检索结果-内蒙古大学图书馆

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Jingyu Zhang Xingxing Hou Yilong Teng Lailong Luo School of Computer and Communication Engineering Changsha University of Science and Technology Changsha China Science and Technology on Information Systems Engineering Laboratory School of Systems Engineering National University of Defense Technology Changsha China

Unspent Transaction Output (UTXO) is part of the transaction data set, which represents the digital cryptocurrency asset in transaction-based blockchain systems. The data management capability, storage method and occupied space of UTXOs will greatly affect the running efficiency and the verification performance of blockchain systems. Especially, with the popularity of blockchain technology, the relevant UTXO data sets have been growing, and all the stored data can no longer be almost completely stored in memory. How should the UTXO transaction data be stored and managed at this time, it is an urgent issue to be solved in bitcoin-like blockchain systems. This paper provides a blockchain transaction data management optimization mechanism based on multi-partitioning. First, we analyze the influencing factors of transactions through real blockchain data. The proposed method can evaluate the time interval and transaction frequency factors, and use the received information to realize the efficient transaction data storage. In our design, UTXOs with lower likelihood to be used in new transactions will be stored in the disk, and the other UTXOs with higher likelihood to be used in new generated transactions should be stored in the cache. This approach aims to minimize memory consumption for the transaction data sets, accelerate UTXO access time during block verification, and ultimately decrease the overall time required for verification, leading to efficient UTXO transaction data management. Finally, the effectiveness of the proposed optimization mechanism is verified through theoretical analysis and simulation experiments, and the UXTO access time has been reduced compared with state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis for Aircraft Aileron Actuator Based on Graph Regularization Network

Fault Diagnosis for Aircraft Aileron Actuator Based on Graph...

引用

International Conference on Guidance, Navigation and Control, ICGNC 2022

作者： Cheng, Yujie Wu, Ruipeng Song, Dengwei School of Reliability and Systems Engineering Beihang University Beijing100191 China School of Instrumentation and Optoelectronic Engineering Beihang University Beijing100191 China Science and Technology on Reliability and Environmental Engineering Laboratory Beijing100191 China Institute of Reliability Engineering Beihang University Beijing100191 China

ISBN: (纸本)9789811966125

During the operation of aircraft aileron actuators, a large number of monitoring samples will be accumulated. However, most of the monitoring samples are without labels since the lack of effective data management and data analysis. Most traditional fault diagnosis methods simply use sample parameters to analyze the health condition of aircraft aileron actuators. These methods ignore the relationship between sample parameters and fail to effectively use the fault information in unlabeled samples, which results in low accuracy of fault diagnosis under label missing conditions. Graph regularization network can exploit the relationship between sample parameters to improve the fault diagnosis accuracy and performance under label missing conditions. In this paper, a fault diagnosis method based on graph regularization network is proposed. First, for the monitoring samples, a sample association graph is constructed based on the K-nearest neighbor method. Second, for the nodes in the graph with labeled samples, subgraphs are extracted and generated, each containing one labeled node and K unlabeled nodes. Then, a fault diagnosis model based on graph regularization network is constructed by using subgraphs, and the relationship between sample parameters is used to constrain the optimization, forcing the fault diagnosis model to be trained toward a fixed direction. Finally, a simulation dataset is generated by injecting different faults to an aileron actuator simulation model established using Simulink and AMESim software, and some of the fault labels are removed for case validation of the proposed fault diagnosis method. The results show that the proposed fault diagnosis method based on graph regularization network can effectively use the relationship between sample parameters and improve the performance of fault diagnosis under label missing conditions compared with typical supervised learning methods. © 2023, The Author(s), under exclusive license to Springer Nature Singapo

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Short-term Portfolio optimization using Doubly Regularized Exponential Growth Rate

Short-term Portfolio Optimization using Doubly Regularized E...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Quanlong Guan Jinneng He Zhao-Rong Lai Yuyu Zhou Quming Jiang Ziliang Chen College of Information Science and Technology Jinan University Guangzhou China Guangdong Institute of Smart Education Jinan University Guangzhou China Guangdong Key Laboratory of Data Security and Privacy Preserving Guangzhou China Guangdong-Macao Advanced Intelligent Computing Joint Laboratory Zhuhai China Chutian Dragon Co. Ltd Dongguan China School of Intelligent Systems Science and Engineering Jinan University China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

In the realm of short-term portfolio optimization, the integration of machine learning with exponential growth rate techniques is gaining prominence. This paper introduces a novel approach for short-term portfolio optimization, termed Short-term Portfolio optimization using Doubly Regularized EGR (SPODR), to address the challenges posed by limited data availability. SPODR utilizes radial basis functions for the effective identification of market trends, enabling improved stock market forecasts. The approach uniquely combines ℓ 1 and ℓ 2 -regularization, adhering to empirical financial principles, to strike a balance between risk and return in short-term portfolios. A key aspect of SPODR is addressing the complexity of its ElasticNet-like objective, which poses a challenge for traditional methods due to its online learning nature. To overcome this, we have developed an algorithm based on the log barrier interior-point method. This algorithm is adept at efficiently optimizing portfolio allocation, taking into account the specific constraints inherent in our approach. Extensive comparative experiments across five benchmark datasets demonstrate that SPODR significantly outperforms existing short-term portfolio optimization models. It achieves a right balance between return and risk. Furthermore, SPODR showcases efficient computational speed, enhancing its applicability in real-world financial settings.

关键词： Computational modeling Benchmark testing Market research Robustness Regulation Computational efficiency Resource management

来源：评论

学校读者我要写书评

暂无评论

CNN-Enhanced Deep Sparse Representation Network for Polarimetric SAR Image Classification

CNN-Enhanced Deep Sparse Representation Network for Polarime...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Junfei Shi Mengmeng Nie Haiyan Jin Junhuai Li Yuanlin Zhang Department of Computer Science and Technology Shaanxi Key Laboratory for Network Computing and Security Technology Xi’an University of Technology Xi’an China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Deep learning networks can automatically acquire high-level semantic features for polarimetric SAR image classification, while it involves a blind learning procedure without explicit guidance. In contrast, sparse representation methods represent effective non-deep models with a robust mathematical mechanism serving as guidance. However, they can’t capture complex image features and semantic information. To address these issues, we propose a novel approach known as the CNN-enhanced Deep Sparse Representation Network (CE-DSRNet) for PolSAR image classification, which a Sparse Representation (SR) guided deep learning model. Initially, a sparse representation model is constructed for PolSAR images to capture essential features. Subsequently, to solve the sparse model, a Deep Sparse Representation Network (DSRNet) is devised by transforming the Soft Threshold Iterative (ISTA) optimization procedure into a network, enabling automatic learning of sparse coefficients as features. Finally, a CNN-enhanced DSRNet is introduced, integrating DSRNet with CNN to effectively extract deep semantic features and enhance classification accuracy. Experiments demonstrate the effectiveness of the proposed method compared to state-of-the-art approaches.

关键词： Deep learning Sparse approximation Semantics Feature extraction Mathematical models Radar polarimetry Iterative algorithms

来源：评论

学校读者我要写书评

暂无评论

Derivative-Free optimization for Low-Rank Adaptation in Large Language Models

arXiv

引用

arXiv 2024年

作者： Jin, Feihu Liu, Yifan Tan, Ying School of Intelligence Science and Technology Peking University China Institute for Artificial Intelligence Peking University China National Key Laboratory of General Artificial Intelligence China Peking University China

Parameter-efficient tuning methods such as LoRA could achieve comparable performance to model tuning by tuning a small portion of the parameters. However, substantial computational resources are still required, as this process involves calculating gradients and performing back-propagation throughout the model. Much effort has recently been devoted to utilizing the derivative-free optimization method to eschew the computation of gradients and showcase an augmented level of robustness in few-shot settings. In this paper, we prepend the low-rank modules into each self-attention layer of the model and employ two derivative-free optimization methods to optimize these low-rank modules at each layer alternately. Extensive results on various tasks and language models demonstrate that our proposed method achieves substantial improvement and exhibits clear advantages in memory usage and convergence speed compared to existing gradient-based parameter-efficient tuning and derivative-free optimization methods in few-shot settings1 © 2024, CC BY-SA.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

Algorithm optimization Applied in the Selection of Stress Distribution Supported by FLAC3D Numerical Simulation

Algorithm Optimization Applied in the Selection of Stress Di...

引用

2022 International Conference on Manufacturing, Industrial Automation and Electronics, ICMIAE 2022

作者： Zhu, Mingde Yin, Yantian Cheng, Li Hao, Yingjie Zhang, Jie Hou, Kuikui Zhang, Haoqin Deep Mining Laboratory of Shandong Gold Group Co. Ltd Ji’nan China Shandong Key Laboratory of Deep-sea and Deep-earth Metallic Mineral Intelligent Mining Ji’nan China School of Civil and Resource Engineering University of Science and Technology Beijing Beijing China

ISBN: (数字)9781665473965

ISBN: (纸本)9781665473965

Aiming at the problem of rockburst happened during deep mining activity in Inner Mongolia area, FLAC3D numerical simulation software was used to analyze the supporting effect of different supporting methods. Through the analysis of the influence of the three methods of slot-tube anchor bar, resin bolt and bolt-mesh combined support on the stress, displacement and elastic strain energy distribution of roadway surrounding rock, it is found that the bolt-mesh combined support can effectively reduce the elastic strain energy and the potential of rock burst. © 2022 IEEE.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

SIMULPL: ALIGNING HUMAN PREFERENCES IN SIMULTANEOUS MACHINE TRANSLATION

arXiv

引用

arXiv 2025年

作者： Yu, Donglei Zhao, Yang Zhu, Jie Xu, Yangyifan Zhou, Yu Zong, Chengqing School of Artificial Intelligence University of Chinese Academy of Sciences China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Graduate School of Translation and Interpretation Beijing Foreign Studies University China

Simultaneous Machine Translation (SiMT) generates translations while receiving streaming source inputs. This requires the SiMT model to learn a read/write policy, deciding when to translate and when to wait for more source input. Numerous linguistic studies indicate that audiences in SiMT scenarios have distinct preferences, such as accurate translations, simpler syntax, and no unnecessary latency. Aligning SiMT models with these human preferences is crucial to improve their performances. However, this issue still remains unexplored. Additionally, preference optimization for SiMT task is also challenging. Existing methods focus solely on optimizing the generated responses, ignoring human preferences related to latency and the optimization of read/write policy during the preference optimization phase. To address these challenges, we propose Simultaneous Preference Learning (SimulPL), a preference learning framework tailored for the SiMT task. In the SimulPL framework, we categorize SiMT human preferences into five aspects: translation quality preference, monotonicity preference, key point preference, simplicity preference, and latency preference. By leveraging the first four preferences, we construct human preference prompts to efficiently guide GPT-4/4o in generating preference data for the SiMT task. In the preference optimization phase, SimulPL integrates latency preference into the optimization objective and enables SiMT models to improve the read/write policy, thereby aligning with human preferences more effectively. Experimental results indicate that SimulPL exhibits better alignment with human preferences across all latency levels in Zh→En, De→En and En→Zh SiMT tasks. Our data and code will be available at https://***/EurekaForNLP/SimulPL. Copyright © 2025, The Authors. All rights reserved.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

A SAFE REINFORCEMENT LEARNING ALGORITHM FOR SUPERVISORY CONTROL OF POWER PLANTS

arXiv

引用

arXiv 2024年

作者： Sun, Yixuan Khairy, Sami Vilim, Richard B. Hu, Rui Dave, Akshay J. Mathematics and Computer Science Division Argonne National Laboratory United States Microsoft United States Nuclear Science and Engineering Division Argonne National Laboratory United States

Traditional control theory-based methods require tailored engineering for each system and constant fine-tuning. In power plant control, one often needs to obtain a precise representation of the system dynamics and carefully design the control scheme accordingly. Model-free Reinforcement learning (RL) has emerged as a promising solution for control tasks due to its ability to learn from trial-and-error interactions with the environment. It eliminates the need for explicitly modeling the environment’s dynamics, which is potentially inaccurate. However, the direct imposition of state constraints in power plant control raises challenges for standard RL methods. To address this, we propose a chance-constrained RL algorithm based on Proximal Policy optimization for supervisory control. Our method employs Lagrangian relaxation to convert the constrained optimization problem into an unconstrained objective, where trainable Lagrange multipliers enforce the state constraints. Our approach achieves the smallest distance of violation and violation rate in a load-follow maneuver for an advanced Nuclear Power Plant design. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Efficient operator method for modelling mode mixing in misaligned optical cavities

arXiv

引用

arXiv 2023年

作者： Hughes, William J. Doherty, Thomas H. Blackmore, Jacob A. Horak, Peter Goodwin, Joseph F. Department of Physics University of Oxford Clarendon Laboratory Parks Rd OxfordOX1 3PU United Kingdom Optoelectronics Research Centre University of Southampton SouthamptonSO17 1BJ United Kingdom

The transverse field structure and diffraction loss of the resonant modes of Fabry-Pérot optical cavities are acutely sensitive to the alignment and shape of the mirror substrates. We develop extensions to the 'mode mixing' method applicable to arbitrary mirror shapes, which both facilitate fast calculation of the modes of cavities with transversely misaligned mirrors and enable the determination and transformation of the geometric properties of these modes. We show how these methods extend previous capabilities by including the practically-motivated case of transverse mirror misalignment, unveiling rich and complex structure of the resonant modes. © 2023, CC BY.

关键词： Mirrors

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Automatic Text Summarization

Deep Learning for Automatic Text Summarization

引用

Telecommunications and Intelligent systems (ICTIS), International Conference on

作者： Youcef Ghibeche Abdallah Sellam Nabil Abdelkader Nouri Saad Laggoun Nizar Omar Idris Khadroun Laboratory of Telecommunications and Smart Systems Faculty of Science and Technology University of Djelfa Djelfa Algeria Institute of Science University Center El Cherif Bouchoucha Algeria Faculty of Exact Sciences and Computer Science University of Djelfa Djelfa Algeria

ISBN: (数字)9798331527396

ISBN: (纸本)9798331527402

In today's digital age, the rapid accumulation of textual information necessitates effective automatic text summarization. The demand for computer systems capable of summarizing vast amounts of information has grown exponentially, aiding users in extracting key insights and making informed decisions. This study focuses on the development of a robust abstractive text summarization model utilizing Deep Learning and Seq2Seq models with LSTM networks and attention mechanisms. Through the construction of a Seq2Seq-based framework incorporating LSTM layers and attention mechanisms, the model effectively captures semantic relationships and contextual dependencies within the input text. Training strategies, optimization techniques, and word embedding methods, including pretrained word embedding like GloVe, were employed to enhance the model's ability to generate accurate and concise summaries.

关键词： Training Deep learning Analytical models Vocabulary Attention mechanisms Reviews Computational modeling Text summarization Predictive models Long short term memory

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：