检索结果-内蒙古大学图书馆

Embedding expert demonstrations into clustering buffer for effective deep reinforcement learning

Frontiers of information technology & Electronic Engineering 2023年第11期24卷 1541-1556页

作者： Shihmin WANG Binqi ZHAO Zhengfeng ZHANG Junping ZHANG Jian PU Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200433China Institute of Science and Technology for Brain-inspired Intelligence Fudan UniversityShanghai 200433China

As one of the most fundamental topics in reinforcement learning(RL),sample efficiency is essential to the deployment of deep RL *** most existing exploration methods that sample an action from different types of posterior distributions,we focus on the policy sampling process and propose an efficient selective sampling approach to improve sample efficiency by modeling the internal hierarchy of the ***,we first employ clustering methods in the policy sampling process to generate an action candidate *** we introduce a clustering buffer for modeling the internal hierarchy,which consists of on-policy data,off-policy data,and expert data to evaluate actions from the clusters in the action candidate set in the exploration *** this way,our approach is able to take advantage of the supervision information in the expert demonstration *** on six different continuous locomotion environments demonstrate superior reinforcement learning performance and faster convergence of selective *** particular,on the LGSVL task,our method can reduce the number of convergence steps by 46.7%and the convergence time by 28.5%.Furthermore,our code is open-source for *** code is available at https://***/Shihwin/SelectiveSampling.

关键词： Reinforcement learning Sample eficiency Sampling process Clustering methods Autonomous driving

来源：评论

学校读者我要写书评

暂无评论

Prediction of GDP Carbon Emission Based on Grey Model and Neural Network 4th

Prediction of GDP Carbon Emission Based on Grey Model and Ne...

引用

4th EAI International Conference on Robotic Sensor Networks, 2020

作者： Zhang, Feng Zhao, Huihuang Ramasamy, Manimaran College of Computer Science and Technology Hengyang Normal University Hengyang China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang China

ISBN: (纸本)9783030704506

In order to improve the prediction accuracy of Gross Domestic Product (GDP) carbon emission, combining the advantages of grey prediction and neural network, a discrete grey neural network prediction model named DGMBP is established. This model not only has the advantages of less data sample and larger development coefficient range of GM 1,1 model but also combines the advantages of neural network to deal with nonlinear data sample. Taking the GDP carbon emission data of China, India, the United States and the European Union as an example, the prediction results obtained are stable, and the accuracy of the prediction data is over 95%, which is much higher than that obtained by the linear regression equation and the logical regression equation. Finally, the carbon emission of GDP in 2020–2030 is predicted by using this model. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Adaptive Spatial Modeling and Multi-Scale Attention Aggregation for Semantic Segmentation of Remote Sensing Images

Adaptive Spatial Modeling and Multi-Scale Attention Aggregat...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Wenying Yang Yuchuan Zhang Yuxuan Jin Yupei Wang Liang Chen National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology Chongqing Innovation Center Chongqing China School of Artificial Intelligence Jianghan University Wuhan China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology Chongqing Innovation Center Beijing Institute of Technology Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

As remote sensing technology advances and high-resolution sensors are deployed, the analysis of high-resolution remote sensing images encounters challenging issues, such as intra-class variability, and inter-class similarity, due to the unobvious appearance and complicated background. The high-resolution remote sensing images pose critical issues for precise semantic segmentation due to these fundamental issues. To this end, we propose an adaptive hierarchical aggregation network. Different from the previous approach of modeling semantic interdependencies solely within a single feature map in the channel dimension, we introduce multi-scale channel-wise feature aggregation to capture global contextual dependencies. Meanwhile, we design an adaptive detail-aware module to model long-range spatial dependencies, adaptively extracting effective details from different levels as compensation. Additionally, this module utilizes depth-wise separable convolution to selectively filter out irrelevant spatial details from lower-level feature maps. The outputs of the two modules are fused layer by layer to achieve refined feature representation, thereby generating precise pixel-level segmentation results. Our experiments are conducted on the Vaihingen dataset and the Potsdam dataset. The experimental results demonstrate that the proposed algorithm surpasses several existing state-of-the-art approaches.

关键词： Image sensors Adaptation models Adaptive systems Semantic segmentation Semantics Filtering algorithms Feature extraction Data processing Sensors Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Duration-Aware Task Assignment for Heterogeneous Mobility Users in Crowdsensing 25

Duration-Aware Task Assignment for Heterogeneous Mobility Us...

引用

25th IEEE International Conference on Computer Supported Cooperative Work in Design, CSCWD 2022

作者： Liu, Zhiyuan Li, Peng Huang, Weiyi Wang, Jiahu Nie, Lei Wuhan University of Science and Technology School of Computer Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing Real-Time Industrial System China

ISBN: (纸本)9781665405270

This paper investigates the duration-aware task assignment problem for heterogeneous mobility users in MCS (DTAH problem). There are two types of users in MCS, vehicle users and pedestrian users. The vehicle user gets to the task fast, but the task duration is short. Pedestrian user meets the task duration limit, but it takes a long time to reach the task. Given a set of tasks and two types of users, each user, and each task has a duration limit. The DTAH problem is how to assign tasks to maximize the utility of the system. We prove that the DTAH problem is NP-hard by reducing the weighted maximum set coverage problem to the DTAH problem. Then, we solve the problem from a pedestrian perspective and a vehicle perspective. From the pedestrian user perspective, we propose a pedestrian user task assignment (PTA) algorithm based on the Kuhn-Munkres algorithm. From the vehicle user perspective, we propose a greedy vehicle user task assignment (VTA) algorithm. We prove that the VTA algorithm can obtain the approximate ratio of 1-1/e to the optimal value. Finally, we design the heterogeneous user task assignment (HTA) algorithm based on these PTA and VTA algorithms. Extensive experiments have proved that our proposed HTA algorithm achieves more efficient performance than other comparison algorithms. © 2022 IEEE.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

A Sparsity Knowledge Transfer-Based Evolutionary Algorithm for Large-Scale Multitasking Multi-Objective Optimization

引用

IEEE Transactions on Evolutionary Computation 2024年

作者： Wu, Chengming Tian, Ye Zhang, Limiao Xiang, Xiaoshu Zhang, Xingyi Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Artificial Intelligence Hefei230601 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Hefei230039 China Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Hefei230601 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Hefei230601 China

Multitasking multi-objective evolutionary algorithms (MMEAs) have been extensively studied in the past decade, which mainly concentrate on multitasking multi-objective optimization problems (MMOPs) with dozens of decision variables. Nevertheless, many real-world MMOPs have thousands of decision variables and are of sparse nature, which are regarded as large-scale MMOPs (LSMMOPs) in this study. To address LSMMOPs, a sparsity knowledge transfer-based evolutionary multi-objective algorithm, termed EMO-SKT, is proposed for efficiently finding high-quality sparse solutions of LSMMOPs. For each target optimization task, a sparsity knowledge transfer strategy extracts sparse distribution information from a source task and incorporates the information into the target task for two types of sparsity knowledge: variable importance and sparse degree. The variable importance is utilized to produce high-quality sparse solutions during the evolutionary search for EMO-SKT, while the sparse degree facilitates the reduction of search space and thus speeds up the convergence of the evolutionary search. Experimental results on eight benchmark problems and six practical LSMMOPs demonstrate the effectiveness of the sparsity knowledge transfer strategy. Furthermore, the proposed EMO-SKT is capable of efficiently finding high-quality sparse solutions on an LSMMOP with over 1000 decision variables. In comparison with five state-of-the-art multitasking or sparse optimization algorithms, the proposed EMO-SKT exhibits superior performance in terms of both solution quality and search efficiency. © 1997-2012 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Research on Zenith Tropospheric Delay Model Based on TCN Improving HGPT2 Model 14th

Research on Zenith Tropospheric Delay Model Based on TCN Imp...

引用

14th China Satellite Navigation Conference, CSNC 2024

作者： Li, Dengao Shi, Danyang Zhao, Jumin Wu, Fanming Yan, Liangquan Feng, Ran Zhang, Xinfang Zhao, Jinhua College of Data Science Taiyuan University of Technology Taiyuan030024 China College of Information and Computer Taiyuan University of Technology Taiyuan030024 China Key Laboratory of Big Data Fusion Analysis and Application of Shanxi Province Taiyuan030024 China Intelligent Perception Engineering Technology Center of Shanxi Taiyuan030024 China Shanxi Province Engineering Technology Research Center of Spatial Information Network Taiyuan030024 China

ISBN: (纸本)9789819969272

The zenith tropospheric delay (ZTD) obtained by global navigation satellite system (GNSS) atmospheric sounding is a pivotal data source for water vapor monitoring. Meteorological changes in Antarctica play an important role in analysis of the global climate, but factors such as complex climatic conditions can limit the collection of meteorological data needed for ZTD retrieval. Therefore, it is necessary to establish high-precision ZTD models that do not rely on measured meteorological data. The existing global pressure and temperature 3 (GPT3) model has limited ability to capture complex weather variations and cannot obtain high-precision GPT3_ZTD. To address the above issues, this research proposes a high-precision ZTD model through using temporal convolutional network (TCN) for improving the hourly global pressure and temperature 2 (HGPT2) model. The HGTP2 model based on Fourier analysis and the time-segmentation concept can consider the linear trend of climate variations, simultaneously the TCN is introduced to simulate the long-term temporal dependence of HGPT2_ZTD, so as to achieve the goal of obtaining high-precision ZTD without relying on measured meteorological data. The experimental results show that the precision of TCN_ZTD obtained from the proposed model is higher than GPT3_ZTD and HGPT2_ZTD when using the GNSS_ZTD observations obtained from 35 stations in Antarctica as a reference, and the improvement of the model is obvious. © 2024, Aerospace information Research Institute.

关键词： Fourier analysis

来源：评论

学校读者我要写书评

暂无评论

Feature Selection Algorithm Based on Discernibility Matrix and Fruit Fly Optimization 16th

Feature Selection Algorithm Based on Discernibility Matrix a...

引用

16th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2021

作者： Ao, Jiaxin Ye, Jun Ji, Yuxuan Yang, Zhenyu College of Information Engineering Nanchang Institute of Technology Nanchang330000 China Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing Nanchang330000 China

ISBN: (纸本)9789811912559

Feature selection methods that combine swarm intelligence optimization algorithms with rough sets have been widely used. Normally, this type of method can quickly search for feature subsets, effectively reducing the computational workload;However, in some decision tables of this type of method, there were also problems such as the searched feature subset containing redundant features, which led to a decrease in accuracy. Aiming at such problems in the current feature selection algorithms based on rough sets and fruit fly optimization, improvements have been made from two aspects. Firstly, a method for measuring the importance of discernibility matrix attributes was proposed and used as a heuristic factor to constructed a new fitness function;Secondly, guided by the fitness function, a fruit fly optimized feature selection method was designed, which can avoid redundant attributes in the feature subset. Examples and experimental results on the UCI datasets show that the new feature selection method can effectively search for the smallest feature subset and improve the stability. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Age estimation of Caenorhabditis elegans with label distribution learning

Age estimation of Caenorhabditis elegans with label distribu...

引用

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Zhao, Zi-Kang Liu, Jun Wang, Jun-Ji Chen, Gong Li, Chen-Qian Zhao, Zihao Jiang, Min Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Caenorhabditis elegans (C. elegans) is widely used in life research as a model organism. Accurate measurement of its age has practical implications for follow-up research. However, due to the similar characteristics of nematodes in different age groups, the general method is difficult to estimate accurately. Aiming at this problem, this paper proposes a method of label distribution learning, and uses fluorescence microscopy images to estimate the age of C. elegans. First, the logical age label are mapped to the label distribution. Secondly, the distribution learning loss function is used to make the neural network learn the relationship between the label distribution and corresponding image. Finally, the distribution learning loss function and the classification loss function are combined to strengthen the learning of the neural network. Experiments show that the accuracy and mean absolute error (MAE) of the method in this paper are improved compared with the baseline. In the experiment of estimating the age on different parts' data set, it was also concluded that the fluorescent image of the torso of C. elegans can better reflect the age characteristics than the head and tail. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An English Pronunciation Quality Evaluation Model Based on Multi-dimensional Features 2

An English Pronunciation Quality Evaluation Model Based on M...

引用

2021 2nd International Symposium on Automation, information and Computing, ISAIC 2021

作者： Li, Yiqun Huang, Guimin Guangxi Key Laboratory of Image and Graphic Intelligent Processing School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China

As a universal language, English has been paid more and more attention, among which oral English learning is very important. In this paper, the two key technologies of pronunciation error detection and quality evaluation are studied, both of them are effectively integrated, aiming to build a model for L2 learners' English pronunciation quality evaluation. This paper mainly studies two different methods of pronunciation error detection. Based on the speech recognition framework, the standard score is compared with the threshold to judge the correctness of phoneme pronunciation, and the phoneme-dependent threshold is set to improve the maximum Precision to 0.44. By judging the correct pronunciation and confusing phoneme, the accuracy of pronunciation error detection is improved to 81.26%. This paper proposes the fusion algorithm from multi-dimensions of speech fluency and intonation respectively, and a newly designed feature called word duration ratio, which significantly improve the correlation of pronunciation quality evaluation to 0.746. © Published under licence by IOP Publishing Ltd.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Wasserstein GAN Based Underwater Acoustic Channel Simulator

Wasserstein GAN Based Underwater Acoustic Channel Simulator

引用

2023 IEEE International Conference on Signal processing, Communications and Computing, ICSPCC 2023

作者： Zhou, Mingzhang Wang, Junfeng Sun, Haixin School of Informatics Xiamen University Xiamen China Key Laboratory of Southeast Coast Marine Information Intelligent Perception and Application Ministry of Natural Resources Zhangzhou China School of Integrated Circuit Science and Engineering Tianjin University of Technology Tianjin China

ISBN: (纸本)9798350316728

Underwater acoustic channel is a crucial part for implementation of underwater communications, and its measurement is expensive. This leads to the lack of samples for the training of deep neural network (DNN)-based underwater communication receivers. To solve this problem, A Wasserstein generative adversarial network (WGAN)-based underwater acoustic channel simulator is proposed in this paper for channel sample augmentation. The overlap between the distributions of the measured channel and generator output is analyzed. Then the CNN-based WGAN is constructed with the earth-mover's distance as part of the loss function. Tested with the measured channels in Wuyuanwan Bay, Xiamen, the proposed WGAN performs steadily in simulating the complete channel impulse responses and their single taps distributions. Moreover, a simple DNN-based OFDM channel estimator is built and completely trained with the generated channels. The simulation results show that the BER DNN-based channel estimator outperforms the LS and MMSE estimators. © 2023 IEEE.

关键词： Deep neural networks

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：