Emotion detection and recognition using HRV features derived from photoplethysmogram signals

Rakshit, Raj; Reddy, V. Ramu; Deshpande, Parijat

doi:10.1145/3009960.3009962

Cited by 44 publications

(14 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, the use of digital health care has proliferated, increasing the need for ambulatory ECG measurements. In addition to clinical uses, studies on ECG use in daily life to manage health, exercise, stress, and emotional well-being have been actively conducted (Taelman et al, 2009 ; Hynynen et al, 2010 ; Kaikkonen et al, 2010 , 2012 ; Choi et al, 2012 ; Valenza et al, 2014 , 2015 ; Guo et al, 2015 ; Hernando et al, 2016 ; Rakshit et al, 2016 ; Verkuil et al, 2016 ; Goessl et al, 2017 ; Lischke et al, 2018 ; May et al, 2018 ; Van Boxtel et al, 2018 ). As the use of ECG increases in ambulatory environments, removing motion artifacts has become more important to properly detect the QRS complex.…”

Section: Introductionmentioning

confidence: 99%

Quantitative Analysis of the Effect of an Ectopic Beat on the Heart Rate Variability in the Resting Condition

Choi

Shin

2018

Front. Physiol.

View full text Add to dashboard Cite

The purpose of this study is to quantitatively analyze the effect of an ectopic beat on heart rate variability (HRV) in the time domain, frequency domain, and in a non-linear analysis. A quantitative analysis was carried out by generating artificial ectopic beats that probabilistically contained a missed beat or a false-detected beat, and the statistical significance was evaluated though a comparison with an ectopic-free HRV by increasing the ratio of the ectopic beat in 0.1% increments from 0 to 50%. The effect of the interpolation on the ectopic HRV was also investigated by applying nearest-neighbor interpolation, linear interpolation, and cubic spline interpolation. The results confirmed a statistically significant difference (P < 0.05) even in the less-than-1% ectopic HRV in every domain. When interpolation was applied, there were differences according to the interpolation method used, but statistical significance was secured for an ectopic beat ratio from 1 to 2% to several tens of a percent. In the effect, linear interpolation, and spline interpolation were confirmed to have a higher effect on the high-frequency related HRV variables, and nearest-neighbor interpolation had a higher effect on low-frequency related variables.

show abstract

Section: Introductionmentioning

confidence: 99%

Quantitative Analysis of the Effect of an Ectopic Beat on the Heart Rate Variability in the Resting Condition

Choi

Shin

2018

Front. Physiol.

View full text Add to dashboard Cite

show abstract

“…The Emotion API is one of the pieces of research on emotion detection that can identify a person's emotional state from images and videos [25]. There has been some research to classify emotion using Heart Rate Variability (HRV) features [26]. The HRV features deal with multiple signals that a patient produces in order to extract the emotional state.…”

Section: The State-of-artmentioning

confidence: 99%

iHealthcare: Predictive Model Analysis Concerning Big Data Applications for Interactive Healthcare Systems †

2019

View full text Add to dashboard Cite

Recently, the healthcare industry has caught the attention of researchers due to a need to develop a smart and interactive system for effective and efficient treatment facilities. The healthcare system consists of massive biological data (unstructured or semi-structured) which needs to be analyzed and processed for early disease detection. In this paper, we have designed a piece of healthcare technology which can deal with a patient’s past and present medical data including symptoms of a disease, emotional data, and genetic data. We have designed a probabilistic data acquisition scheme to analyze the medical data. This model contains a data warehouse with a two-way interaction between high-performance computing and cloud synchronization. Finally, we present a prediction scheme that is performed in the cloud server to predict disease in a patient. To complete this task, we used Random Forest, Support Vector Machine (SVM), C5.0, Naive Bayes, and Artificial Neural Networks for prediction analysis, and made a comparison between these algorithms.

show abstract

“…The study of emotion has been developed in recent years in the field of computer science, psychology, cognitive neuroscience, and affective computing [1]. With the increasing popularity of AI applications, some studies for affective computing have been published using shallow models or deep learning models, as in [2] [3]. To quantize the intensity of the emotion, the circumplex model separating the emotion into two-dimensional axes that are valence and arousal [4] is well adapted.…”

Section: Introductionmentioning

confidence: 99%

Real-Time EEG-Based Affective Computing Using On-Chip Learning Long-Term Recurrent Convolutional Network

Yang

Wan

et al. 2021

2021 IEEE International Symposium on Circuits and Systems (ISCAS)

View full text Add to dashboard Cite

In this paper, we presented an affective computing engine using the Long-term Recurrent Convolutional Network (LRCN) on electroencephalogram (EEG) physiological signal with 8 emotion-related channels. LRCN was chosen as the emotional classifier because compared to the traditional CNN, it integrates memory units allowing the network to discard or update previous hidden states which are particularly adapted to explore the temporal emotional information in the EEG sequence data. To achieve a real-time AI-edge affective computing system, the LRCN model was implemented on a 16nm Fin-FET technology chip. The core area and total power consumption of the LRCN chip are respectively 1.13x1.14 mm 2 and 48.24 mW. The computation time was 1.9µs and met the requirements to inference every sample. The training process cost 5.5µs per sample on clock frequency 125Hz which was more than 20 times faster than 128µs achieved with GeForce GTX 1080 Ti using python. The proposed model was evaluated on 52 subjects with cross-subject validation and achieved average accuracy of 88.34%, and 75.92% for respectively 2-class, 3-class.

show abstract

Emotion detection and recognition using HRV features derived from photoplethysmogram signals

Cited by 44 publications

References 25 publications

Quantitative Analysis of the Effect of an Ectopic Beat on the Heart Rate Variability in the Resting Condition

Quantitative Analysis of the Effect of an Ectopic Beat on the Heart Rate Variability in the Resting Condition

iHealthcare: Predictive Model Analysis Concerning Big Data Applications for Interactive Healthcare Systems †

Real-Time EEG-Based Affective Computing Using On-Chip Learning Long-Term Recurrent Convolutional Network

Contact Info

Product

Resources

About