Feature selection for stress level classification into a physiologycal signals set

Jimenez-Limas, Marco A.; Ramirez-Fuentes, Carlos A.; Tovar-Corona, Blanca; Jiménez, Laura Ivoone Garay

doi:10.1109/iceee.2018.8533968

Cited by 8 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is worth noting that the authors analyzed their own collected dataset, which differs from the dataset (i.e., SRAD) used in our experiments. Jiménez-Limas et al [ 30 ] detected two driver stress classes using logistic regression and 5-min FGSR and HR signals and respiration rate. As drivers’ conditions should be detected as quickly as possible to prevent potential accidents, long signals (over 100 s) are not very helpful in detecting drivers’ stress early in actual situations.…”

Section: Resultsmentioning

confidence: 99%

“…In stress recognition studies, feature extraction has been performed mainly in the time or frequency domain of physiological signals. Time domain features were typically extracted from time series segments truncated by window sliding strategies [2,6,[23][24][25][26][27][28], whereas frequency domain features were extracted from low-and/or high-frequency regions [6,[25][26][27]29,30]. Based on these features, statistical measures such as mean, standard deviation, skewness and kurtosis were commonly calculated and used to differentiate between stressed and non-stressed conditions [24].…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, in driving situations, short-term monitoring is essential to driving safety. However, many previous studies on stress detection used relatively long-term physiological signals, typically several minutes long [ 30 , 37 ]. In some recent studies [ 14 , 26 , 38 ], short-term ECG signals were often used which have high sampling frequency and correlation with stress conditions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Driving Stress Detection Using Multimodal Convolutional Neural Networks with Nonlinear Representation of Short-Term Physiological Signals

Lee

Shin

2021

Sensors

View full text Add to dashboard Cite

Mental stress can lead to traffic accidents by reducing a driver’s concentration or increasing fatigue while driving. In recent years, demand for methods to detect drivers’ stress in advance to prevent dangerous situations increased. Thus, we propose a novel method for detecting driving stress using nonlinear representations of short-term (30 s or less) physiological signals for multimodal convolutional neural networks (CNNs). Specifically, from hand/foot galvanic skin response (HGSR, FGSR) and heart rate (HR) short-term input signals, first, we generate corresponding two-dimensional nonlinear representations called continuous recurrence plots (Cont-RPs). Second, from the Cont-RPs, we use multimodal CNNs to automatically extract FGSR, HGSR, and HR signal representative features that can effectively differentiate between stressed and relaxed states. Lastly, we concatenate the three extracted features into one integrated representation vector, which we feed to a fully connected layer to perform classification. For the evaluation, we use a public stress dataset collected from actual driving environments. Experimental results show that the proposed method demonstrates superior performance for 30-s signals, with an overall accuracy of 95.67%, an approximately 2.5–3% improvement compared with that of previous works. Additionally, for 10-s signals, the proposed method achieves 92.33% classification accuracy, which is similar to or better than the performance of other methods using long-term signals (over 100 s).

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Driving Stress Detection Using Multimodal Convolutional Neural Networks with Nonlinear Representation of Short-Term Physiological Signals

Lee

Shin

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Using the Global System for Mobile Communications (GSM) and the Global Positioning System, temperatures were captured and analyzed at a remote location (GPS). Whereas other investigations used the physionet database to get the datasets of ECG signal, GSR, and respiration rate [8][9] [10]. In the work referred to as [11], a new noninvasive electroencephalogram (EEG) measure for detecting stress was devised.…”

Section: Related Work a Stress And Its Detectionmentioning

confidence: 99%

An Intelligent System for Detection of Mental Stress Using Machine Learning

2020

Journal of Algebraic Statistics

View full text Add to dashboard Cite

Tens of millions of people experience depression each year, yet only a small percentage of them receive timely, effective therapy. So, it is essential to timely identify human tension and relaxation through social media. It is crucial to identify and control stress before it becomes a serious issue. Daily posts to blogs, discussion forums, and social networking sites total in millions of casual communications. This essay outlines a method for identifying stress using data from social media networking sites like Twitter. Using sentiment analysis to uncover emotions or feelings about daily life, this research proposes a method to find expressions of tension and relaxation in tweeter datasets. Sentiment analysis automatically extracts information about sentiment from text. Here, sentiment strength from the informal English language is extracted using the TensiStrength framework for sentiment strength identification on social networking sites. TensiStrength is a technology that analyzes social media text messages to identify the levels of tension and relaxation that are being conveyed. With the purpose of identifying both overt and covert signs of tension or relaxation, TensiStrength employs a linguistic approach and a set of rules. According to the strength scale from -5 to +5, this categorizes both pleasant and negative emotions. Stressed and relaxed sentences from the dialogue are both taken into consideration. TensiStrength is a robust system that may be used in a number of social media scenarios. TensiStrength's efficacy is based on the content of the tweets. Humans have the innate capacity to distinguish between the various meanings of a word in a specific situation, but machines just function as directed. Word Sense Disambiguation is the main flaw in machine translation. A single word might really have several different meanings or "senses," as the case may be. Pre-processing analyzes part-of-speech disambiguation, and the suggested technique uses unigrams, bigrams, and trigrams to get around WSD's shortcomings and get better results with ambiguous terms. SVM with Ngram provides a superior outcome in this case. Recall is 67% and Precision is 65%. But, this technique's primary goal is to identify the explicit and implicit levels of tension and relaxation reflected in tweets.

show abstract

Automatic stress detection in car drivers based on non-invasive physiological signals using machine learning techniques

Siam

Gamel

Talaat

2023

Neural Comput & Applic

View full text Add to dashboard Cite

Stress is now thought to be a major cause to a wide range of human health issues. However, many people may ignore their stress feelings and disregard to take action before serious physiological and mental disorders take place. The heart rate (HR) and blood pressure (BP) are the most physiological markers used in various studies to detect mental stress for a human, and because they are captured non-invasively using wearable sensors, these markers are recommended to provide information on a person’s mental state. Most stress assessment studies have been undertaken in a laboratory-based controlled environment. This paper proposes an approach to identify the mental stress of automotive drivers based on selected biosignals, namely, ECG, EMG, GSR, and respiration rate. In this study, six different machine learning models (KNN, SVM, DT, LR, RF, and MLP) have been used to classify between the stressed and relaxation states. Such system can be integrated with a Driver Assistance System (DAS). The proposed stress detection technique (SDT) consists of three main phases: (1) Biosignal Pre-processing, in which the signal is segmented and filtered. (2) Feature Extraction, in which some discriminate features are extracted from each biosignal to describe the mental state of the driver. (3) Classification. The results show that the RF classifier outperforms other techniques with a classification accuracy of 98.2%, sensitivity 97%, and specificity 100% using the drivedb dataset.

show abstract

Feature selection for stress level classification into a physiologycal signals set

Cited by 8 publications

References 7 publications

Driving Stress Detection Using Multimodal Convolutional Neural Networks with Nonlinear Representation of Short-Term Physiological Signals

Driving Stress Detection Using Multimodal Convolutional Neural Networks with Nonlinear Representation of Short-Term Physiological Signals

An Intelligent System for Detection of Mental Stress Using Machine Learning

Automatic stress detection in car drivers based on non-invasive physiological signals using machine learning techniques

Contact Info

Product

Resources

About