Multivariate time series (MTS) forecasting presents significant challenges due to the diverse noise distributions and complex periodic patterns across different channels. Existing Transformer-based models often apply uniform noise reduction techniques and simplistic patch segmentation, resulting in suboptimal performance in capturing fine-grained periodic dependencies. In this paper, we propose PPDformer, which independently denoises each channel’s data and identifies key periodic components using Short Time Fourier Transform (STFT). Additionally, we present a novel period-based patch segmentation strategy with period clustering, which transforms 1D time series data into 2D patches based on the identified periodicity. Furthermore, we design a dual attention mechanism for local and global information aggregation. Extensive experiments on public datasets demonstrate that PPDformer achieves state-of-the-art forecasting accuracy, particularly in scenarios with complex periodicity and noise. Code is available at https://github.com/damonwan1/PPDformer.

Deep-learning-based lossless compression is of immense importance in real-world applications, such as cold data persistence, sensor data collection, and astronomical data transmission. However, existing compressors typically model data using single-byte symbols as tokens, which makes it hard to capture the inherent correlations and cannot effectively utilize the parallel capabilities of GPU and multi-core CPU. This paper proposes SEP, a novel lossless compression framework for most time-series backbone neural networks. We first introduce a semantic enhancement module to capture the complex intra-patch relationships of binary byte streams. To improve the compression speed, we design multi-stream pipelines that dynamically assign parallel tasks to GPU streams and multi-cores. We further propose a novel GPU memory optimization strategy, which reuses GPU memory by a shared pool across streams. We conduct experiments on seven real-world datasets and the results demonstrate that our SEP framework outperforms state-of-the-art compressors with an average speed improvement of 30.0% and an average compression ratio gain of 5.1%, which is further elevated to 7.6% with the use of pre-training models. The GPU memory footprint is reduced by as high as 63.1% and by an average of 36.2%. The source code is available at: https://github.com/damonwan1/SEP.

Over 4.15 million low-income households across nearly 60,000 villages in China benefit from photovoltaic (PV) poverty alleviation power stations. However, weak infrastructure and limited capabilities make these systems vulnerable to fluctuations. One of the United Nations' Sustainable Development Goals (SDG 7) seeks to ensure access to affordable and reliable energy for all, especially in underdeveloped regions. This paper proposes MCloudNet, a multi-modal framework designed to improve ultra-short-term PV prediction in data-scarce, cloud-dynamic environments. MCloudNet explicitly models multi-layer cloud structures from satellite imagery and fuses them with time-series meteorological data to enhance prediction accuracy and interpretability. A province-level dispatch system with MCloudNet has been deployed in Hebei, supporting scheduling across rural PV stations. Experiments conducted in counties such as Shexian and Luxi highlight the framework's effectiveness for use in underdeveloped micro-grids. Operational results show that the system has reduced over 60 million kWh of solar curtailment and generated 24 million CNY in economic value, benefiting approximately 50,000 rural households. By minimizing power fluctuations and improving rural energy scheduling, MCloudNet supports essential services such as lighting, medical facilities, and communications. The source code is available at: https://github.com/AI4SClab/MCloudNet.

Knowledge tracing is effective in modeling learners' knowledge levels to predict future answering situations based on their past learning history and interaction processes. However, current methods often overlook the impact of knowledge point correlations on answer prediction. This paper design a model based on deep hierarchical knowledge fusion networks (DHKFN). It utilizes statistical approaches to construct correlation matrices to capture the correlations between knowledge points. Subsequently, it constructs a topology graph structure of questions and knowledge points and utilizes a multi-head attention network to learn student interaction information from multiple perspectives, effectively constructing adjacency matrices. Finally, it uses GCN to learn the interaction information representation between deep-level knowledge points from dynamically constructed a topology graph structures. Experimental results on three large public datasets show that DHKFN effectively considers the influence of correlations between different knowledge points, thus showing promising effectiveness.

Ma et al. recently submitted a comment correspondence which points out a flaw in our paper (a sequel of our earlier paper published in the Proceedings of IEEE INFOCOM). The flaw led to the leakage of the system-wide master key; therefore, we improved our own scheme by addressing it.

Modeling and learning of brain activity patterns represent a huge challenge to the brain-computer interface (BCI) based on electroencephalography (EEG). Many existing methods estimate the uncorrelated instantaneous demixing of EEG signals to classify multiclass motor imagery (MI). However, the condition of uncorrelation does not hold true in practice, because the brain regions work with partial or complete collaboration. This work proposes a novel method, termed as a common Bayesian network (CBN), to discriminate multiclass MI EEG signals. First, with the constraints of a Gaussian mixture model on every channel, only related channels are selected to construct a normal Bayesian network. Second, the nodes that have both common and varying edges are selected to construct a CBN. Third, the probabilities on common edges are used to learn about the support vector machine for classification. To validate the proposed method, we conduct experiments on two well-known BCI datasets and perform a numerical analysis of the propose algorithm for EEG classification in a multiclass MI BCI. Experimental results show that the proposed CBN method not only has excellent classification performance, but also is highly efficient. Hence, it is suitable for the cases where a system is required to respond within a second.

Much research has been conducted to securely outsource multiple parties' data aggregation to an untrusted aggregator without disclosing each individual's privately owned data, or to enable multiple parties to jointly aggregate their data while preserving privacy. However, those works either require secure pair-wise communication channels or suffer from high complexity. In this paper, we consider how an external aggregator or multiple parties can learn some algebraic statistics (e.g., sum, product) over participants' privately owned data while preserving the data privacy. We assume all channels are subject to eavesdropping attacks, and all the communications throughout the aggregation are open to others. We first propose several protocols that successfully guarantee data privacy under semi-honest model, and then present advanced protocols which tolerate up to k passive adversaries who do not try to tamper the computation. Under this weak assumption, we limit both the communication and computation complexity of each participant to a small constant. At the end, we present applications which solve several interesting problems via our protocols.

Cloud computing is a revolutionary computing paradigm, which enables flexible, on-demand, and low-cost usage of computing resources, but the data is outsourced to some cloud servers, and various privacy concerns emerge from it. Various schemes based on the attribute-based encryption have been proposed to secure the cloud storage. However, most work focuses on the data contents privacy and the access control, while less attention is paid to the privilege control and the identity privacy. In this paper, we present a semianonymous privilege control scheme AnonyControl to address not only the data privacy, but also the user identity privacy in existing access control schemes. AnonyControl decentralizes the central authority to limit the identity leakage and thus achieves semianonymity. Besides, it also generalizes the file access control to the privilege control, by which privileges of all operations on the cloud data can be managed in a fine-grained manner. Subsequently, we present the AnonyControl-F, which fully prevents the identity leakage and achieve the full anonymity. Our security analysis shows that both AnonyControl and AnonyControl-F are secure under the decisional bilinear Diffie-Hellman assumption, and our performance evaluation exhibits the feasibility of our schemes.

Evolution mechanisms of different biological and social systems have inspired a variety of evolutionary computation (EC) algorithms. However, most existing EC algorithms simulate the evolution procedure at the individual-level. This paper proposes a new EC mechanism inspired by the evolution procedure at the tribe-level, namely tribal ecosystem inspired algorithm (TEA). In TEA, the basic evolution unit is not an individual that represents a solution point, but a tribe that covers a subarea in the search space. More specifically, a tribe represents the solution set locating in a particular subarea with a coding structure composed of three elements: tribal chief, attribute diversity, and advancing history. The tribal chief represents the locally best-so-far solution, the attribute diversity measures the range of the subarea, and the advancing history records the local search experience. This way, the new evolution unit provides extra knowledge about neighborhood profiles and search history. Using this knowledge, TEA introduces four evolution operators, reforms, self-advance, synergistic combination, and augmentation, to simulate the evolution mechanisms in a tribal ecosystem, which evolves the tribes from potentially promising subareas to the global optimum. The proposed TEA is validated on benchmark functions. Comparisons with three representative EC algorithms confirm its promising performance.

Differential evolution (DE) has been demonstrated to be one of the most promising evolutionary algorithms (EAs) for global numerical optimization. DE mainly differs from other EAs in that it employs difference of the parameter vectors in mutation operator to search the objective function landscape. Therefore, the performance of a DE algorithm largely depends on the design of its mutation strategy. In this paper, we propose a new kind of DE mutation strategies whose greediness degree can be adaptively adjusted. The proposed mutation strategies utilize the information of top t solutions in the current population. Such a greedy strategy is beneficial to fast convergence performance. In order to adapt the degree of greediness to fit for different optimization scenarios, the parameter t is adjusted in each generation of the algorithm by an adaptive control scheme. This way, the convergence performance and the robustness of the algorithm can be enhanced at the same time. To evaluate the effectiveness of the proposed adaptive greedy mutation strategies, the approach is applied to original DE algorithms, as well as DE algorithms with parameter adaptation. Experimental results indicate that the proposed adaptive greedy mutation strategies yield significant performance improvement for most of cases studied.

Cloud computing is a revolutionary computing paradigm which enables flexible, on-demand and low-cost usage of computing resources. Those advantages, ironically, are the causes of security and privacy problems, which emerge because the data owned by different users are stored in some cloud servers instead of under their own control. To deal with security problems, various schemes based on the Attribute-Based Encryption have been proposed recently. However, the privacy problem of cloud computing is yet to be solved. This paper presents an anonymous privilege control scheme AnonyControl to address not only the data privacy problem in a cloud storage, but also the user identity privacy issues in existing access control schemes. By using multiple authorities in cloud computing system, our proposed scheme achieves anonymous cloud data access and fine-grained privilege control. Our security proof and performance analysis shows that AnonyControl is both secure and efficient for cloud computing environment.

We present a 3D tracking system for detecting and tracking multiple targets. An extended Kalman Filter (EKF) is used to maintain each target's 3D state and provide location predictions to the pattern matchers whose task it is to follow the targets in images. An adaptive background modeling algorithm is used together with the tracking process to detect moving objects in complex environments. We propose a warping-based pattern matching approach to deal with object deformation during tracking. We present examples of results of our tracker for outdoor scenes.