Bilateral Filtering Graph Convolutional Network for Multi-relational Social Recommendation in the Power-law Networks

In recent years, advances in Graph Convolutional Networks (GCNs) have given new insights into the development of social recommendation. However, many existing GCN-based social recommendation methods often directly apply GCN to capture user-item and user-user interactions, which probably have two main limitations: (a) Due to the power-law property of the degree distribution, the vanilla GCN with static normalized adjacency matrix has limitations in learning node representations, especially for the long-tail nodes; (b) multi-typed social relationships between users that are ubiquitous in the real world are rarely considered. In this article, we propose a novel Bilateral Filtering Heterogeneous Attention Network (BFHAN), which improves long-tail node representations and leverages multi-typed social relationships between user nodes. First, we propose a novel graph convolutional filter for the user-item bipartite network and extend it to the user-user homogeneous network. Further, we theoretically analyze the correlation between the convergence values of different graph convolutional filters and node degrees after stacking multiple layers. Second, we model multi-relational social interactions between users as the multiplex network and further propose a multiplex attention network to capture distinctive inter-layer influences for user representations. Last but not least, the experimental results demonstrate that our proposed method outperforms several state-of-the-art GCN-based methods for social recommendation tasks.

Neuroprotective Effect of Monosialotetrahexosylganglioside (GM1) on Patients with Parkinson’s Disease Anesthetized by Ketamine under Denoising Algorithm-Based Ultrasound Image Diagnosis

This study was to investigate the value of ultrasound technology based on the bilateral filtering noise elimination algorithm in evaluating the neuroprotective effect of monosialoganglioside in ketamine-anesthetized Parkinson’s disease patients. The research subjects were 75 patients with Parkinson’s disease admitted to the hospital. The patients were randomly divided into three groups according to different treatment methods: A (GM1 + ketamine anesthesia group), B (conventional treatment + ketamine anesthesia group), and C (GM1 + nonketamine anesthesia group), with 25 patients in each group. Twenty-five healthy people with similar general data in the three groups (groups A, B, and C) were also selected as the control group (group D). All patients underwent ultrasonography, and ultrasound images were processed using the bilateral filter noise elimination. Structural similarity (SSIM), mean absolute error (MAE), and peak signal to noise ratio (PSNR) were used to evaluate the treatment effect. Plasma phospholipids, the third part of the PD unified score scale, Montreal cognitive assessment scale, and other indicators were analyzed and compared among the four groups. The bilateral filtering image noise was effectively suppressed, and the edge details were kept well. Some of the weak edges and texture information in the image were eliminated, the visual effect was ideal, and the accuracy of the edges of the picture remained good. The serotonin lipid level in group A was greatly lower than the serum phospholipid level in group B after GM1 treatment (6.55 VS 7.84, P < 0.05 ). Compared with that before treatment, the serotonin lipid level of group A patients decreased after the treatment, and the difference was considerable (7.46 VS 6.55, P < 0.05 ). In short, GM1 had a protective effect on the nerves of patients with Parkinson’s disease anesthetized by ketamine.

An Image Preprocessing Model of Coal and Gangue in High Dust and Low Light Conditions Based on the Joint Enhancement Algorithm

The lighting facilities are affected due to conditions of coal mine in high dust pollution, which bring problems of dim, shadow, or reflection to coal and gangue images, and make it difficult to identify coal and gangue from background. To solve these problems, a preprocessing model for low-quality images of coal and gangue is proposed based on a joint enhancement algorithm in this paper. Firstly, the characteristics of coal and gangue images are analyzed in detail, and the improvement ways are put forward. Secondly, the image preprocessing flow of coal and gangue is established based on local features. Finally, a joint image enhancement algorithm is proposed based on bilateral filtering. In experimental, K-means clustering segmentation is used to compare the segmentation results of different preprocessing methods with information entropy and structural similarity. Through the simulation experiments for six scenes, the results show that the proposed preprocessing model can effectively reduce noise, improve overall brightness and contrast, and enhance image details. At the same time, it has a better segmentation effect. All of these can provide a better basis for target recognition.

An Empirical Study on the Artificial Intelligence-Aided Quantitative Design of Art Images

This paper presents an indepth analysis and research on the quantitative design of fine art images through artificial intelligence algorithms. A CycleGAN-based network model for automatic generation of sketches of fine art images is constructed to extract the edge and contour features of fine art images. The network uses 512 × 1024 high-resolution art images as input and Pitchman as a discriminator. To further enhance the sketch generation effect, a bilateral filtering algorithm is added to the generator model for noise reduction, and then a K -means algorithm is used for color quantization to solve the problem of cluttered lines in the generated sketches. The experimental results show that the network model can effectively realize the automatic generation of art image sketches and can retain the detailed part of the costume information well. A rendering platform is built to realize the application of art image generation algorithms and coloring algorithms. The platform integrates the functions of image preprocessing, sketch generation, and sketch coloring, demonstrates the results of the main research content of this paper, and finally increases the interest of the system through the rendering function of the art image grid, which further improves the practicality of the platform.

Noise Removal Algorithm for Out-of-focus Blurred Images Based on Bilateral Filtering

The feature resolution of traditional methods for fuzzy image denoising is low, for the sake of improve the strepitus removal and investigation ability of defocused blurred night images, a strepitus removal algorithm based on bilateral filtering is suggested. The method include the following steps of: Building an out-of-focus blurred night scene image acquisition model with grid block feature matching of the out-of-focus blurred night scene image; Carrying out information enhancement processing of the out-of-focus blurred night scene image by adopting a high-resolution image detail feature enhancement technology; Collecting edge contour feature quantity of the out-of-focus blurred night scene image; Carrying out grid block feature matching design of the out-of-focus blurred night scene image by adopting a bilateral filtering information reconstruction technology; And building the gray-level histogram information location model of the out-of-focus blurred night scene image. Fuzzy pixel information fusion investigation method is used to collect gray features of defocused blurred night images. According to the feature collection results, bilateral filtering algorithm is used to automatically optimize the strepitus removal of defocused blurred night images. The simulation results show that the out-of-focus blurred night scene image using this method for machine learning has better strepitus removal performance, shorter time cost and higher export peak signal-to-strepitus proportion.

Evaluation of left ventricular diastolic function of patients with coronary heart disease by ultrasound images on bilateral filtering image noise reduction algorithm combined with electrocardiogram

Objective: To explore the evaluation of left ventricular diastolic function (LVDF) in patients with coronary heart disease (CHD) using ultrasound images (UI) combined with electrocardiogram (ECG) on bilateral filtering image noise reduction algorithm (BFINRA). Methods: A BFINRA was constructed, and 60 subjects who were investigated were divided into a control group (CG) from June 2019 to November 2019 in Taizhou People’s Hospital, a myocardial infarction group (MIG), and an angina pectoris group (APG). The patient’s LVDF was examined by two-dimensional electrophoresis (2DE) and real-time three-dimensional echocardiography (RT-3DE) combined with ECG. The results showed BFINRA could improve UI quality. Results: Clinical data indicated there were no substantial differences in age, gender, and fasting blood glucose of all subjects. 2DE examination results showed the left ventricular end-diastolic volume (LVEDV), left ventricular end-systolic volume (LVESV), and early diastolic mitral blood flow velocity / early diastolic mitral annulus velocity (E/E’) of MIG were much higher than CG (P<0.05), while the left ventricular ejection fraction (LVEF), E / late diastolic mitral blood flow velocity (E/A) and E’ peak value were sharply decreased (P<0.05);LVESV and E/E’ of APG were increased dramatically (P<0.05), while E peak, E/A and E’ peak were decreased greatly. RT-3DE examination results indicated LVEDV and LVESV of MIG were considerably higher than CG (P<0.05), while LVEF and macrophage resistance factor (MRF) were enormously decreased (P<0.05);LVEDV and LVESV of APG were greatly increased (P<0.05). However, LVEF and MRF were not changed significantly (P>0.05). LVEDV had a remarkable difference (P<0.05), but LVESV and LVEF had no obvious differences (P>0.05). The electrocardiogram results illustrated the increase in QT dispersion (QTd) of MIG and APG was statistically significant (P<0.05) compared with CG, while the negative increase of P-wave terminal force in lead V1 (PTFV1) also had a statistical significance (P<0.05). Correlation analysis revealed that MRF and PTFV1 had positive correlation, while MRF and QTd showed a negative correlation. Conclusion: The combination of UI and ECG could better assess LVDF in CHD patients. doi: https://doi.org/10.12669/pjms.37.6-WIT.4886 How to cite this:Li W. Evaluation of left ventricular diastolic function of patients with coronary heart disease by ultrasound images on bilateral filtering image noise reduction algorithm combined with electrocardiogram. Pak J Med Sci. 2021;37(6):1699-1704. doi: https://doi.org/10.12669/pjms.37.6-WIT.4886 This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Wavelet Bilateral Filter Algorithm-Based High-Frequency Ultrasound Image Analysis on Effects of Skin Scar Repair

It aimed to explore the application value of high-frequency ultrasound image based on the wavelet bilateral filtering algorithm in the repair evaluation of hypertrophic scar and keloid, as well as the expression change of nerve growth factor (NGF). 72 patients with scars admitted to hospital from October 2018 to October 2019 were chosen and classified as hypertrophic scar patients (group A) and keloid patients (group B), with 36 cases in each group. All patients received scar repair treatment, and another 30 normal skin volunteers (group C) were selected. High-frequency ultrasound images based on the wavelet bilateral filter algorithm were utilized for skin examination. The expression differences of NGF and pro-NGF in each group were measured by immunohistochemical staining and Western blot. The results showed that the denoising effect (signal-to-noise ratio (PSNR) = 33.2762), structural similarity (SSIM = 0.8963), and edge similarity (FoM = 0.2975) of the proposed algorithm were better than those of bilateral filtering and wavelet soft-threshold algorithms. The skin thickness of groups A and B was considerably higher relative to that of group C ( P < 0.05), but the echo intensity of the skin dermis of groups A and B was evidently inferior to that of group C ( P < 0.05). The results of immunohistochemistry showed that in contrast to group C, the average optical density of NGF in groups A and B increased remarkably ( P < 0.01). In contrast to group C, the positive expression of pro-NGF in groups A and B was notably reduced ( P < 0.05). Western blot results showed that relative to group C, the expression of NGF protein in groups A and B was increased greatly ( P < 0.01), but the expression of pro-NGF protein in groups A and B was reduced ( P < 0.01). The results suggested that the wavelet bilateral filter algorithm can be adopted to evaluate pathological skin scars, and pathological skin scar formation was closely related to the expression levels of NGF and pro-NGF.

A Novel Defensive Strategy for Facial Manipulation Detection Combining Bilateral Filtering and Joint Adversarial Training

Facial manipulation enables facial expressions to be tampered with or facial identities to be replaced in videos. The fake videos are so realistic that they are even difficult for human eyes to distinguish. This poses a great threat to social and public information security. A number of facial manipulation detectors have been proposed to address this threat. However, previous studies have shown that the accuracy of these detectors is sensitive to adversarial examples. The existing defense methods are very limited in terms of applicable scenes and defense effects. This paper proposes a new defense strategy for facial manipulation detectors, which combines a passive defense method, bilateral filtering, and a proactive defense method, joint adversarial training, to mitigate the vulnerability of facial manipulation detectors against adversarial examples. The bilateral filtering method is applied in the preprocessing stage of the model without any modification to denoise the input adversarial examples. The joint adversarial training starts from the training stage of the model, which mixes various adversarial examples and original examples to train the model. The introduction of joint adversarial training can train a model that defends against multiple adversarial attacks. The experimental results show that the proposed defense strategy positively helps facial manipulation detectors counter adversarial examples.