检索结果-内蒙古大学图书馆

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Raman Arora Raef Bassily Cristóbal Guzmán Michael Menart Enayat Ullah Department of Computer Science The Johns Hopkins University Department of Computer Science & Engineering Translational Data Analytics Institute (TDAI) The Ohio State University Inst. for Mathematical and Comput. Eng. Fac. de Matemáticas and Esc. de Ingeniería Pontificia Universidad Católica de Chile Department of Computer Science & Engineering The Ohio State University

ISBN: (纸本)9781713871088

We study the problem of (ε, δ)-differentially private learning of linear predictors with convex losses. We provide results for two subclasses of loss functions. The first case is when the loss is smooth and non-negative but not necessarily Lipschitz (such as the squared loss). For this case, we establish an upper bound on the excess population risk of $\tilde{O}\left(\frac{\Vert w^*\Vert}{\sqrt{n}} + \min\left\{\frac{\Vert w^* \Vert^2}{(n\epsilon)^{2/3}},\frac{\sqrt{d}\Vert w^*\Vert^2}{n\epsilon}\right\}\right)$, where n is the number of samples, d is the dimension of the problem, and w* is the minimizer of the population risk. Apart from the dependence on ‖w*‖, our bound is essentially tight in all parameters. In particular, we show a lower bound of $\tilde{\Omega}\left(\frac{1}{\sqrt{n}} + {\min\left\{\frac{\Vert w^*\Vert^{4/3}}{(n\epsilon)^{2/3}}, \frac{\sqrt{d}\Vert w^*\Vert}{n\epsilon}\right\}}\right)$. We also revisit the previously studied case of Lipschitz losses [SSTT20]. For this case, we close the gap in the existing work and show that the optimal rate is (up to log factors) $\Theta\left(\frac{\Vert w^*\Vert}{\sqrt{n}} + \min\left\{\frac{\Vert w^*\Vert}{\sqrt{n\epsilon}},\frac{\sqrt{\text{rank}}\Vert w^*\Vert}{n\epsilon}\right\}\right)$, where rank is the rank of the design matrix. This improves over existing work in the high privacy regime. Finally, our algorithms involve a private model selection approach that we develop to enable attaining the stated rates without a-priori knowledge of ‖w*‖.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EC²Detect: Real-Time Online Video Object Detection in Edge-Cloud Collaborative IoT

引用

IEEE Internet of Things Journal 2022年第20期9卷 20382-20392页

作者： Siyan Guo Cong Zhao Guiqin Wang Jiaqing Yang Shusen Yang National Engineering Laboratory for Big Data Analytics and the School of Mathematics and Statistics Xi’an Jiaotong University Xi’an China Department of Computing Imperial College London London U.K. National Engineering Laboratory for Big Data Analytics and the School of Computer Science and Technology Xi’an Jiaotong University Xi’an China School of Mathematics and Statistics Xi’an Jiaotong University Xi’an China National Engineering Laboratory for Big Data Analytics and Ministry of Education Key Laboratory for Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an China Industrial Artificial Intelligence Center Pazhou Laboratory Guangzhou China

Video object detection is a fundamental technology of intelligent video analytics for Internet of Things (IoT) applications. However, even with extraordinary detection accuracy, predominating solutions based on deep convolutional neural networks (DCNNs) cannot achieve real-time online object detection on video streams with a low end-to-end (E2E) response latency and therefore cannot be applied to proliferating latency-sensitive IoT applications like autonomous driving requiring large-scale intelligent video analytics. To address this issue, we present EC2Detect, an edge-cloud collaborative real-time online video object detection method. Specifically, we propose a tracking-assisted object detection architecture based on edge-cloud collaboration with keyframe selection, where the accurate but heavy object detection is conducted by the Cloud on sparse keyframes adaptively selected according to their semantic variation, and the lightweight object tracking is used to localize and identify objects in other frames at edge devices. Extensive experiments of our real-world prototype demonstrate that, EC2Detect significantly outperforms state-of-the-art methods in terms of processing speed (up to $4.77\times $ faster), E2E latency (up to $8.12 \times $ lower), and edge-cloud bandwidth occupation ( $17 \times $ lower) with an acceptable mAP, which can effectively support large-scale intelligent video analytics in practice. Source code of EC2Detect is available at https://***/ECCDetect/ECCDetect .

关键词： Object detection Image edge detection Streaming media Internet of Things Collaboration Visual analytics Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Direct public transportation guide using location and AI

引用

AIP Conference Proceedings 2025年第1期3204卷

作者： V. Savitha N. Leena L. Rajeshwari S. Roobini M. Rosheni Department of Data Analytics in Healthcare SNS College of Technology Coimbatore India Department of Computer Science and Engineering SNS College of Technology Coimbatore India

An innovative system that uses geolocation and artificial intelligence (AI) to deliver precise and timely trip information to those using public transportation is called a "direct public transportation guide." This system provides timely and tailored help for navigating metropolitan transit networks by integrating real-time data, predictive analytics, and user preferences. This guide employ’s location services to determine the user’s exact location and final destination. With this information, it can provide the best possible routes complete with transfers and schedules for buses, trains, subways, trams, and other public transportation options. This method is improved by the AI component, which analyzes enormous volumes of data and provides dynamic, adaptive recommendations by taking into account past patterns, traffic situations, and service interruptions. In addition, the direct public transit guide could provide other elements like fare predictions, accessibility data, and recommendations for different routes in the event of unforeseen delays. With this all-encompassing strategy, people who depend on public transportation should find it easier, more convenient, and more user-friendly to commute. All things considered, this system is a huge step forward for urban mobility, fusing geospatial knowledge with state-of-the-art technology to completely change how people use and manage public transit systems. It ultimately encourages the usage of public transit choices, which leads to more accessible and sustainable urban environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

data Driven based Malicious URL Detection using Explainable AI

Data Driven based Malicious URL Detection using Explainable ...

引用

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

作者： Saranda Poddar Deepraj Chowdhury Ashutosh Dhar Dwivedi Raghava Rao Mukkamala Department of Computer Science RCC Institute of Information Technology Kolkata India Department of Electronics and Communication International Institute of Information Technology Naya Raipur India Department of Digitization Centre for Business Data Analytics Copenhagen Business School Frederiksberg Denmark

With the ever-increasing reach of the internet, and its increasing access through various types of devices, the spread of malware, phishing attempts, etc. have steadily been increasing, along with their level of sophistication. Thus it becomes very important to conduct research on different methods to prevent such harmful attacks on systems and users. Using a malicious URL is the common way for hackers to attack a system, thus, to accommodate the variety attack vectors of malicious websites, 21 features were extracted from 651,191 URLs to train the proposed model. A two-stage stacked ensemble learning model, based on gradient boosting methods and random forest, has been trained and tested in the 70:30 ratio of the 651,191 URLs, and an accuracy of 97% has been achieved. Then Explainable AI (XAI) has been used to clearly explain the working of the model, and study the impact of each of the 21 features on the 4 class predictions (benign, defacement, phishing and malware).

关键词： Uniform resource locators Phishing Forestry Predictive models Feature extraction Malware Security

来源：评论

学校读者我要写书评

暂无评论

Beyond Reality: Crafting Logical Systems for Autonomous Vehicles through Virtual Reality

Beyond Reality: Crafting Logical Systems for Autonomous Vehi...

引用

Communication & Computing (WCONF), World Conference on

作者： N.K. Senthil Kumar Sumalatha A Dhivyabharathi R K. Suresh Kumar A. Hency Juliet S. Rajarajeswari Department of CSE School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Computer Science Kristu Jayanti College Bengaluru Karnataka India Department of Computer Science and Engineering S.A. Engineering College Chennai Tamil Nadu India Department of MBA Panimalar Engineering College Chennai Tamil Nadu India Department of Data Analytics Saveetha College of Liberal Arts and Sciences Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India Department of Science and Humanities Prince Shri Venkateshwara Padmavathy Engineering College Chennai Tamil Nadu India

ISBN: (数字)9798350395327

ISBN: (纸本)9798350395334

The current paradigm for advancing autonomous driving functionalities on public roads predominantly operates within the tangible realm. Autonomous vehicles (AVs) are equipped with an array of sensors, including Lidar, cameras, radar, GPS, and on-board-unit (OBU) modems, each actively collecting data about the surrounding environment. This data is then processed through sophisticated algorithms, enhancing the vehicle's situational awareness. In our pursuit of refining autonomous driving capabilities, we leverage the AVTSC Simulator as our chosen Autonomous Vehicle (AV) simulation environment. Notably, this simulator stands out for its ability to replicate realistic urban settings and seamlessly integrate with widely used platforms such as Apollo and ROS. By harnessing the capabilities of this simulation environment, we aim to bridge the gap between real-world testing and simulated scenarios. This abstract encapsulates the essence of our strategy, emphasizing the integration of advanced sensor technologies and simulation environments for the development of autonomous driving features. Preliminary results indicate a promising 94% success rate for the proposed methodology, showcasing the efficacy of our approach in enhancing the robustness and reliability of autonomous systems.

关键词： Laser radar Roads Virtual reality Modems Cameras Robustness Autonomous vehicles Testing Global Positioning System Sensor arrays

来源：评论

学校读者我要写书评

暂无评论

Automated Mobility Context Detection with Inertial Signals

arXiv

引用

arXiv 2022年

作者： Bevilacqua, Antonio Alcock, Lisa Caulfield, Brian Gazit, Eran Hansen, Clint Ireson, Neil Ifrim, Georgiana The Insight Centre for Data Analytics School of Computer Science University College Dublin Ireland The Insight Centre for Data Analytics School of Public Health Physiotherapy and Sports Science University College Dublin Ireland The Clinical Ageing Research Unit Faculty of Medical Sciences Newcastle University United Kingdom The Center for the Study of Movement Congnition and Mobility Department of Neurology Tel Aviv Sourasky Medical Center The Department of Neurology Kiel University Germany The Organisation Information and Knowledge Group Department of Computer Science University of Sheffield United Kingdom

Remote monitoring of motor functions is a powerful approach for health assessment, especially among the elderly population or among subjects affected by pathologies that negatively impact their walking capabilities. This is further supported by the continuous development of wearable sensor devices, which are getting progressively smaller, cheaper, and more energy efficient. The external environment and mobility context have an impact on walking performance, hence one of the biggest challenges when remotely analysing gait episodes is the ability to detect the context within which those episodes occurred. The primary goal of this paper is the investigation of context detection for remote monitoring of daily motor functions. We aim to understand whether inertial signals sampled with wearable accelerometers, provide reliable information to classify gait-related activities as either indoor or outdoor. We explore two different approaches to this task: (1) using gait descriptors and features extracted from the input inertial signals sampled during walking episodes, together with classic machine learning algorithms, and (2) treating the input inertial signals as time series data and leveraging end-to-end state-of-the-art time series classifiers. We directly compare the two approaches through a set of experiments based on data collected from 9 healthy individuals. Our results indicate that the indoor/outdoor context can be successfully derived from inertial data streams. We also observe that time series classification models achieve better accuracy than any other feature-based models, while preserving efficiency and ease of use. © 2022, CC BY-NC-SA.

关键词： Remote control

来源：评论

学校读者我要写书评

暂无评论

Eigenvalue-Based Randomness Test for Residual Diagnostics in Panel data Models

arXiv

引用

arXiv 2025年

作者： Kurbucz, Marcell T. Garrido, Betsabé Pérez Jakovác, Antal Institute for Global Prosperity The Bartlett University College London 149 Tottenham Court Road LondonW1T 7NF United Kingdom Department of Computer Science Institute of Data Analytics and Information Systems Corvinus University of Budapest 8 Fővám Square Budapest1093 Hungary Department of Computational Sciences Institute for Particle and Nuclear Physics HUN-REN Wigner Research Centre for Physics 29-33 Konkoly-Thege Miklós Street Budapest1121 Hungary Department of Statistics Institute of Data Analytics and Information Systems Corvinus University of Budapest 8 Fővám Square Budapest1093 Hungary

This paper introduces the Eigenvalue-Based Randomness (EBR) test—a novel approach rooted in the Tracy-Widom law from random matrix theory—and applies it to the context of residual analysis in panel data models. Unlike traditional methods, which target specific issues like cross-sectional dependence or autocorrelation, the EBR test simultaneously examines multiple assumptions by analyzing the largest eigenvalue of a symmetrized residual matrix. Monte Carlo simulations demonstrate that the EBR test is particularly robust in detecting not only standard violations such as autocorrelation and linear cross-sectional dependence (CSD) but also more intricate non-linear and non-monotonic dependencies, making it a comprehensive and highly flexible tool for enhancing the reliability of panel data *** Codes 62H25, 15B52, 62M10 © 2025, CC BY.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

Empirical Measurements of AI Training Power Demand on a GPU-Accelerated Node

arXiv

引用

arXiv 2024年

作者： Latif, Imran Newkirk, Alex C. Carbone, Matthew R. Munir, Arslan Lin, Yuewei Koomey, Jonathan Yu, Xi Dong, Zhihua Computing and Data Sciences Directorate Brookhaven National Laboratory UptonNY United States Building Technology and Urban Systems Lawrence Berkeley National Laboratory BerkeleyCA United States Department of Electrical Engineering and Computer Science Florida Atlantic University Boca RatonFL United States Koomey Analytics San FranciscoCA United States

The expansion of artificial intelligence (AI) applications has driven substantial investment in computational infrastructure, especially by cloud computing providers. Quantifying the energy footprint of this infrastructure requires models parameterized by the power demand of AI hardware during training. We empirically measured the instantaneous power draw of an 8-GPU NVIDIA H100 HGX node during the training of open-source image classifier (ResNet) and large-language models (Llama2-13b). The maximum observed power draw was approximately 8.4 kW, 18% lower than the manufacturer-rated 10.2 kW, even with GPUs near full utilization. Holding model architecture constant, increasing batch size from 512 to 4096 images for ResNet reduced total training energy consumption by a factor of 4. These findings can inform capacity planning for data center operators and energy use estimates by researchers. Future work will investigate the impact of cooling technology and carbon-aware scheduling on AI workload energy consumption. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integration of AI and Cloud-Native Technologies for Personalized Mobile Banking Experiences

Integration of AI and Cloud-Native Technologies for Personal...

引用

Recent Innovation in Smart and Sustainable Technology (ICRISST), International Conference on

作者： N. Legapriyadharshini T. Thirumalaikumari K. Senbagam R. Sarasu H. Anwer Basha P. Malathi Department of Computer Application Saveetha College of Liberal Arts and Sciences Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of Computer Science Saveetha College of Liberal Arts and Sciences SIMATS Deemed to be University Chennai Tamil Nadu India Department of Computer Science and Engineering Dhanalakshmi Srinivasan College of Engineering and Technology Mamallapuram Tamil Nadu India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of Computer Science Saveetha College of Liberal Arts and Sciences Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of Data Analytics Saveetha College of Liberal Arts and Sciences Saveetha Institute of Medical And Technical Sciences Chennai Tamil Nadu India

ISBN: (数字)9798350309140

ISBN: (纸本)9798350309157

In today's rapidly evolving digital landscape, using Artificial Intelligence (AI) and Cloud-Native Technologies is essential for improving personalized mobile banking experiences. The limitations and errors of existing financial systems necessitate such integration. Existing systems often struggle to adapt to modern consumers dynamic tastes and expectations, resulting in unsatisfactory customer experiences. Identifying the gap, the proposed system revolutionizes mobile banking applications by leveraging AI algorithms such as machine learning and natural language processing within a microservices-based cloud infrastructure. As a result, the proposed system solves the limitations of outdated architectures by providing personalized and efficient services while addressing security issues. The study indicates considerable gains in terms of user pleasure, system scalability, and security robustness through an in-depth evaluation of the results. The results highlight AI's and Cloud-Native Technologies transformational potential in revolutionizing the landscape of tailored mobile banking experiences. The study provides helpful information to financial institutions looking to adopt innovation and fulfill the evolving needs of modern consumers.

关键词： Technological innovation Scalability Microservice architectures Banking Predictive models User experience Robustness Natural language processing Security Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

UDHF2-Net: Uncertainty-diffusion-model-based High-Frequency TransFormer Network for Remotely Sensed Imagery Interpretation

arXiv

引用

arXiv 2024年

作者： Zhang, Pengfei Li, Chang Zhang, Yongjun Qin, Rongjun Key Laboratory for Geographical Process Analysis & Simulation of Hubei Province College of Urban and Environmental Science Central China Normal University Wuhan China School of Remote Sensing and Information Engineering Wuhan University China Department of Civil Environmental and Geodetic Engineering Department of Electrical and Computer Engineering Translational Data Analytics Institute The Ohio State University ColumbusOH United States

Remotely sensed imagery interpretation (RSII), including semantic segmentation and change detection, faces the three major problems: (1) objective representation of spatial distribution patterns with coexistence of spatial stationary and non-stationary;(2) edge uncertainty problem caused by downsampling encoder and intrinsic edge noises (e.g., mixed pixel and edge occlusion etc.);and (3) false detection problem caused by geometric registration error in change detection. To solve the aforementioned problems, uncertainty-diffusion-model-based high-Frequency TransFormer network (UDHF2-Net) is the first to be proposed, whose superiorities are as follows: (1) a spatially-stationary-and-non-stationary high-frequency connection paradigm (SHCP) is proposed to enhance the interaction of spatially frequency-wise stationary and non-stationary features to yield high-fidelity edge extraction result. Inspired by HRFormer, SHCP proposes high-frequency-wise stream to replace high-resolution-wise stream in HRFormer through the whole encoder-decoder process with parallel frequency-wise high-to-low streams, so it improves the edge extraction accuracy by continuously remaining high-frequency information;(2) a mask-and-geo-knowledge-based uncertainty diffusion module (MUDM), which is a self-supervised learning strategy, is proposed to improve the edge accuracy of extraction and change detection by gradually removing the simulated spectrum noises based on geo-knowledge and the generated diffused spectrum noises;(3) a frequency-wise semi-pseudo-Siamese UDHF2-Net is the first to be proposed to balance accuracy and complexity for change detection. Besides the aforementioned spectrum noises in semantic segmentation, MUDM is also a self-supervised learning strategy to effectively reduce the edge false change detection from the generated imagery with geometric registration error. In semantic segmentation experiments, UDHF2-Net achieved the best mIoU values of 92.00%, 87.31% and 55.27% respecti

关键词： Semantic Segmentation

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：