检索结果-内蒙古大学图书馆

Air Pollution Monitoring By Integrating Local and Global Information in Self-Adaptive Multiscale Transform Domain

IEEE Transactions on Multimedia 2025年 27卷 3716-3728页

作者： Gu, Ke Liu, Yuchen Liu, Hongyan Liu, Bo Qiao, Junfei Lin, Weisi Zhang, Wenjun Beijing University of Technology School of Information Science and Technology Engineering Research Center of Intelligent Perception and Autonomous Control of Ministry of Education Beijing Laboratory of Smart Environmental Protection Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing Artificial Intelligence Institute Beijing100124 China Massey University School of Mathematical and Computational Sciences New Zealand Nanyang Technological University College of Computing and Data Science Singapore Shanghai Jiao Tong University Institute of Image Communication and Information Processing Shanghai China

As the deadliest form of pollution, air pollution had a prolonged severe damage to the human health and life safety of nearly 99% of the world's population. Facing to the problem that billions of tons of pollutants discharged into the air per year by industrial activities, this paper proposed a novel image-based air pollution monitor (IAPM) by incorporating local and global information in the self-adaptive multiscale transform domain, so as to achieve the timely and effective leakage detection of typical air pollutants from a single image. To be specific, this paper first developed a screen-shaped module according to two significant findings in visual neuroscience, which include the high sensitivity of human eyes to horizontal and vertical stimuli and the center-surround inhibition, by designing and fusing the square module, horizontal strip module and vertical strip module parallelly for simulating the behaviour of human eyes to extract local features. Second, the learnable weights and proportional mapping were applied to incorporate the screen-shaped module and lightweight vision transformer as backbone, towards more richly exploiting and fusing local and global information just as the way a brain perceives external stimuli. Third, a new self-adaptive multiscale transform domain method was devised based on two motivations from the visual characteristics of multiscale perception and the brain characteristics of self-adaptive domain transform to modify the backbone by using the operations of pooling and pointwise convolution. Extensive experiments implemented on the datasets of carbon particulate matters and ethylene leakage confirmed the superior monitoring performance of the proposed IAPM model beyond the state-of-the-art (SOTA) peers by an accuracy gain of about 4%. Furthermore, the proposed IAPM model only required 0.089 GFLOPs and 0.15 million model parameters, remarkably outperforming SOTA competitors in computational efficiency and storage resources. © 1999-2

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Improving the Short-Range Precipitation Forecast of Numerical Weather Prediction through a Deep Learning-Based Mask Approach

引用

Advances in Atmospheric sciences 2024年第8期41卷 1601-1613页

作者： Jiaqi ZHENG Qing LING Jia LI Yerong FENG School of Computer Science and Engineering/Guangdong Provincial Key Laboratory of Computational Science Sun Yat-Sen UniversityGuangzhou 510006China School of Mathematics Sun Yat-Sen UniversityGuangzhou 510275China Guangzhou Institute of Tropical and Marine Meteorology/Guangdong Provincial Key Laboratory of Regional Numerical Weather Prediction Guangzhou 510641China Shenzhen Institute of Meteorological Innovation Shenzhen 518038China

Due to various technical issues,existing numerical weather prediction(NWP)models often perform poorly at forecasting rainfall in the first several *** correct the bias of an NWP model and improve the accuracy of short-range precipitation forecasting,we propose a deep learning-based approach called UNet Mask,which combines NWP forecasts with the output of a convolutional neural network called *** UNet Mask involves training the UNet on historical data from the NWP model and gridded rainfall observations for 6-hour precipitation *** overlap of the UNet output and the NWP forecasts at the same rainfall threshold yields a *** UNet Mask blends the UNet output and the NWP forecasts by taking the maximum between them and passing through the mask,which provides the corrected 6-hour rainfall *** evaluated UNet Mask on a test set and in real-time *** results showed that UNet Mask outperforms the NWP model in 6-hour precipitation prediction by reducing the FAR and improving CSI *** tests also showed that different small rainfall thresholds applied to the UNet and the NWP model have different effects on UNet Mask's forecast *** study shows that UNet Mask is a promising approach for improving rainfall forecasting of NWP models.

关键词： deep learning numerical weather prediction(NWP) 6-hour quantitative precipitation forecast

来源：评论

学校读者我要写书评

暂无评论

Surface tension effects on Rayleigh-Taylor instability in nonideal fluids:A multiple-relaxation-time discrete Boltzmann study

引用

science China(Physics,Mechanics & Astronomy) 2024年第12期67卷 87-105页

作者： Feng Chen Aiguo Xu Jiahui Song Yanbiao Gan Yudong Zhang Ning Guan School of Aeronautics Shan Dong Jiaotong UniversityJinan 250357China National Key Laboratory of Computational Physics Institute of Applied Physics and Computational MathematicsBeijing 100088China HEDPS Center for Applied Physics and Technologyand College of EngineeringPeking UniversityBeijing100871China State Key Laboratory of Explosion Science and Safety Protection Beijing Institute of TechnologyBeijing100081China National Key Laboratory of Shock Wave and Detonation Physics Mianyang621999China School of Aerospace Engineering Beijing Institute of TechnologyBeijing100081China Hebei Key Laboratory of Trans-Media Aerial Underwater Vehicle North China Institute of Aerospace EngineeringLangfang065000China School of Mechanics and Safety Engineering Zhengzhou UniversityZhengzhou450001China

A multi-relaxation-time discrete Boltzmann model for compressible non-ideal gases with adjustable specific heat ratio is proposed,and the impact of surface tension on Rayleigh-Taylor instability(RTI)is investigated from two perspectives:macroscopic and non-equilibrium *** terms of physical cognition,(1)it is found that there are two critical surface tensions:the upper critical value and the lower critical *** the surface tension is below the lower critical value,the RTI evolution aligns qualitatively with the case without surface *** the surface tension coefficient increases,the inhibitory effect on RTI evolution gradually *** the surface tension is greater than the upper critical value,the disturbance interface tends to be stable after multiple *** the surface tension is in between,the perturbation interface first reverses,or even multiple reverses,and then destabilizes and develops rapidly.(2)A series of new kinetic behavior characteristics are given,and it is found that some behavior characteristics have important reference value for the control of system *** example,the first peak in the growth rate of the global average non-organized momentum flux strength D_(2)corresponds to the onset of the regular nonlinear *** peak in the growth rate of the global average non-organized energy flux strength D_(3,1)marks the beginning of the re-acceleration *** onset of the uniform acceleration stage in the growth rate of the global average nonequilibrium strength D_(T NE)corresponds to the system transitioning into the regular nonlinear stage,while its terminal point(also the peak)corresponds to the system entering the re-acceleration *** insights enhance understanding of RTI mechanisms in complex fluids kinetically.

关键词： statistical mechanics of classical fluids flow instabilities kinetic theory

来源：评论

学校读者我要写书评

暂无评论

Phase-field-based lattice Boltzmann method for containerless freezing

引用

Physical Review E 2024年第3期110卷 035301页

作者： Jiangxu Huang Lei Wang Zhenhua Chai Baochang Shi School of Mathematics and Statistics School of Mathematics and Physics Institute of Interdisciplinary Research for Mathematics and Applied Science Hubei Key Laboratory of Engineering Modeling and Scientific Computing

In this paper we first propose a phase-field model for the containerless freezing problems, in which the volume expansion or shrinkage of the liquid caused by the density change during the phase change process is considered by adding a mass source term to the continuum equation. Then a phase-field-based lattice Boltzmann (LB) method is further developed to simulate solid-liquid phase change phenomena in multiphase systems. We test the developed LB method by the problem of conduction-induced freezing in a semi-infinite space, the three-phase Stefan problem, and the droplet solidification on a cold surface, and the numerical results are in agreement with the analytical and experimental solutions. In addition, the LB method is also used to study the rising bubbles with solidification. The results of the present method not only accurately capture the effect of bubbles on the solidification process, but also are in agreement with the previous work. Finally, a parametric study is carried out to examine the influences of some physical parameters on the sessile droplet solidification, and it is found that the time of droplet solidification increases with the increase of droplet volume and contact angle.

关键词： Drops & bubbles Liquid-solid phase transition

来源：评论

学校读者我要写书评

暂无评论

Emergency Transportation and Structural Prediction and Optimization of Goods Based on ARIMA and Multi-objective E-commerce Logistics Network Model 1

Emergency Transportation and Structural Prediction and Optim...

引用

1st IEEE International Conference on Applied Intelligence and Sustainable computing, ICAISC 2023

作者： Nie, Yiyang Chen, Xiang Wu, Xuanli Deng, Zihao Hunan University of Science and Technology School of Computer Science and Engineering Xiangtan China Hunan Key Laboratory for Service Computing and Novel Software Technology Xiangtan China Hunan University of Science and Technology Shcool of Mathematics and Computational Science Xiangtan China

ISBN: (纸本)9798350323795

With the development of the internet, online shopping has gradually become a popular way of shopping among the general public, which in turn poses a greater challenge to the e-commerce logistics network. Predicting the volume of goods for each logistics site and route, and establishing a model for quickly adjusting the network in response to sudden situations can save logistics network costs and improve its efficiency. Therefore, this article has done the following work: first, it establishes an effective logistics network volume prediction model;second, for the two scenarios of network structure that cannot be modified and can be modified, it provides a model that can effectively guide the adjustment of the volume of goods on each route when a logistics site is closed;finally, it establishes a logistics network evaluation model to evaluate the importance of logistics sites and routes. © 2023 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

AN ACCELERATION STRATEGY FOR RANDOMIZE-THEN-OPTIMIZE SAMPLING VIA DEEP NEURAL NETWORKS

引用

Journal of computational mathematics 2021年第6期39卷 848-864页

作者： Liang Yan Tao Zhou School of Mathematics Southeast UniversityNanjing210096China Nanjing Center for Applied Mathematics Nanjing211135China LSEC Institute of Computational Mathematics and Scientific/Engineering ComputingAcademy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China

Randomize-then-optimize (RTO) is widely used for sampling from posterior distributions in Bayesian inverse problems. However, RTO can be computationally intensive forcomplexity problems due to repetitive evaluations of the expensive forward model and itsgradient. In this work, we present a novel goal-oriented deep neural networks (DNN) surrogate approach to substantially reduce the computation burden of RTO. In particular,we propose to drawn the training points for the DNN-surrogate from a local approximatedposterior distribution – yielding a flexible and efficient sampling algorithm that convergesto the direct RTO approach. We present a Bayesian inverse problem governed by ellipticPDEs to demonstrate the computational accuracy and efficiency of our DNN-RTO approach, which shows that DNN-RTO can significantly outperform the traditional RTO.

关键词： Bayesian inverse problems Deep neural network Markov chain Monte Carlo

来源：评论

学校读者我要写书评

暂无评论

Bayesian Network-based Active Learning for Ontology-based Video Retrieval using Hidden Markov Logic Model with Edge Histogram Descriptor

Bayesian Network-based Active Learning for Ontology-based Vi...

引用

2023 IEEE IAS Global Conference on Emerging Technologies, GlobConET 2023

作者： Sathiyaprasad, B. Sreeji, S. Satheeshkumar, B. Menaka, D. Babu, K. Jones, G. Maria Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai600 119 India Galgotias University School of Computing Science and Engineering UP Greater Noida India SRM Institute of Science and Technology Katankulathur Department of Computational Intelligence Chennai603203 India

ISBN: (纸本)9798350331790

A large amount of data is collected, analysed, and used on a regular basis by a large number of people for web pages, books, journals, and files which make up a significant portion of the data on the Internet. The burden on significant content-based retrieval and other applications is increasing as the volume of surveillance video data grows. Therefore to reduce the burden during retrieval and to solve the problem of video surveillance an ontology based video retrieval by feature extraction and classification techniques is proposed. In the Initial step the examined form of description files in OWL (Web Ontology Language is fed as input. Then the video pre-processed and segmented before extracting the features. The features of video has been extracted using "Hidden Markov Logic Model With Edge Histogram Descriptor (HMLM-EHD)"in which the spatio based features are extracted with Shape-based features that define object shapes in image is extracted from object contours or regions. After the extraction of features, classification is done using Bayesian network based active learning. The retrieval subsystem evaluates the provided query, performs similarity matching operations (which can be done using the correlation Distance Algorithm), and finally provides the result to the end user for these categorised video frames. The experimental results shows retrieved video frames and their parametric analysis in terms of accuracy of 94%, precision of 85%, recall of 71 % and F-1 score of 73%. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

An Optimization Method for Renewable Energy and Energy Storage Capacity Allocation Based on Temporal Production Simulation 7

An Optimization Method for Renewable Energy and Energy Stora...

引用

7th IEEE Conference on Energy Internet and Energy System Integration, EI2 2023

作者： Du, Hongbo Li, Chi Chen, Liang Zhang, Jinping Kou, Caixia College of Sciences Beijing University of Posts and Telecommunications Beijing China National Key Laboratory of Renewable Energy Grid-Integration China Electric Power Research Institute Beijing China Institute of Computational Mathematics and Scientific Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350345094

With the rapid expansion of large-scale renewable energy bases in China, optimizing the allocation of renewable energy and energy storage capacity is crucial for improving system efficiency. In this paper, a joint optimal configuration method of wind-photovoltaic-energy storage capacity based on time series production simulation is proposed for renewable energy transmission base. Its aim is to minimize the total investment cost of the system under certain constraints about the proportion of renewable energy power generation, renewable energy utilization rate, conventional thermal power operation, energy storage power station operation, ultra-high voltage direct current (UHVDC) regulation and power transmission. To handle the nonlinear constraints, linearization is achieved by introducing integer variables. For the complex operation constraints of conventional thermal power and UHVDC channel, a simplified modeling method of start-stop cycle and adjustment cycle is proposed, which can effectively reduce the number of integer variables and improve the solving efficiency. The effectiveness of the proposed method is tested on the data of a renewable energy base in Northwest China. © 2023 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Leveraging Instruction-based Learning for Effective UAV Traffic Management in Dynamic Environment

Leveraging Instruction-based Learning for Effective UAV Traf...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Ramya, R.S. Daniel, Keren Lois Rajkumar, S. Madhavan, Sruthi S. Akshya, J. Choudhry, Mani Deepak Sri Ramakrishna Engineering College Department of Computer Science and Engineering Coimbatore India KGiSL Institute of Technology Department of Computer Science and Business Systems Coimbatore India Sona College of Technology Department of Information Technology Salem India Nehru Institute of Engineering and Technology Department of Artificial Intelligence and Data Science Coimbatore India Srm Institute of Science and Technology Department of Computational Intelligence Chennai India Srm Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798331509828

With the popularization of UAVs (Unmanned Aerial Vehicles) in surveillance, delivery services, environmental monitoring, and increasingly other operational aspects, besides the need to take off and land, efficient traffic management becomes integral for assuring and securing further development and exploitation. Most of the existing traffic management systems for UAVs depend on traditional rule-based algorithms or simpler machine learning techniques, such as DQN or PPO. However, these systems also have enormous challenges: dynamic environments, high-density traffic, and robust decision-making over unpredictable weather and network conditions. In addition, the above traditional models usually experience difficulties in balancing exploration and exploitation, leading to suboptimal routing and enlarged collision risks in complicated urban airspaces. These challenges have driven us to develop a new proposal: a UA V traffic management framework based on Double Deep Q-Network (DDQN) combined with Instruction-Based Learning. In this approach, advanced learning for DDQN optimizes processes at decision-making points for UAVs. The model proposed herein, along with comprehensive simulations and quantitative analyses, demonstrated higher performance in terms of leadership and cumulative rewards while keeping lower training loss compared to the classical algorithms such as DQN, A3C, and PPO. At the same time, the DDQN model presented a better success rate (95%), as also reflected in the balanced precision-recall curve showing an area under the curve of 0.90, over others in the on-point prediction of UAVstate and safety margin of collision. Our experimental results demonstrate that the proposed DDQN-based framework significantly enhances UA V traffic management by optimizing energy consumption in complex airspaces and reducing the risk of collision. © 2025 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Hybrid architecture CNN-BLSTM for automatic speech recognition 3

Hybrid architecture CNN-BLSTM for automatic speech recogniti...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Dar, Muzaffar Ahmad Pushparaj, Jagalingam Vellore Institute of Technology School of Advanced Sciences Department of Mathematics Tamil Nadu Vellore India Vellore Institute of Technology School of Computer Science and Engineering Department of Computational Intelligence Tamil Nadu Vellore India

ISBN: (纸本)9798350372120

With several deep learning approaches, the domain of automatic speech recognition (ASR) has seen notable advancements in recent times. The domains of intelligent human- computer interaction and machine translation greatly benefited from accurate speech recognition. The present study introduces a hybrid architecture amalgamating a convolutional neural network (CNN) and bidirectional long short-term memory (BLSTM) for speech recognition. For aligning speech input sequences with corresponding text output sequences, it uses the connectionist temporal classification (CTC) technique. The experiments were done on the LJ speech dataset, and the results showed with an increased number of training samples, the performance of the speech recognition algorithm tended to be increased but the time taken for training gradually increased over time. Moreover, a trained speech recognition algorithm exhibits a longer training time when the recognition accuracy is lower. In this study, we implemented a hybrid deep learning model CNN-BLSTM, in conjunction with the CTC loss function, which attains a word error rate (WER) of 36.97% on the testing dataset. © 2024 IEEE.

关键词： Speech recognition

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：