检索结果-内蒙古大学图书馆

3rd International Conference on Machine Vision, Automatic Identification, and Detection, MVAID 2024

作者： Liu, Dongsheng Peng, Zhiping He, Jieguang Liang, Zhushen Qiu, Jinbo Cui, Delong School of Information and Control Engineering Jilin Institute of Chemical Technology Jilin132022 China School of Electronic and Information Engineering Guangdong University of Petrochemical Technology Maoming525000 China

ISBN: (纸本)9781510681880

Some effective word embeddings have been proposed by researchers and acted in NER (Named Entity Recognition) tasks, but these embeddings often suffer from under-utilization, resulting in poorly characterized word vectors encoded. Driven by the lack of entity information, I perform lexical enhancement techniques at the input layer of the NER model for Chinese. Roughly speaking, we introduce an attention mechanism to the Softlexicon approach, which makes the embedded entity information more complete. We conducted experiments. On all four Chinese NER datasets, the performance of the improved Softlexicon is improved compared to the original one. In addition to using different datasets, we also embedded the improve d Softlexicon in combi nation with different pre-trained models, and the attention mechanism still led to good performance. © 2024 SPIE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Entropy evolution law of general quadratic state in a laser channel

引用

Frontiers of physics 2025年第2期20卷 169-175页

作者： Xiang-Guo Meng Bao-Long Liang Jian-Ming Liu Xu-Cong Zhou School of Basic Medical Sciences Shandong Second Medical UniversityWeifang 261053China Shandong Provincial Key Laboratory of Optical Communication Science and Technology School of Physical Science and Information EngineeringLiaocheng UniversityLiaocheng 252059China

Using the integration within ordered products,we obtain the analytical density-operator evolution of the general quadratic state ρ_(0)in a laser channel,which always maintains the same form as the initial density operator ρ_(0).Introducing the differential representation of the von-Neumann entropy and two important resemble formulas,we analytically and numerically investigate the entropy evolution of the state ρ_(0)in a laser channel,which is determined by not only the competition of the gain and loss of the laser channel,but also the coefficients α,β of the initial quadratic state.

关键词： general quadratic state laser channel quantum entropy operator ordering integration within ordered product

来源：评论

学校读者我要写书评

暂无评论

A Novel Short-Term Load Forecasting Model Based on Bidirectional Long Short-Term Memory and Kolmogorov-Arnold Network

A Novel Short-Term Load Forecasting Model Based on Bidirecti...

引用

2024 China Automation Congress, CAC 2024

作者： Wang, Jiaqi Zhang, Linghua Hu, Feng School of Communication and Information Engineering Nanjing University of Posts and Telecommunications Nanjing China School of Communication and Information Engineering Nanjing University of Posts and Telecommunications Jiangsu Province Engineering Research Center of Communication and Network Technology Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9798350368604

With the development of modern power systems and the widespread adoption of smart grids, accurate short-term load forecasting has become increasingly important. Although Bidirectional Long Short-Term Memory (BILSTM) networks excel at capturing bidirectional dependencies in time series data, they exhibit limitations when dealing with highly nonlinear data and often lack interpretability. This paper proposes a novel prediction model based on BILSTM and Kolmogorov-Arnold Network (KAN). The model captures bidirectional contextual information through BILSTM and enhances nonlinear representation capabilities using KAN with learnable activation functions, thereby improving both interpretability and prediction accuracy. Experimental results demonstrate that the BILSTM-KAN model reduces the Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE) by 16.8%, 16.39%, and 16.6%, respectively. Compared to existing models, the BILSTM-KAN model exhibits significant advantages in short-term load forecasting tasks. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Prediction of Air Blower Flow Setpoint in Wastewater Treatment Plants Based on the LSTM Model 15th

Prediction of Air Blower Flow Setpoint in Wastewater Treatme...

引用

15th International Conference on Computer Science and its Applications, CSA 2023 and 17th KIPS International Conference on Ubiquitous information Technologies and Applications, CUTE 2023

作者： Xu, Jiuzhe Li, Xuefei Liu, Changqing Miao, Sheng School of Information and Control Engineering Qingdao University of Technology Qingdao China School of Environmental and Municipal Engineering Qingdao University of Technology Qingdao China

ISBN: (纸本)9789819724468

Effective wastewater treatment is key to protecting the environment, wastewater treatment plants are responsible for treating domestic sewage in built-up areas. The process of wastewater treatment is a long-term, complex, non-linear reaction, consuming chemicals and electrical energy to satisfy effluent standards. In the Anaerobic-Anoxic-Oxic process, Dissolved Oxygen (DO) needs to be accurately controlled to reduce treatment costs. Air blowers provide oxygen via the aeration system, and DO adjustment by changing the air blower flow setpoint. Most previous studies have considered single variables and linear control, and can not take comprehensive consideration of all effecting parameters. In this study, the Long Short-Term Memory model is used to predict the air blower flow setpoint, taking into account the effects of multiple variables. In addition, the Long Short-Term Memory (LSTM) model has lower Mean Absolute Error (MAE = 21.00), Root Mean Square Error (RMSE = 28.83) and Mean Absolute Percentage Error (MAPE = 0.47%) than the Support Vector Regression (SVR) and Feedforward Neural Networks (FNN). © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Feedforward neural networks

来源：评论

学校读者我要写书评

暂无评论

Explainable Neural Network for Sensitivity Analysis of Lithium-ion Battery Smart Production

引用

IEEE/CAA Journal of Automatica Sinica 2024年第9期11卷 1944-1953页

作者： Kailong Liu Qiao Peng Yuhang Liu Naxin Cui Chenghui Zhang School of Control Science and Engineering Shandong UniversityJinan 250061China Information Technology Analytics&Operations groupQueen’s University BelfastBelfast BT71NNUK

Battery production is crucial for determining the quality of electrode,which in turn affects the manufactured battery *** battery production is complicated with strongly coupled intermediate and control parameters,an efficient solution that can perform a reliable sensitivity analysis of the production terms of interest and forecast key battery properties in the early production phase is urgently *** paper performs detailed sensitivity analysis of key production terms on determining the properties of manufactured battery electrode via advanced data-driven *** be specific,an explainable neural network named generalized additive model with structured interaction(GAM-SI)is designed to predict two key battery properties,including electrode mass loading and porosity,while the effects of four early production terms on manufactured batteries are explained and *** experimental results reveal that the proposed method is able to accurately predict battery electrode properties in the mixing and coating *** addition,the importance ratio ranking,global interpretation and local interpretation of both the main effects and pairwise interactions can be effectively visualized by the designed neural *** to the merits of interpretability,the proposed GAM-SI can help engineers gain important insights for understanding complicated production behavior,further benefitting smart battery production.

关键词： Battery management battery manufacturing data science explainable artificial intelligence sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

A Downward Compatible Navigation and communication Integrated Signal technology

A Downward Compatible Navigation and Communication Integrate...

引用

2023 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2023

作者： Zou, Deyue Zhao, Yangzhen He, Liansheng Han, Shuai Dalian University of Technology School of Information and Communication Engineering Dalian China Harbin Institute of Technology School of Electronics and Information Engineering Harbin China

ISBN: (纸本)9798350321524

Satellite transmission technology is developing rapidly, and based on the satellite system's broadcast transmission ability, the satellite system's navigation and communication ability has become a hot topic of future development. In earlier research, our team proposed a satellite navigation and communication integrated technology based on spread spectrum broadband signals. The technology can significantly increase the GNSS satellite downlink broadcast rate while ensuring downward compatibility. This paper summarizes the technology and its technical system. The proposed broadcast signal consists of the navigation signal and communication signal. The navigation signal part is precisely the same as the existing GNSS signal and provides the synchronous service for the communication signal based on the original positioning service. Cyclic Code Shift Keying (CCSK) modulation is used for the communication signal. PN codes in the same family as the navigation signal are used for the spread spectrum. The communication and navigation signals are in the same frequency and phase on radio frequency and synchronized on the baseband. In order to avoid the degradation of detection performance and error performance caused by cross-correlation interference between navigation and communication signals, the code phase optimization algorithm is introduced to turn the cross-correlation function into a favorable condition and enhance the detection performance of the pilot channel and communication channel. Because of the discontinuity of the code phase set, the receiver of the signal can use the fuzzy decision algorithm to improve the fault tolerance of the system to phase jitter and synchronization deviation. Because the proposed signal system transmits information by adjusting the signal delay, the signal is susceptible to the multipath effect. To solve this problem, we design the master-slave Rake receiver strategy by taking advantage of the characteristics of the pilot and communicat

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Design of electrical cabinet wire cutting machine based on STM32 3

Design of electrical cabinet wire cutting machine based on S...

引用

2024 3rd International Conference on Electrical, control and information technology, ECITech 2024

作者： Chen, Hao Liu, Hongxi Mu, Xiaofei Wang, Chaoyong School of Electrical and Information Engineering Changchun Institute of Technology Jilin Changchun130012 China School of Information and Control Engineering Jilin Institute of Chemical Technology Jilin 132022 China

The wire in the electric cabinet is one of the keys to ensuring the normal operation of the electric cabinet. In order to improve the production efficiency of wire cutting, this project designed a wire-cutting machine for an electrical cabinet, which could recognize the CSV table file of the electrical cabinet wiring list on a U disk and cut wires of different lengths and quantities according to the order in the file. The main control chip of the device uses STM32 single chip microcomputer (STM32F103C8T6) and CH376S module to realize the function of reading CSV file on U disk through serial communication. In terms of control, the device adopts a proportional-integral-differential (PID) control algorithm to achieve accurate control of the JGB37-520 gear motor and TD-8120MG steering gear and then realizes wire feeding, wire stripping, cutting, and other functions. The experimental results show that the average relative error of length is about 0.5%, and the error is within a reasonable range. © 2024 Published under licence by IOP Publishing Ltd.

关键词： Wire

来源：评论

学校读者我要写书评

暂无评论

3D SPARSE SAR IMAGING BASED ON COMPLEX NONCONVEX PENALTY FUNCTION

3D SPARSE SAR IMAGING BASED ON COMPLEX NONCONVEX PENALTY FUN...

引用

IET International Radar Conference 2023, IRC 2023

作者： Wang, Yangyang Gao, Jing Yao, Jinjie Zhan, Xu Bai, Jiansheng Li, Kun School of Information and Communication Engineering North University of China Taiyuan China School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9781839539954

Combining sparse signal processing with imaging can improve different types of SAR image quality. The L1 penalty function is an effective and typical sparse prior representation in sparse reconstruction. However, as a convex optimization function, L1 penalty function often introduces bias in sparse signal reconstruction. Therefore, in this paper, nonconvex penalty function is used to obtain high-quality and high-precision 3D SAR images. In order to improve the accuracy of sparse reconstruction, we adopt complex valued smoothly clipped absolute deviation penalty (CSCAD) for sparse reconstruction. Compared to the existing sparse reconstruction method with L1 penalty function, the proposed method not only improves the quality of array SAR images, but also reduces bias effects. In addition, the variant of alternating direction method of multipliers (ADMM) framework is used to achieve 3D sparse reconstruction, which can effectively reduce the computational complexity compared to traditional ADMM. The experiment is implemented to verify the effectiveness of the proposed method. © The Institution of engineering & technology 2023.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

A Synthetic Aperture Radar UHF RFID Localization Method Based on Phase Jumps 12

A Synthetic Aperture Radar UHF RFID Localization Method Base...

引用

12th IEEE Asia-Pacific Conference on Antennas and Propagation, APCAP 2024

作者： Wang, Xianping Inserra, Daniele Wen, Guangjun Nepa, Paolo University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu China University of Pisa Department of Information Engineering Pisa Italy

ISBN: (纸本)9798350351019

This paper presents a new synthetic aperture radar (SAR) ultra-high frequency (UHF) radio frequency identification (RFID) localization method that exploits the periodicity of the received signal phase. In fact, the phase measurement is a non-continuous function, and its derivative exhibits evident peaks in correspondence of the phase jumps. Therefore, the distance among peak points is herein exploited to establish a cost function closely related to the tag position, achieving high precision localization. Numerical results show that the proposed method can effectively locate tag with an average accuracy of 14 cm. © 2024 IEEE.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

A Model-free Combined Energy and Thermal Management Strategy for HEVs Based on Reinforcement-Learning Under Low-Temperature

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-15页

作者： Li, Kai Chen, Hong Wu, Yuhu Zhao, Jing Ding, Shihong Gao, Jinwu Changchun China Changchun China School of Control Science and Engineering Dalian University of Technology Dalian China Department of Electromechanical Engineering University of Macau Macau China School of Electrical and Information Engineering Jiangsu University Zhenjiang China

To improve vehicle adaptability to low-temperature environments, this paper proposes a combined energy and thermal management strategy (C-ETM) based on twin delayed deep deterministic policy gradient (TD3) algorithm for hybrid electric vehicles (HEVs). First, a vehicle energy management system (EMS) model and a engine-battery-cabin coupled thermal management system (CTMS) model are developed. By analyzing the coupling relationship between the CTMS and the EMS, a multiobjective optimization problem is constructed to minimize fuel consumption and battery aging damage and ensure SOC stability. Facing the challenges of solving optimization problems caused by the high-order complex nonlinearity of thermal-electrical coupling systems, the optimization problems are transformed into a Markov decision process (MDP). A reinforcement learning framework based on the TD3 algorithm is designed to achieve a real-time solution to the problem from a new perspective, overcoming the reliance on the system models and accurate future traffic information. The proposed strategy has efficient performance in terms of fuel economy, battery life, ensuring SOC stability, and adaptability. The total optimization cost reaches 91.42% level of the dynamic programming (DP) strategy, which is 30.3% lower than the model predictive control (MPC) strategy. The online computing burden is only 0.19% of the MPC strategy, which has strong potential for real-time applications. IEEE

关键词： Waste heat

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：