The inherent fluctuations in the stock market present significant challenges in understanding stock dynamics, especially for investment decisions based on stock ranking. Recent advancements in learning-based methods have led to promising results in exploring temporal dependencies to understand stock movements. However, they often assume stable, certain, and reliable environments, narrowing their insight into the complex and fluctuating nature of markets. This complexity is driven by two influential factors: the explicit consistency of dynamic yet stable trends across diverse temporal patterns, coupled with the implicit interplay of logic and possibility under uncertainty. Hence, we introduce aSensitivity-awareDependencyLearning solution (SDL) for stock ranking. With bridging the ideal and reality in mind, SDL captures short-term fluctuations under the guidance of long-term dependencies, associated with the augmentation of counterfactual knowledge. Specifically, SDL devises aShort-termCo-integrationDetector (SCD) that concentrates on capturing time-varying correlations and immediate market reactions, in addition to multi-period attention. Furthermore, aLong-termCo-movementsTracker (LCT) takes advantage of enduring industry relationships and incorporates counterfactual knowledge, allowing the model to generalize beyond observed patterns and identify diverse long-term trends. Comprehensive experiments on five real-world stock markets demonstrate that our proposed SDL outperforms several representative baselines.

The metro flow in Urban Rail Transit Systems (URTS) differs from other urban traffic flows because it is characterized by: (1) highly predetermined scheduling; and (2) interactively dynamic dependencies over the fixed physical infrastructure that vary with spatiotemporal and environmental factors. Notwithstanding the advances in graph neural networks, existing efforts fail to fully capture the characteristics and complex spatiotemporal dynamics specific to metro flow, as the innate graph-aware interactions underlying a metro flow are frequently affected by an amalgamation of: intrinsic connectivity, environmental associations, and flow-activated correlation, which usually dynamically evolve over time while containing redundant signals. We propose ReDyNet, a novel Responsive Dynamic Graph Neural Network to accurately understand the spatiotemporal dynamics of metro flow and external factors. Specifically, it employs a responsive mechanism that adapts to variations in metro flow and external influences, ensuring the construction of an appropriate dynamic graph. In addition, ReDyNet follows the merits of information bottleneck (IB) theory with redundancy disentanglement to enhance the clarity and precision of contextual spatial signals. Our experiments conducted on three real-world metro passenger flow datasets demonstrate that the proposed ReDyNet outperforms several representative baselines.

Text-to-video (T2V) generation models have made significant progress in creating visually appealing videos. However, they struggle with generating coherent sequential narratives that require logical progression through multiple events. Existing T2V benchmarks primarily focus on visual quality metrics but fail to evaluate narrative coherence over extended sequences. To bridge this gap, we present SeqBench, a comprehensive benchmark for evaluating sequential narrative coherence in T2V generation. SeqBench includes a carefully designed dataset of 320 prompts spanning various narrative complexities, with 2,560 human-annotated videos generated from 8 state-of-the-art T2V models. Additionally, we design a Dynamic Temporal Graphs (DTG)-based automatic evaluation metric, which can efficiently capture long-range dependencies and temporal ordering while maintaining computational efficiency. Our DTG-based metric demonstrates a strong correlation with human annotations. Through systematic evaluation using SeqBench, we reveal critical limitations in current T2V models: failure to maintain consistent object states across multi-action sequences, physically implausible results in multi-object scenarios, and difficulties in preserving realistic timing and ordering relationships between sequential actions. SeqBench provides the first systematic framework for evaluating narrative coherence in T2V generation and offers concrete insights for improving sequential reasoning capabilities in future models. Please refer to https://videobench.github.io/SeqBench.github.io/ for more details.

Client selection is a promising approach to address heterogeneity in Federated learning. Existing methods predominantly focus on optimizing training efficiency, often neglecting the impact of selection fairness. In this paper, we investigate client selection in volatile environments, leveraging the Age-of-Information concept to formulate long-term fairness constraints and develop an optimization model that ensures fairness while maximizing overall efficiency. By converting the offline problem into an online framework via Lyapunov optimization, we reframe client selection under the Contextual Combinatorial Multi-Armed Bandit (C2MAB) framework. Integrated with the LinUCB algorithm, we propose FedECS, an efficient client selection strategy. Experiments on public datasets demonstrate FedECS’s superior fairness guarantees, achieving 13% higher accuracy than FedCS and 5.8% improvement over RBCS-F.

Multi-replica storage is an advanced extension of traditional cloud storage that allows data owners to customize the number of backups for file blocks based on their relative importance. In such settings, remote auditing mechanisms are essential for verifying data integrity and ensuring that the cloud service provider (CSP) maintains the pre-negotiated number of replicas. However, existing schemes often expose block positions and backup quantities to the CSP, making users' data vulnerable to template attacks. Meanwhile, secure deduplication significantly reduces storage overhead and user costs while preserving data confidentiality. In this paper, we propose a novel multi-replica cloud storage scheme that, for the first time, simultaneously supports cross-user deduplication and integrity auditing in the ciphertext domain. The proposed scheme can not only protect data privacy from template attacks but also enable the elimination of redundant ciphertext replicas and audit authentication tags across users at the block level. Formal analysis validates the correctness and security guarantees of our scheme. Experimental results demonstrate its effectiveness with modest overhead.

Federated learning (FL) is a distributed learning paradigm that enables multiple client devices to collaboratively train a global model based on their local datasets while protecting data privacy. However, due to its distributed nature, FL is susceptible to the resources of heterogeneous client devices with different data quantities, communication resources, and computing capabilities. Heterogeneity leads to uncertain global model training time and hinders the convergence of the global model. Therefore, selecting suitable clients to participate in the FL training process is necessary to improve the efficiency of FL. This paper proposes an FL client selection method (FedAHP) based on the Analytic Hierarchy Process (AHP) to optimally balance the trade-off between model accuracy and training time during client selection. Experiments show that FedAHP outperforms the greedy method regarding training time consumption and model accuracy. Specifically, FedAHP achieves a 67% reduction in communication rounds compared to the greedy method when the model accuracy reaches 0.90. Furthermore, when taking the same 20 hours, FedAHP improves the accuracy of the global model by 6% in comparison to the greedy method.

Graph neural networks, as well as attention mechanisms, have gained widespread popularity for traffic flow forecasting due to their capacity to incorporate the complicated interactions behind flow dynamics. However, existing solutions either formulate a graph-based skeleton with narrow (e.g., static) interaction capture or build the spatiotemporal (e.g., dynamic) attention without proper comprehension of diverse risks, which inevitably burdens the generalization of high-accuracy traffic trends. In this study, we introduce Gboot (Graph bootstrap) enhancement framework for traffic flow forecasting. Gboot takes the traffic flow forecasting problem from a dependency dynamic learning perspective by treating each traffic sensor as the graph node while regarding the observed flows at each sensor as the node feature. In addition to exposing the explicit spatial connectivity behind traffic flows, we hierarchically devise temporal-aware and factual-aware graph learning blocks to consider temporal interactive dynamics and factual interactive dynamics. The former shows the trend dependencies behind flow signals and the latter uncovers different views of traffic situations (e.g., current observation vs. historical observation). More importantly, we present a Dual-view Bootstrap (DvBoot) mechanism in Gboot, which includes both risk-free and risk-aware stands. DvBoot attempts to flexibly align these two views in the latent space to enhance the generalization capability of capturing dynamic dependencies. Experiments on several real-world traffic datasets demonstrate the superiority of our Gboot over representative approaches.

Sketch-based traffic measurement is a crucial building block for monitoring traffic statistics and ensuring the quality of services of end-host applications. However, existing approaches for building sketches in end-hosts exhibit poor packet processing performance or high CPU consumption. In this paper, we propose MPU, which automatically offloads sketch-based measurement to the emerging hardware, DPU. MPU consists of a sketch analyzer that profiles sketch resource consumption and an optimization framework that formulates the offloading problem and maximizes sketch performance on DPU. We implement MPU on the NVIDIA BlueField DPU. Our testbed results indicate that MPU achieves 85% lower per-packet processing latency and 47% higher traffic measurement accuracy when compared to existing approaches.

This work proposes a command filter-based adaptive practical prescribed-time (PPT) asymptotic tracking control scheme for autonomous underwater vehicles (AUVs) under dynamic uncertainties. Considering that the followers have limited communication angles in the leader–follower formation structure, where a novel controller is proposed to ensure communication angles to achieve preassignable precision within a predefined time. First, we present a PPT control for handling the limited communication angles and, thus, they are allowed to be limited, turnable, and controllable. Then, to achieve the asymptotic convergence of output tracking errors, the proposed adaptive controllers can effectively insure the trajectory tracking errors of AUVs asymptotically converge to zero under the influence of dynamic uncertainties. Furthermore, the derived asymptotically tracking command filter technique for AUVs not only deduce an acceleration-free strategy for followers but also achieve the asymptotic convergence of output tracking errors for the command filters themselves. In the end, the effectiveness of the proposed control strategy is demonstrated through stability analysis and simulation test.

Predicting disease progression in the initial stage to implement early intervention and treatment can effectively prevent the further deterioration of the condition. Traditional methods for medical data analysis usually fail to perform well because of their incapability for mining the correlation pattern of pathogenies. Therefore, many calculation methods have been excavated from the field of deep learning. In this study, we propose a novel method of influence hypergraph convolutional generative adversarial network (IHGC-GAN) for disease risk prediction. First, a hypergraph is constructed with genes and brain regions as nodes. Then, an influence transmission model is built to portray the associations between nodes and the transmission rule of disease information. Third, an IHGC-GAN method is constructed based on this model. This method innovatively combines the graph convolutional network (GCN) and GAN. The GCN is used as the generator in GAN to spread and update the lesion information of nodes in the brain region-gene hypergraph. Finally, the prediction accuracy of the method is improved by the mutual competition and repeated iteration between generator and discriminator. This method can not only capture the evolutionary pattern from early mild cognitive impairment (EMCI) to late MCI (LMCI) but also extract the pathogenic factors and predict the deterioration risk from EMCI to LMCI. The results on the two datasets indicate that the IHGC-GAN method has better prediction performance than the advanced methods in a variety of indicators.

The traditional median filtering method uses a fixed filter window size method to remove the impulse noise in a fingerprint image. If the filtering window size is small, the traditional median filtering method will not filter out the impulse noise completely. If the filtering window size is large, the fingerprint image may become blurred. To solve the problem, a method based on adaptive median filter is proposed for fingerprint image enhancement processing and impulse noise removal in the paper. The use of adaptive median filtering to remove the impulse noise of the fingerprint image mainly involves three steps. First, the size of the adaptive median filter window is initialized, and it is judged whether the center pixel of the filter window in the fingerprint image is impulse noise. Second, the size of the filter window is determined based on the median value, the maximum value, and the minimum value within the filter window. Finally, median filtering is performed on the fingerprint image under the filter window size obtained in the previous steps, and the filter output value is used instead of the window center pixel value. The method is tested on rolled fingerprint images contaminated by impulse noise and fingerprint images contaminated by impulse noise from a crime scene. Experimental results show that the method based on adaptive median filter for fingerprint image enhancement outperforms the traditional median filtering method in filtering impulse noise performance.

Light detection and ranging is a relatively new technology, developed to complement traditional remote sensing technology. Digital aerial image provides reflectance information for land cover while LIDAR data provide more accurate geometrical information. There is much potential for fusing these two sources to achieve increased accuracy and utility for feature detection and classification. In order to assist Guangxi Electric Power Design Institute to improve their efficiency in power transmission line selection and design, field survey work, and reduce the cost, we have recently carried out the first power line project by using LIDAR and high resolution digital camera in China. The use of coloring LIDAR points by RGB of digital images makes it possible for obtaining high quality of in-room surveying, feature detection and classification. In addition, high quality and high resolution of DEM, DSM, DOM and visualization provides our customer not only with better selection and design of power line route, and reduced survey work, but also significant savings by 10 percent reduction of power line construction.