检索结果-内蒙古大学图书馆

Chinese Control and Decision Conference, CCDC

作者： Yanling Qin Hongyan Ma Wei He School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing China School of Electrical and Information Engineering Institute of Distributed Energy Storage Safety Big Data Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and Architecture Beijing China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

To address the problem that the Air Quality Index (AQI) is difficult to predict, a prediction model based on Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN), Sparrow Search Algorithm (SSA), and Long Short-Term Memory (LSTM) is proposed. First, the AQI sequence was decomposed by ICEEMDAN. Second, the initial learning rate, max training epoch and the number of hidden layers of the LSTM model are optimized by the SSA algorithm to establish the SSA-LSTM model. Last, the results decomposed were imported into the SSA-LSTM model to predict AQI. Compared with the prediction results of the LSTM, CEEMD-LSTM, and CEEMDAN-SSA-LSTM model, the accuracy (measured by correlation coefficients) of the CEEMDAN-SSA-LSTM is 98%. The result confirmed that the ICEEMDAN-SSA-LSTM can obtaining an improvement of the correlation coefficients and reduce the mean square error, which is valuable for engineering applications.

关键词： Training Correlation coefficient Adaptation models Accuracy Empirical mode decomposition Atmospheric modeling Predictive models

来源：评论

学校读者我要写书评

暂无评论

Spatial Commonsense Reasoning for Machine Reading Comprehension 9th

Spatial Commonsense Reasoning for Machine Reading Comprehen...

引用

19th International Conference on Advanced data Mining and Applications, ADMA 2023

作者： Lin, Miaopei Wang, Meng-xiang Yu, Jianxing Wang, Shiqi Lai, Hanjiang Liu, Wei Yin, Jian School of Computer Science and Engineering Sun Yat-sen University Guangzhou China School of Artificial Intelligence Sun Yat-sen University Zhuhai China China National Institute of Standardization Beijing100088 China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

ISBN: (纸本)9783031466632

This paper studies the problem of spatial commonsense reasoning for the machine reading comprehension task. Spatial commonsense is the human-shared but latent knowledge of object shape, size, distance, and position. Reasoning this abstract knowledge can facilitate machines better perceive their surroundings, which is crucial for general intelligence. However, this valuable topic is challenging and has been less studied. To bridge this research gap, we focus on this topic and propose a new method to realize spatial reasoning. Given a text, we first build a potential reasoning graph based on its parsing tree. To better support spatial reasoning, we retrieve the related commonsense entities and relations from external knowledge sources, including the pre-trained language model (LM) and knowledge graph (KG). LM covers all kinds of factual knowledge and KG has abundant commonsense relations. We then propose a new fusion method called LEGRN (LM Edge-GNN Reasoner Networks) to fuse the text and graph. LEGRN adopts layer-based attention to integrate the LM text encoder and KG graph encoder, which can capture correlations between LM text context and KG graph structure. Considering that spatial relations involve a variety of attributes, we propose an attribute-aware inferential network to deduce the correct answers. To evaluate our approach, we construct a new large-scale dataset named CRCSpatial, consisting of 40k spatial reasoning questions. Experiment results illustrated the effectiveness of our approach. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Estimation and spatiotemporal variations of black carbon aerosol over the North China Plain in 2018

Estimation and spatiotemporal variations of black carbon aer...

引用

2023 International Conference on Remote Sensing, Mapping, and Geographic Systems, RSMG 2023

作者： Cai, Kun Qi, Yongkai Li, Shenshen Zhang, Shuo College of Computer and Information Engineering Henan University Kaifeng475004 China Henan Key Laboratory of Big Data Analysis and Processing Kaifeng475004 China State Key Laboratory of Remote Sensing Science Aerospace Information Research Institute Chinese Academy of Sciences Beijing100101 China

ISBN: (纸本)9781510668898

With the rapid economic development in the North China Plain, the significant emissions of black carbon (BC) aerosol have exerted notable impacts on climate, environment, and health, making it a hot topic in environmental studies in recent years. To compensate for the insufficient ground monitoring data, the PM2.5 satellite remote sensing inversion data and chemical model simulation data were utilized, applying the proportionality factor method to estimate the satellite concentration of BC. The estimation results were validated using BC monitoring data from seven stations in 2018, and based on this, the spatiotemporal variations of BC satellite concentration was obtained. The results showed that the estimated BC concentration using the proportionality factor method had good accuracy, with a correlation coefficient (R2) of 0.72. The spatial distribution of BC over the North China Plain in 2018 exhibited a decreasing trend from the inner region to the outer region, with high concentration areas mainly located in provinces with high straw burning and steel production. The seasonal variation of BC in the North China Plain in 2018 was pronounced, showing higher concentrations in autumn and winter and lower concentrations in spring and summer. © 2023 SPIE.

关键词： Satellites

来源：评论

学校读者我要写书评

暂无评论

Real Time Voice/Speech Command and Control System (CCS) for Unmanned Aerial and Ground Vehicles on 4G Cellular/GPRS Network

Real Time Voice/Speech Command and Control System (CCS) for ...

引用

Information Technologies and Communications (GCITC), Global Conference on

作者： Leelavathy B Anurag Varma Penmesta Ram Mohan Rao Kovvur Raghavendra Kune Department of Information Technology Vasavi College of Engineering Hyderabad India Department of Space Advanced Data Processing Research Institute Hyderabad India

Unmanned Autonomous systems are the vehicles/systems that operate without/less human interaction and carryout the operations by means of advanced electronic components as On-Board Computing technologies. Unmanned Autonomous systems are some of the most important applications of Artificial Intelligence (AI) and the development of such technologies promote innovations in Advanced Intelligent technologies. Examples of Unmanned Autonomous systems are- Unmanned Aerial Vehicles (UAV’s), Unmanned Ground vehicles (UGVs) Unmanned Water Vehicles (UWV) those have made ground-breaking advancements in many real-world applications for societal needs. Some of the applications include from surveying to transportation to security surveillance etc. Most of the Unmanned Autonomous systems are operated through HCI (Human Computer Interface) like Ground Control Stations (GCS) or Joystick for commanding and controlling the vehicles via command is sent in the compatible format by which vehicles would understand for operations. However, a very less/no work is carried out to operate the vehicles through voice/speech and translate the same into the compatible format by which the system would understand. HCI technologies with speech/edge computing devices is increasing in operating the vehicles through voice/speech models running on the edge devices. However, the accuracy and real time performance of the interconnected devices plays a major role. In this paper, we propose to build one such system, operating on the edge computing devices for Unmanned Autonomous systems to operate through speech/voice commanding. In this paper, we present one such Autonomous unmanned system for operating UAV’s using Cellular (GPRS) communication, using Deep Learning system (LSTM) network running on Edge Computing devices, working with DroneKit with Speech based Commanding system. The system has an accuracy of 95.36% with Google Speech data augmented with custom data sets and the system has been tested in real t

关键词：

来源：评论

学校读者我要写书评

暂无评论

Capacity Maximization for Double Passive/Active RIS-Aided MISO Systems in Multi-User Scenarios

引用

IEEE Internet of Things Journal 2025年

作者： Peng, Xin Liu, Chenyu Yu, Chao Xie, Wenwu Yang, Liang Hunan Institute of Science and Technology School of Information Science and Engineering Yueyang414006 China Hunan Engineering Research Center for Autonomous Data Perception and Processing in Industrial Intelligent Networking Yueyang414006 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China

This paper addresses the problem of capacity maximization in double reconfigurable intelligent surface (RIS) -aided multiple-input single-output (MISO) systems under multi-user scenarios. A system model is proposed for double RIS-aided MISO configurations, incorporating both passive RIS (PRIS) and active RIS (ARIS). The primary objective is to maximize the minimum channel capacity across all users, and a corresponding optimization problem is formulated to achieve this goal. To overcome the challenges posed by the fractional structure of the non-convex objective function, auxiliary variables are introduced, and the bisection method is utilized. Given the highly coupled and nonconvex nature of the optimization variables, a joint alternating optimization (AO) algorithm is designed based on the bisection method and successive convex approximation (SCA), enabling iterative determination of the beamforming vectors at the base station and the reflection coefficients of RISs. The results indicate that deploying double RISs substantially enhances the system’s channel capacity through reflected links. Notably, the ARIS protocols yield higher performance gains, particularly under scenarios involving high total power and large amplification factors. In multi-user environments, the double RIS configuration significantly outperforms the single RIS setup due to the increased degrees of freedom, especially when supported by ARIS protocols. These findings underscore the substantial potential and advantages of double RIS configurations in complex communication environments. © 2014 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potentials of polymer-based CMUTs for 3D Ultrasound Computed Tomography

Exploring the Potentials of polymer-based CMUTs for 3D Ultra...

引用

IEEE Symposium (IUS) Ultrasonics

作者： Martin Angerer Jonas Welsch Carlos D. Gerardo Nicole V. Ruiter Edmond Cretu Robert Rohling Department of Electrical and Computer Engineering University of British Columbia (UBC) Vancouver Canada Institute for Data Processing and Electronics Karlsruhe Institute of Technology (KIT) Karlsruhe Germany

This work presents a quantitative evaluation of polymer-based Capacitive Micromachined Ultrasonic Transducers (polyCMUTs) for 3D Ultrasound Computed Tomography (3D USCT). The study was motivated by limitations of the currently used PZT fiber technology in terms of bandwidth and transmit sensitivity. We developed finite element models of polyCMUT elements consisting of 127 cells to predict the acoustic performance. We fabricated prototype transducers using a novel method for microstructuring polymer layers. The produced samples reach a fractional bandwidth of 116%, an opening angle of 44° and increase the transmit sensitivity by 54%, compared to the PZT fiber transducers. The developed models allow for accurate predictions of the acoustic field over a large range of angles and frequencies. More work is required to improve the reliability and reduce sample-to-sample variations. Based on the measured performance and the general properties of the technology, polyCMUTs are very promising for 3D USCT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Drug-Drug Interaction Prediction by Knowledge Graph Embedding

Enhancing Drug-Drug Interaction Prediction by Knowledge Grap...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： CHAO LIU XIZHAO WANG QIANG LIU Big Data Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

ISBN: (数字)9798331528041

ISBN: (纸本)9798331528058

Drug-drug interactions (DDIs) refer to the synergistic or antagonistic effects between different drugs. Synergistic effects can enhance therapeutic efficacy, while antagonistic effects may reduce efficacy or even trigger adverse reactions, worsening the patient's condition. Most existing DDI prediction studies overlook the features of chemical bonds between atoms within drug molecules and the interaction types between drug pairs, which to some extent limits the accuracy and reliability of the predictions. In view of this, we have designed a novel framework called KGE-DDI, which leverages knowledge graph embedding (KGE) technology to enhance the prediction of DDIs. Specifically, for individual drug molecules, KGE-DDI first integrates the features of atoms and chemical bond. Then, by introducing attention mechanisms and graph neural network technology, it learns representations of the drug molecules. For pairs of drug molecules, KGE-DDI models their interactions utilizing atom-level Pearson correlation matrices. Finally, it predicts the interactions between drug pairs by employing our designed scoring function. We conducted comprehensive experiments under both transductive and inductive settings, and the results demonstrate the effectiveness and superiority of KGE-DDI in three scenarios: (existing drug, existing drug), (new drug, new drug), and (new drug, existing drug).

关键词： Drugs Measurement Correlation Knowledge graphs Atoms Predictive models Graph neural networks Reliability Chemicals Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Augmenting Prototype Network with TransMix for Few-shot Hyperspectral Image Classification

arXiv

引用

arXiv 2024年

作者： Liu, Chun Yang, Longwei Dong, Dongmei Li, Zheng Yang, Wei Han, Zhigang Wang, Jiayao School of Computer and Information Engineering Henan Key Laboratory of Big Data Analysis and Processing Henan Engineering Laboratory of Spatial Information Processing Henan Industrial Technology Academy of Spatio-Temporal Big Data Henan University Zhengzhou450046 China Beijing Electro-Mechanical Engineering Institute Beijing100074 China College of Geography and Environmental Science Henan Industrial Technology Academy of Spatio-Temporal Big Data Henan University Zhengzhou450046 China

Few-shot hyperspectral image classification aims to identify the classes of each pixel in the images by only marking few of these pixels. And in order to obtain the spatial-spectral joint features of each pixel, the fixed-size patches centering around each pixel are often used for classification. However, observing the classification results of existing methods, we found that boundary patches corresponding to the pixels which are located at the boundary of the objects in the hyperspectral images, are hard to classify. These boundary patchs are mixed with multi-class spectral information. Inspired by this, we propose to augment the prototype network with TransMix for few-shot hyperspectrial image classification(APNT). While taking the prototype network as the backbone, it adopts the transformer as feature extractor to learn the pixel-to-pixel relation and pay different attentions to different pixels. At the same time, instead of directly using the patches which are cut from the hyperspectral images for training, it randomly mixs up two patches to imitate the boundary patches and uses the synthetic patches to train the model, with the aim to enlarge the number of hard training samples and enhance their diversity. And by following the data agumentation technique TransMix, the attention returned by the transformer is also used to mix up the labels of two patches to generate better labels for synthetic patches. Compared with existing methods, the proposed method has demonstrated sate of the art performance and better robustness for few-shot hyperspectral image classification in our experiments. All the codes are available at https://***/HENULWY/APNT. Copyright © 2024, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Power Cycle Testing, Behaviour of Clip-Sintered Bare Dies

Power Cycle Testing, Behaviour of Clip-Sintered Bare Dies

引用

International Conference on Electronics Packaging (ICEP)

作者： Felix Steiner Janis Blank Dai Ishikawa Hideo Nakako Liuda Mereacre Thomas Blank Institute for Data Processing and Electronics Karlsruhe Institute of Technology Karlsruhe Germany Institute of Radio Frequency Engineering and Electronics Karlsruhe Institute of Technology Karlsruhe Germany Resonac Corporation Institute for Advanced Integrated Technology Ibaraki Japan Institute for Applied Materials Karlsruhe Institute of Technology Karlsruhe Germany

ISBN: (数字)9784991191190

ISBN: (纸本)9798331514747

Sintering is a state-of-the-art die-attach method for high-reliability power modules, and double-sided sintering can further enhance device lifetime by replacing aluminum wire bonds with robust copper interconnections. We investigate the feasibility of thick Cu clip sintering as a top-side connection for $\text{SiC}$ power devices, aiming to reduce parasitic inductance and improve thermal performance. The device under test, comprising a double-sided sintered $\text{SiC}$ MOSFET and a thick copper clip, is evaluated using scanning acoustic microscopy (SAM) and power cycling tests (PCT). SAM reveals variations in sintering quality, highlighting the need for process optimization. PCT results show a wide spread in cycles to failure, with early failures at only 2500 cycles while other devices survive more than 80000 cycles. Additionally, gate leakage currents in failed devices suggest potential gate oxide degradation due to thermomechanical stresses. Despite challenges, the study demonstrates the potential of Cu clip sintering for high-reliability $\text{SiC}$ power modules, emphasizing the need for further refinement in processing techniques.

关键词： MOSFET Silver Thermomechanical processes Sintering Multichip modules Copper Wire Optimization Stress Testing

来源：评论

学校读者我要写书评

暂无评论

Additive Manufacturing of Ceramics opens the door to Components for Biomanufacturing Applications with high Functionality 6

Additive Manufacturing of Ceramics opens the door to Compone...

引用

6th CIRP Conference on BioManufacturing, BioM 2024

作者： Scheithauer, Uwe Holtzhausen, Stefan Wiemer, Hajo Fraunhofer Institute for Ceramic Technologies and Systems Group Additive and Hybrid Manufacturing Winterbergstr. 28 Dresden01277 Germany TUD Dresden University of Technology Institute of Machine Elements and Machine Design Virtual Product Development Group Advanced Geometric Modeling And Analysis Dresden01062 Germany TUD Dresden University of Technology Institute of Mechatronic Engineering Machine Tools Development and Adaptive Controls Department of Machine Data Processing Dresden01062 Germany

Significant advancements in production technology, materials, component design, and data science foster innovation across industries, including biomanufacturing. Ceramic materials, adapted additive manufacturing processes, and novel construction methods hold immense innovation potential due to ceramics' exceptional thermal, chemical, and mechanical properties. Additive manufacturing enables the creation of intricate ceramic components with unprecedented functionality. Hybridizing manufacturing technologies and materials facilitates direct integration of additional features like sensors and actuators. Despite their potential, ceramic materials remain underutilized. This article aims to spark a discourse on leveraging high-performance ceramic components in biomanufacturing, leveraging superior material properties, innovative design methods, additive manufacturing, process data analysis, and AI. © 2024 The Authors.

关键词： Ceramic materials

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：