检索结果-内蒙古大学图书馆

LOPO: An Out-of-order Layer Pulling Orchestration Strategy for Fast Microservice Startup

学校读者我要写书评

暂无评论

LOPO: An Out-of-order Layer Pulling Orchestration Strategy f...

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Lin Gu Junhao Huang Shaoxing Huang Deze Zeng Bo Li Hai Jin 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 University of Science and Technology Wuhan China School of Computer Science China University of Geosciences Wuhan China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

Container based microservices have been widely applied to promote the cloud elasticity. The mainstream Docker containers are structured in layers, which are organized in stack with bottom-up dependency. To start a microservice, the required layers are pulled from a remote registry and stored on its host server, following the layer dependency order. This incurs long microservice startup time and hinders the performance efficiency. In this paper, we discover that, for the first time, the layer pulling order can be adjusted to accelerate the microservice startup. Specifically, we address the problem on microservice layer pulling orchestration for startup time minimization and prove it as NP-hard. We propose a Longest-chain based Out-of-order layer Pulling Orchestration (LOPO) strategy with low computational complexity and guaranteed approximation ratio. Through extensive real-world trace driven experiments, we verify the efficiency of our LOPO and demonstrate that it reduces the microservice startup time by 22.71% on average in comparison with state-of-the-art solutions.

关键词：

ViLa-MIL: Dual-scale Vision-Language Multiple Instance Learning for Whole Slide Image Classification

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Shi, Jiangbo Li, Chen Gong, Tieliang Zheng, Yefeng Fu, Huazhu School of Computer Science and Technology Xi’an Jiaotong University Xi’an China Jarvis Research Center Tencent YouTu Lab Shenzhen China Institute of High Performance Computing Agency for Science Technology and Research Singapore

Multiple instance learning (MIL)-based framework has become the mainstream for processing the whole slide image (WSI) with giga-pixel size and hierarchical image context in digital pathology. However, these methods heavily depend on a substantial number of bag-level labels and solely learn from the original slides, which are easily affected by variations in data distribution. Recently, vision language model (VLM)-based methods introduced the language prior by pre-training on large-scale pathological image-text pairs. However, the previous text prompt lacks the consideration of pathological prior knowledge, therefore does not substantially boost the model’s performance. Moreover, the collection of such pairs and the pre-training process are very time-consuming and source-intensive. To solve the above problems, we propose a dual-scale vision-language multiple instance learning (ViLa-MIL) framework for whole slide image classification. Specifically, we propose a dual-scale visual descriptive text prompt based on the frozen large language model (LLM) to boost the performance of VLM effectively. To transfer the VLM to process WSI efficiently, for the image branch, we propose a prototype-guided patch decoder to aggregate the patch features progressively by grouping similar patches into the same prototype;for the text branch, we introduce a context-guided text decoder to enhance the text features by incorporating the multi-granular image contexts. Extensive studies on three multi-cancer and multi-center subtyping datasets demonstrate the superiority of ViLa-MIL. Copyright © 2025, The Authors. All rights reserved.

关键词： Visual languages

ASGEA: Exploiting Logic Rules from Align-Subgraphs for Entity Alignment

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Luo, Yangyifei Chen, Zhuo Guo, Lingbing Li, Qian Zeng, Wenxuan Cai, Zhixin Li, Jianxin School of Computer Science and Engineering Beihang University China College of Computer Science and Technology Zhejiang University China Bejing Advanced Innovation Center for Big Data and Brain Computing Beihang University China

Entity alignment (EA) aims to identify entities across different knowledge graphs that represent the same real-world objects. Recent embedding-based EA methods have achieved state-of-the-art performance in EA yet faced interpretability challenges as they purely rely on the embedding distance and neglect the logic rules behind a pair of aligned entities. In this paper, we propose the Align-Subgraph Entity Alignment (ASGEA) framework to exploit logic rules from Align-Subgraphs. ASGEA uses anchor links as bridges to construct Align-Subgraphs and spreads along the paths across KGs, which distinguishes it from the embedding-based methods. Furthermore, we design an interpretable Path-based Graph Neural Network, ASGNN, to effectively identify and integrate the logic rules across KGs. We also introduce a node-level multi-modal attention mechanism coupled with multi-modal enriched anchors to augment the Align-Subgraph. Our experimental results demonstrate the superior performance of ASGEA over the existing embedding-based methods in both EA and Multi-Modal EA (MMEA) tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： computer circuits

3D visualization and detection of glomeruli in whole mouse kidney 16

学校读者我要写书评

暂无评论

3D visualization and detection of glomeruli in whole mouse k...

16th International Conference on Photonics and Imaging in Biology and Medicine, PIBM 2023

作者： Li, Yuxin Cao, Jia Li, Anan Li, Xiangning Feng, Zhao Shaanxi Key Laboratory for Network Computing and Security Technology School of Computer Science and Engineering Xi an University of Technology Xi an710048 China Britton Chance Center for Biomedical Photonics Wuhan National Laboratory for Optoelectronics MoE Key Laboratory for Biomedical Photonics Huazhong University of Science and Technology Wuhan430074 China HUST-Suzhou Institute for Brainsmatics Suzhou215123 China

ISBN: (纸本)9781510667341

The kidney is an important organ in the body to excrete metabolic waste, and the glomerulus is an essential structure for the kidney to play a role in blood filtration. Abnormal glomerular numbers are associated with nephropathy or circulatory disease. With the development of imaging technology, mesoscopic optical imaging can obtain whole kidney images at single cell resolution. The detection of glomeruli from images is very crucial for understanding the renal function and studying nephropathy. Existing detection methods cannot balance both accuracy and efficiency, so we proposed a deep learning-based glomeruli detection method. First, we imaged an entire mouse kidney with High-Definition fluorescent Micro-Optical Sectioning Tomography (HD-fMOST) and obtained a three-dimensional (3D) kidney image at cellular resolution. Then, we designed an end-To-end 3D convolutional neural network based on the morphological features of glomeruli in the kidney image, which can directly read 3D images and predict the precise coordinates of glomeruli. We used the acquired kidney dataset to train the network and validated the effect of glomeruli detection. Finally, we applied our approach to detect glomeruli in large-scale mouse kidney. The results showed that the proposed method reached the state-of-The-Art level, which is more efficient and accurate compared to similar methods. The proposed method will provide a powerful tool for kidney-related research. © 2023 SPIE.

关键词： Convolutional neural networks

Joint Waveform and Beamforming Design in RIS-ISAC Systems: A Model-Driven Learning Approach

学校读者我要写书评

暂无评论

IEEE Transactions on Communications 2025年

作者： Jiang, Peng Li, Ming Liu, Rang Wang, Wei Liu, Qian Dalian University of Technology School of Information and Communication Engineering Dalian116024 China University of California Center for Pervasive Communications and Computing IrvineCA United States Dalian University of Technology School of Computer Science and Technology Dalian116024 China

Integrated Sensing and Communication (ISAC) has emerged as a key enabler for future wireless systems. The recently developed symbol-level precoding (SLP) technique holds significant potential for ISAC waveform design, as it leverages both temporal and spatial degrees of freedom (DoFs) to enhance multi-user communication and radar sensing capabilities. Concurrently, reconfigurable intelligent surfaces (RIS) offer additional controllable propagation paths, further amplifying interest in their application. However, previous studies have encountered substantial computational challenges due to the complexity of jointly designing SLP-based waveforms and RIS passive beamforming. In this paper, we propose a novel model-driven learning approach that jointly optimizes waveform and beamforming by unfolding the iterative alternative direction method of multipliers (ADMM) algorithm. Two joint design algorithms are developed for radar target detection and direction-of-arrival (DoA) estimation tasks in a cluttered RIS-ISAC system. While ensuring the communication quality-of-service (QoS) requirements, our objectives are: 1) to maximize the radar output signal-to-interference-plus-noise ratio (SINR) for target detection, and 2) to minimize the Cramér-Rao bound (CRB) for DoA estimation. Simulation results verify that our proposed model-driven learning algorithms achieve satisfactory communication and sensing performance, while also offering a substantial reduction in computational complexity, as reflected by the average execution time. © 1972-2012 IEEE.

关键词： Cramer-Rao bounds

WildOcc: A Benchmark for Off-Road 3D Semantic Occupancy Prediction

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhai, Heng Mei, Jilin Min, Chen Chen, Liang Zhao, Fangzhou Hu, Yu Research Center for Intelligent Computing Systems Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China School of Information Science and Technology ShanghaiTech University Shanghai201210 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100190 China

3D semantic occupancy prediction is an essential part of autonomous driving, focusing on capturing the geometric details of scenes. Off-road environments are rich in geometric information, therefore it is suitable for 3D semantic occupancy prediction tasks to reconstruct such scenes. However, most of researches concentrate on on-road environments, and few methods are designed for off-road 3D semantic occupancy prediction due to the lack of relevant datasets and benchmarks. In response to this gap, we introduce WildOcc, to our knowledge, the first benchmark to provide dense occupancy annotations for off-road 3D semantic occupancy prediction tasks. A ground truth generation pipeline is proposed in this paper, which employs a coarse-to-fine reconstruction to achieve a more realistic result. Moreover, we introduce a multi-modal 3D semantic occupancy prediction framework, which fuses spatio-temporal information from multi-frame images and point clouds at voxel level. In addition, a cross-modality distillation function is introduced, which transfers geometric knowledge from point clouds to image features. Dataset will be released at https://***/LedKashmir/WildOcc Copyright © 2024, The Authors. All rights reserved.

关键词： Off road vehicles

SLP-Based Dual-Functional Waveform Design for ISAC Systems: A Deep Learning Approach

学校读者我要写书评

暂无评论

IEEE Transactions on Vehicular technology 2025年

Integrated Sensing and Communication (ISAC) is emerging as a critical enabling technology for 6G communication systems, with increasing attention on dual-functional waveform design to facilitate various applications. Recently developed symbol-level precoding (SLP) demonstrates significant potential for ISAC waveform design due to its superior capacity to enhance both communication and radar sensing capabilities by simultaneously leveraging temporal and spatial degrees of freedom (DoFs). To address the high complexity challenges associated with SLP designs, this paper proposes two efficient deep learning algorithms to tackle the complex SLP-based ISAC waveform design problem. The first algorithm employs a supervised data-driven training strategy that reformulates the original problem as a solvable linear regression issue, while the second algorithm utilizes a gradient-based procedure to fine-tune the trained network, enhancing communication and radar sensing performance. Additionally, we introduce a lightweight SLP-Inception-Net to mitigate computational complexity at the network structural level, incorporating a phase-based activation function to ensure the satisfaction of equality constraints. Extensive simulation results demonstrate that our proposed deep learning algorithms achieve comparable communication and sensing performance to optimization-based approaches, while delivering a remarkable 1000-fold reduction in computational complexity in terms of average execution time. Furthermore, they outperform classical learning-based schemes at the same level of floating point operations per second (FLOPs). © 1967-2012 IEEE.

关键词： Deep learning

Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Yichen Chou, Yuxuan Zhou, Ziqi Zhang, Hangtao Wan, Wei Hu, Shengshan Li, Minghui National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of School of Software Engineering Huazhong University of Science and Technology China

As deep neural networks (DNNs) are widely applied in the physical world, many researches are focusing on physical-world adversarial examples (PAEs), which introduce perturbations to inputs and cause the model’s incorrect outputs. However, existing PAEs face two challenges: unsatisfactory attack performance (i.e., poor transferability and insufficient robustness to environment conditions), and difficulty in balancing attack effectiveness with stealthiness, where better attack effectiveness often makes PAEs more perceptible. In this paper, we explore a novel perturbation-based method to overcome the challenges. For the first challenge, we introduce a strategy Deceptive RF injection based on robust features (RFs) that are predictive, robust to perturbations, and consistent across different models. Specifically, it improves the transferability and robustness of PAEs by covering RFs of other classes onto the predictive features in clean images. For the second challenge, we introduce another strategy Adversarial Semantic Pattern Minimization, which removes most perturbations and retains only essential adversarial patterns in AEs. Based on the two strategies, we design our method Robust Feature Coverage Attack (RFCoA), comprising Robust Feature Disentanglement and Adversarial Feature Fusion. In the first stage, we extract target class RFs in feature space. In the second stage, we use attention-based feature fusion to overlay these RFs onto predictive features of clean images and remove unnecessary perturbations. Experiments show our method’s superior transferability, robustness, and stealthiness compared to existing state-of-the-art methods. Additionally, our method’s effectiveness can extend to Large Vision-Language Models (LVLMs), indicating its potential applicability to more complex tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

Assessing the Efficacy of Improved Learning in Hourly Global Irradiance Prediction

学校读者我要写书评

暂无评论

computers, Materials & Continua 2023年第11期77卷 2579-2594页

作者： Abdennasser Dahmani Yamina Ammi Nadjem Bailek Alban Kuriqi Nadhir Al-Ansari Salah Hanini Ilhami Colak Laith Abualigah El-Sayed M.El-kenawy Department of Mechanical Engineering Faculty of Science and TechnologyGIDD Industrial Engineering and Sustainable Development LaboratoryUniversity of RelizaneBourmadiaRelizane48000Algeria Laboratory of Biomaterials and Transport Phenomena(LBMPT) University of MedeaUrban PoleMedea26000Algeria Energies and Materials Research Laboratory Faculty of Sciences and TechnologyUniversity of TamanghassetTamanrasset10034Algeria Sustainable Development and Computer Science Laboratory Faculty of Sciences and TechnologyAhmed Draia University of AdrarAdrarAlgeria CERIS Instituto Superior TécnicoUniversidade de LisboaLisbon1049-001Portugal Civil Engineering Department University for Business and TechnologyPristina10000Kosovo Department of Civil Environmental and Natural Resources EngineeringLulea University of TechnologyLulea97187Sweden Engineering and Architecture Faculty Nisantasi UniversityIstanbulTurkey Computer Science Department Prince Hussein Bin Abdullah Faculty for Information TechnologyAl al-Bayt UniversityMafraq25113Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman UniversityAmman19328Jordan MEU Research Unit Middle East UniversityAmman11831Jordan Applied Science Research Center Applied Science Private UniversityAmman11931Jordan School of Computer Sciences Universiti Sains MalaysiaPulau Pinang11800Malaysia Department of Computing and Information Systems School of Engineering and TechnologySunway University MalaysiaPetaling Jaya27500Malaysia Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt

Increasing global energy consumption has become an urgent problem as natural energy sources such as oil,gas,and uranium are rapidly running *** into renewable energy sources such as solar energy is being pursued to counter *** energy is one of the most promising renewable energy sources,as it has the potential to meet the world’s energy needs *** study aims to develop and evaluate artificial intelligence(AI)models for predicting hourly global *** hyperparameters were optimized using the Broyden-FletcherGoldfarb-Shanno(BFGS)quasi-Newton training algorithm and STATISTICA *** from two stations in Algeria with different climatic zones were used to develop the *** error measurements were used to determine the accuracy of the prediction models,including the correlation coefficient,the mean absolute error,and the root mean square error(RMSE).The optimal support vector machine(SVM)model showed exceptional efficiency during the training phase,with a high correlation coefficient(R=0.99)and a low mean absolute error(MAE=26.5741 Wh/m^(2)),as well as an RMSE of 38.7045 Wh/m^(2) across all ***,this study highlights the importance of accurate prediction models in the renewable energy,which can contribute to better energy management and planning.

关键词： Renewable energy energy prediction global irradiation artificial intelligence BFGS quasi-Newton training algorithm