检索结果-内蒙古大学图书馆

DBJoules: An Energy Measurement Tool for Database Management systems

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lella, Hemasri Sai Chattaraj, Rajrupa Manasa, Kurra Chimalakonda, Sridhar Research in Intelligent Systems and Human Analytics Lab Department of Computer Science and Engineering Indian Institute of Technology Tirupati India

In the rapidly evolving landscape of modern data-driven technologies, software relies on large datasets and constant data center operations using various database systems to support computation-intensive tasks. As energy consumption in software systems becomes a growing concern, selecting the right database from energy-efficiency perspective is also critical. To address this, we introduce DBJoules, a tool that measures the energy consumption of activities in database systems. DBJoules supports energy measurement of CRUD operations for four popular databases. Through evaluations on two widely-used datasets, we identify disparities of 7% to 38% in the energy consumption of these databases. Hence, the goal is to raise developer awareness about the effect of running queries in different databases from an energy consumption perspective, enabling them to select appropriate database for sustainable usage. The tool’s demonstration is available at https://***/D1MTZum0jok and related artifacts at https://***/DBJoules/. Copyright © 2023, The Authors. All rights reserved.

关键词： Energy utilization

Enhancing HIPAA Compliance in AI-driven mHealth Devices Security and Privacy

学校读者我要写书评

暂无评论

Enhancing HIPAA Compliance in AI-driven mHealth Devices Secu...

IEEE Annual International computer Software and Applications Conference (COMPSAC)

作者： ABM Kamrul Islam Riad Md Abdul Barek Md Mostafizur Rahman Mst Shapna Akter Tahia Islam Md Abdur Rahman Md Raihan Mia Hossain Shahriar Fan Wu Sheikh Iqbal Ahamed Department of Intelligent Systems and Robotics University of West Florida USA Dept. of Cybersecurity and Information Technology University of West Florida USA Center for Cybersecurity University of West Florida USA Department of Computer Science Georgia State University USA Dept. of Computer Science Tuskegee University USA Department of Computer Science Marquette University USA

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

-The integration of Artificial Intelligence (AI) in mobile health (mHealth) devices offers significant advancements in patient care but also raises complex security and privacy concerns for sensitive health data. This paper explores the evolving landscape of Health Insurance Portability and Accountability Act (HIP AA) compliance within the context of AI-based mHealth devices, focusing on anticipated challenges in 2024. It examines the current state of HIP AA compliance in AI-driven mHealth, identifying potential vulnerabilities and gaps among mHealth devices in considering privacy and security. The study outlines key security and privacy considerations specific to AI-powered mHealth technologies, emphasizing risks such as data breaches, ransomware attack and unauthorized access. The paper concludes by highlighting the importance of continual adaptation to the dynamic nature of AI technologies and offers insights for stakeholders to navigate the regulatory landscape and ensure the responsible deployment of AI in healthcare.

关键词： Privacy Data privacy Navigation Software Security Stakeholders Ransomware

UNCERTAINTY-PENALIZED DIRECT PREFERENCE OPTIMIZATION

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Houliston, Sam Pace, Alizée Immer, Alexander Rätsch, Gunnar Department of Computer Science ETH Zurich Switzerland ETH AI Center Zurich Switzerland Max Planck Institute for Intelligent Systems Tübingen Germany

Aligning Large Language Models (LLMs) to human preferences in content, style, and presentation is challenging, in part because preferences are varied, context-dependent, and sometimes inherently ambiguous. While successful, Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) are prone to the issue of proxy reward overoptimization. Analysis of the DPO loss reveals a critical need for regularization for mislabeled or ambiguous preference pairs to avoid reward hacking. In this work, we develop a pessimistic framework for DPO by introducing preference uncertainty penalization schemes, inspired by offline reinforcement learning. The penalization serves as a correction to the loss which attenuates the loss gradient for uncertain samples. Evaluation of the methods is performed with GPT2 Medium on the Anthropic-HH dataset using a model ensemble to obtain uncertainty estimates, and shows improved overall performance compared to vanilla DPO, as well as better completions on prompts from high-uncertainty chosen/rejected *** Codes Learning and adaptive systems in artificial intelligence Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

Toward a personalized autonomous transportation system:Vision,challenges,and solutions

学校读者我要写书评

暂无评论

The Innovation 2024年第6期5卷 47-49页

作者： Linlin You Mai Hao Jian Sun Yunpeng Wang Chunming Rong Chau Yuen Paolo Santi Carlo Ratti School of Intelligent Systems Engineering Sun Yat-Sen UniversityShenzhen 518107China Department of Traffic Engineering Tongji UniversityShanghai 200092China School of Transportation Science and Engineering Beihang UniversityBeijing 100083China Department of Electrical Engineering and Computer Science University of Stavanger4036 StavangerNorway School of Electrical and Electronics Engineering Nanyang Technological UniversitySingapore 639798Singapore Senseable City Lab Massachusetts Institute of TechnologyCambridgeMA 02139USA

The fragmented design of intelligent transportation systems creates isolated intelligent *** competition and information gaps are fierce and widespread,worsening traffic issues and degrading overall service ***,empowered by advanced technologies,an evolution toward an autonomous transportation system(ATS)is *** evolution aims to develop a collaborative and sustainable ecosystem,prompting interoperability within the cloud-edge-device continuum.

关键词： autonomous system prompt

Using machine learning and satellite data from multiple sources to analyze mining,water management,and preservation of cultural heritage

学校读者我要写书评

暂无评论

地球空间信息科学学报（英文版） 2024年第3期27卷 552-571页

作者： Joaquim J.Sousa Jiahui Lin Qun Wang Guang Liu Jinghui Fan Shibiao Bai Hongli Zhao Hongyu Pan Wenjing Wei Vanessa Rittlinger Peter Mayrhofer Ruth Sonnenschein Stefan Steger Luís Paulo Reis School of Science and Technology University of Trás-Os-Montes E Alto DouroVila RealPortugal Centre for Robotics in Industry and Intelligent Systems(CRIIS) INESC Technology and SciencePortoPortugal Aerospace Information Research Institute Chinese Academy of SciencesBeijingChina International Research Center of Big Data for Sustainable Development Goals BeijingChina College of Resources and Environment University of Chinese Academy of SciencesBeijingChina Application system Department Ⅰ China Siwei Surveying and Mapping Technology Co.LtdBeijingChina China Aero Geophysical Survey and Remote Sensing Center for Natural Resources BeijingChina College of Marine Science and Engineering Nanjing Normal UniversityNanjingChina Institute of Mountain Hazards and Environment Chinese Academy of SciencesChengduChina College of Marine Science and Engineering Nanjing Normal UniversityNanjingChina Institute for Earth Observation Eurac ResearchBolzanoItaly Faculty of Engineering University of PortoPortoPortugal

Remote sensing,particularly satellite-based,can play a valuable role in monitoring areas prone to *** high spatial and temporal coverage provided by satellite data can be used to reconstruct past events and continuously monitor sensitive areas for potential *** paper presents a range of techniques and methods that were applied for in-depth analysis and utilization of Earth observation data,with a particular emphasis on:(1)detecting mining sub-sidence,where a novel approach is proposed by combining an improved U-Net model and Interferometry Synthetic Aperture Radar(InSAR)*** results showed that the Efficient Channel Attention(ECA)U-Net model performed better than the U-Net(baseline)model in terms of Mean Intersection over Union(MIoU)and Intersection over Union(loU)indicators;(2)monitor-ing water conservancy and hydropower *** Xiaolangdi multipurpose dam complex was monitored using Small BAsline Subsets(SBAS)InSAR method on Sentinel-1 time series data and four small regions with high deformation rates were identified on the slope of the reservoir bank on the north *** dam body also showed obvious deformation with a velocity exceeding 60 mm/a;(3)the evaluation of the potential of InSAR results to integrate monitoring and warning systems for valuable heritage and architectural *** overall outcome of these methods showed that the use of Artificial Intelligence(AI)techniques in combination with InSAR data leads to more efficient analysis and interpretation,resulting in improved accuracy and prompt identification of potential hazards;and(4)finally,this study also presents a method for detecting landslides in mountainous regions,using optical *** new temporal landslide detection method is evaluated over a 7-year analysis period and unlike conventional bi-temporal change detection methods,this approach does not depend on any prior-knowledge and can potentially detect landslides over extended periods of time

关键词： Landslide detection InSAR time series analysis machine learning heritage preservation mining subsidence water conservancy infrastructures

How robust accuracy suffers from certified training with convex relaxations

学校读者我要写书评

暂无评论

arXiv 2023年

作者： De Bartolomeis, Piersilvio Clarysse, Jacob Sanyal, Amartya Yang, Fanny Department of Computer Science ETH Zürich Switzerland Max Planck Institute for Intelligent Systems Tübingen Germany

Adversarial attacks pose significant threats to deploying state-of-the-art classifiers in safety-critical applications. Two classes of methods have emerged to address this issue: empirical defences and certified defences. Although certified defences come with robustness guarantees, empirical defences such as adversarial training enjoy much higher popularity among practitioners. In this paper, we systematically compare the standard and robust error of these two robust training paradigms across multiple computer vision tasks. We show that in most tasks and for both ∞-ball and 2-ball threat models, certified training with convex relaxations suffers from worse standard and robust error than adversarial training. We further explore how the error gap between certified and adversarial training depends on the threat model and the data distribution. In particular, besides the perturbation budget, we identify as important factors the shape of the perturbation set and the implicit margin of the data distribution. We support our arguments with extensive ablations on both synthetic and image datasets. © 2023, CC BY.

关键词： Errors

Human-Factor focused Application of STPA to Remotely driven Vehicles

学校读者我要写书评

暂无评论

Human-Factor focused Application of STPA to Remotely driven ...

Public Safety Technology (WFPST), IEEE World Forum on

作者： Ole Hans Krystian Radlak Jürgen Adamy Department of Control Methods and Intelligent Systems Technical University of Darmstadt Düsseldorf Germany Institute of Computer Science Warsaw University of Technology Warsaw Poland

ISBN: (数字)9798350329148

ISBN: (纸本)9798350329155

This paper presents an analysis of the safety aspects of a Remote Driving System (RDS) using the System-Theoretic Process Analysis (STPA) methodology. The focus is on the human Remote Driver (RD) within the RDS, considering losses and system-level hazards associated with the human-in-the-loop scenario which focuses on the RD actions related to the change in Steering Wheel Angle (SWA). The STPA methodology is applied to identify Unsafe Control Actions (UCA) related to the change in SWA command, resulting in the identification of numerous Causal Factors (CF) that may lead to hazardous scenarios. Several UCAs and CFs are identified that provide information on potential hazards and risks associated with remote driving technology. Based on a selected UCA where the RD does not change the SWA when the road network requires lateral movement, 25 potential loss scenarios were identified and presented in this paper. The results of this work can contribute to the understanding of potential risks and the development of safety mitigation measures in the context of RDS which need to be validated in further research.

关键词： Roads Prevention and mitigation Wheels Hazards Public security Human in the loop Behavioral sciences

Optimal Sensor Placement in Power Transformers Using Physics-Informed Neural Networks

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Sirui Bragone, Federica Barreau, Matthieu Laneryd, Tor Morozovska, Kateryna Division of Decision and Control Systems Department of Intelligent Systems KTH Royal Institute of Technology Stockholm Sweden Division of Computational Science and Technology Department of Computer Science KTH Royal Institute of Technology Stockholm Sweden Hitachi Energy Research Västerås Sweden

Our work aims at simulating and predicting the temperature conditions inside a power transformer using Physics-Informed Neural Networks (PINNs). The predictions obtained are then used to determine the optimal placement for temperature sensors inside the transformer under the constraint of a limited number of sensors, enabling efficient performance monitoring. The method consists of combining PINNs with Mixed Integer Optimization Programming to obtain the optimal temperature reconstruction inside the transformer. First, we extend our PINN model for thermal modelling of power transformers to solve the heat diffusion equation from 1D to 2D space. Finally, we construct an optimal sensor placement model inside the transformer that can be applied to problems in 1D and 2D. Copyright © 2025, The Authors. All rights reserved.

关键词： Integer programming

Recurrent neural networks: vanishing and exploding gradients are not the end of the story

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zucchet, Nicolas Orvieto, Antonio Department of Computer Science ETH Zürich Switzerland ELLIS Institute Tübingen MPI for Intelligent Systems Tübingen AI Center Germany

Recurrent neural networks (RNNs) notoriously struggle to learn long-term memories, primarily due to vanishing and exploding gradients. The recent success of deep state-space models (SSMs), a subclass of RNNs, to overcome such difficulties challenges our theoretical understanding. In this paper, we delve into the optimization challenges of RNNs and discover that, as the memory of a network increases, changes in its parameters result in increasingly large output variations, making gradient-based learning highly sensitive, even without exploding gradients. Our analysis further reveals the importance of the element-wise recurrence design pattern combined with careful parametrizations in mitigating this effect. This feature is present in deep SSMs, as well as in other architectures, such as LSTMs. Overall, our insights provide a new explanation for some of the difficulties in gradient-based learning of RNNs and why some architectures perform better than others. Copyright © 2024, The Authors. All rights reserved.

关键词： State space methods