scispace - formally typeset
Search or ask a question
Institution

Xidian University

EducationXi'an, China
About: Xidian University is a education organization based out in Xi'an, China. It is known for research contribution in the topics: Antenna (radio) & Synthetic aperture radar. The organization has 32099 authors who have published 38961 publications receiving 431820 citations. The organization is also known as: University of Electronic Science and Technology at Xi'an & Xīān Diànzǐ Kējì Dàxué.


Papers
More filters
Journal ArticleDOI
TL;DR: Three fusion methods are proposed to solve the problem of automatic modulation classification in wireless communications, such as voting-based fusion, confidence- based fusion, and feature-based Fusion, and the results show that the three fusion methods perform better than the non-fusion method.
Abstract: An automatic modulation classification has a very broad application in wireless communications. Recently, deep learning has been used to solve this problem and achieved superior performance. In most cases, the input size is fixed in convolutional neural network (CNN)-based modulation classification. However, the duration of the actual radio signal burst is variable. When the signal length is greater than the CNN input length, how to make full use of the complete signal burst to improve the classification accuracy is a problem needs to be considered. In this paper, three fusion methods are proposed to solve this problem, such as voting-based fusion, confidence-based fusion, and feature-based fusion. The simulation experiments are done to analyze the performance of these methods. The results show that the three fusion methods perform better than the non-fusion method. The performance of the two fusion methods based on confidence and feature is very close, which is better than that of the voting-based fusion.

104 citations

Journal ArticleDOI
TL;DR: This article proposes a novel heterogeneous statistical QoS provisioning architecture for 5G mobile wireless networks and shows that the proposed architecture and schemes significantly outperform the existing traditional statistical delay-bounded QS provisioning schemes in terms of satisfying the heterogeneous delay- bounded QoS requirements while maximizing the aggregate system throughput over 5GMobile wireless networks.
Abstract: As a critical step towards the next new era of mobile wireless networks, recently 5G mobile wireless networks have received significant research attention and efforts from both academia and industry. The 5G mobile wireless networks are expected to provide different delay-bounded QoS guarantees for a wide spectrum of services, applications, and users with extremely diverse requirements. Since the time-sensitive services in 5G multimedia wireless networks may vary dramatically in both a large range from milliseconds to a few seconds and diversity from uniform/ constant delay-bound to different/variable delay-bound guarantees among different wireless links, the delay-bound QoS requirements for different types of services promote the newly emerging heterogeneous statistical delay-bounded QoS provisioning over 5G mobile wireless networks, which, however, imposes many new challenging issues not encountered before in 4G wireless networks. To overcome these new challenges, in this article we propose a novel heterogeneous statistical QoS provisioning architecture for 5G mobile wireless networks. First, we develop and analyze the new heterogeneous statistical QoS system model by applying and extending the effective capacity theory. Then, through the wireless coupling channels, we apply our proposed heterogeneous statistical QoS architecture to efficiently implement the following powerful 5G-candidate wireless techniques: 1) device-to-device networks; 2) full-duplex networks; and 3) cognitive radio networks, respectively, for providing heterogeneous statistical delay-bounded QoS guarantees. Finally, using the simulation experiments we show that our proposed architecture and schemes significantly outperform the existing traditional statistical delay-bounded QoS provisioning schemes in terms of satisfying the heterogeneous delay-bounded QoS requirements while maximizing the aggregate system throughput over 5G mobile wireless networks.

104 citations

Proceedings ArticleDOI
23 Oct 2006
TL;DR: The results of the experiments show that these two new strategies of natural exponential functions converge faster than linear one during the early stage of the search process, which is good news for most continuous optimization problems.
Abstract: Inertia weight is one of the most important parameters of particle swarm optimization (PSO) algorithm. Based on the basic idea of decreasing inertia weight (DIW), two strategies of natural exponential functions were proposed. Four different benchmark functions were used to evaluate the effects of these strategies on the PSO performance. The results of the experiments show that these two new strategies converge faster than linear one during the early stage of the search process. For most continuous optimization problems, these two strategies perform better than the linear one.

104 citations

Journal ArticleDOI
TL;DR: This letter investigates the effect of non-parallel misalignment on the channel capacity of the RF-OAM communication system equipped with uniform circular array and proposes a transmit/receive beam steering approach to circumvent the large performance degradation.
Abstract: Radio frequency-orbital angular momentum (RF-OAM) is a technique that provides extra degrees of freedom to improve spectrum efficiency of wireless communications However, OAM requires perfect alignment of the transmit and the receive antennas and this harsh precondition greatly challenges practical applications of RF-OAM In this letter, we first investigate the effect of non-parallel misalignment on the channel capacity of the RF-OAM communication system equipped with uniform circular array Then, we propose a transmit/receive beam steering approach to circumvent the large performance degradation in not only non-parallel case, but also off-axis and other general misalignment cases The effectiveness of the beam steering approach is validated through both mathematical analysis and numerical simulations

104 citations

Proceedings ArticleDOI
18 Jun 2018
TL;DR: A new deep unsupervised hashing function, called HashGAN, is proposed, which efficiently obtains binary representation of input images without any supervised pretraining and achieves the state-of-the-art performance in image clustering on benchmark datasets.
Abstract: Unsupervised deep hash functions have not shown satisfactory improvements against their shallow alternatives, and usually require supervised pretraining to avoid overfitting. In this paper, we propose a new deep unsupervised hashing function, called HashGAN, which efficiently obtains binary representation of input images without any supervised pretraining. HashGAN consists of three networks, a generator, a discriminator and an encoder. By sharing the parameters of the encoder and discriminator, we benefit from the adversarial loss as a data-dependent regularization in training our deep hash function. Moreover, a novel hashing loss function is introduced for real images, which results in minimum entropy, uniform frequency, consistent and independent hash bits. Furthermore, we employ a collaborative loss in training our model, enforcing similar random inputs and hash bits for synthesized images. In our experiments, HashGAN outperforms the previous unsupervised hash functions in image retrieval and achieves the state-of-the-art performance in image clustering on benchmark datasets. We also provide an ablation study, showing the contribution of each component in our loss function.

104 citations


Authors

Showing all 32362 results

NameH-indexPapersCitations
Zhong Lin Wang2452529259003
Jie Zhang1784857221720
Bin Wang126222674364
Huijun Gao12168544399
Hong Wang110163351811
Jian Zhang107306469715
Guozhong Cao10469441625
Lajos Hanzo101204054380
Witold Pedrycz101176658203
Lei Liu98204151163
Qi Tian96103041010
Wei Liu96153842459
MengChu Zhou96112436969
Chunying Chen9450830110
Daniel W. C. Ho8536021429
Network Information
Related Institutions (5)
Beihang University
73.5K papers, 975.6K citations

92% related

Southeast University
79.4K papers, 1.1M citations

91% related

Harbin Institute of Technology
109.2K papers, 1.6M citations

91% related

City University of Hong Kong
60.1K papers, 1.7M citations

90% related

Nanyang Technological University
112.8K papers, 3.2M citations

90% related

Performance
Metrics
No. of papers from the Institution in previous years
YearPapers
2023117
2022529
20213,751
20203,816
20194,017
20183,382