检索结果-内蒙古大学图书馆

A review on optimization techniques for medical image analysis

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2023年第1期35卷 e7443-e7443页

作者： Kaur, Palwinder Singh, Rajesh Kumar IKG Punjab Tech Univ Dept Comp Sci Jalandhar Punjab India SUS Grp Coll Dept Comp Applicat Mohali India

Data mining of medical imaging approaches makes it difficult to determine their value in the disease's insight, analysis, and diagnosis. Image classification presents a significant difficulty in image analysis and plays a vital part in computer-aided diagnosis. This task concerned the use of optimization techniques for the utilization of image processing, pattern recognition, and classification techniques, as well as the validation of image classification results in medical expert reports. The primary intention of this study is to analyze the performance of optimization techniques explored in the area of medical image analysis. For this motive, the optimization techniques employed in existing literature from 2012 to 2021 are reviewed in this study. The contribution of optimization-based medical image classification and segmentation utilized image modalities, data sets, and tradeoffs for each technique are also discussed in this review study. Finally, this review study provides the gap analysis of optimization techniques used in medical image analysis with the possible future research direction.

关键词： brain disease diagnosis breast disease diagnosis heart disease diagnosis lung disease diagnosis medical image analysis optimization algorithm retinal disease diagnosis segmentation techniques

来源：评论

学校读者我要写书评

暂无评论

High-dimensional uncertainty quantification using graph-accelerated non-intrusive polynomial chaos and active subspace methods

High-dimensional uncertainty quantification using graph-acce...

引用

AIAA Aviation Forum

作者： Wang, Bingran Orndorff, Nicholas C. Sperry, Mark Hwang, John T. Univ Calif San Diego Dept Mech & Aerosp Engn La Jolla CA 92093 USA

ISBN: (数字)9781624107047

ISBN: (纸本)9781624107047

Integration-based non-intrusive polynomial chaos (NIPC) is a widely used method for solving low-dimensional uncertainty quantification (UQ) problems that often forms the quadrature points in a tensor structure. A recently developed graph transformation method, Accelerated Model evaluations on Tensor grids using Computational graph transformations (AMTC) can significantly accelerate model evaluations on tensor-structured inputs when the computational graph is sparse. Integration-based NIPC with AMTC has proven effective for low-dimensional UQ problems, but it is limited by the curse of dimensionality in high-dimensional cases. To address this, we propose a new framework, AS-NIPC-AMTC, that connects this approach with the active subspace (AS) method, a popular dimension reduction technique. In the process of developing this new method, we have also developed a general framework, AS-NIPC that connects the integration-based NIPC with the AS method to solve high-dimensional UQ problems. This framework includes rigorous approaches to generate the orthogonal polynomial basis functions of the lower dimensional active subspace inputs and efficient quadrature rules to estimate their coefficients. The AS-NIPC-AMTC method extends the AS-NIPC method and generates the quadrature rule following a desired tensor structure so that the model evaluations can be significantly accelerated when AMTC is available. We demonstrate the effectiveness of both AS-NIPC and AS-NIPC-AMTC methods on an 81-dimensional UQ problem computing the average ground-level sound pressure of an electric air taxi flying a prescribed trajectory. Both methods outperform existing UQ methods when the number of function evaluations is limited to hundreds or fewer. The AS-NIPC-AMTC method results in at least 80% less error with a fixed function evaluation cost, while AS-NIPC results in 30% less error. The proposed methods provide a novel and rigorous way to combine the traditional NIPC method with the recently develo

关键词： Uncertainty Quantification Air Taxi Computing Monte Carlo Method Sparse Nonlinear Optimizer Sound Pressure Level Gaussian Process Regression optimization algorithm Flight Trajectory Cholesky Factorization

来源：评论

学校读者我要写书评

暂无评论

Secrecy rate enhancement in MIMO Networks in the presence of MIMO-capable eavesdropper using a hybrid optimization approach

引用

PHYSICAL COMMUNICATION 2025年 71卷

作者： Rahman, Md. Samiur Kawser, Mohammad Tawhid Rimi, Maisha Mahbub Islamic Univ Technol Gazipur 1704 Bangladesh

In this paper, the problem of secrecy rate optimization in Multiple-Input-Multiple-Output (MIMO) wiretap systems has been investigated under a scenario where even the passive eavesdropper has MIMO capability. To solve the optimization problem, an advanced hybrid meta-heuristic algorithm named Hybrid PSOCSA is proposed, that incorporates the combination of two adaptive swarm intelligence meta-heuristics;Particle Swarm optimization (PSO) with global search proficiency and Chameleon Swarm algorithm (CSA) which includes the adaptive exploration-exploitation mechanism. The Proposed algorithm maintains a population of particles that exploit the best-known solution while also escaping from local optima which in turn helps to speed up the convergence for a global optimum solution. Simulation results show how the Hybrid PSOCSA consistently achieves superior performance compared to other standalone state-of-the-art algorithms for a variety of MIMO configurations - traditional (4 x 4 and 8 x 8) and Massive MIMO (16 x 16, 32 x 32, 64 x 64), as well as a realistic 5G setting with 128 x 128 antennas and a range of eavesdropper antenna arrays up to 64, providing maximized secrecy rates with reduced computational complexity and smaller standard deviations indicating faster convergence and robustness. Moreover, the developed system model is designed with several practical factors, such as;antenna correlation, Doppler effect, interference power from neighboring cells, and imperfect Channel State Information (CSI), which represent the security challenges in real-world secure communications. The numerical results exhibit the generality of the Hybrid PSOCSA to secure and enhance the diversity and robustness of next-generation wireless systems in terms of security and overhead efficiency.

关键词： MIMO Secrecy rate Physical layer security Metaheuristic optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Multiscale Quantum Harmonic Oscillator algorithm With Strict Metastability Constraints for Multi-Modal optimization

引用

IEEE ACCESS 2019年 7卷 17377-17388页

作者： Li, Bo Wang, Peng Jin, Jin Chinese Acad Sci Inst Comp Applicat Chengdu 610041 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Tangshan Univ Dept Comp Sci & Technol Tangshan 063000 Peoples R China Southwest Minzu Univ Coll Comp Sci & Technol Chengdu 610225 Sichuan Peoples R China

Multi-modal optimization is a troublesome problem faced by optimization algorithms. The multiscale quantum harmonic oscillator algorithm (MQHOA) utilizes group statistics strategy to evaluate the state of the population and neglects the individual state. It will lead the particles to be trapped in local optima when addressing multi-modal optimization problems. This paper proposes a modified MQHOA by introducing strict metastability constraints strategy (MQHOA-SMC). The new strategy adopts a joint constraint mechanism to make the particle states mutual constraint with each other. The modified algorithm enhances the ability to find a better quality solution in local areas. To demonstrate the efficiency and effectiveness of the proposed algorithm, simulations are carried out with SPSO2011, ABC, and QPSO on classical benchmark functions and with the newly CEC2013 test suite, respectively. The computational results demonstrate that MQHOA-SMC is a competitive algorithm for multi-modal problems.

关键词： Multiscale quantum harmonic oscillator algorithm metastability multi-modal optimization optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A Jaya algorithm based wrapper method for optimal feature selection in supervised classification

引用

JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES 2022年第6期34卷 3851-3863页

作者： Das, Himansu Naik, Bighnaraj Behera, H. S. Veer Surendra Sai Univ Technol Dept Informat Technol Sambalpur 768018 Odisha India Veer Surendra Sai Univ Technol Dept Comp Applicat Sambalpur 768018 Odisha India

In recent years, Jaya optimization algorithm has been successfully applied in several optimization problems. This paper presents a novel feature selection (FS) approach based on Jaya optimization algorithm (FSJaya) along with supervised machine learning techniques to select the optimal features. This approach uses a search technique to find the best suitable features by updating the worst features to reduce the dimensions of the feature space. This improves the performance of supervised machine learning techniques. The effectiveness of the proposed approach is evaluated for ten benchmark datasets and compared with several FS approaches such as FS using genetic algorithm (FSGA), FS using particle swarm optimization algorithm (FSPSO), and FS using differential evolutionary (FSDE). The experimental result has shown that the average classification accuracy of FSJaya on most of the datasets is superior over the existing methods such as FSGA, FSPSO, and FSDE. The proof of statistical significance of the proposed approach has been validated by using Friedman and Holm test. This proposed approach is found efficient in selecting an optimal subset of features as compared to other counterparts. (C) 2020 The Authors. Published by Elsevier B.V. on behalf of King Saud University.

关键词： Feature selection Supervised classification Jaya optimization algorithm Wrapper method

来源：评论

学校读者我要写书评

暂无评论

Rolling Bearing Fault Diagnosis Based on Parameter-Optimized ICEEMDAN and IPOA-SVM 6

Rolling Bearing Fault Diagnosis Based on Parameter-Optimized...

引用

6th IEEE International Conference on Automation, Electronics and Electrical Engineering, AUTEEE 2023

作者： He, Fei Shen, Xiangyun Liaoning Technical University College of Electrical and Control Engineering Huludao China

ISBN: (纸本)9798350305623

Aiming at the problem of low accuracy of traditional rolling bearing fault diagnosis, a fault diagnosis model of parameter optimization Improved Adaptive Noise Complete Ensemble Empirical Mode Decomposition (ICEEMDAN) and Improved Pelican optimization algorithm (IPOA) optimized Support Vector Machine (SVM) was proposed. We employ the optimized ICEEMDAN method, along with Multiscale Fuzzy Entropy (MFE) and Linear Discriminant Analysis (LDA) for modal decomposition and feature extraction of the original bearing vibration signals. To enhance the accuracy and convergence speed of the algorithm, we introduce Tent chaotic mapping, Levy flights, and differential variation perturbation factors into the basic Pelican optimization algorithm. Furthermore, the improved Pelican optimization algorithm is utilized to optimize the penalty parameter (c) and kernel function (g) of SVM, thus enhancing the fault diagnosis accuracy of the SVM algorithm. Experimental results on a public dataset demonstrate that the proposed method achieves an overall recognition rate of 99% for fault diagnosis of rolling bearings under 10 operating conditions. © 2023 IEEE.

关键词： Fault diagnosis Feature extraction Machine learning optimization algorithm Rolling bearing

来源：评论

学校读者我要写书评

暂无评论

A new experimental and theoretical approach for viscosity Iranian heavy crude oils based on tuning friction theory and friction volume theory parameters

引用

INORGANIC CHEMISTRY COMMUNICATIONS 2022年 139卷 109319-109319页

作者： Farajpour, Ehsan Ghotbi, Cysus Behbahani, Taraneh Jafari Sharif Univ Technol Dept Chem Engn Tehran Iran Res Inst Petr Ind Tehran *** Iran

In this research work, Friction Theory and Free Volume Theory are applied to live oil characterized based on SARA TEST for viscosity modeling and make a new model in combination with two equation of state (PR and PCSAFT). Parameters for pseudo-components are obtained by tuning the viscosity at atmospheric pressure and temperatures of 10, 20, and 40 ?. A new fitting approach is suggested where the number of fitting parameters is 17 and 12 for FT and FVT model, respectively. These parameters are tuned using the Genetic algorithm and Particle Swarm optimization and make eight new models. The results show that PC-SAFT provides viscosity predictions for all models with less deviation from experimental viscosity. The FT and FVT models have less error for oils with API > 40 and API < 40, respectively. The PC-SAFT + PSO improves the accuracy in viscosity modeling for both FT and FVT models. PSO can play a significant role even more than PC-SAFT.

关键词： Crude oil characterization Friction Theory Free Volume Theory optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

An Optimized Binary Scheduling Controller for Microgrid Energy Management Considering Real Load Conditions

An Optimized Binary Scheduling Controller for Microgrid Ener...

引用

2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023

作者： Mannan, Musfika Roslan, M.F. Reza, M.S. Mansor, M. Jern, Ker Pin Hossain, M.J. Hannan, M.A. Universiti Tenaga Nasional Department of Electrical and Electronic Engineering Kajang43000 Malaysia University of Technology Sydney School of Electrical and Data Engineering UltimoNSW2007 Australia Sunway University School of Engineering and Technology Petaling Jaya Bandar Sunway47500 Malaysia Universiti Tenaga Nasional Institute of Sustainable Energy Kajang43000 Malaysia

ISBN: (纸本)9781665471640

A dynamical power demand and stochastic nature of energy resources posses difficulties in controlling and managing output power. These challenges lead to instability and inconsistency of the entire operation which can cause unstable and power quality issues. This study presents an optimal schedule controller for microgrid energy management, utilizing the Binary Particle Swarm algorithm (BPSO) to minimize costs and ensure optimal power delivery to loads. The controller's aims include minimizing total operating costs for distributed energy resources and solving intricate constraint optimization issues with scheduling management operations. The proposed approach's effectiveness is evaluated within an IEEE 14-bus configuration with five microgrids (MGs) integrated with RESs using real load data from Perlis, Malaysia. The BPSO optimization technique offers an exceptional binary fitness function to find the optimal cell, utilizing real data such as solar radiation, wind speed, battery charging/discharging, fuel conditions, and demand. To confirm the efficiency of the developed controller, a comparison is conducted between the results achieved with and without microgrid (MG) integration. The results reveal the robustness of the BPSO algorithm in reducing energy consumption and cost by 199.6 MW to 316.53 MW and RM 87,250.35 to RM 138,327.5 respectively. As a result, an optimized scheduling controller-based BPSO optimization outperforms in terms of savings cost, reduced energy consumption, optimal DER use, and decreased CO2 emissions. © 2023 IEEE.

关键词： Binary Particle Swarm optimization Distributed energy resources Energy management Microgrid optimization algorithm Scheduling controller

来源：评论

学校读者我要写书评

暂无评论

The Defending Mobile Ad Hoc Networks from Anonymity Threats with an Identity-less, OnDemand Routing Scheme 2

The Defending Mobile Ad Hoc Networks from Anonymity Threats ...

引用

2nd IEEE International Conference on Futuristic Technologies, INCOFT 2023

作者： Ahluwalia, Gunveen Chitkara University Institute of Engineering and Technology Chitkara University Centre for Interdisciplinary Research in Business and Technology Punjab India

ISBN: (纸本)9798350308846

We call a network that can be rapidly formed and rearranged on the fly a 'mobile ad hoc network' (MANET). Because of its decentralized administration and lack of stable infrastructure, this sort of network design is best suited for temporary connections. It is challenging to offer quality of service (QoS) and safety-aware routing in such a network because of its unstable architecture and limited resources. The basic objective of safe and trust-based immediately multiple routes transportation is to find a route from origin to target that fulfills at least two end-to-end QoS requirements. Using a variant of the widely used ad hoc ondemand multiple-pathway distance vector technique, this study assesses the idea. The researchers provide a mesh-based multipath navigation system for effective communication in MANET, complete with a secure nearby position trust validation mechanism and a superior link optimum route search using the Dolphin Echolocation algorithm. Our suggested routing protocol has been shown to improve packet delivery percentage, packet latency, overheads, and security against attacks and weaknesses in both analytical and numerical evaluations of its performance. © 2023 IEEE.

关键词： Mobile Ad Hoc Network optimization algorithm Quality of Service Secure & Trusted optimization Trust Verification

来源：评论

学校读者我要写书评

暂无评论

Meta-Importance Sampling Fuzzy Simulation Combined with Kriging Model for Fuzzy Reliability Analysis

引用

AIAA JOURNAL 2022年第8期60卷 5018-5022页

作者： Wang, Jiaqi Lu, Zhenzhou Northwestern Polytech Univ Sch Aeronaut Xian 710072 Peoples R China

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：