for an instance of the training phase for E are a ...
-1
votes
1answer
53 views

How to estimate cut off percentiles to classify cost per metric?

I work at an ad agency and one of our key performance metrics is what we call "cost per outcome". Right now I have advertisements grouped by type of advertisement, lets say type "A"...
-1
votes
1answer
204 views

Anyway i can improve this multi class classification result?

I am building a multi class classification model using SVM to predict the grade for essays. What can I do to improve the result especially for class 1 and class 3? Their precision and recall are ...
-1
votes
2answers
311 views

how to classify input image using clustering algorithm such as k-mean?

I want to classify cifar10 images using a clustering algorithm (k-mean). Each image in the cifar10 dataset has a label, so, the results must be a set of labels which are corresponding to the test ...
-1
votes
1answer
99 views

clustering VS supervised classification, in the case of very small database

I'm trying to classify/cluster subjects according to 4 features in two classes: healthy and sick. Two things to know: I know the labels/classes of each subject + I only have 40 subjects (in total: ...
-1
votes
1answer
874 views

Classification accuracy on multi classes

My target has 5 classes. My testing dataset has an accuracy of about 34%. Can I assume this is a reasonable model purely based on classification accuracy, since random guessing is 20%.
-1
votes
1answer
26 views

Class variable, table and chisq.test functions question

1.-I am calculating the probability of default with Chi-squared test Null Hypothesis [chisq.test() function]. 2.- My dependent variable is "default" that has two values: 1 (applicant defaulted on ...
-1
votes
1answer
366 views

Behavior segmentation using DBSCAN, K-means Clustering and time series clustering

I have web UI event data representing various uses case scenarios with multiple data entry points. I would like to build some sort of DBSCAN, K-means Clustering solution to come up with user behavior ...
-1
votes
1answer
88 views

Why classification algorithms have very high error?

Let me explain more about my question: I have collected 2000 data as the following: age sex education residence music young male Primary_school east ...
-1
votes
1answer
273 views

Principal component analysis on signal … dealing with replicates

I have a spectrum data (wavelength(x) versus absorption(y)) for 25 unique samples that is almost exactly to the problem presented in this thesis: https://brage.bibsys.no/xmlui//bitstream/handle/11250/...
-1
votes
1answer
207 views

Class similarity coefficient for kNN

In our group we are dealing with misplacement of items and we came out with a method derived from knn, but we are not sure if there is already some place where this was described. The method would be ...
-1
votes
1answer
743 views

How to do classification without class labels?

I am comparing different classification and clustering methods for analyzing my game (called Memori) data. It is about diagnosing kids with VSMD. I have fount a dataset from 1980s with only 2 ...