检索结果-内蒙古大学图书馆

Seeing through Dense Fog with an Intelligent Adaptive Dehazing System

学校读者我要写书评

暂无评论

IEEE Sensors Journal 2025年第10期25卷 17696-17705页

作者： Chen, Pengyun Cao, Ning Xu, Ziqin Cui, Shuang Jin, Shaohui Liu, Hao Xu, Mingliang Zhengzhou University School of Computer Science and Artificial Intelligence Zhengzhou450001 China National University of Defense Technology College of Advanced Interdisciplinary Studies Changsha410073 China Ministry of Education Engineering Research Center of Intelligent Swarm Systems Zhengzhou450001 China National Super-computing Center Zhengzhou450001 China

Most existing image dehazing methods are mainly suitable for synthetic datasets and often perform poorly in real-world, complex hazy scenarios. To address this issue, this paper proposes an intelligent adaptive dehazing system that integrates range-gated imaging with deep learning, combining image acquisition and restoration for enhanced dehazing performance. The range-gated imaging system reduces scattered light interference. However, our approach primarily focuses on enhancing image quality through advanced dehazing methods. Specifically, we introduce the MSCENAFormer dehazing network, which achieves high-quality reconstruction of target scenes in dense fog by effectively removing fog and improving visibility. The core modules of MSCENAFormer include the multi-scale enhanced neighborhood attention module (MSENA) and the comprehensive attention refinement module (CARM). MSENA is designed to capture rich local information in harsh environment, improving the dehazing effect and enhancing image details. CARM integrates the local and global information to optimize the visual effect further. In addition, the adaptive feature mixing module (AFM) is used to fuse multi-scale features for better performance. To validate the performance of our method, we utilize our lab-collected non-homogeneous haze real dataset, O-ITDF, along with the public datasets NH-HAZE, NTIRE2021 and NTIRE2023. Experimental results demonstrate that our proposed MSCENAFormer outperforms many methods. We share our code at https://***/NingCao-zzu/MSCENAFormer. © 2001-2012 IEEE.

关键词： Light interference

Energy-efficient and Privacy-preserving Edge Intelligence for 6G-Empowered Intelligent Transportation Systems

学校读者我要写书评

暂无评论

IEEE Network 2025年

作者： Zhu, Chenlu Fan, Xiaoxuan Deng, Xianjun Xiao, Ziheng Guo, Tingting Liu, Shenghao Sun, Jiaqi Park, Jong Hyuk Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Wuhan Kedao Geographic Information Engineering Co. Wuhan China Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul Korea Republic of

6G-empowered Intelligent Transportation Systems (ITS) generate large amounts of data through millions of devices and sensors at the terminal and network edge. Edge intelligence advances the frontier of data-driven artificial intelligence (AI) to the network edge, which enables AI applications to better utilize edge data. Broader connectivity, higher device density, and stronger data exchange present challenges for reliable device communication and privacy data protection in 6G-empowered ITS. To address these challenges, this paper proposes an energy-efficient and privacy-preserving edge intelligence framework named EP-EI. EP-EI deploys a deep reinforcement learning-based cluster head selection model at the edge to ensure energy-efficient communication for terminal devices. Meanwhile, EP-EI designs a privacy-aware hierarchical computing framework for terminal-edge-cloud to prevent privacy leakage. Furthermore, the application scenarios, challenges, and future directions of EP-EI are discussed. Finally, simulation experiments in a specific intelligent transportation case study demonstrate that EP-EI can provide energy-efficient and privacy-protecting services. © 2025 IEEE.

关键词： Differential privacy

KubeSPT: Stateful Pod Teleportation for Service Resilience with Live Migration

学校读者我要写书评

暂无评论

IEEE Transactions on Services Computing 2025年

作者： Zhang, Hansheng Wu, Song Fan, Hao Huang, Zhuo Xue, Weibin Yu, Chen Ibrahim, Shadi Jin, Hai Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong China

Container orchestration systems, such as Kubernetes, streamline containerized application deployment. As more and more applications are being deployed in Kubernetes, there is an increasing need for rescheduling - relocating a running pod to different nodes - due to system upgrades, node failures, and load-balancing optimizations. Live migration, which transfers services from source nodes to target nodes with minimal downtime, is the ideal support for rescheduling. However, implementing live migration for pods that run stateful services is challenging, because Kubernetes manages pods as stateless. First, the current pod's network namespace initialization process causes a mismatch in the network state between the migrated pod and internal containers. Second, migrating the memory state results in extended downtime. Third, Kubernetes operations on pods do not consider preserving the state of the pods. Therefore, we propose KubeSPT to achieve live migration of stateful pods in rescheduling scenarios. Firstly, we synchronize the network state of pods and internal containers by controlling packet flow and implement fast service redirection. Secondly, we introduce a Hot Data and Lazy-Restore method for memory restoration to reduce migration downtime. Finally, we decouple pod migration operations from other Kubernetes operations to ensure compatibility with live migration. Experimental results show that KubeSPT reduces downtime by 86%-93% compared to current rescheduling methods. © 2008-2012 IEEE.

关键词： Cloud Kubernetes Live Migration Pod

Hierarchical Recording Architecture for Three-Dimensional Magnetic Recording

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Jian, Yugen Luo, Ke Chen, Jincai Fong, Xuanyao Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology Wuhan430074 China Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore School of Computer of Science and Technology Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology Ministry of Education of China Wuhan430074 China

Three-dimensional magnetic recording (3DMR) is a highly promising approach to achieving ultra-large data storage capacity in hard disk drives. One of the greatest challenges for 3DMR lies in performing sequential and correct writing of bits into the multi-layer recording medium. In this work, we have proposed a hierarchical recording architecture based on layered heat-assisted writing with a multi-head array. The feasibility of the architecture is validated in a dual-layer 3DMR system with FePt-based thin films via micromagnetic simulation. Our results reveal the magnetization reversal mechanism of the grains, ultimately attaining appreciable switching probability and medium signal-to-noise ratio (SNR) for each layer. In particular, an optimal head-to-head distance is identified as the one that maximizes the medium SNR. Optimizing the system’s noise resistance will improve the overall SNR and allow for a smaller optimal head-to-head distance, which can pave the way for scaling 3DMR to more recording layers. Copyright © 2025, The Authors. All rights reserved.

关键词： Hard disk storage

Ion-Trap Chip Architecture Optimized for Implementation of Quantum Error-Correcting Code

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Lee, Jeonghoon Jeon, Hyeongjun Kim, Taehyun Department of Computer Science and Engineering Seoul National University Korea Republic of NextQuantum Seoul National University Korea Republic of Institute of Applied Physics Seoul National University Korea Republic of Inter-university Semiconductor Research Center Seoul National University Korea Republic of Institute of Computer Technology Seoul National University Korea Republic of Automation and System Research Institute Seoul National University Korea Republic of

We propose a new ion-trap architecture optimized for the efficient execution of both transversal and non-transversal gate operations in a two-dimensional color code. By differentiating the regions for transversal gates from those for non-transversal gates and syndrome extraction, which require distinct qubit connectivities, our chip layout minimizes ion shuttling and simplifies physical implementations. We also provide a dedicated transpiler and scheduler for this architecture, wherein the scheduler coordinates the sequence of operations and inserts the necessary swap and shuttling operations. Finally, we developed an error analyzer to evaluate the chip’s performance across a variety of quantum algorithms. Simulation results confirm that our architecture can significantly increase success rates and reduce gate error probabilities, particularly lowering the effective two-qubit gate error probability to about 10−8 when a quantum error-correcting code of 31 physical qubits is employed. Our findings clearly show that the improvement in success rates clearly outweighs the runtime overhead, demonstrating that strategic hardware-scheduler co-design can advance quantum systems towards reliable, large-scale computing, potentially surpassing classical capabilities. © 2025, CC BY.

关键词： Qubits

How to Select Pre-Trained Code Models for Reuse? A Learning Perspective

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Bi, Zhangqian Wan, Yao Chu, Zhaoyang Hu, Yufei Zhang, Junyi Zhang, Hongyu Xu, Guandong Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Big Data and Software Engineering Chongqing University Chongqing China School of Computer Science University of Technology Sydney Sydney Australia

Pre-training a language model and then fine-tuning it has shown to be an efficient and effective technique for a wide range of code intelligence tasks, such as code generation, code summarization, and vulnerability detection. However, pre-training language models on a large-scale code corpus is computationally expensive. Fortunately, many off-the-shelf Pre-trained Code Models (PCMs), such as CodeBERT, CodeT5, CodeGen, and Code Llama, have been released publicly. These models acquire general code understanding and generation capability during pre-training, which enhances their performance on downstream code intelligence tasks. With an increasing number of these public pre-trained models, selecting the most suitable one to reuse for a specific task is essential. In this paper, we systematically investigate the reusability of PCMs. We first explore three intuitive model selection methods that select by size, training data, or brute-force fine-tuning. Experimental results show that these straightforward techniques either perform poorly or suffer high costs. Motivated by these findings, we explore learning-based model selection strategies that utilize pre-trained models without altering their parameters. Specifically, we train proxy models to gauge the performance of pre-trained models, and measure the distribution deviation between a model's latent features and the task's labels, using their closeness as an indicator of model transferability. We conduct experiments on 100 widely-used open-source PCMs for code intelligence tasks, with sizes ranging from 42.5 million to 3 billion parameters. The results demonstrate that learning-based selection methods reduce selection time to 100 seconds, compared to 2,700 hours with brute-force fine-tuning, with less than 6% performance degradation across related tasks. © 2025, CC BY-NC-SA.

关键词： Adversarial machine learning

An interpretable convolutional neural network via generalized time–frequency scattering

学校读者我要写书评

暂无评论

Signal Processing 2025年 237卷

作者： Liu, Xiaoping Chen, Gong Shi, Jun Tao, Ran School of Information and Electronics Beijing Institute of Technology and the Beijing Key Laboratory of Fractional Signals and Systems Beijing100081 China Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore Communication Research Center Harbin Institute of Technology Harbin150001 China

Convolutional neural networks (CNNs) have recently demonstrated impressive performance in complex machine learning tasks. However, the CNN requires a large quantity of annotated data to converge to a good solution, and the theoretical understanding of this network is still in its infancy. Towards this end, a variant of the CNN, dubbed the deep scattering network (DSN), has been proposed by employing the linear time–frequency transform. The DSN inherits the hierarchical structure of the CNN, but chooses predefined wavelet/Gabor filters as its convolutional kernels instead of data-driven linear filters. Unfortunately, the DSN suffers from a major drawback that it is suitable for stationary image textures but not for non-stationary image textures, since wavelet/Gabor filters are intrinsically linear translation-invariant filters. The aim of this paper is to overcome this deficiency based upon a generalized linear time–frequency transform–the short-time fractional Fourier transform (STFRFT) which can be interpreted as a bank of linear translation-variant filters and thus may be well suitable for non-stationary texture analysis. We first introduce a generalized time–frequency scattering transform using the STFRFT. By applying the derived result, we propose an interpretable CNN by cascading the STFRFTs and modulus operators. Moreover, several basic properties of the proposed interpretable CNN are derived, and an efficient implementation of this network is also presented. Finally, the applications of the derived results are discussed. © 2025 Elsevier B.V.

关键词： Convolutional neural networks

Robust Self-Localization of Wireless Acoustic Sensor Networks

学校读者我要写书评

暂无评论

IEEE Internet of Things Journal 2025年

作者： Wang, Xu Hu, De Liu, Rui Bao, Feilong Inner Mongolia University College of Computer Science Hohhot010021 China National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot 010021 China Inner Mongolia Key Laboratory of Mongolian Information Processing Technology Hohhot 010021 China

Wireless acoustic sensor networks (WASNs), or the so-called internet of audio things (IoAuTs), have attracted increasing attention in the IoT community. As the geometry structure of WASNs is required in audio/speech processing tasks like source localization or acoustic beamforming, automatic self-localization of sensors is necessary. However, most of the existing approaches suffer from poor stability, as their constructed cost functions involve non-convex programming. To address this issue, we investigate the robust self-localization (or geometry calibration) of WASNs in this paper. Specifically, a rough self-localization (RSL) method is first presented based on measurements including time-difference-of-arrivals (TDoAs), direction-of-arrivals (DoA), and energy-rates (ERs), and its closed-form solution is further derived. As ER estimates are sensitive to acoustic environments, the performance of the RSL method is somewhat limited. Therefore, a precise self-localization (PSL) method is then developed by building a weighted (and non-convex) TDoA-DoA cost function, after regarding the RSL approach as an initialization step. As the RSL offers better initial values compared with existing initialization strategies, the combination of RSL and PSL methods (named as RSL-PSL method) shows stronger robustness and stability. In addition, computational complexity of both RSL and PSL methods are analyzed in details. Finally, the Cramér-Rao Bound (CRB) of the PSL method is derived to show its theoretical lower bound. The proposed RSL-PSL method outperforms the state-of-the-arts in terms of stability and accuracy, which is confirmed by numerical real-world and simulation experiments. © 2014 IEEE.

关键词： Cost functions

SatMamba: Development of Foundation Models for Remote Sensing Imagery Using State Space Models

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Duc, Chuc Man Fukui, Hiromichi Department of Computer Science Faculty of Information Technology University of Engineering and Technology Vietnam National University Hanoi Viet Nam International Digital Earth Applied Science Research Center Chubu University Aichi Kasugai487-8501 Japan

Foundation models refer to deep learning models pretrained on large unlabeled datasets through self-supervised algorithms. In the Earth science and remote sensing communities, there is growing interest in transforming the use of Earth observation data, including satellite and aerial imagery, through foundation models. Various foundation models have been developed for remote sensing, such as those for multispectral, high-resolution, and hyperspectral images, and have demonstrated superior performance on various downstream tasks compared to traditional supervised models. These models are evolving rapidly, with capabilities to handle multispectral, multitemporal, and multisensor data. Most studies use masked autoencoders in combination with Vision Transformers (ViTs) as the backbone for pretraining. While the models showed promising performance, ViTs face challenges, such as quadratic computational scaling with input length, which may limit performance on multiband and multitemporal data with long sequences. This research aims to address these challenges by proposing SatMamba, a new pretraining framework that combines masked autoencoders with State Space Model, offering linear computational scaling. Experiments on high-resolution imagery across various downstream tasks show promising results, paving the way for more efficient foundation models and unlocking the full potential of Earth observation data. The source code is available in https://***/mdchuc/HRSFM. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantic Segmentation