Remote Sensing Image Compression via Wavelet-Guided Local Structure Decoupling and Channel–Spatial State Modeling

Previous studies on Sound Event Localization and Detection (SELD) have primarily focused on CNN- and Transformer-based designs. While CNNs possess local receptive fields, making it difficult to capture global dependencies over long sequences, Transformers excel at modeling long-range dependencies but have limited sensitivity to local time–frequency features. Recently, the VMamba architecture, built upon the Visual State Space (VSS) model, has shown great promise in handling long sequences, yet it remains limited in modeling local spatial details. To address this issue, we propose a novel state space model with an attention-enhanced feature fusion mechanism, termed FFMamba, which balances both local spatial modeling and long-range dependency capture. At a fine-grained level, we design two key modules: the Multi-Scale Fusion Visual State Space (MSFVSS) module and the Wavelet Transform-Enhanced Downsampling (WTED) module. Specifically, the MSFVSS module integrates a Multi-Scale Fusion (MSF) component into the VSS framework, enhancing its ability to capture both long-range temporal dependencies and detailed local spatial information. Meanwhile, the WTED module employs a dual-branch design to fuse spatial and frequency domain features, improving the richness of feature representations. Comparative experiments were conducted on the DCASE2021 Task 3 and DCASE2022 Task 3 datasets. The results demonstrate that the proposed FFMamba model outperforms recent approaches in capturing long-range temporal dependencies and effectively integrating multi-scale audio features. In addition, ablation studies confirmed the effectiveness of the MSFVSS and WTED modules.

Deep learning has achieved remarkable success in hyperspectral image (HSI) classification, attributed to its powerful feature extraction capabilities. However, existing methods face several challenges: Convolutional Neural Networks (CNNs) are limited in modeling long-range spectral dependencies because of their limited receptive fields; Transformers are constrained by their quadratic computational complexity; and Mamba-based methods fail to fully exploit spatial–spectral interactions when handling high-dimensional HSI data. To address these limitations, we propose MRFP-Mamba, a novel Multi-Receptive-Field Parallel Mamba architecture that integrates hierarchical spatial feature extraction with efficient modeling of spatial–spectral dependencies. The proposed MRFP-Mamba introduces two key innovation modules: (1) A multi-receptive-field convolutional module employing parallel 1×1, 3×3, 5×5, and 7×7 kernels to capture fine-to-coarse spatial features, thereby improving discriminability for multi-scale objects; and (2) a parameter-optimized Vision Mamba branch that models global spatial–spectral relationships through structured state space mechanisms. Experimental results demonstrate that the proposed MRFP-Mamba consistently surpasses existing CNN-, Transformer-, and state space model (SSM)-based approaches across four widely used hyperspectral image (HSI) benchmark datasets: PaviaU, Indian Pines, Houston 2013, and WHU-Hi-LongKou. Compared with MambaHSI, our MRFP-Mamba achieves improvements in Overall Accuracy (OA) by 0.69%, 0.30%, 0.40%, and 0.97%, respectively, thereby validating its superior classification capability and robustness.

A comparison between neural network and traditional approaches to nonlinear system identification is investigated with respect to aspects of model performance. Two neural network models, the state space and input-output model structures, are considered. A global recurrent RMLP and a teacher forcing RMLP are categorized as the state space models, and a global feedback FMLP and a teacher forcing FMLP are considered as the input-output models. In the traditional methods an AutoRegressive eXogeneous (ARX) Input model and a Nonlinear AutoRegressive eXogeneous (NARX) Input model are considered. Basic algorithms of models are described, and simulation results are also presented through the system output response. Performance of models is compared based on the Mean-Square-Errors (MSE). Noise-added sinusoidal, pulse and step signals are chosen as the test inputs for the validation of the obtained models. Two different noise levels are augmented to the chosen input signals.

HLSK-CASMamba: hybrid large selective kernel and convolutional additive self-attention mamba for hyperspectral image classification

Hyperspectral unmixing is a critical task in remote sensing, challenged by complex mixing mechanisms and long-range spatial dependency modeling. To address the limitations of existing methods in capturing spatial structures and frequency representations, we propose SFMamba, a novel spatial-frequency collaborative unmixing framework. The framework includes two key modules: (1) a multi-view spatial mamba module based on state space model, which captures directional spatial dependencies to enhance contextual representation; and (2) a hyperspectral fourier mixer, which integrates fourier transform-based frequency features to strengthen the spectral modeling of endmembers. Experiments on the Urban and Jasper Ridge datasets demonstrate that the proposed method achieves superior performance in endmember extraction, with competitive results in abundance estimation, thus showing strong potential in hyperspectral unmixing tasks. This work provides a novel and effective solution for hyperspectral unmixing with spatial-frequency collaboration.

This paper discusses and documents the algorithms of SsfPack 2.2. SsfPack is a suite of C routines for carrying out computations involving the statistical analysis of univariate and multivariate models in state space form. The emphasis is on documenting the link we have made to the Ox computing environment. SsfPack allows for a full range of different state space forms: from a simple time-invariant model to a complicated time-varying model. Functions can be used which put standard models such as ARMA and cubic spline models in state space form. Basic functions are available for filtering, moment smoothing and simulation smoothing. Ready-to-use functions are provided for standard tasks such as likelihood evaluation, forecasting and signal extraction. We show that SsfPack can be easily used for implementing, fitting and analysing Gaussian models relevant to many areas of econometrics and statistics. Some Gaussian illustrations are given.

Lung cancer, which accounted for 2.48 million new cases and 1.82 million deaths worldwide in 2022, continues to be the most lethal cancer across the globe, underscoring the urgent demand for more advanced diagnostic tools. Although computed tomography (CT) imaging has long been central to lung cancer detection, the heterogeneous and complex characteristics of lung lesions make accurate segmentation particularly challenging. Current deep learning methods face a critical bottleneck: convolutional neural networks (CNNs) often struggle to capture long-range dependencies due to limited receptive fields, while Transformer-based architectures incur prohibitive computational costs when processing high-resolution CT volumes. Furthermore, standard skip connections in traditional UNet models frequently introduce redundant noise, leading to the dilution of subtle lesion features. To address these specific technical gaps, we introduce a novel deep learning framework that integrates Mamba state-space models with an improved UNet architecture. In this design, to mitigate feature redundancy, Squeeze-and-Excitation networks are embedded into skip connections, while auxiliary losses are introduced to address the degradation of shallow features and capture fine-grained lesion features across varied morphologies. Such a framework not only accommodates the intricate differences in lesion size, shape, and spatial distribution but also achieves a balance between global context modeling and linear computational efficiency. By uniting the local feature extraction strengths of convolutional layers with the long-range dependency modeling power of state-space models, our approach achieves more precise delineation of lung lesion boundaries. Extensive experiments conducted on multiple datasets provide compelling evidence of the method's effectiveness: it attains state-of-the-art segmentation accuracy and demonstrates significant promise for enhancing early detection, ongoing disease monitoring, and treatment planning in lung cancer patients. This advancement delivers a robust solution for the inherently complex task of lung lesion segmentation. Moreover, because lung cancer treatment is costly and insurance coverage plays a decisive role in distributing expenses, the study's outcomes also carry considerable implications for the insurance sector.

Various analytical techniques are available for modeling multivariate time series data. One such approach is the State Space Model, which can be employed to model this type of data. In this study, the data to be analyzed are data on the Indonesia Rupiah (IDR) exchange rate (ExR) against the US Dollar (USD), oil and gas exports (OGE), money supply (MS) and non-oil and gas exports (non-OGE) from January 2008 to December 2019. The aim of this study is to identify the most suitable state space model for the given data. In this research, the state space method will be applied to multivariate time series data, with the state space represented in the Vector Autoregressive (VAR) model to explore the interrelationships among groups of observed variables. The VAR model is a statistical technique used to analyze the relationships between variables in the dataset, employing the Granger Causality Test. The state space model is utilized to model and forecast multiple interconnected time series, where the variables exhibit dynamic interactions and to examine additional unobserved variables in the time series data. Based on the analysis results and the minimum value of the Akaike Information Criterion (AIC), the optimal VAR model identified is the VAR (6) model. The results of forecasting values using the state space model show that the predicted values and the real values for the state space model are very closed to each other.

Convolutional neural networks (CNNs) have been widely used in the field of hyperspectral image change detection (HSI-CD) due to their excellent feature extraction capabilities. However, traditional convolution methods usually rely on a limited number of convolution kernels when extracting local features, and the local information only covers a small range of details, making it difficult to flexibly extract local changes at different levels in the image. In addition, CNNs have certain limitations in modeling global dependencies. In recent years, state-space model (SSM)-based methods (such as mamba) have effectively solved the quadratic complexity problem of transformer in capturing long-distance global dependencies. However, due to the processing method of expanding images into sequences, the spatial location structure of the image is destroyed, the spatial correlation between adjacent pixels is weakened, and spatial location information is easily lost, resulting in poor performance on complex hyperspectral datasets. To address these issues, we propose a wavelet-augmented dual-branch position-embedding mamba network (WDP-Mamba) for hyperspectral image change detection. This network combines the complementary advantages of mamba and wavelet convolution (WTconv) in global feature extraction and local edge feature extraction. Specifically, our method includes the following key innovations: 1) a novel state-space model, the adaptive position residual state space block (APRSSB) is designed, embedding learnable positional encodings within the mamba framework. Through a dual-temporal spatial-spectral scoring mechanism, the model dynamically preserves the topological relationships of pixel positions, enabling global dependency modeling with linear complexity; 2) a multi-level frequency-domain aware (MLFA) module is proposed to fully extract representative local features by decomposing information into frequency components of different scales and analyzing signals locally in multiple time and frequency windows. Extensive experiments on three hyperspectral datasets show that WDP-Mamba outperforms existing methods in both qualitative and quantitative assessments. Compared with other comparative models, WDP-Mamba achieves significant improvements in multiple performance metrics with a lower number of parameters, demonstrating its superior performance in the HSI-CD task.

Temporal Forgery Localization (TFL) aims to precisely identify manipulated segments in video and audio, offering strong interpretability for security and forensics. While recent State Space Models (SSMs) show promise in precise temporal reasoning, their use in TFL is hindered by ambiguous boundaries, sparse forgeries, and limited long-range modeling. We propose DeformTrace, which enhances SSMs with deformable dynamics and relay mechanisms to address these challenges. Specifically, Deformable Self-SSM (DS-SSM) introduces dynamic receptive fields into SSMs for precise temporal localization. To further enhance its capacity for temporal reasoning and mitigate long-range decay, a Relay Token Mechanism is integrated into DS-SSM. Besides, Deformable Cross-SSM (DC-SSM) partitions the global state space into query-specific subspaces, reducing non-forgery information accumulation and boosting sensitivity to sparse forgeries. These components are integrated into a hybrid architecture that combines the global modeling of Transformers with the efficiency of SSMs. Extensive experiments show that DeformTrace achieves state-of-the-art performance with fewer parameters, faster inference, and stronger robustness.

Image classification, a core computer vision task, faces challenges in balancing long-range dependency capture, computational efficiency, and local detail preservation. Though Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) have seen great success, they suffer from limited receptive fields or quadratic computational complexity. Recent State Space Models (SSMs) enable efficient long-sequence modeling with linear complexity, but they overlook key local structural information. To solve this, we propose Local Information Awareness Vision Mamba (LIA-VMamba), a new image classification network integrating a Bidirectional State Propagation Module (BSPM) and an Adaptive Graph Convolution Enhancement (AGCE) module. BSPM aims to boost global context capture via bidirectional spatial information flow in the SSM framework. AGCE builds dynamic graph structures over image patches, using adaptive graph convolution and multi-head attention to model local dependency and fine-grained features. Extensive experiments on CIFAR-10 and ImageNet-1K benchmarks show a favorable accuracy-efficiency trade-off of our model, and clear ablation studies validate the effectiveness of our key modules.

We propose a statistical strategy to predict differentially regulated genes of case and control samples from time-course gene expression data by leveraging unpredictability of the expression patterns from the underlying regulatory system inferred by a state space model. The proposed method can screen out genes that show different patterns but generated by the same regulations in both samples, since these patterns can be predicted by the same model. Our strategy consists of three steps. Firstly, a gene regulatory system is inferred from the control data by a state space model. Then the obtained model for the underlying regulatory system of the control sample is used to predict the case data. Finally, by assessing the significance of the difference between case and predicted-case time-course data of each gene, we are able to detect the unpredictable genes that are the candidate as the key differences between the regulatory systems of case and control cells. We illustrate the whole process of the strategy by an actual example, where human small airway epithelial cell gene regulatory systems were generated from novel time courses of gene expressions following treatment with(case)/without(control) the drug gefitinib, an inhibitor for the epidermal growth factor receptor tyrosine kinase. Finally, in gefitinib response data we succeeded in finding unpredictable genes that are candidates of the specific targets of gefitinib. We also discussed differences in regulatory systems for the unpredictable genes. The proposed method would be a promising tool for identifying biomarkers and drug target genes.

State space is one of the key concepts of system theory. In general, a state space is introduced into a system description without examining its specific physical meaning. It is known, however, that if we select a suitable state space representation, it becomes easier for us to understand or to manipulate the property of a system. Thus, although it may not be meaningful to try to arrive at a physical meaning of the state space, it is important to find a way where a choice of a state space can be made in accordance with the system of interest, taking into account the theoretical meaning of that choice. In this paper, the choice of a state space is discussed in terms of the concepts that general systems theory have provided and the canonical forms of linear control theory are interpreted using the state space representation. Four realizations of a single-input and single-output discrete basic linear system are constructed, whose state spaces are derived from system properties. such as reachability, past-det...

In medical imaging diagnosis, accurate segmentation of the knee joint can help doctors better observe and diagnose lesions, thereby improving diagnostic accuracy and treatment effectiveness. Vision Mamba mainly relies on the State Space Model (SSM) for feature modeling, which excels at capturing global contextual information but cannot capture local texture features. Moreover, features of different scales are not effectively integrated, resulting in the model's weak segmentation ability on small-scale tissues (such as cartilage areas). To this end, this study proposed a novel multi-scale Vision Mamba Unet (VM-Unet) framework named MSPF-VM-Unet to perform the segmentation on the femur, tibia, femoral cartilage, and tibial cartilage in knee MRI images. The proposed MSPF-VM-Unet extends VM-Unet by introducing a designed multi-scale pyramid feature extraction network named MPSK, which synergizes multi-resolution feature extraction with channel-space attention. MPSK network enhances multi-scale local feature extraction through Selective Kernel (SK) convolution and pyramid pooling. The network merges the overall context information extracted by the Vision Mamba encoder to achieve the coordinated optimization of a multi-scale hierarchical feature fusion mechanism and global long-range dependency modeling. The results of the comparative experiments on the OAI-ZIB dataset indicate that MSPF-VM-Unet significantly improves the boundary accuracy and regional consistency of the MRI tibiofemoral joint tissue structure.

Although control algorithms have been conceived for industrial chemical systems, their acceptance by industry has been slow due to a lack of direct experimental evidence of their effectiveness and to volumes of conflicting, or at least incompatible, recommendations on control structure design. This thesis provides the basis for a concerted theoretical and experimental program in multivariable process control structure design for packed bed chemical reactors by presenting an in-depth control analysis of a practical, multivariable, distributed parameter system-the heat conduction problem defined by the simple diffusion equation-using both frequency-domain and time-domain analyses and the formulation, numerical solution, and analysis of a detailed model for packed bed reactors, along with reduction to a low-order state-space representation suitable for on-line process control. The study of the heat conduction system allowed for consideration of various control design techniques and the relation between measurement structure and control system design. This study shows that the choice of measurements and their locations significantly affects the optimal control design and the usefulness of the different design techniques and the importance of an accurate process model and the necessity of model reduction to a low-order state-space representation for control structure design and implementation. The second portion of this study provides a detailed mathematical modeling analysis of packed bed catalytic reactors that significantly extends previous studies in the detail of the model and in the consideration of all aspects of the model development and reduction to a state-space control representation. The general view that modeling simplifications are desired since they lead to a reduction in numerical solution effort is contested, and it is shown that many simplifications are no longer necessary with today's advanced computational capabilities. A unified approach to dynamic reactor modeling is developed and its importance in the accurate description of dynamic and steady state reactor behavior, in the investigation of reactor start-up or the effects of process disturbances, and in the development of an accurate reduced state-space model for the design of control structures to stabilize the reactor under various disturbances or to provide optimal system recovery from input changes is shown.