Recognition of Negative Emotion Using Long Short-Term Memory with Bio-Signal Feature Compression
Negative emotion is one reason why stress causes negative feedback. Therefore, many studies are being done to recognize negative emotions. However, emotion is difficult to classify because it is subjective and difficult to quantify. Moreover, emotion changes over time and is affected by mood. Theref...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/2/573 |
| _version_ | 1798038992838459392 |
|---|---|
| author | JeeEun Lee Sun K. Yoo |
| author_facet | JeeEun Lee Sun K. Yoo |
| author_sort | JeeEun Lee |
| collection | DOAJ |
| description | Negative emotion is one reason why stress causes negative feedback. Therefore, many studies are being done to recognize negative emotions. However, emotion is difficult to classify because it is subjective and difficult to quantify. Moreover, emotion changes over time and is affected by mood. Therefore, we measured electrocardiogram (ECG), skin temperature (ST), and galvanic skin response (GSR) to detect objective indicators. We also compressed the features associated with emotion using a stacked auto-encoder (SAE). Finally, the compressed features and time information were used in training through long short-term memory (LSTM). As a result, the proposed LSTM used with the feature compression model showed the highest accuracy (99.4%) for recognizing negative emotions. The results of the suggested model were 11.3% higher than with a neural network (NN) and 5.6% higher than with SAE. |
| first_indexed | 2024-04-11T21:47:47Z |
| format | Article |
| id | doaj.art-65071f0ce7284dd98b5e38117e70f4ae |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T21:47:47Z |
| publishDate | 2020-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-65071f0ce7284dd98b5e38117e70f4ae2022-12-22T04:01:21ZengMDPI AGSensors1424-82202020-01-0120257310.3390/s20020573s20020573Recognition of Negative Emotion Using Long Short-Term Memory with Bio-Signal Feature CompressionJeeEun Lee0Sun K. Yoo1Graduate Program of Biomedical Engineering, Yonsei University, Seoul 03722, KoreaDepartment of Medical Engineering, Yonsei University College of Medicine, Seoul 03722, KoreaNegative emotion is one reason why stress causes negative feedback. Therefore, many studies are being done to recognize negative emotions. However, emotion is difficult to classify because it is subjective and difficult to quantify. Moreover, emotion changes over time and is affected by mood. Therefore, we measured electrocardiogram (ECG), skin temperature (ST), and galvanic skin response (GSR) to detect objective indicators. We also compressed the features associated with emotion using a stacked auto-encoder (SAE). Finally, the compressed features and time information were used in training through long short-term memory (LSTM). As a result, the proposed LSTM used with the feature compression model showed the highest accuracy (99.4%) for recognizing negative emotions. The results of the suggested model were 11.3% higher than with a neural network (NN) and 5.6% higher than with SAE.https://www.mdpi.com/1424-8220/20/2/573emotionbio-signalauto-encoderlstm |
| spellingShingle | JeeEun Lee Sun K. Yoo Recognition of Negative Emotion Using Long Short-Term Memory with Bio-Signal Feature Compression Sensors emotion bio-signal auto-encoder lstm |
| title | Recognition of Negative Emotion Using Long Short-Term Memory with Bio-Signal Feature Compression |
| title_full | Recognition of Negative Emotion Using Long Short-Term Memory with Bio-Signal Feature Compression |
| title_fullStr | Recognition of Negative Emotion Using Long Short-Term Memory with Bio-Signal Feature Compression |
| title_full_unstemmed | Recognition of Negative Emotion Using Long Short-Term Memory with Bio-Signal Feature Compression |
| title_short | Recognition of Negative Emotion Using Long Short-Term Memory with Bio-Signal Feature Compression |
| title_sort | recognition of negative emotion using long short term memory with bio signal feature compression |
| topic | emotion bio-signal auto-encoder lstm |
| url | https://www.mdpi.com/1424-8220/20/2/573 |
| work_keys_str_mv | AT jeeeunlee recognitionofnegativeemotionusinglongshorttermmemorywithbiosignalfeaturecompression AT sunkyoo recognitionofnegativeemotionusinglongshorttermmemorywithbiosignalfeaturecompression |