Proposed EEG/Speech-Based Emotion Recognition System

Abhang, Priyanka A.; Gawali, Bharti W.; Mehrotra, S. C.

doi:10.1016/b978-0-12-804490-2.00007-5

Cited by 63 publications

(34 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researches showed that the changes in the ratio of alpha, beta, and theta oscillations are the AD markers, so we extracted the data of these brain oscillations. On the other hand, we did not consider the gamma and delta oscillations, because the delta and gamma oscillations are activated during sleep and cognitive learning activities, respectively (Abhang et al, 2016 ). The resting alpha and beta oscillation indicate relaxed and alert wakefulness (Abhang et al, 2016 ), and the theta/alpha ratio is indicative of cognitive deficits (Fahimi et al, 2017 ).…”

Section: Discussionmentioning

confidence: 99%

“…On the other hand, we did not consider the gamma and delta oscillations, because the delta and gamma oscillations are activated during sleep and cognitive learning activities, respectively (Abhang et al, 2016 ). The resting alpha and beta oscillation indicate relaxed and alert wakefulness (Abhang et al, 2016 ), and the theta/alpha ratio is indicative of cognitive deficits (Fahimi et al, 2017 ). Decreased alpha oscillation power has been reported in AD (Hsiao et al, 2013 ; Koelewijn et al, 2017 ), which is associated with an increase in the theta/alpha ratio.…”

Section: Discussionmentioning

confidence: 99%

“…Although the exact mechanisms of change in the brain oscillation ratio due to exercise training are unknown in AD, the alpha oscillation power seems to be correlated with higher cerebral blood flow in the brain areas, involved in attentional modulation (Jann et al, 2010 ). Alpha oscillations are generated mainly in the occipital and parietal lobes, as well as thalamocortical feedback loops, whereas beta oscillations mainly originate from the frontal and temporal lobes (Abhang et al, 2016 ). The eye-closing part of our training protocol forced the individuals to focus on the auditory and proprioceptive data, originating from beta and alpha oscillation.…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Dual-Task Training Affect Cognitive and Physical Performances and Brain Oscillation Ratio of Patients With Alzheimer’s Disease: A Randomized Controlled Trial

Parvin

Mohammadian

Amani-Shalamzari

et al. 2020

Front. Aging Neurosci.

View full text Add to dashboard Cite

This study aimed to investigate the effect of 12 weeks of dual-task training on cognitive status, physical performance, and brain oscillation of patients with Alzheimer’s disease (AD). Twenty-six AD patients were randomly assigned to two groups, the training group (TG) and control group (CG). TG executed progressive combined exercises with visual stimulation twice a week for 12 weeks. Training included muscle endurance, balance, flexibility, and aerobic exercises with eyes closed and opened. Brain oscillation on electroencephalography (EEG) and a series of physical, cognitive, and mental tests were taken before and post-intervention. There was a significant improvement after training protocol in cognitive function, particularly in short-term and working memory, attention, and executive function (p < 0.01). Besides, there were substantial improvements in depression status (GDS scale), aerobic fitness (6 min walking), flexibility (chair sit and reach) functional ability (chair stand, timed up and go test), strength (knee extensions, preacher biceps curl, handgrip) in TG compared to CG. These signs of progress were associated with a significant increase (p < 0.05) in the frequency of brain oscillation and a decrease in the theta/alpha ratio. In addition to physical performance, the regular combined training with visual stimulation improves brain health as indicated by improving cognitive function and reducing the theta/alpha ratio.Clinical Trial Registration: Iranian Registry of Clinical Trials (IRCT) https://www.irct.ir/, identifier IRCT20190504043468N1—August 5, 2020.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Dual-Task Training Affect Cognitive and Physical Performances and Brain Oscillation Ratio of Patients With Alzheimer’s Disease: A Randomized Controlled Trial

Parvin

Mohammadian

Amani-Shalamzari

et al. 2020

Front. Aging Neurosci.

View full text Add to dashboard Cite

show abstract

“…As shown in Figure 1, a SER system generally consists of three modules: speech acquisition module, feature extraction module and emotion recognition module [32]. Natural speech is imported into the system through the sensors in the speech acquisition module, and then transmitted to the feature extraction module to extract the emotional features.…”

Section: Introductionmentioning

confidence: 99%

Recognize basic emotional statesin speech by machine learning techniques using mel-frequency cepstral coefficient features

Yang

Dey

Sherratt

et al. 2020

IFS

View full text Add to dashboard Cite

AI based Speech Recognition has been widely used in the consumer field for control of smart home personal assistants, with many such devices on the market. Smart home assistants that could detect the user's emotion would improve the communication between a user and the assistant enabling the assistant to offer more productive feedback. Thus, the aim of this work is to analyze emotional states in speech and propose a suitable algorithm considering performance verses complexity for deployment in smart home devices. The four emotional speeches were selected from the Berlin Emotional Database (EMO-DB) as experimental data, 26 MFCC features were extracted from each type of emotional speech to identify the emotions of happiness, anger, sadness and neutrality. Then, speaker-independent experiments for our Speech emotion Recognition (SER) were conducted by using the Back Propagation Neural Network (BPNN), Extreme Learning Machine (ELM), Probabilistic Neural Network (PNN) and Support Vector Machine (SVM). Synthesizing the recognition accuracy and processing time, this work shows that the performance of SVM was the best among the four methods as a good candidate to be deployed for SER in smart home devices. SVM achieved an overall accuracy of 92.4% while offering low computational requirements when training and testing. We conclude that the MFCC features and the SVM classification models used in speaker-independent experiments are highly effective in the automatic prediction of emotion.

show abstract

“…The activity inherent in the brain can be observed in its different parts, and the sign of emotion correlates with a certain hemisphere of the brain (Killgore and Yurgelun-Todd, 2007;Abhang, Gawali and Mehrotra, 2016).…”

Section: Introductionmentioning

confidence: 99%

Results of recording electrophysiological signals by nanosensors during tests on volunteers

Avdeeva

Guo

Nguyen

et al. 2020

View full text Add to dashboard Cite

Purpose The purpose of this paper is to analyze the results of recording electrophysiological signals by nanosensors during tests on volunteers using neutral questions and questions that cause excitement. Design/methodology/approach The nanosensor-based hardware and software complex (HSC) was used for simultaneous recording of electrocardiogram, electroencephalogram and galvanic skin response during tests on volunteers using neutral questions and questions that cause excitement. The recording was carried out in real time without averaging and filtering in the extended frequency range from 0 to 10,000 Hz, level of more than 1 µV and sampling frequency equal to 64 kHz. Findings For the first time, the following signals were recorded by nanosensors without filtering and averaging in the measuring channels: real-time micropotentials on an electrocardiogram with a duration of 0.2 ms and a level of 1 µV or more. Also, for the first time, changes in the shape and amplitude of the P wave, slow waves on the electroencephalography (EEG), high impulse activity of the EEG and impulse activity of short duration on the GSR were recorded in response to questions that cause excitement. Practical implications The obtained results will be used for high-resolution equipment to develop additional measuring channels in existing types of equipment for psychophysiological studies. Originality/value For the first time, new data undistorted by filters was obtained on the amplitude and time parameters of electrophysiological signals in the frequency range from 0 to 10,000 Hz in response to questions that cause excitement, which was due to high sensitivity and noise immunity of nanosensors in comparison with existing electrodes for biopotential recording.

show abstract

Proposed EEG/Speech-Based Emotion Recognition System

Cited by 63 publications

References 1 publication

Dual-Task Training Affect Cognitive and Physical Performances and Brain Oscillation Ratio of Patients With Alzheimer’s Disease: A Randomized Controlled Trial

Dual-Task Training Affect Cognitive and Physical Performances and Brain Oscillation Ratio of Patients With Alzheimer’s Disease: A Randomized Controlled Trial

Recognize basic emotional statesin speech by machine learning techniques using mel-frequency cepstral coefficient features

Results of recording electrophysiological signals by nanosensors during tests on volunteers

Contact Info

Product

Resources

About