A Novel Method of Heart Failure Prediction Based on DPCNNXGBOOST Model

The occurrence of perioperative heart failure will affect the quality of medical services and threaten the safety of patients. Existing methods depend on the judgment of doctors, the results are affected by many factors such as doctors’ knowledge and experience. The accuracy is difficult to guarantee and has a serious lag. In this paper, a mixture prediction model is proposed for perioperative adverse events of heart failure, which combined with the advantages of the Deep Pyramid Convolutional Neural Networks (DPCNN) and Extreme Gradient Boosting (XGBOOST). The DPCNN was used to automatically extract features from patient’s diagnostic texts, and the text features were integrated with the preoperative examination and intraoperative monitoring values of patients, then the XGBOOST algorithm was used to construct the prediction model of heart failure. An experimental comparison was conducted on the model based on the data of patients with heart failure in southwest hospital from 2014 to 2018. The results showed that the DPCNN-XGBOOST model improved the predictive sensitivity of the model by 3% and 31% compared with the text-based DPCNN Model and the numeric-based XGBOOST Model.     

Complementary Kalman Filter as a Baseline Vector Estimator for GPS-Based Attitude Determination

The Global Positioning System (GPS) offers the interferometer for attitude determination by processing the carrier phase observables. By using carrier phase observables, the relative positioning is obtained in centimeter level. GPS interferometry has been firstly used in precise static relative positioning, and thereafter in kinematic positioning. The carrier phase differential GPS based on interferometer principles can solve for the antenna baseline vector, defined as the vector between the antenna designated master and one of the slave antennas, connected to a rigid body. Determining the unknown baseline vectors between the antennas sits at the heart of GPS-based attitude determination. The conventional solution of the baseline vectors based on least-squares approach is inherently noisy, which results in the noisy attitude solutions. In this article, the complementary Kalman filter (CKF) is employed for solving the baseline vector in the attitude determination mechanism to improve the performance, where the receiversatellite double differenced observable was utilized as the measurement. By using the carrier phase observables, the relative positioning is obtained in centimeter level. Employing the CKF provides several advantages, such as accuracy improvement, reliability enhancement, and real-time assurance. Simulation results based on the conventional method where the least-squares approach is involved, and the proposed method where the CKF is involved are compared and discussed.     

Empirical Analysis of Agricultural Cultural Resources Value Evaluation under DEA Model

Agricultural culture is a productive activity about education and management. It aims at high efficiency and high quality, uses technology as its means, and takes nature as its carrier. Agricultural cultural resources are the product of the rapid development of modern economy. It promotes the development of the national economy and profoundly affects people's production and life. DEA model, also known as data envelope analysis method, is an algorithm that uses multiple data decision units for input and output training to obtain the final model. This article explains the concept and basic characteristics of agricultural culture. Through questionnaire surveys and expert interviews, we collected development data, screened human, material, and financial data, and calculated information on economic and social resources. On this basis, this paper establishes the evaluation index of agricultural culture based on DEA model. Then, through empirical analysis from a specific perspective, it can be concluded that increasing human, material and financial input can achieve economic and social benefits. Generally speaking, cultural investment can promote the development of the industry. The research results of this paper laid a theoretical foundation for the development of agricultural culture, and put forward a development model focusing on technology development, improving investment efficiency, and investing in material resources.     

Multi-Purpose Forensics of Image Manipulations Using Residual- Based Feature

The multi-purpose forensics is an important tool for forge image detection. In this paper, we propose a universal feature set for the multi-purpose forensics which is capable of simultaneously identifying several typical image manipulations, including spatial low-pass Gaussian blurring, median filtering, re-sampling, and JPEG compression. To eliminate the influences caused by diverse image contents on the effectiveness and robustness of the feature, a residual group which contains several highpass filtered residuals is introduced. The partial correlation coefficient is exploited from the residual group to purely measure neighborhood correlations in a linear way. Besides that, we also combine autoregressive coefficient and transition probability to form the proposed composite feature which is used to measure how manipulations change the neighborhood relationships in both linear and non-linear way. After a series of dimension reductions, the proposed feature set can accelerate the training and testing for the multipurpose forensics. The proposed feature set is then fed into a multi-classifier to train a multi-purpose detector. Experimental results show that the proposed detector can identify several typical image manipulations, and is superior to the complicated deep CNN-based methods in terms of detection accuracy and time efficiency for JPEG compressed image with low resolution.     

Image and Feature Space Based Domain Adaptation for Vehicle Detection

The application of deep learning in the field of object detection has experienced much progress. However, due to the domain shift problem, applying an off-the-shelf detector to another domain leads to a significant performance drop. A large number of ground truth labels are required when using another domain to train models, demanding a large amount of human and financial resources. In order to avoid excessive resource requirements and performance drop caused by domain shift, this paper proposes a new domain adaptive approach to cross-domain vehicle detection. Our approach improves the cross-domain vehicle detection model from image space and feature space. We employ objectives of the generative adversarial network and cycle consistency loss for image style transfer in image space. For feature space, we align feature distributions between the source domain and the target domain to improve the detection accuracy. Experiments are carried out using the method with two different datasets, proving that this technique effectively improves the accuracy of vehicle detection in the target domain.     

MOOC Learner’s Final Grade Prediction Based on an Improved Random Forests Method

Massive Open Online Course (MOOC) has become a popular way of online learning used across the world by millions of people. Meanwhile, a vast amount of information has been collected from the MOOC learners and institutions. Based on the educational data, a lot of researches have been investigated for the prediction of the MOOC learner’s final grade. However, there are still two problems in this research field. The first problem is how to select the most proper features to improve the prediction accuracy, and the second problem is how to use or modify the data mining algorithms for a better analysis of the MOOC data. In order to solve these two problems, an improved random forests method is proposed in this paper. First, a hybrid indicator is defined to measure the importance of the features, and a rule is further established for the feature selection; then, a Clustering-Synthetic Minority Over-sampling Technique (SMOTE) is embedded into the traditional random forests algorithm to solve the class imbalance problem. In experiment part, we verify the performance of the proposed method by using the Canvas Network Person-Course (CNPC) dataset. Furthermore, four well-known prediction methods have been applied for comparison, where the superiority of our method has been proved.     

美国大数据战略及对我国启示

美国当前在大数据方面全球领先。2010年奥巴马将发展大数据上升为国家战略,建立了一系列负责大数据的专门机构,发布大量相关战略性文件和法令。大数据在美国各个领域得到广泛应用,并基本成体系。当前我国大数据发展取得进步但仍存在问题,借鉴美国大数据战略的具体做法可为完善我国大数据战略提供较好的参考价值。     

Preparation of Aqueous Nanodispersions of Disperse Dye by High-Gravity Technology and Spray Drying

Disperse dyes are poorly water-soluble and difficult to stably disperse in an aqueous medium, which greatly limits their application in dyeing synthetic fibers. Micronization can solve this problem. Herein, a facile way to prepare stable aqueous nanodispersions of disperse dye (C.I. disperse yellow 54) is presented by combining high-gravity antisolvent precipitation in a rotating packed bed (RPB) with spray drying. The as-prepared product had an average particle size of 120 nm, which could be readily redispersed in water. Compared with raw dye, the wettability and dispersibility of disperse dye nanoparticles were remarkably improved. Furthermore, the dyeing properties of the nanodispersions were obviously better than those of the commercial dye, which was micronized by ball milling.     

Hypoxia-Responsive Class III Peroxidases in Maize Roots: Soluble and Membrane-Bound Isoenzymes

Flooding induces low-oxygen environments (hypoxia or anoxia) that lead to energy disruption and an imbalance of reactive oxygen species (ROS) production and scavenging enzymes in plants. The influence of hypoxia on roots of hydroponically grown maize (Zea mays L.) plants was investigated. Gene expression (RNA Seq and RT-qPCR) and proteome (LC–MS/MS and 2D-PAGE) analyses were used to determine the alterations in soluble and membrane-bound class III peroxidases under hypoxia. Gel-free peroxidase analyses of plasma membrane-bound proteins showed an increased abundance of ZmPrx03, ZmPrx24, ZmPrx81, and ZmPr85 in stressed samples. Furthermore, RT-qPCR analyses of the corresponding peroxidase genes revealed an increased expression. These peroxidases could be separated with 2D-PAGE and identified by mass spectrometry. An increased abundance of ZmPrx03 and ZmPrx85 was determined. Further peroxidases were identified in detergent-insoluble membranes. Co-regulation with a respiratory burst oxidase homolog (Rboh) and key enzymes of the phenylpropanoid pathway indicates a function of the peroxidases in membrane protection, aerenchyma formation, and cell wall remodeling under hypoxia. This hypothesis was supported by the following: (i) an elevated level of hydrogen peroxide and aerenchyma formation; (ii) an increased guaiacol peroxidase activity in membrane fractions of stressed samples, whereas a decrease was observed in soluble fractions; and (iii) alterations in lignified cells, cellulose, and suberin in root cross-sections.     

Demonstration of pseudo-ductility in unidirectional hybrid composites made of discontinuous carbon/epoxy and continuous glass/epoxy plies

A new, partially discontinuous architecture is proposed to improve the mechanical performance of pseudo-ductile, unidirectional (UD) interlayer carbon/glass hybrid composites. The concept was successfully demonstrated in different laminates with high strength and high modulus carbon and S-glass epoxy UD prepregs. The novel hybrid architecture provided pseudo-ductile tensile stress–strain responses with a linear initial part followed by a wide plateau and a second linear part, all connected by smooth transitions. The best hybrid configuration showed 60% improvement in modulus compared to pure glass, 860 MPa plateau stress and 2% pseudo-ductile strain. The initial modulus, the plateau stress and the overall tensile stress–strain response of each specimen configuration were predicted accurately.