Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Dan Feng has a total of 33 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Block-Cyclic Zadoff–Chu Sequences-Based Preamble Design and Detection for OTFS-Enabled LEO Satellite Random Access Systems

    by Shuchang Li, Guangyue Lu, Li Zhen, Dan Feng, Keping Yu, Derrick Wing Kwan Ng

    Low-earth-orbit (LEO) satellite communication, owing to its capability to provide ubiquitous and continuous connectivity, is expected to play a pivotal role in sixth-generation (6 G) global communication networks. Focusing on ensuring reliable access for massive users in high-dynamic satellite environments, we propose a novel random access (RA) preamble design and detection scheme incorporating orthogonal time frequency space (OTFS) modulation. Specifically, a RA preamble utilizing block-cyclic Zadoff-Chu (ZC) sequences is developed by arranging multiple single-root ZC sequences in the delay-Doppler domain with strategically configured cyclic shift sets. In particular, our design not only ensures substantial preamble capacity and low peak-to-average power ratio (PAPR), but also facilitates multi-user detection without being affected by non-orthogonal interference. By leveraging the characteristics of the proposed preamble, we introduce an effective three-stage preamble detection algorithm for accurate user identification and timing advance estimation. Moreover, we conduct theoretical derivations to analyze the impacts of preamble design parameters on the PAPR and detection performance of our scheme. Simulation results corroborate our theoretical analysis, demonstrating that the proposed scheme facilitates a flexible tradeoff between PAPR and preamble capacity by adapting the number of sequences, and significantly outperforms the existing approach in terms of the successful detection probability in typical LEO satellite scenarios.


  • Multi-Domain Index Modulation for MIMO-OTFS and a Coarse-to-Fine Network for Detection

    by Dan Feng, Baoming Bai, Jingyu Ma, Weijie Yuan, Shuangyang Li, Jing Jiang

    Recently, index modulated orthogonal time frequency space modulation combined with multi-input and multi-output (MIMO-OTFS) has been introduced to get superior bit error rate (BER) performance than conventional MIMO-OTFS schemes. In this paper, we propose a novel transmission scheme called generalized space-delay-Doppler index modulated OTFS (GSDDIM-OTFS) to further utilize the multi-domain resources and explore the potential benefits of the index modulated MIMO-OTFS. In this scheme, additional information bits are transmitted through the combined space-delay-Doppler resource units. We also derive the analytical expressions of average bit error probability (ABEP) to evaluate the performance of the proposed scheme. For multi-domain index modulation schemes, the traditional detection suffers a supreme complexity with a large size of look-up table. To address this issue, we propose a coarse-to-fine (CTF) network for the GSDDIM-OTFS detection, called the CTFIM detector. In the proposed detector, the characteristic of the transmit constellation of index modulated schemes is fully utilized and we explore the coarse-to-fine strategy to capture the general features more efficiently from different dimensions. Specifically, the coarse module is used to capture features based on the index pattern and the fine classification to establish the global relationships in each GSDDIM-OTFS subblock. Furthermore, we also employ feature fusion to increase the feature dimensions. Simulation results demonstrate the enhanced performance of the GSDDIM-OTFS over doubly-selective fading channels and the proposed DL-based detectors under perfect and imperfect channel conditions.


  • Spatio-Temporal GNN-Based Cell-Free Massive MIMO Network With Maximal Benefit-Cost Ratio

    by Jing Jiang, Yanni Li, Yinghui Ye, Dan Feng, Jiayi Zhang, Worakrin Sutthiphan, Dusit Niyato

    Due to the network's rapid expansion, mobile networks bear extra high deployment costs. Being a key enabler of 6th generation (6G) mobile networks, it is crucial that cell-free massive MIMO (CF mMIMO) networks achieve green and cost-effective development. In this correspondence, we propose spatio-temporal graph neural networks (STGNN)-based CF mMIMO networks with a maximal benefit-cost ratio. First, we formulate a new coverage cost metric named benefit-cost ratio (BCR), which can evaluate the deployment cost while fulfilling various traffic requirements. Next, CF mMIMO networks are modeled as a spatio-temporal graph to utilize STGNN to extract the spatial-temporal properties of traffic demands. Finally, STGNN optimizes the number and location of access points (APs) based on the maximal BCR criterion so that the CF mMIMO networks can achieve on-demand service capability with minimum deployment cost. Numerical results demonstrate that the proposed algorithm can significantly reduce the deployment cost while providing on-demand and high-quality mobile service.


  • Change Masked Modality Alignment Network for Multimodal Change Detection

    by Fenlong Jiang, Bo Huang, Husheng Wu, Dan Feng, Yu Zhou, Mingyang Zhang, Maoguo Gong, Wei Zhao, Ziyu Guan

    Using multimodal remote sensing images for change detection (CD) can significantly improve the feasibility and reliability in challenging environments. However, the differences in imaging mechanisms make multimodal images highly heterogeneous. A key challenge for multimodal CD (MCD) is that the heterogeneity of the modalities and changes in ground objects are intertwined during processing. To address this issue, this article proposes a change masked modality alignment network (CMMAN), which uses a multitask framework consisting of one CD branch and two image modal transformation (IMT) branches. Specifically, to ensure a unified feature space, bi-temporal multimodal images are first input into the same Swin-Transformer-based encoder. The extracted features are then fed simultaneously into the CD branch and separately into the two IMT branches. In the CD branch, the decoder is also designed based on the Swin-Transformer, and a weakly modality-correlated feature enhancement (WMCFE) module is introduced to mitigate the interference of modality heterogeneity on CD. For the two IMT branches, both employ a generative adversarial network (GAN) to transform between modalities, and the distributions of features from different modalities are aligned through simultaneous optimization. Uniquely, the change probability map predicted by the CD branch is utilized to mask the change regions in IMT, further decoupling ground object changes and modal heterogeneity. Experimental results on multiple public datasets demonstrate that the proposed CMMAN significantly improves MCD performance and shows good compatibility and portability with various common backbone networks.


  • Generalized Index Modulation for MIMO-OTFS Transmission

    by Dan Feng, Jianping Zheng, Baoming Bai, Jing Jiang, Hongyun Chu

    Recently, the combination of multiple-input multiple-output technology with orthogonal time frequency space modulation (MIMO-OTFS) has drawn extensive attention with the advantage of exploring the additional transmit diversity or spatial multiplexing of the MIMO scheme. Motivated by the potential spectral efficiency of multi-domain index modulation, in this paper, we propose a generalized index modulation based MIMO-OTFS (GIM-MIMO-OTFS) to convey extra information with the aid of the spatial and delay-Doppler indices. To reduce the supreme complexity of maximum likelihood (ML) detection with a large size of look-up table in GIM-MIMO-OTFS, a two stage index detector based on power information is presented. Furthermore, the analytical expression of average bit error probability (ABEP) is derived to evaluate the performance of the proposed scheme. Simulation results demonstrate the enhanced performance of the proposed scheme in high-mobility scenarios, and highlight the complexity and outperformance of the proposed detector compared to ML detector.


  • Open Access

    Frequency Spectrum Intensity Attention Network for Building Detection from High-Resolution Imagery

    by Dan Feng, Hongyun Chu, Ling Zheng

    Computational intelligence techniques have been widely used for automatic building detection from high-resolution remote sensing imagery and especially the methods based on neural networks. However, existing methods do not pay attention to the value of high-frequency and low-frequency information in the frequency domain for feature extraction of buildings in remote sensing images. To overcome these limitations, this paper proposes a frequency spectrum intensity attention network (FSIANet) with an encoder–decoder structure for automatic building detection. The proposed FSIANet mainly involves two innovations. One, a novel and plug-and-play frequency spectrum intensity attention (FSIA) mechanism is devised to enhance feature representation by evaluating the informative abundance of the feature maps. The FSIA is deployed after each convolutional block in the proposed FSIANet. Two, an atrous frequency spectrum attention pyramid (AFSAP) is constructed by introducing FSIA in widely used atrous spatial pyramid pooling. The AFSAP is able to select the features with high response to building semantic features at each scale and weaken the features with low response, thus enhancing the feature representation of buildings. The proposed FSIANet is evaluated on two large public datasets (East Asia and Inria Aerial Image Dataset), which demonstrates that the proposed method can achieve the state-of-the-art performance in terms of F1-score and intersection-over-union.


  • In-Phase and Quadrature Index Modulation Aided OTFS Transmission

    by Dan Feng, Jianping Zheng, Baoming Bai, Jing Jiang, Ling Zheng

    Recently, orthogonal time frequency space modulation with index modulation (OTFS-IM) has been proposed, which can achieve better bit error rate (BER) performance than conventional OTFS. In this letter, a new transmission scheme, OTFS with in-phase and quadrature index modulation (OTFS-I/Q-IM), is presented to increase the spectral efficiency of OTFS-IM, in which additional information bits are carried through the grid index of OTFS block in in-phase and quadrature dimensions. Furthermore, the analytical expressions of average bit error probability (ABEP) and the maximum peak to average power ratio (PAPR) are derived to evaluate the performance of the proposed scheme. Simulation results demonstrate the enhanced performance of the proposed scheme in high-mobility scenarios.


  • Open Access

    Multipopulation Particle Swarm Optimization for Evolutionary Multitasking Sparse Unmixing

    by Dan Feng, Mingyang Zhang, Shanfeng Wang

    Recently, the multiobjective evolutionary algorithms (MOEAs) have been designed to cope with the sparse unmixing problem. Due to the excellent performance of MOEAs in solving the NP hard optimization problems, they have also achieved good results for the sparse unmixing problems. However, most of these MOEA-based methods only deal with a single pixel for unmixing and are subjected to low efficiency and are time-consuming. In fact, sparse unmixing can naturally be seen as a multitasking problem when the hyperspectral imagery is clustered into several homogeneous regions, so that evolutionary multitasking can be employed to take advantage of the implicit parallelism from different regions. In this paper, a novel evolutionary multitasking multipopulation particle swarm optimization framework is proposed to solve the hyperspectral sparse unmixing problem. First, we resort to evolutionary multitasking optimization to cluster the hyperspectral image into multiple homogeneous regions, and directly process the entire spectral matrix in multiple regions to avoid dimensional disasters. In addition, we design a novel multipopulation particle swarm optimization method for major evolutionary exploration. Furthermore, an intra-task and inter-task transfer and a local exploration strategy are designed for balancing the exchange of useful information in the multitasking evolutionary process. Experimental results on two benchmark hyperspectral datasets demonstrate the effectiveness of the proposed method compared with the state-of-the-art sparse unmixing algorithms.


  • Spatial Modulation With Multi-Dimensional Constellations

    by Dan Feng, Qingli He, Baoming Bai, Jianping Zheng, Mengmeng Liu

    Quadrature spatial modulation (QSM) was proposed to strengthen conventional SM by creating a new spatial constellation dimension. Inspired by that, we present a spatial modulation scheme which expands spatial constellation to a new dimension and utilizes the spatial dimension to transmit multi-dimensional constellation signals. In the proposed scheme, Gallager mapping is used for spatial mapping to increase the transmission rate in spatial domain. The design method of multi-dimensional constellations is also described in this letter. We investigate both 5G LDPC codes and nonbinary LDPC codes with the designed multi-dimensional constellations. Simulation results show that the proposed scheme can achieve significant performance gains.


  • A Low-Profile Dual-Polarized MIMO Antenna Array with High Isolation

    by Xiangyu Zhou, Junhao Shi, Dan Feng, Huiqing Zhai

    A low-profile dual-polarized MIMO antenna array with high isolation is proposed in this paper. As is shown in this paper, the unit of the presented MIMO antenna array is two crossed dipole antennas. The height of the dipole antenna is just 10mm. It is a low profile because of the application of the AMC surface. As a result, the proposed MIMO antenna array can offer an impedance band from 2.50 GHz to 2.68 GHz when the VSWR is lower than 1.5. At the same time, The MIMO antenna array also presents great performance in radiation patterns, with the gain of 9dBi and the isolation between the two ports can reach 25dB. The proposed MIMO antenna array can be applied to the base stations.