Dark Mode
HTRU2 Pulsar Candidate Classification Data
Education & Learning Analytics
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
Data details the characteristics of pulsar candidates observed during the High Time Resolution Universe survey. Pulsars are a unique variety of Neutron star that produces radio emission detectable on Earth, making them objects of considerable scientific interest for studying space-time and stellar matter. The resource is specifically structured for machine learning tools to automatically label these candidates, framing the task as a binary classification problem for rapid analysis.
Columns
Each candidate in the collection is described by 8 continuous variables and a single class variable. The first four variables are simple statistics obtained from the integrated pulse profile, which is a longitude-resolved, time and frequency averaged signal that serves as a unique signature for each pulsar. The remaining four variables are similarly obtained from the DM-SNR curve, which measures how radio waves are dispersed by free electrons in space.
- 1. Mean of the integrated profile: Has a mean of 111 and a standard deviation of 25.7.
- 2. Standard deviation of the integrated profile: Has a mean of 46.5 and a standard deviation of 6.84.
- 3. Excess kurtosis of the integrated profile: Has a mean of 0.48 and a standard deviation of 1.06.
- 4. Skewness of the integrated profile: Has a mean of 1.77 and a standard deviation of 6.17.
- 5. Mean of the DM-SNR curve: Has a mean of 12.6 and a standard deviation of 29.5.
- 6. Standard deviation of the DM-SNR curve: Has a mean of 26.3 and a standard deviation of 19.5.
- 7. Excess kurtosis of the DM-SNR curve: Has a mean of 8.3 and a standard deviation of 4.51.
- 8. Skewness of the DM-SNR curve: Has a mean of 105 and a standard deviation of 107.
- 9. Class: The target variable for classification, containing 1,639 positive examples and 16,259 negative examples.
Distribution
The material is stored in a CSV file, named
HTRU_2.csv, with a file size of 1.73 MB. The dataset contains 17,898 total examples. All 9 columns are perfectly reliable, showing 100% validity with zero missing or mismatched records.Usage
This resource is ideally suited for implementing classification algorithms and developing machine learning models. It allows researchers to build systems to automatically identify and label pulsar candidates. The data can be used to compare the performance of various classification methods applied to astronomical signal analysis and binary classification problems in astrophysics.
Coverage
The data covers pulsar candidates identified during the High Time Resolution Universe survey. The scope includes statistical features derived from two key signal components: the integrated pulse profile and the DM-SNR curve. The data is static and is never expected to receive future updates.
License
CC BY-NC-SA 4.0
Who Can Use It
The dataset is intended for researchers, data scientists, and academics, particularly those focused on Astronomy and classification challenges. It is highly useful for users seeking to apply binary classification techniques to real-world stellar data. The material has a high usability rating of 10.00.
Dataset Name Suggestions
- HTRU2 Pulsar Candidate Classification Data
- Neutron Star Radio Emission Characteristics
- Binary Classification of Pulsar Candidates
- Pulsar Dataset HTRU2
Attributes
Original Data Source:HTRU2 Pulsar Candidate Classification Data
QUALITYLoading...