DASPS: A Database for Anxious States based on a Psychological Stimulation

Baghdadi, Asma; Aribi, Yassine; Fourati, Rahma; Halouani, Najla; Siarry, Patrick; Alimi, Adel M.

doi:10.48550/arxiv.1901.02942

Cited by 3 publications

(9 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, at the beginning, the database for anxious states based on a psychological stimulus (DASPS) is investigated and since these data are noise-free, there is no need for any noise removal method [9,10]. In this work, we intend to take into account the best extracted features that have been reported in previous works.…”

Section: Methodsmentioning

confidence: 99%

“…This can be done using filters, error correction methods, or data preprocessing techniques. Therefore, since the data in the DASPS database are noise-free, there is no need to use noise removal methods [9,10].…”

Section: Noise Reductionmentioning

confidence: 99%

“…One of the most time-consuming stages of research is recording and collecting data related to research. The data used in this thesis was used from the " Database for Anxious States based on a Psychological Stimulus (DASPS)" database [9,10]. This database consists of EEG signals of 23 people, 13 women and 10 men, with an average age of 30 years.…”

Section: Datasetmentioning

confidence: 99%

“…𝑙𝑛𝑃 𝑔 (9) where P is the probability distribution as (𝑃 1 , 𝑃 2 , … , 𝑃 𝑘 ), g=1,2,...,k and m is the dimension.…”

Section: Permutation Entropymentioning

confidence: 99%

See 3 more Smart Citations

Enhancing Anxiety Diagnosis through ADABOOST-Assisted Decision-Level Fusion

Hosseini,

Maghooli

2024

Preprint

View full text Add to dashboard Cite

Background: Humans naturally respond with anxiety to mental stress caused by a variety of circumstances. Anxiety impairs memory function and makes it difficult to learn and retain information. Additionally, sustaining high productivity while balancing life's stresses can be achieved through good anxiety and stress management. New Method: This paper presents an effective technique for automatically classifying two anxiety levels: normal and anxious, using an analysis of EEG data. The EEG signals found in the DASPS database were utilized. This database includes 14-channel EEG recordings taken under normal and anxious settings from 23 individuals (10 male and 13 female, average age 30 years). Brain subbands were extracted from EEG signals using wavelet transform. Different features such as Hjorth coefficients, entropy, autoregressive, and energy were extracted. The feature vector was reduced by the PCA method, and the classification was carried out by the Adaboost classification method. Results: The results demonstrate the effectiveness and efficiency of the proposed model in diagnosing anxiety, with an accuracy of 80.58%. Comparison with Existing Methods: Our study highlights the superior performance of the Adaboost method compared to other methods, showcasing its potential for accurate anxiety classification using EEG data. Conclusions: In conclusion, the proposed method shows promise for automatic classification of anxiety levels using EEG data. By leveraging machine learning techniques and EEG analysis, our approach could contribute to improved anxiety diagnosis and stress management strategies.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Noise Reductionmentioning

confidence: 99%

Section: Datasetmentioning

confidence: 99%

“…𝑙𝑛𝑃 𝑔 (9) where P is the probability distribution as (𝑃 1 , 𝑃 2 , … , 𝑃 𝑘 ), g=1,2,...,k and m is the dimension.…”

Section: Permutation Entropymentioning

confidence: 99%

See 2 more Smart Citations

Enhancing Anxiety Diagnosis through ADABOOST-Assisted Decision-Level Fusion

Hosseini,

Maghooli

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In the next section, we describe the innovation of applying our entropy parameters to a set of EEGs collected from stressful situations. Such an EEG database was registered and communicated in [24][25][26] and it is also a novelty as a result of the aforementioned ethical considerations. The experiences and reactions of the participants are parallel to those suffered by attendants.…”

Section: Introductionmentioning

confidence: 99%

Stress Response Analysis via Dynamic Entropy in EEG: Caregivers in View

Zavala-Yoé

Iqbal

Parra‐Saldívar

et al. 2023

IJERPH

View full text Add to dashboard Cite

According to the World Health Organization (WHO), stress can be defined as any type of alteration that causes physical, emotional, or psychological tension. A very important concept that is sometimes confused with stress is anxiety. The difference between stress and anxiety is that stress usually has an existing cause. Once that activator has passed, stress typically eases. In this respect, according to the American Psychiatric Association, anxiety is a normal response to stress and can even be advantageous in some circumstances. By contrast, anxiety disorders differ from temporary feelings of anxiousness or nervousness with more intense feelings of fear or anxiety. The Diagnostic and Statistical Manual (DSM-5) explicitly describes anxiety as exorbitant concern and fearful expectations, occurring on most days for at least 6 months, about a series of events. Stress can be measured by some standardized questionnaires; however, these resources are characterized by some major disadvantages, the main one being the time consumed to interpret them; i.e., qualitative information must be transformed to quantitative data. Conversely, a physiological recourse has the advantage that it provides quantitative spatiotemporal information directly from brain areas and it processes data faster than qualitative supplies. A typical option for this is an electroencephalographic record (EEG). We propose, as a novelty, the application of time series (TS) entropies developed by us to inspect collections of EEGs obtained during stress situations. We investigated this database related to 23 persons, with 1920 samples (15 s) captured in 14 channels for 12 stressful events. Our parameters reflected that out of 12 events, event 2 (Family/financial instability/maltreatment) and 10 (Fear of disease and missing an important event) created more tension than the others. In addition, the most active lobes reflected by the EEG channels were frontal and temporal. The former is in charge of performing higher functions, self-control, self monitoring, and the latter is in charge of auditory processing, but also emotional handling. Thus, events E2 and E10 triggering frontal and temporal channels revealed the actual state of participants under stressful situations. The coefficient of variation revealed that E7 (Fear of getting cheated/losing someone) and E11 (Fear of suffering a serious illness) were the events with more changes among participants. In the same sense, AF4, FC5, and F7 (mainly frontal lobe channels) were the most irregular on average for all participants. In summary, by means of dynamic entropy analysis, the goal is to process the EEG dataset in order to elucidate which event and brain regions are key for all participants. The latter will allow us to easily determine which was the most stressful and on which brain zone. This study can be applied to other caregivers datasets. All this is a novelty.

show abstract