MuLHiTA: A Novel Multiclass Classification Framework With Multibranch LSTM and Hierarchical Temporal Attention for Early Detection of Mental Stress.

Mental stress is an increasingly common psychological issue leading to diseases such as depression, addiction, and heart attack. In this study, an early detection framework based on electroencephalogram (EEG) data is developed for reducing the risk of these diseases. In existing frameworks, signals are often segmented into smaller sections prior to being input to a deep neural network. However, this approach ignores the fundamental nature of EEG signals as a carrier of valuable information (e.g., the integrity of frequency and phase, and temporal fluctuations of EEG components). As such, this type of segmenting may lead to information loss and a failure to effectively identify mental stress levels. Thus, we propose a novel multiclass classification framework termed multibranch LSTM and hierarchical temporal attention (MuLHiTA) for the early identification of mental stress levels. It specifically focuses on not only intraslice (within each slice) but also interslice (between different slices) samples in parallel. This was achieved by including two complementary branches, each of which integrated a specifically designed attention module into a bidirectional long short-term memory (BLSTM) network, enabling extraction of the most discriminative features from interslice and intraslice EEG signals simultaneously. The outputs of attention modules were then summed to obtain a feature representation that contributes to reduce overfitting and more effective multiclass classification. In addition, electrode positions were optimized using neural activity areas under high-stress conditions, thereby reducing computational costs by minimizing the number of critical electrodes. MuLHiTA was evaluated across one private [Montreal imaging stress task (MIST)] and two publicly available EEG datasets [EEG during mental arithmetic tasks (DMAT) and Simultaneous task EEG workload (STEW)]. These were divided into training and test sets using an 8:2 ratio, and the training data were further divided into training and validation sets using a fivefold cross-validation (CV) method, in which the model with the highest accuracy among the five was selected. The model was trained once more with the full training set, and the test data were then used to evaluate its performance. This approach achieved average classification accuracies of 93.58%, 91.80%, and 99.71% for the MIST, STEW, and DMAT datasets, respectively. Experimental results showed MuLHiTA was superior to state-of-the-art algorithms, including EEGNet, BLSTM, EEGLearn, convolutional neural network (CNN)-long short-term memory (LSTM), and convolutional recurrent attention model (CRAM), for multiclass classification. This demonstrates the viability of MuLHiTA for the early detection of mental stress.

Two-Branch Attention Network via Efficient Semantic Coupling for One-Shot Learning.

Over the past few years, Convolutional Neural Networks (CNNs) have achieved remarkable advancement for the tasks of one-shot image classification. However, the lack of effective attention modeling has limited its performance. In this paper, we propose a Two-branch (Content-aware and Position-aware) Attention (CPA) Network via an Efficient Semantic Coupling module for attention modeling. Specifically, we harness content-aware attention to model the characteristic features (e.g., color, shape, texture) as well as position-aware attention to model the spatial position weights. In addition, we exploit support images to improve the learning of attention for the query images. Similarly, we also use query images to enhance the attention model of the support set. Furthermore, we design a local-global optimizing framework that further improves the recognition accuracy. The extensive experiments on four common datasets (miniImageNet, tieredImageNet, CUB-200-2011, CIFAR-FS) with three popular networks (DPGN, RelationNet and IFSL) demonstrate that our devised CPA module equipped with local-global Two-stream framework (CPAT) can achieve state-of-the-art performance, with a significant improvement in accuracy of 3.16% on CUB-200-2011 in particular.

Multi-representation adaptation network for cross-domain image classification.

In image classification, it is often expensive and time-consuming to acquire sufficient labels. To solve this problem, domain adaptation often provides an attractive option given a large amount of labeled data from a similar nature but different domains. Existing approaches mainly align the distributions of representations extracted by a single structure and the representations may only contain partial information, e.g., only contain part of the saturation, brightness, and hue information. Along this line, we propose Multi-Representation Adaptation which can dramatically improve the classification accuracy for cross-domain image classification and specially aims to align the distributions of multiple representations extracted by a hybrid structure named Inception Adaptation Module (IAM). Based on this, we present Multi-Representation Adaptation Network (MRAN) to accomplish the cross-domain image classification task via multi-representation alignment which can capture the information from different aspects. In addition, we extend Maximum Mean Discrepancy (MMD) to compute the adaptation loss. Our approach can be easily implemented by extending most feed-forward models with IAM, and the network can be trained efficiently via back-propagation. Experiments conducted on three benchmark image datasets demonstrate the effectiveness of MRAN.

Formal modeling and verification of fractional order linear systems.

This paper presents a formalization of a fractional order linear system in a higher-order logic (HOL) theorem proving system. Based on the formalization of the Grünwald-Letnikov (GL) definition, we formally specify and verify the linear and superposition properties of fractional order systems. The proof provides a rigor and solid underpinnings for verifying concrete fractional order linear control systems. Our implementation in HOL demonstrates the effectiveness of our approach in practical applications.

Increase of circulating cholesterol in vitamin D deficiency is linked to reduced vitamin D receptor activity via the Insig-2/SREBP-2 pathway.

SCOPE: Individuals deficient in vitamin D are more likely to have higher circulating cholesterol levels and cardiovascular diseases. However, the underlying mechanisms are still unclear. METHODS AND RESULTS: A cross-sectional survey, animal study, and in vitro experiments were conducted to investigate the effect and mechanisms of vitamin D deficiency on endogenous cholesterol metabolism. We demonstrated that vitamin D deficiency was positively associated with an increase of total serum cholesterol and low-density lipoprotein cholesterol levels in northern Chinese individuals. The vitamin D deficiency-induced increase of cholesterol concentration was mainly due to enhanced cholesterol biosynthesis rather than reduced catabolism. Under vitamin D deficiency, the transcriptional activity of vitamin D receptor (VDR) was decreased, leading to the downregulation of insulin-induced gene-2 (Insig-2) expression and thus its inhibitory role on sterol regulatory element-binding protein 2 activation; 3-hydroxy-3-methylglutaryl-coenzyme A reductase expression was accordingly increased. Vitamin D3 was protective against vitamin D deficiency-induced cholesterol increase by maintaining the transcriptional activity of VDR and Insig-2 expression. CONCLUSION: Vitamin D deficiency is associated with the increase of circulating cholesterol in the people of northern China by enhancing hepatic cholesterol biosynthesis, which was linked to the reduction of transcriptional activity of VDR.

Ursolic acid increases energy expenditure through enhancing free fatty acid uptake and ß-oxidation via an UCP3/AMPK-dependent pathway in skeletal muscle.

SCOPE: Ursolic acid (UA) is a triterpenoid compound with multifold biological functions. Our previous studies have reported that UA protects against high-fat diet-induced obesity and improves insulin resistance (IR). However, the potential mechanisms are still undefined. Free fatty acid (FFA) metabolism in skeletal muscle plays a central role in obesity and IR. Therefore, in this study, we investigated the effect and the potential mechanisms of UA on skeletal muscle FFA metabolism. METHODS AND RESULTS: In diet-induced obese rats, 0.5% UA supplementation for 6 weeks markedly reduced body weight, increased energy expenditure, decreased FFA level in serum and skeletal muscle and triglyceride content in skeletal muscle. In vitro, the data provided directly evidence that UA significantly increased fluorescently labeled FFA uptake and (3) H-labeled palmitic acid ß-oxidation. UA-activated AMP-activated protein kinase (AMPK) and downstream targets were involved in the increase of FFA catabolism. Moreover, upregulated uncoupling protein 3 (UCP3) by UA contributed to AMPK activation via elevating adenosine monophosphate/adenosine triphosphate ratio. CONCLUSION: UA increases FFA burning through enhancing skeletal muscle FFA uptake and ß-oxidation via an UCP3/AMPK-dependent pathway, which provides a novel perspective on the biological function of UA against obesity and IR.

A high-throughput metabolomic approach to explore the regulatory effect of mangiferin on metabolic network disturbances of hyperlipidemia rats.

This paper was designed to study metabolomic characters of the high-fat diet (HFD)-induced hyperlipidemia and the intervention effects of Mangiferin (MG). In this study, we aimed to investigate the intervention of MG on rats with hyperlipidemia induced by HFD and explore the possible mechanisms of hyperlipidemia. Urine metabolic profiles were analyzed using ultra-performance liquid chromatography/electrospray ionization quadruple time-of-flight mass spectrometry (UPLC-ESI-QTOF-MS) coupled with the principal component analysis (PCA) and partial least squares-discriminate analysis (PLS-DA) models, Heatmap and metabolism pathway analysis. PCA was applied to study the trajectory of the urinary metabolic phenotype of hyperlipidemia rat after administration of MG. The VIP-plot of orthogonal PLS-DA was used for discovering potential biomarkers to clarify the mechanism of MG. Biochemical analyses indicate that MG can alleviate the hyperlipidemia damage. Twenty significantly changed metabolites (potential biomarkers) were found to be reasonable in explaining the action mechanism of MG. The effectiveness of MG on hyperlipidemia is proved using the established metabolomic method and the regulated metabolic pathways involve the TCA cycle, taurine and hypotaurine metabolism, glyoxylate and dicarboxylate metabolism, glycine and serine and threonine metabolism, glycerophospholipid metabolism, primary bile acid biosynthesis etc. The results indicated that MG has a favourable protective effect on HFD-induced hyperlipidemia by adjusting the metabolic disorders. It also suggests that the metabolomic technology is a powerful approach for elucidation of the action mechanisms of MG.

A computational model for feature binding.

The "Binding Problem" is an important problem across many disciplines, including psychology, neuroscience, computational modeling, and even philosophy. In this work, we proposed a novel computational model, Bayesian Linking Field Model, for feature binding in visual perception, by combining the idea of noisy neuron model, Bayesian method, Linking Field Network and competitive mechanism. Simulation Experiments demonstrated that our model perfectly fulfilled the task of feature binding in visual perception and provided us some enlightening idea for future research.