检索结果-内蒙古大学图书馆

Motion path planning method based on map reference points

Multimedia Tools and Applications 2024年 1-21页

作者： Yu, Wenbin Fan, Cheng Zhang, Chengjun Chen, Yadang Li, Yangsong Zhang, Yifan Yin, Na Cen, Xiaolin School of Software Nanjing University of Information Science and Technology Jiangsu Nanjing210044 China School of Computer Science Nanjing University of Information Science and Technology Jiangsu Nanjing210044 China Wuxi Institute of Technology Nanjing University of Information Science and Technology Jiangsu Wuxi214000 China Nanjing University of Information Science and Technology Jiangsu Nanjing210044 China School of Computer Science Northeastern University Boston02101 United States Computer Science and Engineering The University of New South Wales SydneyNSW02101 Australia

In recent years, significant progress has been made in the development of the Rapidly-exploring Random Trees (RRT) algorithm, a probabilistic sampling-based search approach. This algorithm effectively addresses complex challenges in path planning within high-dimensional spaces characterized by intricate constraints. However, the RRT algorithm faces certain limitations, including sluggish computational performance in handling intricate calculations, susceptibility to becoming trapped in confined path regions, and difficulties in generating randomized paths across a given map. To overcome these issues, this study introduces a motion path planning method based on map reference points. Initially, the algorithm selects strategic map reference points, followed by the utilization of an enhanced RRT algorithm for fundamental path selection. Real-world scenario data is collected to empirically evaluate the algorithm’s performance. The outcomes of the experiments reveal that, within the same experimental setting, the proposed method outperforms conventional motion path planning algorithms by effectively circumventing obstacles. Furthermore, it substantially reduces the resource wastage caused by global random sampling in the RRT algorithm, leading to expedited path planning and improved pathfinding success rates. Additionally, the proposed approach enhances the RRT algorithm’s adaptability to some extent, particularly in negotiating narrow passages and intricate environments. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

A Domain-Adaptive Large Language Model With Refinement Framework For IoT Cybersecurity 17

A Domain-Adaptive Large Language Model With Refinement Frame...

引用

IEEE Congress on Cybermatics: 17th IEEE International Conference on Internet of Things, iThings 2024, 20th IEEE International Conference on Green Computing and Communications, GreenCom 2024, 17th IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2024, 10th IEEE International Conference on Smart Data, SmartData 2024

作者： Che, Xun Zheng, Yu Zhu, Minhao Li, Qianmu Dong, Xu Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China Nari Group Corporation Nanjing China Nanjing University of Science and Technology School of Cyber Science and Engineering Nanjing China

ISBN: (纸本)9798350351637

To address the increasingly complex security challenges in Internet-of-Things (IoT) environments, Large Language Models (LLMs) have demonstrated effectiveness in enhancing device and data security, as well as improving the security and reliability overall IoT system. However, general LLMs struggle to effectively handle IoT security data. Therefore, developing IoT security domain-specific LLMs based on IoT-specific corpus and terminologies has become a key focus for enhancing cybersecurity defense capabilities. These areas of focus can be broadly categorized into three main directions: training from scratch, retrieval-augmented prompting, and instruction fine-tuning. Training from scratch is discouraged in cybersecurity due to its high computational and data requirements, making effective model training and convergence difficult given the scarcity of cybersecurity data. Retrieval-augmented prompting may suffer from incomplete or conflicting information, impacting the accuracy and reliability of the model. Conversely, instruction fine-tuning allows for the usage of domain-specific task instructions to adjust the model, achieving effective domain adaptation on limited datasets. However, inadequate or inaccurate instructions may degrade the generalization ability and performance. For these shortcomings, we propose a novel and robust fine-tuning framework to refine the original corpus and output a refined corpus for high-quality domain adaptation. Furthermore, we introduce two auxiliary strategies in the training phase to enhance efficiency and accuracy. Finally, our framework is evaluated across multiple task scenarios and demonstrates the best performance on most of them, which proves the effectiveness and efficiency of the model presented in this work. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

supported by the National Natural science Foundation of China(Nos.62172051,61772085,and 61877005)and Jiangsu Agriculture science and technology Innovation Fund(***(18)3054).

引用

Tsinghua science and technology 2023年第1期28卷 82-92页

作者： Jinghui Zhang Yuchen Wang Tianyu Huang Fang Dong Wei Zhao Dian Shen School of Computer Science and Engineering Southeast UniversityNanjing 211189China Hefei Comprehensive National Science Center Hefei 231299China School of Computer Science and Technology Anhui University of TechnologyHefei 230026China Department of Computer Science&Engineering The Chinese University of Hong KongHong Kong 999077China

Numerous neural network(NN)applications are now being deployed to mobile *** applications usually have large amounts of calculation and data while requiring low inference latency,which poses challenges to the computing ability of mobile ***,devices’life and performance depend on ***,in many scenarios,such as industrial production and automotive systems,where the environmental temperatures are usually high,it is important to control devices’temperatures to maintain steady *** this paper,we propose a thermal-aware channel-wise heterogeneous NN inference *** contains two parts,the thermal-aware dynamic frequency(TADF)algorithm and the heterogeneous-processor single-layer workload distribution(HSWD)*** on a mobile device’s architecture characteristics and environmental temperature,TADF can adjust the appropriate running speed of the central processing unit and graphics processing unit,and then the workload of each layer in the NN model is distributed by HSWD in line with each processor’s running speed and the characteristics of the layers as well as heterogeneous *** experimental results,where representative NNs and mobile devices were used,show that the proposed method can considerably improve the speed of the on-device inference by 21%–43%over the traditional inference method.

关键词： neural network inference mobile device temperature adjustment channel-wise parallelization

来源：评论

学校读者我要写书评

暂无评论

Solving Sparse Reward Tasks Using Self-Balancing Exploration and Exploitation

引用

Journal of Internet technology 2025年第3期26卷 293-301页

作者： Kong, Yan Wei, Junfeng Hsia, Chih-Hsien School of Computer and Software Nanjing University of Information Science and Technology China Department of Computer Science and Information Engineering National Ilan University Taiwan Department of Business Administration Chaoyang University of Technology Taiwan

A core challenge in applying deep reinforcement learning (DRL) to real-world tasks is the sparse reward problem, and shaping reward has been one effective method to solve it. However, due to the enormous state space and sparse rewards in the real world, a large number of useless samples may be generated, leading to reduced sample efficiency and potential local optima. To address this issue, this study proposes a self-balancing method of exploration and development to solve the issue of sparse rewards. Firstly, we shape the reward function according to the evaluated progress, to guide the agent’s learning of high-reward samples. Secondly, we construct a dual-trajectory exploration network, which provides intrinsic rewards based on the novelty of states and the trajectory difference of sibling agents to encourage the agent to explore and adjust the balance between exploration and exploitation. This method effectively prevents the generation of a large amount of useless training data during the interaction between the agent and the environment, resolves local optimal dilemmas through state novelty, and adjusts the strategy in a timely manner to solve sparse reward tasks. Our method outperforms basic reinforcement learning (RL) and curiosity-driven incentives in these experimental tasks. The self-balancing exploration and exploitation approach in our research provides a new perspective and effective solution for addressing the problem of sparse rewards, thereby advancing the application of DRL in real-world problems and achieving greater success. © 2025 Taiwan Academic Network Management Committee. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Residual diverse ensemble for long-tailed multi-label text classification

引用

science China(Information sciences) 2024年第11期67卷 92-105页

作者： Jiangxin SHI Tong WEI Yufeng LI National Key Laboratory for Novel Software Technology Nanjing University School of Artificial Intelligence Nanjing University School of Computer Science and Engineering Southeast University Key Laboratory of Computer Network and Information Integration Southeast UniversityMinistry of Education

Long-tailed multi-label text classification aims to identify a subset of relevant labels from a large candidate label set, where the training datasets usually follow long-tailed label distributions. Many of the previous studies have treated head and tail labels equally, resulting in unsatisfactory performance for identifying tail labels. To address this issue, this paper proposes a novel learning method that combines arbitrary models with two steps. The first step is the “diverse ensemble” that encourages diverse predictions among multiple shallow classifiers, particularly on tail labels, and can improve the generalization of tail *** second is the “error correction” that takes advantage of accurate predictions on head labels by the base model and approximates its residual errors for tail labels. Thus, it enables the “diverse ensemble” to focus on optimizing the tail label performance. This overall procedure is called residual diverse ensemble(RDE). RDE is implemented via a single-hidden-layer perceptron and can be used for scaling up to hundreds of thousands of labels. We empirically show that RDE consistently improves many existing models with considerable performance gains on benchmark datasets, especially with respect to the propensity-scored evaluation ***, RDE converges in less than 30 training epochs without increasing the computational overhead.

关键词： multi-label learning extreme multi-label learning long-tailed distribution multi-label text classification ensemble learning

来源：评论

学校读者我要写书评

暂无评论

A boundary evidence controlled level set inference method for nuclei instance segmentation in histopathology images

引用

Multimedia Tools and Applications 2024年 1-31页

作者： Vatani, Amir Song, Jie Xiao, Liang School of Computer Science and Engineering Nanjing University of Science and Technology Jiangsu Nanjing210094 China College of Automation & College of Artificial Intelligence Nanjing University of Posts and Telecommunications Jiangsu Nanjing210023 China

Periodic B-spline (PBS) has been a successfully used technique in histopathology image segmentation. However, it is limited when dealing with multi-instance objects in real-world biomedical applications. Moreover, its segmentation results are quite sensitive to the initial settings of the model and highly depend on the selection of control points. To address these issues and boost the canonical PBS to a new level of adaptive fitting, we present Level-Set B-Spline (LSBS), a novel definition of nuclear contour inference that employs B-splines under the energy minimization of a variational level set functional, which can promote each other. To this end, we adopt a two-stage approach: The first stage solves the marker detection and image segmentation problem and the second stage solves the joint modeling of the missing contour and the latent shape. To do so, we propose the use of modified concavity measurement and optimal boundary-to-marker association as an efficient basis for computing a periodic set of knots to drive the LSBS. For any probe image, our approach enables to analysis of free-lying and overlapping cell nuclei with weak boundaries. We demonstrated the superiority of the proposed LSBS by evaluating it on various datasets, including the challenging TCGA KIRC and Kumar nuclei, where the consistently state-of-the-art performances were achieved for comparison against state-of-the-art image analysis-based methods. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Data-driven output regulation control for constrained linear systems

引用

science China(Information sciences) 2025年第3期68卷 338-353页

作者： Chaoyu XIA Yi DONG Chaoli WANG Shengyuan XU Shanghai Research Institute for Intelligent Autonomous Systems Tongji University College of Electronic and Information Engineering Shanghai Research Institute for Intelligent Autonomous SystemsTongji University Department of Control Science and Engineering School of Optical-Electrical and Computer EngineeringUniversity of Shanghai for Science and Technology Department of Automation Nanjing University of Science and Technology

This study introduces a data-driven approach for state and output feedback control addressing the constrained output regulation problem in unknown linear discrete-time systems. Our method ensures effective tracking performance while satisfying the state and input constraints, even when system matrices are not available. We first establish a sufficient condition necessary for the existence of a solution pair to the regulator equation and propose a data-based approach to obtain the feedforward and feedback control gains for state feedback control using linear programming. Furthermore, we design a refined Luenberger observer to accurately estimate the system state, while keeping the estimation error within a predefined set. By combining output regulation theory, we develop an output feedback control strategy. The stability of the closed-loop system is rigorously proved to be asymptotically stable by further leveraging the concept of λ-contractive sets.

关键词： output regulation constrained system data-driven.

来源：评论

学校读者我要写书评

暂无评论

A Spectral Convolutional Neural Network Model Based on Adaptive Fick’s Law for Hyperspectral Image Classification

引用

computers, Materials & Continua 2024年第4期79卷 19-46页

作者： Tsu-Yang Wu Haonan Li Saru Kumari Chien-Ming Chen School of Artificial Intelligence(School of Future Technology) Nanjing University of Information Science&TechnologyNanjing210044China College of Computer Science and Engineering Shandong University of Science and TechnologyQingdao266590China Department of Mathematics Chaudhary Charan Singh UniversityMeerutUttar Pradesh250004India

Hyperspectral image classification stands as a pivotal task within the field of remote sensing,yet achieving highprecision classification remains a significant *** response to this challenge,a Spectral Convolutional Neural Network model based on Adaptive Fick’s Law Algorithm(AFLA-SCNN)is *** Adaptive Fick’s Law Algorithm(AFLA)constitutes a novel metaheuristic algorithm introduced herein,encompassing three new strategies:Adaptive weight factor,Gaussian mutation,and probability update *** adaptive weight factor,the algorithmcan adjust theweights according to the change in the number of iterations to improve the performance of the *** helps the algorithm avoid falling into local optimal solutions and improves the searchability of the *** probability update strategy helps to improve the exploitability and adaptability of the *** the AFLA-SCNN model,AFLA is employed to optimize two hyperparameters in the SCNN model,namely,“numEpochs”and“miniBatchSize”,to attain their optimal ***’s performance is initially validated across 28 functions in 10D,30D,and 50D for CEC2013 and 29 functions in 10D,30D,and 50D for *** results indicate AFLA’s marked performance superiority over nine other prominent optimization ***,the AFLA-SCNN model was compared with the Spectral Convolutional Neural Network model based on Fick’s Law Algorithm(FLA-SCNN),Spectral Convolutional Neural Network model based on Harris Hawks Optimization(HHO-SCNN),Spectral Convolutional Neural Network model based onDifferential Evolution(DE-SCNN),SpectralConvolutionalNeuralNetwork(SCNN)model,and SupportVector Machines(SVM)model using the Indian Pines dataset and Paviauniv.rsity *** experimental results show that the AFLA-SCNN model outperforms other models in terms of Accuracy,Precision,Recall,and F1-score on Indian Pines and Pavia *** them,the Accuracy of the AFLA-SCNN model on India

关键词： Adaptive Fick’s law algorithm spectral convolutional neural network metaheuristic algorithm intelligent optimization algorithm hyperspectral image classification

来源：评论

学校读者我要写书评

暂无评论

Hybrid-Frequency Feature Evolution Network for Endoscopic Ultrasound Image Segmentation 22

Hybrid-Frequency Feature Evolution Network for Endoscopic Ul...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Wang, Dongfang Zhou, Tao Yang, Jian School of Computer Science and Engineering Nanjing University of Science and Technology Pca Lab China

ISBN: (纸本)9798331520526

The segmentation of lesions in endoscopic ultrasound images is essential for clinical diagnosis. However, such as the low contrast in ultrasound images, patient-specific factors, and inter-case variations, make accurate segmentation highly challenging. To address these issues, we propose a novel Hybrid-frequency Feature Evolution Network (HFENet) for EUS image segmentation. Specifically, we propose a Hybrid-frequency Feature Evolution and Supervision (HFES) module that ensures consistent segmentation across multiple scales, mitigating the impact of patient-specific factors and inter-case variability. Additionally, by integrating wavelet transform, multi-scale features are decomposed into low- and high-frequency components to capture global structures and fine details, respectively. A Selective Co-Evolution (SCE) module is also proposed to adaptively balance these components to enhance feature representation. Experimental results on three EUS datasets show that our HFENet outperforms state-of-the-art segmentation methods. © 2025 IEEE.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

From Generative AI to Generative Internet of Things: Fundamentals, Framework, and Outlooks

引用

IEEE Internet of Things Magazine 2024年第3期7卷 30-37页

作者： Wen, Jinbo Nie, Jiangtian Kang, Jiawen Niyato, Dusit Du, Hongyang Zhang, Yang Guizani, Mohsen College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China School of Computer Science and Engineering Nanyang Technological University China School of Automation Guangdong University of Technology China United Arab Emirates

Generative Artificial Intelligence (GAI) possesses the capabilities of generating realistic data and facilitating advanced decision-making. By integrating GAI into modern Internet of Things (IoT), Generative Internet of Things (GIoT) is emerging and holds immense potential to revolutionize various aspects of society, enabling more efficient and intelligent IoT applications, such as smart surveillance and voice assistants. In this article, we present the concept of GIoT and conduct an exploration of its potential prospects. Specifically, we first overview four GAI techniques and investigate promising GIoT applications. Then, we elaborate on the main challenges in enabling GIoT and propose a general GAI-based secure incentive mechanism framework to address them, in which we adopt Generative Diffusion Models (GDMs) for incentive mechanism designs and apply blockchain technologies for secure GIoT management. Moreover, we conduct a case study on modern Internet of Vehicle traffic monitoring, which utilizes GDMs to generate effective contracts for incentivizing users to contribute sensing data with high quality. Numerical results demonstrate the superiority of the proposed scheme. Finally, we suggest several open directions worth investigating for the future popularity of GIoT. © 2018 IEEE.

关键词： Internet of things

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：