Emotion is a crucial aspect of human interaction, helping to understand others’ feelings and guiding how to respond appropriately to the situation. Unfortunately, some patients are unable to perceive emotions, thus challenging their interaction with their relatives and friends. Today, with the current proliferation of technology in human life, data-driven methods can contribute to alleviating emotional disorders by developing modules that automatically predict emotions from sources, such as physiological signals, facial gestures, speech, or text
Predicting emotions in controlled or in-the-wild environments allows finding relationships between human-executive neural responses and clinical, synthetic, and behavioral biomarkers presented in different experimental setups, particularly on individuals diagnosed with multiple neurodevelopmental/emotional disorders. Artificial-Intelligence (AI) systems help toward that goal by providing various techniques to classify and recognize emotions.
This research topic aims to bring together research that focuses on developing data-driven approaches to detect emotions from physiological signals, images, or text. Our goal is to present studies that could potentially develop emotion recognition systems that endow neurodevelopmental/emotional disorder patients with the functionality to respond to emotional states, thus improving their interactions with others. Moreover, we are interested in studies showing how data-driven approaches to detecting emotions can help future clinical interventions or treatments.
The main topics include but are not limited to:
1. Machine learning and artificial intelligence techniques for emotion recognition
2. Emotion Recognition from physiology signals, such as Electroencephalogram (EEG) or Electrocardiogram (ECG)
3. Emotion Recognition from facial expression images
4. Emotion Recognition from body posture images
5. Emotion Recognition from text
6. Emotion Recognition from speech
7. Human-Machine interaction system for emotional disorder patients
8. Signal processing techniques for emotion recognition
Emotion is a crucial aspect of human interaction, helping to understand others’ feelings and guiding how to respond appropriately to the situation. Unfortunately, some patients are unable to perceive emotions, thus challenging their interaction with their relatives and friends. Today, with the current proliferation of technology in human life, data-driven methods can contribute to alleviating emotional disorders by developing modules that automatically predict emotions from sources, such as physiological signals, facial gestures, speech, or text
Predicting emotions in controlled or in-the-wild environments allows finding relationships between human-executive neural responses and clinical, synthetic, and behavioral biomarkers presented in different experimental setups, particularly on individuals diagnosed with multiple neurodevelopmental/emotional disorders. Artificial-Intelligence (AI) systems help toward that goal by providing various techniques to classify and recognize emotions.
This research topic aims to bring together research that focuses on developing data-driven approaches to detect emotions from physiological signals, images, or text. Our goal is to present studies that could potentially develop emotion recognition systems that endow neurodevelopmental/emotional disorder patients with the functionality to respond to emotional states, thus improving their interactions with others. Moreover, we are interested in studies showing how data-driven approaches to detecting emotions can help future clinical interventions or treatments.
The main topics include but are not limited to:
1. Machine learning and artificial intelligence techniques for emotion recognition
2. Emotion Recognition from physiology signals, such as Electroencephalogram (EEG) or Electrocardiogram (ECG)
3. Emotion Recognition from facial expression images
4. Emotion Recognition from body posture images
5. Emotion Recognition from text
6. Emotion Recognition from speech
7. Human-Machine interaction system for emotional disorder patients
8. Signal processing techniques for emotion recognition
