检索结果-内蒙古大学图书馆

Advances in Transportation Studies 2021年第Special issue 1期2021卷 81-92页

作者： Liu, X.L. Lin, N. Wang, Z.Y. Lin, H. College of Physics and Electronic Information Engineering Minjiang University Fuzhou350108 China Fujian Engineering Research Center of Safety Control for Ship Intelligent Navigation Minjiang University Fuzhou350108 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350108 China

In order to overcome the single factor problem of risk model analysis in traditional quantitative analysis method of shipping traffic accident risk, a quantitative analysis method of shipping traffic accident risk superposition based on traffic big data is proposed. This method constructs a multi factor shipping traffic accident risk measurement model through traffic big data. Through the model, the interaction information between different risk factors is calculated to quantify the risk of shipping traffic accidents. The results show that there are many kinds of risk factors in most shipping accidents, and the risk of shipping accidents increases with the decrease of uncertainty and the increase of interactive information. © 2021, Aracne Editrice. All rights reserved.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

An improved multi-attribute decision-making based network selection algorithm for heterogeneous vehicular network

引用

Frontiers of Computer Science 2022年第3期16卷 211-213页

作者： Lei NIE Bo LIU Peng LI Heng HE Libing WU School of Computer Science and Technology Wuhan University of Science and TechnologyWuhan 430065China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan 430065China School of Cyber Science and Engineering and School of Computer Science Wuhan UniversityWuhan 430072China Shenzhen Research Institute of Wuhan University Shenzhen 518057China

1 Introduction With sharply rising quantity of urban vehicles over the past few decades,traffic jams and safety have gradually become outstanding *** recent years,Vehicular Ad hoc Network(VANET)is appeared and utilized to solve traffic related *** is a type of self-organized and open-structured network,and provides Vehicle-to-Everything(V2X)*** all kinds of applications in VANET rely on efficient data transmission and interaction[1-3].

关键词： network sharply utilized

来源：评论

学校读者我要写书评

暂无评论

Mildew Detection for Stored Wheat Using Gas Chromatography–Ion Mobility Spectrometry and Broad Learning Network

SSRN

引用

SSRN 2023年

作者： Lian, Fei-Yu Fu, Mai-Xia Qin, Yao Key Laboratory of Grain Information Processing and Control Henan University of Technology Ministry of Education Zhengzhou China School of Information Science and Engineering Henan University of Technology Zhengzhou China

Most of the existing methods for wheat mildew detection are biochemical methods, which have the problems of complicated procedure and slow speed. In this paper, a novel wheat mildew detection and classification model was proposed by combining gas chromatography-ion mobility spectrometry (GC-IMS) with broad learning network (BLN) model. Firstly, GC-IMS fingerprint spectrum of wheat samples with different degrees of mildew were collected by GC-IMS spectrometer, and then a classification models was constructed based on broad learning. To improve the classification accuracy of the model, the incremental learning model and the spatial attention mechanism (SAM) were introduced into the model. The model uses the feature information and structure information of the nodes to calculate the attention weight, and extracts the more important feature information in the fingerprint of the samples. At the same time, regularization mechanism was introduced to enhance the generalization performance of the model. Experimental results show that the training time of the proposed model is greatly reduced compared to existing deep learning models. Under the small sample set condition, the mean average accuracy (mAP) of wheat mildew types reaches 90.32%, and the identification precision of early wheat mildew reach 95.34%, and the overall performance index is better than that of the deep learning model. The experiment also proved that GC-IMS combined with broad learning model is an efficient and accurate method for wheat mildew detection. © 2023, The Authors. All rights reserved.

关键词： Gas chromatography

来源：评论

学校读者我要写书评

暂无评论

Raindrop Removal for In-Vehicle Camera Images with Generative Adversarial Network

Raindrop Removal for In-Vehicle Camera Images with Generativ...

引用

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

作者： Zhao, Zihao Jiang, Min Guo, Jia Yang, Xiaoyu Hu, Yudie Zhou, Xianlong Wuhan University of Science and Technology College of Computer Science and Technology Wuhan430065 China Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan430065 China

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Raindrop removal for in-vehicle camera images is useful for surveillance and analysis system such as intelligent driving or case diagnosis. As in rainy days, images taken by in-vehicle cameras such as monitor or drive recorder often suffer from noticeable image degradation, and make it difficult to identify the objects on the road. With the uncertainty of raindrop distribution and the complexity of raindrop status, the attached raindrops of in-vehicle camera images can have different effects. And the large-diameter raindrop will greatly reduce the image quality. However, most of the popular deraining algorithms have been successful in recovering images with small raindrop noise and tiny image distortion, but fails to restore those with raindrops covering large areas. We propose a single image raindrop removal network based on Generative Adversarial Network for in-vehicle camera images. We incorporate two overlapping attention layers into the deraining network, which adopt task-driven visual attention and content perception mechanism. The former obtains features by recursive neural network to guide network more interested in the raindrop regions and the surrounding structures, while the content perception schema extracts the features far from raindrops. Moreover, we collect a new benchmark for In-Vehicle Camera Image Deraining (IVCRID), it chooses in-vehicle camera images from various deraining dataset. The experimental results show that the proposed deraining network outperforms other state-of-the-art raindrop removal methods in image recovering test on the IVCRID dataset and also has the best performance on the experiments of traffic objects detection. © 2022 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Language-Queried Target Sound Extraction Without Parallel Training Data

Language-Queried Target Sound Extraction Without Parallel Tr...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Ma, Hao Peng, Zhiyuan Li, Xu Li, Yukai Shao, Mingjie Kong, Qiuqiang Liu, Ju School of Information Science and Engineering Shandong University Qingdao China Department of Computer Science North Carolina State University NC United States ARC Lab Tencent PCG China Key Laboratory of System and Control AMSS Chinese Academy of Sciences Beijing China The Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9798350368741

Language-queried target sound extraction (TSE) aims to extract specific sounds from mixtures based on language queries. Traditional fully-supervised training schemes require extensively annotated parallel audio-text data, which are labor-intensive. We introduce a parallel-data-free training scheme, requiring only unlabelled audio clips for TSE model training by utilizing the contrastive language-audio pre-trained model (CLAP). In a vanilla parallel-data-free training stage, target audio is encoded using the pre-trained CLAP audio encoder to form a condition embedding, while during testing, user language queries are encoded by CLAP text encoder as the condition embedding. This vanilla approach assumes perfect alignment between text and audio embeddings, which is unrealistic. Two major challenges arise from training-testing mismatch: the persistent modality gap between text and audio and the risk of overfitting due to the exposure of rich acoustic details in target audio embedding during training. To address this, we propose a retrieval-augmented strategy. Specifically, we create an embedding cache using audio captions generated by a large language model (LLM). During training, target audio embeddings retrieve text embeddings from this cache to use as condition embeddings, ensuring consistent modalities between training and testing and eliminating information leakage. Extensive experiment results show that our retrieval-augmented approach achieves consistent and notable performance improvements over existing state-of-the-art with better generalizability. © 2025 IEEE.

关键词： contrastive language-audio pre-training retrieval-augmented strategy target sound extraction uni-modal training for multi-modal tasks

来源：评论

学校读者我要写书评

暂无评论

systematic Cloud-Based Optimization: Twin-Fold Moth Flame Algorithm for VM Deployment and Load-Balancing

引用

Intelligent Automation & Soft Computing 2024年第3期39卷 477-510页

作者： Umer Nauman Yuhong Zhang Zhihui Li Tong Zhen Information Science and Engineering College Henan University of TechnologyZhengzhou450001China School of Artificial Intelligence and Big Data Henan University of TechnologyZhengzhou450001China Key Laboratory of Grain Information Processing and Control Ministry of EducationHenan University of TechnologyZhengzhou450001China

Cloud computing has gained significant recognition due to its ability to provide a broad range of online services and ***,existing commercial cloud computing models demonstrate an appropriate design by concentrating computational assets,such as preservation and server infrastructure,in a limited number of large-scale worldwide data *** the deployment of virtual machines(VMs)is crucial in this scenario to ensure system dependability,performance,and minimal latency.A significant barrier in the present scenario is the load distribution,particularly when striving for improved energy consumption in a hypothetical grid computing *** design employs load-balancing techniques to allocate different user workloads across several virtual *** address this challenge,we propose using the twin-fold moth flame technique,which serves as a very effective optimization *** intentionally designed the twin-fold moth flame method to consider various restrictions,including energy efficiency,lifespan analysis,and resource *** provides a thorough approach to evaluating total costs in the cloud computing *** assessing the efficacy of our suggested strategy,the study will analyze significant metrics such as energy efficiency,lifespan analysis,and resource *** investigation aims to enhance cloud computing techniques by developing a new optimization algorithm that considers multiple factors for effective virtual machine placement and load *** proposed work demonstrates notable improvements of 12.15%,10.68%,8.70%,13.29%,18.46%,and 33.39%for 40 count data of nodes using the artificial bee colony-bat algorithm,ant colony optimization,crow search algorithm,krill herd,whale optimization genetic algorithm,and improved Lévy-based whale optimization algorithm,respectively.

关键词： Optimizing cloud computing deployment of virtual machines load-balancing twin-fold moth flame algorithm grid computing computational resource distribution data virtualization

来源：评论

学校读者我要写书评

暂无评论

A Direct Anti-high Repetition Jamming Design Method via The Minimum Interval Period Optimization

A Direct Anti-high Repetition Jamming Design Method via The ...

引用

Chinese control and Decision Conference, CCDC

作者： Jingjing Qiang Hui Liu Xiongjun Wu Yingbo Li Peipei Cao The Eighth Academy of China Aerospace Science and Technology Corporation The 802 Institute of Shanghai Academy of Space Flight Technology Shanghai China Department of Automation Ministry of Education of China Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Shanghai China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

Semi-active laser detection is used extensively on many kinds of high-precision guidance weapon systems in the varied military fields. Although it is of high detection accuracy, this kind of detection mechanism, on the other hand, suffers from various laser interference modes which are added in view of the semi-active laser detection principle, covering from angle deception interference, synchronous forwarding interference, and high repetition frequency interference, etc. As a consequence, the overall performance is reduced accordingly. Among these types of deception interference, the high repetition frequency interference is the most effective one. In this work, to overcome this specific type of interference, a minimum interval period method (MIPM) is proposed to remove high repetition frequency interference and improve the detection accuracy of the laser semi-active guidance system. Numerical experiments validate that, this method is able to achieve good performance testing on the Semi-active laser detection under high repetition frequency interference via the False Alarm Probability (FAP for short) and Missed Alarm Probability (MAP).

关键词： Laser theory Accuracy Weapons Interference Resists Logic gates Laser modes

来源：评论

学校读者我要写书评

暂无评论

Quality Prediction of Injection Molding Process Using CNN and Parallel-Cascade LSTMs

Quality Prediction of Injection Molding Process Using CNN an...

引用

第43届中国控制会议

作者： Yibo Zhang Dewei Li Yuanqiang Zhou Furong Gao Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University College of Electronic and Information Engineering Tongji University Department of Chemical and Biological Engineering Hong Kong University of Science and Technology Clear Water Bay KowloonHong Kong and the Guangzhou HKUST Fok Ying Tung Research Institute

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Quality prediction of plastic products has always been an important research topic in the injection molding production process. However, existing quality prediction methods struggle to handle both high-frequency data and statistical data generated during the injection molding production process. This paper introduces a novel quality prediction model for injection molding production, utilizing a combination of Convolutional Neural Networks(CNN) and Parallel-Cascade Long Short-Term Memory(PCLSTM) networks. The PCLSTM network is designed to handle the complexities of high-frequency data in injection molding,overcoming the limitations of traditional LSTM methods in processing long sequence data. By segmenting data into stages and utilizing a cascade mechanism, the PCLSTM architecture efficiently captures important temporal dynamics. Additionally, the CNN network is designed to extract statistical data features. The quality prediction results are obtained by fusing two types of data features and then passing them through a fully connected network. Experimental results on real production datasets show that the CNN-PCLSTM model outperforms existing models in prediction accuracy and training convergence speed.

关键词： LSTM CNN Quality Prediction Injection Molding Process

来源：评论

学校读者我要写书评

暂无评论

Domain-adaptation with knowledge accumulation through parallel stacked autoencoders: methodology and application to sulfur recovery

Domain-adaptation with knowledge accumulation through parall...

引用

American control Conference (ACC)

作者： Tianhao Mou Jinfeng Liu Yuanyuan Zou Shaoyuan Li Maria Gabriella Xibilia Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University Shanghai China Department of Chemical and Materials Engineering University of Al-berta Edmonton Alberta Canada Department of Engineering University of Messina Messina Italy

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

Data-driven predictive models for end-point quality variables are important tools in industrial process modeling. However, establishing an effective predictive model with limited labeled data remains challenging. Transfer learning (TL) offers a solution by leveraging knowledge from similar but different tasks. This paper introduces a novel TL-based predictive model, domain-adaptation parallel stacked auto encoders (DA-PSAE), which can extract and accumulate knowledge from multiple similar processes. First, a parallel model structure is designed for the simultaneous extraction of static and plastic latent features. Besides, an effective TL-based training strategy is proposed, which utilizes data from multiple similar processes. The proposed model is applied to a sulfur recovery unit composed of four parallel sub-units. Experimental results verify the effectiveness of the proposed model.

关键词： Training Industries Process modeling Transfer learning Predictive models Feature extraction Data models

来源：评论

学校读者我要写书评

暂无评论

Mixture Gaussian Process Model with Gaussian Mixture Distribution for Big Data

SSRN

引用

SSRN 2024年

作者： Guan, Yaonan Li, Dewei He, Shaoying Ren, Shuangshuang Liu, Shuren Key Laboratory of System Control and Information Processing Department of Automation Shanghai Jiao Tong University Dongchuan Road 800 Shanghai200240 China Northwest Branch China Petroleum Exploration and Development Research Institute Yanerwan Road 535 Gansu Lanzhou730000 China

In the era of chemical big data, the high complexity and strong interdependencies present in the datasets pose considerable challenges when constructing accurate parametric models. The Gaussian process model, owing to its non-parametric nature, demonstrates better adaptability when confronted with complex and interdependent data. However, the standard Gaussian process has two significant limitations. Firstly, the time complexity of inverting its kernel matrix during the inference process is tremendous. Secondly, all data share a common kernel function parameter, which mixes different data types and reduces the model accuracy in mixing-category data identification problems. In light of this, this paper proposes a mixture Gaussian process model that addresses these limitations. This model reduces time complexity and distinguishes data based on different data features. It incorporates a Gaussian mixture distribution for the inducing variables to approximate the original data distribution. Stochastic Variational Inference is utilized to reduce the computational time required for parameter inference. The inducing variables have distinct parameters for the kernel function based on the data category, leading to improved analytical accuracy and reduced time complexity of the Gaussian process model. Numerical experiments are conducted to analyze and compare the performance of the proposed model on different-sized datasets and various data category cases. © 2024, The Authors. All rights reserved.

关键词： Big data

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：