检索结果-内蒙古大学图书馆

A multivariable hybrid prediction system of wind power based on outlier test and innovative multi-objective optimization

引用

ENERGY 2022年第PartE期239卷 122333-122333页

作者： Guo, Honggang Wang, Jianzhou Li, Zhiwu Jin, Yu Dongbei Univ Finance & Econ Sch Stat Dalian 116025 Peoples R China Macau Univ Sci & Technol Inst Syst Engn Taipa Macau Peoples R China

Wind power forecasting is critical to the safe running of the power grid. However, due to the strong intermittence and instability of wind, reliable forecast of wind power remains a significant difficulty. In this study, a novel multivariable machine learning hybrid prediction system that incorporates data preprocessing, prediction, and multi-objective system optimization is designed to quantify the certainty and uncertainty of wind power. To increase the quality of data input, the data preparation module performs outlier tests based on the correlation between wind power and wind speed, as well as feature extraction, on the original data. In the prediction process, this paper offers an incremental kernel extreme learning machine (IK-elm), the parameters of which are set synchronously by an enhanced multi-objective optimization technique (MOCEHHO) developed in this paper. It overcomes the restrictions of duplicated hidden layer nodes and low learning efficiency caused by classic ELM and successfully maximizes the model's prediction capabilities. The simulation results on four datasets from Turkish wind farms show that the hybrid forecasting system outperforms the benchmark and may be utilized as a useful tool for wind power forecasting. (C) 2021 Elsevier Ltd. All rights reserved.

关键词： Wind power prediction Outlier test Multivariable machine learning Multi-objective optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Symmetric Cryptography With a Chaotic Map and a Multilayer Machine Learning Network for Physiological Signal Infosecurity: Case Study in Electrocardiogram

引用

IEEE ACCESS 2021年 9卷 26451-26467页

作者： Lin, Chia-Hung Wu, Jian-Xing Chen, Pi-Yun Li, Chien-Ming Pai, Neng-Sheng Kuo, Chao-Lin Natl Chin Yi Univ Technol Dept Elect Engn Taichung 41170 Taiwan Chi Mei Med Ctr Dept Med Div Infect Dis Tainan 41710 Taiwan Natl Kaohsiung Univ Sci & Technol Dept Maritime Informat & Technol Kaohsiung 80543 Taiwan

Digital physiological signals in telecare medicine information systems have been widely applied in remote medical applications, such as telecare, tele-examination, and telediagnosis, via computer networking transmission or wireless communication. However, these medical records need to ensure authorization demands in the channel model for human body communication and remote medical servers and enhance the confidentiality, recoverability, and availability of transmission data. Hence, this study proposes a symmetric cryptography scheme with a chaotic map and a multilayer machine learning network (MMLN) to achieve physiological signal infosecurity. A chaotic pseudorandom number generator within specific control parameters can dynamically produce unordered sequence numbers to set the secret keys for a regular secret key update, thereby improving the security of private cipher codes. The chaotic map is quickly iterated to produce a pseudorandom key stream for real-time applications, and the private cipher codes are selected using the initial and specific control parameters at the data emitter and receiver ends. A general regression neural network is used to map the high-dimensional input-output pair of cipher codes for substitution and permutation processes. Its adaptive MMLN with an optimization algorithm can rapidly train the random cipher code protocol to achieve an encryptor and a decryptor for a regular encrypted communication. Using the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) Arrhythmia Database, 100 electrocardiogram fragments are used to verify the proposed model, and the peak signal-to-noise ratio (PSNR) as a quantitative quality metric is used to evaluate the visual quality after encryption and decryption processes for further diagnosis applications. Experimental results show that the proposed scheme has a higher mean PSNR (35.26 +/- 3.77 dB) and shorter mean executing time (0.16 +/- 0.01 s) compared with traditional cryptography pro

关键词： Electrocardiography Chaotic communication Ciphers Protocols Measurement Encryption Wireless communication Symmetric cryptography chaotic map general regression neural network optimization algorithm peak signal-to-noise ratio

来源：评论

学校读者我要写书评

暂无评论

Application of Self-adaptive Vision-Correction algorithm for Water-Distribution Problem

引用

KSCE JOURNAL OF CIVIL ENGINEERING 2021年第3期25卷 1106-1115页

作者： Lee, Eui Hoon Chungbuk Natl Univ Sch Civil Engn Cheongju 28644 South Korea

Water is one of the essential elements in human life, and the water-distribution system is an important infrastructure that distributes water to the people. The design of the water-distribution system was done manually in the past, but recently, it was conducted by applying optimization algorithms. Various optimization algorithms were developed for the optimal design of the water-distribution system, but there was a disadvantage to perform sensitivity analysis for parameter estimation manually. A vision-correction algorithm (VCA) was developed to emulate the conventional manual vision-correction procedure, and it exhibited a good performance in many mathematical benchmark and civil engineering problems. However, the VCA has limited usefulness because of its large number of parameters, many of which require estimation. In this study, a self-adaptive VCA (SAVCA) was developed to overcome these shortcomings by modifying the parameters of the VCA to be self-adaptive or fixed. The Balerma network - a water-distribution system - was selected as a civil engineering problem. The results of SAVCA were better than those of other methods for the design of Balerma network. The SAVCA exhibited good usability and performance and can be applied to various fields in civil engineering including the water-distribution system.

关键词： Water-distribution system Civil engineering problem Metaheuristic Self-adaptive Vision correction optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Tour Design Using Resonant-Orbit Invariant Manifolds in Patched Circular Restricted Three-Body Problems

引用

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS 2021年第1期44卷 106-119页

作者： Anderson, Rodney L. CALTECH Jet Prop Lab 4800 Oak Grove DrM-S 301-121 Pasadena CA 91109 USA

It is increasingly desirable to incorporate multibody effects in tour design early in the process to both discover new solutions and reduce the number and size of required maneuvers. Flybys have previously been designed using the heteroclinic connections of resonant orbits in the circular restricted three-body problem (CRTBP), but tour design often requires the consideration of additional moons, especially within the Jovian system. In this study, the heteroclinic connections of multiple resonant orbits are chained together within separate CRTBP models to perform multiple flybys that advance through desired resonances. Methods for patching these trajectories together are explored, and sample trajectories are computed.

关键词： Ganymede Orbital Period Computing optimization algorithm Numerical optimization Keplerian Orbit Libration Points Astrodynamics Astronomy Earth

来源：评论

学校读者我要写书评

暂无评论

Advanced Meta-Heuristics, Convolutional Neural Networks, and Feature Selectors for Efficient COVID-19 X-Ray Chest Image Classification

引用

IEEE ACCESS 2021年 9卷 36019-36037页

作者： El-Kenawy, El-Sayed M. Mirjalili, Seyedali Ibrahim, Abdelhameed Alrahmawy, Mohammed El-Said, M. Zaki, Rokaia M. Eid, Marwa Metwally Delta Higher Inst Engn & Technol DHIET Dept Commun & Elect Mansoura 35111 Egypt Torrens Univ Australia Ctr Artificial Intelligence Res & Optimizat Fortitude Valley Qld 4006 Australia Yonsei Univ Yonsei Frontier Lab Seoul 03722 South Korea Mansoura Univ Fac Engn Comp Engn & Control Syst Dept Mansoura 35516 Egypt Mansoura Univ Fac Comp & Informat Dept Comp Sci Mansoura 35516 Egypt Mansoura Univ Fac Engn Elect Engn Dept Mansoura 35516 Egypt Delta Higher Inst Engn & Technol DHIET Mansoura 35111 Egypt Benha Univ Shoubra Fac Engn Dept Elect Engn Banha 11629 Egypt

The chest X-ray is considered a significant clinical utility for basic examination and diagnosis. The human lung area can be affected by various infections, such as bacteria and viruses, leading to pneumonia. Efficient and reliable classification method facilities the diagnosis of such infections. Deep transfer learning has been introduced for pneumonia detection from chest X-rays in different models. However, there is still a need for further improvements in the feature extraction and advanced classification stages. This paper proposes a classification method with two stages to classify different cases from the chest X-ray images based on a proposed Advanced Squirrel Search optimization algorithm (ASSOA). The first stage is the feature learning and extraction processes based on a Convolutional Neural Network (CNN) model named ResNet-50 with image augmentation and dropout processes. The ASSOA algorithm is then applied to the extracted features for the feature selection process. Finally, the Multi-layer Perceptron (MLP) Neural Network's connection weights are optimized by the proposed ASSOA algorithm (using the selected features) to classify input cases. A Kaggle chest X-ray images (Pneumonia) dataset consists of 5,863 X-rays is employed in the experiments. The proposed ASSOA algorithm is compared with the basic Squirrel Search (SS) optimization algorithm, Grey Wolf Optimizer (GWO), and Genetic algorithm (GA) for feature selection to validate its efficiency. The proposed (ASSOA + MLP) is also compared with other classifiers, based on (SS + MLP), (GWO + MLP), and (GA + MLP), in performance metrics. The proposed (ASSOA + MLP) algorithm achieved a classification mean accuracy of (99.26%). The ASSOA + MLP algorithm also achieved a classification mean accuracy of (99.7%) for a chest X-ray COVID-19 dataset tested from GitHub. The results and statistical tests demonstrate the high effectiveness of the proposed method in determining the infected cases.

关键词： X-ray imaging Feature extraction Diseases optimization Lung COVID-19 Classification algorithms Chest X-ray transfer learning convolutional neural network squirrel search optimization multilayer perceptron optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Comprehensive exploration: Automatic mode-locking technology and its multidisciplinary applications

引用

INFRARED PHYSICS & TECHNOLOGY 2024年 138卷

作者： Liu, He Sun, Chenxi Zhang, Haoran Harbin Univ Sci & Technol Sch Measurement & Commun Engn Harbin Peoples R China

We present a thorough review of the evolution and current status of automatic mode -locking technology, offering insights into its remarkable developments. Automatic mode -locking technology commences with traversal algorithms and genetic algorithms, progressing to machine learning. The advancements of optimization algorithms have ushered in a new era characterized by exceptional time efficiency, enhanced precision, adaptability to multiple variables, and the ability to engage with complex mode -locking regimes. This review concentrates on the improvements of hardware components of automatic mode -locking technology in addition to these algorithmic advances. We introduce the evolution of pivotal components, including polarization control elements and central control sections, which play a critical role in achieving stability and integration, and introduction of realtime measurement techniques in hardware, such as the time -stretched dispersive Fourier transform, which accurate monitoring and adjustment of clamping status and optical characteristics. Finally, a summary and outlook on the development of automatic mode -locking technology is presented.

关键词： Automatic mode -locking optimization algorithm Time -stretched dispersive Fourier transform

来源：评论

学校读者我要写书评

暂无评论

Optimizing Urban Electric Vehicle Charging Infrastructure Selection: An Approach Integrating GPS Data, Battery Levels, and Energy Availability

引用

IFAC-PapersOnLine 2024年第13期58卷 392-397页

作者： Meriem Belaid Said El Beid Anas Hatim CISIEV Team Cadi Ayyad University Marrakech 40160 Morocco TIM team Cadi Ayyad University Marrakech 40160 Morocco

This research paper offers a comprehensive exploration of how to enhance the charging infrastructure for Electric Vehicles (EVs) in urban settings. The analysis assesses three hypothetical charging infrastructures in a city, each with generators connected to the national grid and strategically placed AC and DC chargers. The proposed method employs GPS data, EV battery levels, and energy availability across the charging infrastructures. Using an optimization algorithm implemented via the Pandapower Python library, the most appropriate charging infrastructure is identified for individual drivers. The algorithm considers factors such as GPS data and energy availability to suggest the optimal charging station for each EV’s battery level. This pioneering solution aims to streamline the charging process, enhance user experience, and encourage efficient use of urban charging infrastructure for electric vehicles.

关键词： Electric Vehicle (EV) Charging Infrastructure Urban Environments AC Chargers DC Chargers GPS Data Battery Levels optimization algorithm Pandapower Python Library Sustainable Transportation User Experience

来源：评论

学校读者我要写书评

暂无评论

Toroidal Inductor Design in Multilevel DC-DC Electric Vehicle Battery Charger Including High-Frequency Effects 23

Toroidal Inductor Design in Multilevel DC-DC Electric Vehicl...

引用

IEEE 23rd Workshop on Control and Modeling for Power Electronics (COMPEL)

作者： Elizondo, David Barrios, Ernesto L. Sanchis, Pablo Publ Univ Navarre UPNA Inst Smart Cities ISC Dept Elect Elect & Commun Engn Campus Arrosadia Pamplona 31006 Spain

ISBN: (纸本)9781665410816

Inductor filters, such as the ones implemented in DC-DC buck-boost converters for electric vehicle chargers, have a major impact on the converter weight, volume and cost. Thus, their design is key in order to obtain an optimal design of the whole converter. This paper proposes a design methodology for powder core toroidal inductors, which is based on a holistic approach of the design of the inductor, where losses due to high-frequency effects are computed by means of specific loss model for toroidal windings, and saturation, geometrical and thermal constraints are considered. The convenience of the design tool is shown through an analysis over a wide variation of parameters, including converter topology, parallelization, switching frequency and inductance. The analysis demonstrates the relevance of high-frequency effects on the inductor design, so certain misconceptions can be avoided, such as that the inductor volume monotonically decreases when the inductance value is decreased or that paralleling inductors always results in more compact designs. A design example is presented for a 15-kW, three-level electric vehicle battery charger. The algorithm is used to obtain an optimal design of the converter, including the inductors and SiC MOSFET devices. Finally, an easy method to obtain a commercial inductor design from the theoretical one provided by the algorithm is presented.

关键词： toroidal inductor high-frequency effects winding loss optimization algorithm multilevel dc-dc converter electric vehicle

来源：评论

学校读者我要写书评

暂无评论

Theoretical and experimental analyses and optimizations of direct coupling photovoltaic-thermoelectric systems

引用

ENERGY 2024年 307卷

作者： Xiong, Bowen Zhang, Jiayao Liao, Tianjun Zhao, Ye He, Zhihui Yang, Zhimin Yanan Univ Sch Phys & Elect Informat Yanan 716000 Peoples R China Chongqing Univ Technol Dept Phys & Energy Chongqing 400054 Peoples R China

A photovoltaic-thermoelectric (PV-TE) system is modeled theoretically and demonstrated experimentally. Mathematical formulations of the system are proposed according to energy conservation and finite-time thermodynamics, which can be applicable to analyze and optimize the system that consists of commercial photovoltaic (PV) cells and thermoelectric generators (TEGs). The genetic algorithm is introduced to maximize the system's power by optimizing multiple parameters. In Yan'an City, which is located in the northern Shaanxi Province in northwest China, the actual solar irradiance is recorded for almost a full year and the proposed model is verified. Theoretical and experimental results are analyzed and compared. It is found that there are several independent structure parameters in the PV-TE systems and they should be optimized simultaneously to maximize the performance. The PV-TE system's maximum theoretical average power of 0.343 W is 2.69 % greater than the solo PV cell's maximum theoretical power of 0.334 W. The measured average power of the system of 0.317 W is 0.32 % more than that of a solo PV cell of 0.316 W. The duration of strong lighting in Yan'an City reaches 8 h every day for nearly one year and the irradiation intensity can approach 1000 W/m2. The solar radiance is weakly affected by the seasonal changes of four seasons but is greatly affected by rainy days and cloud thickness. The research findings can serve as a helpful guide for the specific implementation of the PV-TE system and exploitation of solar energy resources in northwest China.

关键词： Photovoltaic-thermoelectric system Theoretical analysis Experimental validation Northwest China optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

An intelligent controller of homo-structured chaotic systems under noisy conditions and applications in image encryption

引用

CHAOS SOLITONS & FRACTALS 2024年 180卷

作者： Guo, Pengteng Shi, Qiqing Jian, Zeng Zhang, Jing Ding, Qun Yan, Wenhao Heilongjiang Univ Elect Engn Coll Harbin 150080 Peoples R China

Due to the maturation of research on chaos and secure communication, the control technology of nonlinear systems, specifically chaos synchronization, has captured the attention of numerous researchers. Focusing on the issues of inflexibility in the design of chaotic synchronization controllers, the need for prior synchronization of the target system structure, and noise's disruptive impact on synchronization, this paper presents solutions that enhance the practical application of chaos. Firstly, the RBF neural controller is adjusted in this paper to bolster the control precision of the chaotic system and enhance its resilience to external disturbances. Secondly, this article presents an enhanced PSO optimization algorithm for the improved RBF neural controller to improve the optimization efficiency of the controller parameters. Finally, the simulation results of the Lorenz system validate the feasibility of the proposed synchronization control scheme. Additionally, the use of chaotic synchronization in image encryption demonstrates that synchronization accuracy can fulfill the requirements of image encryption application scenarios.

关键词： Neural controller RBF optimization algorithm External disturbance Continuous chaotic system Chaotic synchronization

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：