Data
robot-failures-lp3

robot-failures-lp3

active ARFF Publicly available Visibility: public Uploaded 01-06-2015 by Rafael G. Mantovani
0 likes downloaded by 0 people , 0 total downloads 0 issues 0 downvotes
Issue #Downvotes for this reason By


Loading wiki
Help us complete this description Edit
Author: Luis Seabra Lope, Luis M. Camarinha-Matos Source: UCI Please cite: * Dataset Title: Robot Execution Failures Data Set * Abstract: This dataset contains force and torque measurements on a robot after failure detection. Each failure is characterized by 15 force/torque samples collected at regular time intervals * Source: Original Owner and Donor Luis Seabra Lopes and Luis M. Camarinha-Matos, Universidade Nova de Lisboa, Monte da Caparica, Portugal * Data Set Information: The donation includes 5 datasets, each of them defining a different learning problem: * LP1: failures in approach to grasp position * LP2: failures in transfer of a part * LP3 (This dataset): position of part after a transfer failure * LP4: failures in approach to ungrasp position * LP5: failures in motion with part In order to improve classification accuracy, a set of five feature transformation strategies (based on statistical summary features, discrete Fourier transform, etc.) was defined and evaluated. This enabled an average improvement of 20% in accuracy. The most accessible reference is [Seabra Lopes and Camarinha-Matos, 1998]. * Attribute Information: All features are numeric although they are integer valued only. Each feature represents a force or a torque measured after failure detection; each failure instance is characterized in terms of 15 force/torque samples collected at regular time intervals starting immediately after failure detection; The total observation window for each failure instance was of 315 ms. Each example is described as follows: class Fx1 Fy1 Fz1 Tx1 Ty1 Tz1 Fx2 Fy2 Fz2 Tx2 Ty2 Tz2 ...... Fx15 Fy15 Fz15 Tx15 Ty15 Tz15 where Fx1 ... Fx15 is the evolution of force Fx in the observation window, the same for Fy, Fz and the torques; there is a total of 90 features. * Relevant Papers: Seabra Lopes, L. (1997) "Robot Learning at the Task Level: a Study in the Assembly Domain", Ph.D. thesis, Universidade Nova de Lisboa, Portugal. Seabra Lopes, L. and L.M. Camarinha-Matos (1998) Feature Transformation Strategies for a Robot Learning Problem, "Feature Extraction, Construction and Selection. A Data Mining Perspective", H. Liu and H. Motoda (edrs.), Kluwer Academic Publishers. Camarinha-Matos, L.M., L. Seabra Lopes, and J. Barata (1996) Integration and Learning in Supervision of Flexible Assembly Systems, "IEEE Transactions on Robotics and Automation", 12 (2), 202-219.

91 features

Class (target)nominal4 unique values
0 missing
V1numeric29 unique values
0 missing
V2numeric33 unique values
0 missing
V3numeric31 unique values
0 missing
V4numeric37 unique values
0 missing
V5numeric35 unique values
0 missing
V6numeric28 unique values
0 missing
V7numeric32 unique values
0 missing
V8numeric29 unique values
0 missing
V9numeric26 unique values
0 missing
V10numeric34 unique values
0 missing
V11numeric38 unique values
0 missing
V12numeric25 unique values
0 missing
V13numeric27 unique values
0 missing
V14numeric34 unique values
0 missing
V15numeric25 unique values
0 missing
V16numeric34 unique values
0 missing
V17numeric36 unique values
0 missing
V18numeric21 unique values
0 missing
V19numeric26 unique values
0 missing
V20numeric25 unique values
0 missing
V21numeric27 unique values
0 missing
V22numeric33 unique values
0 missing
V23numeric30 unique values
0 missing
V24numeric18 unique values
0 missing
V25numeric28 unique values
0 missing
V26numeric27 unique values
0 missing
V27numeric23 unique values
0 missing
V28numeric36 unique values
0 missing
V29numeric32 unique values
0 missing
V30numeric21 unique values
0 missing
V31numeric26 unique values
0 missing
V32numeric24 unique values
0 missing
V33numeric19 unique values
0 missing
V34numeric29 unique values
0 missing
V35numeric31 unique values
0 missing
V36numeric18 unique values
0 missing
V37numeric23 unique values
0 missing
V38numeric22 unique values
0 missing
V39numeric22 unique values
0 missing
V40numeric32 unique values
0 missing
V41numeric30 unique values
0 missing
V42numeric18 unique values
0 missing
V43numeric23 unique values
0 missing
V44numeric20 unique values
0 missing
V45numeric23 unique values
0 missing
V46numeric31 unique values
0 missing
V47numeric32 unique values
0 missing
V48numeric18 unique values
0 missing
V49numeric21 unique values
0 missing
V50numeric21 unique values
0 missing
V51numeric18 unique values
0 missing
V52numeric33 unique values
0 missing
V53numeric34 unique values
0 missing
V54numeric19 unique values
0 missing
V55numeric17 unique values
0 missing
V56numeric25 unique values
0 missing
V57numeric17 unique values
0 missing
V58numeric33 unique values
0 missing
V59numeric31 unique values
0 missing
V60numeric16 unique values
0 missing
V61numeric19 unique values
0 missing
V62numeric23 unique values
0 missing
V63numeric20 unique values
0 missing
V64numeric32 unique values
0 missing
V65numeric32 unique values
0 missing
V66numeric20 unique values
0 missing
V67numeric19 unique values
0 missing
V68numeric24 unique values
0 missing
V69numeric20 unique values
0 missing
V70numeric28 unique values
0 missing
V71numeric27 unique values
0 missing
V72numeric19 unique values
0 missing
V73numeric13 unique values
0 missing
V74numeric17 unique values
0 missing
V75numeric18 unique values
0 missing
V76numeric29 unique values
0 missing
V77numeric24 unique values
0 missing
V78numeric15 unique values
0 missing
V79numeric15 unique values
0 missing
V80numeric18 unique values
0 missing
V81numeric21 unique values
0 missing
V82numeric27 unique values
0 missing
V83numeric24 unique values
0 missing
V84numeric20 unique values
0 missing
V85numeric14 unique values
0 missing
V86numeric19 unique values
0 missing
V87numeric20 unique values
0 missing
V88numeric27 unique values
0 missing
V89numeric24 unique values
0 missing
V90numeric19 unique values
0 missing

62 properties

47
Number of instances (rows) of the dataset.
91
Number of attributes (columns) of the dataset.
4
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.
90
Number of numeric attributes.
1
Number of nominal attributes.
1.07
Third quartile of means among attributes of the numeric type.
Maximum mutual information between the nominal attributes and the target attribute.
4
The minimal number of distinct values among attributes of the nominal type.
98.9
Percentage of numeric attributes.
Third quartile of mutual information between the nominal attributes and the target attribute.
4
The maximum number of distinct values among attributes of the nominal type.
-5.87
Minimum skewness among attributes of the numeric type.
1.1
Percentage of nominal attributes.
0.75
Third quartile of skewness among attributes of the numeric type.
6.12
Maximum skewness among attributes of the numeric type.
3.32
Minimum standard deviation of attributes of the numeric type.
First quartile of entropy among attributes.
21.92
Third quartile of standard deviation of attributes of the numeric type.
169.18
Maximum standard deviation of attributes of the numeric type.
6.38
Percentage of instances belonging to the least frequent class.
0.63
First quartile of kurtosis 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.
3
Number of instances belonging to the least frequent class.
-8.1
First quartile of means among attributes of the numeric type.
4.85
Mean kurtosis among attributes of the numeric type.
0
Number of binary attributes.
First quartile of mutual information between the nominal attributes and the target attribute.
8.58
Mean of means among attributes of the numeric type.
-0.46
First quartile of skewness among attributes of the numeric type.
0.7
Average class difference between consecutive instances.
Average mutual information between the nominal attributes and the target attribute.
5.8
First quartile of standard deviation of attributes of the numeric type.
1.76
Entropy of the target attribute values.
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.
1.94
Number of attributes divided by the number of instances.
4
Average number of distinct values among the attributes of the nominal type.
2.89
Second quartile (Median) of kurtosis 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.
0.07
Mean skewness among attributes of the numeric type.
-4.68
Second quartile (Median) of means among attributes of the numeric type.
42.55
Percentage of instances belonging to the most frequent class.
18.98
Mean standard deviation of attributes of the numeric type.
Second quartile (Median) of mutual information between the nominal attributes and the target attribute.
20
Number of instances belonging to the most frequent class.
Minimal entropy among attributes.
0.3
Second quartile (Median) of skewness among attributes of the numeric type.
Maximum entropy among attributes.
-0.8
Minimum kurtosis among attributes of the numeric type.
0
Percentage of binary attributes.
11.37
Second quartile (Median) of standard deviation of attributes of the numeric type.
Third quartile of entropy among attributes.
40.4
Maximum kurtosis among attributes of the numeric type.
-21.13
Minimum of means among attributes of the numeric type.
0
Percentage of instances having missing values.
5.32
Third quartile of kurtosis among attributes of the numeric type.
82.66
Maximum of means among attributes of the numeric type.
Minimal mutual information between the nominal attributes and the target attribute.
0
Percentage of missing values.

5 tasks

40 runs - estimation_procedure: 10-fold Crossvalidation - evaluation_measure: predictive_accuracy - target_feature: Class
31 runs - estimation_procedure: 10-fold Crossvalidation - target_feature: Class
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
Define a new task