检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Web Services, ICWS 2023

作者： Xu, Xiaofei Sheng, Quan Z. Benatallah, Boualem Chen, Zhong Gazda, Robert Saddik, Abdulmotableb Ei Singh, Munindar P. Faculty of Computing Harbin Institute of Technology China Macquarie University School of Computing NSW2109 Australia Dublin City University School of Computing Ireland Peking University School of Computer Science China Wireless Networking Lab Interdigital United States University of Ottawa School of Electrical Engineering and Computer Science Canada North Carolina State University Department of Computer Science United States

ISBN: (纸本)9798350304855

With the emergence of new generation of digital technologies, e.g., artificial intelligence, blockchain, cloud computing, big data, edge computing, 5G/6G, VR/AR/MR, and the Internet of Things, an exciting era of metaverse is coming. Interacted and linked with the physical world, metaverse offers a platform of a new social ecosystem, dealing with digital twins and empowering virtual-reality symbiosis. In metaverse, social activities and business processes are performed based on the sequences of workflow or service processes. Bridging both the virtual space and the real world, such metaverse services are more complicated and present many new challenges and research topics. In this paper, the concept and characteristics of metaverse services are presented, the key technologies and typical use cases are reviewed, and the future challenges and opportunities of metaverse services are also discussed. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics 38

Probabilistic Decomposed Linear Dynamical Systems for Robust...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Chen, Yenho Mudrik, Noga Johnsen, Kyle A. Alagapan, Sankaraleengam Charles, Adam S. Rozell, Christopher J. Machine Learning Center Georgia Institute of Technology United States School of Electrical and Computer Engineering Georgia Institute of Technology United States Coulter Dept. of Biomedical Engineering Emory University Georgia Institute of Technology United States Department of Biomedical Engineering Mathematical Institute for Data Science Center for Imaging Science Kavli Neuroscience Discovery Institute Johns Hopkins University United States

Time-varying linear state-space models are powerful tools for obtaining mathematically interpretable representations of neural signals. For example, switching and decomposed models describe complex systems using latent variables that evolve according to simple locally linear dynamics. However, existing methods for latent variable estimation are not robust to dynamical noise and system nonlinearity due to noise-sensitive inference procedures and limited model formulations. This can lead to inconsistent results on signals with similar dynamics, limiting the model's ability to provide scientific insight. In this work, we address these limitations and propose a probabilistic approach to latent variable estimation in decomposed models that improves robustness against dynamical noise. Additionally, we introduce an extended latent dynamics model to improve robustness against system nonlinearities. We evaluate our approach on several synthetic dynamical systems, including an empirically-derived brain-computer interface experiment, and demonstrate more accurate latent variable inference in nonlinear systems with diverse noise conditions. Furthermore, we apply our method to a real-world clinical neurophysiology dataset, illustrating the ability to identify interpretable and coherent structure where previous models cannot. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Salient Region Detection in Images Based on U-Net and Deep Learning 2

Salient Region Detection in Images Based on U-Net and Deep L...

引用

2nd IEEE International Conference on Advanced Technologies in Intelligent Control, Environment, computing and Communication engineering, ICATIECE 2022

作者： Kumar, Krishna Marimuthu, M. Das Gupta, Ayan Pant, Bhasker Shukla, Surendra Kumar Kapila, Dhiraj Bansal Institute of Engineering and Technology Department of Computer Science and Engineering Lucknow India Coimbatore Institute of Technology Department of Computing-Data Science Coimbatore India Chandernagore Government College Department of Geography Hugli India Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India Lovely Professional University Department of Computer Science and Engineering Phagwara India

ISBN: (纸本)9781665493963

Image analysis tasks use salient object detection because it not only identifies important elements of a visual scene but also lessens computational complexity by removing unimportant elements. In this research, we propose a novel salient object recognition method based on a deep learning network that maintains picture information in the mid and low regions. Using a deep learning model, our technique generates a coarse saliency map for the entire target image. The map is then fine-Tuned utilising low-To-mid level information particular to the image. For detection of salient objects, we use a U-Net as our architecture. The saliency map can be predicted pixel by pixel, reducing low-level visual information loss. Our results show that our system regularly outperforms other approaches for detecting salient objects, resulting in superior precision and recall rates. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent System Based data Mining Technique for Supplier Selection

Multi-Agent System Based Data Mining Technique for Supplier ...

引用

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Dhatterwal, Jagjit Singh Kaswan, Kuldeep Singh Singh, Jay Naruka, Mahaveer Singh Govardhan, D. Artificial Intelligence and Data Science Koneru Lakshmaiah Education Foundation AP Guntur India School of Computing Science and Engineering Galgotias University UP Greater Noida India G L Bajaj Institute of Technology and Management Department of Electrical and Electronics Engineering Greater Noida India Institute of Aeronautical Engineering Department of Aeronautical Engineering Hyderabad India

ISBN: (纸本)9798350357769

Different target knowledge representations, which correspond to different hypothesis spaces, are suitable for learning various types of target functions. A distinct learning algorithm, capitalizing on an underlying structure to guide the exploration of the hypothesis space, leverages each of these hypothesis representations. Consequently, making decisions on these matters entails navigating an expansive landscape of alternative approaches to determine the one that best aligns with the defined learning problem. To select an appropriate learning algorithm that performs optimally for the given problem and target function, it is essential to analyze the interplay between the size and completeness of the hypothesis space, the availability of training examples, the learner's prior knowledge, and the confidence in a hypothesis's ability to generalize correctly to unseen data points. This challenge often arises in the context of poorly integrated systems. The objective of this paper is to introduce a specific approach to addressing these challenges, involving the use of enhanced elicitation techniques and tools, improved development paradigms, knowledge modeling languages, ontologies, and advanced methods for system maintenance. However, in the past decade, an alternative reasoning paradigm and computational problem-solving approach have garnered significant attention, involving the use of Multi-Agent System (MAS) based data Mining (DM) techniques. This paper proposes the integration of MAS and DM for supplier selection, with a focus on partitioning-based algorithms such as K-means, Farthest First, Expectation Maximization, and Filtered Clusterer. These algorithms are compared based on factors such as dataset size, the number of clusters, and the time required for cluster formation. Finally, within this integrated model, MAS-DM is exemplified through an illustrative result-matching process. © 2023 IEEE.

关键词： Cluster data Mining JADE Multi-Agent Ontologies

来源：评论

学校读者我要写书评

暂无评论

Successive Pose Estimation and Beam Tracking for mmWave Vehicular Communication Systems

Successive Pose Estimation and Beam Tracking for mmWave Vehi...

引用

2023 IEEE Globecom Workshops, GC Wkshps 2023

作者： Liu, Cen Zhu, Guangxu Liu, Fan Liu, Yuanwei Huang, Kaibin National University of Singapore Department of Electrical and Computer Engineering Singapore Shenzhen Research Institute of Big Data Shenzhen China Peng Cheng Laboratory Shenzhen China Guangzhou China Southern University of Science and Technology Department of Electronic and Electrical Engineering Shenzhen China School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom The University of Hong Kong Department of Electrical and Electronic Engineering Hong Kong

ISBN: (纸本)9798350370218

The millimeter wave (mmWave) radar sensing-aided communications in vehicular mobile communication systems is investigated. To alleviate the beam training overhead under high mobility scenarios, a successive pose estimation and beam tracking (SPEBT) scheme is proposed to facilitate mmWave communications with the assistance of mmWave radar sensing. The proposed SPEBT scheme first resorts to a Fast Conservative Filtering for Efficient and Accurate Radar odometry (Fast-CFEAR) approach to estimate the vehicle pose consisting of 2-dimensional position and yaw from radar point clouds collected by mmWave radar sensor. Then, the pose estimation information is fed into an extend Kalman filter to perform beam tracking for the line-of-sight channel. Owing to the intrinsic robustness of mmWave radar sensing, the proposed SPEBT scheme is capable of operating reliably under extreme weather/illumination conditions and large-scale global navigation satellite systems (GNSS)-denied environments. The practical deployment of the SPEBT scheme is verified through rigorous testing on a real-world sensing dataset. Simulation results demonstrate that the proposed SPEBT scheme is capable of providing precise pose estimation information and accurate beam tracking output, while reducing the proportion of beam training overhead to less than 5% averagely. © 2023 IEEE.

关键词： beam tracking extended Kalman filter millimeter wave pose estimation radar odometry Sensing-aided communications

来源：评论

学校读者我要写书评

暂无评论

Large Language Models as Evolutionary Optimizers 13

Large Language Models as Evolutionary Optimizers

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Liu, Shengcai Chen, Caishun Qu, Xinghua Tang, Ke Ong, Yew-Soon Southern University of Science and Technology Centre for Frontier Ai Research A∗star Department of Computer Science and Engineering China Centre for Frontier Ai Research A∗star Singapore Tianqiao & Chrissy Chen Institute China Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering China Nanyang Technological University Centre for Frontier Ai Research A∗star College of Computing and Data Science Singapore

ISBN: (纸本)9798350308365

Evolutionary algorithms (EAs) have achieved remarkable success in tackling complex combinatorial optimization problems. However, EAs often demand carefully-designed operators with the aid of domain expertise to achieve satisfactory performance. In this work, we present the first study on large language models (LLMs) as evolutionary combinatorial optimizers. The main advantage is that it requires minimal domain knowledge and human efforts, as well as no additional training of the model. This approach is referred to as LLM-driven EA (LMEA). Specifically, in each generation of the evolutionary search, LMEA instructs the LLM to select parent solutions from current population, and perform crossover and mutation to generate offspring solutions. Then, LMEA evaluates these new solutions and include them into the population for the next generation. LMEA is equipped with a self-adaptation mechanism that controls the temperature of the LLM. This enables it to balance between exploration and exploitation and prevents the search from getting stuck in local optima. We investigate the power of LMEA on the classical traveling salesman problems (TSPs) widely used in combinatorial optimization research. Notably, the results show that LMEA performs competitively to traditional heuristics in finding high-quality solutions on TSP instances with up to 20 nodes. Additionally, we also study the effectiveness of LLM-driven crossover/mutation and the self- adaptation mechanism in evolutionary search. In summary, our results reveal the great potentials of LLMs as evolutionary optimizers for solving combinatorial problems. We hope our research shall inspire future explorations on LLM-driven EAs for complex optimization challenges. © 2024 IEEE.

关键词： Traveling salesman problem

来源：评论

学校读者我要写书评

暂无评论

Plant Disease Classification Using VGG-19 Based Faster-RCNN 7th

Plant Disease Classification Using VGG-19 Based Faster-RCNN

引用

Proceedings of the 7th International Conference on Advances in computing and data sciences, ICACDS 2023

作者： Nawaz, Marriam Nazir, Tahira Khan, Muhammad Attique Rajinikanth, Venkatesan Kadry, Seifedine Department of Software Engineering University of Engineering and Technology Taxila Taxila47050 Pakistan Faculty of Computing Department of Computer Science Riphah International University Gulberg Green Campus Islamabad Pakistan Department of Computer Science HITEC University Taxila Pakistan Department of Computer Science and Engineering Division of Research and Innovation Saveetha School of Engineering SIMATS Chennai602105 India Department of Applied Data Science Noroff University College Kristiansand4612 Norway Ajman University Ajman346 United Arab Emirates Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon

ISBN: (纸本)9783031379390

Early plant disease diagnosis can help farmers avoid spending money on costly crop pesticides and aid them to boost food production. Scientists have put a lot of effort to classify plant diseases, but it is difficult to quickly locate and identify different crop abnormalities due to the high degree of resemblance between the normal and damaged parts of plant leaves. Additionally, the procedure of detecting plant diseases has been made more challenging due to the extensive color, size, shape, and intensity variations in the background and foreground of the plant images. To address the existing difficulties, we have introduced an effective deep learning (DL) based system called Faster-RCNN o recognize and classify various types of plant diseases. The suggested method consists of 3 basic steps. In order to identify the area of interest in investigated samples, we first create annotations for them which are later used for Faster-RCNN training. The Faster-RCNN model employs the VGG-19 network to extract the relevant keypoints from the given images which are later passed to the regressor and classification units to identify and categorize the various crop diseases using the estimated features. We evaluated our method on a widely used standard plant sample repository called the PlantVillage database, and the findings show that our approach is reliable for classifying plant diseases under a variety of image-capturing scenarios. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

On the System Performance of Mobile Edge computing in an Uplink NOMA WSN With a Multiantenna Access Point Over Nakagami-m Fading

引用

IEEE/CAA Journal of Automatica Sinica 2022年第4期9卷 668-685页

作者： Van-Truong Truong Van Nhan Vo Dac-Binh Ha Chakchai So-In the Faculty of Electrical-Electronic Engineering Duy Tan University the Institute of Research and Development Duy Tan University the Faculty of Information Technology Duy Tan University IEEE the Applied Network Technology(ANT)Laboratory Department of Computer ScienceCollege of ComputingKhon Kaen University

In this paper,we study the system performance of mobile edge computing(MEC)wireless sensor networks(WSNs)using a multiantenna access point(AP)and two sensor clusters based on uplink nonorthogonal multiple access(NOMA).Due to limited computation and energy resources,the cluster heads(CHs)offload their tasks to a multiantenna AP over Nakagami-m *** proposed a combination protocol for NOMA-MEC-WSNs in which the AP selects either selection combining(SC)or maximal ratio combining(MRC)and each cluster selects a CH to participate in the communication process by employing the sensor node(SN)*** derive the closed-form exact expressions of the successful computation probability(SCP)to evaluate the system performance with the latency and energy consumption constraints of the considered *** results are provided to gain insight into the system performance in terms of the SCP based on system parameters such as the number of AP antennas,number of SNs in each cluster,task length,working frequency,offloading ratio,and transmit power ***,to determine the optimal resource parameters,i.e.,the offloading ratio,power allocation of the two CHs,and MEC AP resources,we proposed two algorithms to achieve the best system *** approach reveals that the optimal parameters with different schemes significantly improve SCP compared to other similar *** use Monte Carlo simulations to confirm the validity of our analysis.

关键词： Mobile edge computing(MEC) Nakagami-m fading offloading selection combining(SC)/maximal ratio combining(MRC) successful computation probability(SCP) uplink nonortho-gonal multiple access(NOMA) wireless sensor networks(WSNs)

来源：评论

学校读者我要写书评

暂无评论

Principled penalty-based methods for bilevel reinforcement learning and RLHF 24

Principled penalty-based methods for bilevel reinforcement l...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Han Shen Zhuoran Yang Tianyi Chen Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute Department of Statistics and Data Science Yale University

Bilevel optimization has been recently applied to many machine learning tasks. However, their applications have been restricted to the supervised learning setting, where static objective functions with benign structures are considered. But bilevel problems such as incentive design, inverse reinforcement learning (RL), and RL from human feedback (RLHF) are often modeled as dynamic objective functions that go beyond the simple static objective structures, which pose significant challenges of using existing bilevel solutions. To tackle this new class of bilevel problems, we introduce the first principled algorithmic framework for solving bilevel RL problems through the lens of penalty formulation. We provide theoretical studies of the problem landscape and its penalty-based (policy) gradient algorithms. We demonstrate the effectiveness of our algorithms via simulations in the Stackelberg game and RLHF.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced Multidimensional Harmonic Retrieval in MIMO Wireless Channel Sounding

引用

IEEE Internet of Things Journal 2025年第11期12卷 16243-16255页

作者： Zhang, Yanming Xu, Wenchao Jin, A-Long Tang, Tianquan Li, Min Ma, Peifeng Jiang, Lijun Gao, Steven The Chinese University of Hong Kong Department of Electronic Engineering Hong Kong Hong Kong The Hong Kong Polytechnic University Department of Computing Hong Kong Xi’an Jiaotong-Liverpool University Department of Communications and Networking Suzhou215123 China HKU Zhejiang Institute of Research and Innovation Lab for Aerodynamics and Acoustics Hangzhou311305 China Tianjin University School of Microelectronics Tianjin300000 China Institute of Space and Earth Information Science The Chinese University of Hong Kong Department of Geography and Resource Management Hong Kong Missouri University of Science and Technology Department of Electrical and Computer Engineering RollaMO65409 United States

This article introduces a recursive parallel dynamic mode decomposition (RPDMD) scheme tailored for multidimensional harmonic retrieval (MHR), specifically applied to MIMO wireless channel sounding. The RPDMD algorithm is devised to address the complexities inherent in multidimensional scenarios, leveraging the dynamic mode decomposition (DMD) framework within a recursive parallel structure. Initially, the observed tensorial multidimensional harmonic data is transformed into a 2-D matrix format along the rth dimension. Subsequently, DMD dissects this matrix data into eigenvalues and their associated modes. The real and imaginary components of the DMD eigenvalues yield damping factors and frequencies in the rth dimension, respectively. Furthermore, recursive DMD is employed to scrutinize each mode independently for parameter retrieval across the remaining dimensions, enabling parallel analysis. Ultimately, this high-dimensional correlated decomposition scheme delivers paired damping factors and frequencies for all tones. Notably, the proposed approach can ascertain the number of tones in undamped sinusoidal signals, making it particularly suitable for MHR even without prior knowledge of the source count. Numerical experiments demonstrate the accuracy and robustness of the RPDMD scheme, with comparative analysis indicating that RPDMD outperforms similar methods, achieving optimal results with minimal mean square error in high signal-to-noise ratio scenarios. This work presents an effective data-driven solution for the MHR problem in MIMO wireless channel sounding. © 2014 IEEE.

关键词： Eigenvalues and eigenfunctions

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：