检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Poe, Kyle Mallada, Enrique Vidal, René Applied Mathematics and Computational Science Group University of Pennsylvania PA19104 United States Department of Electrical and Computer Engineering Johns Hopkins University MD21218 United States Departments of Electrical and Systems Engineering Radiology Computer and Information Science Statistics and Data Science University of Pennsylvania PA19104 United States

One of the fundamental problems of interest for discrete-time linear systems is whether its input sequence may be recovered given its output sequence, a.k.a. the left inversion problem. Many conditions on the state space geometry, dynamics, and spectral structure of a system have been used to characterize the well-posedness of this problem, without assumptions on the inputs. However, certain structural assumptions, such as input sparsity, have been shown to translate to practical gains in the performance of inversion algorithms, surpassing classical guarantees. Establishing necessary and sufficient conditions for left invertibility of systems with sparse inputs is therefore a crucial step toward understanding the performance limits of system inversion under structured input assumptions. In this work, we provide the first necessary and sufficient characterizations of left invertibility for linear systems with sparse inputs, echoing classic characterizations for standard linear systems. The key insight in deriving these results is in establishing the existence of two novel geometric invariants unique to the sparse-input setting, the weakly unobservable and strongly reachable subspace arrangements. By means of a concrete example, we demonstrate the utility of these characterizations. We conclude by discussing extensions and applications of this framework to several related problems in sparse control. © 2024, CC BY.

关键词： Linear systems

来源：评论

学校读者我要写书评

暂无评论

Malware Identification Method Based on Image Analysis 11

Malware Identification Method Based on Image Analysis

引用

11th International Conference on Information Technology in Medicine and Education, ITME 2021

作者： Liu, Yanhua Li, Jiaqi Liu, Baoxu Gao, Xiaoling Liu, Ximeng Fuzhou University College of Computer and Data Science Fuzhou China Institute of Information Engineering Beijing China

ISBN: (纸本)9781665406796

In this paper, we propose a malware identification method employed by image analysis and generative adversarial networks, designed to solve the problems of increasingly sophisticated attack forms, insufficient sample data in malware. Specifically, we first generate fixed-size gray images of malware, which neither disassembly nor code execution is required for identification. Moreover, we introduce generative adversarial networks into malware identification for few samples scenarios and malware variants. Through the game training of generator and discriminator, the malware detection model is obtained from the discriminator and the samples are generated by the generator for data augment. Finally, we demonstrate that the proposed method is efficient and feasible using extensive experiments. © 2021 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Synergizing Vision and Language in Remote Sensing: A Multimodal Approach for Enhanced Disaster Classification in Emergency Response Systems

Synergizing Vision and Language in Remote Sensing: A Multimo...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Shubham Gupta Nandini Saini Suman Kundu Chiranjoy Chattopadhyay Debasis Das Computer Science & Engineering Indian Institute of Technology Jodhpur Rajasthan India School of Computing and Data Sciences FLAME University Pune Maharashtra India

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

As remote sensing capabilities continue to advance, there is a growing interest in leveraging computer vision and natural language processing for enhanced interpretation of remote sensing scenes. This paper explores the integration of textual information with images to augment traditional disaster classification methods. Our approach utilizes a predefined vision-language model to generate descriptive captions for images, fostering a more nuanced understanding of the remote sensing data. Next, we seamlessly integrate the generated textual information with image data through multimodal training, employing a multimodal deep learning method for disaster classification. The system categorizes input data into predefined disaster categories, presenting a comprehensive and accurate approach to emergency response system development. Experimental evaluations conducted on the AIDER dataset (Aerial Image database for Emergency Response applications) showcase the efficacy of our approach, demonstrating improved accuracy compare to unimodal approach and reliability in disaster classification. This research contributes to the advancement of intelligent emergency response systems by harnessing the synergy between vision and language in the context of remote sensing.

关键词： Training Accuracy Social networking (online) Image databases Disasters Emergency services Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Intersecting-boundary-sensitive fingerprinting for tampering detection of DNN models 24

Intersecting-boundary-sensitive fingerprinting for tampering...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Xiaofan Bai Chaoxiang He Xiaojing Ma Bin Benjamin Zhu Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Hubei Engineering Research Center on Big Data Security and Hubei Key Laboratory of Distributed System Security Microsoft School of Computer Science and Technology Huazhong University of Science and Technology and National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Cluster and Grid Computing Lab.

Cloud-based AI services offer numerous benefits but also introduce vulnerabilities, allowing for tampering with deployed DNN models, ranging from injecting malicious behaviors to reducing computing resources. Fingerprint samples are generated to query models to detect such tampering. In this paper, we present Intersecting-Boundary-Sensitive Fingerprinting (IBSF), a novel method for black-box integrity verification of DNN models using only top-1 labels. Recognizing that tampering with a model alters its decision boundary, IBSF crafts fingerprint samples from normal samples by maximizing the partial Shannon entropy of a selected subset of categories to position the fingerprint samples near decision boundaries where the categories in the subset intersect. These fingerprint samples are almost indistinguishable from their source samples. We theoretically establish and confirm experimentally that these fingerprint samples' expected sensitivity to tampering increases with the cardinality of the subset. Extensive evaluation demonstrates that IBSF surpasses existing state-of-the-art fingerprinting methods, particularly with larger subset cardinality, establishing its state-of-the-art performance in black-box tampering detection using only top-1 labels. The IBSF code is available at: https://***/CGCL-codes/IBSF.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prompt Learning on Temporal Interaction Graphs

arXiv

引用

arXiv 2024年

作者： Chen, Xi Zhang, Siwei Xiong, Yun Wu, Xixi Zhang, Jiawei Sun, Xiangguo Zhang, Yao Zhao, Feng Kang, Yulin Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China IFM Lab Department of Computer Science University of California DavisCA United States Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong Ant Group Shanghai Hangzhou China

Temporal Interaction Graphs (TIGs) are widely utilized to represent real-world systems, such as e-commerce and social networks. To facilitate representation learning on TIGs, researchers have proposed a series of TIG models. However, these models are still facing two tough gaps between the pre-training and downstream predictions in their "pre-train, predict" training paradigm. First, there is a temporal gap that exhibits limited accommodation ability to their timely predictions. This shortcoming severely undermines their applicability in distant future predictions on the dynamically evolving TIG data. Second, there is a semantic gap due to the lack of versatility in these pre-trained models to effectively cater to diverse downstream tasks. This hinders their practical applications, as they struggle to align with their learning and prediction capabilities across various application scenarios. Recently, the "pre-train, prompt" paradigm has emerged as a lightweight mechanism for model generalization. Therefore, applying this paradigm within TIGs is a potential solution to solve the aforementioned challenges. However, the adaptation of this paradigm to TIGs is not straightforward. The prevalent application of prompting in static graph contexts falls short in temporal settings due to a lack of consideration for time-sensitive dynamics and a deficiency in expressive power. To address this issue, we introduce Temporal Interaction Graph Prompting (TIGPrompt), a versatile framework that seamlessly integrates with existing TIG models, bridging both the temporal and semantic gaps mentioned above. In detail, we propose a temporal prompt generator to offer temporally-aware prompts for different tasks. These prompts stand out for their minimalistic design, relying solely on the fine-tuning of the prompt generator with very little supervision data, which is extremely efficient. To cater to varying computational resource demands, we propose an extended "pre-train, prompt-based fine

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Learning regularized graphon mean-field games with unknown graphons

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 18217-18311页

作者： Fengzhuo Zhang Vincent Y. F. Tan Zhaoran Wang Zhuoran Yang Department of Electrical and Computer Engineering National University of Singapore Singapore Department of Mathematics Department of Electrical and Computer Engineering National University of Singapore Singapore Department of Industrial Engineering and Management Sciences Northwestern University Evanston IL Department of Statistics and Data Science Yale University New Haven CT

We design and analyze reinforcement learning algorithms for Graphon Mean-Field Games (GMFGs). In contrast to previous works that require the precise values of the graphons, we aim to learn the Nash Equilibrium (NE) of the regularized GMFGs when the graphons are unknown. Our contributions are threefold. First, we propose the Proximal Policy Optimization for GMFG (GMFG-PPO) algorithm and show that it converges at a rate of Õ(T1-3) after T iterations with an estimation oracle, improving on a previous work by Xie et al. (ICML, 2021). Second, using kernel embedding of distributions, we design efficient algorithms to estimate the transition kernels, reward functions, and graphons from sampled agents. Convergence rates are then derived when the positions of the agents are either known or unknown. Results for the combination of the optimization algorithm GMFG-PPO and the estimation algorithm are then provided. These algorithms are the first specifically designed for learning graphons from sampled agents. Finally, the efficacy of the proposed algorithms are corroborated through simulations. These simulations demonstrate that learning the unknown graphons reduces the exploitability effectively.

关键词： Graphon mean-field games multi-agent reinforcement learning policy gradient model-based reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

StAGN: Spatial-Temporal Adaptive Graph Network via Contrastive Learning for Sleep Stage Classification

StAGN: Spatial-Temporal Adaptive Graph Network via Contrasti...

引用

2023 SIAM International Conference on data Mining, SDM 2023

作者： Chen, Junyang Dai, Yidan Chen, Xianhui Shen, Yingshan Luximon, Yan Wang, Hailiang He, Yuxin Ma, Wenjun Fan, Xiaomao College of Big Data and Internet Shenzhen Technology University Shenzhen China School of Computer Science South China Normal University Guangzhou China Department of Electrical and Computer Engineering New York University New York United States School of Design The Hong Kong Polytechnic University Hong Kong

ISBN: (纸本)9781611977653

Sleep stage classification is a critical concern in sleep quality assessment and disease diagnosis. Graph network based studies for sleep stages classification have achieved promising performance. However, these studies still ignored the importance of learning morphological feature information with the spatial-temporal relationship among multi-modal physiological signals. To address this issue, we propose a Spatial-temporal Adaptive Graph Network named StAGN for sleep stage classification. The main advantage of StAGN is to adaptively learn the time-dependent and channel-wise interdependent waveform morphological features in multimodal physiological signals. Such features will be extracted by a modified 1-dimensional ResNet with a projection shortcut connection and adjusted by a joint spatial-temporal attention, thereby best serving the followed brain topological connection graph network for sleep stage classification. Meanwhile, we leverage the contrastive learning scheme with label information to further improve classification accuracy without changing the signal morphology. Experiment results on two publicly available sleep datasets of ISRUC-S1 and ISRUC-S3 show that the proposed StAGN can achieve a competitive performance for sleep stage classification, which is superior to the state-of-the-art counterparts. Copyright © 2023 by SIAM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Galaxy: A Resource-Efficient Collaborative Edge AI System for In-situ Transformer Inference

Galaxy: A Resource-Efficient Collaborative Edge AI System fo...

引用

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

作者： Shengyuan Ye Jiangsu Du Liekang Zeng Wenzhong Ou Xiaowen Chu Yutong Lu Xu Chen School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China IoT Thrust and Research Center for Digital World With Intelligent Things HKUST (Guangzhou) Guangzhou China Data Science and Analytics Thrust HKUST (Guangzhou) Guangzhou China Department of Computer Science and Engineering HKUST Hong Kong SAR China

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

Transformer-based models have unlocked a plethora of powerful intelligent applications at the edge, such as voice assistant in smart home. Traditional deployment approaches offload the inference workloads to the remote cloud server, which would induce substantial pressure on the backbone network as well as raise users’ privacy concerns. To address that, in-situ inference has been recently recognized for edge intelligence, but it still confronts significant challenges stemming from the conflict between intensive workloads and limited on-device computing resources. In this paper, we leverage our observation that many edge environments usually comprise a rich set of accompanying trusted edge devices with idle resources and propose Galaxy, a collaborative edge AI system that breaks the resource walls across heterogeneous edge devices for efficient Transformer inference acceleration. Galaxy introduces a novel hybrid model parallelism to orchestrate collaborative inference, along with a heterogeneity-aware parallelism planning for fully exploiting the resource potential. Furthermore, Galaxy devises a tile-based fine-grained overlapping of communication and computation to mitigate the impact of tensor synchronizations on inference latency under bandwidth-constrained edge environments. Extensive evaluation based on prototype implementation demonstrates that Galaxy remarkably outperforms state-of-the-art approaches under various edge environment setups, achieving up to 2.5× end-to-end latency reduction.

关键词： Tensors Computational modeling Collaboration Prototypes Edge AI Smart homes Parallel processing

来源：评论

学校读者我要写书评

暂无评论

Sentimental Insight 2.0: Exploring the Frontiers of Opinion Mining with Deep Learning

Sentimental Insight 2.0: Exploring the Frontiers of Opinion ...

引用

Distributed Computing and Optimization Techniques (ICDCOT), International Conference on

作者： S.Karthick Murugan S. Jayachandran G. Mageshwari J. Latha Naveen G Department of Computer Science and Engineering R. M. D. Engineering College Kavaraipettai Thiruvallur Tamilnadu India Department of Computer Science and Application SRM Institute of Science and Technology Ramapuram Chennai India Department of Artificial Intelligence and Data Science R.M.K. College of Engineering and Technology Tiruvallur Tamilnadu India Department of Computer Science and Engineering R. M. K. Engineering College Kavaraipettai Tiruvallur Tamilnadu India Department of Electronics and Communication Engineering Madha Institute of Engineering and Technology Chennai Tamilnadu India

“Sentimental Insight 2.0” emerges as revolutionary research using deep learning techniques in response to the increasing demand for more complex sentiment analysis in the age of information abundance. Traditional sentiment analysis methods sometimes fail to accurately capture the particulars of emotions, sarcasm, and context, demanding a more advanced technique. The existing system's limitations include its inability to detect minor sentiment variations and its vulnerability to noisy and distorted data. The proposed system integrates cutting-edge deep learning architectures such as recurrent neural networks (RNNs), extended short-term memory networks (LSTMs), and transformer models into an extensive structure. The result showcases the advanced sentiment analysis, outperforming existing systems with 94% accuracy, 93% precision, 91% recall, and 93% F1 score, demonstrating superior computational efficiency and emotion classification across diverse sentiments. In the information-centric world, the study's results significantly expand sentiment analysis skills, providing a vital resource for applications in social media analytics, consumer feedback, and market sentiment prediction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring Deep Convolutional Neural Networks: A Grad-CAM Enhanced Comparative Study for Automated COVID-19 Diagnosis from Chest X-Ray Images

Exploring Deep Convolutional Neural Networks: A Grad-CAM Enh...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Md. Sazid Reza Mir Md. Jahangir Kabir Md. Abdur Rakib Mollah Nazmul Islam Nahin Department of Computer Science & Engineering Data Science and Innovation TD School University of Technology Sydney Sydney Australia Department of Electronics & Telecommunication Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh

The emergence of COVID-19 in late 2019 sparked a global health crisis. Identifying infections quickly is key to providing proper care and limiting transmission. The Reverse Transcription-Polymerase Chain Reaction (RT-PCR) test, a widely recognized primary diagnostic method for detecting COVID-19, faces challenges associated with cost and compatibility in resource-constrained environments. This issue is resolved by chest X-ray imaging since it is non-invasive and inexpensive. In this domain, research often utilizes pre-trained models on relatively small datasets of chest X-ray images, limiting the potential for optimal generalization and accuracy achievable with larger training sets. Also, these research works limit the exploration of crucial information on salient regions within CXR images, constraining the depth of analysis and interpretation. This study addresses current research challenges through a detailed comparative analysis of convolutional neural network (CNN) architectures, including pre-trained models like Inception V3, Xception, DenseNet-121, VGG-19, and a Custom CNN developed from scratch. The evaluation focuses on their effectiveness in detecting COVID-19 using a relatively vast and comprehensive dataset. The evaluation focuses on assessing the efficacy of these models in detecting COVID-19 across binary-class and multi-class classifications within a large dataset, offering valuable insights into their overall effectiveness. Grad-CAM is employed in this study, which visualizes picture salient areas affecting deep neural network predictions and improves model interpretability. The heatmaps reveal the model's decision-making processes, making their behavior more understandable to medical practitioners. With resulting accuracies of 99.13% and 97.66% in binary-class and multi-class classification, Inception V3 demonstrated the most optimal performance. This proposed approach surpasses existing benchmark methods, underscoring its superiority.

关键词：

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：