检索结果-内蒙古大学图书馆

Radial Vibration Measurement Based on Slope-assisted BOCDA Enabled by Multi-core Fiber

学校读者我要写书评

暂无评论

Radial Vibration Measurement Based on Slope-assisted BOCDA E...

Conference on Lasers and Electro-Optics (CLEO)

作者： Shuyan Chen Huan He Zhiyong Zhao Songnian Fu Ming Tang Wuhan National Lab for Optoelectronics (WNLO) & National Engineering Laboratory for Next Generation Internet Access System School of Optical and Electronic Information Huazhong University of Science and Technology Wuhan China Guangdong Provincial Key Laboratory of Photonics Information Technology and School of Information Engineering Guangdong University of Technology Guangzhou China

We propose a novel SA-BOCDA sensor based on multicore fiber. By subtracting the output probe powers of two symmetrical outer cores, response enhanced vibration detection is realized without frequency scanning.

ISBN: (纸本)9781957171258

关键词： Absolute distance measurement Fiber optic sensors Multicore fibers Single mode fibers Spatial resolution Vibration

A Binary PSO Based Ensemble Under-Sampling Model for Rebalancing Imbalanced Training Data

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Jinyan Wu, Yaoyang Fong, Simon Tallón-Ballesteros, Antonio J. Yang, Xin-She Mohammed, Sabah Department of Computer and Information Science University of Macau Taipa China Department of Languages and Computer Systems University of Seville Seville Spain Design Engineering and Math School of Science & Technology Middlesex University London United Kingdom Department of Computer Science Lakehead University Thunder Bay Canada

Ensemble technique and Under-sampling technique are both effective tools for resolvig imbalanced dataset classification problems, which commonly denotes the quantitative imbalance of a binary class dataset where minority class is the target class. In this paper, a novel ensemble method absorbing the advantages of both ensemble learning for biasing classifiers and a new evolutional under-sampling method is proposed. The under-sampling method is named Binary PSO instance selection, it gathers with ensemble classifiers to find the most suitable length and combination of majority class samples to build a new dataset with minority class samples. The proposed method adopts multi-objective strategy, objectives of this method is to improve the performances of imbalanced classification and to guarantee the maximum integrity of the original dataset. We examined our proposed method, the Binary PSO instance selection by comparing its performance of processing imbalanced dataset with several other conventional basic ensemble methods. Experiments are also conducted with Binary PSO instance selection wrapping with ensemble classifiers for further improvement of imbalanced classification. Based on comaprison experiments, our proposed methods outperform single ensemble methods, state-of-the-art under-sampling methods as well as their combinations with traditional PSO instance selection algorithm. Copyright © 2025, The Authors. All rights reserved.

关键词： Data assimilation

Dynamic mode decomposition for Koopman spectral analysis of elementary cellular automata

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Taga, Keisuke Kato, Yuzuru Yamazaki, Yoshihiro Kawahara, Yoshinobu Nakao, Hiroya Department of Physics School of Advanced Science and Engineering Waseda University Tokyo169-8555 Japan Department of Complex and Intelligent Systems School of Systems Information Science Future University Hakodate Hokkaido041-8655 Japan Graduate School of Information Science and Technology Osaka University Osaka565-0871 Japan Center for Advanced Intelligence Project RIKEN Tokyo103-0027 Japan Department of Systems and Control Engineering School of Engineering Tokyo Institute of Technology Tokyo152-8552 Japan

We apply Dynamic Mode Decomposition (DMD) to Elementary Cellular Automata (ECA). Three types of DMD methods are considered and the reproducibility of the system dynamics and Koopman eigenvalues from observed time series are investigated. While standard DMD fails to reproduce the system dynamics and Koopman eigenvalues associated with a given periodic orbit in some cases, Hankel DMD with delay-embedded time series improves reproducibility. However, Hankel DMD can still fail to reproduce all the Koopman eigenvalues in specific cases. We propose an Extended DMD method for ECA that uses nonlinearly transformed time series with discretized Walsh functions and show that it can completely reproduce the dynamics and Koopman eigenvalues. Linear-algebraic backgrounds for the reproducibility of the system dynamics and Koopman eigenvalues are also discussed. Copyright © 2023, The Authors. All rights reserved.

关键词： Dynamic mode decomposition

Design and Comparison of Collaborative Filtering technology for Product Suggestions in E-Commerce 1

学校读者我要写书评

暂无评论

Design and Comparison of Collaborative Filtering Technology ...

1st IEEE International Conference on Automation, Computing and Renewable systems, ICACRS 2022

作者： Rajasekar, P. Mohanraj, B. Padhi, S.N. Sivakumar, N. Lavanya, J. Charles Prabu, V. Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Tamil Nadu Chennai603203 India Department of Information Technology Karpagam College of Engineering Tamil Nadu Coimbatore641032 India Department of Mechanical Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram522302 India Department of Computer Science and Engineering Panimalar Engineering College Chennai City Campus Tamil Nadu Chennai600029 India Department of Fashion Designing SRM Institute of Science and Technology CSH Kattankulathur campus Tamil Nadu Chennai603203 India Department of Computer Science Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamil Nadu Chennai600 062 India

ISBN: (纸本)9781665460842

E-commerce websites and internet purchasing have never been more necessary. Product recommendations are a key tactic employed by online buying platforms. This study compares two different filtering algorithms that are used in product recommendationson websites like Amazon and Flipkart. Reviews of electrical devices, user data, and timestamps were all gathered from Kaggle and put into a dataset. These specifics then undergo several preprocessing steps. The steps are data visualization, duplicate value analysis, missing value analysis, and datatype analysis. The exhibited data is then used to train and test the machine learning models. For this purpose, two machine learning models are developed using two different algorithms. The algorithms K-Nearest Neighbor(KNN) and Support Vector Decomposition (SVD) are employed. The models are then trained to acquire used in the prediction procedure after that. The best models for the prediction process are then determined by scrutinizing the results of both models. The Root Mean Square Error (RMSE), Mean Square Error (MSE), and Mean Absolute Error (MAE) values are located and compared because the findings of the analysis weren't *** erroneous data are plotted into a graph and evaluated to further demonstrate the point. As the SVD method is discovered to be the best of the group, the algorithm's greatest and worst predictions are discovered and examined. Even the poorest model constructed for the study's predictions turned out to be superior to several other prediction algorithms used for product suggestions. This algorithm can be deployed into the backend of any e-commerce website making it more effective. © 2022 IEEE

关键词： Value engineering

DeepACO: Neural-enhanced Ant systems for Combinatorial Optimization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ye, Haoran Wang, Jiarui Cao, Zhiguang Liang, Helan Li, Yong School of Computer Science & Technology Soochow University China School of Computing and Information Systems Singapore Management University Singapore Department of Electronic Engineering Tsinghua University China

Ant Colony Optimization (ACO) is a meta-heuristic algorithm that has been successfully applied to various Combinatorial Optimization Problems (COPs). Traditionally, customizing ACO for a specific problem requires the expert design of knowledge-driven heuristics. In this paper, we propose DeepACO, a generic framework that leverages deep reinforcement learning to automate heuristic designs. DeepACO serves to strengthen the heuristic measures of existing ACO algorithms and dispense with laborious manual design in future ACO applications. As a neural-enhanced meta-heuristic, DeepACO consistently outperforms its ACO counterparts on eight COPs using a single neural architecture and a single set of hyperparameters. As a Neural Combinatorial Optimization method, DeepACO performs better than or on par with problem-specific methods on canonical routing problems. Our code is publicly available at https://***/henry-yeh/DeepACO. Copyright © 2023, The Authors. All rights reserved.

关键词： Ant colony optimization

METHODOLOGY OF ARCHITECTURE REPRESENTATION AND ENUMERATION OF MORE-ELECTRIC FLIGHT CONTROL SYSTEM

学校读者我要写书评

暂无评论

METHODOLOGY OF ARCHITECTURE REPRESENTATION AND ENUMERATION O...

2022 CSAA/IET International Conference on Aircraft Utility systems, AUS 2022

作者： Wang, Zhe Jiao, Zongxia Li, Yang School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Ningbo Institute of Technology Beihang University Ningbo315800 China Science and Technology on Aircraft Control Laboratory Beihang University Beijing100191 China Research Institute for Frontier Science Beihang University Beijing100191 China Key Laboratory of Advanced Aircraft Utility Systems Beihang University Ministry of Industry and Information Technology China

ISBN: (数字)9781839537769

ISBN: (纸本)9781839537769

When building complex systems, the design space of the system architecture needs to be modelled and fully expanded to support experts in making further decisions. The trend of more-electric aircraft (MEA) allows electric energy and electric actuators to replace part of hydraulic energy and hydraulic actuators, making the design of flight control systems (FCS) more and more complicated. In this paper, a representation and enumeration method of the architecture of the MEA flight control system based on the morphological analysis method is proposed. The morphological matrix is used to represent the structure of the system, and the enumeration method is used to obtain all possible architecture combinations. A method of determining whether a combination is expected to be generated is proposed. © 2022 IET Conference Proceedings. All rights reserved.

关键词： Flight control systems

A Computer Vision-Based Framework for Behavior Monitoring and Estrus Detection Through Dynamic Behavioral Analysis 1

学校读者我要写书评

暂无评论

10th International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making, IUKM 2023

作者： Kanjanarut, Panisara Pannakkong, Warut Olapiriyakul, Sun Sanglerdsinlapachai, Nuttapong Hasegawa, Shoichi School of Information Computer and Communication Technology Sirindhorn International Institute of Technology Thammasat University Pathum Thani Khlong Nueng 12121 Thailand School of Manufacturing Systems and Mechanical Engineering Sirindhorn International Institute of Technology Thammasat University Pathum Thani Khlong Nueng 12121 Thailand National Electronics and Computer Technology Center 112 Thailand Science Park Phahon Yothin Road Klong I Pathumthani Klong Luang 12120 Thailand Tokyo Institute of Technology 4259 Nagatsuta-cho Midori-ku Yokohama Japan

ISBN: (数字)9783031467813

ISBN: (纸本)9783031467806

The research field of behavior monitoring and estrus detection in cows has predominantly concentrated on investigating isolated occurrences of mounting behavior, neglecting the analysis of dynamic behaviors exhibited during the estrus period, before and following mounting. To address these limitations, this paper proposes a framework that utilizes computer vision techniques to analyze visual data, classify behavioral features, track the duration of behaviors, and identify potential deviations from normal behavior based on historical data. The part of dynamic behavioral analysis, which encompasses the assessment of behavioral changes and historical behavior data to identify the optimal time window for Artificial Insemination (AI) and potential abnormalities in behaviors, is the main novelty of this framework. Based on our preliminary experiments conducted on a well-known public dataset, the behavior classification model achieves an overall accuracy of 80.7% in accurately classifying various behaviors, including standing, walking, lying down, and feeding. While the model demonstrates proficiency in identifying feeding, lying down, and standing behaviors, there is still room for improvement in accurately recognizing walking behavior. This research contributes to advancing behavior monitoring and estrus detection techniques, providing a way for improved AI practices in the cattle industry. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Mountings

PG-Attack: A Precision-Guided Adversarial Attack Framework Against Vision Foundation Models for Autonomous Driving

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Fu, Jiyuan Chen, Zhaoyu Jiang, Kaixun Guo, Haijing Gao, Shuyong Zhang, Wenqiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Shanghai Engineering Research Center of AI & Robotics Academy for Engineering & Technology Fudan University China Engineering Research Center of Robotics Ministry of Education Academy for Engineering & Technology Fudan University China

Vision foundation models are increasingly employed in autonomous driving systems due to their advanced capabilities. However, these models are susceptible to adversarial attacks, posing significant risks to the reliability and safety of autonomous vehicles. Adversaries can exploit these vulnerabilities to manipulate the vehicle’s perception of its surroundings, leading to erroneous decisions and potentially catastrophic consequences. To address this challenge, we propose a novel Precision-Guided Adversarial Attack (PG-Attack) framework that combines two techniques: Precision Mask Perturbation Attack (PMP-Attack) and Deceptive Text Patch Attack (DTP-Attack). PMP-Attack precisely targets the attack region to minimize the overall perturbation while maximizing its impact on the target object’s representation in the model’s feature space. DTP-Attack introduces deceptive text patches that disrupt the model’s understanding of the scene, further enhancing the attack’s effectiveness. Our experiments demonstrate that PG-Attack successfully deceives a variety of advanced multi-modal large models, including GPT-4V, Qwen-VL, and imp-V1. Additionally, we won First-Place in the CVPR 2024 Workshop Challenge: Black-box Adversarial Attacks on Vision Foundation Models‡ and codes are available at https://***/fuhaha824/PG-Attack. Copyright © 2024, The Authors. All rights reserved.

关键词： Autonomous vehicles

Life Cycle Cost Assessment and LCOE of 10.2 MW wind farm

学校读者我要写书评

暂无评论

Life Cycle Cost Assessment and LCOE of 10.2 MW wind farm

Electrical engineering and Automatic Control (ICEEAC), International Conference on

作者： Abdelkarim Tahtah Driss Raouti Lionel Vido Rachid Meziane Electrotechnical Engineering Laboratory University of Saida Dr Taher Moulay Saîda Algeria Lab. of Information and Energy Technology Systems and Application CY Cergy Paris University Cergy-Pontoise France

ISBN: (数字)9798350349740

ISBN: (纸本)9798350349757

Wind farm system is an exciting renewables energies sources, on all the plans. Wind turbines are now part of our landscape and which are developing at high speed. The expansion recent accelerated of wind farms is synonymous of a set of techno-economic constraints and ecological emit. This has resulted in the work on the improvement of the life cycles cost in order to achieve Balance in the levelized cost of energy. Renewable energies are among the goals of the Algerian government to reduce the production of energies through gas and coal by encouraging investment in green energies. The economic cost associated with the life cycles of renewable energies is a main problem that must be optimize. The life-cycle study simulates the chronology of a wind farm and the mechanism of the contribution of phases over the lifespan. Four phases are used manufacturing, transportation & installation, exploitation & operations, and finally dismantling and recycling. according on the cost of one kWh, this study is the subject of a real case which is the Kabertanne wind farm located in the W. Adrar who counts 12 wind power turbines, type G.52-850 kW. The results obtained respectively show the rates of contribution from each phase in relation to the total cost, which are as follows: 47.04%; 41.3%; 8.5%; 3.2%. To assess the effectiveness of the obtained results of LCOE, the LCA and Monte Carlo methods were used to compare the results.

关键词： Life cycle assessment Costs Transportation Production Wind farms Wind power generation Wind turbines