检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Shen, Chuyun Li, Wenhao Chen, Haoqing Wang, Xiaoling Zhu, Fengping Li, Yuxin Wang, Xiangfeng Jin, Bo School of Computer Science and Technology East China Normal University Shanghai200062 China School of Data Science The Chinese University of Hong Kong Shenzhen Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518172 China Huashan Hospital Fudan University Shanghai200040 China School of Computer Science and Technology East China Normal University Shanghai AI Laboratory Shanghai200062 China School of Software Engineering Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai200092 China

Radiologists must utilize medical images of multiple modalities for tumor segmentation and diagnosis due to the limitations of medical imaging technology and the diversity of tumor signals. This has led to the development of multimodal learning in medical image segmentation. However, the redundancy among modalities creates challenges for existing subtraction-based joint learning methods, such as misjudging the importance of modalities, ignoring specific modal information, and increasing cognitive load. These thorny issues ultimately decrease segmentation accuracy and increase the risk of overfitting. This paper presents the complementary information mutual learning (CIML) framework, which can mathematically model and address the negative impact of inter-modal redundant information. CIML adopts the idea of addition and removes inter-modal redundant information through inductive bias-driven task decomposition and message passing-based redundancy filtering. CIML first decomposes the multimodal segmentation task into multiple subtasks based on expert prior knowledge, minimizing the information dependence between modalities. Furthermore, CIML introduces a scheme in which each modality can extract information from other modalities additively through message passing. To achieve non-redundancy of extracted information, the redundant filtering is transformed into complementary information learning inspired by the variational information bottleneck. The complementary information learning procedure can be efficiently solved by variational inference and cross-modal spatial attention. Numerical results from the verification task and standard benchmarks indicate that CIML efficiently removes redundant information between modalities, outperforming SOTA methods regarding validation accuracy and segmentation effect. To emphasize, message-passing-based redundancy filtering allows neural network visualization techniques to visualize the knowledge relationship among different modalitie

关键词： Redundancy

来源：评论

学校读者我要写书评

暂无评论

CorcPUM: Efficient Processing Using Cross-Point Memory via Cooperative Row-Column Access Pipelining and Adaptive Timing Optimization in Subarrays

CorcPUM: Efficient Processing Using Cross-Point Memory via C...

引用

Design Automation Conference

作者： Chengning Wang Dan Feng Wei Tong Jingning Liu Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology Ministry of Education of China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Emerging cross-point memory can in-situ perform vector-matrix multiplication (VMM) for energy-efficient scientific computation. However, parasitic-capacitance-induced row charging and discharging latency is a major performance bottleneck of subarray VMM. We propose a memory-timing-compliant bulk VMM processing-using-memory design with row access and column access co-optimization from rethinking of read access commands and µ-op timing. We propose row-level-parallelism-adaptive timing termination mechanism to reduce tail latency of tRCD and tRP by exploiting row nonlinear charging and bulk-interleaved row-column-cooperative VMM access mechanism to reduce tRAS and overlap CL without increasing column ADC precision. Evaluations show that our design can achieve 5.03× performance speedup compared with an aggressive baseline.

关键词：

来源：评论

学校读者我要写书评

暂无评论

data Poisoning Attack to X-armed Bandits

Data Poisoning Attack to X-armed Bandits

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Zhi Luo Youqi Li Lixing Chen Zichuan Xu Pan Zhou School of Cyber Science and Engineering Huazhong University of Science and Technology School of Cyberspace Science and Technology and School of Computer Science Beijing Institute of Technology Institute of Cyber Science and Technology Shanghai Jiao Tong University School of Software Dalian University of Technology Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology

X-armed bandits have achieved the state-of-the-art performance in optimizing unknown stochastic continuous functions, which can model many machine learning tasks, specially in big data-driven personalized recommendation. However, bandit algorithms are vulnerable to adversarial attacks. Existing works mainly focus on attacking multi-armed bandits in discrete setting; nevertheless, the attacks against X-armed bandits in continuous setting have not been well explored. In this paper, we aim to bridge this gap and investigate the robustness problem for the X-armed bandits. Specifically, we consider data poisoning attack and propose an attack algorithm named Confidence Poisoning Attack algorithm, which could hijack the clean tree-based X-armed bandits algorithm, i.e., high confidence tree (HCT) and make it choose the nodes including the arm targeted by the attacker very frequently with a sub-linear attack cost, i.e., O(T α )(0

关键词： Threat modeling Privacy Costs Machine learning algorithms Stochastic processes Machine learning Robustness

来源：评论

学校读者我要写书评

暂无评论

Workload Prediction of Serverless Computing 21

Workload Prediction of Serverless Computing

引用

5th International Conference on Deep Learning Technologies, ICDLT 2021

作者： Wei, Jinyue Gao, Ming School of Data Science and Artificial Intelligence Dongbei University of Finance and Economics Liaoning Dalian China School of Management Science and Engineering Dongbei University of Finance and Economics Liaoning Dalian China Center for Post-doctoral Studies of Computer Science Northeastern University Liaoning Shenyang China

ISBN: (纸本)9781450390163

As enterprises continue to move to the cloud, Reasonable resource scheduling is of great significance to cloud service management. Accurate prediction and reasonable explanation provide important guarantee for resource scheduling management. However, there is no excellent data set to support workload prediction of cloud computing, which has hysteresis. Moreover, due to the lack of interpretation of the model for managers, complex models still have serious limitations, which limit the application of managers in practice. The paper starts from the actual application of Serverless, makes use of the time series data set provided by Huawei Cloud and makes the workload prediction of Serverless based on the business scenario of renting the server. First of all, the optimal feature engineering construction method is mined to increase the prediction ac-curacy. Secondly, the results of different prediction models and the complexity of prediction are compared to explore the comparative advantages between different methods. Finally, through multiple groups of comparative experiments to explore the optimal use of LightGBM in this example, using SHAP method to explain the model black box, to provide a reference for the management and operation of Serverless. © 2021 ACM.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Constructing MDS Array Codes with Small Repair Bandwidth under Sub-packetization Two

Constructing MDS Array Codes with Small Repair Bandwidth und...

引用

International Conference on Wireless Communications and Signal Processing (WCSP)

作者： Lei Li Chenhao Ying Xinchun Yu Liang Chen Yuanyuan Dong Yuan Luo Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Institute of Data and Informtion Shenzhen International Graduate School of Tsinghua University Shenzhen China Alibaba Group Hangzhou China

Erasure Codes are widely implemented in distributed storage systems to achieve fault tolerance with high storage efficiency. Reed-Solomon code is commonly deployed in data centers due to its optimal storage efficiency, but it requires massive repair bandwidth for node repair. Minimum Storage Regenerating (MSR) code and Locally Repairable (LR) code are proposed to reduce repair bandwidth. However, MSR code usually carries a heavy disk I/O burden and LR code is not optimal in storage efficiency. In this paper, we take disk I/O, storage efficiency, repair bandwidth, sub-packetization level, and repair degree (number of helper nodes) into consideration together, and propose explicit construction of MDS array code (named LDIO code) with low disk I/O and reduced repair bandwidth, where the sub-packetization level is 2. Besides the low disk I/O consumption, LDIO code also achieves a small repair bandwidth of ${\bar \gamma _{sys}} = \frac{1}{2} + \frac{1}{{4(r - 1)}}$ for systematic nodes with repair degree d = k+1. Normally, LDIO code can provide bandwidth savings of 25% to 50% for the repair of systematic nodes compared with RS code, and almost savings of 6% compared with piggybacking code. For an LDIO code of length n and redundancy r, the size of the finite field needed is Θ(n r+1 ).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Global Exponential Rendezvous Control of Nonholonomic Unicycle Vehicles with Directed Communication Topology

Global Exponential Rendezvous Control of Nonholonomic Unicyc...

引用

Chinese Intelligent Systems Conference, CISC 2020

作者： Zhao, Yixin Xing, Bin Huang, Wei Luo, Shiyu Li, Peng Xie, Wenjing The School of Computer and Information Science Southwest University Chongqing400715 China Chongqing Innovation Center of Industrial Big-Data Co. Ltd. National Engineering Laboratory for Industrial Big-Data Application Technology Chongqing400065 China

ISBN: (纸本)9789811584572

This paper studies the full-state rendezvous control problem of multiple nonholonomic unicycle systems. A distributed state feedback time-varying control law is derived by exploiting model transformation, input-output feedback linearization technology, linear cooperation control theory and graph theory. Based on the carefully constructed output-like variable, the input-output feedback linearization approach overcomes the underactuated control challenge, makes the choice of controller parameters independent of initial states of vehicles, and allows the linear control theory applicable, rather than using the Lyapunov method and hence requiring the information flow undirected. Stability analysis proves that all the unicycle vehicles globally exponentially converge to a common fixed location and orientation, provided that the communication topology is directed and having a spanning tree. A numerical simulation is implemented for five nonholonomic unicycle vehicles, demonstrating the effectiveness of the proposed control scheme. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Global Learnable Attention for Single Image Super-Resolution

arXiv

引用

arXiv 2022年

作者： Su, Jian-Nan Gan, Min Chen, Guang-Yong Yin, Jia-Li Chen, C.L. Philip The College of Computer and Data Science Fuzhou University Fuzhou350108 China The School of Computer Science and Engineering South China University of Technology Guangzhou510641 China The Faculty of Science and Technology University of Macau Macau China

Self-similarity is valuable to the exploration of non-local textures in single image super-resolution (SISR). Researchers usually assume that the importance of non-local textures is positively related to their similarity scores. In this paper, we surprisingly found that when repairing severely damaged query textures, some non-local textures with low-similarity which are closer to the target can provide more accurate and richer details than the high-similarity ones. In these cases, low-similarity does not mean inferior but is usually caused by different scales or orientations. Utilizing this finding, we proposed a Global Learnable Attention (GLA) to adaptively modify similarity scores of non-local textures during training instead of only using a fixed similarity scoring function such as the dot product. The proposed GLA can explore non-local textures with low-similarity but more accurate details to repair severely damaged textures. Furthermore, we propose to adopt Super-Bit Locality-Sensitive Hashing (SB-LSH) as a preprocessing method for our GLA. With the SB-LSH, the computational complexity of our GLA is reduced from quadratic to asymptotic linear with respect to the image size. In addition, the proposed GLA can be integrated into existing deep SISR models as an efficient general building block. Based on the GLA, we constructed a Deep Learnable Similarity Network (DLSN), which achieves state-of-the-art performance for SISR tasks of different degradation types (e.g. blur and noise). Our code and a pre-trained DLSN have been uploaded to GitHub† for validation. Copyright © 2022, The Authors. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

A Provable Splitting Approach for Symmetric Nonnegative Matrix Factorization

arXiv

引用

arXiv 2023年

作者： Li, Xiao Zhu, Zhihui Li, Qiuwei Liu, Kai School of Data Science The Chinese University of Hong Kong Shenzhen China China The Department of Electrical and Computer Engineering The University of Denver United States The Decision Intelligence Lab Damo Academy Alibaba Group US United States Computer Science Division Clemson University United States

The symmetric Nonnegative Matrix Factorization (NMF), a special but important class of the general NMF, has found numerous applications in data analysis such as various clustering tasks. Unfortunately, designing fast algorithms for the symmetric NMF is not as easy as for its nonsymmetric counterpart, since the latter admits the splitting property that allows state-of-the-art alternating-type algorithms. To overcome this issue, we first split the decision variable and transform the symmetric NMF to a penalized nonsymmetric one, paving the way for designing efficient alternating-type algorithms. We then show that solving the penalized nonsymmetric reformulation returns a solution to the original symmetric NMF. Moreover, we design a family of alternating-type algorithms and show that they all admit strong convergence guarantee: the generated sequence of iterates is convergent and converges at least sublinearly to a critical point of the original symmetric NMF. Finally, we conduct experiments on both synthetic data and real image clustering to support our theoretical results and demonstrate the performance of the alternating-type algorithms. © 2023, CC BY.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Analyzing drop coalescence in microfluidic device with a deep learning generative model

arXiv

引用

arXiv 2023年

作者： Zhu, Kewei Cheng, Sibo Kovalchuk, Nina Simmons, Mark Guo, Yi-Ke Matar, Omar K. Arcucci, Rossella Department of Computer Science University of York United Kingdom Data Science Institute Department of Computing Imperial College London United Kingdom School of Chemical Engineering University of Birmingham United Kingdom Department of Chemical Engineering Imperial College London United Kingdom Department of Earth Science & Engineering Imperial College London United Kingdom

Predicting drop coalescence based on process parameters is crucial for experiment design in chemical engineering. However, predictive models can suffer from the lack of training data and more importantly, the label imbalance problem. In this study, we propose the use of deep learning generative models to tackle this bottleneck by training the predictive models using generated synthetic data. A novel generative model, named double space conditional variational autoencoder (DSCVAE) is developed for labelled tabular data. By introducing label constraints in both the latent and the original space, DSCVAE is capable of generating consistent and realistic samples compared to standard conditional variational autoencoder (CVAE). Two predictive models, namely random forest and gradient boosting classifiers, are enhanced on synthetic data and their performances are evaluated on real experimental data. Numerical results show that considerable improvement in prediction accuracy can be achieved by using synthetic data and the proposed DSCVAE clearly outperforms the standard CVAE. This research clearly brings more insight into handling imbalanced data for classification problems, especially in chemical engineering. © 2023, CC BY-NC-SA.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Edge Intelligence Hybrid Framework for Real-Time IoT Applications Using Multi-Stage Adaptive Processing Methods

Edge Intelligence Hybrid Framework for Real-Time IoT Applica...

引用

Mobile Computing and Sustainable Informatics (ICMCSI), International Conference on

作者： Sajja Suneel Rakesh Kumar Yadav K.Nirmala Devi B.Teja Sree Aarthi R Shrikant Upadhyay Department of CSE(Data Science) Institute of Aeronautical Engineering Hyderabad Telangana India Amity School of Engineering and Technology Amity University Patna Bihar Department of Computer Applications Madanapalle Institute of Technology & Science Department of IT S.R.K.R Engineering College Bhimavaram Department of ECE Rajalakshmi Institute of Technology Chembarambakkam Tamil Nadu Department of Electronics and Communication Engineering MLR Institute of Technology Hyderabad India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

The rapid proliferation of IoT devices has created an unprecedented need for real-time data processing and decision-making. This paper proposes an Edge Intelligence Hybrid Framework designed for real-time IoT applications using multi-stage adaptive processing methods. The framework structured into three layers: edge-level processing, fog-level aggregation, and cloud-level computation, enabling efficient distribution of tasks across the hierarchy. At the edge, lightweight models and preprocessing techniques, such as Kalman Filtering and Huffman Coding, ensure low-latency and energy-efficient operation. Intermediate computations and model synchronization occur at the fog level, while high-complexity tasks like deep learning model training performed at the cloud level. Results demonstrate that edge-level processing achieves an accuracy of 85.4 %, while fog and cloud levels improve accuracy to 89.4% and 94.9%, respectively. Latency at the edge is as low as 9-13ms, compared to fog (23-29ms) and cloud (117-125ms), ensuring suitability for time-critical IoT tasks. The proposed framework effectively balances latency, accuracy, and resource optimization, making it ideal for applications such as predictive maintenance, healthcare, and smart surveillance.

关键词： Performance evaluation Adaptation models Accuracy Computational modeling Decision making Medical services Real-time systems Internet of Things Time factors Low latency communication

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：