Xinheng Wang

Xinheng Wang


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 May 2020 in IEEE Access
Verified
Journal Article
Open access
FZFen Zhao
Fen Zhao
YLYinguo Li
Yinguo Li
XWXinheng Wang
Xinheng Wang
LBLing Bai
Ling Bai
TLTailin Liu
Tailin Liu
Capsule network is a promising model in computer vision. It has achieved excellent results on simple datasets such as MNIST, but the performance deteriorates as data becomes complicated. In order to address this issue, we propose a deep capsule network in this paper. To deepen the capsule network, we present a new tensor capsule based routing algorithm and the corresponding convolution operation. Compared to vector capsules, tensor capsules can capture more instance-level information. Together, the relevant convolution operation is beneficial for reducing the amount of parameters in the routing process. Furthermore, we propose a dropout mechanism for vectors and tensors in order to alleviate the potential overfitting problem. Finally, we also inject the multi-scale capsules of the middle layers into a multi-scale decoder to pursue more details of an image and more clear reconstructed image. Experimental results on CIFAR10, Fashion-MNIST, and SVHN demonstrate that the proposed deep tensor network can achieve very competitive performance compared to other state-of-the-art capsule networks.

1 November 2017 in IEEE Communications Letters
Verified
Journal Article
Closed access
XWXinheng Wang
Xinheng Wang
CXChuan Xu
Chuan Xu
GZGuofeng Zhao
Guofeng Zhao
SYShui Yu
Shui Yu
Recently, network function virtualization (NFV) has been widely used in 5G innovation. However, with the implementation of NFV, virtualized wireless access point has suffered a significant performance degradation. In this letter, we propose an efficient packet processing scheme (Tuna) to improve the performance of wireless network virtualization. Specifically, we locate management frame into user space for virtualization, and place control and data frame in kernel space to reduce packet processing delay. Moreover, hostapd and network address translation are modified to accelerate packet processing. We implemented the prototype of the proposed scheme, and the experimental results demonstrate that Tuna can improve both delay and throughput dramatically.

2 April 2020 in IEEE Access
Verified
Journal Article
Open access
FZFen Zhao
Fen Zhao
YLYinguo Li
Yinguo Li
LBLing Bai
Ling Bai
ZTZhen Tian
Zhen Tian
XWXinheng Wang
Xinheng Wang
With the rapid growth of advanced driving assistance technology, how to implement humancar interaction humanely and personally becomes increasingly important. Existing methods typically rely on hand-crafted data to conduct training, which cannot fully extract information hidden in text. In this paper, we tackle the problem of label data acquisition difficulties and inadequate feature extraction via semisupervised learning and multi-granularity learning. To fulfill the goal of label data acquisition and feature extraction, we present a novel semi-supervised multi-granularity convolutional neural networks (CNNs)- based (SSMGCNNs-based) model for an application in human-car interaction, which consists of the twoview- embedding (TVE) module and the multi-granularity CNNs (MGCNNs) module. The TVE module learns embeddings of text regions from the unlabeled user command data set and then integrate the learned tv-embeddings into MGCNNs, so that the learned tv-embedded regions are used as an additional input into MGCNNs’ convolution layer to solve the problem of data annotation. MGCNNs can fully extract information hidden in text by multiple convolution kernels of the same convolution layer. We compared our model with some state-of-the-art machine learning models. On the car operation command data set, the simulation results demonstrated that, compared with CNNs, our method respectively improved 5.13%, 5.64%, 3.60% and 5.34% on precision, recall, F-1 and training loss.

13 March 2018 in IEEE Access
Verified
Journal Article
Open access
XWXinheng Wang
Xinheng Wang
CXChuan Xu
Chuan Xu
GZGuofeng Zhao
Guofeng Zhao
KXKun Xie
Kun Xie
SYShui Yu
Shui Yu
Inspired by the concept of software-defined network and network function virtualization, vast virtual networks are generated to isolate and share wireless resources for different network operators. To achieve fine-grained resource control and scheduling among virtual networks (VNs), network performance monitoring is essential. However, due to limitation of hardware, real-time performance monitoring is impossible for a complete virtual network. In this paper, taking advantage of the low-rank characteristic of 90 virtual access points (VAPs) measurement data, we propose an intelligent measurement scheme, namely, adaptive and sequential sampling based on matrix completion (MC), which exploits from the MC to construct the complete data of VN performance from a partial direct monitoring data. First, to construct the initial measurement matrix, we propose a sampling correction model based on dispersion and coverage. Second, a stopping condition for the sequential sampling is introduced, based on the stopping condition, the sampling process for a period can stop without waiting for the matrix reconstruction to reach certain of accuracy level. Finally, the sampled VAPs are determined by referring the backforth completed matrixes' normalized mean absolute error. The experiments show that our approach can achieve a constant network perception and maintain a relatively low error rate with a small sampling rate.

8 February 2017 in Applied Sciences
Verified
Journal Article
Open access
PDF file
XWXinheng Wang
Xinheng Wang
CXChuan Xu
Chuan Xu
WJWenqiang Jin
Wenqiang Jin
JWJiajie Wang
Jiajie Wang
QWQianyun Wang
Qianyun Wang
GZGuofeng Zhao
Guofeng Zhao
The past years have witnessed the significant development of the Internet. Numerous emerging network architectures and protocols have triggered the demand for traffic generators which stand in stark contrast to previous schemes. Namely, fixed test content is inefficient in the presence of such a dynamic and realistic demand. Moreover, the requirement of high-performance has raised the stakes on developing a new concurrent system. In this paper, we present a hierarchical parallel design for a Web traffic generator on a TILERAGX36 processor, called TGMP. We discuss the challenges in developing its hierarchical architectural design, and elaborate on its implementation details. Specifically, in order to generate a realistic network workload over a long and large time scale, we propose a user-control scheme based on cubic spline interpolation. To better improve the scalability of the system and satisfy the required flow rate, we adopt techniques, including optimization of parameters under the Linux kernel, event-driven concurrency, and parallel architectures of a TILERAGX36 processor. The experimental results demonstrate that TGMP is able to create real traffic and simulate 50,000 users accessing the Web server simultaneously.