This study presents a framework for time-causal wavelet analysis. It targets real-time processing of temporal signals, where data from the future are not available. The study builds upon temporal scale-space theory, originating from a complete classification of temporal smoothing kernels that guarantee non-creation of new structures from finer to coarser temporal scale levels. We construct temporal wavelets from the temporal derivatives of a special time-causal smoothing kernel, referred to as the “time-causal limit kernel”—arising from the classification of variation-diminishing smoothing transformations with the complementary requirement of temporal scale covariance—to guarantee self-similar handling of structures in the input signal at different temporal scales. This enables the decomposition of the signal into different components at different scales while adhering to temporal causality. The study establishes theoretical foundations for these time-causal wavelet representations and maps structural relationships to the non-causal Ricker/Mexican hat wavelets. We also describe how efficient discrete approximations of the theory presented can be performed in terms of first-order recursive filters coupled in cascade, enabling numerically well-conditioned real-time processing with low resource usage. We characterize and quantify how the continuous scaling properties transfer to the discrete implementation, demonstrating how the proposed time-causal wavelet representation can reflect the duration of locally dominant temporal structures in the input signal. We propose this notion of time-causal wavelet analysis as a generic multi-purpose tool for signal processing tasks, where streams of signals are to be processed in real time—specifically for signals that may contain local variations over a rich span of temporal scales or more generally for analyzing physical or biophysical temporal phenomena, where a fully time-causal analysis needs to be physically realistic, by not accessing data from the future, as is often done for prerecorded data.
Accurate indoor localization remains difficult in GPS-denied environments because Wi-Fi received signal strength indicator (RSSI) fingerprints are sparse, noisy, device-dependent, and strongly affected by multipath propagation, non-line-of-sight conditions, and environmental dynamics. To address these challenges, we present IndoorCART (Indoor Context-Aware RSSI Transformer), an encoder-only transformer framework designed specifically for coordinate-regression-based Wi-Fi fingerprinting. IndoorCART represents access-point measurements as RSSI tokens, incorporates learnable access-point identity information, applies missing-signal-aware Adaptive Attention to model contextual dependencies among observed and unobserved signals, and combines CLS-token and global-average representations for robust coordinate prediction. The model is evaluated on three public indoor-localization benchmarks, namely, UJIIndoorLoc, TUJI1, and SODIndoorLoc, using a controlled comparison with nine reproducible regression baselines. IndoorCART achieves mean absolute errors of 4.79 m, 0.18 m, and 1.33 m on UJIIndoorLoc, TUJI1, and SODIndoorLoc, respectively, with corresponding R 2 scores of 0.99, 0.98, and 0.99. These results show that the proposed context-aware transformer consistently provides the lowest localization error among the implemented baselines and is particularly beneficial in sparse or structurally complex fingerprinting scenarios. We further position the proposed method against recent transformer-based indoor-localization studies through a literature-level comparison, while explicitly distinguishing reported external results from controlled reimplementations. Overall, IndoorCART offers an accurate and reliable framework for Wi-Fi-based indoor positioning; however, practical deployment should further consider model size, inference latency, energy consumption, device heterogeneity, and the modest performance gain observed on densely sampled datasets such as UJIIndoorLoc.
Abdominal medical image segmentation is essential for computer-aided diagnosis, lesion localization, quantitative organ analysis, and treatment planning. However, abdominal computed tomography (CT) images often contain large anatomical variations, complex tissue structures, low contrast, blurred boundaries, and small tumor regions, which make accurate and efficient segmentation challenging. Convolutional neural networks (CNNs) are effective in extracting local textures, edges, and spatial details, but their limited receptive fields restrict long-range dependency modeling. Transformers can capture global contextual relationships, yet dense token modeling introduces redundant background information and high computational cost, while fine-grained local details may be insufficiently preserved. To address these limitations, we propose a Polynomial Dynamic Sparse Attention-driven Dual-Branch U-Net, termed PDSA-DBUNet, for abdominal medical image segmentation. The network adopts a parallel CNN–Transformer architecture, where the CNN branch preserves local boundary and texture information, and the Transformer branch models global semantic dependencies. A dynamic sparse visual token generation module adaptively aggregates dense image tokens into a compact set of discriminative sparse tokens, emphasizing organ regions and blurred boundaries while suppressing irrelevant background responses. A PoM-based polynomial mixing mechanism is further incorporated into the dynamically generated sparse token set to replace conventional multi-head self-attention, enabling efficient global contextual interaction with reduced computational and memory costs. In addition, a Dual-Scale Parallel Attention Fusion (DSPAF) module integrates CNN-derived local details with Transformer-derived global semantics to enhance boundary localization and small-target representation. Experiments on the LiTS and KiTS19 datasets show that PDSA-DBUNet achieves Dice scores of 96.79% and 86.13% on LiTS-Liver and LiTS-Tumors, and 94.03% and 89.06% on Kidney and Kidney-Tumor segmentation tasks, respectively. The model requires 72.87 GFLOPs, contains 41.62M learnable parameters, and has a checkpoint storage size of 129.93 MB. These results demonstrate that PDSA-DBUNet achieves a favorable balance between segmentation accuracy and computational efficiency.
Abhrendu Bhattacharya, Raktim Kumar Dey, Amit R. Welekar, Rajesh Bose, Sandip Roy, Arfat Ahmad Khan, Muhammad Shoaib Ayub, Insoo Koo
In the era of extensive developmental growth, multimedia communication systems demand protective and indiscernible information-hiding techniques that can maintain a balance between robustness, capacity, and computational efficacy. The research gap analysis highlights the necessity for a mathematically defined steganographic strategy that integrates rate–distortion optimization, knowledge-based adaptive embedding, hybrid domain modeling, and statistical invisibility constraints in a non-heuristic approach toward scalable high-capacity transmission systems. The novelty of the proposed strategy lies in the combination of rate–distortion optimization, adaptive CNN-based control for embedding, and histogram preservation of frequency channel embedding within a consolidated information-hiding architecture, within illuminated components of color areas. This ensures observable fidelity and configurational stability. To generate an adaptive embedding-based probability map, a lightweight convolutional neural network that enables a content-aware embedding dependent on local picture complexity is incorporated. Moreover, incorporating a histogram-preservation restriction reduces sensitivity to classical and learning-guided steganalysis and increases analytical security. Furthermore, Toom–Cook accelerated convolution is utilized to achieve improved computational scalability through accelerated transform-domain convolution, ensuring scalability for high-resolution images. Experimental analysis illustrates excellent performance with superior imperceptibility in average values obtained for a peak signal-to-noise ratio (PSNR) maintained above 50 dB (≈51.40 dB) and average structural similarity index measure (SSIM) ≈0.9816, low bit error rates, and near-random detectability (area under curve ≈0.5). Comparative and ablation analyses confirm that the proposed framework outperforms existing spatial, transform-domain, and deep learning-based methods. The proposed approach provides a unified, theoretically constrained, and scalable solution for secure high-capacity image steganography.
Xiaomei Gai, Meichun Wang, Yantong Guo, Shiyu Wang, Ye Li, Rui Fu
Test-time adaptation (TTA) can improve detector robustness under distribution shift, but indiscriminate online updating may amplify errors from unreliable frames. We present AdaTent++, a reliability-guided hybrid TTA framework for traffic sign detection. For each unlabeled frame, the framework combines predictive entropy and cross-view agreement to select among a smoothed batched normalization (BN)-statistics update, a guarded BN-affine gradient update, and no adaptation. Exponential moving average (EMA) threshold tracking, prototype regularization, gradient control, and state restoration are used as supporting safeguards rather than claimed as independent novelties. On one public traffic sign dataset evaluated under 12 corrupted domains, AdaTent++ achieves a mean average precision (mAP50) of 68.87%, compared with 68.03% for the strongest baseline, T3A, corresponding to an improvement of 0.84 percentage points. It ranks first in three of the twelve domains and is less effective under several structure-destructive corruptions. The results indicate a favorable average trade-off in the studied setting, while cross-dataset, cross-architecture, embedded-device, and long-horizon validation remain open.
