An EEG Database and Its Initial Benchmark Emotion Classification Performance
Ontology highlight
ABSTRACT:
SUBMITTER: Seal A
PROVIDER: S-EPMC7422491 | biostudies-literature | 2020 Jan
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Giving emotional intelligence to machines can facilitate the early detection and prediction of mental diseases and symptoms. Electroencephalography (EEG)-based emotion recognition is widely applied because it measures electrical correlates directly from the brain rather than indirect measurement of other physiological responses initiated by the brain. Therefore, we used non-invasive and portable EEG sensors to develop a real-time emotion classification pipeline. The pipeline trains different binary classifiers for Valence and Arousal dimensions from an incoming EEG data stream achieving a 23.9% (Arousal) and 25.8% (Valence) higher F1-Score on the state-of-art AMIGOS dataset than previous work. Afterward, the pipeline was applied to the curated dataset from 15 participants using two consumer-grade EEG devices while watching 16 short emotional videos in a controlled environment. Mean F1-Scores of 87% (Arousal) and 82% (Valence) were achieved for an immediate label setting. Additionally, the pipeline proved to be fast enough to achieve predictions in real-time in a live scenario with delayed labels while continuously being updated. The significant discrepancy from the readily available labels on the classification scores leads to future work to include more data. Thereafter, the pipeline is ready to be used for real-time applications of emotion classification.
| S-EPMC10007607 | biostudies-literature
Project description:Constructing a robust emotion-aware analytical framework using non-invasively recorded electroencephalogram (EEG) signals has gained intensive attentions nowadays. However, as deploying a laboratory-oriented proof-of-concept study toward real-world applications, researchers are now facing an ecological challenge that the EEG patterns recorded in real life substantially change across days (i.e., day-to-day variability), arguably making the pre-defined predictive model vulnerable to the given EEG signals of a separate day. The present work addressed how to mitigate the inter-day EEG variability of emotional responses with an attempt to facilitate cross-day emotion classification, which was less concerned in the literature. This study proposed a robust principal component analysis (RPCA)-based signal filtering strategy and validated its neurophysiological validity and machine-learning practicability on a binary emotion classification task (happiness vs. sadness) using a five-day EEG dataset of 12 subjects when participated in a music-listening task. The empirical results showed that the RPCA-decomposed sparse signals (RPCA-S) enabled filtering off the background EEG activity that contributed more to the inter-day variability, and predominately captured the EEG oscillations of emotional responses that behaved relatively consistent along days. Through applying a realistic add-day-in classification validation scheme, the RPCA-S progressively exploited more informative features (from 12.67 ± 5.99 to 20.83 ± 7.18) and improved the cross-day binary emotion-classification accuracy (from 58.31 ± 12.33% to 64.03 ± 8.40%) as trained the EEG signals from one to four recording days and tested against one unseen subsequent day. The original EEG features (prior to RPCA processing) neither achieved the cross-day classification (the accuracy was around chance level) nor replicated the encouraging improvement due to the inter-day EEG variability. This result demonstrated the effectiveness of the proposed method and may shed some light on developing a realistic emotion-classification analytical framework alleviating day-to-day variability.
| S-EPMC5515900 | biostudies-other
Project description:Dynamic Wave Arc (DWA) is a clinical approach designed to maximize the versatility of Vero SBRT system by synchronizing the gantry-ring noncoplanar movement with D-MLC optimization. The purpose of this study was to verify the delivery accuracy of DWA approach and to evaluate the potential dosimetric benefits.DWA is an extended form of VMAT with a continuous varying ring position. The main difference in the optimization modules of VMAT and DWA is during the angular spacing, where the DWA algorithm does not consider the gantry spacing, but only the Euclidian norm of the ring and gantry angle. A preclinical version of RayStation v4.6 (RaySearch Laboratories, Sweden) was used to create patient specific wave arc trajectories for 31 patients with various anatomical tumor regions (prostate, oligometatstatic cases, centrally-located non-small cell lung cancer (NSCLC) and locally advanced pancreatic cancer-LAPC). DWA was benchmarked against the current clinical approaches and coplanar VMAT. Each plan was evaluated with regards to dose distribution, modulation complexity (MCS), monitor units and treatment time efficiency. The delivery accuracy was evaluated using a 2D diode array that takes in consideration the multi-dimensionality of DWA during dose reconstruction.In centrally-located NSCLC cases, DWA improved the low dose spillage with 20 %, while the target coverage was increased with 17 % compared to 3D CRT. The structures that significantly benefited from using DWA were proximal bronchus and esophagus, with the maximal dose being reduced by 17 % and 24 %, respectively. For prostate and LAPC, neither technique seemed clearly superior to the other; however, DWA reduced with more than 65 % of the delivery time over IMRT. A steeper dose gradient outside the target was observed for all treatment sites (p < 0.01) with DWA. Except the oligometastatic cases, where the DWA-MCSs indicate a higher modulation, both DWA and VMAT modalities provide plans of similar complexity. The average ? (3 % /3 mm) passing rate for DWA plans was 99.2 ± 1 % (range from 96.8 to 100 %).DWA proven to be a fully functional treatment technique, allowing additional flexibility in dose shaping, while preserving dosimetrically robust delivery and treatment times comparable with coplanar VMAT.
| S-EPMC4850693 | biostudies-other
Project description:Emotion classification based on brain-computer interface (BCI) systems is an appealing research topic. Recently, deep learning has been employed for the emotion classifications of BCI systems and compared to traditional classification methods improved results have been obtained. In this paper, a novel deep neural network is proposed for emotion classification using EEG systems, which combines the Convolutional Neural Network (CNN), Sparse Autoencoder (SAE), and Deep Neural Network (DNN) together. In the proposed network, the features extracted by the CNN are first sent to SAE for encoding and decoding. Then the data with reduced redundancy are used as the input features of a DNN for classification task. The public datasets of DEAP and SEED are used for testing. Experimental results show that the proposed network is more effective than conventional CNN methods on the emotion recognitions. For the DEAP dataset, the highest recognition accuracies of 89.49% and 92.86% are achieved for valence and arousal, respectively. For the SEED dataset, however, the best recognition accuracy reaches 96.77%. By combining the CNN, SAE, and DNN and training them separately, the proposed network is shown as an efficient method with a faster convergence than the conventional CNN.
| S-EPMC7492909 | biostudies-literature
Project description:We present a new machine learning benchmark for reading task classification with the goal of advancing EEG and eye-tracking research at the intersection between computational language processing and cognitive neuroscience. The benchmark task consists of a cross-subject classification to distinguish between two reading paradigms: normal reading and task-specific reading. The data for the benchmark is based on the Zurich Cognitive Language Processing Corpus (ZuCo 2.0), which provides simultaneous eye-tracking and EEG signals from natural reading of English sentences. The training dataset is publicly available, and we present a newly recorded hidden testset. We provide multiple solid baseline methods for this task and discuss future improvements. We release our code and provide an easy-to-use interface to evaluate new approaches with an accompanying public leaderboard: www.zuco-benchmark.com.
| S-EPMC9878684 | biostudies-literature
Project description:ObjectivesBig data analytics can potentially benefit the assessment and management of complex neurological conditions by extracting information that is difficult to identify manually. In this study, we evaluated the performance of commonly used supervised machine learning algorithms in the classification of patients with traumatic brain injury (TBI) history from those with stroke history and/or normal EEG.MethodsSupport vector machine (SVM) and K-nearest neighbors (KNN) models were generated with a diverse feature set from Temple EEG Corpus for both two-class classification of patients with TBI history from normal subjects and three-class classification of TBI, stroke and normal subjects.ResultsFor two-class classification, an accuracy of 0.94 was achieved in 10-fold cross validation (CV), and 0.76 in independent validation (IV). For three-class classification, 0.85 and 0.71 accuracy were reached in CV and IV respectively. Overall, linear discriminant analysis (LDA) feature selection and SVM models consistently performed well in both CV and IV and for both two-class and three-class classification. Compared to normal control, both TBI and stroke patients showed an overall reduction in coherence and relative PSD in delta frequency, and an increase in higher frequency (alpha, mu, beta and gamma) power. But stroke patients showed a greater degree of change and had additional global decrease in theta power.ConclusionsOur study suggests that EEG data-driven machine learning can be a useful tool for TBI classification.SignificanceOur study provides preliminary evidence that EEG ML algorithm can potentially provide specificity to separate different neurological conditions.
| S-EPMC9513823 | biostudies-literature
Project description:Motor Imagery Brain-Computer Interfaces (MI-BCIs) are AI-driven systems that capture brain activity patterns associated with mental imagination of movement and convert them into commands for external devices. Traditionally, MI-BCIs operate on Machine Learning (ML) algorithms, which require extensive signal processing and feature engineering to extract changes in sensorimotor rhythms (SMR). In recent years, Deep Learning (DL) models have gained popularity for EEG classification as they provide a solution for automatic extraction of spatio-temporal features in the signals. However, past BCI studies that employed DL models, only attempted them with a small group of participants, without investigating the effectiveness of this approach for different user groups such as inefficient users. BCI inefficiency is a known and unsolved problem within BCI literature, generally defined as the inability of the user to produce the desired SMR patterns for the BCI classifier. In this study, we evaluated the effectiveness of DL models in capturing MI features particularly in the inefficient users. EEG signals from 54 subjects who performed a MI task of left- or right-hand grasp were recorded to compare the performance of two classification approaches; a ML approach vs. a DL approach. In the ML approach, Common Spatial Patterns (CSP) was used for feature extraction and then Linear Discriminant Analysis (LDA) model was employed for binary classification of the MI task. In the DL approach, a Convolutional Neural Network (CNN) model was constructed on the raw EEG signals. Additionally, subjects were divided into high vs. low performers based on their online BCI accuracy and the difference between the two classifiers' performance was compared between groups. Our results showed that the CNN model improved the classification accuracy for all subjects within the range of 2.37 to 28.28%, but more importantly, this improvement was significantly larger for low performers. Our findings show promise for employment of DL models on raw EEG signals in future MI-BCI systems, particularly for BCI inefficient users who are unable to produce desired sensorimotor patterns for conventional ML approaches.
| S-EPMC9307149 | biostudies-literature
Project description:In this study, we report the validation results of the EU-Emotion Voice Database, an emotional voice database available for scientific use, containing a total of 2,159 validated emotional voice stimuli. The EU-Emotion voice stimuli consist of audio-recordings of 54 actors, each uttering sentences with the intention of conveying 20 different emotional states (plus neutral). The database is organized in three separate emotional voice stimulus sets in three different languages (British English, Swedish, and Hebrew). These three sets were independently validated by large pools of participants in the UK, Sweden, and Israel. Participants' validation of the stimuli included emotion categorization accuracy and ratings of emotional valence, intensity, and arousal. Here we report the validation results for the emotional voice stimuli from each site and provide validation data to download as a supplement, so as to make these data available to the scientific community. The EU-Emotion Voice Database is part of the EU-Emotion Stimulus Set, which in addition contains stimuli of emotions expressed in the visual modality (by facial expression, body language, and social scene) and is freely available to use for academic research purposes.
| S-EPMC6478635 | biostudies-literature
Project description:In this work, we present an extensive dataset of laser-induced breakdown spectroscopy (LIBS) spectra for the pre-training and evaluation of LIBS classification models. LIBS is a well-established spectroscopic method for in-situ and industrial applications, where LIBS is primarily applied for clustering and classification tasks. As such, our dataset is aimed at helping with the development and testing of classification and clustering methodologies. Moreover, the dataset could be used to pre-train classification models for applications where the amount of available data is limited. The dataset consists of LIBS spectra of 138 soil samples belonging to 12 distinct classes. The spectra were acquired with a state-of-the-art LIBS system. Lastly, the composition of each sample is also provided, including estimated uncertainties.
| S-EPMC7018695 | biostudies-literature
Project description:Protein classification by machine learning algorithms is now widely used in structural and functional annotation of proteins. The Protein Classification Benchmark collection (http://hydra.icgeb.trieste.it/benchmark) was created in order to provide standard datasets on which the performance of machine learning methods can be compared. It is primarily meant for method developers and users interested in comparing methods under standardized conditions. The collection contains datasets of sequences and structures, and each set is subdivided into positive/negative, training/test sets in several ways. There is a total of 6405 classification tasks, 3297 on protein sequences, 3095 on protein structures and 10 on protein coding regions in DNA. Typical tasks include the classification of structural domains in the SCOP and CATH databases based on their sequences or structures, as well as various functional and taxonomic classification problems. In the case of hierarchical classification schemes, the classification tasks can be defined at various levels of the hierarchy (such as classes, folds, superfamilies, etc.). For each dataset there are distance matrices available that contain all vs. all comparison of the data, based on various sequence or structure comparison methods, as well as a set of classification performance measures computed with various classifier algorithms.
| S-EPMC1669728 | biostudies-literature