Data
Satellite

Satellite

active ARFF Publicly available Visibility: public Uploaded 22-09-2017 by Minh-Anh Le
3 likes downloaded by 70 people , 133 total downloads 0 issues 0 downvotes
  • Life Science Medicine study_293 study_270 study_271
Issue #Downvotes for this reason By


Loading wiki
Help us complete this description Edit
Author: Markus Goldstein Source: [Dataverse](http://www.madm.eu/downloads https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/OPQMVF) Please cite: The satellite dataset comprises of features extracted from satellite observations. In particular, each image was taken under four different light wavelength, two in visible light (green and red) and two infrared images. The task of the original dataset is to classify the image into the soil category of the observed region. ### Classes We defined the soil classes “red soil”, “gray soil”, “damp gray soil” and “very damp gray soil” as the normal class. From the semantically different classes “cotton crop” and “soil with vegetation stubble” anomalies are sampled. After merging the original training and test set into a single dataset, the resulting dataset contains 5,025 normal instances as well as 75 randomly sampled anomalies (1.49%) with 36 dimensions ### Relevant Papers Goldstein, Markus, and Seiichi Uchida. A comparative evaluation of unsupervised anomaly detection algorithms for multivariate data." PloS one 11.4 (2016): e0152173 This dataset is not the original dataset. The target variable 'Target' is relabeled into 'Normal' and 'Anomaly'

37 features

Target (target)nominal2 unique values
0 missing
V1numeric49 unique values
0 missing
V2numeric81 unique values
0 missing
V3numeric69 unique values
0 missing
V4numeric78 unique values
0 missing
V5numeric48 unique values
0 missing
V6numeric76 unique values
0 missing
V7numeric68 unique values
0 missing
V8numeric76 unique values
0 missing
V9numeric47 unique values
0 missing
V10numeric77 unique values
0 missing
V11numeric69 unique values
0 missing
V12numeric81 unique values
0 missing
V13numeric49 unique values
0 missing
V14numeric77 unique values
0 missing
V15numeric67 unique values
0 missing
V16numeric73 unique values
0 missing
V17numeric49 unique values
0 missing
V18numeric72 unique values
0 missing
V19numeric67 unique values
0 missing
V20numeric75 unique values
0 missing
V21numeric47 unique values
0 missing
V22numeric73 unique values
0 missing
V23numeric69 unique values
0 missing
V24numeric84 unique values
0 missing
V25numeric49 unique values
0 missing
V26numeric78 unique values
0 missing
V27numeric69 unique values
0 missing
V28numeric78 unique values
0 missing
V29numeric48 unique values
0 missing
V30numeric78 unique values
0 missing
V31numeric68 unique values
0 missing
V32numeric78 unique values
0 missing
V33numeric49 unique values
0 missing
V34numeric76 unique values
0 missing
V35numeric70 unique values
0 missing
V36numeric80 unique values
0 missing

62 properties

5100
Number of instances (rows) of the dataset.
37
Number of attributes (columns) of the dataset.
2
Number of distinct values of the target attribute (if it is nominal).
0
Number of missing values in the dataset.
0
Number of instances with at least one value missing.
36
Number of numeric attributes.
1
Number of nominal attributes.
-0.41
Minimum skewness among attributes of the numeric type.
2.7
Percentage of nominal attributes.
Third quartile of mutual information between the nominal attributes and the target attribute.
2
The maximum number of distinct values among attributes of the nominal type.
11.66
Minimum standard deviation of attributes of the numeric type.
First quartile of entropy among attributes.
0.07
Third quartile of skewness among attributes of the numeric type.
0.12
Maximum skewness among attributes of the numeric type.
1.47
Percentage of instances belonging to the least frequent class.
-0.88
First quartile of kurtosis among attributes of the numeric type.
15.73
Third quartile of standard deviation of attributes of the numeric type.
16.22
Maximum standard deviation of attributes of the numeric type.
75
Number of instances belonging to the least frequent class.
74.66
First quartile of means among attributes of the numeric type.
0
Standard deviation of the number of distinct values among attributes of the nominal type.
Average entropy of the attributes.
1
Number of binary attributes.
First quartile of mutual information between the nominal attributes and the target attribute.
-0.46
Mean kurtosis among attributes of the numeric type.
-0.3
First quartile of skewness among attributes of the numeric type.
85.71
Mean of means among attributes of the numeric type.
12.35
First quartile of standard deviation of attributes of the numeric type.
1
Average class difference between consecutive instances.
Average mutual information between the nominal attributes and the target attribute.
An estimate of the amount of irrelevant information in the attributes regarding the class. Equals (MeanAttributeEntropy - MeanMutualInformation) divided by MeanMutualInformation.
Second quartile (Median) of entropy among attributes.
0.11
Entropy of the target attribute values.
2
Average number of distinct values among the attributes of the nominal type.
-0.44
Second quartile (Median) of kurtosis among attributes of the numeric type.
0.01
Number of attributes divided by the number of instances.
-0.11
Mean skewness among attributes of the numeric type.
85.34
Second quartile (Median) of means among attributes of the numeric type.
Number of attributes needed to optimally describe the class (under the assumption of independence among attributes). Equals ClassEntropy divided by MeanMutualInformation.
14.24
Mean standard deviation of attributes of the numeric type.
Second quartile (Median) of mutual information between the nominal attributes and the target attribute.
98.53
Percentage of instances belonging to the most frequent class.
Minimal entropy among attributes.
-0.09
Second quartile (Median) of skewness among attributes of the numeric type.
5025
Number of instances belonging to the most frequent class.
-1
Minimum kurtosis among attributes of the numeric type.
2.7
Percentage of binary attributes.
14.66
Second quartile (Median) of standard deviation of attributes of the numeric type.
Maximum entropy among attributes.
72.36
Minimum of means among attributes of the numeric type.
0
Percentage of instances having missing values.
Third quartile of entropy among attributes.
0.08
Maximum kurtosis among attributes of the numeric type.
Minimal mutual information between the nominal attributes and the target attribute.
0
Percentage of missing values.
-0.09
Third quartile of kurtosis among attributes of the numeric type.
99.57
Maximum of means among attributes of the numeric type.
2
The minimal number of distinct values among attributes of the nominal type.
97.3
Percentage of numeric attributes.
97.14
Third quartile of means among attributes of the numeric type.
Maximum mutual information between the nominal attributes and the target attribute.

16 tasks

2078 runs - estimation_procedure: 10-fold Crossvalidation - evaluation_measure: area_under_roc_curve - target_feature: Target
0 runs - estimation_procedure: 10 times 10-fold Crossvalidation - target_feature: Target
0 runs - estimation_procedure: 10-fold Crossvalidation - evaluation_measure: f_measure - target_feature: Target
0 runs - estimation_procedure: 33% Holdout set - target_feature: Target
0 runs - estimation_procedure: 4-fold Crossvalidation - target_feature: Target
0 runs - estimation_procedure: 10-fold Crossvalidation - evaluation_measure: predictive_accuracy - target_feature: Target
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
Define a new task