摘要：
The batch verification methods can relieve the bottleneck problem of vehicular authentication efficiency to accelerate the authentication speed during the group construction phase. However, in current batch verification methods, there exist some deficiencies such as the authentication methods applied in the actual scenario are sensitive to the group initialization and dynamic construction process and the intra-group communication efficiency have not been improved due to lack of effective dynamic group management. This paper proposes a fast and secure batch verification scheme based on dynamic group management and certificateless public-key cryptography. First, the two-way authentication between the proxy vehicle and the roadside unit (RSU) is established, and then the batch verification method relying on RSU-assisted are proposed based on dynamic management of the intra-group vehicles. Our method fully considers the security requirements of the group while solving certification efficiency. Theoretical analysis and simulation experiments show that compared with other existing solutions, the verification scheme in this paper reduces the computational delay and transmission overhead whilst increasing robustness in dynamic environments.
摘要：
International Classification of Diseases (ICD) code is an important label of electronic health record. The automatic ICD code assignment based on the narrative of clinical documents is an essential task which has drawn much attention recently. When Chinese clinical notes are the input corpus, the nature of Chinese brings some issues that need to be considered, such as the accuracy of word segmentation and the representation of single Chinese characters which contain semantics. Taking the lengthy text of patient notes and the representation of Chinese words into account, we present a multilayer attention bidirectional recurrent neural network (MA-BiRNN) model to implement the assignment of disease codes. A hierarchical approach is used to represent the feature of discharge summaries without manual feature engineering. The combination of character level embedding and word level embedding can improve the representation of words. Attention mechanism is introduced into bidirectional long short term memory networks, which helps to solve the performance dropping problem when plain recurrent neural networks encounter long text sequences. The experiment is carried out on a real-world dataset containing 7732 admission records in Chinese and 1177 unique ICD-10 labels. The proposed model achieves 0.639 and 0.766 in F1-score on full-level code and block-level code, respectively. It outperforms the baseline neural network models and achieves the lowest Hamming loss value. Ablation analysis indicates that the multilevel attention mechanism plays a decisive role in the system for dealing with Chinese clinical notes.
作者：
Ying Yu;Min Li 0007;Liangliang Liu 0001;Yaohang Li;Jianxin Wang 0001
期刊：
大数据挖掘与分析(英文),2019年2(4):288-305 ISSN：2096-0654
通讯作者：
Wang, Jianxin(yaohang@odu.edu)
作者机构：
[Ying Yu; Min Li 0007; Liangliang Liu 0001; Jianxin Wang 0001] School of Computer Science and Engineering, Central South University, Changsha;410083, China;School of Computer Science and Technology, University of South China, Hengyang;421001, China;[Yaohang Li] Department of Computer Science, Old Dominion University, Norfolk
通讯机构：
[Wang, J.] S;School of Computer Science and Engineering, China
关键词：
Clinical data;Clinical note;Deep learning;Electronic health record (EHR);Medical image
摘要：
LTE-A技术是在LTE(长期演进)技术基础上进一步提升的移动通信标准.随着LTE-A技术的快速发展,用户群日益扩大,使其成为潜在的、发展空间巨大的隐信道媒介.在本文中,我们基于LTE-A系统提出了一种新型的时序型鲁棒隐信道TCCBL(Timing Covert Channel Based on LTE-A). TCCBL利用包数据单元( PDU)头部中的序列号( SN)来选择传输隐蔽信息的数据包,然后利用所选中数据包负载中的附加位元来传输隐蔽信息.特别地,我们利用一个预先共享的哈希函数和一个独立的变量来实现不同的信息嵌入规则,保证了我们所设计隐信道的灵活性.
会议论文集名称：
DEStech Transactions on Computer Science and Engineering
关键词：
Complex networks;Routing strategy;Effective path;Local visibility and Detecting communities
摘要：
A routing strategy using nodes' effective path and dynamic information weight distribution was proposed, which based on the improved efficient path routing strategy in complex network. The strategy's weight factor was optimized by the new strategy, Considering the insufficient of local routing strategies in global performance and the community division technology in complex network, a kind of local visibility routing strategy according to the thought of community division was presented. On the condition of community division of the Bgll condensation algorithm, the topology structure information of neighbor nodes and all the community nodes were only stored in each node's routing list in the new strategy. When node transaction in community, global routing strategy was adopted and when between communities, minimum load strategy will be used. The simulation results indicate that in the different connection density networks, the performance of the new strategy achieves the best when community division's degree of modularization is the highest. Contrasted to other local routing strategy, the optimized strategy holds incomparable superiority on throughput, transmission delay and the packet loss.
期刊：
Lecture Notes in Electrical Engineering,2018年425:86-93 ISSN：1876-1100
通讯作者：
Wang, Liqun(guoshuqiang@gmail.com)
作者机构：
[Han, Sunyi; Wang, Liqun; Shi, Xuenan] School of Information Engineering, Northeast Electric Power University Jilin, Jilin, 132012, China;[Jinchi] School of Computer Science and Technology, University of South China, China
会议名称：
14th International Conference on Semantics, Knowledge and Grids (SKG)
会议时间：
SEP 12-14, 2018
会议地点：
Guangzhou, PEOPLES R CHINA
会议主办单位：
[Chen, Xianglong;Ouyang, Chunping;Liu, Yongbin;Luo, Lingyun;Yang, Xiaohua] Univ South China, Sch Comp Sci & Technol, Hengyang 421001, Peoples R China.
会议论文集名称：
International Conference on Semantics Knowledge and Grids
关键词：
Text classification;Deep learning;CNN;RNN
摘要：
Deep learning has shown its effectiveness in many tasks such as text classification and computer vision. Most text classification tasks are concentrated in the use of convolution neural network and recurrent neural network to obtain text feature representation. In some researches, Attention mechanism is usually adopted to improve classification accuracy. According to the target of task 6 in NLP&CC2018, a hybrid deep learning model which combined BiGRU, CNN and Attention mechanism was proposed to improve text classification. The experimental results show that the Fl-score of the proposed model successfully excels the task's baseline model. Besides, this hybrid Deep Learning model gets higher Precision, Recall and Fl-score comparing with some other popular Deep Learning models, and the improvement of on Fl-score is 5.4% than the single CNN model.
摘要：
A routing strategy using nodes' effective path and dynamic information weight distribution was proposed,which based on the improved efficient path routing strategy in complex network.The strategy's weight factor was optimized by the new strategy,and it was compared with the shortest path routing strategy with the traditional routing strategy and the strategy in the view of nodes' efficient path.Simulation results show that the proposed strategy can effectively improve the network throughput without increase average data packet transmission delay.Considering the insufficient of local routing strategies in global performance and the community division technology in complex network,a kind of local visibility routing strategy according to the thought of community division was presented.On the condition of community division of the BGLL condensation algorithm,the topology structure information of neighbor nodes and all the community nodes were only stored in the each node's routing list in the new strategy.When node transaction in community,global routing strategy was adopted and when between communities,minimum load strategy will be used.The simulation results indicate that in the different connection density networks,the performance of the new strategy achieves the best when community division's degree of modularization is the highest.Contrasted to other local routing strategy,the optimized strategy holds incomparable superiority on Throughput,Transmission delay and the Packet Loss.
