Identifying autism spectrum disorder from multi-modal data with privacy-preserving.

The application of deep learning models to precision medical diagnosis often requires the aggregation of large amounts of medical data to effectively train high-quality models. However, data privacy protection mechanisms make it difficult to perform medical data collection from different medical institutions. In autism spectrum disorder (ASD) diagnosis, automatic diagnosis using multimodal information from heterogeneous data has not yet achieved satisfactory performance.

Attention-Based Temporal Graph Representation Learning for EEG-Based Emotion Recognition.

Due to the objectivity of emotional expression in the central nervous system, EEG-based emotion recognition can effectively reflect humans' internal emotional states. In recent years, convolutional neural networks (CNNs) and recurrent neural networks (RNNs) have made significant strides in extracting local features and temporal dependencies from EEG signals. However, CNNs ignore spatial distribution information from EEG electrodes; moreover, RNNs may encounter issues such as exploding/vanishing gradients and high time consumption.

An adaptive weighted ensemble learning network for diabetic retinopathy classification.

Diabetic retinopathy (DR) is one of the leading causes of blindness. However, because the data distribution of classes is not always balanced, it is challenging for automated early DR detection using deep learning techniques. In this paper, we propose an adaptive weighted ensemble learning method for DR detection based on optical coherence tomography (OCT) images.

An Interpretable Deep Embedding Model for Few and Imbalanced Biomedical Data.

In healthcare, training examples are usually hard to obtain (e.g., cases of a rare disease), or the cost of labelling data is high.

EEG Emotion Recognition Based on Self-attention Dynamic Graph Neural Networks.

In recent years, due to the fundamental role played by the central nervous system in emotion expression, electroencephalogram (EEG) signals have emerged as the most robust signals for use in emotion recognition and inference. Current emotion recognition methods mainly employ deep learning technology to learn the spatial or temporal representation of each channel, then obtain complementary information from different EEG channels by adopting a multi-modal fusion strategy. However, emotional expression is usually accompanied by the dynamic spatio-temporal evolution of functional connections in the brain.

Unaligned Multimodal Sequences for Depression Assessment From Speech.

A growing area of mental health research pertains to how an individual's degree of depression might be automatically assessed through analyzing multimodal-based objective markers. However, when combined with machine learning, this research can be challenging due to the existence of unaligned multimodal sequences and the limited amount of annotated training data. In this paper, a novel cross-modal framework for automatic depression severity assessment is proposed.

A Comprehensive Review of Artificial Intelligence in Prevention and Treatment of COVID-19 Pandemic.

The unprecedented outbreak of the Corona Virus Disease 2019 (COVID-19) pandemic has seriously affected numerous countries in the world from various aspects such as education, economy, social security, public health, etc. Most governments have made great efforts to control the spread of COVID-19, e.g.

Emotion Recognition of Chinese Paintings at the Thirteenth National Exhibition of Fines Arts in China Based on Advanced Affective Computing.

Today, with the rapid development of economic level, people's esthetic requirements are also rising, they have a deeper emotional understanding of art, and the voice of their traditional art and culture is becoming higher. The study expects to explore the performance of advanced affective computing in the recognition and analysis of emotional features of Chinese paintings at the 13th National Exhibition of Fines Arts. Aiming at the problem of "semantic gap" in the emotion recognition task of images such as traditional Chinese painting, the study selects the AlexNet algorithm based on convolutional neural network (CNN), and further improves the AlexNet algorithm.

Combining a parallel 2D CNN with a self-attention Dilated Residual Network for CTC-based discrete speech emotion recognition.

A challenging issue in the field of the automatic recognition of emotion from speech is the efficient modelling of long temporal contexts. Moreover, when incorporating long-term temporal dependencies between features, recurrent neural network (RNN) architectures are typically employed by default. In this work, we aim to present an efficient deep neural network architecture incorporating Connectionist Temporal Classification (CTC) loss for discrete speech emotion recognition (SER).

Epidemiologic characteristics and influencing factors of cluster infection of COVID-19 in Jiangsu Province.

To understand the characteristics and influencing factors related to cluster infections in Jiangsu Province, China, we investigated case reports to explore transmission dynamics and influencing factors of scales of cluster infection. The effectiveness of interventions was assessed by changes in the time-dependent reproductive number (Rt). From 25th January to 29th February, Jiangsu Province reported a total of 134 clusters involving 617 cases.

Metabolic syndrome, hypertension, and hyperglycemia were positively associated with knee osteoarthritis, while dyslipidemia showed no association with knee osteoarthritis.

Objective: Metabolic syndrome (MetS) is a clustering of at least three of the following four medical conditions: obesity, hypertension, dyslipidemia, and hyperglycemia. We aimed to discover the relationships between these diseases and osteoarthritis (OA) of the knee.

Methods: We searched four databases (EMBASE, PubMed, Cochrane Library, and MEDLINE), as well as articles on websites and conference materials.

Classification of Lung Nodules Based on Deep Residual Networks and Migration Learning.

The classification process of lung nodule detection in a traditional computer-aided detection (CAD) system is complex, and the classification result is heavily dependent on the performance of each step in lung nodule detection, causing low classification accuracy and high false positive rate. In order to alleviate these issues, a lung nodule classification method based on a deep residual network is proposed. Abandoning traditional image processing methods and taking the 50-layer ResNet network structure as the initial model, the deep residual network is constructed by combining residual learning and migration learning.

End-to-End Automatic Pronunciation Error Detection Based on Improved Hybrid CTC/Attention Architecture.

Advanced automatic pronunciation error detection (APED) algorithms are usually based on state-of-the-art automatic speech recognition (ASR) techniques. With the development of deep learning technology, end-to-end ASR technology has gradually matured and achieved positive practical results, which provides us with a new opportunity to update the APED algorithm. We first constructed an end-to-end ASR system based on the hybrid connectionist temporal classification and attention (CTC/attention) architecture.

HNGF6A Inhibits Oxidative Stress-Induced MC3T3-E1 Cell Apoptosis and Osteoblast Phenotype Inhibition by Targeting Circ_0001843/miR-214 Pathway.

Humanin (HN), a mitochondrial derived peptide, plays cyto-protective role under various stress. In this study, we aimed to investigate the effects of HNGF6A, an analogue of HN, on osteoblast apoptosis and differentiation and the underlying mechanisms. Cell proliferation of murine osteoblastic cell line MC3TC-E1 was examined by CCK8 assay and Edu staining.

Wavelet-based method for removing global physiological noise in functional near-infrared spectroscopy.

Functional near-infrared spectroscopy (fNIRS) is a fast-developing non-invasive functional brain imaging technology widely used in cognitive neuroscience, clinical research and neural engineering. However, it is a challenge to effectively remove the global physiological noise in the fNIRS signal. The global physiological noise in fNIRS arises from multiple physiological origins in both superficial tissues and the brain.

Tricycloalternarene Analogs from a Symbiotic Fungus Aspergillus sp. D and Their Antimicrobial and Cytotoxic Effects.

Bioassay-guided fractionation of the crude extract of fermentation broth of one symbiotic strain sp. D from the coastal plant Lindl. led to isolation of one new meroterpenoid, tricycloalternarene 14b (), together with four known analogs (-), tricycloalternarenes 2b (), 3a (), 3b (), and ACTG-toxin F ().

Cytotoxic Natural Products from Marine Sponge-Derived Microorganisms.

A growing body of evidence indicates that marine sponge-derived microbes possess the potential ability to make prolific natural products with therapeutic effects. This review for the first time provides a comprehensive overview of new cytotoxic agents from these marine microbes over the last 62 years from 1955 to 2016, which are assorted into seven types: terpenes, alkaloids, peptides, aromatics, lactones, steroids, and miscellaneous compounds.

[Experimental study of osteogenic induction of fetal mouse liver mesenchymal stem cells in vitro and their biologic attachment properties to true bone ceramic].

Objective: To study the culture and purification of the fetal mouse liver mesenchymal stem cells (MSCs) in vitro and to investigate their differentiation potential and the composite ability with true bone ceramic(TBC).

Methods: The single cell suspension of MSCs was primarily cultured and passaged, which was prepared from the fetal mouse liver; the flow cytometry was applied to detect CD29, CD34, CD44 and CD45. The osteogenic differentiation was induced in chemical inducing system; the osteogenic induction potency was tested.

[Analysis of the different effects of murine bone marrow endothelial cell conditioned medium on the growth of embryonic and adult hematopoietic stem/progenitor cells in vitro].

In the present study, the effects of murine bone marrow endothelial cell conditioned medium (mBMEC-CM) on the growth of yolk sac and bone marrow hematopoietic stem/progenitor cells (HSPC) were investigated. Nonadherent cells of yolk sac and bone marrow were collected for semisolid culture assay of CFU-GM and HPP-CFC after being cultured in DMEM with 10% FBS, 10% mBMEC-CM and/or FL (5 ng/ml), TPO (2 ng/ml) for 24 hours. The number of CFU-GM and HPP-CFC was counted by day 7 and 14 respectively.

[Osteogenic differentiation of murine yolk sac mesenchymal stem cells in vitro].

Objective: To investigate the potential of yolk sac mesenchymal stem cells in osteogenic differentiation.

Methods: Murine yolk sacs were harvested on day 8.5 postcoitus, yolk sac cells were obtained after the yolk sacs were digested by 0.

[Effects of murine bone marrow endothelial cell conditioned medium on the growth of yolk sac hematopoietic stem cells and progenitors].

Objective: To investigate the effects of murine bone marrow endothelial cell conditioned medium (mBMEC-CM) on the growth of yolk sac hematopoietic progenitors.

Methods: The serum-free mBMEC-CM was obtained from subcultures of murine endothelial cell line derived from bone marrow which was established in our laboratory. The murine yolk sacs were harvested on day 8.