When the world is recovering from the chaos that COVID-19 creates, the epidemic is still posing challenges to the public health system and communication. However, a case of information communication ...during the COVID-19 outbreak can provide a reference for the current information promulgate strategy in China. In January 2020, CCTV broadcasted the construction of two cabin hospitals on a 24-h Livestream (24H-LS), creating a remarkable viewing effect. We conducted a quantitative analysis based on the number of views, social media communication, and internet search index. We collected posts and comment data of the 24H-LS audience and related topics on Weibo, using sentiment classification and word frequency analysis to study the communication effect of 24H-LS from three perspectives: perception effect, psychology, and subject issue. The results show that, first, 24H-LS has attracted extensive public attention on the Internet and social media after its launch. Second, the public's perception of the risks of the COVID-19 outbreak and its uncertainty has decreased after watching the 24H-LS. At the same time, the positive emotions of the public have been enhanced to a certain extent. Third, through subject analysis, we found that the public had high participation and strong interaction in 24H-LS, which produced collective symbols and emotions. The study shows that through 24H-LS, a new information form, the media can effectively convey important information and resolve the public's fear and anxiety.
Background: Radiomics can quantify tumor phenotypic characteristics non-invasively by applying feature algorithms to medical imaging data. In this study, we investigated the association between ...radiomics features and the tumor histological subtypes, and we aimed to establish a nomogram for the classification of small cell lung cancer (SCLC) and non-small-cell lung cancer (NSCLC). Methods: This was a retrospective single center study. In total, 468 cases including 202 patients with SCLC and 266 patients with NSCLC were enrolled in our study, and were randomly divided into a training set (n = 327) and a validation set (n = 141) in a 7:3 ratio. The clinical data of the patients, including age, sex, smoking history, tumor maximum diameter, clinical stage, and serum tumor markers, were collected. All patients underwent enhanced computed tomography (CT) scans, and all lesions were pathologically confirmed. A radiomics signature was generated from the training set using the least absolute shrinkage and selection operator algorithm. Independent risk factors were identified by multivariate logistic regression analysis, and a radiomics nomogram based on the radiomics signature and clinical features was constructed. The capability of the nomogram was evaluated in the training set and validated in the validation set. Results: Fourteen of 396 radiomics parameters were screened as important factors for establishing the radiomics model. The radiomics signature performed well in differentiating SCLC and NSCLC, with an area under the curve (AUC) of 0.86 (95% CI: 0.82-0.90) in the training set and 0.82 (95% CI: 0.75-0.89) in the validation set. The radiomics nomogram had better predictive performance AUC = 0.94 (95% CI: 0.90-0.98) in the validation set than the clinical model AUC = 0.86 (95% CI: 0.80-0.93) and the radiomics signature AUC = 0.82 (95% CI: 0.75-0.89), and the accuracy was 86.2% (95% CI: 0.79-0.92) in the validation set. Conclusion: The enhanced CT radiomics signature performed well in the classification of SCLC and NSCLC. The nomogram based on the radiomics signature and clinical factors has better diagnostic performance for the classification of SCLC and NSCLC than the simple application of the radiomics signature.
The rapid development of social networks has completely changed the way people communicate and greatly promoted the interaction between people, and further generated the concept of the influence of ...social networks, which has attracted more and more scholars' attention. The purpose of this article is to summarize the current research progress and dig the gaps in the current research by combing and reviewing the existing research on social network influence. Specifically, this paper mainly analyzes the research progress of social network influence, and through summarizing and analyzing the related literatures of the social network influence of individual Weibo, the influence of user social network and the social network influence of the topic, we put forward the research progress and existing problems, based on them the direction of future research is put forward. We believe it has considerable reference value for the research of social network influence.
Water repellent is an important functional finish for cotton fabric. However, cotton fabrics often have poor washing resistance and other performances after actual finishing. In this study, based on ...the structural characteristics of cotton fiber and durability of water repellent, a cross-linked amino long-chain alkyl polysiloxane (CAHPS) was first prepared, and then reacted with modified silica. Finally, a chemically bonded organic-inorganic nanohybrid cross-linked polysiloxane (rSiO
-CAHPS) was fabricated. Furthermore, the rSiO
-CAHPS was emulsified to obtain a durable fluorine-free water repellent. The water repellent finishing for cotton fabric was carried out by the pad-dry-cure process. After finishing, the cotton fabric had good resistance to conventional liquids and excellent washing resistance, and still maintained good water repellency after 30 rounds of soaping. Moreover, properties including air permeability, mechanical property and whiteness are hardly affected after finishing. SEM and XPS characterization show that a layer of dense silicon film is formed on the surface of cotton fabric by rSiO
-CAHPS water repellent. The existence of nanosilica can improve the surface roughness of cotton fibers. The synergistic effect of fiber matrix, nanoparticles and CAHPS endows the fabric with a micro/nano-multi-scale micro-rough structure, which improves the water repellency of cotton fabric after water repellent finishing.
The corrosion of chloride-induced on concrete is affected by many factors. In this research, an innovative empirical model was developed to predict the long-term chloride migration behavior in ...concrete, considering the effects of water-cement ratio, time, bonding effect, temperature, relative humidity, and concrete deterioration. The reliability and validity of the results evaluated by the empirical prediction model were verified by the chloride concentration data in concrete specimens exposed to the marine environment for 3, 5, and 10 years reported in the literature. Combined with the established empirical prediction model, the concrete model was regarded as a three-phase composite material composed of mortar, coarse aggregate, and interfacial transition zone. The effects of key factors on chloride migration were further analyzed by using the mesoscopic finite element numerical simulation method. It was observed that when temperature increases from 5 ℃ to 65 ℃, chloride diffusion depth rises by 3.3 times. When relative humidity increases from 20% to 100%, chloride diffusion depth rises by 4.3 times. Also, the water-cement ratio, concrete deterioration, and chloride binding effect have a non-negligible impact on chloride migration.
Class imbalance learning (CIL), which aims to addressing the performance degradation problem of traditional supervised learning algorithms in the scenarios of skewed data distribution, has become one ...of research hotspots in fields of machine learning, data mining, and artificial intelligence. As a postprocessing CIL technique, the decision threshold moving (DTM) has been verified to be an effective strategy to address class imbalance problem. However, no matter adopting random or optimal threshold designation ways, the classification hyperplane could be only moved parallelly, but fails to vary its orientation, thus its performance is restricted, especially on some complex and density variable data. To further improve the performance of the existing DTM strategies, we propose an improved algorithm called CDTM by dividing majority training instances into multiple different density regions, and further conducting DTM procedure on each region independently. Specifically, we adopt the well-known DBSCAN clustering algorithm to split training set as it could adapt density variation well. In context of support vector machine (SVM) and extreme learning machine (ELM), we respectively verified the effectiveness and superiority of the proposed CDTM algorithm. The experimental results on 40 benchmark class imbalance datasets indicate that the proposed CDTM algorithm is superior to several other state-of-the-art DTM algorithms in term of G-mean performance metric.
Missing value imputation (MVI) is important for DNA microarray data analysis because microarray data with missing values would significantly degrade the performance of the downstream analysis. ...Although there have been lots of MVI algorithms for dealing with the missing DNA microarray data, we note that most of them have a lack of robustness owing to only adopting the single model. In this paper, a flexible and robust MVI algorithm named EELMimpute is proposed to address missing DNA microarray data imputation problem. First, the algorithm constructs a relevant feature space for the missing target gene, where the relevant feature space only includes those co-expression genes of the target gene based on calculating their Pearson's correlation coefficients. Then, some fix-sized feature subspaces are randomly extracted from the relevant feature space to construct extreme learning machine (ELM) regression models between the extracted genes and the target gene. Furthermore, selecting those models without missing input gene values to construct the ensemble framework, and then imputing the missing gene by calculating the average output of all models included in the ensemble framework. Experimental results show that the EELMimpute algorithm is able to reduce the estimated errors in comparison with several previous imputation algorithms.
Cost-sensitive learning is a popular paradigm to address class-imbalance learning (CIL) problem. Traditional cost-sensitive learning approaches always solve CIL problem by assigning a constant higher ...training error penalty for all minority instances than that of majority instances, but ignore the significance of location information. Therefore, several recent studies began to focus on the personalized cost assignment, i.e., designating different costs for different instances based on their location information. The emerging personalized cost-sensitive approaches always perform better than those traditional ones; however, the estimation for location information may be inaccurate as it is apt to be impacted by data density variation. To address this problem, we propose a novel location information estimation and cost assignment strategy called RUE. Unlike previous approaches, our proposed strategy explores location information by an indirect way: the error rate feed backed from a random undersampling ensemble. The strategy is robust towards data distribution, and is helpful for accurately estimating the significance of each instance regardless the complexity of data distribution. In context of Fuzzy Support Vector Machine (FSVM) and Weighted Extreme Learning Machine (WELM), the proposed cost assignment strategy is compared with several popular and state-of-the-art approaches, and the results show its effectiveness and superiority.
Learning from imbalanced data is a challenging task in the machine learning field, as with this type of data, many traditional supervised learning algorithms tend to focus more on the majority class ...while damaging the interests of the minority class. Stacking ensemble, which formulates an ensemble by using a meta-learner to combine the predictions of multiple base classifiers, has been used for solving class imbalance learning issues. Specifically, in the context of class imbalance learning, a stacking ensemble learning algorithm is generally considered to combine with a specific sampling algorithm. Such an operation, however, might suffer from suboptimization problems as only using a sampling strategy may make it difficult to acquire diverse enough features. In addition, we also note that using all of these features may damage the meta-learner as there may exist noisy and redundant features. To address these problems, we have proposed a novel stacking ensemble learning algorithm named MSFSS, which divides the learning procedure into two phases. The first stage combined multiple sampling algorithms and multiple supervised learning approaches to construct meta feature space by means of cross combination. The adoption of this strategy satisfied the diversity of the stacking ensemble. The second phase adopted the whale optimization algorithm (WOA) to select the optimal sub-feature combination from the meta feature space, which further improved the quality of the features. Finally, a linear regression classifier was trained as the meta learner to conduct the final prediction. Experimental results on 40 benchmarked imbalanced datasets showed that the proposed MSFSS algorithm significantly outperformed several popular and state-of-the-art class imbalance ensemble learning algorithms. Specifically, the MSFSS acquired the best results in terms of the F-measure metric on 27 datasets and the best results in terms of the G-mean metric on 26 datasets, out of 40 datasets. Although it required consuming more time than several other competitors, the increment of the running time was acceptable. The experimental results indicated the effectiveness and superiority of the proposed MSFSS algorithm.
Heterogeneous cross-project defect prediction (HCPDP) aims to learn a prediction model from a heterogeneous source project and then apply the model to a target project. Existing HCPDP works mapped ...the data of the source and target projects in a common space. However, the pre-defined forms of mapping methods often limit prediction performance and it is difficult to measure the distance between two data instances from different feature spaces. This paper introduced optimal transport (OT) theory for the first time to build the relationship between source and target data distributions, and two prediction algorithms were proposed based on OT theory. In particular, an algorithm based on the Gromov-Wasserstein (EGW) entropic discrepancy was developed to perform the HCPDP model. The proposed EGW model measures the distance between two metric spaces by learning an optimal transfer matrix with the minimum data transfer cost and avoids measuring the distance of two instances of different feature spaces. Then, to improve EGW performance, an EGW+ transport algorithm based on EGW was developed by integrating target labels. Experimental results showed the effectiveness of EGW and EGW+ methods, and proved that our methods can support developers to find the defects in the early phase of software development.
PDF
