检索结果-内蒙古大学图书馆

Generation of a scenario library for testing driver-automation cooperation safety under cut-in working conditions

Green Energy and Intelligent Transportation 2022年第2期1卷 1-8页

作者： Hongyan Guo Jiaming Zhang Jun Liu Yunfeng Hu Wanqing Shi College of Communication Engineering Jilin UniversityRenmin Street 5988Changchun130012China The State Key Laboratory of Automotive Simulation and Control Jilin UniversityRenmin Street 5988Changchun130012China College of Automotive Engineering Jilin UniversityRenmin Street 5988Changchun130012China

To improve the efficiency of safety tests of driver-automation cooperation,a method for generating a scenario library is proposed that considers the probability of scenario occurrence and driver-handling challenges in real driving ***,the original scenario data under cut-in conditions stored in a time series are extracted from the scenario data ***,a mathematical performance index is used to model the scenario and a significance function in terms of the occurrence frequency of the scenario,and the performance challenge between the driver and the vehicle is ***,the important scenario set is extracted from the original scenario set by constructing and optimizing a significance auxiliary ***,the extracted important scenario sets are filtered by using the significance function values of the scenarios to generate a scenario *** results show that the proposed method for scenario library generation can effectively identify scenarios with potential adventure during driver-automation cooperation and thus accelerate safety tests compared with traditional methods.

关键词： Scenario library generation Cut-in working condition Driver-automation cooperation Performance challenge Significance function

来源：评论

学校读者我要写书评

暂无评论

Fine-grained Personalized Hierarchical Federated Learning towards Heterogeneous Internet of Vehicles

引用

IEEE Internet of Things Journal 2025年第11期12卷 16349-16362页

作者： Zhang, Puning Shao, Shuman Wu, Chao Yang, Zhigang Zhang, Ruoying Chongqing University of Posts and Telecommunications School of Communications and Information Engineering Chongqing400065 China Chongqing Key Laboratory of Ubiquitous Sensing and Networking Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China Chongqing400065 China Chongqing Innovation Center of Industrial Big-Data Co. Ltd National Engineering Laboratory for Industrial Big-data Application Technology Chongqing400707 China China Merchants Testing Vehicle Technology Research Institute Co. Ltd Chongqing404100 China Chongqing University of Posts and Telecommunications School of Cyber Security and Information Law Chongqing400065 China Chongqing Key Laboratory of Ubiquitous Sensing and Networking Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China China China Academy of Information and Communications Beijing100083 China

High mobility and non-independent and identically distributed (non-iid) data in the Internet of Vehicles (IoV) pose challenges for the convergence speed and accuracy of federated learning model training. Traditional federated learning approaches fail to account for the unique characteristics of local vehicle data, limiting the model performances. To address this, we propose a personalized hierarchical federated learning method tailored for heterogeneous IoV. Our approach customizes models for each vehicle, enhancing their performance on local data. We introduce a network-aware client selection method that dynamically chooses vehicle clients based on their spatiotemporal distribution and changing channel conditions. Additionally, our fine-grained personalized learning method leverages frequency domain analysis to extract and retain both fundamental and personalized knowledge from local model parameters. This allows us to build highly accurate personalized models suited to each vehicle's data characteristics. Experimental results show that our method improves model accuracy by up to 10.31% and reduces training time by up to 24.93% compared to the latest personalized federated learning algorithms. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

IDIDNG: A Domain Generalization Remaining Useful Life Prediction Method of Unknown Bearings 3

IDIDNG: A Domain Generalization Remaining Useful Life Predic...

引用

3rd International Conference on Sensing, Measurement and data Analytics in the Era of Artificial Intelligence, ICSMD 2022

作者： Xu, Juan Xu, Zhen Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data School of Computer and Information Hefei China

ISBN: (纸本)9781665492812

Domain adaptation (DA) -based RUL prediction methods have achieved great success for the adaptation ability of the distribution discrepancy between the source and target domains. However, DA methods are powerless when the target domain data are not available for training. To solve this problem, we propose an inter-domain intra-domain normalized generalization (IDIDNG) network, which consists of three modules, respectively, the pre-processing module, the feature transformation module, and the RUL prediction module. First, we design the pre-processing module to process the bearing vibration data with peak-to-peak and Z-score. Finally, it is connected into a four-dimensional array. In the feature transformation module, via intra-domain and inter-domain normalization as well as mean-variance cross-swap, we transform the data distribution expressions of invariant features of bearings from the perspective of different bearings and different degradation stage of one bearing, such that the model enables to learn the intra-domain and inter-domain discrepancy. Further we design four adaptable weighting parameters into the intra-domain normalization to learn the appropriate normalized mean and variance via the model training. Finally, we design the GRU-based RUL prediction module to predict the unknown bearings. We conducted experiments under the PHM2012 dataset, experimental results show that our method achieves satisfactory prediction accuracy in the unknown bearings. © 2022 IEEE.

关键词： adaptive weights cross-swap generalization inter-domain intra-domain normalization RUL

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Speech Extraction for Multiple Target Speakers Under Meeting Scenarios

引用

Journal of Shanghai Jiaotong university (Science) 2024年 1-7页

作者： Zeng, Bang Suo, Hongbin Wan, Yulong Li, Ming School of Computer Science Wuhan University Wuhan430027 China Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems Duke Kunshan University Kunshan Jiangsu215316 China Data & amp AI Engineering System OPPO Beijing100125 China

The common target speech separation directly estimates the target source, ignoring the interrelationship between different speakers at each frame. We propose a multiple-target speech separation (MTSS) model to simultaneously extract each speaker’s voice from the mixed speech rather than just optimally estimating the target source. Moreover, we propose a speaker diarization (SD) aware MTSS system (SD-MTSS). By exploiting the target speaker voice activity detection (TSVAD) and the estimated mask, our SD-MTSS model can extract the speech signal of each speaker concurrently in a conversational recording without additional enrollment audio in advance. Experimental results show that our MTSS model achieves improvements of 1.38 dB signal-to-distortion ratio (SDR), 1.34 dB scale-invariant signal-to-distortion ratio (SISDR), and 0.13 perceptual evaluation of speech quality (PESQ) over the baseline on the WSJ0-2mix-extr dataset, separately. The SD-MTSS system makes a 19.2% relative speaker dependent character error rate reduction on the Alimeeting dataset. © Shanghai Jiao Tong university 2024.

关键词： Speech analysis

来源：评论

学校读者我要写书评

暂无评论

Secure Multi-way Join Query and Its Bench-Marking with Trusted Execution Environments 2nd

Secure Multi-way Join Query and Its Bench-Marking with Tru...

引用

2nd International Conference on data Security and Privacy Protection, DSPP 2024

作者： Zhao, Yi Zhao, Sen Lv, Siyi School of Cyber Engineering Xidian University Xi’an China State Key Laboratory of Integrated Service Networks Xidian University Xi’an China Key Laboratory of Data and Intelligent System Security Ministry of Education Nankai University Tianjin China

ISBN: (纸本)9789819785452

Because of server-untrustable model in outsourcing encrypted database system, it’s fatal for data owners to keep their data confidential under complex query operations performed by database servers. Trusted Execution Environments (TEEs) provide a secure space for privacy computation via hardware-based methods to increase the efficiency of database system, and it ensures the availability of computing directly on sensitive data in untrusted outsourcing database servers. However, while various query schemes are designed under the combination of encrypted database and TEEs, designing an available and secure scheme for join queries on multiple data tables with TEEs remains an open problem. Besides, previous works also devote less to bench-marking multi-way joins on TEEs. In our work, we extend binary join query scheme into multi-way forms in encrypted database system based on TEEs. It combines various join algorithms based on hash functions (hash-based, radix-based, etc.) with parallelized optimizing mechanism. Besides, we do bench-marking with TEEBench framework on those multi-way join schemes in three-way forms using both cache-fit and cache-exceed datasets and do different evaluation on two TEEs hardware platforms (Intel SGX and AMD SEV) to show its availability. After that, we also propose a multi-way join scheme with access pattern protection through the combination between our previous scheme and oblivious I/O methods. With the evaluation of its efficiency and memory leakage, we can also verify the feasibility of our access-pattern-protected multi-way join scheme. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Outsourcing

来源：评论

学校读者我要写书评

暂无评论

First-principles study on the interfacial bonding strength and segregation at Mg/MgZn_(2)matrix interface

引用

Journal of Magnesium and Alloys 2024年第10期12卷 4053-4062页

作者： Longke Bao Peng Du Shengkun Xi Cuiping Wang Kaihong Zheng Rongpei Shi Guoqiang Xie Xingjun Liu State Key Laboratory of Advanced Welding and Joining Harbin Institute of TechnologyShenzhen 518055PR China College of Materials Science and Engineering and Institute of Materials Genome and Big DataHarbin Institute of TechnologyShenzhen 518055PR China College of Materials Science and Engineering Xiamen UniversityXiamen 361005PR China Institute of New Materials Guangdong Academy of SciencesGuangzhou 510650PR China

To understand the interface characteristics between the precipitateβ2'and the Mg matrix,and thus guide the development of new Mg-Zn alloys,we investigated the atomic interface structure,work of adhesion(Wad),and interfacial energy(γ)of Mg(0001)/β2’(MgZn_(2))(0001)interface,as well as the effect of segregation behavior of the introduced transition metal atoms(3d,4d and 5d)on interfacial bonding *** calculated works of adhesion and interfacial energies dementated that the Zn2-terminated MT+HCP configuration is the most stable structure for all considered *** the Zn2-MT+HCP interface as the research object,estimated segregated energies(Eseg)reveal that added transition metal atoms prefer to segregate at Mg-I and Mg-II *** predicted Wad and charge density difference results reveal that the segregation of alloying additives employed may all strengthen Mg(0001)/MgZn_(2)(0001)interface,with the enhancement effect of Os,Re,Tc,W,and Ru at the Mg-II site being the most pronounced.

关键词： Mg/MgZn_(2)interface Work of adhesion Interfacial energy Interface segregation

来源：评论

学校读者我要写书评

暂无评论

GACP:graph neural networks with ARMA flters and a parallel CNN for hyperspectral image classification

引用

International Journal of Digital Earth 2023年第1期16卷 1770-1800页

作者： Jing Yang Jie Sun Yaping Ren Shaobo Li Shujie Ding Jianjun Hu School of Mechanical Engineering Guizhou UniversityGuiyangPeople’s Republic of China State Key Laboratory of Public Big Data Guizhou UniversityGuiyangPeople’s Republic of China School of Intelligent Systems Science and Engineering Jinan UniversityZhuhaiPeople’s Republic of China Department of Computer Science and Engineering University of South CarolinaColumbiaSCUSA

In recent years,the use of convolutional neural networks(CNNs)and graph neural networks(GNNs)to identify hyperspectral images(HSIs)has achieved excellent results,and such methods are widely used in agricultural remote sensing,geological exploration,and marine remote *** many generalization classification algorithms are designed for the purpose of learning a small number of samples,there is often a problem of a low utilization rate of position information in the empty spectral *** on this,a GNN with an autoregressive moving average(ARMA)-based smoothingfilter samples the node information in the null spectral domain and then captures the spatial information at the pixel level via spatial feature convolution;then,the null spectral domain position information lost by the CNN is located by a coordinate attention(CA)***,autoregressive,spatial convolution,and CA mechanisms are combined into multiscale features to enhance the learning capacity of the network for tiny *** conducted on the widely used Indian Pines(IP)dataset,the Botswana(BS)dataset,Houton 2013(H2013),and the WHU-Hi-HongHu(WHU)benchmark HSI dataset demonstrate that the proposed GACP technique can perform classification work with good accuracy even with a small number of training examples.

关键词： Graph neural networks word convolutional neural networks hyperspectral image classification attention mechanisms

来源：评论

学校读者我要写书评

暂无评论

LoRS: Efficient Low-Rank Adaptation for Sparse Large Language Model

arXiv

引用

arXiv 2025年

作者： Hu, Yuxuan Zhang, Jing Chen, Xiaodong Zhao, Zhe Li, Cuiping Chen, Hong School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering Beijing China Engineering Research Center of Database and Business Intelligence Beijing China Tencent AI Lab Beijing China

Existing low-rank adaptation (LoRA) methods face challenges on sparse large language models (LLMs) due to the inability to maintain sparsity. Recent works introduced methods that maintain sparsity by augmenting LoRA techniques with additional masking mechanisms. Despite these successes, such approaches suffer from an increased memory and computation overhead, which affects efficiency of LoRA methods. In response to this limitation, we introduce LoRS, an innovative method designed to achieve both memory and computation efficiency when fine-tuning sparse LLMs. To mitigate the substantial memory and computation demands associated with preserving sparsity, our approach incorporates strategies of weight recompute and computational graph rearrangement. In addition, we also improve the effectiveness of LoRS through better adapter initialization. These innovations lead to a notable reduction in memory and computation consumption during the fine-tuning phase, all while achieving performance levels that outperform existing LoRA approaches. © 2025, CC BY.

关键词： Problem oriented languages

来源：评论

学校读者我要写书评

暂无评论

Order Forecasting Method for Large-Scale Personalized Customization Model 16th

Order Forecasting Method for Large-Scale Personalized Custom...

引用

16th International Conference on Modelling, Identification and Control, ICMIC 2024

作者： Wang, Lijun Wu, Chaohang Chen, Xianzhong Li, Qing Yao, Qijia School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China Key Laboratory of Knowledge Automation for Industrial Processes of Science and Technology Beijing Beijing China

ISBN: (纸本)9789819617760

Based on the personalized customization model in bearing steel enterprises, it is studied in this paper how historical data can be fully utilized to predict orders in the face of multi-variety and small-batch order models.. In order to overcome the bottleneck of information exchange that cannot be obtained from pure historical data based on diverse small batch customer needs. A demand fusion mechanism based on local rules is proposed, taking fuzzy customer demand preferences as "individuals" and introducing historical data such as order area and external environmental factors. First, based on the Hegselmann-Krause (HK) model, a personalized customized customer demand preference prediction model is proposed to simulate and predict the evolution process of large-scale customer demand preferences. Secondly, according to the fuzzy rules, the customer's demand preference in the historical data is used as the center point to introduce the fuzzy individual, and the standard deviation is determined based on the order area. Finally, the effectiveness of the proposed method was verified through simulation results. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Detector array with digital data acquisition system for charged-particle decay studies

引用

Nuclear Science and Techniques 2025年第4期36卷 140-150页

作者： Hao Jian Xin-Xing Xu Kai-Long Wang Jia-Jian Liu Chao-Yi Fu Peng-Jie Li Yan-Yun Yang Guang-Xin Zhang Kang Wang Fang-Fang Duan Long-Hui Ru Guang-Shun Li Bing Ding Yun-Hua Qiang Cen-Xi Yuan Jun-Bing Ma Shi-Wei Xu Yu-Feng Gao Rui Fan Fan-Chao Dai Si-Xian Zha Hao-Fan Zhu Jin-Hai Li Shu-Lian Qin Zhi-Fang Chang Cheng Kong He-Xuan Yan Hao-Wei Xu Jia-Long Ning Bo-Ren Liu Jie Zhou Yu-Dong Chen Bo-Shuai Cai Yu-Ting Wang Hong-Yi Wu Zhi-Xuan Wang Dong-Sheng Hou Hu-Shan Xu Xiao-Hong Zhou Yu-Hu Zhang Meng Wang Zheng-Guo Hu Jenny Lee State Key Laboratory of Heavy Ion Science and Technology Institute of Modern PhysicsChinese Academy of SciencesLanzhou 730000China School of Nuclear Science and Technology University of Chinese Academy of SciencesBeijing 100049China Advanced Energy Science and Technology Guangdong Laboratory Huizhou 516003China Department of Physics The University of Hong KongHong KongChina Sino-French Institute of Nuclear Engineering and Technology Sun Yat-sen UniversityZhuhai 519082China Institute of Particle and Nuclear Physics Henan Normal UniversityXinxiang 453007China Key Laboratory of Nuclear Data China Institute of Atomic EnergyBeijing 102413China School of Physics and State Key Laboratory of Nuclear Physics and Technology Peking UniversityBeijing 100871China

A state-of-the-art detector array with a digital data acquisition system has been developed for charged-particle decay studies,includingβ-delayed protons,αdecay,and direct proton emissions from exotic proton-rich *** digital data acquisition system enables precise synchronization and processing of complex signals from various detectors,such as plastic scintillators,silicon detectors,and germaniumγ*** system's performance was evaluated using theβdecay of^(32)Ar and its neighboring nuclei,produced via projectile fragmentation at the first Radioactive Ion Beam Line in Lanzhou(RIBLL1).key measurements,including the half-life,charged-particle spectrum,andγ-ray spectrum,were obtained and compared with previous results for *** the implantation–decay method,the isotopes of interest were implanted into two doublesided silicon strip detectors,where their subsequent decays were measured and correlated with preceding implantations using both position and time *** detection system has potential for further applications,including the study ofβ-delayed charged-particle decay and direct proton emissions from even more exotic proton-rich nuclei.

关键词： β-delayed proton decay Double-sided silicon strip detector High-purity germanium detector Digital data acquisition system Implantation–decay correlation

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：