Search

Medical imaging refers to the process of obtaining images of internal organs for therapeutic purposes such as discovering or studying diseases. The primary objective of medical image analysis is to improve the efficacy of clinical research and treatment options. Deep learning has revamped medical image analysis, yielding excellent results in image processing tasks such as registration, segmentation, feature extraction, and classification. The prime motivations for this are the availability of computational resources and the resurgence of deep convolutional neural networks. Deep learning techniques are good at observing hidden patterns in images and supporting clinicians in achieving diagnostic perfection. It has proven to be the most effective method for organ segmentation, cancer detection, disease categorization, and computer-assisted diagnosis. Many deep learning approaches have been published to analyze medical images for various diagnostic purposes. In this paper, we review the work exploiting current state-of-the-art deep learning approaches in medical image processing. We begin the survey by providing a synopsis of research works in medical imaging based on convolutional neural networks. Second, we discuss popular pretrained models and general adversarial networks that aid in improving convolutional networks' performance. Finally, to ease direct evaluation, we compile the performance metrics of deep learning models focusing on COVID-19 detection and child bone age prediction. [ABSTRACT FROM AUTHOR]

Handmade is an important part of preschool education, which was aimed at improving children's ability to work with their hands. Preschool education is the most basic and important aspect of a country's educational system. As a result, individuals pursuing a degree in preschool education take on a lot of responsibility. The preschool education handmade course has become an important component of preschool education due to its practicality and creativity. Preschool education major offers classes in traditional crafts such as paper cutting, paper dyeing, origami, paper three-dimensional modeling, and ornamental painting. The teaching methods for custom-made preschool education courses are always evolving with the progress of society. The question of how to assess the efficacy of unique teaching methodologies for handmade courses has become crucial. This study employs artificial intelligence to create a neural network for assessing the creativity of teaching approaches for handmade courses in preschool education. The following is the specific work: Firstly, the idea, as well as the benefits and drawbacks of genetic algorithms, is investigated. To build an improved genetic algorithm (IGA), the chromosome encoding, fitness function, and three operation options are enhanced. Secondly, by improving the genetic algorithm, the selection of weights and thresholds in the BP neural network model is improved, and a combined model (IGA-BP) is created by integrating the improved genetic algorithm with the BP network. Finally, rigorous and systematic tests confirm the work's efficacy and viability. [ABSTRACT FROM AUTHOR]

Every year, various experiments emerge in which a strong link between topological chemical structures and their properties is found. These properties are numerous such as melting point, boiling point, and drug toxicity. Topological index is the functional tool to determine these properties. This research paper will analyze some of the molecular drug structures, i.e., hyaluronic acid-paclitaxel conjugates G n , anticancer drug SP n , polyomino chain of n -cycle Z n , triangular benzenoid T n , and circumcoronene benzenoid series H k using multicriteria decision-making techniques including TOPSIS and SAW. The topological indices used in this research paper include the Randić index for α = 1 , − 1 , 1 / 2 , the augmented Zagreb index and the forgotten topological index. [ABSTRACT FROM AUTHOR]

Congenital heart defect (CHD) refers to the overall structural abnormality of the heart or large blood vessels in the chest cavity. It is the most common type of fetal congenital defects. Prenatal diagnosis of congenital heart disease can improve the prognosis of the fetus to a certain extent. At present, prenatal diagnosis of CHD mainly uses 2D ultrasound to directly evaluate the development and function of fetal heart and main structures in the second trimester of pregnancy. Artificial recognition of fetal heart 2D ultrasound is a highly complex and tedious task, which requires a long period of prenatal training and practical experience. Compared with manual scanning, computer automatic identification and classification can significantly save time, ensure efficiency, and improve the accuracy of diagnosis. In this paper, an effective artificial intelligence recognition model is established by combining ultrasound images with artificial intelligence technology to assist ultrasound doctors in prenatal ultrasound fetal heart standard section recognition. The method data in this paper were obtained from the Second Affiliated Hospital of Fujian Medical University. The fetal apical four-chamber heart section, three vessel catheter section, three vessel trachea section, right ventricular outflow tract section, and left ventricular outflow tract section were collected at 20-24 weeks of gestation. 2687 image data were used for model establishment, and 673 image data were used for model validation. The experiment shows that the map value of this method in identifying different anatomical structures reaches 94.30%, the average accuracy rate reaches 94.60%, the average recall rate reaches 91.0%, and the average F1 coefficient reaches 93.40%. The experimental results show that this method can effectively identify the anatomical structures of different fetal heart sections and judge the standard sections according to these anatomical structures, which can provide an auxiliary diagnostic basis for ultrasound doctors to scan and lay a solid foundation for the diagnosis of congenital heart disease. [ABSTRACT FROM AUTHOR]

Traditional Chinese medicine (TCM) prescriptions have made great contributions to the treatment of diseases and health preservation. To alleviate the shortage of TCM resources and improve the professionalism of automatically generated prescriptions, this paper deeply explores the connection between symptoms and herbs through deep learning technology, and realizes the automatic generation of TCM prescriptions. Particularly, this paper considers the significance of referring to similar underlying prescriptions as herbal candidates in the TCM prescribing process. Moreover, this paper incorporates the idea of referring to the potential guidance information of corresponding prescriptions when model extracts symptoms representations. To provide a reference for inexperienced young TCM doctors when they prescribe, this paper proposes a dual-branch guidance strategy combined with candidate attention model (DGSCAM) to automatically generate TCM prescriptions based on symptoms text. The format of the data used this paper is the "symptoms-prescription" data pair. The specific method is as follows. First, DGSCAM realizes the extraction of key information of prescription-guided symptoms through a dual-branch network. Then, herbal candidates in the form of prescriptions that can treat symptoms are proposed in view of the compatibility knowledge of TCM prescriptions. To our knowledge, this is the first attempt to use prescriptions as herbal candidates in the prescription generation process. We conduct extensive experiments on a mixed public and clinical dataset, achieving 37.39% precision, 25.04% recall, and 29.99% F1 score, with an average doctor score of 7.7 out of 10. The experimental results show that our proposed model is valid and can generate more specialized TCM prescriptions than the baseline models. The DGSCAM developed by us has broad application scenarios and greatly promotes the research on intelligent TCM prescribing. [ABSTRACT FROM AUTHOR]

This paper discusses the imaging diagnostic features of arteriosclerotic encephalopathy and combines the spatial context information of local features to study the clinical imaging image copy detection algorithm. Moreover, this paper proposes a clinical imaging copy detection algorithm that combines the BOW model and spatial context embedding and a clinical imaging copy detection algorithm that combines the BOW model and global context verification. In addition, this paper applies the algorithm to the imaging diagnostic features of arteriosclerotic encephalopathy and sets up a controlled experiment to start research. The experimental research shows that the application of imaging diagnosis to the detection of subcortical arteriosclerotic encephalopathy has good clinical effects and rapid remission of patients' symptoms. The effectiveness of this method can be verified by a large number of clinical practices in follow-up studies. [ABSTRACT FROM AUTHOR]

In order to improve the prediction effect of sports training performance and improve the effect of sports training, this paper classifies the sports training image area, refines the image into different areas, finds suspicious areas, and completes the error prediction. Moreover, this paper calculates the regional similarity of sports training images in the fully connected layer of the convolutional neural network and introduces the local linear weighting method for analysis. In addition, this paper gives a certain weight to each prediction point near the area to be predicted and selects the suspicious area feature based on the multievaluation standard fusion method. Finally, this paper combines the convolutional neural network algorithm to construct a sports training performance prediction system to improve the effect of sports training and design experiments to verify the system proposed in this paper. From the experimental research results, we can see that the sports training performance prediction system based on the convolutional neural network proposed in this paper has good practical effects. [ABSTRACT FROM AUTHOR]

Volleyball is a sport of teamwork competition and tactical coordination. It tests the ability of team members to cooperate with each other and personal resilience. With the development of wireless communication networks, how to use wireless communication networks in the analysis of volleyball tactics is the subject of this article. To explore how to design the volleyball tactics analysis model of the wireless communication network, this paper proposes the method of LTE system and MIMO technology and designs the tactics analysis model based on the characteristics of the wireless network, then combined volleyball tactics and game theory to design a wireless communication network volleyball tactics analysis model. Then, this paper designs the simulation experiment of scene allocation problem, the algorithm simulation experiment, and the comparative investigation and analysis of volleyball game spiking technical ability. The results of the experiment are optimized for the tactical analysis model, and finally, the improvement of the training of the volleyball tactical analysis model based on the wireless communication network is verified through comparative experiments. The experimental results show that the team fit of the volleyball tactical analysis model training based on the wireless communication network has increased by 22.12% compared with the traditional volleyball tactical training. Compared with the traditional volleyball tactical training, the personal on-the-spot adaptability of the volleyball tactical analysis model training based on the wireless communication network has increased by 9.05%. [ABSTRACT FROM AUTHOR]

At present, lumbar disc herniation has become a problem that plagues people's health, life safety, and social and economic development. Among them, the research of lumbar disc nucleus pulposus tissue is the focus of the treatment of lumbar disc diseases. At present, the treatment methods of lumbar disc herniation are divided into conservative treatment and surgical treatment, among which surgical treatment can be divided into open surgery and minimally invasive surgery. Surgical treatment to remove the nucleus pulposus from the disc by fenestration includes conventional ablation of the nucleus pulposus and microscopic lumbar discs. This treatment is effective, but it has a great impact on the stabilization mechanism of the spine, with large soft tissue damage and large blood loss, which can easily cause nerve damage and postdural adhesions. At the same time, single-segment lumbar discectomy has also been gradually applied to the treatment of this disease. Under this, this paper studies single-segment lumbar disc nucleus pulposus resection. The lumbar nucleus resection is performed in a single segment in the physiological load area, which can greatly ensure the stability of the sagittal plane of the lumbar spine. In order to better understand the postoperative rehabilitation and clinical effects of single-segment lumbar discectomy, as well as the changes in the sagittal plane of the lumbar vertebrae before and after the operation, so as to provide a reference for further improving the quality of life of patients, this paper uses questionnaire survey and data analysis methods. According to the results of the questionnaire survey, compared with other operations, single-segment lumbar discectomy is more stable in the sagittal plane of the lumbar spine within the physiological load range, and there is less displacement. The displacement may be caused or influenced by different kinds of factors such as heavy loads or manual labor. In addition, most patients have less abnormal pain after surgery, indicating that the surgery has a certain effect on the treatment of the disease, and there are fewer abnormalities after surgery. [ABSTRACT FROM AUTHOR]

Background. Despite guidelines provided by the Brain Trauma Foundation (BTF) for treating patients with TBI, including advice to monitor intracranial pressure (ICP), the clinical application of ICP monitoring is far from universal. This laxity has been attributed to the relationship between mortality in TBI patients and ICP monitoring. Objective. This systematic review and meta-analysis was aimed at determining the effect of intracranial pressure (ICP) monitoring on the mortality of patients with traumatic brain injury (TBI). Method. A systematic search for articles was conducted on PubMed, Scopus, Cochrane Central Register of Control Trials (CENTRAL), and APA PsycNet for articles published from 1 January 2000 to 1 August 2022. Manager 5.4 was used to carry out statistical analysis. Results. Article search yielded 1421 articles, but only 23 cohort studies were included in the systematic review and meta-analysis. The total number of study participants is 80,058. Seventeen studies reported unadjusted odds ratios (OR), and only 8 reported the adjusted odds ratio (OR). Nine out of seventeen studies reported an unadjusted OR of less than 1, and five out of eight studies reported an adjusted OR of less than 1. From this paper's analysis, the OR for in-hospital mortality was 1.01 [95% CI, 0.80, 1.28], with a p value of 0.92. OR for ICU mortality was 0.84 [95% CI, 0.52, 1.35], with a p value of 0.47. Conclusion. But due to conflicting results, as evident above, it is unsatisfyingly challenging to draw any substantial conclusions from them. This paper thus calls for more research on this particular paper. [ABSTRACT FROM AUTHOR]

Aims. This paper aims to investigate the relationship of waist circumference (WC) with digestive tract cancer morbidity and mortality. Methods. Based on the data from a nationally representative US population survey, we summarized the prevalence of digestive tract cancer and all-cause mortality of cancer patients across WC quartiles. Adjusted logistic regression and restricted spline curve were used to analyze WC and the prevalence of digestive tract cancer. Moreover, Cox regression and the Kaplan-Meier curve were applied to investigate the association of WC with all-cause mortality. We also attempted to make a model to predict cancer happening. Results. This paper included a total of 34,041 participants, with digestive tract cancer observed in 265 (0.7%) individuals. WC was positively associated with digestive tract cancer morbidity after full adjustment of covariates (OR: 1.72 and 95% CI: 1.41-2.10). Also, individuals in the highest WC group had a higher risk of digestive tract cancer (Q4, OR: 2.71 and 95% CI: 1.48-5.00). Moreover, no significant association was observed in upper digestive cancer, and WC was associated with a longer survival time once diagnosed (hazard ratio (HR): 0.50 and 95% CI: 0.28-0.92). Finally, the model we made proved to be effective. Conclusion. High WC is a risk factor for digestive tract cancer with or without adjusting for body mass index, especially those located in the lower digestive tract. However, once digestive tract cancer has been diagnosed, patients with higher WC showed better survival outcomes. Moreover, machine learning methods can be used to predict digestive tract cancer risk in the future. [ABSTRACT FROM AUTHOR]

Background and Objective. Breast cancer is a common malignant tumor that seriously threatens the health of women in my country and even around the world. The proliferation marker Ki-67 has been utilized to distinguish luminal B from luminal A tumors and is a reliable indicator of more aggressive breast cancer growth. If a reliable prediction method for breast cancer patients to avoid invasive damage can be found to predict Ki-67 before pathological examination, it will be very beneficial for doctors to formulate later treatment plans and provide more useful treatment options. Methodology. This paper proposes a tumor segmentation and prediction framework based on the combination of improved attention U-Net and SVM. The framework first improves on attention U-Net by introducing coefficients for learning multidimensional attention. Make the attention mechanism more aware of the main situation in the segmentation process. At the same time, the segmented breast MRI results and corresponding labels were input into the SVM classifier to accurately predict the expression of Ki-67. Results. The DSC, PPV, and sensitivity of our combined model are 0.94, 0.93, and 0.94, respectively, with better segmentation performance. And we compare with the segmentation frameworks of other papers and find that our combined model can make accurate segmentation of breast tumors. Conclusion. Our method can adapt to the variability of breast tumors and segment breast tumors accurately and efficiently. In the future, it can be widely used in clinical practice, so as to help the clinic better formulate a reasonable diagnosis and treatment plan for breast cancer patients. [ABSTRACT FROM AUTHOR]

Falls in elderly patients are an important cause of fractures, functional impairment, and mortality. In this paper, a questionnaire was used to collect information on fall history, balance function and sensory function from patients over 65 years of age. In the analysis, the presence or absence of falls was used as a factor, and a corresponding prediction model was constructed using methods such as univariate analysis and regression analysis. This survey found that in the past year, 60% of the patients had fallen, 16.67% had one fall, 33.33% had two falls, and 50% had three or more falls; model specificity is 61.54%, the sensitivity is 71.43%, and the misjudgment is 38.46%. The model has good specificity and sensitivity and a small misjudgment rate; so, the model is more reasonable. This paper selects several sensitivity indices that have a certain impact on the risk of falling and makes a satisfactory forecast, which can provide a theoretical basis for the prevention of the risk of falls in elderly patients during hospitalization. [ABSTRACT FROM AUTHOR]

Compared with the traditional trading model, the problem of information asymmetry in export cross-border e-commerce (CBEC) transactions actually exists. Since the buyers and sellers of export CBEC are located in different countries, it is difficult for both parties to make accurate judgments on each other's credit. Besides, the number of export CBEC financing is relatively small, and the financing situation is not optimistic. Fortunately, the Internet of Things (IOT) technology has a wide range of applications and strong social penetration, especially in e-commerce, which can effectively improve payment, logistics, and distribution. By employing the concept of the IOT, this paper expounds the application of the IOT in the e-commerce transaction process and the impact of the IOT on the development of e-commerce. Besides, this paper also proposes some security issues in the application of the IOT in e-commerce. In addition, this paper analyzes the relationship and development trend of CBEC and IOT technology; meanwhile, it also points out the practical problems currently faced by combining the regional advantage of a certain region. The e-commerce industry develops IOT technology and drives innovation-driven development in the region. In addition, this paper builds an evaluation index system for the development of export CBEC enterprises based on the analysis of the problems and reasons by using the sample data to train the BP neural network and using the test samples to test the model. It is found that the model accuracy rate is 89.47%. Then, this paper also takes the export CBEC company A as an example to conduct empirical research and to prove the operability of the credit evaluation model. Finally, it provides relevant suggestions for improving the credit evaluation system of export CBEC enterprises. [ABSTRACT FROM AUTHOR]

The angle of progression (AoP) for assessing fetal head (FH) descent during labor is measured from the standard plane of transperineal ultrasound images as the angle between a line through the long axis of pubic symphysis (PS) and a second line from the right end of PS tangentially to the contour of the FH. This paper presents a multitask network with a shared feature encoder and three task-special decoders for standard plane recognition (Task1), image segmentation (Task2) of PS and FH, and endpoint detection (Task3) of PS. Based on the segmented FH and two endpoints of PS from standard plane images, we determined the right FH tangent point that passes through the right endpoint of PS and then computed the AoP using the above three points. In this paper, the efficient channel attention unit is introduced into the shared feature encoder for improving the robustness of layer region encoding, while an attention fusion module is used to promote cross-branch interaction between the encoder for Task2 and that for Task3, and a shape-constrained loss function is designed for enhancing the robustness to noise based on the convex shape-prior. We use Pearson's correlation coefficient and the Bland–Altman graph to assess the degree of agreement. The dataset includes 1964 images, where 919 images are nonstandard planes, and the other 1045 images are standard planes including PS and FH. We achieve a classification accuracy of 92.26%, and for the AoP calculation, an absolute mean (STD) value of the difference in AoP (∆ AoP) is 3.898° (3.192°), the Pearson's correlation coefficient between manual and automated AoP was 0.964 and the Bland-Altman plot demonstrates they were statistically significant (P < 0.05). In conclusion, our approach can achieve a fully automatic measurement of AoP with good efficiency and may help labor progress in the future. [ABSTRACT FROM AUTHOR]

Breast cancer is one of the most widespread and fatal cancers in women. At present, anticancer drug-inhibiting estrogen receptor α subtype (ER α) can greatly improve the cure rate for breast cancer patients, so the research and development of this kind of drugs are very urgent. In this paper, the problem of how to screen excellent anticancer drugs is abstracted as an optimization problem. Firstly, the graph model is used to extract low-dimensional features with strong distinguishing and describing ability according to various attributes of candidate compounds, and then, kernel functions are used to map these features to high-dimensional space. Then, the quantitative analysis model of ER α biological activity and the classification model based on ADMET properties of the support vector machine are constructed. Finally, sequential least square programming (SLSQP) is utilized to solve the ER α biological activity model. The experimental results show that for anticancer data sets, compared with principal component analysis (PCA), the error rate of the graph model constructed in this paper is reduced by 6.4%, 15%, and 7.8% on mean absolute error (MAE), mean squared error (MSE), and root mean square error (RMSE), respectively. In terms of classification prediction, compared with principal component analysis (PCA), the recall and precision rates of this method are enhanced by 19.5% and 12.41%, respectively. Finally, the optimal biological activity value (IC50_nM) 34.6 and inhibitory biological activity value (pIC50) 7.46 were obtained. [ABSTRACT FROM AUTHOR]

Due to the high transmission rate and high pathogenicity of the novel coronavirus (COVID-19), there is an urgent need for the diagnosis and treatment of outbreaks around the world. In order to diagnose quickly and accurately, an auxiliary diagnosis method is proposed for COVID-19 based on federated learning and blockchain, which can quickly and effectively enable collaborative model training among multiple medical institutions. It is beneficial to address data sharing difficulties and issues of privacy and security. This research mainly includes the following sectors: in order to address insufficient medical data and the data silos, this paper applies federated learning to COVID-19's medical diagnosis to achieve the transformation and refinement of big data values. With regard to third-party dependence, blockchain technology is introduced to protect sensitive information and safeguard the data rights of medical institutions. To ensure the model's validity and applicability, this paper simulates realistic situations based on a real COVID-19 dataset and analyses problems such as model iteration delays. Experimental results demonstrate that this method achieves a multiparty participation in training and a better data protection and would help medical personnel diagnose coronavirus disease more effectively. [ABSTRACT FROM AUTHOR]

Under the global pandemic of COVID-19, public health facilities, such as hospitals, are required to readjust, design, and plan a safe movement flow of people to meet the social distance rules and quarantine COVID-19 and the non-COVID-19 patients to prevent cross-infection. However, readjustments to separate patients have significantly reduced the maximum throughput of public health facilities, worsening already scarce public health resources. Therefore, this paper proposes throughput maximization algorithms based on the one-way street problem which meets the requirements of social distance rules. First, the floor plan of a hospital is transformed into a graph, each node is traversed by breadth-first search. Then, this paper considers patients' node pair sets as different set unions, the direction of edges, and the color of links based on DFS-XOR algorithm are designed to distinguish the paths of COVID-19 and non-COVID-19 patients. Finally, this paper utilizes minimum shared link algorithms to determine the minimized sharing links between paths linking different set unions and components. The throughput is maximized by reducing the number of shared links and alternating links. The results indicate that compared with the brute force algorithms, the algorithms proposed in this paper significantly improve the maximum throughput. [ABSTRACT FROM AUTHOR]

Background. Since the COVID-19 pandemic, social media has become an important arena for the public to transmit and exchange messages, feelings, opinions, and information about the epidemic. In the era of social media, many UGC contents from self-media and various information about the epidemic on social media have strong emotional colors. These contents are not only rich in resources for text sentiment analysis but also reveal the laws and characteristics of the evolution of users' emotional tendencies in public health emergencies. It even ties together the interaction between media content and society. Objective. As the Sina Weibo platform's characteristics of communication are real-time, open, and "many-to-many," the objective of this study is to collect Weibo-blog contents tagged with the outbreak of COVID-19 in a certain metropolis in China and analyze the emotional evolution situation of Weibo-blogs of the unexpected public health emergency involved. This will provide a dynamic understanding of the mechanisms underlying the evolution of emotional conditions in the context of public health emergencies. Methods. This paper uses a Python crawler, the SnowNLP sentiment analysis model, and correlation analysis to calculate the emotional tendencies of the event "Covid-19 outbreak in a Chinese metropolis" on the Sina Weibo platform. The study was carried out in terms of the evolutionary stages of the event and the factors which induce it. Results. This paper revealed characteristics of time-varying laws and dynamic propagation of users' emotional evolution in public health emergencies. (1) This study refers to the life cycle model of COVID-19, combined with the statistics of the time series of the quantities of Weibo-blog posting, and divides the law of the quantities of Weibo-blog posting changing with the event into three stages: outbreak period, stalemate period, and resolution period. (2) Users' emotional tendencies are changeable and unstable which are easily induced by various factors. (3) There is a significant positive correlation between the reported confirmed cases and the quantities of Weibo-blog posts. (4) Individual emotional tendencies will have a positive changing trend with the public's average emotional tendencies after the event occurs. (5) There is no correlation between reposts, comments, and Weibo-blog emotional tendencies. Conclusion. The research found that, given staged evolution and repeated fluctuations of emotional tendencies, relevant departments should effectively use this law and set up different response plans according to different stages. In addition, what is highly coupled with users' emotional tendencies is not only the information about the virus but more large-scale infected by different intensities of emotions. [ABSTRACT FROM AUTHOR]

Colorectal cancer has a high incidence rate in all countries around the world, and the survival rate of patients is improved by early detection. With the development of object detection technology based on deep learning, computer-aided diagnosis of colonoscopy medical images becomes a reality, which can effectively reduce the occurrence of missed diagnosis and misdiagnosis. In medical image recognition, the assumption that training samples follow independent identical distribution (IID) is the key to the high accuracy of deep learning. However, the classification of medical images is unbalanced in most cases. This paper proposes a new loss function named the double-balanced loss function for the deep learning model, to improve the impact of datasets on classification accuracy. It introduces the effects of sample size and sample difficulty to the loss calculation and deals with both sample size imbalance and sample difficulty imbalance. And it combines with deep learning to build the medical diagnosis model for colorectal cancer. Experimentally verified by three colorectal white-light endoscopic image datasets, the double-balanced loss function proposed in this paper has better performance on the imbalance classification problem of colorectal medical images. [ABSTRACT FROM AUTHOR]

The automatic segmentation method of MRI brain tumors uses computer technology to segment and label tumor areas and normal tissues, which plays an important role in assisting doctors in the clinical diagnosis and treatment of brain tumors. This paper proposed a multiresolution fusion MRI brain tumor segmentation algorithm based on improved inception U-Net named MRF-IUNet (multiresolution fusion inception U-Net). By replacing the original convolution modules in U-Net with the inception modules, the width and depth of the network are increased. The inception module connects convolution kernels of different sizes in parallel to obtain receptive fields of different sizes, which can extract features of different scales. In order to reduce the loss of detailed information during the downsampling process, atrous convolutions are introduced in the inception module to expand the receptive field. The multiresolution feature fusion modules are connected between the encoder and decoder of the proposed network to fuse the semantic features learned by the deeper layers and the spatial detail features learned by the early layers, which improves the recognition and segmentation of local detail features by the network and effectively improves the segmentation accuracy. The experimental results on the BraTS (the Multimodal Brain Tumor Segmentation Challenge) dataset show that the Dice similarity coefficient (DSC) obtained by the method in this paper is 0.94 for the enhanced tumor area, 0.83 for the whole tumor area, and 0.93 for the tumor core area. The segmentation accuracy has been improved. [ABSTRACT FROM AUTHOR]

Due to limitations of computer resources, when utilizing a neural network to process an image with a high resolution, the typical processing approach is to slice the original image. However, because of the influence of zero-padding in the edge component during the convolution process, the central part of the patch often has more accurate feature information than the edge part, resulting in image blocking artifacts after patch stitching. We studied this problem in this paper and proposed a fusion method that assigns a weight to each pixel in a patch using a truncated Gaussian function as the weighting function. In this method, we used the weighting function to transform the Euclidean-distance between a point in the overlapping part and the central point of the patch where the point was located into a weight coefficient. With increasing distance, the value of the weight coefficient decreased. Finally, the reconstructed image was obtained by weighting. We employed the bias correction model to evaluate our method on the simulated database BrainWeb and the real dataset HCP (Human Connectome Project). The results show that the proposed method is capable of effectively removing blocking artifacts and obtaining a smoother bias field. To verify the effectiveness of our algorithm, we employed a denoising model to test it on the IXI-Guys human dataset. Qualitative and quantitative evaluations of both models show that the fusion method proposed in this paper can effectively remove blocking artifacts and demonstrates superior performance compared to five commonly available and state-of-the-art fusion methods. [ABSTRACT FROM AUTHOR]

Diabetes mellitus is a common chronic noncommunicable disease, the main manifestation of which is the long-term high blood sugar level in patients due to metabolic disorders. However, due to excessive reliance on the clinical experience of ophthalmologists, our diagnosis takes a long time, and it is prone to missed diagnosis and misdiagnosis. In recent years, with the development of deep learning, its application in the auxiliary diagnosis of diabetic retinopathy has become possible. How to use the powerful feature extraction ability of deep learning algorithm to realize the mining of massive medical data is of great significance. Therefore, under the action of computer-aided technology, this paper processes and analyzes the retinal images of the fundus through traditional image processing and convolutional neural network-related methods, so as to achieve the role of assisting clinical treatment. Based on the admission records of diabetic patients after data analysis and feature processing, this paper uses an improved convolutional neural network algorithm to establish a model for predicting changes in diabetic conditions. The model can assist doctors to judge the patient's treatment effect by using it based on the case records of inpatient diagnosis and treatment and to predict the risk of readmission of inpatients after discharge. It also can help to judge the effectiveness of the treatment plan. The results of the study show that the model proposed in this paper has a lower probability of misjudging patients with poor recovery as good recovery, and the prediction is more accurate. [ABSTRACT FROM AUTHOR]

Medical colleges need to strengthen the cultivation of medical students' humanistic and spiritual literacy. First of all, schools need to change the current educational concept and the cultivation mode of humanistic quality. In educational work, schools should pay attention to the social cognitive skills of medical students, and at the same time pay attention to the cultivation of students' basic qualities. Schools need to find problems in time, and schools need to take corresponding measures to deal with these problems. Medical colleges need to strengthen the training of medical students' comprehensive quality and incorporate humanistic education into the goal of all-round development of medical students. Specifically, schools need to adopt a work method of distributed implementation and distributed guidance to fully mobilize the enthusiasm and initiative of school leaders, teachers, and students themselves. Schools need to strengthen inspection and supervision and summarize the experiences and lessons that students have learned in their learning. On this basis, schools need to improve the quality and efficiency of students' humanities education work. Through the analysis of multisource medical data, this paper conducts research on the working mode of humanistic quality cultivation in medical colleges. Specifically, school education will be people-centered. Schools need to cultivate the humanistic spirit of medical students in the ideological and political education work. This paper conducts mathematical statistical analysis based on multisource medical data and analyzes the differences in the effect of different teaching modes and training methods on the cultivation of medical students' humanistic spiritual literacy. Based on this, the research proposes recommendations for the future development of medical schools. First of all, schools need to build a humanized classroom, combine skills education with moral education, and improve the learning efficiency of student groups. In addition, schools need to teach students to feel respected and valued. Secondly, schools need to implement human-oriented teaching work to give full play to students' own talents and personalities. During school education work, schools need to organically combine classroom education and social practice. Schools need to link teaching and real society and link students' learning process with real life. Schools need to organically combine reading and learning with life, so as to promote the all-round development of students' humanistic quality. [ABSTRACT FROM AUTHOR]

The turn of contemporary visual culture has led to the expansion of the connotation and scope of visual communication design (VCD) education, the generation of new artistic concepts and forms, and the great changes in the subject education system. VCD instruction now has an enhanced teaching environment and operational platform because of the rapid advancement of digital technology. Digital technology is expected to break through traditional learning methods in the future and will be more widely integrated into VCD courses. A topic that must be addressed and explored in the reform and growth of VCD education is how to build a fairer and more inclusive college art education subject system. Therefore, it is particularly important to design a complete VCD teaching evaluation system. In this paper, artificial intelligence technology is applied to the teaching quality evaluation (TQE) system, and a scientific and reliable TQE model is obtained. The main works of this paper are as follows: (1) analyze the background and significance of TQE research, and systematically expound the domestic and foreign research status of TQE, genetic algorithm, and neural network. (2) Using an adaptive mutation evolutionary method, this research builds a TQE system for the VCD course and produces a BPNN model. The adaptive mutation genetic algorithm's convergence speed is considerably faster than the regular genetic algorithms, the optimized neural network's performance is also superior, and the model has a faster convergence time and better prediction accuracy. [ABSTRACT FROM AUTHOR]

At present, children's psychological and behavioral health care is mainly based on the doctor's observation and diagnosis. On the whole, it is inefficient, and the effect of health care cannot meet the current needs of children's behavior. Therefore, this paper uses the method of functional imaging to study the key factors of children's behavioral health care. In this paper, the structure and function of children's brain are associated with children's psychological behavior. The brain structure of 64 children in our city is detected by functional image processing, and 64 children are divided into groups according to the detection results. According to the children's performance, the children were divided into physical disorder (11 cases), emotional disorder (14 cases), cognitive disorder (12 cases), and normal group (42 cases). Among them, 3 cases had three kinds of disorders, 6 cases had both emotional and cognitive disorders, 7 cases had physical and emotional disorders, and 5 cases had physical and cognitive disorders. In this paper, according to the research data of functional imaging on different levels of children's brain, we use computer to model and simulate through digital conversion technology, draw the neural network Atlas of children's psychological behavior, compare the children's representation and image characteristics according to functional imaging, and then, study the relationship between children's signs and images, to make a plan for improving children's psychological behavior health care. The study shows that in the above different groups, the linear correlation between the functional imaging results and the representation of 22 abnormal children is 98%, and the fuzzy deviation is only 3.52%, which indicates that functional imaging can be used as the basic judgment basis in improving children's psychological and behavioral health care and can predict and reasonably prevent children's potential psychological behavior according to the images. [ABSTRACT FROM AUTHOR]

In order to explore the effective way of gestational diabetes care, this paper applies comprehensive nursing to gestational diabetes care. In terms of nursing intervention for pregnant women with gestational diabetes mellitus, combining the phased changes of pregnant women's physiological and psychological needs during pregnancy, this paper comprehensively implements health education, diet intervention, exercise intervention, pregnancy monitoring, psychological intervention, infection prevention, and perinatal monitoring and other nursing interventions in a selective and focused manner. This makes the intervention measures at each stage focused, intersecting, interpenetrating, and continuing to play a role, which can effectively improve the implementation effect of the intervention measures and better promote the effective improvement of pregnancy outcomes. In addition, this paper studies the effect of gestational diabetes care based on comprehensive nursing intervention through a controlled trial, and the study verifies that comprehensive nursing has a good effect in gestational diabetes care. [ABSTRACT FROM AUTHOR]

The insulated gate bipolar transistor (IGBT) is widely utilized in the transportation, power, and energy domains because of its high input impedance and minimal on-voltage drop. IGBTs are frequently used in industrial applications for lengthy periods of time, collecting fatigue damage and eventually aging and failing, which can result in system shutdown and financial losses in severe circumstances. As a result, a study into the IGBT's reliability is extremely important. Fault prediction technology, which is an important aspect of reliability research, may analyze device state through changes in terminal parameters, anticipate aging trends, and issue early warnings at thresholds to avoid significant safety issues caused by IGBT aging failures. Therefore, the appropriate end parameters are selected as aging characteristic parameters, and fault prediction is performed. Therefore, this paper has carried out research on the IGBT fault prediction technology that integrates the terminal characteristics and artificial intelligence neural network. The main research contents include the following: (1) this paper starts from the basic principle of IGBT and the structure of its device and analyzes its failure mode on the failure of IGBT. The characteristic parameter of collector-emitter turn-off peak voltage value is selected for IGBT fault prediction, and the aging data of NASA PCoE Research Center is used to verify that the characteristic parameter can be used for fault prediction. (2) In view of the shortcomings of traditional fault forecasting methods, this paper proposes to use deep learning time series forecasting methods for fault forecasting. The LSTM is theoretically analyzed, and the prediction network is built. The experimental results show that the LSTM network model can improve the accuracy of IGBT fault prediction, with fewer parameters and higher prediction efficiency. [ABSTRACT FROM AUTHOR]

The children's intensive care unit is a closed management area with limited visiting time and no accompanying persons. It fails to systematically reflect and summarize the opinions and needs of the families of the children. The more critically ill the family members are, the higher the requirements for medical care. Good relationship between doctors, nurses, assistant, and patients can promote the rehabilitation of children's diseases and achieve the advanced medical model level of "seamless management and no loopholes." In order to aid the complete intensive care process, it is vital to understand children's psychological and physical development based on children's behavioral psychology when the medical-nursing-assistance (MNA) integration model is used in the children's intensive care unit. Therefore, this paper has completed the following tasks: (1) the development status of the domestic and foreign MNA integration model in the quality management of children's intensive care units is introduced, and the MNA integration model based on the theoretical basis of behavioral psychology is proposed for the following article in children's intensive care. The effect evaluation system of room management provides a theoretical basis. (2) The principle of BP neural network is introduced, and the effect evaluation model of the integrated mode of MNA based on BPNN in the management of children's intensive care unit is constructed. (3) The relevant data collected are used to form an available data set for the model accuracy test. The experimental results show that, after the research in this paper, the BPNN model proposed in this paper is introduced into the MNA integration model to evaluate the effect of the management of children's intensive care units which is practical and effective. [ABSTRACT FROM AUTHOR]

Esophageal squamous cell carcinoma (ESCC) is one of the highest incidence and mortality cancers in the world. An effective survival prediction model can improve the quality of patients' survival. Therefore, a parameter-optimized deep belief network based on the improved Archimedes optimization algorithm is proposed in this paper for the survival prediction of patients with ESCC. Firstly, a combination of features significantly associated with the survival of patients is found by the minimum redundancy and maximum relevancy (MRMR) algorithm. Secondly, a DBN network is introduced to make predictions for survival of patients. Aiming at the problem that the deep belief network model is affected by parameters in the construction process, this paper uses the Archimedes optimization algorithm to optimize the learning rate α and batch size β of DBN. In order to overcome the problem that AOA is prone to fall into local optimum and low search accuracy, an improved Archimedes optimization algorithm (IAOA) is proposed. On this basis, a survival prediction model for patients with ESCC is constructed. Finally, accuracy comparison tests are carried out on IAOA-DBN, AOA-DBN, SSA-DBN, PSO-DBN, BES-DBN, IAOA-SVM, and IAOA-BPNN models. The results show that the IAOA-DBN model can effectively predict the five-year survival rate of patients and provide a reference for the clinical judgment of patients with ESCC. [ABSTRACT FROM AUTHOR]

The purpose of this study is to strengthen the procurement management of public hospitals and ensure the quality of medical equipment. In this paper, combined with the procurement process of medical equipment in public hospitals, on the basis of RFID technology, a JRP model of random demand for medical equipment procurement in public hospitals is established. At the same time, according to the type and quantity of decision variables, the DE solution algorithm is redesigned, and based on the support of the algorithm, a mathematical model for cost control of medical equipment procurement in public hospitals is established. It can be seen from the analysis results that the cost control system for medical equipment procurement in public hospitals based on the mathematical model proposed in this paper can play an important role in public hospital equipment procurement and promote the standardized operation of public hospital procurement management. [ABSTRACT FROM AUTHOR]

Aiming at the problem of insufficient details of retinal blood vessel segmentation in current research methods, this paper proposes a multiscale feature fusion residual network based on dual attention. Specifically, a feature fusion residual module with adaptive calibration weight features is designed, which avoids gradient dispersion and network degradation while effectively extracting image details. The SA module and ECA module are used many times in the backbone feature extraction network to adaptively select the focus position to generate more discriminative feature representations; at the same time, the information of different levels of the network is fused, and long-range and short-range features are used. This method aggregates low-level and high-level feature information, which effectively improves the segmentation performance. The experimental results show that the method in this paper achieves the classification accuracy of 0.9795 and 0.9785 on the STARE and DRIVE datasets, respectively, and the classification performance is better than the current mainstream methods. [ABSTRACT FROM AUTHOR]

Chloasma is a prevalent clinical hyperpigmentation skin disorder that causes symmetrical brown to tan patches on the cheeks, as well as the neck and forearms on rare occasions. The pathophysiology of this condition is complicated, and there is now no cure. Under the light microscope, the full-thickness melanin of the epidermis in the skin lesions was increased, and the dermal chromophages increased. At present, the treatment of melasma mainly includes topical drugs, chemical peels, systemic drugs, laser therapy, and traditional Chinese medicine. With the development of medical technology, intense pulsed light and Q-switched laser have been widely used in the treatment of melasma, which can emit laser beams to penetrate the dermis uniformly to treat deep pigmented lesions in the dermis. After a stable treatment outcome for melasma is achieved, it is important to minimize side effects such as postinflammatory hyperpigmentation and skin irritation. Therefore, this paper uses a reflection confocal microscope to establish an evaluation index system and then uses a neural network to evaluate the treatment effect. The work of this paper is as follows: (1) this paper introduces various methods of treating melasma at home and abroad and focuses on the application of intense pulsed light therapy and low-energy Q-switched Nd: YAG laser in the treatment of melasma. (2) In this paper, the case data samples are trained with the designed BP network to obtain a reliable evaluation network model. (3) The results and mistakes of the evaluation are produced by training the genetic algorithm optimized backpropagation (GA-BP) network structure model to evaluate the treatment effect of chloasma. Finally, it has been demonstrated that the GA-BP network has great accuracy and stability. [ABSTRACT FROM AUTHOR]

With the development of wireless network technology, the transformation of educational concepts, the upgrading of users' educational needs, and the transformation of lifestyles, online education has made great strides forward. However, due to the rapid growth of online education in my country, many regulatory systems have not kept pace with the development of online education, resulting in low user experience and satisfaction with online education. The establishment of a user satisfaction model is beneficial for attracting attention and thinking about research in the field of online education service quality, assisting enterprises in recognizing the specific impact of various factors in services, accelerating service quality improvement, and assisting in the formulation of industry norms and improving enterprise competitiveness, all of which help students acquire knowledge more easily. In the era of big data, traditional satisfaction evaluation methods have many drawbacks, so more and more machine learning methods are applied to satisfaction evaluation models. This paper takes the research of machine learning algorithm as the core to carry out the research work, uses the cost-sensitive idea to improve the decision tree, considers the cost of different types of classification errors, and uses the random forest principle to integrate the generated decision tree, thereby improving the accuracy of the model. The model has better stability, and the validity of the model is verified by experiments. For a follow-up in-depth investigation of online education satisfaction rating technology, the linked work of this paper has certain reference and reference value. [ABSTRACT FROM AUTHOR]

At present, with the rapid increase of emergency knowledge and the improvement of people's requirements for medical quality, the traditional teaching mode cannot fully meet the needs of emergency teaching in the new era. This paper is aimed at improving the clinical emergency teaching mode by problem based learning (PBL) teaching method and improving the comprehensive ability of clinical emergency of medical students. This article proposes a problem-based PBL imaging teaching method, combining the characteristics and content of clinical emergency courses, focusing on students, highlighting the problem-solving process, and improving students' creative thinking ability. To cultivate students' interest in clinical learning, develop their self-learning ability, train their teamwork and communication skills, and cultivate their ability to set, question, and solve questions, so as to promote medical students' overall comprehensive ability to integrate specialized knowledge and clinical practice. In this paper, the PBL teaching method and the traditional teaching method of comparative experiments show that the PBL teaching method can more effectively highlight the characteristics of clinical emergency medicine teaching mode and make full use of the limited emergency teaching resources, so as to improve the quality of clinical emergency teaching. Compared with the traditional teaching mode, the theoretical knowledge and clinical operation skills of medical students under the PBL teaching mode are improved by 13%. Autonomous learning ability, communication ability, and creative thinking ability have also been relatively improved. [ABSTRACT FROM AUTHOR]

Objective. The purpose of this study was to investigate the effect of lumbar disc herniation (LDH) disease degree on lumbar discectomy and to explore the relationship between the degree of intervertebral disc disease and postoperative pain score changes. Methods. We conducted a comprehensive search in China National Knowledge Infrastructure (CNKI), Wanfang Data, PubMed, MEDLINE, Embase, Cochrane database, and other databases, obtained all relevant studies as of April 2017, and then followed strict inclusion and exclusion criteria. Standard screening was performed on the retrieved literature. We extract and analyze key data using Review Manager 5.3 software. Pooled effects were calculated by mean difference or odds ratio and 95% confidence interval analysis, depending on data attributes. Results. Various databases were searched for the results of papers from lumbar discectomy since April 2017 to April 2022. Nine papers from 2502 patients were selected. The average overall follow-up was 52 weeks. There were statistically significant reductions in postoperative pain scores and degree of disc disease. There was a significant correlation between the reduction in pain score after discectomy and the degree of disc disease (r = 0.73 , 95 % CI = 0.01 -1.20, p = 0.005). Conclusions. Decreased disc disease grade is one of the reasons for the lower back pain score after discectomy. Furthermore, region-dependent economic factors must be considered before developing a treatment strategy. Larger, well-defined randomized controlled trials are needed to further confirm these results. [ABSTRACT FROM AUTHOR]

This paper applies the situational teaching mode to obstetric clinical nursing. When explaining the nursing operation skills, according to the pre written script, design some common clinical nurse-patient conflicts and carry out situational simulation performances, so as to inspire students to think about how to effectively communicate with patients and their families and establish a harmonious nurse-patient relationship. At the same time, this paper also urges students to improve their initiative of autonomous learning and actively participate in the whole process of learning, rather than passively accept knowledge. Finally, the teaching methods of combining obstetric clinical nursing teaching with experimental teaching were compared to explore the effectiveness of situational teaching simulation teaching mode. Through the experimental comparative analysis, it can be seen that the obstetric clinical nursing teaching model based on situational teaching simulation has a certain effect and has a good guiding significance for the practical teaching of obstetric clinical nursing. [ABSTRACT FROM AUTHOR]

Physical exercise refers to various physical exercises carried out through certain means and methods. Physical exercise can not only achieve the purpose of strengthening the body and health but also make people face challenges in physical and mental sports, and the resulting psychological satisfaction and excitement make exercisers happy physically and mentally. Physical activity has a certain appeal that makes it one of the most effective ways for modern people to alleviate mental illnesses. The human brain's reaction time is linked to its thinking speed and intelligence. Regular physical activity can increase human brain cell reaction time and completely utilize human brain capacity, which is beneficial to the healthy development of human attention, memory, imagination, and thinking ability. Scientific and reasonable physical exercise is also an important means to improve people's intelligence levels. Everyone's physical health level is closely related to their mental health. A healthy mind comes from a healthy body. A large number of scientific studies have confirmed that reasonably arranging the contents and methods of physical exercise according to their own health level and psychological state cannot only enhance the physique of college students but also cultivate their excellent personality. Firstly, this paper summarizes the influence of physical exercise on mental health. The ways of employing physical exercise to improve and improve the mental health of college students are presented in this study. Then, this paper proposes a physical exercise intervention based on an improved neural network (NN), which has an impact on the mental health level of college students, and the effectiveness of this model is verified by simulation experiments. [ABSTRACT FROM AUTHOR]

Today's rule of law construction in China is walking between the conflict and coordination of factors such as reality and ideals, tradition and modernity, local and foreign, and local knowledge and universal principles, all while continuing to strengthen the unification of the legal system and advance the modernization of the rule of law. Traditional customary law, which is the most representative local resource culture, is unquestionably one of the most important themes in the formation of the rule of law. It has far-reaching significance for the development of ethnic jurisprudence, the reunderstanding of traditional culture, and the construction of ethnic unity and harmonious society. Based on this background, this paper uses big data technology to collect relevant experimental data and proposes a traditional customary law value assessment based on BPNN. The completed work is as follows: (1) this paper clarifies the concept of customary law and the difference between it and related concepts and introduces the domestic relevant research on traditional customary law and the interactive relationship between customary law and national law in dynamic legal practice and puts forward the status and influence of customary law in contemporary legal practice. (2) The related technologies of neural network are introduced, and a traditional customary value evaluation system that can be used for experiments is constructed. (3) Experiment with the designed data set to see if the BP model is feasible. The experimental results suggest that the model proposed in this study has a low error rate and performs well while evaluating traditional common law values. [ABSTRACT FROM AUTHOR]

Hospital information system (HIS) can provide a full range of information support for various hospital business activities and information collection, processing, and transmission, helping medical service providers. And HIS can reduce medical service costs and improve work efficiency, greatly reducing errors in diagnosis and treatment. Although the advantages of using the HIS are obvious, there are still some challenges in its use, the most prominent being how to make the medical staff use HIS effectively. Based on this background, this paper uses machine learning (ML) technology to predict and analyze the satisfaction of HIS use in hospitals and completes the following work: firstly, introduce the situation and development trend of HIS construction at home and abroad and provide theoretical basis for model design. The related development technologies are discussed and studied in detail. Second, the ML algorithm is used to provide a prediction strategy. The support vector machine (SVM) can handle small data sets well, and this study applies the AdaBoost technique to improve the model's generalization ability and accuracy. Lastly, a diversity metric is included to guarantee that the basic learner has good variety in order to increase the algorithm's performance. Accuracy rates may reach more than 95% in the case of tiny data sets, according to the self-built data set used for testing. This proves the superiority of the model proposed in this paper. [ABSTRACT FROM AUTHOR]

Text interpretation of public English vocabulary is a critical task in the subject of natural language processing, which uses technology to allow humans and computers to communicate effectively using natural language. Text feature extraction is one of the most fundamental and crucial elements in allowing computers to effectively grasp and read text. This paper proposes a text feature extraction method based on wavelet analysis that performs fast discrete wavelet transform and inverse discrete wavelet transform on the feature vectors under the traditional TF-IDF vector space model to address the problem of low feature differentiation of high-dimensional data in text feature extraction. In particular, due to the design of the Mallat algorithm, there is frequency aliasing in the signal decomposition process. This phenomenon is a problem that cannot be ignored when using wavelet analysis for feature extraction. Therefore, this paper proposes an improved inverse discrete wavelet transform method, in which the signal is decomposed by Mallat algorithm to obtain wavelet coefficients at each scale and then reconstructed to the required wavelet space coefficients according to the reconstruction method, and the reconstructed coefficients are used to analyze the signal at that scale instead of the wavelet coefficients obtained at the corresponding scale. Experiments on the public English vocabulary dataset reveal that the wavelet transform-based strategy suggested in this research outperforms existing feature extraction methods while maintaining greater classification accuracy while reducing the dimensionality of the TF-IDF vector space model. [ABSTRACT FROM AUTHOR]

Drug combinations have recently been studied intensively due to their critical role in cancer treatment. Computational prediction of drug synergy has become a popular alternative strategy to experimental methods for anticancer drug synergy predictions. In this paper, a deep learning model called DCE-DForest is proposed to predict the synergistic effect of drug combinations. To sufficiently extract drug information, the paper leverages BERT (Bidirectional Encoder Representations from Transformers) to encode the drug and the deep forest to model the nonlinear relationship between the drugs and cell lines. The experimental results on the synergy datasets demonstrate that the proposed method consistently shows superior performance over the other machine learning models. [ABSTRACT FROM AUTHOR]

New media has become incorporated into people's lives as a result of its advent and great popularity. Students make substantial use of new media, and using it for student management necessitates social attention and assistance. It has to do with the management effect of colleges and universities, as well as the development of college students and societal harmony and advancement. Under the new media environment, student management workers should apply new media to daily student management work on the basis of traditional student management work methods, carry out new extensions and expansions, and use various forms of new media platforms as working methods and means. To carry out student work to improve the efficiency and effectiveness of student management work, in this context, this paper uses deep learning to carry out the application and practical effect evaluation of new media in student management and completes the following work: (1) This paper examines and discusses the development history, concept, connotation, and characteristics of new media using the literature analysis approach. The literature is used to synthesize the study findings of contemporary academic circles on the management of student issues in the new media environment. (2) The related technologies of BPNN are introduced, the evaluation index of the application effect of new media on student management work is constructed, and then, the appropriate BPNN structure is designed. (3) Experiments are carried out with the self-designed data set. The results of the experiments reveal that the model proposed in this research has a low error and good performance. [ABSTRACT FROM AUTHOR]

Higher education has always been the top priority of the country and society. With the gradual completion of the Chinese curriculum system, in addition to some subject knowledge, the education on ideology, morality, and quality has also become more and more perfect. Moral education in colleges and universities is an example of this. However, current moral education instruction in colleges and universities is still based on examination-oriented education, and students have not been exposed to the culture deeply. As a result, the goal of this study is to strengthen traditional culture's function in moral education instruction in colleges and universities, as well as conduct research on its application value. In response to this, this paper designs an embedded moral education network teaching platform, which focuses on increasing the importance of the role of administrators, and is responsible for collecting statistics of traditional culture resources and applying them to teaching. The education for traditional culture also traces its origins and provides suggestions for the new era with reference to historical moral education research. The results of this paper believe that, for the response time of the system, in the campus network environment, the response time is about 3 s, the minimum value is 2.8 s, and the maximum value is also 3.2 s. In an ordinary network environment, the response time is also within 3.8 s. This demonstrates that the approach proposed in this research is efficient and capable of meeting the needs of moral education instruction in colleges and universities. [ABSTRACT FROM AUTHOR]

Unused hotel rooms, unused event tickets, and unsold items are all examples of wasted expenses and earnings. Governments require accurate tourism demand forecasting in order to make informed decisions on topics such as infrastructure development and lodging site planning; therefore, accurate tourism demand forecasting becomes vital. Artificial intelligence (AI) models such as neural networks and security violation report (SVR) have been used effectively in tourist demand forecasting as a result of the fast advancement of AI. This paper constructs a tourism demand forecasting model based on machine learning on the basis of the existing forecasting model research. The completed work is as follows: (1) It introduces a large number of domestic and foreign literatures on tourism volume forecasting and proposes the research content of this paper. (2) It is proposed to stack the long short-term memory- (LSTM-) based autoencoders deeply, by adopting a hierarchical greedy pretraining method to replace the random weight initialization method used in the deep network and combining this pretraining stage and fine-tuning network together to form the SAE-LSTM prediction model for improving the performance of deep learning models. (3) This paper uses the monthly search engine strength data of city A's monthly tourist volume and its related influencing factors as the data set; processes the data set to make the model adapt to the data input; uses mean absolute error (MAE), root mean square error (RMSE), MAPE, and other model evaluation indicators; and uses LSTM and the constructed SAE-LSTM model to conduct comparative experiments to predict the number of tourist arrivals in four years. The prediction results of the models proposed in this paper are better than those of the LSTM model. According to the experimental results, the superiority of the proposed LSTM-based unsupervised pretraining method is demonstrated. [ABSTRACT FROM AUTHOR]

With the continuous deepening of artificial intelligence (AI) in the medical field, the social risks brought by the development and application of medical AI products have become increasingly prominent, bringing hidden worries to the protection of civil rights, social stability, and healthy development. There are many new problems that need to be solved in our country's existing risk regulation theories when dealing with such risks. By introducing the theory of risk administrative law, it analyzes the social risks of medical AI, organically combines the principle of risk prevention with benefit measurement, and systematically and flexibly reconstructs the theoretical system of medical AI social risk assessment. This paper has completed the following work: (1) reviewed and sorted out the works and papers related to medical AI ethics, medical AI risk, etc., and sorted out the current situation of medical AI social risk regulation at home and abroad to provide help for follow-up research. (2) The related technologies of artificial neural network (ANN) are introduced, and the risk assessment index system of medical AI is constructed. (3) With the self-designed dataset, the trained neural network model is utilized to assess risk. The experimental results reveal that the created BPNN model's error is relatively tiny, indicating that the algorithm model developed in this research is worth popularizing and applying. [ABSTRACT FROM AUTHOR]

In this paper, we proposed a stochastic SVEI brucellosis model with stage structure by introducing the effect of environmental white noise on transmission dynamics of brucellosis. By Has'minskii theory and constructing suitable Lyapunov functions, we established sufficient conditions on the existence of ergodic stationary distribution for the considered model. Moreover, we also established sufficient condition for extinction of the disease. Finally, two examples with numerical simulations are given to illustrate the main results of this paper. [ABSTRACT FROM AUTHOR]

Occupational identity is an individual's view, recognition, and approval of his long-term occupation, and its importance to every professional is self-evident. Only when a professional person agrees with the profession he is engaged in from the bottom of his heart can he devote himself wholeheartedly to it and unreservedly exert his greatest potential. On the basis of sorting out and analyzing the prevailing theoretical and empirical research results, this paper deliberates the empirical research on the influence mechanism between employees' occupational identity and occupational well-being. In this study, through big data analysis, literature search, questionnaire survey, and other methods, this paper obtained the professional identity data of employees in different companies and used a method of big data analysis, namely, BP neural network (BPNN) to design in this paper to verify the data, and finally obtain an effective theoretical model of the influence mechanism of occupational identity and occupational well-being. The main work of this paper is as follows: (1) it introduces the interpretation of the concept of "professional identity" by different scholars at home and abroad and makes a brief review of the researches on professional identity and professional well-being made by foreign scholars in recent years. (2) The basic knowledge and algorithm process of artificial neural network (ANN) are introduced, and the design of the evaluation model of the influence mechanism of occupational identity on occupational well-being based on BPNN is proposed. (3) The simulation software validates the neural network (NN) assessment system developed in this paper. Experiments reveal that the BPNN system is a reasonable and feasible evaluation approach for analyzing the impact of occupational identity on occupational well-being. [ABSTRACT FROM AUTHOR]

This paper discusses the imaging diagnostic features of arteriosclerotic encephalopathy and combines the spatial context information of local features to study the clinical imaging image copy detection algorithm. Moreover, this paper proposes a clinical imaging copy detection algorithm that combines the BOW model and spatial context embedding and a clinical imaging copy detection algorithm that combines the BOW model and global context verification. In addition, this paper applies the algorithm to the imaging diagnostic features of arteriosclerotic encephalopathy and sets up a controlled experiment to start research. The experimental research shows that the application of imaging diagnosis to the detection of subcortical arteriosclerotic encephalopathy has good clinical effects and rapid remission of patients' symptoms. The effectiveness of this method can be verified by a large number of clinical practices in follow-up studies. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to study the feasibility and economic benefits of intelligent medical Internet of Things (IOT) systems for improving the quality of life of hemophilia patients, thereby reducing the risk of teratogenicity and disability for patients. This article selects 60 severe hemophilia patients who were followed up in our hospital from 2018 to 2019 as the research object. In the intelligent medical system, the Gaussian mixture model discretization algorithm is used to preprocess patient data collection. The observation group uses the intelligent medical system to implement home nursing for the patients, and the control group uses ordinary home nursing. This paper evaluates the quality of life of the two groups of patients 6 months after the intervention, including self-care ability, transfer function, and home nursing cognitive ability. The research results show that the home nursing based on smart medical IOT proposed in this paper is feasible and effective for improving the quality of life of patients. It can effectively improve the patient's self-care ability and joint functions and has important reference value for the development of intelligent medical IOT equipment. [ABSTRACT FROM AUTHOR]