检索结果-内蒙古大学图书馆

IEEE International Conference on Communications (ICC)

作者： Xi Zhang Qixuan Zhu Department of Electrical and Computer Engineering Networking and Information Systems Laboratory Texas A&M University College Station TX USA

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

To satisfy the stringent quality-of-service (QoS) requirements of 6G mobile wireless networks on both channel state estimations and information transmissions, the integrated sensing and communication (ISAC) has been an enabling technique to sense and communicate by sharing the same frequency band and hardware. Simultaneous wireless information and power transfer (SWIPT) has also emerged to simultaneously deliver information and energy to a receiver. However, how to integrate ISAC with SWIPT to support the 6G traffic has imposed many new challenges not encountered before. To conquer these difficulties, in this paper we propose an integrated sensing, communications, and powering (ISACP) scheme for supporting statistical-QoS provisioning over 6G wireless networks using massive multiple-input and multiple-output (massive MIMO) communications. First, we establish system models for our ISACP scheme and define the Cramér-Rao bound and channel estimation distortion under our proposed ISACP scheme. Second, we develop the performance metrics of Cramér-Rao bound and channel estimation distortion to derive the capacity-distortion function to jointly measure the performance of integrated sensing, communication, and powering. Third, we integrate the capacity-distortion function with the finite blocklength coding (FBC) through deriving the ISACP-based ϵ-effective capacity to support the statistical delay and error-rate bounded QoS provisioning in 6G. Fourth, we maximize the energy-efficiency by controlling the optimal wireless power transfer for our ISACP scheme. Finally, we use numerical analyses to validate and evaluate our proposed ISACP scheme.

关键词： 6G mobile communication Wireless sensor networks Wireless networks Channel estimation Quality of service Integrated sensing and communication Distortion

来源：评论

学校读者我要写书评

暂无评论

Neuromimetic Dynamic Networks with Hebbian Learning

arXiv

引用

arXiv 2023年

作者： Sun, Zexin Baillieul, John The Division of Systems Engineering Boston University BostonMA02215 United States The Departments of Mechanical Engineering Electrical and Computer Engineering The Division of Systems Engineering Boston University BostonMA02215 United States

Leveraging recent advances in neuroscience and control theory, this paper presents a neuromimetic network model with dynamic symmetric connections governed by Hebbian learning rules. Formal analysis grounded in graph theory and classical control establishes that this biologically plausible model exhibits boundedness, stability, and structural controllability given a generalized sym-cactus structure with multiple control nodes. We prove the necessity of this topology when there are distributed control inputs. Simulations using a 14-node generalized sym-cactus network with two input types validate the model’s effectiveness in capturing key neural dynamics. © 2023, CC BY-NC-SA.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Gradual domain adaptation via manifold-constrained distributionally robust optimization 24

Gradual domain adaptation via manifold-constrained distribut...

引用

Proceedings of the 38th International Conference on Neural information Processing systems

作者： Amirhossein Saberi Amir Najafi Amin Behjati Ala Emrani Yasaman Zolfi Mahdi Shadrooy Abolfazl Motahari Babak H. Khalaj Department of Electrical Engineering and Sharif Center for Information Systems and Data Science Sharif University of Technology Tehran Iran Department of Computer Engineering Sharif University of Technology Tehran Iran

ISBN: (纸本)9798331314385

The aim of this paper is to address the challenge of gradual domain adaptation within a class of manifold-constrained data distributions. In particular, we consider a sequence of T ≥ 2 data distributions P1, ..., PT undergoing a gradual shift, where each pair of consecutive measures Pi, Pi+1 are close to each other in Wasserstein distance. We have a supervised dataset of size n sampled from P0, while for the subsequent distributions in the sequence, only unlabeled i.i.d. samples are available. Moreover, we assume that all distributions exhibit a known favorable attribute, such as (but not limited to) having intra-class soft/hard margins. In this context, we propose a methodology rooted in Distributionally Robust Optimization (DRO) with an adaptive Wasserstein radius. We theoretically show that this method guarantees the classification error across all Pis can be suitably bounded. Our bounds rely on a newly introduced compatibility measure, which fully characterizes the error propagation dynamics along the sequence. Specifically, for inadequately constrained distributions, the error can exponentially escalate as we progress through the gradual shifts. Conversely, for appropriately constrained distributions, the error can be demonstrated to be linear or even entirely eradicated. We have substantiated our theoretical findings through several experimental results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards an ultrafast 3D imaging scanning LiDAR system:a review

引用

Photonics Research 2024年第8期12卷 1709-1729页

作者： ZHI LI YAQI HAN LICAN WU ZIHAN ZANG MAOLIN DAI SZE YUN SET SHINJI YAMASHITA QIAN LI H.Y.FU Tsinghua Shenzhen International Graduate School Tsinghua UniversityShenzhen 518055China Department of Electrical Engineering and Information Systems The University of TokyoTokyo 113-8656Japan Research Center for Advanced Science and Technology The University of TokyoTokyo 153-8904Japan School of Electronic and Computer Engineering Peking UniversityShenzhen 518055China

Light detection and ranging(LiDAR),as a hot imaging technology in both industry and academia,has undergone rapid innovation and *** current mainstream direction is towards system miniaturization and *** are many metrics that can be used to evaluate the performance of a LiDAR system,such as lateral resolution,ranging accuracy,stability,size,and *** recently,with the continuous enrichment of LiDAR application scenarios,the pursuit of imaging speed has attracted tremendous research ***,for autonomous vehicles running on motorways or industrial automation applications,the imaging speed of LiDAR systems is a critical *** this review,we will focus on discussing the upper speed limit of the LiDAR *** on the working mechanism,the limitation of optical parts on the maximum imaging speed is *** beam scanner has the greatest impact on imaging *** provide the working principle of current popular beam scanners used in LiDAR systems and summarize the main constraints on the scanning ***,we highlight the spectral scanning LiDAR as a new paradigm of ultrafast ***,to further improve the imaging speed,we then review the parallel detection methods,which include multiple-detector schemes and multiplexing ***,we summarize the LiDAR systems with the fastest point acquisition rate reported *** the outlook,we address the current technical challenges for ultrafast LiDAR systems from different aspects and give a brief analysis of the feasibility of different approaches.

关键词： LiDAR scanner system

来源：评论

学校读者我要写书评

暂无评论

Predictive Analytics for Business Decision-Making: Unleashing the Power of Data-driven Insights

Predictive Analytics for Business Decision-Making: Unleashin...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Nourin Nishat Mithila Mehedi Saidur Rashid Muniroopesh Raasetti Department of Management Information Systems Lamar University Texas USA Department of Electrical and Computer Engineering Rajshahi University of Engineering and Technology Rajshahi Bangladesh Department of Electrical and Electronics Engineering Lamar University Texas USA Department of Electrical Engineering Lamar University Texas USA

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

This study examines how Predictive Analytics may alter company decision-making by employing sophisticated data-driven insights to improve strategic decisions. The report examines predictive analytics’ methods, algorithms, and applications, showing how it has transformed industry decision-making. Predictive Analytics’ ability to anticipate future trends, recognize patterns, and generate accurate forecasts based on previous data is examined in corporate operations. The paper uses case studies and practical examples to show how predictive models enhance risk management, resource efficiency, and strategic planning. Business decision-making is explored in relation to predictive analytics components including machine learning algorithms, statistical modeling, and data mining. The study highlights predictive analytics’ benefits in sales forecasting, consumer behavior research, and market trend projections. The study also examines the social and economic effects of corporate predictive analytics. It examines how data-driven decision-making boosts competitiveness, innovation, and economic development, serving national interests. For a balanced and transparent deployment, ethics, data privacy, and predictive analytics are considered. This study shows how predictive analytics can help firms make smart decisions in an age of unparalleled data availability. The study shares successful applications and addresses problems to help business professionals, analysts, and researchers navigate datadriven business strategies.

关键词： Technological innovation Accuracy Decision making Urban areas Companies Predictive models Strategic planning Market research Risk management Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

RFC-Net: Learning High Resolution Global Features for Medical Image Segmentation on a Computational Budget 37

RFC-Net: Learning High Resolution Global Features for Medica...

引用

37th AAAI Conference on Artificial Intelligence, AAAI 2023

作者： Saha, Sourajit Saha, Shaswati Gani, Md Osman Oates, Tim Chapman, David Department of Computer Science and Electrical Engineering University of Maryland Baltimore CountyMD21250 United States Department of Information Systems University of Maryland Baltimore CountyMD21250 United States Department of Computer Science University of Miami FL33124 United States

ISBN: (纸本)9781577358800

Learning High-Resolution representations is essential for semantic segmentation. Convolutional neural network (CNN) architectures with downstream and upstream propagation flow are popular for segmentation in medical diagnosis. However, due to performing spatial downsampling and upsampling in multiple stages, information loss is inexorable. On the contrary, connecting layers densely on high spatial resolution is computationally expensive. In this work, we devise a Loose Dense Connection Strategy to connect neurons in subsequent layers with reduced parameters. On top of that, using a m-way Tree structure for feature propagation we propose Receptive Field Chain Network (RFC-Net) that learns high-resolution global features on a compressed computational space. Our experiments demonstrates that RFC-Net achieves state-of-the-art performance on Kvasir and CVC-ClinicDB benchmarks for Polyp segmentation. Our code is publicly available at ***/sourajitcs/RFC-NetAAAI23. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Machine Learning and Optimization Approaches for Dissolved Oxygen Prediction in River systems

Machine Learning and Optimization Approaches for Dissolved O...

引用

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Hazem Alnajjar Nadia Al-Rousan Douaa Al-Rouan Department of Computer Science College of Information Technology University of Petra Amman Jordan Department of computer engineering College of Engineering AlBalqa Applied University Salt Jordan Department of Computer Engineering Faculty of Electrical Engineering and Information Systems German Jordanian University Amman Jordan School of Civil Engineering Universiti Sains Malaysia Nibong Tebal Pulau Pinang MALAYSIA

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

This study aims to combine optimization algorithms of feature selection and machine learning models for DO prediction at a water monitoring station. The dataset consisted of water quality indicators from three stations, whose DO was the target variable at the third station. This study used seven optimization algorithms to select the most relevant features. The selected features were then used along with ten machine-learning models for building predictive models. Several models were evaluated based on R 2 , MAE, and MSE metrics. Hence, Gradient Boosting and Random Forest models yielded better prediction results. The results showed high accuracy, reflected by the values of R 2 , which were 0.987 and 0.922 for the training data and 0.769 and 0.745 for the test data, respectively. The findings underscore the effectiveness of combining feature selection with optimized machine learning models for accurate DO prediction, which is essential for monitoring water quality.

关键词： Machine learning algorithms Biological system modeling Water quality Predictive models Prediction algorithms Feature extraction Rivers Water monitoring Optimization Random forests

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Robust Optimization Under Decision Dependent Uncertainty

引用

IEEE/CAA Journal of Automatica Sinica 2022年第7期9卷 1295-1306页

作者： Yunfan Zhang Feng Liu Yifan Su Yue Chen Zhaojian Wang João P.S.Catalão State Key Laboratory of Power System and Generation Equipment the Department of Electrical EngineeringTsinghua UniversityBeijing 100084China Department of Mechanical and Automation Engineering the Chinese University of Hong KongHong Kong SARChina Ministry of Education Key Laboratory of System Control and Information Processing the Department of AutomationShanghai Jiao Tong Universityand also with Shanghai Engineering Research Center of Intelligent Control and ManagementShanghai 200240China Faculty of Engineering of the University of Porto and Institute for Systems and Computer Engineering Technology and Science(INESC TEC)Porto 4200-465Portugal IEEE

In the conventional robust optimization(RO)context,the uncertainty is regarded as residing in a predetermined and fixed uncertainty *** many applications,however,uncertainties are affected by decisions,making the current RO framework *** paper investigates a class of two-stage RO problems that involve decision-dependent *** introduce a class of polyhedral uncertainty sets whose right-hand-side vector has a dependency on the here-and-now decisions and seek to derive the exact optimal wait-and-see decisions for the second-stage problem.A novel iterative algorithm based on the Benders dual decomposition is proposed where advanced optimality cuts and feasibility cuts are designed to incorporate the uncertainty-decision *** computational tractability,robust feasibility and optimality,and convergence performance of the proposed algorithm are guaranteed with theoretical *** motivating application examples that feature the decision-dependent uncertainties are ***,the proposed solution methodology is verified by conducting case studies on the pre-disaster highway investment problem.

关键词： Benders decomposition decision-dependent uncertainty endogenous uncertainty robust optimization(RO)

来源：评论

学校读者我要写书评

暂无评论

Adaptive Deep Reinforcement Learning-based Resource Management for Complex Decision Making in Industry Internet of Things Applications 4

Adaptive Deep Reinforcement Learning-based Resource Manageme...

引用

4th International Conference on Evolutionary Computing and Mobile Sustainable Networks, ICECMSN 2024

作者： Karne, Niharika Ramagundam, Chandra Shekar Patnala, Ranga Rao Ramagundam, Shashishekhar Tadiboina, Sai Nitisha Sr. Principal Systems Engineer in C&RS Platform Services University of South Alabama Department of Electrical Engineering Masters in Electrical Engineering Amtrak DT United States Software Engineer in Cloud Platform Services City of Philadelphia Pennsylvania United States Vice President Neuberger Berman United States Software Development & Engineering in Content Discovery & AI Troy University Department of Computer Science Masters in Computer Science AL Comcast Montgomery Campus United States Department of Information Technology GEICO - Chevy Chase Chevy ChaseMD20815 United States

An independent industrial system may transform into a connected network through the assistance of Industrial Internet of Things (IIoT). The deployed sensors in the IIoT maintain surveillance of the industrial machinery and equipment. As a result, safety and reliability emerge as the primary concerns in IIoT. This presents a variety of well-known and increasing issues related to the industrial system. The IIoT devices are exposed to a wide range of malware, threats, and assaults. To prevent the IIoT devices from malware effects, effective protection plans must be implemented. But adequate security mechanisms are not be incorporated in IIoT devices with limited resources. It is essential to ensure the accuracy and dependability of information gathered by IIoT devices. Decisions taken with incomplete or inaccurate data might be devastating. To overcome these difficulties deep learning with reinforcement learning for complex decision-making in industry applications is developed in this research work. In this developed model, an Adaptive Deep Reinforcement learning (ADRL)-based resource management is performed to reduce the operation cost associated with IIoT deployments. Energy efficiency is essential in IIoT ecosystem, particularly for the devices that run on batteries. Through dynamic resource allocation based on workload needs and energy limits, ADRL-based resource management optimizes the usage of energy. The reliability of the designed model is enhanced by fine-tuning the parameters from DRL using the Ship Rescue Optimization (SRO) algorithm. Thus, ADRL-based resource management systems make real-time decisions based on current environmental conditions and system requirements. This helps the IIoT systems to react quickly to change demands and optimize resource allocation. Finally, the experimental analysis is performed to find the success rate of the developed resource management system via various metrics. Throughout the validation, the statistical analysis of the

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Detecting Hallucinations in Large Language Models Using Machine Learning Classifiers: A Comparative Study

Detecting Hallucinations in Large Language Models Using Mach...

引用

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Hazem Al-Najjar Nadia Al-Rousan Douaa Al-Rousan Department of Computer Science College of Information Technology University of Petra Amman Jordan Department of computer engineering College of Engineering AIBalqa Applied University Salt Jordan Department of Computer Engineering Faculty of Electrical Engineering and Information Systems German Jordanian University Amman Jordan School of Civil Engineering Universiti Sains Malaysia Nibong Tebal Pulau Pinang Malaysia

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

This study is concerned with the comprehensive evaluation of machine learning models intended for the detection of hallucination in Large Language Model output. The preprocessing of the prompt and answers using TF-IDF vectorization has been done as a preliminary step before developing a hallucination prediction model. Afterwards, the generated dataset was then divided into training and testing, with percentages equal to 70% and 30%, respectively. The selected machine learning models were trained with the dataset created. In this research, eight various classifiers are implemented and compared. To evaluate the results of our approach, multiple metrics were taken into consideration: accuracy, precision, recall, and Fl-score. While the training results showed exceptional performance with accuracies exceeding 99% in several models, the test results indicated huge challenges in generalization. Random Forest had the highest testing accuracy of 94.77% at 65% precision but with a very low recall of 4.85%. Besides, cross validation is used with random forest and decision tree, the results showed that the cross-validation is better than the test and train splitting model. The study shows the significant trade-offs between precision and recall in hallucination detection, which is especially problematic while working with imbalanced datasets.

关键词： Training Measurement Accuracy Large language models Computational modeling Predictive models Decision trees Random forests Computational intelligence Testing

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：