Cracks are one of the most common types of pavement damage. If not repaired promptly, they can significantly shorten the pavement’s service life and increase the risk of traffic accidents. Existing crack segmentation methods often misclassify cracks as discontinuous segments due to complex textures and backgrounds. This results in noise misclassification and inaccurate segmentation. To address these challenges, this paper proposes a Multi-Scale Frequency-Attentive Fusion Network (MSFAF-Net) for improved crack feature detection. The network uses a U-shaped structure and combines multi-scale frequency feature fusion with an attention mechanism. First, a Frequency-Enhanced Multi-scale Fusion Skip (FEMF-Skip) module integrates features from multiple scales. Additionally, a Multi-Scale Feature-Enhanced Bottleneck (MSFEB) is introduced. The MSFEB consists of a Multi-Scale Convolutional Block (MSCB) and a Weighted Spatial Channel Attention Block (WSCA). It focuses on different convolutional scales to extract enriched features and adjust feature weights using the attention mechanism. Finally, the decoder applies a Multi-Scale Feature Fusion (MSFF) strategy for more accurate segmentation. The model is evaluated on four publicly available crack datasets: CRACK500, DeepCrack, CFD, and EdmCrack600. Six metrics were used for objective assessment. Experimental results demonstrate that MSFAF-Net consistently outperforms existing methods.

Structural equation models (SEMs) are widely used in sciences, ranging from economics to psychology, to uncover causal relationships underlying a complex system under consideration and estimate structural parameters of interest. We study estimation in a class of generalized SEMs where the object of interest is defined as the solution to a linear operator equation. We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using the stochastic gradient descent. We consider both 2-layer and multi-layer NNs with ReLU activation functions and prove global convergence in an overparametrized regime, where the number of neurons is diverging. The results are established using techniques from online learning and local linearization of NNs, and improve in several aspects the current state-of-the-art. For the first time we provide a tractable estimation procedure for SEMs based on NNs with provable convergence and without the need for sample splitting.

We reformulate the Wasserstein Discriminant Analysis (WDA) as a ratio trace problem and present an eigensolver-based algorithm to compute the discriminative subspace of WDA. This new formulation, along with the proposed algorithm, can be served as an efficient and more stable alternative to the original trace ratio formulation and its gradient-based algorithm. We provide a rigorous convergence analysis for the proposed algorithm under the self-consistent field framework, which is crucial but missing in the literature. As an application, we combine WDA with low-dimensional clustering techniques, such as K-means, to perform subspace clustering. Numerical experiments on real datasets show promising results of the ratio trace formulation of WDA in both classification and clustering tasks.

In Mobile WiMAX, a mobile station (MS) scans neighboring base stations (BSs) before conducting handover. The MS may perform the association further, i.e., initial ranging, with neighboring BSs during scanning to obtain ranging parameters and/or service availability information for a potential handover to a BS and/or the selection of target BSs. However, the scanning with association scheme may introduce additional latency for handover. This study first evaluates the conventional scanning with association process, and then proposes a mechanism to reduce the association latency. The performance models of the proposed mechanism are presented and the accuracies of analytical models are verified by simulations. Results demonstrate that the proposed mechanism reduces the association latency by 61.9%-78.0% for audio services and 41.3%-65.4% for video services.

In this paper, we propose a passive-blind scheme for detecting forged images. The scheme leverages quantization table estimation to measure the inconsistency among images. To improve the accuracy of the estimation process, each AC DCT coefficient is first classified into a specific type; then the corresponding quantization step size is measured adaptively from its energy density spectrum (EDS) and the EDS's Fourier transform. The proposed content-adaptive quantization table estimation scheme is comprised of three phases: pre-screening, candidate region selection, and tampered region identification. In the pre-screening phase, we determine whether an input image has been JPEG compressed, and count the number of quantization steps whose size is equal to one. To select candidate regions for estimating the quantization table, we devise a candidate region selection algorithm based on seed region generation and region growing. First, the seed region generation operation finds a suitable region by removing suspect regions, after which the selected seed region is merged with other suitable regions to form a candidate region. To avoid merging suspect regions, a candidate region refinement operation is performed in the region growing step. After estimating the quantization table from the candidate region, an maximum-likelihood-ratio classifier exploits the inconsistency of the quantization table to identify tampered regions block by block. To evaluate the scheme's performance in terms of tampering detection, three common forgery techniques, copy-paste tampering, inpainting, and composite tampering, are used. Experiment results demonstrate that the proposed scheme can estimate quantization tables and identify tampered regions effectively.

One of the most important issues in offering real-time communication services in a mobile environment is support for seamless handover between base stations during a communication session. In Mobile WiMAX, a mobile station may have to perform a scan and association process before handover, but unfortunately, this scan and association process introduces service disruption. In this letter, we investigate the scan and association latency in Mobile WiMAX, and evaluate its performance through analytic models and simulations.

Broadband wireless access systems usually provide flexible sleep-mode operations for mobile stations to conserve energy during idle or active modes. For example, the IEEE 802.16e offers several sleep-mode classes that can be applied to mobile subscriber stations (MSSs) to reduce their power consumptions for different applications. Unfortunately, previous studies did not fully utilize sleep-mode features, and the power consumption of an MSS with multiple network connections is not optimized. In this work, two scheduling algorithms for sleep-mode operations based on the IEEE 802.16e are proposed. These schemes guarantee the quality of services (QoSs) of the network connections for an MSS and also minimize the power consumption of the MSS. Simulation results demonstrate that the proposed schemes outperform the traditional approaches.