Fasheng Liu
Fasheng Liu has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Haitao Pu
Shandong University of Science and Technology
1 shared publication Jinjiao Lin
School of Information Management, Shandong Economic University, Jinan, 250014, China
1 shared publication- Ning Du
College of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, China
1 shared publication - Shaohua Wang
School of Computer Science and Technology, Shandong Jianzhu University, Jinan, China
1 shared publication - Xiao Kang
Shandong University, Jinan, China
1 shared publication - Xingbo Liu
Shandong Jianzhu University, Jinan, China
1 shared publication
Latest Publications
- Open Access
- 1 January 2021
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2021 (1)
Discrete Two‐Step Cross‐Modal Hashing through the Exploitation of Pairwise Relations
The cross‐modal hashing method can map heterogeneous multimodal data into a compact binary code that preserves semantic similarity, which can significantly enhance the convenience of cross‐modal retrieval. However, the currently available supervised cross‐modal hashing methods generally only factorize the label matrix and do not fully exploit the supervised information. Furthermore, these methods often only use one‐directional mapping, which results in an unstable hash learning process. To address these problems, we propose a new supervised cross‐modal hash learning method called Discrete Two‐step Cross‐modal Hashing (DTCH) through the exploitation of pairwise relations. Specifically, this method fully exploits the pairwise similarity relations contained in the supervision information: for the label matrix, the hash learning process is stabilized by combining matrix factorization and label regression; for the pairwise similarity matrix, a semirelaxed and semidiscrete strategy is adopted to potentially reduce the cumulative quantization errors while improving the retrieval efficiency and accuracy. The approach further combines an exploration of fine‐grained features in the objective function with a novel out‐of‐sample extension strategy to enable the implicit preservation of consistency between the different modal distributions of samples and the pairwise similarity relations. The superiority of our method was verified through extensive experiments using two widely used datasets.
- 1 January 2021
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2021 (1)
Open AccessDiscrete Two‐Step Cross‐Modal Hashing through the Exploitation of Pairwise Relations
The cross‐modal hashing method can map heterogeneous multimodal data into a compact binary code that preserves semantic similarity, which can significantly enhance the convenience of cross‐modal retrieval. However, the currently available supervised cross‐modal hashing methods generally only factorize the label matrix and do not fully exploit the supervised information. Furthermore, these methods often only use one‐directional mapping, which results in an unstable hash learning process. To address these problems, we propose a new supervised cross‐modal hash learning method called Discrete Two‐step Cross‐modal Hashing (DTCH) through the exploitation of pairwise relations. Specifically, this method fully exploits the pairwise similarity relations contained in the supervision information: for the label matrix, the hash learning process is stabilized by combining matrix factorization and label regression; for the pairwise similarity matrix, a semirelaxed and semidiscrete strategy is adopted to potentially reduce the cumulative quantization errors while improving the retrieval efficiency and accuracy. The approach further combines an exploration of fine‐grained features in the objective function with a novel out‐of‐sample extension strategy to enable the implicit preservation of consistency between the different modal distributions of samples and the pairwise similarity relations. The superiority of our method was verified through extensive experiments using two widely used datasets.
- Open Access
- 21 May 2017
- Published by MDPI AG in Applied Sciences
- Vol. 7 (5) , 520
Joint Resource Allocation in Secure OFDMA-Based Networks Taking a Base Station as a Two-Way Relay
Due to the broadcast nature of wireless media, all nodes in the coverage of a transmitter are capable of capturing its signals, thus wireless transmission is sensitive to wiretapping. Several existing schemes place an emphasis on secrecy rate improvement, under the protocols of amplify-and-forward or decode-and-forward, when there are only relay users in the network. We set up a novel communication model in which normal and two-way relay users coexist in the same cell, taking the base station as a relay. Our objective is to maximize the total secrecy rate, taking subcarrier pairing, subcarrier assignment and power allocation into account, when there is one eavesdropper in one cell of the cellular network. Although this problem is very intricate, we reformulate it as a convex optimization problem by means of Lagrange duality. In order to reduce the computational complexity, equal power allocation is proposed. Lastly, the experimental results show the proposed resource allocation scheme can obtain a higher secrecy rate than traditional schemes.
- 21 May 2017
- Published by MDPI AG in Applied Sciences
- Vol. 7 (5) , 520
Open AccessJoint Resource Allocation in Secure OFDMA-Based Networks Taking a Base Station as a Two-Way Relay
Due to the broadcast nature of wireless media, all nodes in the coverage of a transmitter are capable of capturing its signals, thus wireless transmission is sensitive to wiretapping. Several existing schemes place an emphasis on secrecy rate improvement, under the protocols of amplify-and-forward or decode-and-forward, when there are only relay users in the network. We set up a novel communication model in which normal and two-way relay users coexist in the same cell, taking the base station as a relay. Our objective is to maximize the total secrecy rate, taking subcarrier pairing, subcarrier assignment and power allocation into account, when there is one eavesdropper in one cell of the cellular network. Although this problem is very intricate, we reformulate it as a convex optimization problem by means of Lagrange duality. In order to reduce the computational complexity, equal power allocation is proposed. Lastly, the experimental results show the proposed resource allocation scheme can obtain a higher secrecy rate than traditional schemes.
- 1 August 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 575-578
The approach of device independence for mobile learning system
Mobile learning is transforming the way of tradition education. But most of e-learning system and contents are not suitable for mobile device. In order to provide suitable mobile learning services, the approach for self-adaptation is proposed in this paper. Firstly, the formal definitions of context and its influence on learning service, including NCxt, side S, weighing Q and adaptation coefficient E, are presented. Then, using the approach, the mobile learning system is constructed. The example implies this approach can detect the contextual environment of mobile computing and adapt the mobile learning service to the mobile learners' device automatically.
- 1 August 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 575-578
The approach of device independence for mobile learning system
Mobile learning is transforming the way of tradition education. But most of e-learning system and contents are not suitable for mobile device. In order to provide suitable mobile learning services, the approach for self-adaptation is proposed in this paper. Firstly, the formal definitions of context and its influence on learning service, including NCxt, side S, weighing Q and adaptation coefficient E, are presented. Then, using the approach, the mobile learning system is constructed. The example implies this approach can detect the contextual environment of mobile computing and adapt the mobile learning service to the mobile learners' device automatically.