检索结果-内蒙古大学图书馆

A Modified U-Shaped Transfer Function: Applied to Classify Parkinson'S Disease

COMPUTATIONAL INTELLIGENCE 2025年第2期41卷

作者： Sharma, Suvita Rani Singh, Birmohan Kaur, Manpreet St Longowal Inst Engn & Technol Dept Comp Sci & Engn Sangrur Punjab India St Longowal Inst Engn & Technol Dept Elect & Instrumentat Engn Sangrur Punjab India

Transfer functions have a very important role in metaheuristic optimization-based feature selection algorithms as these functions map the continuous search space into binary space. The U-shaped transfer function (UTF) is one of the transfer functions used to solve the problem of feature selection. However, the UTF requires the selection of parametric values, which can vary for different types of data. To address this issue, an approach to select the parameters of the UTF has been proposed based on a time-varying adaption method, resulting in the modified U-shaped transfer function (MUTF). Furthermore, a methodology has been proposed to enhance feature selection and classification for Parkinson's disease by utilizing z-score normalization in conjunction with a modified U-shaped transfer function and the binary self-adaptive bald eagle search (MUTF-SABES) optimization algorithm. The z-score normalization has been used to mitigate issues caused by outliers. Also, the performance of the k nearest neighbor classifier is improved by selecting an optimal parameter value using the proposed MUTF-SABES algorithm. The effectiveness of the proposed methodology is validated on seven different Parkinson's disease datasets and compared with five state-of-the-art optimization algorithms: Salp Swarm algorithm, Harris Hawks optimization, equilibrium optimizer, aquilla optimizer, and Honey Badger algorithm, to evaluate its performance superiority. The results achieved using the proposed approach have been superior or analogous to the erstwhile algorithms for performance comparability. Friedman's mean rank test is used to check the statistical significance of the propounded approach. The lowest Friedman's mean rank value obtained using the proposed approach indicates that the proposed approach has the potential to become an alternative to other well-known strategies.

关键词： classification feature selection normalization optimization algorithm Parkinson's disease

来源：评论

学校读者我要写书评

暂无评论

Efficient Automatic Design of IGBT Structural Parameters Using Differential Evolution and Machine Learning Model

引用

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 2025年第3期44卷 1059-1069页

作者： Yao, Qing Chen, Jing Yang, Kemeng Yao, Jiafei Zhang, Jun Dai, Yuxuan Tang, Weihua Zhang, Bo Guo, Yufeng Nanjing Univ Posts & Telecommun Coll Integrated Circuit Sci & Engn Nanjing 210023 Peoples R China Nanjing Univ Posts & Telecommun Natl & Local Joint Engn Lab RF Integrat & Micropac Nanjing 210023 Peoples R China Univ Elect Sci & Technol China State Key Lab Elect Thin Films & Integrated Device Chengdu 610054 Peoples R China

Insulated gate bipolar transistors (IGBTs) are the key component in power electronics, and the intricate relationship between their performance and structural parameters poses a formidable challenge in the design process. This article proposes an automatic optimal design method for IGBT structural parameters to leverage the pretrained machine learning (ML) model to efficiently predict the initial IGBT device's performance, followed by utilizing the differential evolution (DE) algorithm to automatically adjust structural parameters based on the disparity between predicted and expected device performance until the expected performance is achieved. The method is validated in the design of punch-through IGBTs (PT-IGBTs) and trench gate field-stop IGBTs (FS-IGBTs), and the performance of technology computer-aided design (TCAD) simulation of the designed device is similar to the target performance. In particular, the simulation results of the designed FS-IGBT are highly fitted to the datasheet of the commercial device, which verifies the generalizability and effectiveness of the method. In addition, comparative analyses with various algorithms show DE provides the fastest optimization and extraordinary robustness under the exact specifications. Crucially, the proposed design scheme aligns with semiconductor physics. The method simplifies IGBT design without the need for manual tuning and TCAD tool simulation.

关键词： Insulated gate bipolar transistors Structural engineering Performance evaluation Predictive models optimization Training Prediction algorithms Artificial neural networks (ANNs) automatic optimization electrical performance insulated gate bipolar transistor (IGBT) optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Feature Selection Approach: β-Hill Climbing and Henry Gas optimization

A Hybrid Feature Selection Approach: β-Hill Climbing and He...

引用

International Conference on Machine Intelligence and Smart Innovation (ICMISI)

作者： ELgazzar, Shadia Mohamed, Hatem Haroun, Asmaa Menoufia Univ Fac Comp Sci & Informat Syst Dept Informat Syst Shibin Al Kawm Egypt

ISBN: (纸本)9798350365740;9798350365757

Improved Henry gas solubility optimization algorithm is a better way to use an existing method (HGSO) inspired by gas dissolving in liquids, to find optimal solutions. It leverages the influence of pressure and temperature on gas solubility to guide their search for optimal solutions in optimization problems. It aims to overcome the limitations of the original Henry gas solubility optimization algorithm and enhance its performance in solving various optimization problems. It can be used in many applications, such as feature extraction, task scheduling, joint mining, and parameter optimization. This paper proposes a new approach called the beta-Hill operator, which builds upon the traditional hill climbing method. to improve the balance between finding better solutions (exploitation) and exploring new possibilities (exploration).

关键词： HGSO optimization algorithm Feature Extraction Prediction

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Design and Trajectory optimization for Boosted Hypersonic Glide Vehicles

Simultaneous Design and Trajectory Optimization for Boosted ...

引用

AIAA SciTech Forum

作者： Cangelosi, Jonathan R. Heinkenschloss, Matthias Needels, Jacob T. Alonso, Juan J. Rice Univ Dept Computat Appl Math & Operat Res Houston TX 77005 USA Stanford Univ Dept Aeronaut & Astronaut Stanford CA 94305 USA

ISBN: (数字)9781624107115

ISBN: (纸本)9781624107115

This manuscript describes a methodology for simultaneous vehicle and trajectory optimization of a hypersonic glide vehicle. The co-design problem is formulated as an optimization problem with constraints including vehicle dynamics, path constraints (e.g., surface heating), and other constraints. The discretized optimization problem is solved simultaneously in the vehicle design parameters, the state variables, and the controls using an interior point method. Gaussian process (GP) surrogates, which are generated from sample candidate designs and flight conditions, are used to model vehicle aerodynamic performance and mass properties, as well as their first and second-order derivatives required by the optimizer. These GP surrogates and their derivatives are computationally inexpensive, making the all-at-once optimization approach for the co-design problem more tractable. To mitigate the effect of surrogate model errors on the solution of the optimal control problem, the GP models are refined using samples of the vehicle aerodynamic performance and mass properties at the solution of the co-design problem with the current surrogate. The resulting framework is applied to maximizing the range of a hypersonic glide vehicle with path and terminal constraints. Possible extensions of this methodology are also discussed, including the incorporation of more complex vehicle models such as multi-fidelity models, as well as adaptive surrogate modeling strategies to mitigate the effect of model errors on the solution of the optimal control problem.

关键词： Hypersonic Glide Vehicle Optimal Control Problem Aerodynamic Performance Reduced Order Modelling optimization algorithm Gaussian Process Aerodynamic Force Coefficients Dynamic Pressure Thermal Protection System Lift to Drag Ratio

来源：评论

学校读者我要写书评

暂无评论

Optimizing energy hubs with a focus on ice energy storage: a strategic approach for managing cooling, thermal, and electrical loads via an advanced slime mold algorithm

引用

INTERNATIONAL JOURNAL OF LOW-CARBON TECHNOLOGIES 2024年第19期19卷 2568-2579页

作者： Hai, Tao Shami, Hayder Oleiwi Saleh, Sami Abdulhak Agarwal, Diwakar Rajab, Husam Mahmood, Ahmed Mohammed Hussein, Abbas Hameed Abdul Hasan, Dheyaa Flayih Mushtaq, Hiba Singh, Narinderjit Singh Sawaran Nanchang Inst Sci & Technol Sch Informat & Artificial Intelligence Nanchang 330108 Peoples R China Qiannan Normal Univ Nationalities Sch Comp & Informat Duyun 558000 Guizhou Peoples R China INTI Int Univ Fac Data Sci & Informat Technol Nilai 71800 Malaysia Ajman Univ Artificial Intelligence Res Ctr AIRC POB 346 Ajman U Arab Emirates Al Amarah Univ Coll Dept Accounting Amarah Maysan Iraq Univ Misan Coll Adm & Econ Dept Econ Amarah Iraq Al Amarah Univ Coll Engn Tech Mech Power Dept Amarah Maysan Iraq GLA Univ Inst Engn & Technol Dept Elect & Commun Engn Mathura India Najran Univ Coll Engn Dept Mech Engn King Abdulaziz RdPOB 1988 Najran Saudi Arabia Alnoor Univ Hlth & Med Tech Coll Dept Opt Tech Mosul Iraq Ahl Al Bayt Univ Karbala Iraq Natl Univ Sci & Technol Coll Hlth & Med Technol Dhi Qar Iraq Gilgamesh Ahliya Univ Baghdad Iraq

Amidst the increasing incorporation of multicarrier energy systems in the industrial sector, this article presents a detailed stochastic methodology for the optimal operation and daily planning of an integrated energy system that includes renewable energy sources, adaptive cooling, heating, and electrical loads, along with ice storage capabilities. To address this problem, it applies the 2 m + 1 point estimation method to accurately assess system uncertainties while minimizing computational complexity. The "2 m + 1 point" technique swiftly evaluates unpredictability through Taylor series calculations, capturing deviations in green energy output, and the demand for both electric and thermal energy across power networks, while also considering the oscillating costs associated with senior energy transmission systems. In addition, this article proposes a novel self-adaptive optimization technique, called the enhanced self-adaptive mucilaginous fungus optimization algorithm (SMSMA), dedicated to overcoming the intricate nonlinear challenges inherent in the optimal daily operation of an energy system. The advanced self-adaptive strategy relies on wavelet theory to enhance the capability and effectiveness of the original mucilaginous fungus algorithm in optimizing daily schedules for an integrated energy system. Numerical analyses demonstrate that the introduced stochastic daily scheduling framework, coupled with the SMSMA optimization algorithm, effectively reduces the operating costs of the energy system.

关键词： multicarrier energy spheres stochastic framework renewable energy sources optimization algorithm operating cost

来源：评论

学校读者我要写书评

暂无评论

Cross-Entropy Method for Laser Defense Applications

引用

JOURNAL OF AEROSPACE INFORMATION SYSTEMS 2025年第1期22卷 53-58页

作者： Hanak, J. Novak, J. Ben-Asher, J. Z. Chudy, P. Brno Univ Technol Fac Informat Technol Brno 61200 Czech Republic Technion Israel Inst Technol Dept Aerospace Engn IL-32000 Haifa Israel Univ Wurzburg Inst Comp Sci D-97074 Wurzburg Germany

来源：评论

学校读者我要写书评

暂无评论

An Ultrasonic Synthetic Jet Piezo Pump for Air Delivery

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2025年第5期72卷 5177-5186页

作者： Wang, Meng Liu, Zenghao Wang, Conghui Liu, Guojun Jilin Univ Sch Mech & Aerosp Engn Changchun 130025 Peoples R China

A combination of piezoelectric drive and synthetic jet technology is proposed for an ultrasonic synthetic jet piezo pump. The piezo vibrator operates silently and has a resonant frequency exceeding 20 kHz. The inlet channel of the proposed piezo pump is equipped with a special Tesla structure to increase the flow resistance difference and reduce flow loss. The results demonstrate that the proposed piezo pump has a significant advantage over a typical pump in flow rate. The optimized piezo pump achieves a flow rate of 1037 mL/min when subjected to a typical square wave signal excitation. The optimized waveform enhances the flow rate to 1343.9 mL/min, resulting in a 29.6% improvement. Additionally, this article also investigates the ultrasonic synthetic jet piezo pump in the form of a dual cavity. The two cavities are positioned on either side of the piezo vibrator and alternate between suction and discharge. When the two cavities were connected in parallel, the flow rate was 1912.68 mL/min. Finally, the proposed piezo pump was explored for impact cooling applications. The impact cooling effect on the heated ceramic is good at an impact distance and angle of 30 mm and 60 degrees, respectively.

关键词： Acoustics Cooling Voltage Resonant frequency Vibrations Ceramics Surface acoustic waves Plasmas Heat pumps Genetic algorithms Impact cooling optimization algorithm piezo pump synthetic jet ultrasonic

来源：评论

学校读者我要写书评

暂无评论

A layered metastructure-based smart radiant regulator with enhanced emissivity modulation utilizing phase change material

引用

INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER 2025年 164卷

作者： Yao, Ting-Shuo Sui, Jun-Yang Du, Rui Zhang, Ting-Hao Zhang, Hai-Feng Nanjing Univ Posts & Telecommun Coll Elect & Opt Engn Nanjing 210023 Peoples R China Nanjing Univ Posts & Telecommun Coll Flexible Elect Future Technol Nanjing 210023 Peoples R China

Based on thermal radiation, radiative cooling is a widely used technology, and plays an important role in many scenarios such as passive building cooling and infrared camouflage. Currently, dynamic control of thermal radiation devices is endowed with great expectations. However, a more efficient systematic strategy for designing smart radiant temperature regulators (SRTRs) is still urgently needed. By leveraging the phase change properties of vanadium dioxide, the proposed SRTR achieves dynamic modulation of thermal emissivity, demonstrating an average total directional emissivity exceeding 0.9 when the temperature is above the threshold temperature, and dropping below 0.1 when the threshold temperature is not been reached, particularly within the atmospheric transparent window band. The optimization results achieved by using Autonomous Particles Groups for Particle Swarm optimization demonstrate better performance metrics compared to those obtained using conventional methods. Notably, the absorption mechanism of layered metastructure is further investigated, and its high angle dependency is effectively addressed. The demonstrates excellent angular stability and polarization insensitivity, with up to 73 degrees in transverse electric mode and 60 degrees in transverse magnetic one. Without taking non-radiative heat transfer into account, the cooling power achieves 214.59 W.m(-2). In this paper, a more systematic strategy for designing SRTRs is exhibited, which offers extensive potential in fields such as surface radiative cooling, infrared camouflage, and spacecraft thermal management.

关键词： Radiative cooling Layered metastructure Phase change material Smart radiant temperature regulation optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Task allocation algorithm and optimization model on edge collaboration

引用

JOURNAL OF SYSTEMS ARCHITECTURE 2020年 110卷 101778-101778页

作者： Deng, Xiaoheng Li, Jun Liu, Enlu Zhang, Honggang Cent South Univ Sch Comp Sci & Engn Changsha 410083 Peoples R China Univ Massachusetts Engn Dept Boston MA 02125 USA

This paper investigates a mobile edge computing environment for video analysis tasks where edge nodes provide their computation capacities to process the computation intensive tasks submitted by end users. First, we introduce a Cloudlet Assisted Cooperative Task Assignment (CACTA) system that organizes edge nodes that are geographically close to an end user into a cluster to collaboratively work on the user's tasks. It is challenging for the system to find an optimal strategy that assigns workload to edge nodes to meet the user's optimization goal. To address the challenge, this paper proposes multiple algorithms for different situations. Firstly, considering the situation that historical data cannot be obtained, a multi-round allocation algorithm based on EMA prediction is proposed, and the experimental results prove the efficiency and necessity of multiple rounds of transmission. To address the second case of obtaining historical data, this paper introduces a prediction-based dynamic task assignment algorithm that assigns workload to edge nodes in each time slot based on the prediction of their capacities/costs and an empirical optimal allocation strategy which is learned from an offline optimal solution from historical data. Experimental results demonstrate that our proposed algorithm achieves significantly higher performance than several other algorithms, and especially its performance is very close to that of an offline optimal solution. Finally, we propose an online task assignment algorithm based on Q-learning, which uses the model-free Q-learning algorithm to actively learn the allocation strategy of the system, and the experimental results verify the superiority and effectiveness of this algorithm.

关键词： Edge computing Task assignment Prediction Q-Learning optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Global Multiobjective Aerodynamic optimization of Wingtip Design for Micro Aerial Vehicle

Global Multiobjective Aerodynamic Optimization of Wingtip De...

引用

AIAA SciTech Forum

作者： Nimura, Naruhiko Oyama, Akira Univ Tokyo Dept Aeronaut & Astronaut 3-1-1 Yoshinodai Sagamihara Kanagawa 2525210 Japan JAXA Inst Space & Astronaut Sci Dept Space Flight Syst 3-1-1 Yoshinodai Sagamihara Kanagawa 2525210 Japan

ISBN: (数字)9781624107115

ISBN: (纸本)9781624107115

A global multiobjective design optimization method is introduced for optimizing three-dimensional geometries based on topology optimization. To validate the method's effectiveness in aerodynamic design optimization problems, design optimization of wingtip design for micro aerial vehicles is conducted The proposed method employs a technique for compressing three-dimensional images using octree encoding to reduce the number of design variables and increase optimization efficiency. The octree structure is optimized through genetic programming. It is confirmed that the proposed method can reproduce a variety of geometry. Compared to the baseline SD7003 rectangular wing, the obtained non-dominated solutions show improvements of up to about 50% in lift coefficient and a reduction of up to about 2% in drag coefficient. The geometry, aerodynamic performance, and surface pressure distribution of the obtained non-dominated solutions revealed that volume, surface area, and positions of cant-up and cant-down geometry play a significant role in designing the wingtip geometry.

关键词： Unmanned Aerial Vehicle Aerodynamic Design optimization Aerodynamic Performance Rectangular Wing Design optimization Topology optimization Wing Planforms Reynolds Averaged Navier Stokes Winglets optimization algorithm

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：