检索结果-内蒙古大学图书馆

2025 ieee International conference on Computational, Communication and Information Technology, ICCCIT 2025

作者： Kukreti, Sanjeev Shrivastava, Anurag Chandrashekar, Rakesh Rani, K. Pushpa Badhoutiya, Arti Lakhanpal, Sorabh Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India New Horizon College of Engineering Department of Mechanical Engineering Bangalore India MLR Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India GLA University Department of Electrical Engineering Mathura India Lovely Professional University Punjab Phagwara India

ISBN: (纸本)9798331512965

The integration of artificial intelligence (AI) into Clinical Decision Support systems (CDSS) is changing the face of healthcare by allowing AI powered predictive, data driven insights, enabling medical practitioners to prolong their diagnosis and treatment planning. To make better and faster clinical judgements, CDSS based on AI using machine learning techniques such as ensemble methods and deep learning is discussed in this paper. He said most of the focus is on models that can predict future events, diagnose plagues and deliver tailored treatment programs sifting through mountains of health care data, such as genetics, medical imaging and EHRs. Some of the main problems we work with as we implement AI driven CDSS is its data privacy, model interpretability and integration to current healthcare processes. In addition this study summarizes recent advances in artificial intelligence (AI), enabling real time analysis and making real time decisions to improve patient outcomes and reduce workloads of healthcare personnel. Case examples that employ AI-CDSS to identify diseases, optimize treatments and predict risk are provided to show how they can change the face of clinical practice. Finally, we explore where AI healthcare may be going from here with a focus on the importance of deploying these systems with patient well being in mind and with full compliance to the relevant regulations. © 2025 ieee.

关键词： AI-driven CDSS Clinical Decision Support Healthcare Machine learning Predictive Models

来源：评论

学校读者我要写书评

暂无评论

I. Federated learning: Pushing Forward Machine learning Without Scarifising Privacy

I. Federated Learning: Pushing Forward Machine Learning With...

引用

2024 International conference on Artificial Intelligence and Quantum Computation-Based Sensor Applications, ICAIQSA 2024

作者： Ghade, Om Narad, Supriya School of Allied Sciences DMIHER Faculty of Science & Technology Maharshtra Wardha India

ISBN: (纸本)9798331517953

Federated learning is a new family of privacy-preserving machine learning, tackling at the same time the most demanding challenges set by data-driven systems. In this paper, we attempt to present a study on federated learning topics concerning the principles, architecture, and mechanisms for preserving privacy and the protection of information. We survey the challenges and bounds of FL, its communication efficiency, heterogeneity-driven issues, and tradeoffs between privacy and utility. We also relate real-world FL applications to healthcare, finance, and mobile computing. We continue to investigate current research and future directions of the federated learning research landscape, showing in this way that federated learning is really changing the machine learning field as it was known before, that it allows collaborative training of models without violating people's sensitive data. © 2024 ieee.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Gait learning for 3D Bipedal Robots Based on a Combined Strategy of Hybrid Zero Dynamics Feedback control and Periodic Reward

Gait Learning for 3D Bipedal Robots Based on a Combined Stra...

引用

2024 International conference on Electrical Power systems and Intelligent control, EPSIC 2024

作者： Cui, Lingzhi Deng, Tianqi Ma, Lihua He, Wenhao Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350366075

In this study, we introduce an innovative gait learning methodology for three-dimensional bipedal robots, integrating Hybrid Zero Dynamics (HZD) priors with periodic reward functions to enhance gait stability, symmetry, and smooth action transitions. Notably, we employ a data-driven Bezier curve parameterization technique optimized through Reinforcement learning (RL) to significantly improve learning efficiency and dynamic stability of the gait. The effectiveness of our approach is systematically validated across three key metrics: lateral deviation, training speed, and robustness in challenging environments. The results demonstrate our method's superiority in maintaining path stability, accelerating the learning process, and adapting to complex terrains over traditional gait learning approaches. This research not only advances the efficiency and stability of gait learning for three-dimensional bipedal robots but also provides valuable insights for future studies on robotic gait optimization. ©2024 ieee.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Power and Power Delivery For data Center GPUs 33

Optimizing Power and Power Delivery For Data Center GPUs

引用

33rd conference on Electrical Performance of Electronic Packaging and systems

作者： Rahal-Arabi, Tawfik Van der Arend, Paul Jain, Ashish Saidi, Mehdi Oreijeh, Rashad Sundaram, Sriram Seahra, R. O., I Adv Micro Devices Inc Santa Clara CA 95054 USA

ISBN: (纸本)9798350351248;9798350351231

GPUs are used in products from ultra-low power mobile devices to high performance machine learning accelerators in data centers. Across the products, power and power delivery have become top limiters to performance and are key considerations in the early stages of product definition and design. In particular, the power and power delivery problem has been significantly exacerbated with the recent trends in the growth of AI workloads. In this paper, we present some of the data centers driven power optimizations used in latest generation of AMD GPUs including the recently announced AMD Instinct (TM) MI300 GPU. To this end, we cover power and power delivery optimization techniques spanning the product life cycle from architecture, physical design, validation, test, and manufacturing with an eye on the challenges in the road ahead.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generation of Synthetic data to Improve Security Monitoring for Cyber-Physical Production systems 21

Generation of Synthetic Data to Improve Security Monitoring ...

引用

ieee 21st International conference on Industrial Informatics (INDIN)

作者： Specht, Felix Otto, Jens Ratz, Daniel Fraunhofer IOSB INA Campusallee 1 D-32657 Lemgo Germany

ISBN: (纸本)9781665493130

Machine learning based security monitoring can be used to detect cyberattacks and malfunctions in cyberphysical production systems. Acquiring real data sets for training machine learning algorithms is a problem due to high costs, low data quality, data diversity, and the violation of privacy policies. This paper introduces CyberSyn, a novel approach to generate synthetic data sets for machine learning based security monitoring systems. The generated data sets are analyzed using data quality metrics. Two scenarios from process manufacturing and industrial communication networks are used to evaluate the introduced approach. The proposed approach is able to generate synthetic data sets for both scenarios.

关键词： synthetic data sets industrial control systems machine learning cybersecurity cyber-physical production systems

来源：评论

学校读者我要写书评

暂无评论

SIGNEASE: AI-driven American Sign Language Interpretation System 5

SIGNEASE: AI-Driven American Sign Language Interpretation Sy...

引用

5th International conference on IoT Based control Networks and Intelligent systems, ICICNIS 2024

作者： Palanisamy, Mathiveendhan Mohanraj, Rameshkumar Karthikeyan, Akshatha Mohanraj, E. K.S.Rangasamy College of Technology Department of Artificial Intelligence and Data Science Tiruchengode India

ISBN: (纸本)9798331518097

Sign Language Recognition has grown to be increasingly important as a mean to improve the access and effective communication for the hearing impaired through Human Computer Interaction (HCI). This paper presents a hybrid approach, unifying deep learning with graph theory, that effectively recognizes sign language gestures in terms of recent state-of-the-art advances in artificial intelligence. Such being applied to a large dataset thus proves to yield quite noteworthy improvements both in terms of recognition accuracy and computational efficiency that can be gained. For these reasons, this method is established to be a competitive solution in the field. © 2024 ieee.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Model-Based Reinforcement learning via Stochastic Hybrid Models

IEEE OPEN JOURNAL OF CONTROL SYSTEMS

引用

ieee OPEN JOURNAL OF control systems 2023年 2卷 155-170页

作者： Abdulsamad, Hany Peters, Jan Aalto Univ Dept Elect Engn & Automat Espoo 02150 Finland Tech Univ Darmstadt Dept Comp Sci D-64289 Darmstadt Germany

Optimal control of general nonlinear systems is a central challenge in automation. Enabled by powerful function approximators, data-driven approaches to control have recently successfully tackled challenging applications. However, such methods often obscure the structure of dynamics and control behind black-box over-parameterized representations, thus limiting our ability to understand closed-loop behavior. This article adopts a hybrid-system view of nonlinear modeling and control that lends an explicit hierarchical structure to the problem and breaks down complex dynamics into simpler localized units. We consider a sequence modeling paradigm that captures the temporal structure of the data and derive an expectation-maximization (EM) algorithm that automatically decomposes nonlinear dynamics into stochastic piecewise affine models with nonlinear transition boundaries. Furthermore, we show that these time-series models naturally admit a closed-loop extension that we use to extract local polynomial feedback controllers from nonlinear experts via behavioral cloning. Finally, we introduce a novel hybrid relative entropy policy search (Hb-REPS) technique that incorporates the hierarchical nature of hybrid models and optimizes a set of time-invariant piecewise feedback controllers derived from a piecewise polynomial approximation of a global state-value function.

关键词： Hidden Markov models Switches Behavioral sciences Bayes methods Stochastic processes Nonlinear dynamical systems Reinforcement learning Bayesian inference behavioral cloning expectation-maximization hidden Markov models hybrid models piecewise feedback control reinforcement learning system identification

来源：评论

学校读者我要写书评

暂无评论

Proactive Content Caching via Interplay Between Deep learning and Stochastic Optimization 21

Proactive Content Caching via Interplay Between Deep Learnin...

引用

21st ieee International conference on Mobile Ad-Hoc and Smart systems (MASS)

作者： Park, Yongmoon Lee, Kyungtae Choi, Minseok Kim, Yeongjin Inha Univ Incheon South Korea Kyung Hee Univ Yongin South Korea

ISBN: (纸本)9798350363999;9798350364002

The increasing demand for video data traffic, along with the proliferation of smart devices, poses significant challenges to content and Internet service providers. In response to this challenge, content caching on mobile edge computing (MEC) servers has emerged to reduce content download latency. However, existing caching solutions often assume stationary content popularity or require real-time knowledge of popularity, which does not align with real-world scenarios. To address these limitations, we introduce ProCache, a novel content caching algorithm. ProCache takes into account spatial and temporal monetary budget sharing for caching, content sizes, and original server locations while dealing with uncertain regional content popularity. The goal of ProCache is to minimize the long-term expected content download latency overall active users, comprising two key components. First, the deep learning module includes the 1DCNN-LSTM-Dense layered deep learning model for predicting future content requests and the data mapping module which makes the model focus more on the request trend rather than the magnitude. Second, based on our predictions, the stochastic optimization module runs a dynamic content caching algorithm based on the Lyapunov optimization technique that operates in a fully distributed manner by region and ensures overall performance bounds. Trace-driven simulations using the YouTube dataset demonstrate that ProCache outperforms existing prediction models and content caching algorithms.

关键词： Content Caching Deep learning Edge computing Proactive caching Stochastic optimization

来源：评论

学校读者我要写书评

暂无评论

data-driven Predictive control and MPC: Do we achieve optimality? 20

Data-Driven Predictive Control and MPC: Do we achieve optima...

引用

20th IFAC Symposium on System Identification (SYSID)

作者： Anand, A. S. Sawant, S. Reinhardt, D. Gros, S. Norwegian Univ Sci & Technol NTNU Dept Engn Cybernet Trondheim Norway

In this paper, we explore the interplay between Predictive control and closed-loop optimality, spanning from Model Predictive control to data-driven Predictive control. Predictive control in general relies on some form of prediction scheme on the real system trajectories. However, these predictions may not accurately capture the real system dynamics, for e.g., due to stochasticity, resulting in sub-optimal control policies. This lack of optimality is a critical issue in case of problems with economic objectives. We address this by providing sufficient conditions on the underlying prediction scheme such that a Predictive controller can achieve closed-loop optimality. However, these conditions do not readily extend to data-driven Predictive control. In this context of closed-loop optimality, we conclude that the factor distinguishing the approaches within data-driven Predictive control is if they can be cast as a sequential decision-making process or not, rather than the dichotomy of model-based vs. model-free. Furthermore, we show that the conventional approach of improving the prediction accuracy from data may not guarantee optimality. Copyright (c) 2024 The Authors.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

data-driven Based Decoupled control Scheme for Interacting Quadruple Tank Process 12

Data-Driven Based Decoupled Control Scheme for Interacting Q...

引用

2024 12th International conference on systems and control, ICSC 2024

作者： Aal, Osama F. Abdel Hemeimat, Raghad University of California Merced Mechanical Eng. Dept. MercedCA94343 United States University of Jordan Amman Industrial Eng. Dept. Amman11942 Jordan

ISBN: (纸本)9798331531812

It is known that many industrial processes are multiple input multiple output (MIMO) in nature. The main challenge in controlling such processes is the interaction between the loops. In this article, the data-driven virtual reference feedback tuning method VRFT scheme has been applied to control a coupled quadruple tank process. Minimum/Non-minimum phase characteristics may appear based on the valve opening ratios. Simulation results are presented to assess the performance of the data-based tuned PID controllers. Maximum sensitivity is used as a robustness specification tool for the tuning method. Moreover, the gain margin and phase margin are used to asses the robustness of the VRFT based controller due to a plant gain variations. © 2024 ieee.

关键词： MIMO systems

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：