Data
ParkinsonSpeechDatasetwithMultipleTypesofSoundRecordings

ParkinsonSpeechDatasetwithMultipleTypesofSoundRecordings

active ARFF Publicly available Visibility: public Uploaded 17-02-2016 by Hilda Fabiola Bernard
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
Source: 1. Olcay KURSUN, PhD., Istanbul University, Department of Computer Engineering, 34320, Istanbul, Turkey Phone: +90 (212) 473 7070 - 17827 Email: okursun '@' istanbul.edu.tr 2. Betul ERDOGDU SAKAR, PhD., Bahcesehir University, Department of Software Engineering, 34381, Istanbul, Turkey Phone: +90 (212) 381 0589 Email: betul.erdogdu '@' eng.bahcesehir.edu.tr 3. M. Erdem ISENKUL, M.S., Istanbul University, Department of Computer Engineering, 34320, Istanbul, Turkey Email: eisenkul '@' istanbul.edu.tr 4. C. Okan SAKAR, PhD., Bahcesehir University, Department of Computer Engineering, 34381, Istanbul, Turkey Phone: +90 (212) 381 0571 Email: okan.sakar '@' eng.bahcesehir.edu.tr 5. Ahmet SERTBAS, PhD, Istanbul University, Department of Computer Engineering, 34320, Istanbul, Turkey Email: asertbas '@' istanbul.edu.tr 6. Fikret GURGEN, PhD., Bogazici University, Department of Computer Engineering, 34342, Istanbul, Turkey Email: gurgen '@' boun.edu.tr 7. Sakir DELIL, M.D., PhD., Istanbul University, Cerrahpaşa Faculty of Medicine, Department of Neurology, 34098, Istanbul, Turkey Email: sakir.delil '@' ctf.edu.tr 8. Hulya APAYDIN, M.D., PhD., Istanbul University, Cerrahpaşa Faculty of Medicine, Department of Neurology, 34098, Istanbul, Turkey Email: hulya.apaydin '@' ctf.edu.tr Donor: C. Okan SAKAR, PhD., Bahcesehir University, Department of Computer Engineering, 34381, Istanbul, Turkey Phone: +90 (212) 381 0571 Email: okan.sakar '@' eng.bahcesehir.edu.tr Data Set Information: The PD database consists of training and test files. The training data belongs to 20 PWP (6 female, 14 male) and 20 healthy individuals (10 female, 10 male) who appealed at the Department of Neurology in Cerrahpasa Faculty of Medicine, Istanbul University. From all subjects, multiple types of sound recordings (26 voice samples including sustained vowels, numbers, words and short sentences) are taken. A group of 26 linear and time–frequency based features are extracted from each voice sample. UPDRS ((Unified Parkinson’s Disease Rating Scale) score of each patient which is determined by expert physician is also available in this dataset. Therefore, this dataset can also be used for regression. After collecting the training dataset which consists of multiple types of sound recordings and performing our experiments, in line with the obtained findings we continued collecting an independent test set from PWP via the same physician’s examination process under the same conditions. During the collection of this dataset, 28 PD patients are asked to say only the sustained vowels 'a' and 'o' three times respectively which makes a total of 168 recordings. The same 26 features are extracted from voice samples of this dataset. This dataset can be used as an independent test set to validate the results obtained on training set. Further details are contained in the following reference -- if you use this dataset, please cite: Erdogdu Sakar, B., Isenkul, M., Sakar, C.O., Sertbas, A., Gurgen, F., Delil, S., Apaydin, H., Kursun, O., 'Collection and Analysis of a Parkinson Speech Dataset with Multiple Types of Sound Recordings', IEEE Journal of Biomedical and Health Informatics, vol. 17(4), pp. 828-834, 2013 Training Data File: Each subject has 26 voice samples including sustained vowels, numbers, words and short sentences. The voice samples in the training data file are given in the following order: sample# - corresponding voice samples 1: sustained vowel (aaa……) 2: sustained vowel (ooo…...) 3: sustained vowel (uuu…...) 4-13: numbers from 1 to 10 14-17: short sentences 18-26: words Test Data File: 28 PD patients are asked to say only the sustained vowels 'a' and 'o' three times respectively which makes a total of 168 recordings (each subject has 6 voice samples) The voice samples in the test data file are given in the following order: sample# - corresponding voice samples 1-3: sustained vowel (aaa……) 4-6: sustained vowel (ooo……) Attribute Information: Training Data File: column 1: Subject id colum 2-27: features features 1-5: Jitter (local),Jitter (local, absolute),Jitter (rap),Jitter (ppq5),Jitter (ddp), features 6-11: Shimmer (local),Shimmer (local, dB),Shimmer (apq3),Shimmer (apq5), Shimmer (apq11),Shimmer (dda), features 12-14: AC,NTH,HTN, features 15-19: Median pitch,Mean pitch,Standard deviation,Minimum pitch,Maximum pitch, features 20-23: Number of pulses,Number of periods,Mean period,Standard deviation of period, features 24-26: Fraction of locally unvoiced frames,Number of voice breaks,Degree of voice breaks column 28: UPDRS column 29: class information Test Data File: column 1: Subject id colum 2-27: features features 1-5: Jitter (local),Jitter (local, absolute),Jitter (rap),Jitter (ppq5),Jitter (ddp), features 6-11: Shimmer (local),Shimmer (local, dB),Shimmer (apq3),Shimmer (apq5), Shimmer (apq11),Shimmer (dda), features 12-14: AC,NTH,HTN, features 15-19: Median pitch,Mean pitch,Standard deviation,Minimum pitch,Maximum pitch, features 20-23: Number of pulses,Number of periods,Mean period,Standard deviation of period, features 24-26: Fraction of locally unvoiced frames,Number of voice breaks,Degree of voice breaks column 28: class information Relevant Papers: Erdogdu Sakar, B., Isenkul, M., Sakar, C.O., Sertbas, A., Gurgen, F., Delil, S., Apaydin, H., Kursun, O., 'Collection and Analysis of a Parkinson Speech Dataset with Multiple Types of Sound Recordings', IEEE Journal of Biomedical and Health Informatics, vol. 17(4), pp. 828-834, 2013. Isenkul, M.E., Erdoğdu, B., Sakar, C.O., Gümüs, E., Delil, M.S., Gürgen, F., Sertbas, A., Kursun, O., Parkinson Hastalığının Ses Disfonilerinden Teşhisi için bir Ses Veritabanı Olusturulması ve Örüntülerinin Kullanımı, 16. Biyomedikal Mühendisliği Ulusal Toplantısı (BİYOMUT 2011), Antalya, Turkey, October, 2011. Citation Request: Please cite the following paper if you use this dataset: Erdogdu Sakar, B., Isenkul, M., Sakar, C.O., Sertbas, A., Gurgen, F., Delil, S., Apaydin, H., Kursun, O., 'Collection and Analysis of a Parkinson Speech Dataset with Multiple Types of Sound Recordings', IEEE Journal of Biomedical and Health Informatics, vol. 17(4), pp. 828-834, 2013.

29 features

X1numeric40 unique values
0 missing
X1.488numeric943 unique values
0 missing
X0.000090213numeric1036 unique values
0 missing
X0.9numeric838 unique values
0 missing
X0.794numeric873 unique values
0 missing
X2.699numeric960 unique values
0 missing
X8.334numeric1006 unique values
0 missing
X0.779numeric722 unique values
0 missing
X4.517numeric979 unique values
0 missing
X4.609numeric979 unique values
0 missing
X6.802numeric943 unique values
0 missing
X13.551numeric1017 unique values
0 missing
X0.905905numeric1038 unique values
0 missing
X0.119116numeric1034 unique values
0 missing
X11.13numeric992 unique values
0 missing
X166.533numeric1037 unique values
0 missing
X164.781numeric1036 unique values
0 missing
X10.421numeric1028 unique values
0 missing
X142.229numeric1036 unique values
0 missing
X187.576numeric1037 unique values
0 missing
X160numeric274 unique values
0 missing
X159numeric270 unique values
0 missing
X0.006064725numeric1039 unique values
0 missing
X0.000416276numeric1038 unique values
0 missing
X0numeric669 unique values
0 missing
X0.1numeric13 unique values
0 missing
X0.2numeric594 unique values
0 missing
X23numeric15 unique values
0 missing
X1.1numeric2 unique values
0 missing

107 properties

1039
Number of instances (rows) of the dataset.
29
Number of attributes (columns) of the dataset.
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.
29
Number of numeric attributes.
0
Number of nominal attributes.
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.RandomTree -depth 1
0.03
Number of attributes divided by the number of instances.
Maximum mutual information between the nominal attributes and the target attribute.
The minimal number of distinct values among attributes of the nominal type.
0
Percentage of binary attributes.
4.84
Second quartile (Median) of standard deviation of attributes of the numeric type.
Error rate achieved by the landmarker weka.classifiers.trees.RandomTree -depth 1
Number of attributes needed to optimally describe the class (under the assumption of independence among attributes). Equals ClassEntropy divided by MeanMutualInformation.
The maximum number of distinct values among attributes of the nominal type.
-0.86
Minimum skewness among attributes of the numeric type.
0
Percentage of instances having missing values.
Third quartile of entropy among attributes.
Kappa coefficient achieved by the landmarker weka.classifiers.trees.RandomTree -depth 1
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.J48 -C .00001
4.9
Maximum skewness among attributes of the numeric type.
0
Minimum standard deviation of attributes of the numeric type.
0
Percentage of missing values.
9.06
Third quartile of kurtosis among attributes of the numeric type.
Average class difference between consecutive instances.
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.RandomTree -depth 2
Error rate achieved by the landmarker weka.classifiers.trees.J48 -C .00001
150.09
Maximum standard deviation of attributes of the numeric type.
Percentage of instances belonging to the least frequent class.
100
Percentage of numeric attributes.
27.64
Third quartile of means among attributes of the numeric type.
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.DecisionStump -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W
Error rate achieved by the landmarker weka.classifiers.trees.RandomTree -depth 2
Kappa coefficient achieved by the landmarker weka.classifiers.trees.J48 -C .00001
Average entropy of the attributes.
Number of instances belonging to the least frequent class.
0
Percentage of nominal attributes.
Third quartile of mutual information between the nominal attributes and the target attribute.
Error rate achieved by the landmarker weka.classifiers.trees.DecisionStump -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W
Kappa coefficient achieved by the landmarker weka.classifiers.trees.RandomTree -depth 2
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.J48 -C .0001
7.37
Mean kurtosis among attributes of the numeric type.
Area Under the ROC Curve achieved by the landmarker weka.classifiers.bayes.NaiveBayes
First quartile of entropy among attributes.
2.51
Third quartile of skewness among attributes of the numeric type.
Kappa coefficient achieved by the landmarker weka.classifiers.trees.DecisionStump -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.RandomTree -depth 3
Error rate achieved by the landmarker weka.classifiers.trees.J48 -C .0001
37.83
Mean of means among attributes of the numeric type.
Error rate achieved by the landmarker weka.classifiers.bayes.NaiveBayes
0.67
First quartile of kurtosis among attributes of the numeric type.
28.83
Third quartile of standard deviation of attributes of the numeric type.
Area Under the ROC Curve achieved by the landmarker weka.classifiers.bayes.NaiveBayes -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W
Error rate achieved by the landmarker weka.classifiers.trees.RandomTree -depth 3
Kappa coefficient achieved by the landmarker weka.classifiers.trees.J48 -C .0001
Average mutual information between the nominal attributes and the target attribute.
Kappa coefficient achieved by the landmarker weka.classifiers.bayes.NaiveBayes
1.17
First quartile of means among attributes of the numeric type.
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.REPTree -L 1
Error rate achieved by the landmarker weka.classifiers.bayes.NaiveBayes -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W
Kappa coefficient achieved by the landmarker weka.classifiers.bayes.NaiveBayes -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W
Kappa coefficient achieved by the landmarker weka.classifiers.trees.RandomTree -depth 3
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.J48 -C .001
An estimate of the amount of irrelevant information in the attributes regarding the class. Equals (MeanAttributeEntropy - MeanMutualInformation) divided by MeanMutualInformation.
0
Number of binary attributes.
First quartile of mutual information between the nominal attributes and the target attribute.
Error rate achieved by the landmarker weka.classifiers.trees.REPTree -L 1
Area Under the ROC Curve achieved by the landmarker weka.classifiers.lazy.IBk -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W
Standard deviation of the number of distinct values among attributes of the nominal type.
Error rate achieved by the landmarker weka.classifiers.trees.J48 -C .001
Average number of distinct values among the attributes of the nominal type.
0.95
First quartile of skewness among attributes of the numeric type.
Kappa coefficient achieved by the landmarker weka.classifiers.trees.REPTree -L 1
Error rate achieved by the landmarker weka.classifiers.lazy.IBk -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W
Area Under the ROC Curve achieved by the landmarker weka.classifiers.lazy.IBk
Kappa coefficient achieved by the landmarker weka.classifiers.trees.J48 -C .001
1.72
Mean skewness among attributes of the numeric type.
0.74
First quartile of standard deviation of attributes of the numeric type.
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.REPTree -L 2
Kappa coefficient achieved by the landmarker weka.classifiers.lazy.IBk -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W
Error rate achieved by the landmarker weka.classifiers.lazy.IBk
Percentage of instances belonging to the most frequent class.
24.92
Mean standard deviation of attributes of the numeric type.
Second quartile (Median) of entropy among attributes.
Error rate achieved by the landmarker weka.classifiers.trees.REPTree -L 2
Kappa coefficient achieved by the landmarker weka.classifiers.trees.REPTree -L 2
Entropy of the target attribute values.
Kappa coefficient achieved by the landmarker weka.classifiers.lazy.IBk
Number of instances belonging to the most frequent class.
Minimal entropy among attributes.
3.6
Second quartile (Median) of kurtosis among attributes of the numeric type.
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.REPTree -L 3
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.DecisionStump
Maximum entropy among attributes.
-2
Minimum kurtosis among attributes of the numeric type.
10
Second quartile (Median) of means among attributes of the numeric type.
Error rate achieved by the landmarker weka.classifiers.trees.REPTree -L 3
Error rate achieved by the landmarker weka.classifiers.trees.DecisionStump
35.8
Maximum kurtosis among attributes of the numeric type.
0
Minimum of means among attributes of the numeric type.
Second quartile (Median) of mutual information between the nominal attributes and the target attribute.
Kappa coefficient achieved by the landmarker weka.classifiers.trees.REPTree -L 3
Kappa coefficient achieved by the landmarker weka.classifiers.trees.DecisionStump
234.92
Maximum of means among attributes of the numeric type.
Minimal mutual information between the nominal attributes and the target attribute.
1.43
Second quartile (Median) of skewness among attributes of the numeric type.

11 tasks

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
0 runs - estimation_procedure: 50 times Clustering
Define a new task