检索结果-内蒙古大学图书馆

9th International Conference on Business and Industrial Research, ICBIR 2024

作者： Srichavengsup, Warakorn Thai-Nichi Institute of Technology Robotics and Technology Laboratory Faculty of Engineering Bangkok Thailand

ISBN: (纸本)9798350383010

This paper presents technique for improving the performance of Ternary tree algorithm. In order to avoid the collision, Ternary tree algorithm divides the users involved in collisions into 3 groups. However, in the case of continuous collisions, keeping the number of divided groups equal to 3 all the time may cause an inefficient use of channel. This is because in later collisions there are fewer users involved in the collision. Dividing the number of groups to 2 in later collisions can provide better performance. Therefore, this paper proposes adaptive Group Splitting technique to improve the channel access efficiency of Ternary tree algorithm. In adaptive Group Splitting Technique, the threshold value is defined as the number of collisions in a continuous collision that start to change the number of divided groups from 3 to 2. From the results, we found that the threshold value is an important parameter and affects the system performance. When we use the appropriate threshold value adaptive Group Splitting technique can help reduce the number of idle slots and improve the performance of Ternary tree algorithm. Especially in the case where there are a large number of users in the system. © 2024 IEEE.

关键词： adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

A momental bound algorithm based on precise stepsize adjustment for training deep neural networks 43

A momental bound algorithm based on precise stepsize adjustm...

引用

43rd Chinese Control Conference, CCC 2024

作者： Zhang, Haixia Li, Dequan Qian, Zhen Anhui University of Science and Technology School of Mathematics and Big Data Huainan232000 China Anhui University of Science and Technology School of Artificial Intelligence Huainan232000 China

ISBN: (纸本)9789887581581

adaptive algorithms are extensively employed in the field of deep learning owing to their rapid convergence properties. Adam is the most common adaptive algorithm among them. However, it has revealed that Adam has a poor generalization ability. AdaBelief is an algorithm based on Adam with exact stepsize adjustment. It introduces a new second-order momentum that corrects Adam's second-order moments. These algorithms still fail to converge during training due to the presence of instability and extreme learning rates. In this paper, we propose a new adaptive and momental bounded algorithm, called AdaBMod, which can effectively mitigate the sudden large learning rate problem and is especially suitable for training deep neural networks. By setting an adaptive finite learning rate in AdaBelief algorithm, the obtained AdaBMod can effectively eliminate the problem of high learning rate in the late training of neural networks, so as to make the training process more stable. Numerical simulation experiments on deep neural network tasks also show that our proposed AdaBMod algorithm eliminates the large learning rate during the training process. The results are also better than other current state-of-the-art optimizers. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： adaptive algorithms adaptive and Momental Bound Deep Neural Networks Image Classification Robustness

来源：评论

学校读者我要写书评

暂无评论

adaptive Fault-Tolerant Visual Control For Electrically Driven Robotic Manipulators Using An Uncalibrated Camera 6

Adaptive Fault-Tolerant Visual Control For Electrically Driv...

引用

6th International Conference on Electronics and Communication, Network and Computer Technology, ECNCT 2024

作者： Chen, Zhitian Lai, Guanyu Li, Liang School of Automation Guangdong University of Technology Guangzhou China

ISBN: (纸本)9798350366143

A novel cascade uncalibrated IBVS control scheme is proposed for electrically driven robotic manipulators with actuator faults and power system faults in this paper. For the actuator failure, we propose to employ the adaptive algorithm to estimate the control deviation value of adverse effects from fault actuator output, and an adaptive compensation method is designed to eliminate the power fluctuation and power bias from the power system fault. The boundedness and convergence of the fault-tolerant control system are proven by the Lyapunov method. A simulation based on the Matlab-Simulink verifies the reliability of the proposed control policy. © 2024 IEEE.

关键词： adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Introduction of Optimization Algorithm for adaptive Gradient 5

Introduction of Optimization Algorithm for Adaptive Gradient

引用

5th International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Lamine, Mouna Kim, Sang-Chul Kookmin Univ Sch Comp Sci Seoul South Korea

ISBN: (纸本)9781665456456

Machine Learning is facing rapid development due to the almost unlimited amount of data available, and it is widely applied in diverse areas. Optimization is one of the core components in the machine learning which attracted more researcher's attention to it. In recent years there has been a great deal of work on improving optimisation methods in machine learning. In this paper we will introduce the adaptive Gradient(Adapg), a new extension in the adaptive learning family Optimization algorithm.

关键词： Machine Learning Optimization Methods Gradient Decent adaptive algorithms AdaDelta Adam Adapg

来源：评论

学校读者我要写书评

暂无评论

Ultra-low Altitude Aircraft Airborne Radar Performance Under Cluttering and Jamming

Ultra-low Altitude Aircraft Airborne Radar Performance Under...

引用

2024 OES China Ocean Acoustics, COA 2024

作者： Shah, Syed Asim Tao, Jiang Ali, Wasiq Khan, Himayat Ullah College of Information and Communication Engineering Harbin Engineering University Harbin150001 China College of Underwater Acoustic Engineering Harbin Engineering University Harbin150001 China

ISBN: (纸本)9798350340297

This study addresses the effectiveness of an Ultra-low Altitude Orbit (ULAO) aircraft radar system when it is required to operate in congested and cluttered environments. This study states that the conventional ULAO airborne radar system suffers from serious problems of multiple target detection and bears great challenges, making it worthwhile to use advanced signal processing techniques and adaptive algorithms to mitigate the adverse effect of clutter and jamming. This study analyzes respective and combined interference from clutter and jamming using echo signal and discusses computational performance of conventional airborne radar systems using theoretical analysis, simulation models, and real data sets. The results show that advanced signal processing techniques and adaptive algorithms can effectively improve the performance of radar systems and can be widely used in military and civil airspace applications. © 2024 IEEE.

关键词： adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

An Edge Caching Strategy Based on Long-Term and Short-Term Interests Reshaping of Users 3

An Edge Caching Strategy Based on Long-Term and Short-Term I...

引用

3rd International Conference on Computing, Communication, Perception and Quantum Technology, CCPQT 2024

作者： Wu, Jiawen Li, Zhidu Guo, Ziwen School of Communications and Information Engineering Chongqing University of Posts and Telecommunications Chongqing China Aerospace New Generation Communications Co. Ltd Chongqing China

ISBN: (纸本)9798331528386

In the context of edge caching, the prevalent challenges of unknown user preferences and high heterogeneity significantly hinder the performance of caching systems. To address these issues, this paper proposes an edge caching strategy based on reshaping users' long-term and short-term interests. Firstly, we establish a basic click-through rate prediction model and introduce automated and adaptive search algorithms to obtain optimal short-term interests durations and high-quality long-term interests feature representations through end-to-end optimization. Then, we design a dynamic recommendation mechanism based on user preferences, reshaping the content request probabilities of different users to influence caching decisions. Finally, we formulate a joint problem of maximizing system utility by integrating diverse edge caching and user recommendations, decoupled into a caching sub-problem and a recommendation sub-problem. These are solved using a regional greedy algorithm and a one-to-one exchange matching algorithm, respectively, and iterative updates are performed to achieve convergent optimization results. Simulation results show that the proposed algorithm effectively improves caching performance. © 2024 IEEE.

关键词： adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Investigating Personalized Learning Paths to Address Educational Disparities Using Advanced Artificial Intelligence Systems

Investigating Personalized Learning Paths to Address Educati...

引用

2024 International Conference on E-Mobility, Power Control and Smart Systems, ICEMPS 2024

作者： Chauhan, Megha Rahman, Hairur Ibrahim, Uin Maulana Malik Reddy, D. Srinivas Padmanabhan, Abhishek Sharma Thirumalaikumari, T. Babu, G.Charles Symbiosis Law School-NOIDA India Pune India Malang Indonesia Vardhaman College of Engineering Department of Mathematics Telangana Hyderabad India Law Christ University Bangalore India Saveetha College of Liberal Arts and Sciences Chennai India Gokaraju Rangaraju Institute of Engineering and Technology Department of Cse Telangana Hyderabad India

ISBN: (纸本)9798350394399

This innovative study reimagines the role of Natural Language Processing (NLP) in individualized education by highlighting the critical need to incorporate cultural subtleties. While natural language processing (NLP) offers great potential for improving classroom instruction, current research frequently fails to account for the complex issues caused by cultural variation. This research fills a significant need by providing a novel framework for the detection and incorporation of cultural subtleties into individualized learning programs. Further research into common biases is driving the development of natural language processing models with greater cultural sensitivity and awareness, such as gender bias in Named Entity Recognition (NER) and sentiment bias in cultural preferences. In order to correct past biases and promote gender neutrality in educational content, the research makes use of an adaptive NER algorithm and a diverse training dataset. Similarly, to guarantee nuanced and fair sentiment evaluations, the study suggests regularly evaluating and retraining sentiment algorithms with datasets that represent multiple cultures. A Cultural Relevance Score of 0.9, adaptive Content Embedding vectors [0.3, 0.6, -0.2.], and an impressive Cosine Similarity of 0.85 are some of the evaluation measures that highlight the effectiveness of the research. These measurements show encouraging gains, which confirms that the research might help make schools more welcoming and sensitive to different cultures. The research has the potential to revolutionize individualized education by making it more accessible and engagingfor students from all backgrounds. © 2024 IEEE.

关键词： adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

E5: Zero-shot Hierarchical Table Analysis using Augmented LLMs via Explain, Extract, Execute, Exhibit and Extrapolate

E5: Zero-shot Hierarchical Table Analysis using Augmented LL...

引用

2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024

作者： Zhang, Zhehao Gao, Yan Lou, Jian-Guang Dartmouth College United States Microsoft Research Asia China

ISBN: (纸本)9798891761148

Analyzing large hierarchical tables with multi-level headers presents challenges due to their complex structure, implicit semantics, and calculation relationships. While recent advancements in large language models (LLMs) have shown promise in flat table analysis, their application to hierarchical tables is constrained by the reliance on manually curated exemplars and the model’s token capacity limitations. Addressing these challenges, we introduce a novel code-augmented LLM-based framework, E5, for zero-shot hierarchical table question answering. This approach encompasses self-explaining the table’s hierarchical structures, code generation to extract relevant information and apply operations, external code execution to prevent hallucinations, and leveraging LLMs’ reasoning for final answer derivation. Empirical results indicate that our method, based on GPT-4, outperforms state-of-the-art fine-tuning methods with a 44.38 Exact Match improvement. Furthermore, we present F3, an adaptive algorithm designed for token-limited scenarios, effectively condensing large tables while maintaining useful information. Our experiments prove its efficiency, enabling the processing of large tables even with models having limited context lengths. The code is available at https://***/zzh-SJTU/ E5-Hierarchical-Table-Analysis. © 2024 Association for Computational Linguistics.

关键词： adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

A framework for adaptive open-pit mining planning under geological uncertainty

引用

OPTIMIZATION AND ENGINEERING 2022年第1期23卷 111-146页

作者： Lagos, Tomas Armstrong, Margaret Homem-de-Mello, Tito Lagos, Guido Saure, Denis Univ Chile Dept Ind Engn Santiago Chile Univ Adolfo Ibanez Sch Business Santiago Chile Univ Chile Ctr Math Modelling Santiago Chile Univ Adolfo Ibanez Fac Engn & Sci Santiago Chile

Mine planning optimization aims at maximizing the profit obtained from extracting valuable ore. Beyond its theoretical complexity-the open-pit mining problem with capacity constraints reduces to a knapsack problem with precedence constraints, which is NP-hard-practical instances of the problem usually involve a large to very large number of decision variables, typically of the order of millions for large mines. Additionally, any comprehensive approach to mine planning ought to consider the underlying geostatistical uncertainty as only limited information obtained from drill hole samples of the mineral is initially available. In this regard, as blocks are extracted sequentially, information about the ore grades of blocks yet to be extracted changes based on the blocks that have already been mined. Thus, the problem lies in the class of multi-period large scale stochastic optimization problems with decision-dependent information uncertainty. Such problems are exceedingly hard to solve, so approximations are required. This paper presents an adaptive optimization scheme for multi-period production scheduling in open-pit mining under geological uncertainty that allows us to solve practical instances of the problem. Our approach is based on a rolling-horizon adaptive optimization framework that learns from new information that becomes available as blocks are mined. By considering the evolution of geostatistical uncertainty, the proposed optimization framework produces an operational policy that reduces the risk of the production schedule. Our numerical tests with mines of moderate sizes show that our rolling horizon adaptive policy gives consistently better results than a non-adaptive stochastic optimization formulation, for a range of realistic problem instances.

关键词： Mine planning Geostatistics Stochastic optimization adaptive algorithms Iterative learning algorithm

来源：评论

学校读者我要写书评

暂无评论

An adaptive reduction method for viscoelastic structures without approximation on viscoelasticity 14

An adaptive reduction method for viscoelastic structures wit...

引用

14th International Conference on Recent Advances in Structural Dynamics, RASD 2024

作者： Zhang, Shuyang Van Belle, Lucas Devriendt, Hendrik Desmet, Wim Department of Mechanical Engineering KU Leuven Heverlee Belgium Flanders Make@KU Leuven Leuven Belgium

Viscoelastic materials are often encountered in engineering applications, such as bonded assemblies, polymer structures, or structures with damping treatments. To simulate the dynamic behavior of large mechanical systems with viscoelastic materials, finite element (FE) models are commonly employed. However, the large size of these models can lead to significant computational costs, making model order reduction (MOR) often a necessary step for improving the computational efficiency. Recently, an adaptive Taylor-based second-order Arnoldi (AT-SOAR) algorithm was introduced, which addresses the frequency-dependency of viscoelastic materials. However, due to the Taylor-based approximation used in the viscoelastic behavior modelling, the resulting reduced order models (ROMs) may leave room for improvement, both from an accuracy as well as from an efficiency point of view. Hence, this work proposes a two-layer Krylov subspace (TLK) method that circumvents the viscoelastic model approximation. Additionally, a sequenced collection approach is used to augment the reduction basis from these two layers of Krylov subspaces. For automating ROM generation in line with specific error criteria, the TLK method is integrated with the adaptive algorithm in AT-SOAR (A-TLK). The proposed method is demonstrated through an adhesive single-lap model example, showing that A-TLK can generate smaller, more efficient ROMs compared to AT-SOAR under the same error tolerance. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： adaptive algorithms

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：