Search

Abstract The performance improvement of CMOS computer fails to meet the enormous data processing requirement of artificial intelligence progressively. The memristive neural network is one of the most promising circuit hardwares to make a breakthrough. This paper proposes a novel memristive synaptic circuit that is composed of four MOS transistors and one memristor (4T1M). The 4T1M synaptic circuit provides flexible control strategies to change memristance or respond to the input signal. Applying the 4T1M synaptic circuit as the cell of memristive crossbar array, based on the structure and algorithm of the back-propagation (BP) neural network, this paper proposes circuit design of the memristive crossbar-based BP neural network. By reusing the 4T1M memristive crossbar array, the computations in the forward-propagation process and back-propagation process of BP neural network are accomplished on the memristive crossbar-based circuit to accelerate the computing speed. The 4T1M memristive crossbar array can change all the cells’ memristance at a time, accordingly, the memristive crossbar-based BP neural network can realize synchronous memristance adjustment. The proposed memristive crossbar-based BP neural network is then evaluated through experiments involving XOR logic operation, iris classification, and MNIST handwritten digit recognition. The experimental results present fewer iterations or higher classification accuracies. Further, the comprehensive comparisons with the existing memristive BP neural networks highlight the advantages of the proposed memristive crossbar-based BP neural network, which achieves the fastest memristance adjustment speed using relatively few components.

Multimodal physiological signals play a pivotal role in drivers’ perception of work stress. However, the scarcity of labels and the multitude of modalities render the utilization of physiological signals for driving cognitive alertness detection challenging. We thus propose a multimodal physiological signal detection model based on self-supervised learning. First, in order to mine the intrinsic information of data and enable data to highlight effective information, we introduce a multiscale entropy (MSE) evoked attention mechanism. Secondly, the multimodal patches undergo processing through a novel cascaded attention mechanism. This attention mechanism is rooted in patch-level interactions within each modality, progressively integrating and interacting with other modalities in a cascading manner, thereby mitigating computational complexity. Moreover, a multimodal uncertainty-aware module is devised to effectively cope with intricate variations in the data. This module enhances its generalization ability through the incorporation of uncertain resampling. Experiments were conducted on the DriveDB dataset and the CogPilot dataset with both the linear probing and the fine-tuning evaluation protocols. Experimental results in subject-dependent setting show that our model significantly outperforms previous competitive baselines. In the linear probing evaluation, our model achieves on average 6.26%, 6.64%, and 7.75% improvements in Accuracy (Acc), Recall (Rec), and F1 Score. It also outperforms other models by 7.96% in Acc, 9.13% in Rec, and 9.2% in F1 using the fine-tuning evaluation. Furthermore, our model also demonstrates robust performance in subject-independent setting.

Emotion recognition from physiological signals (ERPS) has drawn tremendous attention and can be potentially applied to numerous fields. Since physiological signals are nonstationary time series with high sampling frequency, it is challenging to directly extract features from them. Additionally, there are 2 major challenges in ERPS: (a) how to adequately capture the correlations between physiological signals at different times and between different types of physiological signals and (b) how to effectively minimize the negative effect caused by temporal covariate shift (TCS). To tackle these problems, we propose a domain generalization and residual network-based approach for emotion recognition from physiological signals (DGR-ERPS). We first pre-extract time- and frequency-domain features from the original time series to compose a new time series. Then, in order to fully extract the correlation information of different physiological signals, these time series are converted into 3D image data to serve as input for a residual-based feature encoder (RBFE). In addition, we introduce a domain generalization-based technique to mitigate the issue posed by TCS. We have conducted extensive experiments on 2 real-world datasets, and the results indicate that our DGR-ERPS achieves superior performance under both TCS and non-TCS scenarios.

Background: It is unclear whether serum calcium on admission is associated with clinical outcomes in dilated cardiomyopathy (DCM). In this study, we conducted a retrospective study spanning a decade to investigate the prognostic value of baseline calcium in elderly patients with DCM. Methods: A total of 1,089 consecutive elderly patients (age ≥60 years) diagnosed with DCM were retrospectively enrolled from January 2010 to December 2019. Univariate and multivariate analyses were performed to investigate the association of serum calcium with their clinical outcomes. Results: In this study, the average age of the subjects was 68.36 ± 6.31 years. Receiver operating characteristic (ROC) curve analysis showed that serum calcium level had a great sensitivity and specificity for predicting in-hospital death, with an AUC of 0.732. Kaplan–Meier survival analysis showed that patients with a serum calcium >8.62 mg/dL had a better prognosis than those with a serum calcium ≤8.62 mg/dL (log-rank χ2 40.84, p < 0.001). After adjusting for several common risk factors, a serum calcium ≤8.62 mg/dL was related to a higher risk of long-term mortality (HR: 1.449; 95% CI: 1.115~1.882; p = 0.005). Conclusions: Serum calcium level could be served as a simple and affordable tool to evaluate patients’ prognosis in DCM.

Submarine hydrothermal activity has been a focused research topic since its discovery in the 1970s [...]