检索结果-内蒙古大学图书馆

TechRxiv 2022年

作者： Chu, Xiaowen He, Xin Dept. Computer Science Hong Kong Baptist University Hong Kong Data Science and Analytics Thrust The Hong Kong University of Science and Technology Guangzhou China Guangzhou China

data augmentation plays a crucial role in deep learning-based medical imaging analysis, but manually designing tailored data augmentation strategies for each dataset is impractical. Although automatic data augmentation (ADA) techniques have been explored, they often focus solely on data augmentation without considering the importance of neural architecture. Similarly, neural architecture search (NAS) methods mainly concentrate on optimizing the neural architecture while overlooking the impact of data augmentation. However, both data augmentation and neural architecture are interrelated and should be considered together. The joint optimization of data augmentation and neural architecture can lead to improved model performance by harnessing the complementary effects of customized data augmentation strategies and compatible neural architectures. Despite this, the seamless integration of data augmentation and neural architecture search remains under-explored. To address this research gap, we propose MedPipe, an approach that enables end-to-end joint search of data augmentation and neural architecture. We introduce a compact data augmentation search space and unify data augmentation and neural architecture into a cohesive network. This allows simultaneous exploration, optimizing their synergy for enhanced performance. Experimental evaluation on nine medical datasets highlights the necessity of the joint search for data augmentation and neural architecture, demonstrating the superior performance of our approach. Our work opens up possibilities for future applications in diverse medical domains. © 2022, CC BY-NC-SA.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Chameleon: An Adaptive System for Overlapping Keystroke Signal Separation and Identification

Chameleon: An Adaptive System for Overlapping Keystroke Sign...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Jiayi Zhao Yongzhi Huang Qipeng Xie Weizheng Wang Lu Wang Kaishun Wu Internet of Things (IoT)/ Hong Kong University of Science and Technology(Guangzhou) Guangzhou China Data Science and Analytics (DSA) Thrust Information Hub Hong Kong University of Science and Technology(Guangzhou) Guangzhou China Hong Kong University of Science and Technology Hong Kong China Computer Science Engineer City University of Hong Kong Hong Kong China Shenzhen University China

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

Keystroke dynamics has proven to be highly effective, with its applications expanding significantly over the years in areas such as preventing transaction fraud, account takeovers, and identity theft. Key-positioning and feature-learning methods are commonly used to identify keystroke signals. However, the existing methods face challenges in detecting overlapping keystrokes and environmentally changed signals. We propose a solution called Chameleon to address these limitations. Unlike previous signal separation and deep learning methods that are ineffective in keystroke signals and computationally demanding, Chameleon employs a low-computation Ranking Model to separate overlapping keystroke signals. Moreover, our experiments demonstrate that Chameleon separated signals can be recognized with an average accuracy of 92.69%, surpassing the commonly used FastICA method, which only reaches 25% accuracy. To account for environmental changes, we utilize the Fréchet Inception Distance (FID) as a guiding metric for model migration. Additionally, we introduce the Inductive Vector, which enables our key-identifying model to adapt to altered environmental conditions such as environment, phone location, and user variety. The Inductive Vector adjusts the model parameters based on the shift in FID. In scenarios with various phone locations, the Inductive Vector significantly improves recognition accuracy from 61% to 98%, outperforming the best existing keystroke recognition algorithm. In other dynamic environmental conditions, our approach achieves an average accuracy rate of 81.7%, which is at least 1.6 times better than the current state-of-the-art keystroke recognition algorithm.

关键词： Measurement Deep learning Adaptation models Accuracy Source separation Heuristic algorithms Identity theft Face recognition Keystroke dynamics Vectors

来源：评论

学校读者我要写书评

暂无评论

EnsembleFollower: A Hybrid Car-Following Framework Based on Hierarchical Planning and Reinforcement Learning

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Han, Xu Chen, Xianda Zhu, Meixin Cai, Pinlong Zhou, Jianshan Chu, Xiaowen Data Science and Analytics Thrust Information Hub Guangzhou China Intelligent Transportation Thrust Systems Hub Guangzhou China Sensing and Computation for Ubiquitous Internet of Things Guangdong Provincial Key Lab of Integrated Communication China Southeast University School of Transportation Nanjing211189 China Shanghai Artificial Intelligence Laboratory Shanghai China Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems & Safety Control State Key Laboratory of Intelligent Transportation Systems China Beihang University School of Transportation Science and Engineering Beijing100191 China

Car-following models have made significant contributions to our understanding of longitudinal driving behavior. However, they often exhibit limited accuracy and flexibility, as they cannot fully capture the complexity inherent in car-following processes, or may struggle in unseen scenarios due to their reliance on confined driving skills present in training data. It is worth noting that each car-following model possesses its own strengths and weaknesses depending on specific driving scenarios. Therefore, we propose EnsembleFollower, a closed-loop hierarchical planning framework for achieving human-like autonomous car-following. The EnsembleFollower framework involves a high-level Reinforcement Learning-based agent responsible for judiciously managing multiple low-level models (such as Intelligent Driver Model and Gipps model) according to the current state, either by selecting an appropriate car-following model to perform an action or by allocating different weights across all primitive models. Moreover, we propose a jerk-constrained kinematic model for more convincing microscopic traffic simulations. We evaluate the proposed method based on real-world driving data from the HighD dataset. The experimental results illustrate that EnsembleFollower yields an improved accuracy of human-like behavior and achieves effectiveness in combining hybrid models, demonstrating that our proposed framework can handle diverse driving conditions by leveraging the strengths of various car-following models. © 1967-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Feature-Oriented Sampling for Fast and Scalable GNN Training

Feature-Oriented Sampling for Fast and Scalable GNN Training

引用

IEEE International Conference on data Mining (ICDM)

作者： Xin Zhang Yanyan Shen Lei Chen Division of Emerging Interdisciplinary Areas The Hong Kong University of Science and Technology Department of Computer Science and Engineering Shanghai Jiao Tong University Data Science and Analytics Thrust The Hong Kong University of Science and Technology (Guangzhou)

Recently Graph Neural Networks (GNNs) have achieved great success in many applications. To apply GNNs to large graphs, mini-batch training and sampling are widely adopted by recent works. However, existing works generate mini-batches following a topology-oriented sampling style, which first samples a subgraph and then fetches the corresponding node features to construct a mini-batch. This inevitably incurs intensive random access of graph data, the exponential growth of the batch size, and constrained candidates during sampling. In this work, we advocate adopting a feature-oriented sampling style which can overcome these drawbacks. We first sample the node features and then induce the corresponding subgraph to form a mini-batch. We apply the feature-oriented sampling method to three mainstream GNN models to demonstrate the effectiveness and efficiency of this sampling style. Experiments on four large-scale datasets show that feature-oriented sampling can achieve comparable accuracy as topology-oriented sampling while speeding up the training procedure by 2.2 ~ 7.9 times.

关键词： Training Social networking (online) Scalability Sampling methods Graph neural networks data mining

来源：评论

学校读者我要写书评

暂无评论

All in One: Multi-Task Prompting for Graph Neural Networks

arXiv

引用

arXiv 2023年

作者： Sun, Xiangguo Cheng, Hong Li, Jia Liu, Bo Guan, Jihong Department of Systems Engineering and Engineering Management Shun Hing Institute of Advanced Engineering The Chinese University of Hong Kong Hong Kong Data Science and Analytics Thrust The Hong Kong University of Science and Technology Guangzhou China School of Computer Science and Engineering Southeast University Purple Mountain Laboratories China Department of Computer Science and Technology Tongji University China

Recently, "pre-training and fine-tuning" has been adopted as a standard workflow for many graph tasks since it can take general graph knowledge to relieve the lack of graph annotations from each application. However, graph tasks with node level, edge level, and graph level are far diversified, making the pre-training pretext often incompatible with these multiple tasks. This gap may even cause a "negative transfer" to the specific application, leading to poor results. Inspired by the prompt learning in natural language processing (NLP), which has presented significant effectiveness in leveraging prior knowledge for various NLP tasks, we study the prompting topic for graphs with the motivation of filling the gap between pre-trained models and various graph tasks. In this paper, we propose a novel multi-task prompting method for graph models. Specifically, we first unify the format of graph prompts and language prompts with the prompt token, token structure, and inserting pattern. In this way, the prompting idea from NLP can be seamlessly introduced to the graph area. Then, to further narrow the gap between various graph tasks and state-of-the-art pre-training strategies, we further study the task space of various graph applications and reformulate downstream problems to the graph-level task. Afterward, we introduce meta-learning to efficiently learn a better initialization for the multi-task prompt of graphs so that our prompting framework can be more reliable and general for different tasks. We conduct extensive experiments, results from which demonstrate the superiority of our method. Copyright © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Stacking designs: designing multi-fidelity computer experiments with target predictive accuracy

arXiv

引用

arXiv 2022年

作者： Sung, Chih-Li Ji, Yi Mak, Simon Wang, Wenjia Tang, Tao Department of Statistics and Probability Michigan State University United States Department of Statistical Science Duke University United States Data Science and Analytics Thrust Information Hub Hong Kong University of Science and Technology Guangzhou China Department of Mathematics Duke University United States

In an era where scientific experiments can be very costly, multi-fidelity emulators provide a useful tool for cost-efficient predictive scientific computing. For scientific applications, the experimenter is often limited by a tight computational budget, and thus wishes to (i) maximize predictive power of the multi-fidelity emulator via a careful design of experiments, and (ii) ensure this model achieves a desired error tolerance with some notion of confidence. Existing design methods, however, do not jointly tackle objectives (i) and (ii). We propose a novel stacking design approach that addresses both goals. A multi-level reproducing kernel Hilbert space (RKHS) interpolator is first introduced to build the emulator, under which our stacking design provides a sequential approach for designing multi-fidelity runs such that a desired prediction error of ϵ > 0 is met under regularity assumptions. We then prove a novel cost complexity theorem that, under this multi-level interpolator, establishes a bound on the computation cost (for training data simulation) needed to achieve a prediction bound of ϵ. This result provides novel insights on conditions under which the proposed multi-fidelity approach improves upon a conventional RKHS interpolator which relies on a single fidelity level. Finally, we demonstrate the effectiveness of stacking designs in a suite of simulation experiments and an application to finite element analysis. © 2022, CC BY.

关键词： Design of experiments

来源：评论

学校读者我要写书评

暂无评论

A Quality-Aware Rendezvous Framework for Cognitive Radio Networks

A Quality-Aware Rendezvous Framework for Cognitive Radio Net...

引用

International Conference on Mobile Ad-hoc and Sensor Networks, MSN

作者： Hai Liu Lu Yu Chung Keung Poon Zhiyong Lin Yiu- Wing Leung Xiaowen Chu Department of Computing The Hang Seng University of Hong Kong Hong Kong Department of Computer Science GuangDong Polytechnic Normal University Guangzhou China Department of Computer Science Hong Kong Baptist University Hong Kong Data Science and Analytics Thrust Hong Kong University of Science and Technology (Guangzhou)

In cognitive radio networks, rendezvous is a fundamental operation by which cognitive users establish communication links. Most of existing works were devoted to shortening the time-to-rendezvous (TTR) but paid little attention to qualities of the channels on which rendezvous is achieved. In fact, qualities of channels, such as resistance to primary users' activities, have a great effect on the rendezvous operation. If users achieve a rendezvous on a low-quality channel, the communication link is unstable and the communication performance is poor. In this case, re- rendezvous is required which results in considerable communication overhead and a large latency. In this paper, we first show that actual TTRs of existing rendezvous solutions increase by 65.40-104.38% if qualities of channels are not perfect. Then we propose a Quality-Aware Rendezvous Framework (QARF) that can be applied to any existing ren-dezvous algorithms to achieve rendezvous on high-quality channels. The basic idea of QARF is to expand the set of available channels by selectively duplicating high-quality channels. We prove that QARF can reduce the expected TTR of any rendezvous algorithm when the expanded ratio $\lambda$ is smaller than the threshold $(-3+\sqrt{1+4(\frac{\sigma}{\mu})^{2}}) / 2$ , where $\mu$ and $\sigma$ , respectively, are the mean and the standard deviation of qualities of channels. We further prove that QARF can always reduce the expected TTR of Random algorithm by a factor of $1+(\frac{\sigma}{\mu})^{2}$ . Extensive experiments are conducted and the results show that QARF can significantly reduce the TTRs of the existing rendezvous algorithms by 10.50-51.05 % when qualities of channels are taken into account.

关键词： Resistance Sensors Cognitive radio Standards

来源：评论

学校读者我要写书评

暂无评论

Cooperative Multi-source data Trading

Cooperative Multi-source Data Trading

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Jin Cheng Ningning Ding John C. S. Lui Jianwei Huang School of Science and Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society The Chinese University of Hong Kong Shenzhen Data Science and Analytics Thrust Information Hub Hong Kong University of Science and Technology Guangzhou Department of Computer Science and Engineering The Chinese University of Hong Kong School of Science and Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen Key Laboratory of Crowd Intelligence Empowered Low-Carbon Energy Network and CSIJRI Joint Research Centre on Smart Energy Storage The Chinese University of Hong Kong Shenzhen

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

In the era of big data, data trading significantly enhances data-driven technologies by facilitating data sharing. Despite the clear advantages often experienced by data users when incorporating multiple sources, the topic of multi-source data trading remains largely unexplored. This paper designs a novel data trading framework, which enables multi-source data trading through multi-source cooperation. The proposed framework aims to improve data usage efficiency and increase seller revenue. In particular, we model data sellers’ cooperative decisions through the Nash bargaining framework and systematically outline the interactions between sellers and buyers as a two-stage Stackelberg game. A key contribution of this work is the consideration of coupling among diverse data products, which is essential but often overlooked in prior studies. We properly classify data’s utility into endogenous and relational categories to disentangle the coupling. Despite the inherent non-convex nature of the optimization problem, we methodically derive the closed-form optimal solutions by decomposing the problem into several subproblems. Interestingly, we reveal that, under our proposed framework, sellers’ revenue initially remains steady with the increase of product coupling level, but begins to rise once the level exceeds a certain threshold due to the substitute effect. Finally, experimental results show that our proposed framework can improve the seller’s profit by up to 46.32% compared to traditional data trading methods in the current data market.

关键词： Couplings Games Big data data models Global communication Optimization

来源：评论

学校读者我要写书评

暂无评论

The power of randomization: Efficient and effective algorithms for constrained submodular maximization

arXiv

引用

arXiv 2021年

作者： Han, Kai Cui, Shuang Zhu, Tianshuai Tang, Jing Wu, Benwei Huang, He School of Computer Science and Technology SuZhou Research Institute University of Science and Technology of China Data Science and Analytics Thrust Hong Kong University of Science and Technology School of Computer Science and Technology Soochow University

Submodular optimization has numerous applications such as crowdsourcing and viral marketing. In this paper, we study the fundamental problem of non-negative submodular function maximization subject to a k-system constraint, which generalizes many other important constraints in submodular optimization such as cardinality constraint, matroid constraint, and k-extendible system constraint. The existing approaches for this problem achieve the best-known approximation ratio of k + 2 √k + 2 + 3 (for a general submodular function) based on deterministic algorithmic frameworks. We propose several randomized algorithms that improve upon the state-of-the-art algorithms in terms of approximation ratio and time complexity, both under the non-adaptive setting and the adaptive setting. The empirical performance of our algorithms is extensively evaluated in several applications related to data mining and social computing, and the experimental results demonstrate the superiorities of our algorithms in terms of both utility and efficiency. Copyright © 2021, The Authors. All rights reserved.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Fingerprint Construction and Localization System For Large Indoor Area

Semi-supervised Fingerprint Construction and Localization Sy...

引用

Automation, Robotics and Computer Engineering (ICARCE), International Conference on

作者： Min Gao Yuanyuan Fei Zhouhong Wang Chunming Ma Li Luo Digital Life Research Center Guangzhou HKUST Fok Ying Tung Research Institute Guangzhou China Data Science and Analytics Thrust Information Hub The Hong Kong University of Science and Technology(Guang Zhou) Guangzhou China Research and Development Center Jiangsu Mashi Information Technology Co. Ltd Jiangsu China

ISBN: (纸本)9781665475495

Many applications of location-based indoor navigation services require precise location information of a user. While Global Positioning System (GPS) loses reliability indoors, fingerprints-based localization technology (FBLT) embodies superiority regarding accuracy and robustness. In a Bluetooth-based fingerprint localization system, a radio map is constructed offline and used as a reference for subsequent real-time localization tasks. However, the quality of the fingerprint radio map could be problematic when it comes to a large, broad space with low beacon density. data collection in such a space could be exhausting as well. Another main issue is that different mobile devices receive heterogeneous signal strength at the same location. In this article, we propose a highly practical localization system with a semi-supervised learning fingerprints construction method that provides an efficient solution for a large-scale localization system in a complex indoor environment. We also conducted a series of experiments to evaluate the performance of this system.

关键词： Location awareness Indoor navigation Fingerprint recognition Semisupervised learning Robustness Real-time systems Mobile handsets

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：