Search

Graphs are effective for representing various relationships in the real world and have been successfully applied in many areas, such as publication citations and movie networks. Compared to homogeneous graphs (i.e., nodes and edges of a single relation type), heterogeneous graphs have heterogeneity and richer information (i.e., nodes and edges of different relation types). How to tackle complex non-pairwise graph-structured data and model various relation-types is a daunting challenge for heterogenous graphs. However, the existing unsupervised methods focus on node attribute learning, while node neighborhood information utilizes very limited because they only consider node propagation that is within few steps. In this paper, we propose an unsupervised method, called APPTE, that models adequate node neighborhood information in local context, and captures the global neighborhood information. Meanwhile, our method considers the robustness and generalization ability. Specifically, we construct approximate personalized propagation in local context to utilize an infinite number of neighborhood aggregation layers for extending node neighborhood propagation range, and then fuse these local context to capture global neighborhood information. Additionally, we improve the robustness and generalization ability of model, employing throwedge to increase the randomness and diversity of the graph connections by randomly deleting a part of edges. The experimental results on three benchmark datasets containing heterogeneous graphs demonstrate that our proposed method is superior to the available state-of-the-art methods. The research was partially funded by the Key Program of the National Natural Science Foundation of China (Grant Nos. 61133005, 61432005) and National Natural Science Foundation of China (Grant Nos. 62172151, 61876061).

In the era of big data, practical applications in various domains continually generate large-scale time-series data. Among them, some data show significant or potential periodicity characteristics, such as meteorological and financial data. It is critical to efficiently identify the potential periodic patterns from massive time-series data and provide accurate predictions. In this paper, a Periodicity-based Parallel Time Series Prediction (PPTSP) algorithm for large-scale time-series data is proposed and implemented in the Apache Spark cloud computing environment. To effectively handle the massive historical datasets, a Time Series Data Compression and Abstraction (TSDCA) algorithm is presented, which can reduce the data scale as well as accurately extracting the characteristics. Based on this, we propose a Multi-layer Time Series Periodic Pattern Recognition (MTSPPR) algorithm using the Fourier Spectrum Analysis (FSA) method. In addition, a Periodicity-based Time Series Prediction (PTSP) algorithm is proposed. Data in the subsequent period are predicted based on all previous period models, in which a time attenuation factor is introduced to control the impact of different periods on the prediction results. Moreover, to improve the performance of the proposed algorithms, we propose a parallel solution on the Apache Spark platform, using the Streaming real-time computing module. To efficiently process the large-scale time-series datasets in distributed computing environments, Distributed Streams (DStreams) and Resilient Distributed Datasets (RDDs) are used to store and calculate these datasets. Extensive experimental results show that our PPTSP algorithm has significant advantages compared with other algorithms in terms of prediction accuracy and performance.

The current developing situation and prospect of chemical industry of Shandong Province is reviewed and analyzed. The chemical industry of Shandong Province has developed rapidly with a large economic aggregate, and has become one of the pillar industries of Shandong Province. However, its structure is not reasonable and its processing depth is inadequate. This paper points out the main contradiction in the developing process of chemical industry of Shandong Province and its main environmental problems. Combined with the relative industry policies issued by the Country and Shandong Province, several suggestions and recommendations on implementing the sustainable development strategy in chemical industry of Shandong Province are brought out, which includes promulgating the related policies and regulations to establish a threshold of environmental admittance for new chemical projects, gathering the chemical projects into the centralized areas, paying attention to the construction of environmental infrastructure facilities and its perfection of the chemical industry parks, and strengthening the supervision and management of environmental risk of the chemical projects, as aims to harmonize economic development and environmental protection, and to realize the harmonious state of society, environment and human beings, on the base of a fast economic progress of chemical industry. © 2011 Published by Elsevier Ltd. Selection and peer-review under responsibility of RIUDS

Background: Standards in treatment of acute cholecystitis (AC) in the elderly and high-risk patients has not been established. Our study evaluated the efficacy and safety of B-mode ultrasound-guided percutaneous transhepatic gallbladder drainage (PTGD) in combination with laparoscopic cholecystectomy (LC) for acute cholecystitis (AC) in elderly and high-risk patients. Methods: Our study enrolled 35 elderly and high-risk AC patients, hospitalized between January 2010 and April 2014 at the Wenzhou People's Hospital. The patients underwent B-mode ultrasound-guided PTGD and LC (PTGD + LC group). As controls, a separate group of 35 elderly and high-risk AC patients who underwent LC alone (LC group) during the same period at the same hospital were randomly selected from a pool of 186 such cases. The volume of bleeding, surgery time, postoperative length of stay, conversion rate to laparotomy and complication rates (bile leakage, bleeding, incisional hernia, incision infection, pulmonary infarction and respiratory failure) were recorded for each patient in the two groups. Results: All patients in the PTGD + LC group successfully underwent PTGD. In the PTGD + LC group, abdominal pain in patients was relieved and leukocyte count, alkaline phosphatase level, total bilirubin and carbohydrate antigen 19-9 (CA19-9) decreased to normal range, and alanine aminotransferase and aspartate aminotransferase levels improved significantly within 72 h after treatment. All patients in the PTGD + LC group underwent LC within 6–10 weeks after PTGD. Our study revealed that PTGD + LC showed a significantly higher efficacy and safety compared to LC alone in AC treatment, as measured by the following parameters: duration of operation, postoperative length of hospital stay, volume of bleeding, conversion rate to laparotomy and complication rate (operation time of LC: 55.6 ± 23.3 min vs. 91.35 ± 25.1 min; hospitalized period after LC: 3.0 ± 1.3 d vs. 7.0 ± 1.7 d; intraoperative bleeding: 28.7 ± 15.2 ml vs. 60.38 ± 16.4 ml; conversion to laparotomy: 3 cases vs. 10 cases; complication: 3 cases vs. 8 cases; all P

The article introduces the JB (Jade Bird) Component Library system-JBCL. The goal of JBCL is to describe, manage, store and retrieve components. Based on the JB component model, the JB Component Library Data Model is developed. JBCL provides three sets of tools to assist users and managers to make best use of the JB component library, and uses a faceted method as the main classification strategy, and uses some other methods as auxiliary. Accordingly, it provides multiple retrieval means.

In-network caching, a typical feature of information centric networking (ICN) architecture, has played an important role on the network performance. Existing caching management strategies mainly focus on minimizing the redundancy content by exploiting either node data or content data respectively, which may not lead to effectively improve the caching performance, as there is no consideration on supplementary action of these two types of data. In this paper, the correlation between node data and content data brought by the big data are analyzed and mined to determine whether the selected content are cached in a few suitable nodes, and a Big data driven Adaptive In-network Caching management strategy (BAIC) is proposed. Driven by the current state of node and content, a novel multidimensional state attribution data model including network, node and content data is proposed. Based on the data model, the mapping relationship between the status data and the matching relationship value is further analyzed and mined. And then utilizing this mapping relationship function, the matching algorithm to predict the matching relationship between the node and the content in the next time period is proposed. The simulation experiments demonstrate that the proposed BAIC has significantly improved the network performance.