检索结果-内蒙古大学图书馆

Individual mapping and asymmetric dual supervision for discrete cross-modal hashing

EXPERT SYSTEMS WITH APPLICATIONS 2024年 247卷

作者： Wang, Song Zhao, Huan Zhang, Zixing Li, Keqin Hunan Univ Coll Comp Sci & Elect Engn Changsha 410082 Peoples R China Key Lab Embedded & Network Comp Hunan Prov Changsha 410082 Peoples R China SUNY Coll New Paltz Dept Comp Sci New Paltz NY 12561 USA

Cross -modal hashing has gained popularity in similarity search due to its excellent query efficiency and economical storage costs. However, current models frequently overlook the distinctive property of each modality, resulting in reduced accuracy due to inadequate utilization of these attributes. Moreover, there is a weak semantic relevance between modality attributes and multiple supervision knowledge (the labels and similarity constraints constructed by labels), accompanied by a cumulative quantization of the models. To address these issues, we propose an Individual Mapping and Asymmetric Dual Supervision method (IMADS). It merges specific and shared information to effectively learn a cross -modal representation space. Furthermore, we present an asymmetric dual supervision learning framework to produce discriminative hash codes. This framework achieves two primary goals: (1) Combing cross -modal representation and multiple supervision information to enhance the consistent relation of distinct modalities, and (2) developing a discrete optimization algorithm to mitigate the information loss caused by the hash code. Comprehensive experimental results illustrate that the introduced IMADS outperforms other stat-of-the-art hashing methods.

关键词： Asymmetric dual supervision Cross-modal hashing Individual mapping optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Mechanical Behavior Monitoring and Load Inversion Analysis of Large-Diameter Underwater Shield Tunnel during Construction

引用

SENSORS 2024年第4期24卷 1310页

作者： Ma, Si-Yuan Ye, Xiao-Wei Liu, Zhi-Xiong Ding, Yang Zhang, Di Sun, Feng Zhejiang Univ Dept Civil Engn Hangzhou 310058 Peoples R China Hangzhou City Univ Dept Civil Engn Hangzhou 310015 Peoples R China China Railway Siyuan Survey & Design Grp Co Ltd Wuhan 430063 Peoples R China

The construction of large-diameter shield tunnels underwater involves complex variations in water and earth load outside the tunnel segment, as well as intricate mechanical responses. This study analyzes the variation laws of external loads, axial forces, and bending moments acting on the segment ring during the shield assembly and removal from the shield tail. It accomplishes this through the establishment of an on-site monitoring system based on the Internet of Things (IoT) and proposes a Bayesian-genetic algorithm model to estimate the water and earth pressure. The fluctuation section exhibits a peak load twice as high as that in the stable section. These variations are influenced by Jack thrust, shield shell force, and grouting pressure. The peak load observed in the fluctuation section is twice as high as the load observed in the stable section. During the shield tail removal process, the internal forces undergo significant fluctuations due to changes in both load and boundary conditions, and the peak value of the axial force during the fluctuation section is eight times higher than that during the stable section, while the peak value of the bending moment during the fluctuation section is five times higher than that during the stable section. The earth and water pressure calculated using the inversion analysis method, which relies on the measured internal forces, closely matches the actual measured values. The results demonstrate that the accuracy of the water and earth pressure obtained through inversion analysis is twice as high as that obtained using the full coverage pressure method. These results can serve as a valuable reference for similar projects.

关键词： Structural Health Monitoring shield tunnel Fiber Bragg grating inversion analysis Parameter estimation optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A novel reinforcement learning based Heap-based optimizer

引用

KNOWLEDGE-BASED SYSTEMS 2024年 296卷

作者： Ma, Xuesen Zhong, Zhineng Li, Yangyu Li, Dacheng Qiao, Yan Hefei Univ Technol Sch Comp Sci & Informat Engn Hefei Peoples R China Intelligent Mfg Inst HFUT Hefei Peoples R China Chinese Acad Sci Hefei Inst Phys Sci Hefei Peoples R China

The Heap-Based optimization (HBO), a novel meta-heuristic algorithm, constructs a hierarchical heap resembling a company structure to facilitate interaction among search agents. This enables the search agent to learn various levels of information from the population to obtain improved solutions, but it has drawbacks such as limited search capability and slow convergence speed when tackling complex optimization problems. To address these challenges, we propose an enhanced heap optimizer based on reinforcement learning(RLHBO), which demonstrates robust stability, rapid convergence, and high solution accuracy. Firstly, fixed operators are replaced with a reinforcement learning dynamic control search strategy in RLHBO to regulate the search range of agents. This prevents agents from being restricted in their search when encountering local or global optima, thus enhancing their search capability. Additionally, RLHBO introduces a dimensional selflearning strategy and a convergence strategy based on search direction similarity to address issues such as invalid and discrete solutions, accelerating convergence. Furthermore, an initialization strategy based on quasi-oppositional learning is employed to increase the diversity of the algorithm-generated population, surpassing the limitations of random initialization and further boosting convergence speed. Extensive testing on various complex functions from CEC2017 and CEC2022 demonstrates that RLHBO, as presented in this paper, outperforms HBO and numerous other advanced MAs in terms of search capability and convergence speed.

关键词： Meta-heuristic algorithm optimization algorithm Heap-based optimizer Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

End-to-end inverse modeling and optimization for filters based on artificial neural network

引用

INTERNATIONAL JOURNAL OF RF AND MICROWAVE COMPUTER-AIDED ENGINEERING 2022年第11期32卷 e23365-e23365页

作者： Huang, Hao Liang, Xiuye Guan, Fang Zi, Jian Fudan Univ Inst Nanoelect Devices & Quantum Comp State Key Lab Surface Phys Shanghai 200433 Peoples R China Fudan Univ Dept Phys State Key Lab Surface Phys Shanghai Peoples R China Fudan Univ Zhangjiang Fudan Int Innovat Ctr Shanghai Peoples R China

In this letter, we propose an end-to-end inverse modeling and optimization method for microwave filter designs based on the data-augmentation learning strategy. Because of the non-uniqueness of solutions, it is difficult to achieve good convergence with artificial neural networks for inverse designs when the parameter space is very large. We prove that the accuracy of inverse predictions can be significantly improved using the network's self-generated data and the optimization can be greatly accelerated with the help of the inverse network. The predicted structural parameters can be used as initial values for optimization, which reduces the number of iterations and avoids falling into local optima. This method is applied to designs of fourth-order interdigital cavity filters. The measurement and simulation agree well.

关键词： artificial neural network microwave filter optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Fast aircraft separation calculations for gradient based optimization of airspace simulations

Fast aircraft separation calculations for gradient based opt...

引用

AIAA Science and Technology Forum and Exposition (AIAA SciTech Forum)

作者： Hearn, Tristan A. NASA Glenn Res Ctr Prop Syst Anal Branch 21000 Brookpk Rd Ms 5-11 Cleveland OH 44135 USA

ISBN: (数字)9781624106095

ISBN: (纸本)9781624106095

Simulations of airspace operational concepts can play a significant role in determining future paradigms that would allow for a safe increase in airspace density. In particular, airspace simulations which are capable of handling large numbers of aircraft act as an enabling capability for the testing of proposed airspace operational concepts. Simulations allowing for gradient based optimization methods are particularly attractive, since they would potentially allow for an efficient and empirical means to derive best operational practices. These could also allow for vehicle multidisciplinary design and optimization studies to include air traffic management considerations as a discipline. But any large scale simulation of airspace operations must include some methodology for addressing airspace separation requirements, which in the most direct sense would be tracked in a manner that computationally grows as a quadratic function of the number of simulated aircraft. Efficient indirect methods have been developed in certain contexts to address this limitation. However, any means of addressing separation requirements in a gradient based optimization context should be implemented by functions which provide analytic derivative information to maximize numerical precision and computational efficiency. In this paper, a fast and differentiable separation metric is described in application to gradient based optimization of airspace operations. Rather than computing the separation distance between every pair of aircraft in a simulation, this method effectively reduces the problem to a smaller relevant set using a geometric decomposition. This method guarantees that the smallest distance at all points in simulated time is determined exactly. When used in an optimization constraint context, this guarantees that a required separation is maintained between all pairs of aircraft. The presented metric has logarithmic computational growth with respect to the number of simulated aircraft,

关键词： Airspace Management Air Traffic Control Air Traffic Management Computing Multidisciplinary Design optimization optimization algorithm Unmanned Aircraft System Trajectory optimization Collocation Method Brute Force Search

来源：评论

学校读者我要写书评

暂无评论

Sensorless intelligent second-order integral sliding mode maximum power point tracking control for wind turbine system based on wind speed estimation

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART I-JOURNAL OF SYSTEMS AND CONTROL ENGINEERING 2021年第7期235卷 1046-1063页

作者： Ma, Leiming Xiao, Lingfei Yang, Jianfeng Huang, Xinhao Meng, Xiangshuo Nanjing Univ Aeronaut & Astronaut Coll Energy & Power Engn Room 402 Nanjing 210016 Peoples R China Lanzhou Jiaotong Univ Automat & Elect Engn Lanzhou Peoples R China

Aiming at the maximum power point tracking for wind turbine, a sensorless intelligent second-order integral sliding mode control based on wind speed estimation is proposed in this article. The maximum wind energy capture is realized by controlling permanent magnet synchronous motor to adjust the speed of wind turbine. First, an intelligent second-order integral sliding mode control is designed for the speed loop and current loop control, which has fast convergence speed, strong robustness and can effectively reduce chattering. Second, a novel cascade observer based on direct sliding mode observer and extended high-gain observer is used to estimate the rotor speed and position. Besides, combined radial basis function neural network is used to estimate the valid value of wind speed. Both simulation and experiment are implemented, which verify the effectiveness of the proposed strategy under the condition of considering both model uncertainty and external disturbance.

关键词： Wind turbine second-order integral sliding mode maximum power point tracking sensorless control wind speed estimation optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimal Design of Interior Permanent Magnet Synchronous Motor for Eco-friendly ship using Hybrid ABC-SVM algorithm 20

Optimal Design of Interior Permanent Magnet Synchronous Moto...

引用

20th Biennial IEEE Conference on Electromagnetic Field Computation (CEFC)

作者： Park, Jong-Woon Lim, Dong-Kuk Univ Ulsan Dept Elect Elect & Comp Engn Ulsan South Korea

ISBN: (数字)9781665468336

ISBN: (纸本)9781665468336

This paper investigates the best design of IPMSM for eco-friendly ships using a hybrid ABC-SVM algorithm (HAS). HAS is a multimodal optimization method capable of exploring several optimal solutions. HAS enhances navigation capability by combining the existing Artificial Bee Colony algorithm (ABC) with Support Vector Machine (SVM). In addition, hybridization with Simplex enables accurate and quick convergence on neighbor optimization at pointers discovered in ABC. In two test functions, the higher performance of the proposed algorithm is tested with conventional ABC, and the algorithm is applied to the optimal design of the IPMSM for the eco-friendly ship.

关键词： Electromagnetic analysis Eco-friendly ship Motor optimization optimization algorithm Permanent magnet motors

来源：评论

学校读者我要写书评

暂无评论

Optimal Design of Elliptical Beam Cassegrain Antenna

引用

IEEE ACCESS 2021年 9卷 120765-120773页

作者： Liu, Xinglong Du, Biao Zhou, Jianzhai Xie, Lei China Elect Technol Grp Corp Res Inst 54 Shijiazhuang Hebei Peoples R China Xidian Univ Natl Lab Sci & Technol Antennas & Microwaves Xian 710071 Peoples R China

An optimal design method of elliptical beam Cassegrain antenna based on differential evolution with global and local neighborhoods algorithm is proposed to achieve high efficiency, low sidelobe, and low profile at Ku/Ka dual band. A rapid shaping method of elliptical beam antenna is given by applying the algorithm of steepest descent. Constraining of the first sidelobe level, antenna efficiency is optimized with only 17 variables, where aperture field distribution functions in the major and minor axis planes are parameterized by Non-uniform rational B-spline curves, and the transition function is expressed with a sinusoidal function. A prototype of optimized antenna with an aperture of 630 mm x 1150 mm is fabricated and measured. The measured results show that the total efficiency is greater than 54.5%, and the first sidelobe levels are lower than across the Ku/Ka dual-band, which agree well with simulated ones. It is verified that the optimal design method is very effective.

关键词： Reflector antenna elliptical beam low profile dual-band optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence in Geopolymer Concrete Mix Design: A Comprehensive Review of Techniques and Applications

引用

Iranian Journal of Science and Technology - Transactions of Civil Engineering 2025年 1-33页

作者： Mushthofa, Malik Thedy, John Teguh, Mochamad Purwanto Pratama, Adjie Gemilang Han, Ay Lie Department of Civil Engineering Islamic University of Indonesia Yogyakarta 55584 Indonesia Department of Bioenvironmental Systems Engineering National Taiwan University Taipei 10617 Taiwan Department of Civil Engineering Diponegoro University Semarang 50275 Indonesia

This systematic review explores the application of Artificial Intelligence (AI) in optimizing the mix design of fly ash-based geopolymer concrete (FABGC). Analyzing studies published between 2014 and 2025, it examines key methodologies, including machine learning models, optimization algorithms, and multi-criteria decision-making approaches. Critical aspects such as data preprocessing, AI model selection, hyperparameter tuning, explainable AI (XAI), and optimization strategies are synthesized to provide a comprehensive perspective on AI-driven FABGC research. The review identifies Deep Residual Networks (ResNet) and Extreme Gradient Boosting (XGB) as the most accurate models for predicting FABGC strength, consistently outperforming others due to their lower error metrics. Backpropagation Neural Networks (BPNN) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS) also demonstrate competitive performance, while Random Forest (RF) and Decision Tree (DT) models excel in computational efficiency with shorter training times. Despite being the most widely implemented, Artificial Neural Networks (ANN) rarely achieve the highest predictive accuracy. Traditional regression methods, though straightforward, lag behind in performance. These findings underscore the need for standardized datasets, enhanced collaboration, and innovative AI-driven approaches to improve FABGC mix design optimization. Addressing these challenges will facilitate more reliable and efficient AI applications in sustainable concrete technology. © The Author(s), under exclusive licence to Shiraz University 2025.

关键词： Artificial intelligence Fly ash Geopolymer concrete Mix design optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

An effective model for network selection and resource allocation in 5G heterogeneous network using hybrid heuristic-assisted multi-objective function

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年 248卷

作者： Urooj, Shabana Arunachalam, Rajesh Alawad, Mohamad A. Tripathi, Kuldeep Narayan Sukumaran, Damodaran Ilango, Poonguzhali Princess Nourah bint Abdulrahman Univ Coll Engn Dept Elect Engn POB 84428 Riyadh 84428 Saudi Arabia Saveetha Inst Med & Tech Sci Saveetha Sch Engn Dept Elect & Commun Engn Chennai 602105 Tamilnadu India Imam Mohammad Ibn Saud Islamic Univ Dept Elect Engn Riyadh 11432 Saudi Arabia Madhav Inst Technol & Sci MITS Dept Comp Sci & Engn Gwalior Madhya Pradesh India Vel Tech High Tech Dr Rangarajan Dr Sakunthala Eng Dept Math Chennai 600062 Tamilnadu India Panimalar Engn Coll Dept Elect & Commun Engn Chennai 600123 Tamilnadu India

Multiple service requirements in various communication environments are fulfilled by the fifth-generation (5G) mobile communication network. Heterogeneous Networks (HetNet) have been introduced as a newly developed network structure. Conventional cellular networks have prominent limitations in terms of frequency utilization, coverage, proliferation of transmission services, and power consumption. The previously used approaches provide precise results but are time-consuming, making them tricky to apply for huge networks, and makes them complicated to solve multifaceted problems. In order to decrease complementary interference and accomplish spectrum sharing, an effective resource allocation technique is necessary. Likewise, interference produced by the potential Secondary Users (SUs) must be kept at a minimum value within the authorized network. Considering the perspective of the supplementary networks, it is vital to delegate networks to SUs in order to lower the gross contamination and manage the overall network's quantity. An efficient method is developed on a heuristic basis in order to solve the issues regarding resource allocation in 5G networks. With the aid of every user device's network properties, network selection, and resource allocation are considered the two major concerns that need to be attained in 5G heterogeneous network systems. To meet this requirement, the multi-objective constraints are considered with the help of the Integrated African Vultures with Grasshopper optimization algorithm (IAVGOA). The constraints that are taken into consideration are communication cost, interference between all the SU to the primary user, Quality of Service (QoS), and congestion control. The performance of the executed model is examined using various metrics. When compared with the existing models, the proposed method achieves impressive results in appropriately selecting the network and allocating the resources over 5G networks.

关键词： Network selection Resource allocation 5G heterogeneous network Integrated African vultures with grasshopper optimization algorithm Multi -objective constraints

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：