Develop an emotion recognition system using jointly connectivity between electroencephalogram and electrocardiogram signals

Heliyon, Год журнала: 2025, Номер 11(2), С. e41767 - e41767

Опубликована: Янв. 1, 2025

Язык: Английский

---

EEGSNet: A novel EEG cognitive recognition model using spiking neural network

Biomedical Signal Processing and Control, Год журнала: 2025, Номер 105, С. 107610 - 107610

Опубликована: Фев. 4, 2025

Язык: Английский

---

Federated learning in Emotion Recognition Systems based on physiological signals for privacy preservation: a review

Multimedia Tools and Applications, Год журнала: 2024, Номер unknown

Опубликована: Июнь 3, 2024

Язык: Английский

---

Recognition of emotional categories using mined fuzzy rules from electroencephalogram signals with gated eye track data approach

IEEE Access, Год журнала: 2024, Номер 12, С. 118122 - 118140

Опубликована: Янв. 1, 2024

Researchers suggest that a short video clip, when tagged with single label, is sufficient for classification into an emotional category. However, subjects view film similarly, there no guarantee the designated emotion persists throughout duration, or exactly elicited. This inconsistency adversely affects performance of recognition (ER) systems. In this study, we propose multimodal ER system employing eye-tracking gated strategy to identify most effective timing categorization. Initially, common features are extracted and selected using minimum-redundancy-maximum-relevance (mRMR) method. Subsequently, discriminative feature employed as threshold pinpoint relevant timing. EEG signals from these moments then decomposed five standard frequency bands Daubechies wavelet function (order 4). Furthermore, four types entropy four-second segments 62 32 channels SEED-IV MAHNOB-HCI databases, respectively. The best features, determined by mRMR method, fed Sugeno-fuzzy inference (S-FIS) designed derive rules discriminating between categories happiness, fear, sadness, neutrality. S-FIS were refined genetic algorithm (GA), leading achieving average accuracies 94.42% 85.20% alpha results study demonstrate effectiveness fuzzy rule extraction in enhancing

Язык: Английский

---

Evaluating Brain Activity in Patients With Chronic Disorders of Consciousness After Traumatic Brain Injury Using EEG Microstate Analysis During Hyperbaric Oxygen Therapy

CNS Neuroscience & Therapeutics, Год журнала: 2025, Номер 31(1)

Опубликована: Янв. 1, 2025

ABSTRACT Background Hyperbaric oxygen (HBO) therapy is an efficacious intervention for patients with prolonged disorders of consciousness (pDOC). Electroencephalographic (EEG) microstate analysis can provide assessment the global state brain. Currently, misdiagnosis rate consciousness‐level assessments in pDOC high. Therefore, we aimed to assess levels and outcomes by analyzing changes EEG signals during HBO therapy. Methods data were collected from 32 traumatic brain injury before after 20 min obtained sessions. Modified k‐means clustering was used segment into microstates. A paired sample t test compare characteristics Results The duration, occurrence, coverage D significantly increased minimally conscious (MCS) group Significant increases same parameters observed among unresponsive wakefulness group. Furthermore, greater improvements Coma Recovery Scale‐Revised scores (i.e., more than three points) showed significant D. Both MCS improvement presented Conclusions Microstate may be associated recovery patients. This study verified safety feasibility real‐time pDOC. serve as a complement electroencephalographic indices useful predicting levels.

Язык: Английский

---

SimpleRNN Based Human Emotion Recognition Using EEG Signals

Communications in computer and information science, Год журнала: 2025, Номер unknown, С. 48 - 57

Опубликована: Янв. 1, 2025

Язык: Английский

---

DDNet: a hybrid network based on deep adaptive multi-head attention and dynamic graph convolution for EEG emotion recognition

Signal Image and Video Processing, Год журнала: 2025, Номер 19(4)

Опубликована: Фев. 14, 2025

Язык: Английский

---

The Application of Artificial Intelligence Technology in Intellectual Property Protection and Its Impact on the Cultural Industry

Applied Mathematics and Nonlinear Sciences, Год журнала: 2025, Номер 10(1)

Опубликована: Янв. 1, 2025

Abstract Patent data possesses characteristics such as a large amount of relevant data, volume and an application management process that is difficult to control. The protection patent intellectual property rights will be impacted by these features. In order solve the above problems, this paper, in context artificial intelligence technology, takes clothing appearance research object, adopts normalization method mine extract features, uses View-GCN graph convolution module learn features view, after builds DP-MVGCN model based on neural network for classification property. Finally, applied build effective discuss impact cultural industry. results show feature extraction rate >95% when number training times reaches 70. At k=3.0, has highest score result test set 4 evaluation indexes, good accuracy. Starting from 2020, measured values three indices judicial protection, administrative social have increased sharply over time. By 2023 indexes pathways 1.27 times, 1.29 1.26 respectively compared 2020. It clear reasonable patents can significantly improve patented knowledge, also enhance degree industry agglomeration promote self-production subcultural clusters.

Язык: Английский

---

Electroencephalogram Based Emotion Recognition Using Hybrid Intelligent Method and Discrete Wavelet Transform

Applied Sciences, Год журнала: 2025, Номер 15(5), С. 2328 - 2328

Опубликована: Фев. 21, 2025

Electroencephalography-based emotion recognition is essential for brain-computer interface combined with artificial intelligence. This paper proposes a novel algorithm human detection using hybrid paradigm of convolutional neural networks and boosting model. The proposed employs two subsets 18 14 features extracted from four sub-bands discrete wavelet transform. These are identified as the optimal most relevant, among 42 original input 8 6 productive channels dual genetic wise-subject 5-fold cross validation procedure in which first second algorithms address efficient feature subsets. estimated by differently intelligent models on set. produces an accuracy 70.43%/76.05%, precision 69.88%/74.57%, recall 98.70%/99.17%, F1 score 81.83%/85.13% valence/arousal classifications, suggest that frontal left regions cortex associate especially to emotions.

Язык: Английский

---

EEG-based emotion recognition model using fuzzy adjacency matrix combined with convolutional multi-head graph attention mechanism

Cluster Computing, Год журнала: 2025, Номер 28(4)

Опубликована: Фев. 25, 2025

Язык: Английский

---