Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 3 de 3
Filter
Add more filters










Database
Language
Publication year range
1.
Sensors (Basel) ; 23(3)2023 Jan 28.
Article in English | MEDLINE | ID: mdl-36772522

ABSTRACT

In the task of text sentiment analysis, the main problem that we face is that the traditional word vectors represent lack of polysemy, the Recurrent Neural Network cannot be trained in parallel, and the classification accuracy is not high. We propose a sentiment classification model based on the proposed Sliced Bidirectional Gated Recurrent Unit (Sliced Bi-GRU), Multi-head Self-Attention mechanism, and Bidirectional Encoder Representations from Transformers embedding. First, the word vector representation obtained by the BERT pre-trained language model is used as the embedding layer of the neural network. Then the input sequence is sliced into subsequences of equal length. And the Bi-sequence Gated Recurrent Unit is applied to extract the subsequent feature information. The relationship between words is learned sequentially via the Multi-head Self-attention mechanism. Finally, the emotional tendency of the text is output by the Softmax function. Experiments show that the classification accuracy of this model on the Yelp 2015 dataset and the Amazon dataset is 74.37% and 62.57%, respectively. And the training speed of the model is better than most existing models, which verifies the effectiveness of the model.

2.
J Healthc Eng ; 2021: 4222881, 2021.
Article in English | MEDLINE | ID: mdl-34531965

ABSTRACT

At present, cardiovascular disease is regarded as one of the dangerous diseases that threaten human life. The morbidity and lethality caused by cardiovascular disease are constantly increasing every year. In this paper, we propose a two-stream style operation to handle the electrocardiogram (ECG) classification: one for time-domain features and another for frequency-domain features. For the time-domain features, convolutional neural networks (CNN) are constructed for feature learning and classification of ECG signals. For the frequency-domain features, support vector regression (SVR) machines are designed to perform the regression prediction on each signal. Finally, the D-S evidence theory is adopted to perform the decision fusion strategy on the time-domain and frequency-domain classification results. We confirm a recognition performance of 99.64% from the experiment result for the D-S evidence theory recognition system upon the MIT-BIH arrhythmia database. The analysis of various methods of ECG classification shows that the model delivers superior performance promotion across all these scenarios.


Subject(s)
Algorithms , Electrocardiography , Arrhythmias, Cardiac , Humans , Neural Networks, Computer , Signal Processing, Computer-Assisted , Support Vector Machine
3.
Clin Invest Med ; 33(2): E117, 2010 Apr 01.
Article in English | MEDLINE | ID: mdl-20370991

ABSTRACT

BACKGROUND: Damage to the intestinal barrier often occurs following severe trauma. It has been reported that enteral nutrition with dietary fiber (DF) could mitigate impairment of the intestinal barrier and might therefore be effective in clinical application; however, the conclusions from existing trials are controversial and the nature of the protective mechanism is far from clear. This study investigated the protective mechanism of dietary fiber on intestinal barrier in rats under bilateral closed femur fracture. METHODS: Twenty-four Sprague-Dawley rats were divided into four groups: normal control without any manipulation, trauma control with normal feeding, DF and dietary fiber-free (NF) groups fed with Nutrison Fibre and Nutrison, respectively. The later two groups were further divided into 1, 4, 7 and 10 days post-trauma groups. RESULTS: The trauma caused body weight decline, promoted bacterial translocation, and decreased immune function. The levels of portal vein endoxin in DF group was significantly lower than in NF group (p=0.013). Levers of both serum TNF-alpha and IL-6 on post-trauma day 10 showed no statistical differences between DF and NF groups. The incidence of bacterial translocation recovered to normal in DF group. Only secreted immunoglobulin a (sIgA) levels in DF group was higher than in NF group (p=0.005). CONCLUSION: Early enteral nutrition with dietary fiber could alleviate damage to intestinal barrier function and decreased the incidence of bacterial translocation caused by trauma and endotoxemia in rats under extra-abdominal trauma.


Subject(s)
Dietary Fiber/therapeutic use , Intestinal Diseases/prevention & control , Intestinal Diseases/physiopathology , Intestines/physiopathology , Wounds and Injuries/complications , Animals , Bacterial Translocation/drug effects , Body Weight , Dietary Fiber/administration & dosage , Dietary Fiber/pharmacology , Endotoxins/blood , Femoral Fractures/blood , Femoral Fractures/complications , Femoral Fractures/metabolism , Femoral Fractures/physiopathology , Immunoglobulin A, Secretory/metabolism , Interleukin-6/blood , Intestinal Diseases/etiology , Intestinal Diseases/metabolism , Intestinal Mucosa/metabolism , Intestines/drug effects , Liver/microbiology , Lymph Nodes/microbiology , Male , Mucins/metabolism , Permeability/drug effects , Rats , Rats, Sprague-Dawley , Tumor Necrosis Factor-alpha/blood , Wounds and Injuries/blood , Wounds and Injuries/metabolism , Wounds and Injuries/physiopathology
SELECTION OF CITATIONS
SEARCH DETAIL
...