Digital Signal Processing最新文献_第9页

Multimodal survival analysis using optimal transport matching and global-local feature fusion

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-02-26 DOI: 10.1016/j.dsp.2025.105119

Bowen Sun, Yanjun Peng, Yanglei Ge

{"title":"Multimodal survival analysis using optimal transport matching and global-local feature fusion","authors":"Bowen Sun, Yanjun Peng, Yanglei Ge","doi":"10.1016/j.dsp.2025.105119","DOIUrl":"10.1016/j.dsp.2025.105119","url":null,"abstract":"<div><div>The multimodal survival analysis aims to predict patient's mortality risk using multiple modality data. Unlike unimodal task, the essence of multimodal survival prediction is to efficiently integrate the information of different modalities to make more accurate judgments. Despite recent advancements, there are still some serious problems waiting to be properly addressed, such as: (1) there are huge structural differences between gigapixel pathological images and radiological or genetic data. (2) existing multiple instance methods mainly focus on local feature representation, often neglecting global features such as tissue spatial information. In order to reasonably solve these problems, we propose a multimodal survival framework, called the optimal transport (OT) matching and global-local feature fusion (OTGL) framework. Specifically, we first use specially crafted encoders for extracting the class tokens and instance tokens from different data. Then, by applying the optimal transport to the instance tokens of different modalities, the weighted features can be obtained. After that, we perform feature fusion for class tokens and the processed local features to derive the final features that can be used to predict risk score. And we use hybrid loss function to train our OTGL and apply it to pathology-radiomic and pathology-genomic cancer datasets, many experiments demonstrate that the proposed OTGL have better performance than existing state-of-the-art methods. In practical medical settings, our model can aid clinicians in identifying high-risk patients and personalizing treatment plans. The source code will be made available at <span><span>https://github.com/2018213444/OTGLmodel</span><svg><path></path></svg></span> upon acceptance of the manuscript for publication.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"161 ","pages":"Article 105119"},"PeriodicalIF":2.9,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143550093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Adaptive polymorphic mode decomposition

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-02-26 DOI: 10.1016/j.dsp.2024.104913

Zhehao Huang, Jinzhao Liu

{"title":"Adaptive polymorphic mode decomposition","authors":"Zhehao Huang, Jinzhao Liu","doi":"10.1016/j.dsp.2024.104913","DOIUrl":"10.1016/j.dsp.2024.104913","url":null,"abstract":"<div><div>Signal mode decomposition methods have been widely studied and applied for long. Most of them aim at handling specific non-linear signals, like AM-FM signal, close-spaced frequency chirplet signal, dispersive signal, crossed modes signal, periodic impactive signal, etc. For signal modes of multiple types, classical methods may yield undesirable results sometimes. To extract modes from multi-component multiform complex signal, a framework-like Adaptive Polymorphic Mode Decomposition (APMD) method is put forward in this article. First, Short-Time Fourier Transform (STFT) with optimal window length is applied to obtain the Time-Frequency Representation (TFR) of signal. Then, ridges and bandwidths of each mode are consecutively detected and optimized by iteration. Finally, the signal modes are restored by integration and squeezed in TFR. The idea is simple but novel with combination of Variational Mode Decomposition (VMD)-like methods and Synchro-Squeezing Transform (SST)-like methods, which is non-parameterized and fully adaptive. Results of decomposing some typical signal verify the effectiveness and robustness in analyzing complex polymorphic signals, being more suitable than traditional methods for decomposing signals mixed with both time-dominant and frequency-dominant components.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"161 ","pages":"Article 104913"},"PeriodicalIF":2.9,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143549991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

GLS: A hybrid deep learning model for radar emitter signal sorting

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-02-26 DOI: 10.1016/j.dsp.2025.105117

Liangang Qi , Hongzhuo Chen , Qiang Guo , Shuai Huang , Mykola Kaliuzhnyi

{"title":"GLS: A hybrid deep learning model for radar emitter signal sorting","authors":"Liangang Qi , Hongzhuo Chen , Qiang Guo , Shuai Huang , Mykola Kaliuzhnyi","doi":"10.1016/j.dsp.2025.105117","DOIUrl":"10.1016/j.dsp.2025.105117","url":null,"abstract":"<div><div>Radar emitter signal sorting is a pivotal aspect of radar reconnaissance signal processing. The increasing density of the electromagnetic environment in modern radar pulse streams, coupled with the growing complexity and variability of operational modes and signal forms, results in extremely limited reference data. Consequently, most existing sorting methods fall short of meeting the performance requirements of modern electronic warfare. To enhance sorting performance under conditions of limited samples and labeled data, this paper proposes a radar emitter signal sorting model based on ResGCN-BiLSTM-SE (GLS). Firstly, we propose a novel adaptive weighted adjacency matrix construction method that aggregates multi-scale information of local and global features. Based on this, for GLS networks, the graph convolutional network (ResGCN) is combined with the bidirectional long short-term memory (BiLSTM) network. The GCN is employed to extract attribute features from interleaved radar pulse sequences, while the BiLSTM is utilized to deeply capture the temporal dependence in interleaved pulse sequences after feature extraction. Finally, an improved squeeze-and-excitation (SE) module is applied to perform weighted fusion of critical channel information from both spatial and temporal features. Simulation results demonstrate that the proposed method not only achieves higher accuracy under small sample conditions compared to existing methods, but also exhibits strong robustness in challenging scenarios involving measurement errors, missing pulses, and spurious pulses.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"161 ","pages":"Article 105117"},"PeriodicalIF":2.9,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143509856","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

HAMSA: Hybrid attention transformer and multi-scale alignment aggregation network for video super-resolution

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-02-25 DOI: 10.1016/j.dsp.2025.105098

Hanguang Xiao , Hao Wen , Xin Wang , Kun Zuo , Tianqi Liu , Wei Wang , Yong Xu

{"title":"HAMSA: Hybrid attention transformer and multi-scale alignment aggregation network for video super-resolution","authors":"Hanguang Xiao , Hao Wen , Xin Wang , Kun Zuo , Tianqi Liu , Wei Wang , Yong Xu","doi":"10.1016/j.dsp.2025.105098","DOIUrl":"10.1016/j.dsp.2025.105098","url":null,"abstract":"<div><div>Video Super-Resolution (VSR) aims to enhance the resolution of video frames by utilizing multiple adjacent low-resolution frames. For across-frame information extraction, most existing methods usually employ the optical flow or learned offsets through deformable convolution to perform alignment. However, due to the complexity of real-world motions, the estimating of flow or motion offsets can be inaccurate while challenging. To address this problem, we propose a novel hybrid attention transformer and multi-scale alignment aggregation network for video super-resolution, named HAMSA. The proposed HAMSA adopts a U-shaped architecture to achieve progressive alignment using a multi-scale manner. Specifically, we develop a hybrid attention transformer (HAT) feature extraction module, which uses the proposed channel motion attention (CMA) to extract features that facilitate inter-frame alignment. Second, we first design a U-shaped multi-scale feature alignment (MSFA) module that ensures precise motion estimation between different frames by starting from large-scale features, gradually aligning them to smaller scales, and then restoring them using skip connections and upsampling. In addition, to further refine the alignment process, we introduce a non-local feature aggregation (NLFA) module, which serves to apply non-local operations to minimize alignment errors and enhance the detail fidelity, thereby improving the overall quality of the super-resolved video frames. Extensive experiments on the Vid4, Vimeo90k-T, and REDS4 datasets demonstrate that our HAMSA achieves superior VSR performance compared to other state-of-the-art (SOTA) methods while maintaining a good balance between model size and performance.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"161 ","pages":"Article 105098"},"PeriodicalIF":2.9,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143487879","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

High-capacity reversible data hiding in encrypted images based on multi-predictions and efficient parametric binary tree labeling

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-02-24 DOI: 10.1016/j.dsp.2025.105096

Hua Ren , Tongtong Chen , Ming Li , Zhen Yue , Danjie Han , Guangrong Bai

{"title":"High-capacity reversible data hiding in encrypted images based on multi-predictions and efficient parametric binary tree labeling","authors":"Hua Ren , Tongtong Chen , Ming Li , Zhen Yue , Danjie Han , Guangrong Bai","doi":"10.1016/j.dsp.2025.105096","DOIUrl":"10.1016/j.dsp.2025.105096","url":null,"abstract":"<div><div>Reversible data hiding in encrypted images (RDHEI) enables the embedding of secret data into encrypted images while preserving the ability to fully recover the original images. Existing schemes typically leverage pixel redundancies for data embedding, but they are constrained by the choices of predictors and coding rules, which may result in inefficient bit utilization and increased auxiliary data. This paper presents a novel high-capacity RDHEI method to address these issues. We propose a multi-prediction strategy combining the median edge detector (MED) and the gradient-adjusted predictor (GAP) to improve prediction accuracy. Additionally, we introduce an efficient parametric binary tree labeling approach to categorize image pixels into embeddable, self-recording, and non-embeddable categories, which reduces the generation of auxiliary bits. Experimental results show that our method achieves embedding rates of 3.177, 3.098, 2.722, and 2.6533 bit per pixel (bpp) on the BOSSbase, BOWS-2, UCID, and CT-COVID datasets, respectively, while preserving the security and reversibility of the original image.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"161 ","pages":"Article 105096"},"PeriodicalIF":2.9,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143480466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Facing challenges: A survey of object tracking

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-02-24 DOI: 10.1016/j.dsp.2025.105082

Wenqi Zhang , Xinqiang Li , Xingyu Liu , Shiteng Lu , Huanling Tang

引用次数: 0

SGRNet: Semantic-guided Retinex network for low-light image enhancement

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-02-24 DOI: 10.1016/j.dsp.2025.105087

Yun Wei, Lei Qiu

{"title":"SGRNet: Semantic-guided Retinex network for low-light image enhancement","authors":"Yun Wei, Lei Qiu","doi":"10.1016/j.dsp.2025.105087","DOIUrl":"10.1016/j.dsp.2025.105087","url":null,"abstract":"<div><div>Under low-light conditions, details and edges in images are often difficult to discern. Semantic information of an image is related to the human understanding of the image's content. In low-light image enhancement (LLIE), it helps to recognize different objects, scenes and edges in images. Specifically, it can serve as prior knowledge to guide LLIE methods. However, existing semantic-guided LLIE methods still have shortcomings, such as semantic incoherence and insufficient target perception. To address those issues, a semantic-guided low-light image enhancement network (SGRNet) is proposed to improve the role of semantic priors in the enhancement process. Based on Retinex, low-light images are decomposed into illumination and reflectance with the aid of semantic maps. The semantic perception module, integrating semantic and structural information into images, can stabilize image structure and illumination distribution. The heterogeneous affinity module, incorporating high-resolution intermediate features of different scales into the enhancement net, can reduce the loss of image details during enhancement. Additionally, a self-calibration attention module is designed to decompose the reflectance, leveraging its cross-channel interaction capabilities to maintain color consistency. Extensive experiments on seven real datasets demonstrate the superiority of this method in preserving illumination distribution, details, and color consistency in enhanced images.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"161 ","pages":"Article 105087"},"PeriodicalIF":2.9,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143480471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Monotonically accelerated proximal gradient for nonnegative tensor decomposition

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-02-24 DOI: 10.1016/j.dsp.2025.105097

Deqing Wang

引用次数: 0

Fully differential decoder for decoding lattice codes using neural networks

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-02-24 DOI: 10.1016/j.dsp.2025.105088

Mohammad-Reza Sadeghi, Hassan Noghrei

{"title":"Fully differential decoder for decoding lattice codes using neural networks","authors":"Mohammad-Reza Sadeghi, Hassan Noghrei","doi":"10.1016/j.dsp.2025.105088","DOIUrl":"10.1016/j.dsp.2025.105088","url":null,"abstract":"<div><div>Short-length lattice codes are crucial in various applications, including channel estimation and quantization. This paper introduces a novel weighted lattice decoder (WLD) that utilizes a parametric function to process decoder inputs and incorporates a weighted Belief Propagation (BP) algorithm. To further enhance the accuracy of the decoder's estimations, a new two-part multiloss function is proposed. This innovative approach significantly improves the performance of <span><math><msub><mrow><mi>E</mi></mrow><mrow><mn>8</mn></mrow></msub></math></span>, Barns-Wall <span><math><msub><mrow><mtext>BW</mtext></mrow><mrow><mn>8</mn></mrow></msub></math></span>, and BCH lattice codes. The proposed WLD demonstrates notable improvements in the error-floor region, achieving gains of up to 1.4 dB and 2.3 dB on the Symbol Error Rate (SER) curve compared to the primary BP decoder and the Neural Network Lattice Decoding Algorithm, respectively. By leveraging these advancements, the WLD offers a more robust and efficient decoding solution, making it highly suitable for real-time applications where low latency and high accuracy are paramount.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"161 ","pages":"Article 105088"},"PeriodicalIF":2.9,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143480469","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-terminal modulation classification network with rain attenuation interference for UAV MIMO-OFDM communications using blind signal reconstruction and gradient integration optimization

IF 2.9 3区工程技术

Digital Signal Processing Pub Date : 2025-02-24 DOI: 10.1016/j.dsp.2025.105071

Gongjing Zhang , Nan Yan , Jiashu Dai , Zeliang An , Yifa Li

{"title":"Multi-terminal modulation classification network with rain attenuation interference for UAV MIMO-OFDM communications using blind signal reconstruction and gradient integration optimization","authors":"Gongjing Zhang , Nan Yan , Jiashu Dai , Zeliang An , Yifa Li","doi":"10.1016/j.dsp.2025.105071","DOIUrl":"10.1016/j.dsp.2025.105071","url":null,"abstract":"<div><div>The field of Automatic Modulation Classification (AMC) has emerged as a critical component in the advancement of next-generation intelligent Unmanned Aerial Vehicles (UAVs), 6G cognitive space communications, and spectrum regulation initiatives. Our research introduces an innovative AMC algorithm tailored for UAV MIMO-OFDM communication systems. This algorithm leverages blind signal reconstruction, constellation density matrix analysis, multi-terminal decision fusion, and model optimization training to enhance performance. The algorithm begins with the application of blind source separation to reconstruct signals and bolster their representation capabilities. Subsequently, we introduce a novel feature, the Enhanced Constellation Density Matrix (CDM), crafted to withstand the challenges posed by UAV channel interferences while providing a robust representation of the constellation diagram. Building upon this foundation, we propose the UAV-Decision Fusion Network (UAV-DFNet), an advanced network that utilizes CDM features as inputs to deeply mine signal characteristics and achieve superior signal recognition accuracy. To further refine the classification precision, we implement dual strategies: multi-terminal decision fusion and gradient integration, into the UAV-DFNet. Comprehensive experimental results substantiate the effectiveness and superiority of our UAV-DFNet classifier over existing deep learning (DL)-based classifiers, demonstrating its potential to significantly advance the state of the art in UAV cognitive communications and beyond.</div></div>","PeriodicalId":51011,"journal":{"name":"Digital Signal Processing","volume":"161 ","pages":"Article 105071"},"PeriodicalIF":2.9,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143487876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0