The tag has no wiki summary.

learn more… | top users | synonyms

0
votes
0answers
50 views

Setting a decision threshold in one-class classification with LIBSVM

I want to do anomaly detection with the one-class SVM implementation in LIBSVM. However, the prediction output of the trained SVM is binary. In my understanding, there has to be a "radius" parameter ...
1
vote
0answers
23 views

How to determine false detection in vote histograms

Possibly related question (wasn't sure so posted this one). I have a vote map (2D histogram) voting for object presence in an image, which contain multiple modes. Some correspond to true object ...
2
votes
0answers
39 views

How to pick a good threshold for multimodal histograms

I am trying to do multi-modal detection in a vote map (histogram) however, side lobes obviously cause some false peaks. So using mean shift will not do as it will find all of the local maxima. So I ...
1
vote
0answers
24 views

Remove variance from temporal observations (input to HMM emission) by manipulating the individual observations

I have 52 weekly observations of count data that has some spikes and a definite trend (available here). ...
1
vote
0answers
35 views

Modeling threshold effects

First, let me give some context for my question. I'm working on a project in which our research team implemented a workshop intervention at a number of different departments at my university. Each ...
0
votes
0answers
28 views

Relationship between threshold, number of features and accuracy/error? (text classification)

Are you aware of any research papers that explain a relationship between the following concepts? threshold (removal of features, whose frequencies are greater than or less than a defined ...
1
vote
1answer
86 views

How to assess the quality of a return period estimate?

Background I have a time series of structural loads, which are measured forces on a moored ocean buoy, and I need to obtain the return period value so that the structure can be designed to withstand ...
1
vote
0answers
44 views

What's a good measure of spread near a threshold?

I am choosing summary statistics for percentage data that is clustered near 100%. Each subject takes the same test twice. Each test consists of at least 40 questions. I want to be able to predict ...
0
votes
0answers
136 views

Testing threshold cointegration in vector error-correction models

In Hansen and Seo's paper on Testing two regime threshold cointegration in VECM (J. Econometrics, 2002; 110:293), the authors proposed a test based on Lagrange Multiplier for testing treshold in ...
2
votes
0answers
292 views

Distance threshold for clustering

Usually online clustering methods (based on kmeans or not) define a distance threshold value. If a new data-point $x$ is far enough from the nearest center $c$ (i.e. the distance from $x$ to $c$ is ...
2
votes
0answers
108 views

Establishing a dynamic threshold for partitioning data

Given a sorted set of data points, where each point represents the length of a common substring between two files, I want to systematically decide a cut off point where I can start considering them to ...
0
votes
1answer
115 views

How do I deal with datasets that have many values out of range / over threshold?

I have a dataset of genomic information which I'm going to be comparing with various biochemical markers. Unfortunately a lot of the biochemical markers have limited ranges in their assays, so I have ...
0
votes
0answers
157 views

Systematic way of choosing a threshold?

I am performing some analysis on understanding various characteristics of a certain population. To narrow down my selection (as I will be going through them manually), I am using different thresholds ...
6
votes
5answers
778 views

Automatic threshold determination for anomaly detection

I am working with a time series of anomaly scores (the background is anomaly detection in computer networks). Every minute, I get an anomaly score $x_t \in [0, 5]$ which tells me how "unexpected" or ...
3
votes
2answers
438 views

Threshold models and flu epidemic recognition

I'm fooling around with threshold time series models. While I was digging through what others have done, I ran across the CDC's site for flu data. http://www.cdc.gov/flu/weekly/ About 1/3 of the ...