Research on Node Classification Based on Joint Weighted Node Vectors

Node of network has lots of information, such as topology, text and label information. Therefore, node classification is an open issue. Recently, one vector of node is directly connected at the end of another vector. However, this method actually obtains the performance by extending dimensions and considering that the text and structural information are one-to-one, which is obviously unreasonable. Regarding this issue, a method by weighting vectors is proposed in this paper. Three methods, negative logarithm, modulus and sigmoid function are used to weight-trained vectors, then recombine the weighted vectors and put them into the SVM classifier for evaluation output. By comparing three different weighting methods, the results showed that using negative logarithm weighting achieved better results than the other two using modulus and sigmoid function weighting, and was superior to directly concatenating vectors in the same dimension.

Intervention study of finger-movement exercises and finger weight-lift training for improvement of handgrip strength among the very elderly

Objectives:To examine the effects of finger-movement exercises and finger weight-lift training on handgrip strength and Activities of Daily Living Scale(ADLS)values.Methods:A total of 80 very elderly adults(aged
80 years)were assigned to either an intervention group(n?40)or a control group(n?40).Subjects in the intervention group performed finger-movement exercises and weight-lift training for a period of 3 months,while subjects in the control group received no intervention,and were unaware of the interventions received in the other group.Results:After completing 3 months of finger-movement exercises and weight-lift training,the average handgrip strength of the 40 participants in the intervention group had increased by 2.1 kg,whereas that in the control group decreased by 0.27 kg(P<0.05).After receiving intervention,the number of subjects in the intervention group with an ADLS score>22 points decreased by 7.5%(P<0.05,vs.pre-intervention).Conclusions:The combined use interventionwith finger-movement exercises and proper finger weight-lift training improved the handgrip strength andADLS values of very elderly individuals.These rehabilitation exercisesmay be used to help the elderlymaintain their self-care abilities.

Regional cerebral blood flow imaging assessment of brain function reconstruction in elderly hemiplegia patients by body weight support treadmill training

The mechanism underlying body weight support treadmill training in elderly hemiplegic stroke patients is largely unknown. This study aimed to elucidate the changes of cortical blood flow in seven elderly patients with post-stroke hemiplegia before and after body weight support treadmill training by semi-quantitative analysis of regional cerebral blood flow assessed by single photon emission computed tomography. Body weight support treadmill training for 6 months was effective in improving cerebral blood flow and promoting the walking speed and balance recovery in elderly patients with post-stroke hemiplegia.

Effects of Water Weight-Loss Walking Training on Lower Limb Motor Function and Gait in Stroke Patients

Background: Water weight-loss walking training is an emerging physical therapy technique, which provides new ideas for improving the motor function of stroke patients and improving the quality of life of patients. However, the rehabilitation effect of water weight-loss training in stroke patients is currently unclear. Objective: To analyze the effect of water weight loss walking training in stroke patients. Methods: A total of 180 stroke patients admitted to our hospital from January 2019 to December 2021 were selected and randomly divided into two groups. The control group received routine walking training, and the research group performed weight loss walking training in water on this basis. The lower limb motor function, muscle tone grade, daily living ability, gait and balance ability were compared between the two groups before and after treatment. Results: Compared with the control group, the FMA-LE score (Fugl-Meyer motor assessment of Lower Extremity), MBI score (Modified Barthel Index) and BBS score (berg balance scale) of the study group were higher after treatment, and the muscle tone was lower (P Conclusion: Water weight loss walking training can enhance patients’ muscle tension, correct patients’ abnormal gait, improve patients’ balance and walking ability, and contribute to patients’ motor function recovery and self-care ability improvement.

Multitask Learning with Multiscale Residual Attention for Brain Tumor Segmentation and Classification

Automatic segmentation and classification of brain tumors are of great importance to clinical treatment.However,they are challenging due to the varied and small morphology of the tumors.In this paper,we propose a multitask multiscale residual attention network(MMRAN)to simultaneously solve the problem of accurately segmenting and classifying brain tumors.The proposed MMRAN is based on U-Net,and a parallel branch is added at the end of the encoder as the classification network.First,we propose a novel multiscale residual attention module(MRAM)that can aggregate contextual features and combine channel attention and spatial attention better and add it to the shared parameter layer of MMRAN.Second,we propose a method of dynamic weight training that can improve model performance while minimizing the need for multiple experiments to determine the optimal weights for each task.Finally,prior knowledge of brain tumors is added to the postprocessing of segmented images to further improve the segmentation accuracy.We evaluated MMRAN on a brain tumor data set containing meningioma,glioma,and pituitary tumors.In terms of segmentation performance,our method achieves Dice,Hausdorff distance(HD),mean intersection over union(MIoU),and mean pixel accuracy(MPA)values of 80.03%,6.649 mm,84.38%,and 89.41%,respectively.In terms of classification performance,our method achieves accuracy,recall,precision,and F1-score of 89.87%,90.44%,88.56%,and 89.49%,respectively.Compared with other networks,MMRAN performs better in segmentation and classification,which significantly aids medical professionals in brain tumor management.The code and data set are available at https://github.com/linkenfaqiu/MMRAN.