Search

Organic elastomers such as polyurethane are widely used as a filling material in underground coal mines. However, the risk of fire hazard in coal seams is increased due to the flammability of polyurethane. Laboratory tests illustrate that in a thermostatic reactor with initial temperature of 25 °C, the temperature during the production of polyurethane increases up to > 140 °C. Adiabatic oxidation experiments and TG–DTG analysis showed that the heating rate of the mixed samples of polyurethane and coal was higher than that of any single component in the initial oxidation stage. From the initial temperature to 100 °C, increasing the proportion of polyurethane was conducive to the acceleration of temperature rise. From 0.180 to 0.850 mm, the self-heating rate was inversely proportional to the particle size. At the initial stage, the low ventilation rate promoted the spontaneous combustion of mixed samples, but when the temperature is > 70 °C, an opposite trend was seen. Kinetic parameters suggested that the activation energy decreases with the introduction of polyurethane. According to the mathematical model, the variation of the spontaneous combustion period of coal and polyurethane was predicted.

Current development of high-performance fiber-reinforced cementitious composites (HPFRCC) mainly relies on intensive experiments. The main purpose of this study is to develop a machine learning method for effective and efficient discovery and development of HPFRCC. Specifically, this research develops machine learning models to predict the mechanical properties of HPFRCC through innovative incorporation of micromechanics, aiming to increase the prediction accuracy and generalization performance by enriching and improving the datasets through data cleaning, principal component analysis (PCA), and K-fold cross-validation. This study considers a total of 14 different mix design variables and predicts the ductility of HPFRCC for the first time, in addition to the compressive and tensile strengths. Different types of machine learning methods are investigated and compared, including artificial neural network (ANN), support vector regression (SVR), classification and regression tree (CART), and extreme gradient boosting tree (XGBoost). The results show that the developed machine learning models can reasonably predict the concerned mechanical properties and can be applied to perform parametric studies for the effects of different mix design variables on the mechanical properties. This study is expected to greatly promote efficient discovery and development of HPFRCC.

High-performance fiber-reinforced cementitious composites (HPFRCCs) feature high mechanical strengths, crack resistance, and durability. Under excessive loading, HPFRCCs demonstrate dense microcracks that are difficult to identify using existing methods. This study presents a computer vision method for identification, quantification, and visualization of microcracks in HPFRCCs based on deep learning. The presented method integrates multiple deep learning models and computer vision techniques in a hierarchical architecture. The crack pattern (e.g., number, width, and spacing of cracks) are automatically determined from pictures without human intervention. This study shows that the presented method achieves an accuracy of 0.992 for crack detection and an accuracy finer than 50 μm (R2 > 0.984) for quantification of crack width when deep learning models are trained using only 200 pictures of HPFRCCs and 200 pictures of conventional concrete with incorporation of data augmentation. The presented method is expected to be also applicable to other materials featuring complex cracks.

OBJECTIVES: This study aims to investigate the positive detection rate and predictive value of autoantibodies, including anti-double stranded deoxyribonucleic acid (anti-dsDNA) antibodies, anti-histone antibodies (AHAs), anti-ribosomal (anti-Rib) P antibodies, anti-Smith (anti-Sm) antibodies, anti-U1 ribonucleoprotein (anti-U1RNP) antibodies, anti-Sjögren's syndrome type A antibodies and anti-Sjögren's syndrome type B antibodies, on organ damage in patients with systemic lupus erythematous (SLE). PATIENTS AND METHODS: A total of 225 patients with SLE (37 males, 188 females; mean age 37.4±15.9 years; range, 7 to 80 years) were evaluated retrospectively. Statistical analysis was performed to obtain the positive detection rate of autoantibodies and to investigate the predictive value. RESULTS: There were statistically significant differences of positive anti-dsDNA antibodies in renal damage, photosensitization, hematological abnormalities and serositis (p0.05). CONCLUSION: Autoantibody spectrum is an important serological basis for SLE diagnosis. There are differences in the autoantibodies distribution of SLE patients with different organ damage, suggesting a certain clinical value for prediction of organ damage in SLE.

Search engines usually return relevant sorted results based on the keywords. Because of the lack of considering the user's current search interest and intention, this kind of strategy may not meet users' personalized search requirements. In order to retrieve results associated with the user's current search interest, existing researches integrate the user's interest information into the search process and ranking, so as to make the search results fit to the user's current search target more better. Different from the unified model of interest which most current related researches used, we propose a model of combing user's interests for the purpose of ranking in the light of different query types. This paper first classified queries into several types based on the current keywords and the sources of user's interests, such as short-term interest in user clicks, and long-term interest in user's search history, search logs of the search system etc. Then based on the sources of interests, we established a model of combination of interests which based on the artificial neural network and was trained by related approaches and data sets. Depending on different query types, we combined these sources of user's interests that the most best reflecting the user's current search intention to enhance the user's search experience. Comparing with the existing model of single interest, the results of the experiments show that our model can obtain better ranking on the results.

In order to make search results better fit users’ current search interest, this paper proposes an algorithm of repeated results re-ranking using a model of polysemy. The algorithm considers the characteristics of the keywords to improve the rank of repeated results. Based on the analysis of polysemy of the keywords, we propose a polysemous model of concept lattice, then we combine with the user interest model to change the rank of repeated results in a search session. The method of this paper considers the impact of polysemy of keywords which may improve the ranking. The experimental results show that the process based on the polysemy of the keyword can reduce the length of the search session, especially when the keywords have multiple meanings.

Social Tagging is a free but also uncontrolled way to index and organize Web 2.0 resources. Many works have been proposed to leverage such tagging information. However, although previous studies have shown that users could reach consensus on which tags should be attached to a resource, the study about the consensus showing how to use a tag is still lack. This paper proposes a text chance discovery and subjective Bayes based approach to model and detect consensus of tags. In the proposed approach, tag consensus is modeled using characteristics of resources annotated by the tag. Experiment results show that the proposed method could more properly capture to what extent the users have reached consensus about the tag in advance of usage frequency.

Blog provides a simple way for people to share personal experiences and ideas, and has already become an important tool for people to communicate with each other. This fact turns blog into one of the most important information providers of the World Wide Web, but also makes how to find useful blogs for people to read an urgent problem. In this paper, we propose a blog clustering algorithm BCBSM (Blog Clustering based on Blog Set similarity and Mergence) aims at providing a general purpose blog friend recommendation system with high efficiency and effectiveness. By applying BCBSM, blogs are clustered into blog sets and to help improving the effectiveness and efficiency of friend recommendation. We evaluate our method by compare it with traditional blog similarity based recommendation method and measure the result with an automatic measurement. Result shows that our method could help provide better and more reasonable results.

According to the characteristic of auto-body inner packaging, the object-oriented case representation models of auto-body inner packaging were presented by employing the extended object model, in which the index and solution objects were appended. Knowledge of auto-body inner packaging was represented as rule and constraints, and their definitions were described with object models. The nearest neighborhood method was adopted for case retrieval. The strategies for case adaptation, integrating rule-based reasoning and constrain satisfaction, were presented to modify case solution to fit the current problem definition.

Clustered Web pages, such as blog posts, could be used to improve Web search. In this paper, we propose a folksonomy extending framework using relations in the Blogosphere and demonstrate how the framework could be used to help clustering blog posts. We evaluate the framework by comparing it with content-based folksonomy extending approach. Experiment results show that the framework does help the clustering process.