- Mengkai Shi;Yi Zhang;Danya Yao;Chang Lu;
In recent years, the Vehicle-to-Vehicle(V2V) communication system has been considered one of the most promising technologies to build a much safer and more efficient transportation system. Both simulation and field test have been extensively performed to evaluate the performance of the V2V communication system. However,most of the evaluation methods are communication-based, and although in a transportation environment, lack a V2V application-oriented analysis. In this study, we conducted real-world tests and built an application-oriented evaluation model. The experiments were classified into four scenarios: static, following, face 2 face, and crossing vertically, which almost covered all the V2V communication patterns on the road. Under these scenarios, we conducted experiments and built a probability model to evaluate the performance of 802.11p and LTE-V in safetyrelated applications. Consequently, we found out that improvements are still needed in Non-Line-of-Sight scenarios.
2019年02期 v.24 123-133页 [查看摘要][在线阅读][下载 2641K] [下载次数：140 ] |[网刊下载次数：0 ] |[引用频次：13 ] |[阅读次数：116 ] - Zhiguo Chen;Guifa Teng;Xiaolei Zhou;Tao Chen;
Localizability in large-scale, randomly deployed Wireless Sensor Networks(WSNs) is a classic but challenging issue. To become localizable, WSNs normally require extensive adjustments or additional mobile nodes. To address this issue, we utilize occasional passive events to ease the burden of localization-oriented network adjustment. We prove the sufficient condition for node and network localizability and design corresponding algorithms to minimize the number of nodes for adjustment. The upper bound of the number of adjusted nodes is limited to the number of articulation nodes in a connected graph. The results of extensive simulations show that our approach greatly reduces the cost required for network adjustment and can thus provide better support for the localization of large-scale sparse networks than other approaches.
2019年02期 v.24 134-146页 [查看摘要][在线阅读][下载 14242K] [下载次数：36 ] |[网刊下载次数：0 ] |[引用频次：2 ] |[阅读次数：70 ] - Bangbang Ren;Geyao Cheng;Deke Guo;
The use of multicast transmission can efficiently reduce the consumption of network resources by jointly serving multiple destinations with a single source node. Currently, many multicast applications impose the constraint wherein multicast flows must be processed by a series of Virtual Network Functions(VNFs) before reaching their destinations. Given a multicast transmission, there are usually multiple server nodes, each of which is able to host all the required VNFs. Thus, the multicast flow should be initially steered to one or a few selected server nodes that act as pseudo sources, and the destinations will then retrieve new flow from any of these pseudo sources.In this paper, we model this kind of multicast as an uncertain multicast with multiple pseudo sources, whose routing structure is usually a forest consisting of multiple isolated trees. We then characterize and construct the Delay-guaranteed Minimum Cost Forest(D-MCF) such that each path from the source to the destination satisfies the end-to-end delay constraint. To tackle this NP-hard problem, we design two efficient methods, the Partition Algorithm(PA) and the Combination Algorithm(CA), to approximate the optimal solution. Theoretical analyses and evaluations indicate that these two methods can generate the desired routing forest for any multicast transfer.Moreover, the PA method achieves a better balance between performance and time consumption than the CA method. The evaluation results show that PA-(Ω+20) can reduce total cost by 49:02% while consuming 12:59% more time, thus significantly outperforming the CA-(Ω+20) method.
2019年02期 v.24 147-159页 [查看摘要][在线阅读][下载 999K] [下载次数：24 ] |[网刊下载次数：0 ] |[引用频次：2 ] |[阅读次数：112 ] - Shuai Liu;Weitong Zhang;Xiaojun Wu;Shuo Feng;Xin Pei;Danya Yao;
In the connected vehicle environment, real-time vehicle-state data can be obtained through vehicle-toinfrastructure communication, and the prediction accuracy of urban traffic conditions can significantly increase.This study uses the C++/Qt programming language and framework to build a simulation platform. A two-way six-lane intersection is set up on the simulation platform. In addition, two speed guidance algorithms based on optimizing the travel time of a single vehicle or multiple vehicles are proposed. The goal of optimization is to minimize the travel time, with common indicators such as average delay of vehicles, average number of stops, and average stop time chosen as indexes of traffic efficiency. When the traffic flow is not saturated, compared with the case of no speed guidance, single-vehicle speed guidance can improve the traffic efficiency by 20%, whereas multi-vehicle speed guidance can improve the traffic efficiency by 50%. When the traffic flow is saturated, the speed guidance algorithms show outstanding performance. The effect of speed guidance gradually enhances with increasing penetration rate, and the most obvious gains are obtained when the penetration rate increases from 10% to 40%. Thus, this study has shown that speed guidance in the connected vehicle environment can significantly improve the traffic efficiency of intersections, and the multi-vehicle speed guidance strategy is more effective than the single-vehicle speed guidance strategy.
2019年02期 v.24 160-170页 [查看摘要][在线阅读][下载 1273K] [下载次数：129 ] |[网刊下载次数：0 ] |[引用频次：16 ] |[阅读次数：116 ] - Haoyang Zhu;Xiaoyong Li;Qiang Liu;Hao Zhu;
Skyline group, also named as combinational skyline or group-based skyline, has attracted more attention recently. The concept of skyline groups is proposed to address the problem in the inadequacy of the traditional skyline to answer queries that need to analyze not only individual points but also groups of points. Skyline group algorithms aim at finding groups of points that are not dominated by any other same-size groups. Although two types of dominance relationship exist between the groups defined in existing works, they have not been compared systematically under the same experimental framework. Thus, practitioners face difficulty in selecting an appropriate definition. Furthermore, the experimental evaluation in most existing works features a weakness,that is, studies only experimented on small data sets or large data sets with small dimensions. For comprehensive comparisons of the two types of definition and existing algorithms, we evaluate each algorithm in terms of time and space on various synthetic and real data sets. We reveal the characteristics of existing algorithms and provide guidelines on selecting algorithms for different situations.
2019年02期 v.24 171-182页 [查看摘要][在线阅读][下载 1451K] [下载次数：29 ] |[网刊下载次数：0 ] |[引用频次：0 ] |[阅读次数：57 ] - Atif Mughees;Linmi Tao;
A deep-learning-based feature extraction has recently been proposed for HyperSpectral Images(HSI)classification. A Deep Belief Network(DBN), as part of deep learning, has been used in HSI classification for deep and abstract feature extraction. However, DBN has to simultaneously deal with hundreds of features from the HSI hyper-cube, which results into complexity and leads to limited feature abstraction and performance in the presence of limited training data. Moreover, a dimensional-reduction-based solution to this issue results in the loss of valuable spectral information, thereby affecting classification performance. To address the issue, this paper presents a Spectral-Adaptive Segmented DBN(SAS-DBN) for spectral-spatial HSI classification that exploits the deep abstract features by segmenting the original spectral bands into small sets/groups of related spectral bands and processing each group separately by using local DBNs. Furthermore, spatial features are also incorporated by first applying hyper-segmentation on the HSI. These results improved data abstraction with reduced complexity and enhanced the performance of HSI classification. Local application of DBN-based feature extraction to each group of bands reduces the computational complexity and results in better feature extraction improving classification accuracy. In general, exploiting spectral features effectively through a segmented-DBN process and spatial features through hyper-segmentation and integration of spectral and spatial features for HSI classification has a major effect on the performance of HSI classification. Experimental evaluation of the proposed technique on well-known HSI standard data sets with different contexts and resolutions establishes the efficacy of the proposed techniques,wherein the results are comparable to several recently proposed HSI classification techniques.
2019年02期 v.24 183-194页 [查看摘要][在线阅读][下载 995K] [下载次数：93 ] |[网刊下载次数：0 ] |[引用频次：19 ] |[阅读次数：52 ] - Li Sun;Shan Sun;Tianlei Wang;Jiyun Li;Jingsheng Lin;
Adverse Drug Reaction(ADR) is one of the major challenges to the evaluation of drug safety in the medical field. The Bayesian Confidence Propagation Neural Network(BCPNN) algorithm is the main algorithm used by the World Health Organization to monitor ADRs. Currently, ADR reports are collected through the spontaneous reporting system. However, with the continuous increase in ADR reports and possible use scenarios, the efficiency of the stand-alone ADR detection algorithm will encounter considerable challenges. Meanwhile, the BCPNN algorithm requires a certain number of disk I/O, which leads to considerable time consumption. In this study,we propose a Spark-based parallel BCPNN algorithm, which speeds up data processing and reduces the number of disk I/O in BCPNN, and two optimization strategies. Then, the ADR data collected from the FDA Adverse Event Reporting System are used to verify the performance of the proposed algorithm and its optimization strategies.Experiments show that the parallel BCPNN can significantly accelerate data processing and the optimized algorithm has a high acceleration rate and can effectively prevent memory overflow. Finally, we apply the proposed algorithm to a dataset provided by a real medical consortium. Experiments further prove the performance and practical value of the proposed algorithm.
2019年02期 v.24 195-206页 [查看摘要][在线阅读][下载 1851K] [下载次数：99 ] |[网刊下载次数：0 ] |[引用频次：11 ] |[阅读次数：55 ] - Zhenyang Wang;Zhidong Deng;Shiyao Wang;
Semantic segmentation is a fundamental topic in computer vision. Since it is required to make dense predictions for an entire image, a network can hardly achieve good performance on various kinds of scenes. In this paper, we propose a cascade coarse-to-fine network called CasNet, which focuses on regions that are difficult to make pixel-level labels. The CasNet comprises three branches. The first branch is designed to produce coarse predictions for easy-to-label pixel regions. The second one learns to distinguish the relatively difficult-to-label pixels from the entire image. Finally, the last branch generates final predictions by combining both the coarse and the fine prediction results through a weighting coefficient that is estimated by the second branch. Three branches focus on their own objectives and collaboratively learn to predict from coarse-to-fine predictions. To evaluate the performance of the proposed network, we conduct experiments on two public datasets: SIFT Flow and Stanford Background. We show that these three branches can be trained in an end-to-end manner, and the experimental results demonstrate that the proposed CasNet outperforms existing state-of-the-art models, and it achieves prediction accuracy of 91.6% and 89.7% on SIFT Flow and Standford Background, respectively.
2019年02期 v.24 207-215页 [查看摘要][在线阅读][下载 3628K] [下载次数：60 ] |[网刊下载次数：0 ] |[引用频次：3 ] |[阅读次数：128 ] - Jiaqi Zhang;Xiaowei Cui;Hailong Xu;Sihao Zhao;Mingquan Lu;
As an effective deceptive interference technique for military navigation signals, meaconing can be divided into two main types: those that replay directly and those that replay after signal separation. The latter can add different delays to each satellite signal and mislead the victim receiver with respect to any designated position,thus has better controllability and concealment capability. A previous study showed there to be two main spatial processing techniques for separating military signals, whereby either multiple large-caliber antennas or antenna arrays are used to form multiple beams that align with all visible satellites. To ensure sufficient spatial resolution,the main lobe width of the antenna or beam must be sufficiently narrow, which requires the use of a large antenna aperture or a large number of array elements. In this paper, we propose a convenient and effective signal separation method, which is based on an antenna array with fewer elements. While the beam of the array is pointing to a specified satellite, the other satellite signals are regarded as interference and their power is suppressed to a level below the receiver's sensitivity. With this method, the number of array elements depends only on the number of visible satellites, thus greatly reducing the hardware cost and required processing capacity.
2019年02期 v.24 216-225页 [查看摘要][在线阅读][下载 1563K] [下载次数：37 ] |[网刊下载次数：0 ] |[引用频次：4 ] |[阅读次数：75 ] - Guohua Xi;Xibin Zhao;Yan Liu;Jin Huang;Yangdong Deng;
Railway transportation plays an important role in modern society. As China's massive railway transportation network continues to grow in total mileage and operation density, the energy consumption of trains becomes a serious concern. For any given route, the geographic characteristics are known a priori, but the parameters(e.g., loading and marshaling) of trains vary from one trip to another. An extensive analysis of the train operation data suggests that the control gear operation of trains is the most important factor that affects the energy consumption. Such an observation determines that the problem of energy-efficient train driving has to be addressed by considering both the geographic information and the trip parameters. However, the problem is difficult to solve due to its high dimension, nonlinearity, complex constraints, and time-varying characteristics. Faced with these difficulties, we propose an energy-efficient train control framework based on a hierarchical ensemble learning approach. Through hierarchical refinement, we learn prediction models of speed and gear. The learned models can be used to derive optimized driving operations under real-time requirements. This study uses random forest and bagging – REPTree as classification algorithm and regression algorithm, respectively. We conduct an extensive study on the potential of bagging, decision trees, random forest, and feature selection to design an effective hierarchical ensemble learning framework. The proposed framework was testified through simulation. The average energy consumption of the proposed method is over 7% lower than that of human drivers.
2019年02期 v.24 226-237页 [查看摘要][在线阅读][下载 4093K] [下载次数：63 ] |[网刊下载次数：0 ] |[引用频次：11 ] |[阅读次数：60 ] - Yongde Guo;Hongbing Ma;
Image blind deblurring uses an estimated blur kernel to obtain an optimal restored original image with sharp features from a degraded image with blur and noise artifacts. This method, however, functions on the premise that the kernel is estimated accurately. In this work, we propose an adaptive patch prior for improving the accuracy of kernel estimation. Our proposed prior is based on local patch statistics and can rebuild low-level features,such as edges, corners, and junctions, to guide edge and texture sharpening for blur estimation. Our prior is a nonparametric model, and its adaptive computation relies on internal patch information. Moreover, heuristic filters and external image knowledge are not used in our prior. Our method for the reconstruction of salient step edges in a blurry patch can reduce noise and over-sharpening artifacts. Experiments on two popular datasets and natural images demonstrate that the kernel estimation performance of our method is superior to that of other state-of-the-art methods.
2019年02期 v.24 238-248页 [查看摘要][在线阅读][下载 4537K] [下载次数：53 ] |[网刊下载次数：0 ] |[引用频次：9 ] |[阅读次数：59 ] <正>Tsinghua Science and Technology (Tsinghua Sci Technol), an academic journal sponsored by Tsinghua University,is published bimonthly. This journal aims at presenting the up-to-date scientific achievements with high creativity and great significance in computer and electronic engineering. Contributions all over the world are welcome.
2019年02期 v.24 249页 [查看摘要][在线阅读][下载 475K] [下载次数：11 ] |[网刊下载次数：0 ] |[引用频次：0 ] |[阅读次数：55 ]