检索结果-内蒙古大学图书馆

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Wen, Zhuofan Gui, Shangtong Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences China Key Laboratory of Al Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft model to assist the base LLM where the draft model produces drafts and the base LLM verifies the draft for acceptance or rejection. In this framework, the final inference speed is decided by the decoding speed of the draft model and the acceptance rate of the draft provided by the draft model. Currently the widely used draft models usually generate draft tokens for the next several positions in a non-autoregressive way without considering the correlations between draft tokens. Therefore, it has a high decoding speed but an unsatisfactory acceptance rate. In this paper, we focus on how to improve the performance of the draft model and aim to accelerate inference via a high acceptance rate. To this end, we propose a CTC-based draft model which strengthens the correlations between draft tokens during the draft phase, thereby generating higher-quality draft candidate sequences. Experiment results show that compared to strong baselines, the proposed method can achieve a higher acceptance rate and hence a faster inference speed. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Network Combining CNN and Transformer for Blind Image Super-Resolution 12

A Network Combining CNN and Transformer for Blind Image Supe...

引用

12th International Conference on information Technology in Medicine and Education, ITME 2022

作者： Zhang, Shuhao Li, Zuoyong Teng, Shenghua Zeng, Kun Shandong University of Science and Technology College of Electronic and Information Engineering Qingdao266590 China Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Fuzhou350121 China

ISBN: (纸本)9798350310153

Blind super-resolution (SR) requires not only estimating blur kernel, but also super-resolving low-resolution image based on estimated blur kernel. Most blind SR methods use convolutional neural networks (CNNs) for kernel estimation, which cannot exploit long-range dependency within image domain, thus failing to predict blur kernel accurately. To address this issue, we propose a network combining CNN and transformer named NCCT for kernel estimation. By modeling local and non-local image priors simultaneously, NCCT outperforms other blind SR methods in terms of kernel estimation accuracy. Moreover, we design a network module named RRFDB for constructing lightweight blind SR network, which runs faster and achieves comparative SR performance with fewer parameters compared with other state-of-the-art blind SR methods. © 2022 IEEE.

关键词： Optical resolving power

来源：评论

学校读者我要写书评

暂无评论

Medical Waste Traceability Management System Based on RFID Technology 41

Medical Waste Traceability Management System Based on RFID T...

引用

第41届中国控制会议

作者： Shuncheng Jin Genghuang Yang Chongwei Li School of Automation and Electrical Engineering Tianjin University of Technology and Education Tianjin Key Laboratory of Information Sensing and Intelligent Control

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In view of the low efficiency of the current medical waste recycling and disposal operation,it can be concluded that the traditional manual management mode results in the losing of medical waste and the failure of monitoring weight by the statistical analysis of the above *** with the future development of the industry and the Internet of Things technology,we propose a medical waste traceability management system(MWTMs) based on radio frequency identification(RFID) *** overall structure of the medical waste traceability management system is analyzed and the MWTMs are elaborated from both hardware and software *** Internet of Things technology is applied to supervise the various processes of medical waste transportation in detail and to achieve reasonable compliance with the recycling and disposal *** new intelligent,clean,and systematic medical system is implemented to trace the source of the waste in some hospitals with good effect.

关键词： medical waste RFID management system trace to the source

来源：评论

学校读者我要写书评

暂无评论

Mixed Quantization of One-bit and Full-precision Signals for Direction of Arrival Estimation

Mixed Quantization of One-bit and Full-precision Signals for...

引用

International Conference on Signal processing Proceedings (ICSP)

作者： Li Kang Jianbin Ding Jianjun Huang Hao Huang Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

ISBN: (数字)9798350387384

ISBN: (纸本)9798350387391

Direction of Arrival (DOA) estimation is a crucial technology in array signal processing. One-bit quantization is commonly employed to reduce hardware costs in DOA estimation, yet it introduces significant quantization noise, adversely affecting the accuracy of DOA estimation. To mitigate this issue, we propose a mixed-precision quantization method that integrates one-bit and full-precision quantization. We derive the covariance matrix of signals subjected to mixed-precision quantization and establish the Cramér-Rao Bound (CRB) for this quantization approach. Through experiments, we evaluate the performance of mixed-precision quantization in both DOA estimation and target recognition. The results demonstrate that mixed-precision quantization significantly enhances DOA estimation accuracy compared to one-bit quantization. Additionally, this method improves the target recognition capability of signals. Our approach strikes a better balance between hardware costs and quantization errors, offering a promising solution for practical applications.

关键词： Quantization (signal) Direction-of-arrival estimation Costs Accuracy Target recognition Noise Estimation Parallel processing Hardware Covariance matrices

来源：评论

学校读者我要写书评

暂无评论

A control Method for Coal Slime Water Thickening Process in Coal Preparation Plants Based on BP-TSFNN

A Control Method for Coal Slime Water Thickening Process in ...

引用

2024 China Automation Congress, CAC 2024

作者： Fu, Shangluo Zhou, Fan Zhao, Jun Wang, Wei Key Laboratory of Intelligent Control and Optimization for Industrial Equipment Ministry of Education China School of Control Science and Engineering Dalian University of Technology Dalian China School of Information Science and Engineering Dalian Polytechnic University Dalian China

ISBN: (纸本)9798350368604

Aiming at the complex mechanism of coal slime water thickening process in coal preparation plant, which has the characteristics of multivariable and strong nonlinearity leading to the difficulty of realizing the intelligent optimization control, a model predictive control method based on back propagation neural network (BPNN) and Takagi-Sugeno fuzzy neural network (TSFNN) cascade (BP-TSFNN-MPC) is proposed. Further, in order to realize the intelligent optimization control of the thickening process, the BP-TSFNN-MPC controller is constructed, and the gradient descent optimization algorithm is used to solve the optimization problem. In the experimental part, the effectiveness of the model and control method is verified by combining the production data of the slime water concentration process and the simulation model of the thickener. The results show that the BP-TSFNN model has high prediction accuracy for the concentration process and BP-TSFNN-MPC has good control performance. © 2024 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Multi-Attention Gate Based U-net for Retinal Vessel Segmentation 12

Multi-Attention Gate Based U-net for Retinal Vessel Segmenta...

引用

12th International Conference on information Technology in Medicine and Education, ITME 2022

作者： Zhu, Yu Li, Rui Teng, Shenghua Cao, Xinrong Shandong University of Science and Technology College of Electronic and Information Engineering Qingdao266590 China College of Computer and Control Engineering Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China

ISBN: (纸本)9798350310153

Retinal blood vessel segmentation images can be used to detect and evaluate various cardiovascular and ophthalmic diseases. However, due to the intricate vessel structures and blurred boundaries of vessels, it is a huge challenge to efficiently and accurately segment blood vessels. To deal with the above problems, this paper improves on the U-net by firstly using multi-scale feature convolution with kernels of varying size for feature extraction. Second, a non-local attention mechanism is applied to obtain richer global semantic information. Then multi-attention gate is used in the skip connection part by inputting feature maps of various scales and dimensions and selectively learning the interrelated regions, which improves the segmentation ability of the network model for the tiny structure of blood vessels. Quantitative and qualitative experimental results on two public datasets, DRIVE and CHASE-DB1, demonstrate the effectiveness of the proposed method. © 2022 IEEE.

关键词： Blood vessels

来源：评论

学校读者我要写书评

暂无评论

Self-Healing Optimization of Power Grid under High Penetration of New Energy 25

Self-Healing Optimization of Power Grid under High Penetrati...

引用

25th IEEE China Conference on System Simulation Technology and its Application, CCSSTA 2024

作者： Jin, Zelong Yang, Bohan Kong, Xiangyu Zheng, Meiling Liu, Jiancun Tianjin University of Technology Tianjin Key Laboratory of New Energy Power Conversion Transmission and Intelligent Control Tianjin China Tianjin University Key Laboratory of Smart Grid Tianjin China Tianjin University School of Electrical and Information Engineering Tianjin China

ISBN: (纸本)9798350366600

In order to address the problem of high penetration of new energy into the grid, which brings huge intermittency and volatility to the distribution network, and to overcome the shortcomings of the traditional methods such as genetic algorithm and whale algorithm, which are limited and unable In order to construct the most suitable scenarios, this paper considers a distribution network system containing a significant quantity of distributed photovoltaic energy under a high penetration rate. It then builds a stochastic planning model for self-healing of the distribution network by constructing constraint functions and objective functions. The construction of the constraint function and objective function enables the development of a self-healing stochastic planning model for the distribution network. This model is solved using the scenario tree stochastic method and the improved PSO algorithm. Finally, the feasibility of the self-healing optimization method proposed in this paper is verified by applying it to four typical scenarios to demonstrate the limitations of the traditional method. In brief, the methodologies presented in this paper offer superior alternatives to traditional methods. The optimization solution is more expedient and precise, with a discernible positive impact on the self-repair capability of the distribution network and secure operation. © 2024 IEEE.

关键词： Power distribution networks

来源：评论

学校读者我要写书评

暂无评论

Dynamic Template Update Mechanism for Visual Object Tracking 8

Dynamic Template Update Mechanism for Visual Object Tracking

引用

8th International Conference on intelligent Computing and Signal processing, ICSP 2023

作者： Hu, YongQi Cai, ZhongWang Nie, ZiJun Yu, ZiZheng Cao, Ying Yin, Zhijian Yang, Zhen Jiangxi Science and Technology Normal University School of Communications and Electronics Nanchang China Ministry of Education Key Laboratory of System Control and Information Processing Shanghai China

ISBN: (纸本)9798350302455

Given the requirements for robust target classification and accurate target state estimation in visual tracking, SiamFC++ proposes a set of practical guidelines for designing high-performance general-purpose trackers by considering the special nature of visual tracking problems. Inspired by dynamic modules, We propose an empirical method for integrating a dynamic module into the image input, which is concatenated with the template module after feature maps are extracted by the backbone network. Since the position and shape of the object can change significantly within a video sequence, the added dynamic module can better focus on the target region of the feature map to obtain better similarity maps. Extensive experiments and comparisons demonstrate that our simple and effective method achieves reliable results on the benchmarks of LaSOT, TrackingNet, and GOT-10K and provides a significant speed advantage in real-time. © 2023 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Tracking control in Presence of Obstacles and Uncertainties for Bioinspired Spherical Underwater Robots

引用

Journal of Bionic Engineering 2023年第1期20卷 323-337页

作者： Chunying Li Shuxiang Guo Jian Guo Graduate School of Engineering Kagawa UniversityTakamatsuKagawa761-0396Japan Key Laboratory of Convergence Medical Engineering System and Healthcare Technology the Ministry of Industry and Information TechnologySchool of Life Science and TechnologyBeijing Institute of TechnologyBeijing100081China Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems and Intelligent Robot Laboratory Tianjin University of TechnologyBinshui Xidao Extension 391Tianjin300384China

During marine missions,AUVs are susceptible to external disturbances,such as obstacles,ocean currents,etc.,which can easily cause mission failure or *** this paper,considering the strong nonlinearities,external disturbances and obstacles,the kinematic and dynamic model of bioinspired Spherical Underwater Robot(SUR)was ***,the waypoints-based trajectory tracking with obstacles and uncertainties was proposed for SUR to guarantee its safety and ***,the Lyapunov theory was adopted to verify the stability and the Slide Mode control(SMC)method is used to verify the robustness of the control *** addition,a series of simulations were conducted to evaluate the effectiveness of proposed control *** tests,including path-following,static and moving obstacle avoidance were performed which verified the feasibility,robustness and effectiveness of the designed control ***,a series of experiments in real environment were performed to verify the performance of the control *** simulation and experimental results of the study supplied clues to the improvement of the path following capability and multi-obstacle avoidance of AUVs.

关键词： Path following Obstacle avoidance Bioinspired.Spherical underwater robot(SUR) Lyapunov theory

来源：评论

学校读者我要写书评

暂无评论

Reduction of Unipolar Leakage Flux and Torque Ripple in Consequent-pole PM Vernier Machine

引用

CES Transactions on Electrical Machines and Systems 2023年第1期7卷 35-44页

作者： Liang Xu Yang Li Wenxiang Zhao Guohai Liu the School of Electrical and Information Engineering Jiangsu UniversityZhenjiang212013China the Jiangsu Key Laboratory of Drive and Intelligent Control for Electric Vehicle and the National Center for International Research on Structural Health Management of Critical ComponentsJiangsu UniversityZhenjiang212013China IEEE

This paper proposes a new consequent-pole permanent magnet vernier machine(CPMVM),which can be regarded as a combination of two conventional CPMVM with opposite *** on the simplified axial magnetic circuit model,it is verified that the proposed CPMVM can reduce the unipolar leakage *** order to reduce the torque ripple of machine and improve the output torque of machine,the flux barrier is placed on the rotor of the proposed ***,the parameters of the proposed CPMVM are optimized and ***,the electromagnetic performance,including no-load air-gap flux density,average torque and torque ripple,flux linkage,back-electromotive force,cogging torque,average torque,torque ripple,power factor and loss,is compared with conventional surface-mounted permanent magnet vernier machine(SPMVM)and ***,it is demonstrated that proposed CPMVM with flux barrier can effectively reduce the unipolar leakage flux and greatly reduce the torque ripple of ***,compared with the SPMVM,the proposed CPMVM with flux barrier saves more than 45%of the permanent magnet material without reducing output torque.

关键词： Consequent-pole Permanent magnet vernier machine Unipolar leakage flux Torque ripple Flux barrier Output torque

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：