Data
FEER-Dataset

FEER-Dataset

active ARFF CC BY-NC-SA 4.0 Visibility: public Uploaded 24-03-2022 by Dustin Carrion
0 likes downloaded by 0 people , 0 total downloads 0 issues 0 downvotes
  • Computer Systems Machine Learning
Issue #Downvotes for this reason By


Loading wiki
Help us complete this description Edit
Content This database contains six basic emotions (happiness, surprise, anger, fear, disgust, and sadness) of normalized (average mean reference) data and collected from 85 undergraduate university students (55 male; 30 female) aged between 20 - 27 years with a mean age of 24.5 years. The data which contain noises and other movement artifacts are removed from the raw data. A built-in face time HD camera in Apple Mac Pro with a resolution of 2560 1600 at 227 pixels per inch is used to collect the facial images in a controlled environment (25C room temperature with 50 Lux lighting intensity) at 30 frames per second. All the subjects are seated comfortably in a chair in front of the camera and the distance between the subject face to the camera is 0.95m. A computerized PowerPoint slides are used to instruct the subjects to express the facial emotional expression by looking into the International Affective Picture System (IAPS) images of six different emotions. The data file contains 11 columns (10 columns for 10 markers and the last column represents the label of emotion) and 190968 rows. In the file (labels), 0 refers to Angry, 1 refers to Disgust, 2 refers to Fear, 3 refers to Sad, 4 refers to Happy, and 5 refer to S to Surprise. Each emotion has 10 trials and each trial has a duration of 6 sec. In between the emotional expressions, 10 sec of break is given to the subjects to feel calm by showing natural scenes. The PowerPoint show starts with a set of instructions at the beginning of the experiment of 10-sec duration. The computing system continuously records the marker positions and saved them in comma-separated values (CSV) format for further processing. More information about the reproduction of data analysis could be found from the below citations. Citations All documents and papers that report on research that uses the FEER Dataset must acknowledge the use of the database by including a citation M Murugappan, Vasanthan Maruthapillai, Wan Khairunizam, A M Muttawa, Sai Sruthi, Wen Yean, Virtual Markers based Facial Emotion Recognition using ELM and PNN Classifiers, 16th IEEE Colloquium on Signal Processing, (CSPA), pp, 261-265, 2020. Vasanthan, M Murugappan, Optimal Geometrical Set for Automated Marker Placement to Virtualized Real-Time Facial Emotions, PlosOne, 11(2), Feb 2016. DOI: 10.1371/journal.pone.0149003.

11 features

P_e1numeric68714 unique values
0 missing
P_e2numeric65130 unique values
0 missing
P_e3numeric71651 unique values
0 missing
P_e4numeric70581 unique values
0 missing
P_m1numeric73563 unique values
0 missing
P_m2numeric73794 unique values
0 missing
P_m3numeric61376 unique values
0 missing
P_m4numeric71881 unique values
0 missing
Pm6numeric72964 unique values
0 missing
P_m7numeric74456 unique values
0 missing
emotionnumeric6 unique values
0 missing

19 properties

190967
Number of instances (rows) of the dataset.
11
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.
11
Number of numeric attributes.
0
Number of nominal attributes.
0
Number of attributes divided by the number of instances.
100
Percentage of numeric attributes.
Percentage of instances belonging to the most frequent class.
0
Percentage of nominal attributes.
Number of instances belonging to the most frequent class.
Percentage of instances belonging to the least frequent class.
Number of instances belonging to the least frequent class.
0
Number of binary attributes.
0
Percentage of binary attributes.
0
Percentage of instances having missing values.
Average class difference between consecutive instances.
0
Percentage of missing values.

0 tasks

Define a new task