检索结果-内蒙古大学图书馆

Lung cancer detection and classification using optimized CNN features and Squeeze-Inception-ResNeXt model

COMPUTATIONAL BIOLOGY AND CHEMISTRY 2025年 117卷 108437页

作者： Lakshmi, G. Geethu Nagaraj, P. Kalasalingam Acad Res & Educ Dept Comp Sci & Engn Srivilliputhur Tamil Nadu India

Lung cancer, with its high mortality rate, is one of the deadliest diseases globally. The alarming increase in lung cancer deaths and its widespread prevalence have led to the development of various cancer control research and early detection methods aimed at reducing mortality rates. Effective diagnostic techniques are crucial for lowering lung cancer incidence, as early detection significantly impacts treatment success. Human error can often impede accurate identification of lung nodules, in which Computer-Aided Diagnostic (CAD) systems are utilized. These systems help radiologists by automating diagnostic processes and improving accuracy of detecting and classifying malignancies. This paper aims to develop a deep learning approach for classifying lung diseases using chest Computed Tomography (CT) scan images. The approach starts with image pre-processing, including color space conversion, data augmentation, resizing, and normalization. Feature extraction is carried out using a Convolutional Neural Network (CNN) optimized with Slime Mould algorithm (SMA). For classification, a novel approach combining Squeeze-Inception V3 with ResNeXt, referred to as Squeeze-Inception-ResNeXt, is proposed. The Squeeze-Inception-ResNeXt model benefits from reduced computational cost while maintaining high performance in classifying lung diseases. This model categorizes lung diseases into Adenocarcinoma, Large Cell Carcinoma, and Squamous Cell Carcinoma. Additionally, SMA is utilized in training the Squeeze-InceptionResNeXt model. Experimental results show that Squeeze-Inception-ResNeXt surpasses traditional models, with an accuracy of 97.7 %, sensitivity of 98.1 %, and specificity of 97.4 %.

关键词： CT-scan Deep learning Lung cancer Feature extraction optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Compressive strength prediction of sleeve grouting materials in prefabricated structures using hybrid optimized XGBoost models

引用

CONSTRUCTION AND BUILDING MATERIALS 2025年 476卷

作者： Wu, Yanqi Cai, Daqing Gu, Sheng Jiang, Nan Li, Shengli Zhengzhou Univ Sch Civil Engn Zhengzhou 450001 Peoples R China Kunshan Construct Engn Qual Testing Ctr Kunshan 215337 Peoples R China Zhengzhou Univ Sch Ecol & Environm Zhengzhou 450001 Peoples R China

The compressive strength of the grouting material inside the grouting sleeve is a key parameter in ensuring the safety and durability of the grouting sleeve connections in prefabricated assembled structures. To accurately estimate the compressive strength of the grouting material inside the grouting sleeve, this paper proposes a hybrid eXtreme Gradient Boosting (XGBoost) model based on optimization algorithms for hyper-parameter selection, using the surface hardness and age of the specimens as inputs. The XGBoost model optimized with three optimization algorithms accurately outputs the compressive strength of the grouting material on 213 sets of actual measured data samples. The results show that compared with the whale optimization algorithm (WOA) and sparrow search algorithm (SSA), the XGBoost model optimized by Bayesian optimization (BO) has higher prediction accuracy and smaller prediction errors, and is recommended as the preferred model for predicting the compressive strength of grouting material inside the sleeve. Additionally, the importance and influence of the two input variables on the output target were analyzed.

关键词： Prefabricated structures Sleeve grouting material Compressive strength Machine learning optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Solving Multi-Objective Optimal Control Problems Using a Multiresolution Approach

引用

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS 2025年第1期48卷 32-45页

作者： Parsonage, Ben Maddock, Christie Univ Strathclyde Dept Mech & Aerosp Engn Glasgow Scotland

This paper presents an adaptive multiresolution strategy for multi-objective optimal control problems. The optimal control problem is solved using a direct approach, with individualistic grid adaptation facilitated by a local error analysis at element boundaries. Multiple objectives are considered using a dominance-based approach applying both local and global search methods to a collaborative population of unique solutions. These aspects are simultaneously incorporated via a novel application of evolutionary algorithms for adaptive optimal control problems. Together, this avoids the need for a priori specification of the quantity and temporal location of element boundaries and the set of scalarization weights defining the multi-objective descent directions. Solution fidelity can thus increase concurrently with the exploration of the design space, which leads to increased numerical efficiency while propagating and maintaining population diversity. The benefits of the proposed approach over traditional uniform-grid implementations are demonstrated. Results show that the multiresolution approach is capable of striking an effective balance between solution fidelity, population diversity, and computational cost unachievable using uniform grids.

关键词： Evolutionary algorithm Adaptive Mesh Refinement Multidisciplinary Design and optimization optimization algorithm Genetic algorithm Multi-Objective Evolutionary algorithms Optimal Control Problem

来源：评论

学校读者我要写书评

暂无评论

Swarm Intelligent Search and Rescue method for economic emission load dispatch of renewable integrated power system considering uncertainty

引用

SWARM AND EVOLUTIONARY COMPUTATION 2025年 95卷

作者： Mishra, Shilpa Shaik, Abdul Gafoor Mahela, Om Prakash IIT Jodhpur Dept Elect Engn Jheepasani India IIT Jodhpur Ctr Emerging Technol Sustainable Dev Ctr IoT & Applicat Dept Elect Engn Jheepasani India RVPN Power Syst Planning Div Jaipur India

In the realm of power systems, Economic Emission Load Dispatch (EELD) problem is one of the most important bi-objective optimisation problem, associated with high complexity and non-linearities. This research proposes a novel metaheuristic optimization approach hybridizing the PSO and SAR and abbreviated as Swarm Intelligent Search and Rescue method (SISAR). It utilizes the features of Particle Swarm optimization algorithm to strengthen the global searching capability of original SAR algorithm. SISAR overcomes the drawback of SAR of getting trapped into local minima by utilizing velocity-based position update concept of PSO to improve the overall convergence. SISAR approach is initially evaluated on 10-unit, 2000 MW and 6-unit, IEEE30 bus standard test systems. Results are compared with advanced algorithms such as SAR, PSO, GWO, WOA, GA, DE and MFO in order to prove its superiority. Subsequent to the establishment of the proposed algorithm on system without renewable sources, it is further applied to a RE integrated power system comprising of six thermal units, 1 wind and 1 solar unit. Here, uncertainty due to RESs is dealt using a 2-stage uncertainty handling approach to obtain more accurate and feasible EELD solution. Robustness of the uncertainty handling approach is established by investigating the impact of different penetration levels of RE sources on cost and emission while solving EELD. A reduction of 1.67 % in cost and 2.56 % in emission have been achieved by proposed SISAR algorithm as compared to SAR (next competitive method) while performing EELD on RE integrated system with all sources.

关键词： Swarm intelligent search and rescue Economic emission load dispatch optimization algorithm Renewable energy sources Uncertainty Wind Solar

来源：评论

学校读者我要写书评

暂无评论

Optimal Placement and Sizing of DER's with Load Models using a Modified Teaching Learning based optimization algorithm

Optimal Placement and Sizing of DER's with Load Models using...

引用

International Conference on Green Computing Communication and Electrical Engineering (ICGCCEE)

作者： Yammani, Chandrasekhar Sowjanya, G. Maheswarapu, Sydulu Matam, Sailaja Kumari

ISBN: (纸本)9781479949816

In this paper, a method which employs Modified Teaching-Learning Based optimization (MTLBO) algorithm is proposed to determine the optimal placement and size of Distributed Energy Resources (DERs) units in distribution systems. DERs are commonly connected near the load in electric power distribution systems and include renewable energy sources such as wind and solar, fossil-fuel-based generation such as micro turbines, and other distributed energy storage elements. Loss minimization and voltage profile improvement as objective function and for every combination of DERs, impact indices, active and reactive losses and voltage profiles is studied on different load models. For all cases current injection distribution load flow method is used and tested on 84-bus Taiwan Power Company distribution system using MTLBO algorithm.

关键词： Distributed Energy Resource (DER) Load models Loss minimization optimization algorithm MTLBO algorithm

来源：评论

学校读者我要写书评

暂无评论

A Novel optimization algorithm: The Forest algorithm 5

A Novel Optimization Algorithm: The Forest Algorithm

引用

5th International Conference on Intelligent Systems Design and Engineering Applications (ISDEA)

作者： Wu, Qi Chengdu Med Coll Chengdu 610500 Sichuan Peoples R China

ISBN: (纸本)9781479942626

A new optimization algorithm, namely the Forest algorithm (FA), is introduced for the first time. This algorithm simulates trees' growth, reproduction and death in a forest to perform optimization. In the algorithm, trees and branches represent a collection of trial solutions and parameters needed to be optimized respectively, and three mechanisms, i.e. growth, proliferation and death, are employed for improving trees' vitality, which is a factor defined to evaluate the fitness of trial solutions. This algorithm in general execute a global optimization by operating on a group of trial solutions in parallel, but its growth mechanism, which adopts a parameter sweeping method, is a local optimization, so it combines the ability to find global optima of the global optimization and the fast convergence of the local optimization. Several numerical experiments are conducted, in which the performance of the FA in terms of the global optimization capability, accuracy and efficiency is evaluated and compared to that of some widely-used global optimization algorithms such as the Genetic algorithm (GA) and the Particle Swarm optimization (PSO). Results shown the FA is able to perform global optimization effectively and with high accuracy.

关键词： optimization algorithm Forest algorithm global optimization

来源：评论

学校读者我要写书评

暂无评论

PCNN Document Segmentation Method Based on Bacterial Foraging optimization algorithm

PCNN Document Segmentation Method Based on Bacterial Foragin...

引用

6th International Conference on Digital Image Processing (ICDIP)

作者： Liao, Yanping Zhang, Peng Guo, Qiang Wan, Jian Harbin Engn Univ Sch Informat & Commun Engn Harbin Peoples R China

ISBN: (纸本)9781628411867

Pulse Coupled Neural Network(PCNN) is widely used in the field of image processing, but it is a difficult task to define the relative parameters properly in the research of the applications of PCNN. So far the determination of parameters of its model needs a lot of experiments. To deal with the above problem, a document segmentation based on the improved PCNN is proposed. It uses the maximum entropy function as the fitness function of bacterial foraging optimization algorithm, adopts bacterial foraging optimization algorithm to search the optimal parameters, and eliminates the trouble of manually set the experiment parameters. Experimental results show that the proposed algorithm can effectively complete document segmentation. And result of the segmentation is better than the contrast algorithms.

关键词： bacterial foraging optimization algorithm PCNN image segmentation

来源：评论

学校读者我要写书评

暂无评论

Efficient Multi-User Resource Allocation for Urban Vehicular Edge Computing: A Hybrid Architecture Matching Approach

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2025年第1期74卷 1811-1816页

作者： Xie, Hongyang Liu, Haoqiang Chen, Huiming Feng, Shaohan Wei, Zhaobin Zeng, Yonghong Southeast Univ Sch Artificial Intelligence Nanjing 211102 Peoples R China Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China Univ Sci & Technol Beijing Sch Intelligence Sci & Technol Beijing 100083 Peoples R China Zhejiang Gongshang Univ Sch Informat & Elect Engn Hangzhou 314423 Peoples R China Sichuan Univ Coll Elect Engn Chengdu 610017 Peoples R China Agcy Sci Technol & Res Inst Infocomm Res Singapore 138632 Singapore

Advanced in the proliferation of the Internet of Things (IoT), a plethora of functions have been integrated in vehicular networks and thereby transfered it into a smart network. However, the contradiction between the limited on-vehicle computing resource and the massive data collected by these IoT devices hinders the broader adoption of vehicular network as a vast variety of on-vehicle applications are latency-sensitive. To address this issue, vehicular edge computing has become a promising technology as it can offload a large number of tasks from its proximal vehicles. However, the offloading methods recently utilized are inefficient while dealing with multi-user vehicular networks under dynamic scenarios. To design a superior offloading method that can effectively and efficiently offload tasks from vehicles to servers, multiple objectives and constraints with various topologies should be considered. In this paper, instead of constructing a typical multi-user and multi-server vehicular edge computing scenario, a complex scenario with more uncertainties, i.e. urban scenario, is modeled. We propose a Hybrid Architecture Matching algorithm (HAMA) to minimize the average time latency subject to the constraint on energy consumption and evaluate the proposed algorithm in the above two scenarios. Moreover, HAMA is constructed based on hybrid centralized-distributed architecture, which can process the centralized collected information on a distributed manner. Experimental results demonstrate that the matching algorithm can significantly reduce average time latency, achieving up to a 68% improvement compared to local execution.

关键词： Servers Delays Computational modeling Vehicle dynamics Urban areas Roads Handover Vehicular edge computing matching algorithm resource allocation optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Well blowout Flame's thermal radiation prediction under environmental wind based on multi-point heat sources and inverse analysis

GEOENERGY SCIENCE AND ENGINEERING

引用

GEOENERGY SCIENCE AND ENGINEERING 2024年 234卷

作者： Peng, Yudan Fu, Guangming Sun, Baojiang Sun, Xiaohui Wang, Jinbo Chen, Jiying China Univ Petr East China Key Lab Unconvent Oil & Gas Dev Minist Educ Qingdao 266580 Peoples R China China Univ Petr East China Dept Petr Engn Qingdao 266580 Peoples R China Dongying Ruifeng Petr Technol Dev Co Ltd Dongying Peoples R China Univ Cambridge Dept Chem Engn & Biotechnol Cambridge CB30AS England

This study addresses the inadequacy of traditional multi-point source thermal radiation models in predicting the thermal radiation of gas well blowout fires under windy conditions. Initially, a Computational Fluid Dynamics (CFD) approach for predicting thermal radiation from well blowout jet flames was developed and validated against existing literature. Subsequently, the impact of wind on the thermal radiation of well blowout flames was thoroughly analyzed based on CFD model. Next, a novel predictive model for the center trajectory of well blowout flames under wind conditions was introduced based on CFD numerical simulation results and nonreactive jet trajectory theory. Building upon this, a novel prediction method of well blowout flame's thermal radiation under wind condition was proposed based on weighted multi-point sources model. Finally, the weights within proposed model were refined using an inverse optimization technique, specifically the Conjugate Gradient Global optimization algorithm, while also establishing a correlation between the optimal weight and the operating condition parameters of well blowout fires. Results indicated that the average difference between the thermal radiation values computed by the proposed method and those derived from numerical simulations was less than 10%. And the proposed model demonstrates clear superiority, particularly in terms of accuracy and convenience compared with traditional multi-point source model and single point source model. This research offers a practical and effective method for predicting thermal radiation from well blowout flames under wind conditions, which was of great significance for well blowout fire's disposal and rescue.

关键词： Weighted multi -point source Wind environment Heat radiation Blowout fire Jet trajectory optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

An adaptive fractional order optimizer based optimal tilted controller design for artificial ventilator

引用

OPTIMAL CONTROL APPLICATIONS & METHODS 2024年第6期45卷 2651-2668页

作者： Acharya, Debasis Das, Dushmanta Kumar Brainware Univ Dept Comp Sci & Engn Kolkata W Bengal India Natl Inst Technol Nagaland Dept Elect & Elect Engn Dimapur 797103 India

Artificial ventilators are vital respiratory support systems in the field of medical care, especially for patients in critical condition. It is crucial to make sure the ventilator keeps the intended airway pressure because variations might be harmful to the brain and lungs. Thus, achieving accurate pressure tracking is a primary objective in designing optimal controllers for pressure-controlled ventilators (PCVs). To address this need, a novel approach is proposed: a mixed integer tilted fractional order integral and integer order derivation controller (FOT1nI lambda-D)$$ \left({\mathrm{FOT}}<^>{\frac{1}{n}}{I}<^>{\lambda }-D\right) $$ tailored for PCV systems. The gains of different parameters of the proposed controller are optimized using an adaptive chaotic search fractional order class topper optimization algorithm, augmented with a Gaussian-based mutation operator. Moreover, the controller is designed to minimize oscillations in its output signal, thereby mitigating physical risks and reducing the size of actuators required. The efficacy of the optimized controller is further examined across various scenarios, including different lung resistances and compliances across different age groups of patients. Additionally, the impact of endotracheal tube resistance on air pressure is assessed as a potential disturbance in the PCV system. Through comprehensive testing, the proposed controller demonstrates superior performance in accurately tracking airway pressure to the desired levels. Across all evaluated cases, the proposed controller structure and accompanying algorithm outperform existing solutions. Notably, improvements are observed in system response time, overshoot, and settling time. This underscores the significance of employing advanced control strategies to enhancing the functionality and safety of PCV systems in medical settings. A metaheuristic algorithm is developed with a fractional order velocity enhancement concept to design a tilted pressure controll

关键词： artificial ventilation system (AVS) fractional order controller structure optimization algorithm positive end-expiratory pressure (PEEP) pressure control ventilator (PCV)

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：