AIM: To develop a traditional Chinese medicine (TCM) knowledge graph (KG) for diabetic retinopathy (DR) diagnosis and treatment by integrating literature and medical records, thereby enhancing TCM knowledge accessibility and providing innovative approaches for TCM inheritance and DR management. METHODS: First, a KG framework was established with a schema-layer design. Second, high-quality literature and electronic medical records served as data sources. Named entity recognition was performed using the ALBERT-BiLSTM-CRF model, and semantic relationships were curated by domain experts. Third, knowledge fusion was mainly achieved through an alias library. Subsequently, the data layer was mapped to the schema layer to refine the KG, and knowledge was stored in Neo4j. Finally, exploratory work on intelligent question answering was conducted based on the constructed KG. RESULTS: In Neo4j, a KG for TCM diagnosis and treatment was constructed, incorporating 6 types of labels, 5 types of relationships, 5 types of attributes, 822 nodes, and 1,318 relationship instances. This systematic KG supports logical reasoning and intelligent question answering. The question answering model achieved a precision of 95%, a recall of 95%, and a weighted F1-score of 95%. CONCLUSION: This study proposes a semi-automatic knowledge-mapping scheme to balance integration efficiency and accuracy. Clinical data-driven entity and relationship construction enables digital dialectical reasoning. Exploratory applications show the KG's potential in intelligent question answering, providing new insights for TCM health management.

ObjectiveThis study investigates the determinants of medical impoverishment among China's rural near-poor, aiming to enhance public health services and establish preventative and monitoring systems.MethodsUsing China Family Panel Studies and World Bank methods, we categorized rural populations and calculated their 2020 Poverty Incidence (PI) and Poverty Gap (PG), with impoverishing health expenditures (IHE) as the primary indicator. We analyzed the data from 2016 to 2020 using a conditional fixed-effects multinomial logit model and 2020 logistic regression to identify factors influencing medical impoverishment risk.Results(1) In 2020, the near-poor in China faced a PI of 16.65% post-health expenditures, 8.63 times greater than the non-poor's PI of 1.93%. The near-poor's Average Poverty Gap (APG) was CNY 1,920.67, notably surpassing the non-poor's figure of CNY 485.58. Health expenses disproportionately affected low-income groups, with the near-poor more prone to medical impoverishment. (2) Disparities in medical impoverishment between different economic household statuses were significant (P < 0.001), with the near-poor being particularly vulnerable. (3) For rural near-poor households in China, those with over six members faced a lower risk of medical impoverishment compared to those with three or fewer. Unmarried individuals had a 7.1% reduced risk of medical impoverishment relative to married/cohabiting counterparts. Unemployment was associated with a 9% increased risk. A better self-rated health status was linked to a lower probability of IHE, with the “very healthy” reporting a 25.8% lower risk than those “unhealthy.” Chronic disease sufferers in the near-poor and non-poor categories were at an increased risk of 12 and 1.4%, respectively. Other surveyed factors, including migrant status, age, insurance type, gender, educational level, and recent smoking or drinking, were not statistically significant (P > 0.05).ConclusionRural near-poor in China are much more susceptible to medical impoverishment, influenced by specific socio-economic factors. The findings advocate for policy enhancements and health system reforms to mitigate health poverty. Further research should extend to urban areas for comprehensive health poverty strategy development.

As one of the three major grain crops, wheat is widely planted all over the world. Its planting and production have a direct relationship with people’s food security and health safety. However, after increasing rapidly for decades, the rate of increment in wheat yields has slowed down since the early 1990s [3, 5]. According to the Food and Agriculture Organization of United Nations, the whole world’s demand for wheat is expected to reach 850 million tons by 2050 [1], which means the supply may fall short of demand in the future. Wheat production has become ever more challenging worldwide. Recently, precision agriculture is one of the many strategies designed to improve crop management and maximize crop yields. Precision agriculture relies on monitoring and measuring the growth of crops in real-time [2], which means a huge amount of crop data collected to explore the growing status needs well organization and analysis. However, analyzing such a sheer amount of crop data is overly time-consuming and labor-intensive. Yield estimation is one of the most important tasks in precision agriculture. However, traditional wheat yield estimation requires agricultural experts to manually count the heads of wheat, which is extremely challenging, error-prone, and obviously not cost-effective at all.

Knowledge graph can effectively analyze and construct the essential characteristics of data. At present, scholars have proposed many knowledge graph models from different perspectives, especially in the medical field, but there are still relatively few studies on stroke diseases using medical knowledge graphs. Therefore, this paper will build a medical knowledge graph model for stroke. Firstly, a stroke disease dictionary and an ontology database are built through the international standard medical term sets and semiautomatic extraction-based crowdsourcing website data. Secondly, the external data are linked to the nodes of the existing knowledge graph via the entity similarity measures and the knowledge representation is performed by the knowledge graph embedded model. Thirdly, the structure of the established knowledge graph is modified continuously through iterative updating. Finally, in the experimental part, the proposed stroke medical knowledge graph is applied to the real stroke data and the performance of the proposed knowledge graph approach on the series of Trans ∗ models is compared.

In the past ten years, crowd detection and counting have been applied in many fields such as station crowd statistics, urban safety prevention, and people flow statistics. However, obtaining accurate positions and improving the performance of crowd counting in dense scenes still face challenges, and it is worthwhile devoting much effort to this. In this paper, a new framework is proposed to resolve the problem. The proposed framework includes two parts. The first part is a fully convolutional neural network (CNN) consisting of backend and upsampling. In the first part, backend uses the residual network (ResNet) to encode the features of the input picture, and upsampling uses the deconvolution layer to decode the feature information. The first part processes the input image, and the processed image is input to the second part. The second part is a peak confidence map (PCM), which is proposed based on an improvement over the density map (DM). Compared with DM, PCM can not only solve the problem of crowd counting but also accurately predict the location of the person. The experimental results on several datasets (Beijing-BRT, Mall, Shanghai Tech, and UCF_CC_50 datasets) show that the proposed framework can achieve higher crowd counting performance in dense scenarios and can accurately predict the location of crowds.

The idea of constructing the biological neural system model as realistic as possible can not only provide a new artificial neural network (ANN), but also offer an effective object to study biological neural systems. As a very meaningful attempt about the idea, a bionic model of olfactory neural system, KIII model, is introduced in this paper. There are the unique characteristics of KIII model different from those of general ANNs. The KIII model realistically simulates the structure of the real olfactory neural system and the process of odor molecules gradually transformed by the core components of the olfactory system including olfactory receptor, olfactory bulb and olfactory cortex. The neuron model of the KIII model is constructed and optimized based on neurophysiological experimental data and accurately reflects the response of olfactory neurons to odor stimulation. In particular, the noise introduced to KIII model can further improve the performance of the model. In addition, the KIII model is analyzed based on the idea of deep learning. The qualitative analysis shows that there are obvious similarities between the KIII model and the deep learning model. Furthermore, with the epileptic electroencephalograph (EEG) recognition task, two groups of experiments are designed to comprehensively analyze the performance of the KIII model. In the first group of experiments, a typical pattern recognition experiment with feature extraction stage is shown. The features of epileptic EEG were extracted based on Empirical Mode Decomposition (EMD), and the KIII model was used as a classifier. The experimental results show that the KIII model only needs a small number of iterations to memorize different modes and has a high recognition rate, over 91%. In the second group of experiments, a direct recognition experiment without feature extraction stage is shown. The original epileptic EEG signals as KIII model inputs directly were recognized. The experimental results show that there is still an excellent performance in the KIII model, over 96%, and the recognition result is similar to the characteristics of the deep learning model. The theoretical analysis and experimental results prove that KIII model with the idea of deep learning is an excellent bionic model of olfactory neural system and gets a good balance between high bionics and good performance, which is a good reference for related research.

The quality control of meteorological data has lately received great attention for its important significance to national ecological security and military security. However, the observational quality of the data has made it challenging to the quality control of meteorological data. In an effort to overcome this challenge, a random sampling-arithmetic mean (RS-AM) method based on the random observation method is proposed to solve the problem. Firstly, the reason why the arithmetic mean is not ideal for truth estimation is proved in the paper. Secondly, the method evaluates the goodness of fit between the expected distribution and the sampling distribution by repeatedly extracting the random observation vector based on the random sampling model, to find the random observation vector closest to the expected distribution. Then, the distance between the median and arithmetic mean of each set of claims is calculated by the distance formula, and the claims with the minimum distance are selected. The random extraction is continued on the selected set of claims until the stop condition is met. Finally, the truth is calculated by the method of arithmetic mean from the selected claims. Moreover, the convergence of this method is proved by theoretical derivation. Experimental results show that the proposed RS-AM method can effectively solve the problem of data observation quality. And, compared with the conflict resolution on heterogeneous data (CRH) method, the RS-AM method reduces 1.5% on MSE and 2.9% on RMSE while ensuring the error rate is basically the same.