Federated Learning (FL) enables model training on distributed devices while preserving data privacy. However, malicious clients can submit fabricated model updates to fraudulently obtain training rewards, a behavior known as free-rider attacks. Existing detection-based solutions analyze anomalies in model updates but lack direct evidence of local training, making it fail to fully prevent free-riders. To address this limitation, we propose zkVFL, a verifiable FL framework leveraging Zero-Knowledge Proofs (ZKP) to ensure the integrity of local training while preserving privacy. To reduce the computational overhead of proof generation in ZKP, zkVFL introduces two novel techniques: (i) anomaly-aware client sampling to selectively perform ZKP verification and (ii) A recursive ZKP protocol (ReMPoT), incorporating a pruning-based layer selection technique, reduces proof generation costs. Experimental results demonstrate that zkVFL improves the accuracy and convergence of FL training under free-rider attacks while significantly reducing the computational and memory overhead of proof generation on resource-constrained devices.

A novel pinching-antenna systems (PASS)-enabled secure wireless communication framework is proposed. By dynamically adjusting the positions of dielectric particles, namely pinching antennas (PAs), along the waveguides, PASS introduces a novel concept of pinching beamforming to enhance the performance of physical layer security. A fundamental PASS-enabled secure communication system is considered with one legitimate user and one eavesdropper. Both single-waveguide and multiple-waveguide scenarios are studied. 1) For the single-waveguide scenario, the secrecy rate (SR) maximization is formulated to optimize the pinching beamforming. A PA-wise successive tuning (PAST) algorithm is proposed, which ensures constructive signal superposition at the legitimate user while inducing a destructive legitimate signal at the eavesdropper. 2) For the multiple-waveguide scenario, artificial noise (AN) is employed to further improve secrecy performance. A pair of practical transmission architectures are developed:waveguide division (WD)andwaveguide multiplexing (WM). The key difference lies in whether each waveguide carries a single type of signal or a mixture of signals with baseband beamforming. For the SR maximization problem under the WD case, a two-stage algorithm is developed, where the pinching beamforming is designed with the PAST algorithm and the baseband power allocation among AN and legitimate signals is solved using successive convex approximation (SCA). For the WM case, an alternating optimization algorithm is developed, where the baseband beamforming is optimized with SCA and the pinching beamforming is designed employing particle swarm optimization. Numerical results demonstrate that i) PASS can significantly improve the secrecy performance over conventional antenna systems in both scenarios; ii) the proposed PAST algorithm for the single-waveguide scenario is efficient, especially when the number of PAs is even or large; iii) WM provides higher and more stable performance at the cost of increased complexity, while WD serves as a simple yet scalable alternative, which is effective when a large number of PAs are deployed.

Knowledge distillation as a practical tool to enhance the performance of small-capacity student networks on downstream tasks comes at the cost of a lengthy distillation process due to the online inference of teacher networks, especially when there is a large capacity gap between them. Therefore, in this paper, we propose a fast distillation framework called TeDri based on region images by offline saving relevant regional information and its teacher guidance. Specifically, first, to alleviate the lack of diversity caused by the fixed augmentation path in region images, we propose Teacher-driven MixUp strategies with mild intensity and advocate binding the mixing factor$\lambda$with teacher guidance confidence, where more confident category representations dominate the MixUp process. Furthermore, recognizing the need to evaluate these randomly cropped regions, and we propose region contrastive learning, encourage the student network to mimic the region partitioning behavior of the teacher, promoting a comprehensive understanding of global semantic content from multiple local perspectives. Finally, we introduce region mutual learning, employing spatial constraints among regions to require the student network towards consistent content interpretation across localized regions. Experiments on CIFAR-100 and ImageNet-1 K validate the effectiveness of the proposed TeDri, achieving competitive performance while significantly reducing training time.

A simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) assisted simultaneous wireless information and power transfer (SWIPT) system is investigated. Both active and passive STAR-RISs are considered. Passive STAR-RISs can be cost-efficiently fabricated to large aperture sizes with significant near-field regions, but the design flexibility is limited by the coupled phase-shifts. Active STAR-RISs can further amplify signals and have independent phase-shifts, but their aperture sizes are relatively small due to the high cost. To characterize and compare their performance, a power consumption minimization problem is formulated by jointly designing the beamforming at the access point (AP) and the STAR-RIS, subject to both the power and information quality-of-service requirements. To solve the resulting highly-coupled non-convex problem, the original problem is first decomposed into simpler subproblems and then an alternating optimization framework is proposed. For the passive STAR-RIS, the coupled phase-shift constraint is tackled by employing a vector-driven weighted penalty method. While for the active STAR-RIS, the independent phase-shift is optimized with AP beamforming via matrix-driven semidefinite programming, and the amplitude matrix is updated using convex optimization techniques in each iteration. Numerical results show that: 1) given the same aperture sizes, the active STAR-RIS exhibits superior performance over the passive one when the aperture size is small, but the performance gap decreases with the increase in aperture size; and 2) given identical power budgets, the passive STAR-RIS is generally preferred, whereas the active STAR-RIS typically suffers performance loss for balancing between the hardware power and the amplification power.

Visual Place Recognition (VPR) is aimed at predicting the location of a query image by referencing a database of geotagged images. For VPR task, often fewer discriminative local regions in an image produce important effects while mundane background regions do not contribute or even cause perceptual aliasing because of easy overlap. However, existing methods lack precisely modeling and full exploitation of these discriminative regions. In addition, the lack of pixel-level correspondence supervision in the VPR dataset hinders further improvement of the local feature matching capability in the re-ranking stage. In this paper, we propose the Focus on Local (FoL) approach to stimulate the performance of image retrieval and re-ranking in VPR simultaneously by mining and exploiting reliable discriminative local regions in images and introducing pseudo-correlation supervision. First, we design two losses, Extraction-Aggregation Spatial Alignment Loss (SAL) and Foreground-Background Contrast Enhancement Loss (CEL), to explicitly model reliable discriminative local regions and use them to guide the generation of global representations and efficient re-ranking. Second, we introduce a weakly-supervised local feature training strategy based on pseudo-correspondences obtained from aggregating global features to alleviate the lack of local correspondences ground truth for the VPR task. Third, we suggest an efficient re-ranking pipeline that is efficiently and precisely based on discriminative region guidance. Finally, experimental results show that our FoL achieves the state-of-the-art on multiple VPR benchmarks in both image retrieval and re-ranking stages and also significantly outperforms existing two-stage VPR methods in terms of computational efficiency.

Data-Free Knowledge Distillation (DFKD) enables the knowledge transfer from the given pre-trained teacher network to the target student model without access to the real training data. Existing DFKD methods focus primarily on improving image recognition performance on associated datasets, often neglecting the crucial aspect of the transferability of learned representations. In this paper, we propose Category-Aware Embedding Data-Free Knowledge Distillation (CAE-DFKD), which addresses at the embedding level the limitations of previous rely on image-level methods to improve model generalization but fail when directly applied to DFKD. The superiority and flexibility of CAE-DFKD are extensively evaluated, including: i.) Significant efficiency advantages resulting from altering the generator training paradigm; ii.) Competitive performance with existing DFKD state-of-the-art methods on image recognition tasks; iii.) Remarkable transferability of data-free learned representations demonstrated in downstream tasks.

Landmark detection is essential in medical image analysis, serving as the foundation for many downstream tasks. In recent years, supervised anatomical landmark detection models have achieved remarkable success, but typically require large amounts of labeled data for training, which is challenging to obtain due to the expertise and time needed for accurate annotation. Rather than relying on costly expert annotations, this paper focuses on leveraging a one-shot method for automated annotation. To this end, we propose a Spatially Consistent Self-supervised approach (SCS) within a two-stage framework for one-shot anatomical landmark detection. In the first stage, we design a multi-scale contrastive self-supervised method that leverages the inherent spatial consistency of medical images, characterized by clear structures and similar patterns, to extract global and local features. During inference, pseudo-labels are generated based on the one-shot template. In the second stage, we train a supervised model using the pseudo-labels and mitigate label noise through a mask and multi-task approach. Our method is evaluated on three widely-used public X-ray datasets, achieving state-of-the-art performance across almost all metrics with the Mean Radial Error (MRE) reduced to 1.97mm on the Cephalometric dataset, 1.43mm on the Hand dataset, and 6.58mm on the Chest dataset, thereby demonstrating the effectiveness of our Spatially Consistent Self-supervised approach.

Skin cancer is a prevalent and life-threatening disease where early detection significantly improves survival rates. However, existing segmentation models are often too large and computationally intensive, limiting their applicability in resource-constrained medical scenarios. To address this, we propose DCSA-UNet, a lightweight U-Net-based segmentation model designed for efficient and effective skin lesion segmentation. The model integrates a novel Dual Cross-Shaped Attention (DCSA) mechanism, which ensures computational complexity grows linearly with both the number of tokens and the receptive field width. Additionally, the Mask-Guided Progressive Fusion (MGPF) module addresses the feature mismatch between encoder and decoder in lightweight models through progressive multi-scale integration. By combining these innovations, DCSA-UNet achieves state-of-the-art performance with significantly reduced computational and storage requirements. Compared to existing methods, it reduces parameter counts by 59% and GFLOPs by 2%, while improving mIoU by 0.78% and DSC by 0.48%. These results highlight its potential as a robust solution for real-time skin lesion segmentation. https://github.com/Litpill/DCSA-UNet

Camera-based occupancy prediction is a main-stream approach for 3D perception in autonomous driving, aiming to infer complete 3D scene geometry and semantics from 2D images. Almost existing methods focus on improving performance through structural modifications, such as lightweight backbones and complex cascaded frameworks, with good yet limited performance. Few studies explore from the perspective of representation fusion, leaving the rich diversity of features in 2D images underutilized. Motivated by this, we propose CIGOcc, a two-stage occupancy prediction framework based on multi-level representation fusion. CIGOcc extracts segmentation, graphics, and depth features from an input image and introduces a deformable multi-level fusion mechanism to fuse these three multi-level features. Additionally, CIGOcc incorporates knowledge distilled from SAM to further enhance prediction accuracy. Without increasing training costs, CIGOcc achieves state-of-the-art performance on the SemanticKITTI benchmark. The code is provided in the supplementary material and will be released project page.

With the growing need for diverse and scalable data in indoor scene tasks, such as question answering and dense captioning, we propose 3D-MoRe, a novel paradigm designed to generate large-scale 3D-language datasets by lever-aging the strengths of foundational models. The framework integrates key components, including multi-modal embedding, cross-modal interaction, and a language model decoder, to process natural language instructions and 3D scene data. This approach facilitates enhanced reasoning and response generation in complex 3D environments. Using the ScanNet 3D scene dataset, along with text annotations from ScanQA and ScanRefer, 3D-MoRe generates 62,000 question-answer (QA) pairs and 73,000 object descriptions across 1,513 scenes. We also employ various data augmentation techniques and implement semantic filtering to ensure high-quality data. Experiments on ScanQA demonstrate that 3D-MoRe significantly outperforms state-of-the-art baselines, with the CIDEr score improving by 2.15%. Similarly, on ScanRefer, our approach achieves a notable increase in [email protected] by 1.84%, highlighting its effectiveness in both tasks. Our code and generated datasets will be publicly released to benefit the community, and both can be accessed on the https://3D-MoRe.github.io.

Affine frequency division multiplexing (AFDM) has emerged as a promising waveform for high-mobility communication systems, whose performance in doubly dispersive channels relies on accurate channel estimation. However, conventional AFDM channel estimation schemes exhibit significant limitations. Therefore, we propose a low-complexity channel estimation scheme which adopts different pilot designs for integer and fractional Doppler cases. Specifically, the generalized approximate message passing (GAMP) algorithm is employed to replace the expectation step of the sparse Bayesian learning algorithm based on expectation maximization (EM), thereby reducing computational complexity. Extensive simulation results demonstrate that, compared with conventional methods, the proposed scheme not only offers advantages in pilot power consumption and overhead, but also achieves excellent performance and low complexity in various Doppler cases.

A simultaneously transmitting and reflecting reconfigurable-intelligent-surface (STAR-RIS)-assisted wireless powered communication network (WPCN) is proposed, where two energy-limited devices first harvest energy from a hybrid access point (HAP) and then use that energy to transmit information back. To fully eliminate thedoubly-near-far-effect in WPCNs, two STAR-RIS operating protocol-driven transmission strategies, namely energy splitting nonorthogonal multiple access (ES-NOMA) and time switching time division multiple access (TS-TDMA) are proposed. For each strategy, the corresponding optimization problem is formulated to maximize the minimum throughput by jointly optimizing time allocation, user transmit power, active HAP beamforming, and passive STAR-RIS beamforming. For ES-NOMA, the resulting intractable problem is solved via a two-layer algorithm, which exploits the 1-D search and block coordinate descent methods in an iterative manner. For TS-TDMA, the optimal active beamforming and passive beamforming are first determined according to the maximum-ratio transmission beamformer. Then, the optimal solution of the time allocation variables is obtained by solving a standard convex problem. Numerical results show that: 1) the STAR-RIS can achieve considerable performance improvements for both strategies compared to the conventional RIS; 2) TS-TDMA is preferred for single-antenna scenarios, whereas ES-NOMA is better suited for multiantenna scenarios; and 3) the superiority of ES-NOMA over TS-TDMA is enhanced as the number of STAR-RIS elements increases.

A novel movable-element simultaneously transmitting and reflecting surface (ME-STARS)-assisted near-field wideband communication framework is proposed. In particular, the position of each STARS element can be adjusted to combat the significant wideband beam squint issue in the near field instead of using costly true-time delay components. Four practical ME-STARS element movement modes are proposed, namely region-based (RB), horizontal-based (HB), vertical-based (VB), and diagonal-based (DB) modes. Based on this, a near-field wideband multi-user downlink communication scenario is considered, where a sum rate maximization problem is formulated by jointly optimizing the base station (BS) precoding, ME-STARS beamforming, and element positions. To solve this intractable problem, a two-layer algorithm is developed. For the inner layer, the block coordinate descent optimization framework is utilized to solve the BS precoding and ME-STARS beamforming in an iterative manner. For the outer layer, the particle swarm optimization-based heuristic search method is employed to determine the desired element positions. Numerical results show that: 1) the ME-STARSs can effectively address the beam squint for near-field wideband communications compared to conventional STARSs with fixed element positions; 2) the RB mode achieves the most efficient beam squint effect mitigation, while the DB mode achieves the best trade-off between performance gain and hardware overhead; and 3) an increase in the number of ME-STARS elements or BS subcarriers substantially improves the system performance.

Vision-language models (VLMs) have demonstrated remarkable open-vocabulary object recognition capabilities, motivating their adaptation for dense prediction tasks like segmentation. However, directly applying VLMs to such tasks remains challenging due to their lack of pixel-level granularity and the limited data available for fine-tuning, leading to overfitting and poor generalization. To address these limitations, we propose Generalization Boosted Adapter (GBA), a novel adapter strategy that enhances the generalization and robustness of VLMs for open-vocabulary segmentation. GBA comprises two core components: (1) a Style Diversification Adapter (SDA) that decouples features into amplitude and phase components, operating solely on the amplitude to enrich the feature space representation while preserving semantic consistency; and (2) a Correlation Constraint Adapter (CCA) that employs cross-attention to establish tighter semantic associations between text categories and target regions, suppressing irrelevant low-frequency “noise” information and avoiding erroneous associations. Through the synergistic effect of the shallow SDA and the deep CCA, GBA effectively alleviates overfitting issues and enhances the semantic relevance of feature representations. As a simple, efficient, and plug-and-play component, GBA can be flexibly integrated into various CLIP-based methods, demonstrating broad applicability and achieving state-of-the-art performance on multiple open-vocabulary segmentation benchmarks. Code are available athttps://github.com/clearxu/BGA.

Data-Free Knowledge Distillation (DFKD) enables knowledge transfer from teacher networks without access to the real dataset. However, generator-based DFKD methods often suffer from insufficient diversity or low-confidence in synthetic images, negatively impacting student network performance. This paper introduces DFMC, a generative feature-driven framework to mitigate the inherent limitations of DFKD. We propose exploiting semantic description between generative feature domains to guide augmentation strategies, avoiding random abstract inputs caused by inconsistent semantic quality. Then, by applying noise to the generative features, we produce contrastive learning pairs indirectly, limiting the sampling range of the feature domain to encourage the student network to learn domain-invariant features. Finally, we guide the student network to deeply mimic the teacher’s layer-wise implicit classification behavior for the augmented synthetic images. Extensive experiments across various datasets and downstream tasks demonstrate the effectiveness of DFMC, achieving significant improvements while preventing student networks from overfitting to semantic ambiguous images.

Data-free knowledge distillation (DFKD) enables knowledge transfer from a pre-trained teacher to a student network without accessing the real dataset. However, generator-based DFKD methods struggle to ensure that the synthetic images accurately reflect the real dataset distribution. The update of the generator network relies heavily on teacher category guidance, but varying teacher prediction accuracy across categories leads to inconsistent synthetic image quality. Such variations introduce a distribution shift between synthetic and real datasets, negatively impacting student network performance during knowledge distillation. To address this challenge, we propose the SRIF, comprising two components: Student-Driven Flexible Filtering (SDFF) and Re-weighting for Independent Regularization (RIR). SDFF filters out synthetic images affected by the category distribution shift during data generation, producing a more reliable dataset. RIR, applied during distillation, encourages the student to learn stable causal relationships through sample reweighting. Both components flexibly integrate into existing DFKD frameworks, improving performance while reducing training costs.

Recently, CLIP has found practical utility in the domain of pixel-level zero-shot segmentation tasks. The present landscape features two-stage methodologies beset by issues such as intricate pipelines and elevated computational costs. While current one-stage approaches alleviate these concerns and incorporate Visual Prompt Training (VPT) to uphold CLIP's generalization capacity, they still fall short in fully harnessing CLIP's potential for pixel-level unseen class demarcation and precise pixel predictions. To further stimulate CLIP's zero-shot dense prediction capability, we propose SPT-SEG, a one-stage approach that improves CLIP's adaptability from image to pixel. Specifically, we initially introduce Spectral Prompt Tuning (SPT), incorporating spectral prompts into the CLIP visual encoder's shallow layers to capture structural intricacies of images, thereby enhancing comprehension of unseen classes. Subsequently, we introduce the Spectral Guided Decoder (SGD), utilizing both high and low-frequency information to steer the network's spatial focus towards more prominent classification features, enabling precise pixel-level prediction outcomes. Through extensive experiments on two public datasets, we demonstrate the superiority of our method over state-of-the-art approaches, performing well across all classes and particularly excelling in handling unseen classes.

Self-supervised learning and knowledge distillation intersect to achieve exceptional performance on downstream tasks across diverse network capacities. This paper introduces MIM-HD, which implements enhancements for masked image modeling (MIM) distillation, in two key aspects. First, a vision transformer head-level relation adaptive distillation approach is proposed, allowing the student to dynamically draw multi-source knowledge from the teacher based on its evolving state, compatible with scenarios where teacher-student transformer block head count differs. Second, to address the overemphasis on the encoder and neglect of the decoder role in maintaining representation consistency in previous MIM distillations, a dual-view decoding strategy for latent visual representations is introduced, reusing the teacher’s decoder to alleviate MIM burdens on smaller networks. MIM-HD effectiveness is demonstrated through evaluations on ADE20K (mIoU) and ImageNet-1K (Acc), achieving +1.4% and +0.5% improved performance, respectively, compared to state-of-the-art methods, with substantial advantages on smaller pre-training datasets. Moreover, MIM-HD achieves superior efficiency, reducing pre-training epochs from 300 to 100.

A large-scale simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) assisted simultaneous wireless information and power transfer (SWIPT) system is investigated. In contrast to conventional single-field (near or far) models, a mixed near- and far-field SWIPT is considered, where a STAR-RIS with coupled phase-shift is utilized to support near-field energy devices and far-field information users. Under this setup, a transmit power minimization problem is formulated by jointly designing the access point beamforming and the STARRIS beamforming, subject to the quality of service requirements for power and information. To solve this intractable problem, a weight penalty based alternating optimization algorithm is proposed. Finally, numerical results validate the effectiveness of the proposed scheme. Moreover, the coupled phase-shift associated with the STAR-RIS has a more pronounced effect on far-field information users than on near-field energy devices.

Infrared small object detection is an important computer vision task involving the recognition and localization of tiny objects in infrared images, which usually contain only a few pixels. However, it encounters difficulties due to the diminutive size of the objects and the generally complex backgrounds in infrared images. In this paper, we propose a deep learning method, HCF-Net, that significantly improves infrared small object detection performance through multiple practical modules. Specifically, it includes the parallelized patch-aware attention (PPA) module, dimension-aware selective integration (DASI) module, and multi-dilated channel refiner (MDCR) module. The PPA module uses a multi-branch feature extraction strategy to capture feature information at different scales and levels. The DASI module enables adaptive channel selection and fusion. The MDCR module captures spatial features of different receptive field ranges through multiple depth-separable convolutional layers. Extensive experimental results on the SIRST infrared single-frame image dataset show that the proposed HCF-Net performs well, surpassing other traditional and deep learning models. Code is available at https://github.com/zhengshuchen/HCFNet.

A novel downlink hybrid reconfigurable intelligent surface (RIS) transmitter enabled multi-user communication framework is studied. Specifically, elements on the RIS can flexibly switch between active and passive modes to deliver information to multiple users. The system energy efficiency is maximized by jointly optimizing RIS element mode scheduling, transmission beamforming vector, and power allocation coefficients, subject to the user's individual rate requirement and the maximum RIS amplification power constraint. We first exploit the Dinkelbach approach to transform the original mixed-integer nonlinear programming problem into a nonfractional optimization problem. Then, an alternating optimization based algorithm is developed to address this problem. In particular, the optimal RIS element operating mode is determined by the exhaustive search method. Then, the RIS beamforming and power allocation coefficients are alternately designed. Finally, numerical results show that a significant performance improvement can be reaped by the proposed scheme compared to the baseline schemes employing full-active RIS or full-passive RIS.

Accurate segmentation of colorectal polyps in colonoscopy images is crucial for effective diagnosis and management of colorectal cancer (CRC). However, current deep learning-based methods primarily rely on fusing RGB information across multiple scales, leading to limitations in accurately identifying polyps due to restricted RGB domain information and challenges in feature misalignment during multi-scale aggregation. To address these limitations, we propose the Polyp Segmentation Network with Shunted Transformer (PSTNet), a novel approach that integrates both RGB and frequency domain cues present in the images. PSTNet comprises three key modules: the Frequency Characterization Attention Module (FCAM) for extracting frequency cues and capturing polyp characteristics, the Feature Supplementary Alignment Module (FSAM) for aligning semantic information and reducing misalignment noise, and the Cross Perception localization Module (CPM) for synergizing frequency cues with high-level semantics to achieve efficient polyp segmentation. Extensive experiments on challenging datasets demonstrate PSTNet's significant improvement in polyp segmentation accuracy across various metrics, consistently outperforming state-of-the-art methods. The integration of frequency domain cues and the novel architectural design of PSTNet contribute to advancing computer-assisted polyp segmentation, facilitating more accurate diagnosis and management of CRC.

A novel hybrid active-passive reconfigurable intelligent surface (RIS) transmitter enabled downlink multi-user communication system is investigated. Specifically, RISs are exploited to serve as transmitter antennas, where each element can flexibly switch between active and passive modes to deliver information to multiple users. The system energy efficiency (EE) maximization problem is formulated by jointly optimizing the RIS element scheduling and beamforming coefficients, as well as the power allocation coefficients, subject to the user’s individual rate requirement and the maximum RIS amplification power constraint. Using the Dinkelbach relaxation, the original mixed-integer nonlinear programming problem is transformed into a nonfractional optimization problem with a two-layer structure, which is solved by the alternating optimization approach. In particular, an exhaustive search method is proposed to determine the optimal operating mode for each RIS element. Then, the RIS beamforming and power allocation coefficients are properly designed in an alternating manner. To overcome the potentially high complexity caused by exhaustive searching, we further develop a joint RIS element mode and beamforming optimization scheme by exploiting the Big-M formulation technique. Numerical results validate that: 1) The proposed hybrid RIS scheme yields higher EE than the baseline multi-antenna schemes employing fully active/passive RIS or conventional radio frequency chains; 2) Both proposed algorithms are effective in improving the system performance, especially the latter can achieve precise design of RIS elements with low complexity; and 3) For a fixed-size hybrid RIS, maximum EE can be reaped by setting only a minority of elements to operate in the active mode.

A simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) assisted simultaneous wireless information and power transfer (SWIPT) system is proposed. More particularly, an STAR-RIS is deployed to assist in the information/power transfer from a multi-antenna access point (AP) to multiple single-antenna information users (IUs) and energy users (EUs), where two practical STAR-RIS operating protocols, namely energy splitting (ES) and time switching (TS), are employed. Under the imperfect channel state information (CSI) condition, a multi-objective optimization problem (MOOP) framework, that simultaneously maximizes the minimum data rate and minimum harvested power, is employed to investigate the fundamental rate-energy trade-off between IUs and EUs. To obtain the optimal robust resource allocation strategy, the MOOP is first transformed into a single-objective optimization problem (SOOP) via the ϵ-constraint method, which is then reformulated by approximating semi-infinite inequality constraints with the S-procedure. For ES, an alternating optimization (AO)-based algorithm is proposed to jointly design AP active beamforming and STAR-RIS passive beamforming, where a penalty method is leveraged in STAR-RIS beamforming design. Furthermore, the developed algorithm is extended to optimize the time allocation policy and beamforming vectors in a two-layer iterative manner for TS. Numerical results reveal that: 1) deploying STAR-RISs achieves a significant performance gain over conventional RISs, especially in terms of harvested power for EUs; 2) the ES protocol obtains a better user fairness performance when focusing only on IUs or EUs, while the TS protocol yields a better balance between IUs and EUs; 3) the imperfect CSI affects IUs more significantly than EUs, whereas TS can confer a more robust design to attenuate these effects.

An integrated simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs) and full-duplex (FD) relay aided downlink system is investigated. We formulate an optimization problem to maximize the downlink system achievable sum rate, by jointly optimizing the receive beamforming at the relay, the transmit beamforming at both the base station and the relay, and the passive beamforming at the STAR-RIS. To tackle the formulated non-convex problem, we decompose this problem into three subproblems by invoking alternating optimization. In particular, a penalty-based algorithm is developed to solve each subproblem via successive convex approximation technique. Finally, numerical results reveal that the proposed scheme can achieve significant performance gains compared to baselines.

A simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) assisted simultaneous wireless information and power transfer (SWIPT) framework is proposed. More particularly, an STAR-RIS is deployed to assist in SWIPT from a multi-antenna access point (AP) to multiple single-antenna information users (IUs) and energy users (EUs). Due to the near-passive operation of the STAR-RIS, a more practical setup under the assumption of imperfect channel state information is investigated. The max-min fairness optimization problem is formulated to maximize the minimum power harvested by EUs, subject to the signal-to-interference-plus-noise ratio (SINR) constraints for IUs. To tackle this non-convex problem, an alternating optimization (AO) based algorithm is proposed for robust beamforming design. We first approximate the semiinfinite inequality constraints with S-procedure, then the AP active beamforming and the STAR-RIS passive beamforming are alternatively designed, where a penalty based approach is leveraged for STAR-RIS reconfiguration. Numerical results demonstrate that: i) the significant performance gains can be achieved by the proposed scheme over the baseline schemes; and ii) more STAR-RIS elements and higher SINR requirements weaken the robustness of the EU performance in terms of energy harvesting.

Multiple access (MA) design is investigated to facilitate the coexistence of the emerging semantic transmission and the conventional bit-based transmission in future networks. Thesemantic rateis adopted for measuring the performance of the semantic transmission. However, a key challenge is that there is no closed-form expression for a key parameter, namely thesemantic similarity, which characterizes the sentence similarity between an original sentence and the corresponding recovered sentence. To overcome this challenge, we propose a data regression method, where the semantic similarity is approximated by ageneralized logistic function. Using the obtained tractable function, we propose a heterogeneous semantic and bit communication framework, where an access point simultaneously sends the semantic and bit streams to one semantics-interested user (S-user) and one bit-interested user (B-user). To realize this heterogeneous semantic and bit transmission in multi-user networks, three MA schemes are proposed, namely orthogonal multiple access (OMA), non-orthogonal multiple access (NOMA), and semi-NOMA. More specifically, the bit stream in semi-NOMA is split into two streams, one is transmitted with the semantic stream over the shared frequency sub-band and the other is transmitted over the separate orthogonal frequency sub-band. To study the fundamental performance limits of the three proposed MA schemes, thesemantic-versus-bit (SvB) rate regionand thepower regionare defined. An optimal resource allocation procedure is then derived for characterizing the boundary of the SvB rate region and the power region achieved by each MA scheme. The structures of the derived solutions demonstrate that semi-NOMA is superior to both NOMA and OMA given its highly flexible transmission policy. Our numerical results: 1) confirm that the proposed semi-NOMA is the optimal MA scheme as compared to OMA and NOMA even under the symmetric channel case, and 2) reveal that the superiority of semi-NOMA is more prominent when the channel condition of the S-user is better than that of the B-user.

A novel coexisting passive reconfigurable intelligent surface (RIS) and active decode-and-forward (DF) relay assisted non-orthogonal multiple access (NOMA) transmission framework is proposed. In particular, two communication protocols are conceived, namely Hybrid NOMA (H-NOMA) and Full NOMA (F-NOMA). Based on the proposed two protocols, both the sum rate maximization and max-min rate fairness problems are formulated for jointly optimizing the power allocation at the access point and relay as well as the passive beamforming design at the RIS. To tackle the non-convex problems, an alternating optimization (AO) based algorithm is first developed, where the transmit power and the RIS phase-shift are alternatingly optimized by leveraging the two-dimensional search and rank-relaxed difference-of-convex (DC) programming, respectively. Then, a two-layer penalty based joint optimization (JO) algorithm is developed to jointly optimize the resource allocation coefficients within each iteration. Finally, numerical results demonstrate that: i) the proposed coexisting RIS and relay assisted transmission framework is capable of achieving a significant user performance improvement than conventional schemes without RIS or relay; ii) compared with the AO algorithm, the JO algorithm requires less execution time at the cost of a slight performance loss; and iii) the H-NOMA and F-NOMA protocols are generally preferable for ensuring user rate fairness and enhancing user sum rate, respectively.

This paper investigates an integrated passive reconfigurable intelligent surface (RIS) and active relay assisted non-orthogonal multiple access (NOMA) system. To unleash the potential of distant user based on the downlink NOMA protocol, we identify a two-stage transmission strategy. In both stages, RISs provide coverage for paired users by actively modifying the channel response, and in the second stage, we introduce a dedicated active relay to realize the communication between the base station (BS) and distant user. Our goal is to maximize the system sum rate by jointly optimizing the power allocation at the BS and the passive beamforming at the RIS. To tackle the formulated non-convex problem, we propose an alternating penalty-based based algorithm. In particular, for the RIS phase-shift reconfiguration, a difference-of-convex (DC) approach is utilized to accurately detect the feasibility of the rank-one constraint. Numerical results demonstrate that: i) the integrated transmission scheme outperforms other baseline schemes; ii) the proposed scheme is capable of significantly enhancing the performance of distant NOMA users.

The novel concept of non-orthogonal multiple access (NOMA) aided joint radar and multicast-unicast communication (Rad-MU-Com) is investigated. Employing the same spectrum resource, a multi-input-multi-output (MIMO) dual-functional radar-communication (DFRC) base station detects the radar-centric user (R-user), while transmitting mixed multicast-unicast messages both to the R-user and to the communication-centric user (C-user). In particular, the multicast information is intended for both the R- and C-users, whereas the unicast information is only intended for the C-user. More explicitly, NOMA is employed to facilitate this double spectrum sharing, where the multicast and unicast signals are superimposed in the power domain and the superimposed communication signals are also exploited as radar probing waveforms. A beamformer-based NOMA-aided joint Rad-MU-Com framework is proposed for the system having a single R-user and a single C-user. Based on this framework, the unicast rate maximization problem is formulated by optimizing the beamformers employed, while satisfying the rate requirement of multicast and the predefined accuracy of the radar beam pattern. The resultant non-convex optimization problem is solved by a penalty-based iterative algorithm to find a high-quality near-optimal solution. Finally, our numerical results reveal that significant performance gains can be achieved by the proposed scheme over the benchmark schemes.

Medical Visual Question Answering as a specific-domain task requires substantive prior knowledge of medicine. However, deep learning techniques encounter severe problems of limited supervision due to the scarcity of well-annotated large-scale medical VQA datasets. As an alternative to facing the data limitation problem, image captioning can be introduced to learn summary information about the picture, which is beneficial to question answering. To this end, we propose a caption-aware VQA method that can read the summary information of image content and clinic diagnoses from plenty of medical images and answer the medical question with richer multimodality features. The proposed method consists of two novel components emphasizing semantic locations and semantic content respectively. Firstly, to extract and leverage the semantic locations implied in image captioning, similarity analysis is designed to summarize the attention maps generated from image captioning by their relevance and guide the visual model to focus on the semantic-rich regions. Besides, to combine the semantic content in the generated captions, we propose a Progressive Compact Bilinear Interactions structure to achieve cross-modality comprehension over the image, question and caption features by performing bilinear attention in a gradual manner. Qualitative and quantitative experiments on various medical datasets exhibit the superiority of the proposed approach compared to the state-of-the-art methods.

The novel concept of non-orthogonal multiple access (NOMA) aided joint radar and multicast-unicast communication (Rad-MU-Com) is investigated. Employing the same spectrum resource, a multi-input-multi-output (MIMO) dual-functional radar-communication (DFRC) base station detects the radar-centric users (R-user), while transmitting mixed multicast-unicast messages both to the R-user and to the communication-centric user (C-user). In particular, the multicast information is intended for both the R- and C-users, whereas the unicast information is only intended for the C-user. More explicitly, NOMA is employed to facilitate thisdouble spectrum sharing, where the multicast and unicast signals are superimposed in the power domain and the superimposed communication signals are also exploited as radar probing waveforms. First, abeamformer-basedNOMA-aided joint Rad-MU-Com framework is proposed for the system having a single R-user and a single C-user. Based on this framework, the unicast rate maximization problem is formulated by optimizing the beamformers employed, while satisfying the rate requirement of multicast and the predefined accuracy of the radar beam pattern. The resultant non-convex optimization problem is solved by a penalty-based iterative algorithm to find a high-quality near-optimal solution. Next, the system is extended to the scenario of multiple pairs of R- and C-users, where acluster-basedNOMA-aided joint Rad-MU-Com framework is proposed. A joint beamformer design and power allocation optimization problem is formulated for the maximization of the sum of the unicast rate at each C-user, subject to the constraints on both the minimum multicast rate for each R&C pair and on accuracy of the radar beam pattern for detecting multiple R-users. The resultant joint optimization problem is efficiently solved by another penalty-based iterative algorithm developed. Finally, our numerical results reveal that significant performance gains can be achieved by the proposed schemes over the benchmark schemes employing conventional transmission strategies.

Medical images contain various abnormal regions, most of which are closely related to the lesions or diseases. The abnormality or lesion is one of the major concerns during clinical practice and therefore becomes the key in answering questions about medical images. However, the recent efforts still focus on constructing a generic Visual Question Answering framework for medical-domain tasks, which is not adequate for practical medical requirements and applications. In this paper, we present two novel medical-specific modules named multiplication anomaly sensitive module and residual anomaly sensitive module to utilize weakly supervised anomaly localization information in medical Visual Question Answering. Firstly, the proposed multiplication anomaly sensitive module designed for anomaly-related questions can mask the feature of the whole image according to the anomaly location map. Secondly, the residual anomaly sensitive module could learn a flexible anomaly feature while preserving the information of the original questioned image, which is more helpful in answering anomaly-unrelated questions. Thirdly, the transformer decoder and multi-task learning strategy are combined to further enhance the question-reasoning ability and the model generalization performance. Finally, qualitative and quantitative experiments on a variety of medical datasets exhibit the superiority of the proposed approaches compared to the state-of-the-art methods.

The novel concept of simultaneously transmitting and reflecting (STAR) reconfigurable intelligent surfaces (RISs) is investigated, where the incident wireless signal is divided into transmitted and reflected signals passing into both sides of the space surrounding the surface, thus facilitating a full-space manipulation of signal propagation. Based on the introduced basic signal model of `STAR', three practical operating protocols for STAR-RISs are proposed, namely energy splitting (ES), mode switching (MS), and time switching (TS). Moreover, a STAR-RIS aided downlink communication system is considered for both unicast and multicast transmission, where a multi-antenna base station (BS) sends information to two users, i.e., one on each side of the STAR-RIS. A power consumption minimization problem for the joint optimization of the active beamforming at the BS and the passive transmission and reflection beamforming at the STAR-RIS is formulated for each of the proposed operating protocols, subject to communication rate constraints of the users. For ES, the resulting highly-coupled non-convex optimization problem is solved by an iterative algorithm, which exploits the penalty method and successive convex approximation. Then, the proposed penalty-based iterative algorithm is extended to solve the mixed-integer non-convex optimization problem for MS. For TS, the optimization problem is decomposed into two subproblems, which can be consecutively solved using state-of-the-art algorithms and convex optimization techniques. Finally, our numerical results reveal that: 1) the TS and ES operating protocols are generally preferable for unicast and multicast transmission, respectively; and 2) the required power consumption for both scenarios is significantly reduced by employing the proposed STAR-RIS instead of conventional reflecting/transmiting-only RISs.

Anatomical landmark localization has been a key challenge for medical image analysis. Existing researches mostly adopt CNN as the main architecture for landmark localization while they are not applicable to process image modalities with periodic structure. In this paper, we propose a novel two-stage frame-level detection and heatmap regression model for accurate landmark localization in m-mode echocardiography, which promotes better integration between global context information and local appearance. Specifically, a periodic frame detection module with LSTM is designed to model periodic context and detect frames of systole and diastole from original echocardiography. Next, a CNN based heatmap regression model is introduced to predict landmark localization in each systolic or diastolic local region. Experiment results show that the proposed model achieves average distance error of 9.31, which is at a reduction by 24% comparing to baseline models.

This paper investigates intelligent reflecting surface (IRS)-assisted systems, where an access point sends independent information to multiple users with the aid of one IRS. Our goal is to characterize the capacity region of the IRS-assisted multiuser communication systems. We jointly optimize the discrete phase-shift matrix of the IRS and resource allocation with the capacity-achieving non-orthogonal multiple access (NOMA) transmission scheme. The Pareto boundary of the capacity region is characterized by maximizing the average sum rate of all users, subject to a set of rate-profile constraints, total transmit power and discrete IRS phase shift constraints. Though the formulated problem is non-convex, we derive the globally optimal solutions by invoking the Lagrange duality method. It is shown that the optimal transmission strategy is alternating transmission among different user groups by dynamically adjusting the IRS phase shifts. We further propose a Hadamard codebook based scheme, which serves as a lower bound on the optimal performance gains. Numerical results demonstrate that: i) the IRS is capable of significantly improving the capacity region; ii) the capacity region achieved by the Hadamard codebook based scheme is close to that of discrete phase shifts for a small number of IRS elements.

Due to the mobility and flexibility of unmanned aerial vehicle (UAV), it has been widely used in data collection. This article considers multiple UAVs to collect data from multiple sensor nodes (SNs) with the interference. In order to ensure the timeliness of the collected data, we jointly optimize the trajectory of the UAVs and the wake-up time allocation as well as the transmit power of the SNs for minimization of the mission completion time. The formulated problem is non-convex with continuous variables which is difficult to solve. In order to solve this problem, we consider time discretization directly, then use bisection search to turn it into a finite variable problem and use the successive convex approximation and alternating optimization techniques to solve it. In our research, we initialized the UAV's trajectory with tangent circles to speed up the convergence of algorithm. The simulation results show that the proposed method complete the missions of data collection better than benchmark schemes.

Intelligent reflecting surface (IRS) enhanced multi-unmanned aerial vehicle (UAV) non-orthogonal multiple access (NOMA) networks are investigated. A new transmission framework is proposed, where multiple UAV-mounted base stations employ NOMA to serve multiple groups of ground users with the aid of an IRS. The three-dimensional (3D) placement and transmit power of UAVs, the reflection matrix of the IRS, and the NOMA decoding orders among users are jointly optimized for maximization of the sum rate of considered networks. To tackle the formulated mixed-integer non-convex optimization problem with coupled variables, a block coordinate descent (BCD)-based iterative algorithm is developed. Specifically, the original problem is decomposed into three subproblems, which are alternately solved by exploiting the penalty-based method and the successive convex approximation technique. The proposed BCD-based algorithm is demonstrated to be able to obtain a stationary point of the original problem with polynomial time complexity. Numerical results show that: 1) the proposed NOMA-IRS scheme for multi-UAV networks achieves a higher sum rate compared to the benchmark schemes, i.e., orthogonal multiple access (OMA)-IRS and NOMA without IRS; 2) the use of IRS is capable of providing performance gain for multi-UAV networks by both enhancing channel qualities of UAVs to their served users and mitigating the inter-UAV interference; and 3) optimizing the UAV placement can make the sum rate gain brought by NOMA more distinct due to the flexible decoding order design.

The fundamental capacity limits of intelligent reflecting surface (IRS)-assisted multi-user wireless communication systems are investigated in this article. Specifically, the capacity and rate regions for both capacity-achieving non-orthogonal multiple access (NOMA) and orthogonal multiple access (OMA) transmission schemes are characterized by jointly optimizing the IRS reflection matrix and wireless resource allocation under the constraints of a maximum number of IRS reconfiguration times. In NOMA, all users are served in the same resource blocks by employing superposition coding and successive interference cancelation techniques. In OMA, all users are served by being allocated orthogonal resource blocks of different sizes. For NOMA, the ideal case with an asymptotically large number of IRS reconfiguration times is firstly considered, where the optimal solution is obtained by employing the Lagrange duality method. Inspired by this result, an inner bound of the capacity region for the general case with a finite number of IRS reconfiguration times is derived. For OMA, the optimal transmission strategy for the ideal case is to serve each individual user alternatingly with its effective channel power gain maximized. Based on this result, a rate region inner bound for the general case is derived. Finally, numerical results are provided to show that: i) a significant capacity and rate region improvement can be achieved by using IRS; ii) the capacity gain can be further improved by dynamically configuring the IRS reflection matrix.

Integrating robots into cellular networks creating connected robotic users has emerged as a promising technology for future smart cities and smart factories due to their low cost and high maneuverability. However, the requirement of establishing stable and high-quality communication links to the robotic users greatly restricts their applicability, especially in indoor environments where obstacles may block the wireless link. To tackle this challenge, in this paper, an indoor robot navigation system is investigated, where an intelligent reflecting surface (IRS) is employed to enhance the connectivity between the access point (AP) and robotic users. Both single-user and multiple-user scenarios are considered. In the single-user scenario, one mobile robotic user (MRU) communicates with the AP. In the multiple-user scenario, the AP serves one MRU and one static robotic user (SRU) employing either non-orthogonal multiple access (NOMA) or orthogonal multiple access (OMA) transmission. The considered system is optimized for minimization of the travelling time/distance of the MRU from a given starting point to a predefined final location, while satisfying constraints on the communication quality of the robotic users. To this end, a radio map based approach is proposed to exploit location-dependent channel propagation knowledge. For the single-user scenario, a channel power gain map is constructed, which characterizes the spatial distribution of the maximum expected effective channel power gain of the MRU for the optimal IRS phase shifts. Based on the obtained channel power gain map, the communication-aware robot path planing problem is solved by exploiting graph theory. For the multiple-user scenario, a communication rate map is constructed, which characterizes the spatial distribution of the maximum expected rate of the MRU for the optimal power allocation at the AP and the optimal IRS phase shifts subject to a minimum rate requirement for the SRU. The joint optimization problem is efficiently solved by invoking bisection search and successive convex approximation methods. Then, a graph theory based solution for the robot path planning problem is derived by exploiting the obtained communication rate map. Our numerical results show that: 1) the required travelling distance of the MRU can be significantly reduced by deploying an IRS; 2) NOMA yields a higher communication rate for the MRU than OMA; 3) the IRS performance gain is significantly more pronounced for NOMA than for OMA.

The fundamental intelligent reflecting surface (IRS) deployment problem is investigated for IRS-assisted networks, where one IRS is arranged to be deployed in a specific region for assisting the communication between an access point (AP) and multiple users. Specifically, three multiple access schemes are considered, namely non-orthogonal multiple access (NOMA), frequency division multiple access (FDMA), and time division multiple access (TDMA). The weighted sum rate maximization problem for joint optimization of the deployment location and the reflection coefficients of the IRS as well as the power allocation at the AP is formulated. The non-convex optimization problems obtained for NOMA and FDMA are solved by employing monotonic optimization and semidefinite relaxation to find a performance upper bound. The problem obtained for TDMA is optimally solved by leveraging thetime-selectivenature of the IRS. Furthermore, for all three multiple access schemes, low-complexity suboptimal algorithms are developed by exploiting alternating optimization and successive convex approximation techniques, where alocal region optimizationmethod is applied for optimizing the IRS deployment location. Numerical results are provided to show that: 1) near-optimal performance can be achieved by the proposed suboptimal algorithms; 2)asymmetricandsymmetricIRS deployment strategies are preferable for NOMA and FDMA/TDMA, respectively; 3) the performance gain achieved with IRS can be significantly improved by optimizing the deployment location.

In this paper, a multi-scale convolutional neural network-based (MSN) method is proposed for robust automatic modulation classification (AMC). The classifier directly utilizes in-phase and quadrature (I/Q) samples to identify the modulation type of received signal without any data preprocessing, thereby reducing the computational complexity. Further, the network architecture employs one-dimensional convolution (Conv1D) to extract multi-scale feature maps due to its merits of low computational complexity. Then these multi-scale feature maps are merged together by repeated multi-scale fusions, in order to improve the classification accuracy performance and the robustness to varying SNR environment. Repeated multi-scale fusions can make better use of amplitude-phase information because it can learn the local changes brought by modulation as well as the timing characteristics of the samples. Simulation results show that proposed MSN achieves classification rate of 97.38% classification accuracy at high SNR regimes for 24 different modulation types on the public well-known over-the-air (OTA) dataset. Moreover, MSN still can recognize the modulation types of received signals with the accuracy rates of about 95% under varying SNR scenarios. Compared to the methods proposed in other papers, our classifier not only shows a better performance in terms of classification accuracy, but also is the most robust in varying SNR environment.

In millimeter-wave (mmWave) communication systems, hybrid beamforming is regarded as an effective way to increase the spectral efficiency of the massive multiple-input multiple-output (MIMO) system. Assuming perfect channel state information (CSI) is known at the transmitter, we focus on a downlink massive multi-user MIMO system which supports multi-stream per user. In the above scenario, we investigate the hybrid beamforming problem with strong correlation between users' channels, where the existing schemes have performance loss. To tackle this problem, this paper proposes the channel correlation cancelation-based hybrid beamforming (CCCHB) algorithm which considers the correlation between channels and decomposes the optimization of overall spectrum efficiency of the users to a series of sub-rate optimization problems. And the block diagonalization (BD) technique is used in the equivalent channel to eliminate inter-user interference. Simulation results illustrate that the performance of the proposed scheme outperforms the existing algorithm, especially significant when there exists high correlation between users' channels.

This paper investigates ground-aerial uplink non-orthogonal multiple access (NOMA) cellular networks. A rotary-wing unmanned aerial vehicle (UAV) user and multiple ground users (GUEs) are served by ground base stations (GBSs) by utilizing the uplink NOMA protocol. The UAV is dispatched to upload specific information bits to each target GBSs. Specifically, our goal is to minimize the UAV mission completion time by jointly optimizing the UAV trajectory and UAV-GBS association order while taking into account the UAV's interference to non-associated GBSs. The formulated problem is a mixed integer non-convex problem and involves infinite variables. To tackle this problem, we efficiently check the feasibility of the formulated problem by utilizing graph theory and topology theory. Next, we prove that the optimal UAV trajectory needs to satisfy the fly-hover-fly structure. With this insight, we first design an efficient solution with predefined hovering locations by leveraging graph theory techniques. Furthermore, we propose an iterative UAV trajectory design by applying successive convex approximation (SCA) technique, which is guaranteed to coverage to a locally optimal solution. We demonstrate that the two proposed designs exhibit polynomial time complexity. Finally, numerical results show that: 1) the SCA based design outperforms the fly-hover-fly based design; 2) the UAV mission completion time is significantly minimized with proposed NOMA schemes compared with the orthogonal multiple access (OMA) scheme; 3) the increase of GUEs' quality of service (QoS) requirements will increase the UAV mission completion time.

This paper investigates a downlink multiple-input single-output intelligent reflecting surface (IRS) aided non-orthogonal multiple access (NOMA) system, where a base station (BS) serves multiple users with the aid of IRSs. Our goal is to maximize the sum rate of all users by jointly optimizing the active beamforming at the BS and the passive beamforming at the IRS, subject to successive interference cancellation decoding rate conditions and IRS reflecting elements constraints. In term of the characteristics of reflection amplitudes and phase shifts, we consider ideal and non-ideal IRS assumptions. To tackle the formulated non-convex problems, we propose efficient algorithms by invoking alternating optimization, which design the active beamforming and passive beamforming alternately. For the ideal IRS scenario, the two subproblems are solved by invoking the successive convex approximation technique. For the non-ideal IRS scenario, constant modulus IRS elements are further divided into continuous phase shifts and discrete phase shifts. To tackle the passive beamforming problem with continuous phase shifts, a novel algorithm is developed by utilizing the sequential rank-one constraint relaxation approach, which is guaranteed to find a locally optimal rank-one solution. Then, a quantization-based scheme is proposed for discrete phase shifts. Finally, numerical results illustrate that: i) the system sum rate can be significantly improved by deploying the IRS with the proposed algorithms; ii) 3-bit phase shifters are capable of achieving almost the same performance as the ideal IRS; iii) the proposed IRS-aided NOMA systems achieve higher system sum rate than the IRS-aided orthogonal multiple access system.

This paper investigates ground-aerial uplink non- orthogonal multiple access (NOMA) cellular networks. A unmanned aerial vehicle (UAV) user and ground users (GUEs) are served by ground base stations (GBSs) by utilizing uplink NOMA protocol. The goal is to minimize the UAV mission completion time by jointly designing the UAV trajectory and UAV-GBS association vectors while considering the interference of UAV to other non-associated GBSs. The formulated problem is a mixed integer non-convex problem and involves infinite number of variables, which is difficult to be directly solved. To tackle this challenge, we first prove the optimal UAV trajectory satisfies \emph{fly-hover-fly} communication policy. With this insight, we propose an efficient algorithm to solve the original problem based on a properly constructed graph by invoking graph theory and convex optimization techniques. Numerical results show that the UAV mission completion time is significantly minimized with proposed NOMA scheme compared with conventional orthogonal multiple access (OMA) communication and reveal a tradeoff between the UAV mission completion time and GUEs' quality-of-service (QoS) requirements.

Unmanned aerial vehicle (UAV) millimeter-wave (mmWave) communication is emerging as a promising technique for future networks with flexible network topology and ultra-high data transmission rate. Within such full-dimensionally dynamic mmWave network, beam-tracking is challenging and critical, especially when all the UAVs are in motion for some collaborative tasks that require high-quality communications. In this paper, we propose a fast beam tracking scheme, which is built on an efficient position prediction of multiple moving UAVs. In particular, a Gaussian process based machine learning scheme is proposed to achieve fast and accurate UAV position prediction with quantifiable positional uncertainty. Based on the prediction results, the beam-tracking can be confined within some specific spatial regions centered on the predicted UAV positions. In contrast to the full-space searching based scheme, our proposed position prediction based beam tracking requires little system overhead and thus achieves high net spectrum efficiency. Moreover, we also propose a practical communication protocol embedding our beam-tracking scheme, which monitors the channel evolution and triggers the UAV position prediction for beam-tracking, transmit-receive beam pair selection and data transmission. Simulation results validate the advantages of our scheme over the existing works.

Attention-based encoder-decoder approaches have shown promising results in scene text recognition. In the literature, models with different encoders, decoders and attention mechanisms have been proposed and compared on isolated word recognition tasks, where the models are trained on either synthetic word images or a small set of real-world images. In this paper, we investigate different components of the attention based framework and compare its performance with a CNN-DBLSTM-CTC based approach on large-scale real-world scene text sentence recognition tasks. We train character models by using more than 1.6M real-world text lines and compare their performance on test sets collected from a variety of real-world scenarios. Our results show that (1) attention on a two-dimensional feature map can yield better performance than one-dimensional one and an RNN based decoder performs better than CNN based one; (2) attention-based approaches can achieve higher recognition accuracy than CNN-DBLSTM-CTC based approaches on isolated word recognition tasks, but perform worse on sentence recognition tasks; (3) it is more effective and efficient for CNN-DBLSTM-CTC based approaches to leverage an explicit language model to boost recognition accuracy.

In this paper, a supervised approach based on Convolutional Neural Networks (CNN) for polyphonic piano transcription is presented. The system consists of pitch detection model, onset/offset detection model, and note search model. The pitch detection model is a single-channel CNN predicting the probabilities of pitches contained in one frame of the audio. The onset/offset model based on dual-channel CNN is used for estimating the probabilities of each pitch's onset or offset in a frame. The note search model is rule-based; it integrates the outputs of the pitch model and onset/offset model to determine the final onset, offset and pitch of notes in audio. Two experiments with different dataset conditions are accomplished to compare with state-of-the-art approaches on the same datasets. Experimental results reveal that the proposed approach preforms better in both frame- and note-based metrics.

Recently, security problems in massive multiple-input multiple-output (MIMO) network draw more and more attention. In this paper, a security problem for a multi-pair massive MIMO two-way amplify-and-forward (AF) relay network is considered, where multiple users exchange confidential messages via a common relay equipped with large number of antennas. We propose an optimal power allocation scheme that maximizes the secrecy sum rate (SSR) under power constraints, when the multi-pair sources act as both potential eavesdroppers who intend to wiretap the information of other pairs and conventional users who exchange their information with pairings. Simulation results show that the proposed scheme outperforms the equal power allocation especially under the circumstance of large number of relay antennas. Furthermore, the number of user-pairs, the Signal to Noise Ratio (SNR) and the number of relay antennas are all factors which influence the performance of SSR in this network.

In the time-division-duplex (TDD) system, the channel state information (CSI) is mainly obtained through channel estimation. The active eavesdropper is able to attack the channel estimation phase by sending the same pilot signals as the legitimate users send to the base station without being detected, which can destroy the CSI acquired through channel estimation and greatly decrease the communication quality, so it is very necessary to detect the active eavesdropper before the data transmission. In this paper, we propose to design a mechanism to detect active eavesdropper in the massive MIMO network. Specifically, the sender will intentionally add noise to the pilot sequence so that it becomes harder for the bad guys to learn the pilot sequence. At the same time, if the real sender and the attacker signals arrive at the receiver simultaneously, the received signals will demonstrate special properties in the rank of the matrix. we design a mechanism to estimate the ranks to detect active eavesdropper. Comparison between the approach and MDL-based detector is conducted.

With the development of wireless communication, one of the critical demands is secure transmission especially in downlink communication. In this paper, downlink secure transmission in two-cell base station cooperation multiuser network is studied. The two base stations are fully cooperated and an artificial noise (AN) is added to degrade the eavesdropper(EVE)'s channel. Perfect channel state information (CSI) of all users is known by the base stations and regularized channel inversion (RCI) precoding is used. The close form expression of secrecy sum rate is derived in the large system regime. The regularization parameter and the power allocation ratio are optimized based on larger system regime results. From analysis, base station cooperation network could serve more users per cell in secure transmission than single cell network. The numerical results show large system regime results are accurate even in finite case. In the simulation figures, the analytical optimal results can well approximate to the simulation results.

In this study, zero‐forcing matrix decomposition polynomial expansion update (ZF‐MDPE‐update) and zero‐forcing successive over relaxation update (ZF‐SOR‐update) algorithms are proposed to update a zero‐forcing detector quickly without requiring complicated matrix inversion recomputations when massive multiple‐input multi‐output systems channel estimates contain a small perturbation. To further accelerate the convergence rate and to maximise date throughput, a new method of calculating the optimal coefficients for the matrix polynomial that can significantly improve the accuracy of the initial input inverse matrix approximation is considered by the ZF‐MDPE‐update algorithm. On the other hand, the ZF‐SOR‐update algorithm with an optimal iterative initial solution and an optimal relaxation parameter is devised, which achieves excellent detection performance. Results demonstrate that when the ratio of base station (BS) antennas to user terminal (UT) antennas, , is small, the proposed update detection algorithms, with only a few operations, achieve a significant improvement in the average achievable rate of the UTs compared to the recently proposed update algorithm. Therefore, more UTs can be served in a cell with a fixed number of BS antennas. At the same time, the authors' algorithms are shown to facilitate easy memory transfer and are low cost.

A non-reused pilot (NRP) design scheme is presented for Large-scale multi-cell multiuser multiple-input multiple-output (LS-MIMO) systems. As the users at the cell edge suffer from severe pilot contamination (PC), the pilot design based on Chu sequences for two kinds of users is considered. The users in each cell are divided into center users and edge users according to the large-scale fading coefficients. The proposed pilot design scheme can reduce inter-cell interference of center users and improve the performance of edge users, whereby assigning phase shifted pilot groups to center users in adjacent cells and orthogonal pilot group to edge users in all cells.

This paper investigates the cooperative beamforming in the amplify-and-forward-based cognitive relay network. Beamforming coefficients are designed to maximize the sum rate of the secondary users with a total transmit power constraint of the relays and an interference power constraint at the primary receiver. The sum rate maximization problem is firstly solved by characterizing the achievable rate region. This method is optimal but of great complexity. Then, an iteration algorithm based on semidefinite programming (SDP) and the first order Taylor polynomial which has lower complexity but comparable performance is introduced. Simulation results confirm the feasibility of these two methods for the sum rate maximization problem in the cognitive relay network and demonstrate that the lower complexity method finds the global optimum of the problem just as the rate region method does.

In this paper, we propose a filter-and-forward (FF)beamforming strategy in the secondary relays for the one-way cognitive relay network with frequency selective fading channels. Our aim is to optimize the beamforming coefficients and the secondary transmitted power to maximize the SINR at the secondary destination, while satisfying the interference constraint on the primary network and the total relays' transmitted power restriction. To solve this problem, we propose a two-step iterative algorithm. Simulation results show that comparing the amplifyand-forward (AF) strategy, the filter-and-forward strategy (FF) can get higher SINR at the secondary destination by using the algorithm that we proposed.

Distributed beamforming (DBF) is a cooperative technology that several nodes transmit a common message to a receiver efficiently. The key to DBF is to ensure every node's signal adds coherently at the receiver by synchronizing node's carrier phase. In this paper, we present a closed-loop deterministic phase synchronization algorithm in order to pursue less synchronization time, less feedback information, less energy consumption. We analyze the performance of this algorithm and make a comparison between the new and the previous closed-loop phase synchronization algorithms.

This paper investigates an energy-efficient transmission scheme in cognitive radio networks, where primary users (PUs) may reoccupy the spectrum when secondary users (SUs) is transmitting data. We aim to maximize the energy efficiency by jointly optimizing the transmission power, the fusion rule threshold and the sensing/transmission durations. Firstly, it is derived that for a given fusion rule threshold, the objective function is unimodal while only one optimization parameter varies. Furthermore, we provide the corresponding closed-form expressions of the optimal data transmission duration and transmission power. Finally, the globally unimodal property is proven, and hence, the globally optimal point can be easily found with the proposed algorithm based on the alternating direction method (ADM). Numerical simulation results show that our proposed scheme is much better than the existing ones.

While a cognitive radio network sharing the spectrum with a primary network, one of the major concerns is that harmful interference to the primary users should be avoided. In this paper, we propose three low-complexity algorithms for distributed beamforming in cognitive radio networks which opportunistically select a subset of cognitive source nodes whose phases may be compensated, so that the received signals in cognitive destination can combine in a quasi-coherent manner and the interference to the primary users is not destructive. Only a few bits feedback from cognitive destination is required per cognitive source node. Simulation results demonstrate the good performance of the proposed algorithms.

We propose an opportunistic scheduling method to achieve DoF (degrees of freedom) gain by BIA (blind interference alignment) in block fading K-user 2 × 1 MISO broadcast channel. The optimal scheduling method is obtained by solving a general model of linear integer program. All the users are divided into user pairs to form a 2-user 2 × 1 BIA. Each pair has the same opportunity to be scheduled. When K ≥ 10, the expectation of the achieved DoF can be very close to4/3.

This paper investigates the joint design of relay and receive beamforming vectors in cognitive relay networks with the secondary network (SN) using the same frequency band allocated to the primary network (PN). To guarantee the QoS of the primary user (PU), the interference from source and relays in the SN to PU must be lower than what the PU can tolerate. A hybrid relay strategy is adopted by relays that can use amplify-and-forward (AF) or decode-and-forward (DF) strategies to retransmit signal according to signal to interference pulse noise ratio (SINR). The capacity of the source-destination in the SN is maximized with the transmit power and the interference at PU constraints. The simulation results show that the maximum relay transmit power will affect the gain of both the joint beamforming and the hybrid relay strategy, while the maximum interference power at PU will only affect that of the hybrid relay strategy.

We investigate a decode and forward (DF) scheme of Asymmetric modulation suited for two-way relay (TWR) with network coding. The considering network coding consists of two time-slots: two users transmit wireless signal to the relay in time slot 1, and the processed signal is broadcasted in time-slot 2 by the relay. With the received asymmetric modulated signals by relay in time-slot 1, the judging, coding and power allocating problems are investigated. A judging region (JR) scheme is proposed to solve the issues and the symbol error ratio (SER) is derived. We also give the optimized power allocation method of JR scheme according to different asymmetric modulations. The performance evaluations show correctness of SER expression and efficiency of power allocation method.