Unveiling brain response mechanisms of citrus flavor perception: An EEG-based study on sensory and cognitive responses

Food Research International, Год журнала: 2025, Номер 206, С. 116096 - 116096

Опубликована: Фев. 25, 2025

Язык: Английский

---

The more, the better? Evaluating the role of EEG preprocessing for deep learning applications.

IEEE Transactions on Neural Systems and Rehabilitation Engineering, Год журнала: 2025, Номер 33, С. 1061 - 1070

Опубликована: Янв. 1, 2025

The last decade has witnessed a notable surge in deep learning applications for electroencephalography (EEG) data analysis, showing promising improvements over conventional statistical techniques. However, models can underperform if trained with bad processed data. Preprocessing is crucial EEG yet there no consensus on the optimal strategies scenarios, leading to uncertainty about extent of preprocessing required results. This study first thoroughly investigate effects applications, drafting guidelines future research. It evaluates varying levels, from raw and minimally filtered complex pipelines automated artifact removal algorithms. Six classification tasks (eye blinking, motor imagery, Parkinson's, Alzheimer's disease, sleep deprivation, episode psychosis) four established architectures were considered evaluation. analysis 4800 revealed differences between at intra-task level each model inter-task largest model. Models consistently performed poorly, always ranking average scores. In addition, seem benefit more minimal without handling methods. These findings suggest that artifacts may affect performance generalizability neural networks.

Язык: Английский

---

Lap-slip model of rebar-to-concrete in RC/ECC/UHPC based on GA-BP neural network

Case Studies in Construction Materials, Год журнала: 2024, Номер 20, С. e03287 - e03287

Опубликована: Май 15, 2024

Rebar lap splicing is a widely used method of reinforcement connection in precast concrete structures, and the lap-slip model serves as an important prerequisite for conducting detailed mechanical calculations reinforced splice members. Most traditional bond-slip models are semi-empirical semi-theoretical formulas derived from experimental data; they do not consider effect spacing, which prevents them accurately reflecting force transfer characteristics concrete. In this paper, Back Propagation (BP) neural network based on Genetic Algorithm (GA) to establish considering rebar improves current model. Several sets tests RC/ECC/UHPC were designed, full-sample parameter sensitivity analyses carried out using length, thickness cover, spacing stirrup ratio test parameters. The results showed that was influencing factor proposed model, with coefficient reaching 0.471. GA-BP network, developed compared existing models; predictive ability verified by ten-fold crossover method. generalizability randomly selecting non-training data well different types indicated exhibits high generalization abilities, most correlation coefficients exceeding 0.95. established fitting formula method, prediction accuracy slightly lower than obtained but it still offers accuracy, more objective realistic, guiding significance practical applications related research.

Язык: Английский

---

An extended clinical EEG dataset with 15,300 automatically labelled recordings for pathology decoding

NeuroImage Clinical, Год журнала: 2023, Номер 39, С. 103482 - 103482

Опубликована: Янв. 1, 2023

Automated clinical EEG analysis using machine learning (ML) methods is a growing research area. Previous studies on binary pathology decoding have mainly used the Temple University Hospital (TUH) Abnormal Corpus (TUAB) which contains approximately 3,000 manually labelled recordings. To evaluate and eventually even improve generalisation performance of for pathology, larger, publicly available datasets required. A number addressed automatic labelling large open-source as an approach to create new decoding, but little known about extent training automatically dataset affects performances established deep neural networks. In this study, we created additional labels (TUEG) based medical reports rule-based text classifier. We generated 15,300 newly recordings, call TUH Expansion (TUABEX), five times larger than TUAB. Since TUABEX more pathological (75%) non-pathological (25%) then selected balanced subset 8,879 Balanced (TUABEXB). investigate how networks, applied four convolutional networks (ConvNets) task versus classification compared each architecture after different datasets. The results show that TUABEXB rather TUAB increases accuracies itself some architectures. argue can be efficiently utilise massive amount data stored in archives. make proposed open source thus offer research.

Язык: Английский

---

An in-depth survey on Deep Learning-based Motor Imagery Electroencephalogram (EEG) classification

Artificial Intelligence in Medicine, Год журнала: 2023, Номер 147, С. 102738 - 102738

Опубликована: Дек. 2, 2023

Electroencephalogram (EEG)-based Brain-Computer Interfaces (BCIs) build a communication path between human brain and external devices. Among EEG-based BCI paradigms, the most commonly used one is motor imagery (MI). As hot research topic, MI has largely contributed to medical fields smart home industry. However, because of low signal-to-noise ratio (SNR) non-stationary characteristic EEG data, it difficult correctly classify different types MI-EEG signals. Recently, advances in Deep Learning (DL) significantly facilitate development BCIs. In this paper, we provide systematic survey DL-based classification methods. Specifically, first comprehensively discuss several important aspects classification, covering input formulations, network architectures, public datasets, etc. Then, summarize problems model performance comparison give guidelines future studies for fair comparison. Next, fairly evaluate representative models using source code released by authors meticulously analyse evaluation results. By performing ablation study on architecture, found that (1) effective feature fusion indispensable multi-stream CNN-based models. (2) LSTM should be combined with spatial extraction techniques obtain good performance. (3) use dropout contributes little improving performance, (4) adding fully connected layers increases their parameters but might not improve Finally, raise open issues possible directions.

Язык: Английский

---

An intelligent approach using micro-seismic monitoring signal clustering and an optimized K-means model to guide the selection of support patterns in underground mines

Tunnelling and Underground Space Technology, Год журнала: 2024, Номер 154, С. 106095 - 106095

Опубликована: Сен. 25, 2024

Язык: Английский

---

An Intelligent Mobile Application to Classify Employee Mental Workload Based on Eeg Dataset Using Machine Learning

Опубликована: Янв. 1, 2025

Mental workload assessment is critical in professional environments where cognitive demands influence productivity and well-being. Traditional methods for assessing mental workload, which often rely on subjective measures, lack the reliability required real-time applications. This study presents an innovative approach to measuring by integrating machine learning with electroencephalography data enhance objectivity. Using Emotiv headset, brain activity was collected while participants performed job simulation tasks. The employed a dual-model framework: ResNet-34 deep model analyzed Power Spectral Density images of activity, achieving classification accuracy 70\%, Support Vector Machine trained task performance metrics NASA Task Load Index self-assessment independently classified levels. outputs these models were combined meta-learning framework, further improved achieved significant gains. validated incorporated into mobile application, enabling workload. framework demonstrates potential scalable monitoring adaptive management across various industries. Future research aims incorporate additional physiological explore clinical

Язык: Английский

---

OreGenes: An optimized neural network tool for ore deposits classification based on gold grain geochemistry

Journal of Geochemical Exploration, Год журнала: 2025, Номер unknown, С. 107701 - 107701

Опубликована: Янв. 1, 2025

Язык: Английский

---

Computer-Driven Assessment of Weighted Attributes for E-Learning Optimization

Computers, Год журнала: 2025, Номер 14(4), С. 116 - 116

Опубликована: Март 23, 2025

Computer-driven assessment has revolutionized the way educational and professional assessments are conducted. Using artificial intelligence for data analytics, computer-based improves efficiency, accuracy, optimization of learning across disciplines. Optimizing e-learning requires a structured approach to analyzing learners’ progress adjusting instruction accordingly. Although effectiveness is influenced by numerous parameters, competency-based provides measurable evaluate achievements. This study explores application algorithms optimize e-learners’ studying within generalized e-course framework. A model was developed using weighted parameters derived from Bloom’s taxonomy. The key contribution this work an innovative method calculating competency scores attributes dynamic parameter, making process applicable both learners instructors. results indicate that attribute with parameter can improve structuring e-courses, increase learner engagement, provide instructors clearer understanding progress. proposed supports data-driven decision in e-learning, ensuring personalized experience, improving overall outcomes.

Язык: Английский

---

Joint multi-layer network and coupling redundancy minimization for semi-supervised EEG-based emotion recognition

Knowledge-Based Systems, Год журнала: 2025, Номер unknown, С. 113559 - 113559

Опубликована: Апрель 1, 2025

Язык: Английский

---