We present DREAMER, a multi-modal database consisting of electroencephalogram (EEG) and electrocardiogram (ECG) signals recorded during affect elicitation by means of audio-visual stimuli. Signals from 23 participants were recorded along with the participants' self-assessment of their affective state after each stimuli, in terms of valence, arousal, and dominance. All the signals were captured using portable, wearable, wireless, low-cost and off-the-shelf equipment that has the potential to allow the use of affective computing methods in everyday applications. The Emotiv EPOC wireless EEG headset was used for EEG and the Shimmer2 ECG sensor for ECG.

Classification results for valence, arousal and dominance of the proposed database are comparable to the ones achieved for other databases that use non-portable, expensive, medical grade devices.

The proposed database is made publicly available in order to allow researchers to achieve a more thorough evaluation of the suitability of these capturing devices for affect recognition applications.

Please cite as:

S. Katsigiannis, N. Ramzan, "DREAMER: A Database for Emotion Recognition Through EEG and ECG Signals from Wireless Low-cost Off-the-Shelf Devices," IEEE Journal of Biomedical and Health Informatics, vol. 22, no. 1, pp. 98-107, Jan. 2018. doi: 10.1109/JBHI.2017.2688239

Dataset

This dataset was created by Phan Huy Hoang

Contents

Overview The Dream EEG and Mentation (DREAM) database collects and stores metadata about DREAM datasets, and is accessible to the public. DREAM datasets provide polysomnography and associated subjective mentation reports. Some datasets may also contain personally identifiable information about participants, but such information are not stored by the DREAM database. Datasets are contributed to DREAM from many different labs in many different studies and, where possible, made openly accessible in the hope of pushing the fields of sleep, dream, brain-computer interface, and consciousness research forward. If you have data that others in the community might find useful, please consider contributing it to DREAM. Contents The DREAM database consists of a following data tables:

Datasets Data records People

The records in Datasets list all officially accepted DREAM datasets and their summary metadata. Data records lists metadata of each individual datum from these datasets. People provides information on the data contributors, referred to by Key ID in Datasets.

Subscribers can find out export and import data of 23 countries by HS code or product’s name. This demo is helpful for market analysis.

The dataset used in the paper for text-to-3D content creation, which consists of 3D assets generated from text prompts.

Dream EEG and Mentation (DREAM) data set ---Data set information--- Common name: REM_Turku Full name: REM_Turku Authors: Pilleriin Sikka, Antti Revonsuo, Valdas Noreika, and Katja Valli Location: Turku, Finland Year: N/A Set ID: [SET BY DATABASE] Amendment: [SET BY DATABASE] Corresponding author ID: [SET BY DATABASE] Download URL: [SET BY DATABASE] Correspondence: Pilleriin Sikka (pilsik@utu.fi), Katja Valli (katval@utu.fi) ---Metadata--- Key ID: [SET BY DATABASE] Date entered: [SET BY DATABASE] Number of samples: [INFERRED BY DATABASE] Number of subjects: [INFERRED BY DATABASE] Proportion REM: [INFERRED BY DATABASE] Proportion N1: [INFERRED BY DATABASE] Proportion N2: [INFERRED BY DATABASE] Proportion experience: [INFERRED BY DATABASE] Proportion no-experience: [INFERRED BY DATABASE] Proportion healthy: [INFERRED BY DATABASE] Provoked awakening: Yes Time of awakening: Night Form of response: Free Date approved: [SET BY DATABASE] ---How to decode data files--- The PSG files are raw (i.e., not preprocessed) EEG data files and include the last 2 minutes of preawakening EEG from each REM episode obtained using a serial awakening paradigm in the sleep laboratory. Data set includes EEG data from 134 awakenings of 18 participants. Files are organized according to the format: /Data/PSG/casexx_syy, where xx refers to Case ID yy refers to Subject ID In the "Records.csv" file, the following information is presented: Filename: in the format /Data/PSG/Sxx_yy Case ID: number of awakening for the subject Subject ID: unique identifier of subject Experience: 2 = dream experience; 1 = without recall ("white dream"); 0 = no dream experience Treatment group: N/A Duration: duration of the EEG data file in seconds EEG sample rate: the sampling rate of the EEG in Hertz Number of EEG channels: the number of EEG signals in this sample Last sleep stage: the scored sleep stage of the final epoch in the sample Has EOG: whether EOG is included in the sample (1 = yes; 0 = no) Has EMG: whether EMG is included in the sample (1 = yes; 0 = no) Has ECG: whether ECG is included in the sample (1 = yes; 0 = no) Proportion artifacts: N/A Time of awakening: time when this sample’s PSG ends Subject age: age of the subject Subject sex: sex of the subject (key: 0 = male, 1 = female; 2 = other) Subject healthy: whether subject is from a relatively healthy population (key: 0 = no; 1 = yes) Has more data: whether this sample has more data in the form of files under the /Data directory other than the /Data/PSG directory (key: 0=no, 1=yes) Remarks: The first number refers to the number of experimental night in the sleep lab for the subject, the second number refer to the number of awakening during that night (e.g., 1_3 refers to Night 1, Awakening 3). Remarks can also include other important information regarding this subject or data file. In the "Ratings.csv" file, the following information is presented: Filename: in the format /Data/PSG/casexx_syy DreamReport_Wordcount: total number of dream-related words minus utterances, fillers, repetitions, corrections, waking commentaries ER = external ratings of emotions expressed in dream reports, conducted by two blind judges using the Finnish version of the modified Differential Emotions Scale (mDES; Fredrickson, 2013); the number refers to the frequency of occurrence of the emotion item in the dream report SR = self-ratings of emotions experienced in the preceding dream using the mDES, conducted by participants themselves upon awakening and after having reported the dream; each item was rated on the scale from 0 = not at all to 4 = extremely much PA = positive emotion/affect item of mDES NA = negative emotion/affect item of mDES The following are the 10 positive and 10 negative emotion/affect items of the mDES scale: PA1 - Amused_Funloving_Giggly PA2 - Awe_Wonder_Amazement PA3 - Grateful_Appreciative_Thankful PA4 - Hopeful_Optimistic_Encouraged PA5 - Inspired_Uplifted_Elevated PA6 - Interested_Alert_Curious PA7 - Joyful_Glad_Happy PA8 - Love_Closeness_Trust PA9 - Proud_Confident_Selfassured PA10 - Serene_Content_Peaceful NA1 - Angry_Irritated_Annoyed NA2 - Ashamed_Humiliated_Disgraced NA3 - Contemptuous_Scornful_DIsdainful NA4 - Disgust_Distaste_Revulsion NA5 - Embarrassed_Selfconscious_Blushing NA6 - Guilty_Repetant_Blameworthy NA7 - Hate_Distrust_Suspicion NA8 - Sad_Downhearted_Unhappy NA9 - Scared_Fearful_Afraid NA10 - Stressed_Nervous_Overwhelmed ER_InferredExpressed = whether the emotion was directly expressed in the dream report or could be inferred from the behaviour of the dream self (key: 1 = expressed, 2 = inferred, 3 = both) Remarks: any remarks regarding this data file --Treatment group codes-- N/A ---Experimental description--- A full description of the materials and methods can be found in the following article: Sikka, P., Revonsuo, A., Noreika, V., & Valli, K. (2019). EEG frontal alpha asymmetry and dream affect: Alpha oscillations over the right frontal cortex during REM sleep and presleep wakefulness predict anger in REM sleep dreams. Journal of Neuroscience, 39(24): 4775-4784. https://doi.org/10.1523/JNEUROSCI.2884-18.2019 Participants: Healthy, not using medication, right-handed, native Finnish speakers, with good sleep quality (score ≤ 5 on the Pittsburgh Sleep Quality Index; Buysse et al., 1989). Experimental design and procedure: For a Figure displaying the experimental procedure, see Sikka et al. (2019, p. 4777). Participants spent 2 nights (separated by a week) in the sleep laboratory. In the evening, participants arrived in the laboratory 2h before their usual bedtime. First, participants were instructed about the procedure of the study and EEG electrodes attached to their scalp. Next, participants' waking state resting EEG was recorded (8 x 1 min; 10:30pm-12:00am) and they rated their current waking affective state using the Finnish version of the modified Differential Emotions Scale (fmDES, Fredickrson, 2013). Participants were then allowed to fall asleep. Sleep stages were monitored and scored visually (Rechtschaffen and Kales, 1968; Iber et al., 2007). Every time REM sleep had lasted continuously for 5 min, and was in a phasic stage, a tone signal was used to awaken the participants. Upon awakening, participants provided an oral dream report: first, they reported the last image they had in mind just before awakening, followed by a detailed report of the whole dream. Next, participants rated their affective experiences in the preceding dream by filling in the fmDES electronically using a mouse and a computer screen above the bed. In case the participants reported ‘‘no dreams’’, researchers asked whether they had not had a dream or they felt like they had had a dream but could not recall any specific content (i.e., ‘white dream’). In these two cases fmDES was not filled in. Participants were then allowed to continue their sleep. This procedure was repeated throughout the night until the final morning awakening (scheduled between 5:30 A.M. to 8:30 A.M.). Upon final awakening, and after having reported and rated the last dream, participants were asked to lie in bed but stay awake. Similar to the evening, waking state resting (morning baseline) EEG was then recorded for 8 min, followed by participants’ ratings of their current waking state affect using the fmDES. --DREAM categorization procedure-- Dream experiences = participants remembered having a dream and were able to report at least some of its content. Without recall ("white dream" = participants felt like they had had a dream but could not recall any specific content. No recall = participants reported not having had any dream experiences. ---Technical details--- N/A --Data acquisition-- EEG was recorded using 24 single Ag/AgCl electrodes (placed according to standard 10/10 system). Additionally, 4 EOG electrodes were used to record eye movements and an EMG electrode (placed on the chin) was used to record muscle activity. All electrodes (except the bipolar EOG and EMG electrodes) were references to the right mastoid. The ground electrode was placed on the forehead. EEG signal was amplified (SynAmps model 5083), notch-filtered at 50 Hz, digitized at 500 Hz, and recorded with Neuroscan equipment and software. All impedances were kept <5 kΩ. --Data preprocessing-- Data has not been preprocessed.

Dreamer Exports Export Import Data. Follow the Eximpedia platform for HS code, importer-exporter records, and customs shipment details.

This dataset provides information about the number of properties, residents, and average property values for Day Dreamer Drive cross streets in Colorado Springs, CO.

Emotion classification using electroencephalography (EEG) data and machine learning techniques have been on the rise in the recent past. However, past studies use data from medical-grade EEG setups with long set-up times and environment constraints. The images from the OASIS image dataset were used to elicit valence and arousal emotions, and the EEG data was recorded using the Emotiv Epoc X mobile EEG headset. We propose a novel feature ranking technique and incremental learning approach to analyze performance dependence on the number of participants. The analysis is carried out on publicly available datasets: DEAP and DREAMER for benchmarking. Leave-one-subject-out cross-validation was carried out to identify subject bias in emotion elicitation patterns. The collected dataset and pipeline are made open source.

Code: https://github.com/rohitgarg025/Decoding_EEG

Subscribers can find out export and import data of 23 countries by HS code or product’s name. This demo is helpful for market analysis.

This dataset provides information about the number of properties, residents, and average property values for Dreamer Road cross streets in Edinburg, TX.

This dataset is about books. It has 6 rows and is filtered where the book is The dreamer. It features 7 columns including author, publication date, language, and book publisher.

Can you use brainwave data to discern whether someone is feeling good?

Please cite the following if you are using this data

https://www.researchgate.net/publication/329403546_Mental_Emotional_Sentiment_Classification_with_an_EEG-based_Brain-machine_Interface

https://www.researchgate.net/publication/335173767_A_Deep_Evolutionary_Approach_to_Bioinspired_Classifier_Optimisation_for_Brain-Machine_Interaction

This is a dataset of EEG brainwave data that has been processed with our original strategy of statistical extraction (paper below)

The data was collected from two people (1 male, 1 female) for 3 minutes per state - positive, neutral, negative. We used a Muse EEG headband which recorded the TP9, AF7, AF8 and TP10 EEG placements via dry electrodes. Six minutes of resting neutral data is also recorded, the stimuli used to evoke the emotions are below

1 . Marley and Me - Negative (Twentieth Century Fox) Death Scene 2. Up - Negative (Walt Disney Pictures) Opening Death Scene 3. My Girl - Negative (Imagine Entertainment) Funeral Scene 4. La La Land - Positive (Summit Entertainment) Opening musical number 5. Slow Life - Positive (BioQuest Studios) Nature timelapse 6. Funny Dogs - Positive (MashupZone) Funny dog clips

Our method of statistical extraction resampled the data since waves must be mathematically described in a temporal fashion.

If you would like to use the data in research projects, please cite the following:

J. J. Bird, L. J. Manso, E. P. Ribiero, A. Ekart, and D. R. Faria, “A study on mental state classification using eeg-based brain-machine interface,”in 9th International Conference on Intelligent Systems, IEEE, 2018.

J. J. Bird, A. Ekart, C. D. Buckingham, and D. R. Faria, “Mental emotional sentiment classification with an eeg-based brain-machine interface,” in The International Conference on Digital Image and Signal Processing (DISP’19), Springer, 2019.

This research was part supported by the EIT Health GRaCE-AGE grant number 18429 awarded to C.D. Buckingham.

Dreamer Network Co Limited Export Import Data. Follow the Eximpedia platform for HS code, importer-exporter records, and customs shipment details.

Emotion classification using electroencephalography (EEG) data and machine learning techniques have been on the rise in the recent past. However, past studies use data from medical-grade EEG setups with long set-up times and environment constraints. This paper focuses on classifying emotions on the valence-arousal plane using various feature extraction, feature selection, and machine learning techniques. We evaluate different feature extraction and selection techniques and propose the optimal set of features and electrodes for emotion recognition. The images from the OASIS image dataset were used to elicit valence and arousal emotions, and the EEG data was recorded using the Emotiv Epoc X mobile EEG headset. The analysis is carried out on publicly available datasets: DEAP and DREAMER for benchmarking. We propose a novel feature ranking technique and incremental learning approach to analyze performance dependence on the number of participants. Leave-one-subject-out cross-validation was carried out to identify subject bias in emotion elicitation patterns. The importance of different electrode locations was calculated, which could be used for designing a headset for emotion recognition. The collected dataset and pipeline are also published. Our study achieved a root mean square score (RMSE) of 0.905 on DREAMER, 1.902 on DEAP, and 2.728 on our dataset for valence label and a score of 0.749 on DREAMER, 1.769 on DEAP, and 2.3 on our proposed dataset for arousal label.

Three Dreamer Manufacturing Company Limited Export Import Data. Follow the Eximpedia platform for HS code, importer-exporter records, and customs shipment details.

This dataset is about book subjects. It has 4 rows and is filtered where the books is Dreamer. It features 10 columns including number of authors, number of books, earliest publication date, and latest publication date.

Dreamer Trading Llc Export Import Data. Follow the Eximpedia platform for HS code, importer-exporter records, and customs shipment details.

Dreamer Fashions Llc Export Import Data. Follow the Eximpedia platform for HS code, importer-exporter records, and customs shipment details.

Data from My Virtual Dream installation Oct 5-6, 2013. Research article with full description of the data : TBA Data are organized in subject-specific matlab files, according to session number (1-29), pod number (1-4) and player number (1-5). Entire experiment was performed in 29 sessions, from 7pm, Oct 5, 2013 to 6:30am Oct 6, 2013. During each session there were 20 subjects, divided into 4 pods of 5 subjects. Only complete, partially preprocessed, data sets are included. For each subject, condition specific EEG time series were extracted and resampled to 256Hz. Subject's .mat file contains the following variables: session -- number -- session number (1-29), the same as in the filename pod -- number -- pod number (1-4). position -- number -- subject's position within pod (1-5, sitting arrangement from left to right) age -- number -- subject's age in years sex -- string -- 'f' or 'm' srate -- number -- sampling rate is the same for all subjects: 256Hz chan_names -- cell array of strings -- names of 4 EEG channels, given in the same order as EEG data conditions -- cell array of strings -- names of conditions cond_eeg -- cell array of 2D matrices -- conditition specific EEG data in (time x channel) format aP -- 1D array -- condition specific aP performance measure (number of a+ states divided by number of a- states during first 20 seconds of the condition) bP -- 1D array -- condition specific bP performance measure (number of b+ states divided by number of b- states during first 20 seconds of the condition)