Search

An objective and accurate emotion diagnostic reference is vital to psychologists, especially when dealing with patients who are difficult to communicate with for pathological reasons. Nevertheless, current systems based on Electroencephalography (EEG) data utilized for sentiment discrimination have some problems, including excessive model complexity, mediocre accuracy, and limited interpretability. Consequently, we propose a novel and effective feature fusion mechanism named Mutual-Cross-Attention (MCA). Combining with a specially customized 3D Convolutional Neural Network (3D-CNN), this purely mathematical mechanism adeptly discovers the complementary relationship between time-domain and frequency-domain features in EEG data. Furthermore, the new designed Channel-PSD-DE 3D feature also contributes to the high performance. The proposed method eventually achieves 99.49% (valence) and 99.30% (arousal) accuracy on DEAP dataset., Comment: The work has been accepted by MICCAI 2024. The uploaded one is preprint which has not undergone peer review (when applicable) or any post-submission improvements or corrections. The official DOI link will be provided once available

In the fields of brain-computer interaction and cognitive neuroscience, effective decoding of auditory signals from task-based functional magnetic resonance imaging (fMRI) is key to understanding how the brain processes complex auditory information. Although existing methods have enhanced decoding capabilities, limitations remain in information utilization and model representation. To overcome these challenges, we propose an innovative multi-task learning model, Physics-informed Embedding Network with Multi-Task Transformer (PEMT-Net), which enhances decoding performance through physics-informed embedding and deep learning techniques. PEMT-Net consists of two principal components: feature augmentation and classification. For feature augmentation, we propose a novel approach by creating neural embedding graphs via node embedding, utilizing random walks to simulate the physical diffusion of neural information. This method captures both local and non-local information overflow and proposes a position encoding based on relative physical coordinates. In the classification segment, we propose adaptive embedding fusion to maximally capture linear and non-linear characteristics. Furthermore, we propose an innovative parameter-sharing mechanism to optimize the retention and learning of extracted features. Experiments on a specific dataset demonstrate PEMT-Net's significant performance in multi-task auditory signal decoding, surpassing existing methods and offering new insights into the brain's mechanisms for processing complex auditory information.

The correlation between net baryon number and electric charge, $\chi_{11}^{\rm BQ}$, can serve as a magnetometer of QCD. This is demonstrated by lattice QCD computations using the highly improved staggered quarks with physical pion mass of $M_\pi=135~$MeV on $N_\tau=8$ and 12 lattices. We find that $\chi_{11}^{\rm BQ}$ along the transition line starts to increase rapidly with magnetic field strength $eB\gtrsim 2M_\pi^2$ and by a factor 2 at $eB\simeq 8M_\pi^2$. Furthermore, the ratio of electric charge chemical potential to baryon chemical potential, $\mu_{\rm Q}/\mu_{\rm B}$, shows significant dependence on the magnetic field strength and varies from the ratio of electric charge to baryon number in the colliding nuclei in heavy ion collisions. These results can provide baselines for effective theory and model studies, and both $\chi_{11}^{\rm BQ}$ and $\mu_{\rm Q}/\mu_{\rm B}$ could be useful probes for the detection of magnetic fields in relativistic heavy ion collision experiments as compared with corresponding results from the hadron resonance gas model., Comment: 6 pages main text + 6 pages supplemental material, discussions added on the continuum estimate and extrapolation along with additional lattice QCD simulations on Nt=16 lattices, and the proxy of baryon electric charge correlation as well as the thermal fits to obtain the baryon and electric charge chemical potential

A lot of large chemical fertilizer plants producing 1000 ton NH3/day and 1700 ton urea/day were constructed in the 1970's in China. During operation, subsynchronous vibration takes place occasionally in some of the large turbine-compressor sets and has resulted in heavy economic losses. Two cases of subsynchronous vibration are described: Self-excited vibration of the low-pressure (LP) cylinder of one kind of N2-H2 multistage compressor; and Forced subsynchronous vibration of the high-pressure (HP) cylinder of the CO2 compressor.