检索结果-内蒙古大学图书馆

Data-Driven Evolutionary Algorithms for Optimizing Pumping Stations in Water Distribution Networks: Classifier-Guided Search Space Reduction 27th

Data-Driven Evolutionary Algorithms for Optimizing Pumping S...

引用

27th Iberoamerican Congress on Progress in Pattern Recognition, Image Analysis, computer Vision, and Applications, CIARP 2024

作者： Faúndez-Lizama, Thalía Gajardo-Sepúlveda, Nicolás Gutiérrez-Bahamondes, Jimmy H. Mora-Melia, Daniel Astudillo, César A. Master’s in Operations Management Faculty of Engineering Universidad de Talca Curicó3340000 Chile Department of Computer Science Faculty of Engineering Universidad de Talca Curicó3340000 Chile Department of Engineering and Construction Management Faculty of Engineering Universidad de Talca Curicó3340000 Chile

ISBN: (纸本)9783031766060

In the context of increasing water scarcity and the need to enhance water distribution network efficiency, this study focuses on optimizing the design of pumping stations using data-driven evolutionary algorithms guided by classification models. These facilities are critical components in water networks due to their high energy consumption and role in maintaining necessary water pressure. The proposed approach integrates a machine learning classifier model within the evolutionary process to pre-label solutions as feasible or infeasible, thereby reducing search space and computational costs associated with hydraulic simulations. Classification models include support vector classifier, artificial neural networks, and random forest. These models are trained on data generated from initial evolutionary optimization, enabling the classifier to predict the viability of new solutions. Results show that all tested classification models reduced the number of objective function evaluations and consequently, required hydraulic simulations. In some cases, the optimal solution defined by the original method was improved, demonstrating dual benefits by reducing both cost and computational effort. This work highlights that data-driven evolutionary optimization can effectively tackle highly complex problems, offering potential future applications in other areas of civil engineering and water resource management. Implementing this methodology promises significant time and resource savings in large-scale optimization processes. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Hydraulic models

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Genetic Algorithm for the Optimization of Water Distribution Networks: A New Surrogate Model for Estimating Investment and Operational Costs in Pumping Stations 27th

Data-Driven Genetic Algorithm for the Optimization of Water ...

引用

27th Iberoamerican Congress on Progress in Pattern Recognition, Image Analysis, computer Vision, and Applications, CIARP 2024

作者： Gajardo-Sepúlveda, Nicolás Faúndez-Lizama, Thalía Gutiérrez-Bahamondes, Jimmy H. Mora-Melia, Daniel Astudillo, César A. Master’s in Operations Management Faculty of Engineering Universidad de Talca Curicó3340000 Chile Department of Computer Science Faculty of Engineering Universidad de Talca Curicó3340000 Chile Department of Engineering and Construction Management Faculty of Engineering Universidad de Talca Curicó3340000 Chile

ISBN: (纸本)9783031766039

The increase in water consumption and demand has highlighted the need to improve the efficiency of water distribution networks (WDNs). Pumping stations (PS) represent a significant challenge due to their high energy consumption and associated operational costs. This study presents a data-driven evolutionary optimization methodology focused on predicting cost and penalties in the design and operation of PS. The methodology integrates the functioning of genetic algorithms with machine learning techniques, developing a surrogate model capable of predicting associated costs and increasing the computational efficiency of optimization models. A case study is presented to validate the methodology, showing a significant reduction of 31.8% in evaluation times and a decrease in optimization time compared to traditional models. The results indicated that despite the reduction in computational effort, the increase in the final cost of the network was minimal, with only a 2.42% increase compared to the baseline model. These findings underscore the effectiveness of combining machine learning with genetic algorithms for the optimization of PS in WDNs, improving computational efficiency while maintaining high standards in solution quality. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Advanced brain tumor segmentation using DeepLabV3Plus with Xception encoder on a multi-class MR image dataset

引用

Multimedia Tools and Applications 2025年 1-22页

作者： Saifullah, Shoffan Dreżewski, Rafal Yudhana, Anton Faculty of Computer Science AGH University of Krakow Krakow30-059 Poland Department of Informatics Universitas Pembangunan Nasional Veteran Yogyakarta Yogyakarta55281 Indonesia Department of Electrical Engineering Universitas Ahmad Dahlan Yogyakarta55191 Indonesia

Accurate segmentation of brain tumors from Magnetic Resonance Imaging (MRI) scans presents notable challenges. This particularly in differentiating tumors from surrounding tissues with similar intensity. This study utilizes the DeepLabV3Plus model with an Xception encoder to address these challenges. We evaluated the model on a dataset of 3064 MR images, which included meningioma, glioma, and pituitary tumors. The model achieved high segmentation performance, with an accuracy of 0.9991, Dice Similarity Coefficient (DSC) of 0.9529, and Jaccard Index (JI) of 0.9133. It also demonstrated substantial boundary precision, recording an Average Symmetric Surface Distance (ASSD) of 0.84 mm and a Hausdorff Distance (HD) of 2.3 mm. These metrics surpass those of existing state-of-the-art models. While the model performed well with well-defined tumor boundaries, it faced challenges segmenting tumors with ambiuous edges. These findings suggest significant potential for enhancing diagnostic accuracy in neuro-oncology. Future work will focus on enhancing the model’s sensitivity to subtle tumor features and expanding the dataset to include a broader range of tumor characteristics. Additionally, incorporating multimodal imaging data could further improve segmentation precision. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Model for Wind Power Forecasting Using Enhanced Multilayer Perceptron

引用

computers, Materials & Continua 2025年第5期83卷 2287-2303页

作者： Ahmed A.Ewees Mohammed A.A.Al-Qaness Ali Alshahrani Mohamed Abd Elaziz Computer Science and Artificial Intelligence Department College of Computing and Information TechnologyUniversity of BishaBisha61922Saudi Arabia Department of Computer Damietta UniversityDamietta34517Egypt College of Physics and Electronic Information Engineering Zhejiang Normal UniversityJinhua321004China Department of Mathematics Faculty of ScienceZagazig UniversityZagazig44519Egypt

Wind power forecasting plays a crucial role in optimizing the integration of wind energy into the grid by predicting wind patterns and energy *** enhances the efficiency and reliability of renewable energy *** approaches inform energy management strategies,reduce reliance on fossil fuels,and support the broader transition to sustainable energy *** primary goal of this study is to introduce an effective methodology for estimating wind power through temporal data *** research advances an optimized Multilayer Perceptron(MLP)model using recently proposedmetaheuristic optimization algorithms,namely the FireHawk Optimizer(FHO)and the Non-Monopolize Search(NO).A modified version of FHO,termed FHONO,is developed by integrating NO as a local search mechanism to enhance the exploration capability and address the shortcomings of the original *** developed FHONO is then employed to optimize the MLP for enhanced wind power *** effectiveness of the proposed FHONO-MLP model is validated using renowned datasets from wind turbines in *** results of the comparative analysis between FHONO-MLP,conventionalMLP,and other optimized versions of MLP show that FHONO-MLP outperforms the others,achieving an average RootMean Square Error(RMSE)of 0.105,Mean Absolute Error(MAE)of 0.082,and Coefficient of Determination(R^(2))of 0.967 across all *** findings underscore the significant enhancement in predictive accuracy provided by FHONO and demonstrate its effectiveness in improving wind power forecasting.

关键词： Wind power forecasting multilayer perceptron fire hawk optimizer non-monopolize search

来源：评论

学校读者我要写书评

暂无评论

Exploring information hiding in images – problems and measures: a survey

引用

Multimedia Tools and Applications 2025年 1-63页

作者： Khan, Ahmed Sarfaraz, Aaliya School of Computer Science Taylor’s University Subang Jaya Malaysia School of Computing and Artificial Intelligence Faculty of Engineering and Technology Sunway University No. 5 Jalan Universiti Selangor Darul Ehsan Bandar Sunway47500 Malaysia

The widespread adoption of digital communication technologies across various domains has led to a significant shift towards digitalization. However, this evolution has also introduced vulnerabilities, including unauthorized access, data manipulation, and fabrication by malicious entities, which severely impact the confidentiality and integrity of information. The proliferation of digital images on the internet has facilitated the use of these media for embedding confidential data in a way that prevents detection or extraction by unauthorized third parties. Despite numerous efforts, existing image steganography and watermarking techniques often lack robustness. This paper proposes several novel strategies to enhance the dynamism and imperceptibility of these techniques, integrating cryptographic methods by manipulating the entropy of encrypted images using minimal pixel value differences and applying unique image transformations. Additionally, the study highlights that implementing multi-layered security mechanisms can protect confidential information from modern statistical steganalysis attacks, thereby preserving both the integrity of hidden data and image quality. A comprehensive review of information hiding, specifically focusing on image watermarking and steganography, is provided. Furthermore, this survey outlines key problem statements and offers quantitative metrics for future research in this area. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

The Role of Artificial Intelligence in Improving Histopathological Diagnosis of Prostate Cancer: A Review

引用

Journal of engineering and science in Medical Diagnostics and Therapy 2025年第2期8卷 020801页

作者： Afifi, Shereen Faragallah, M. Hamdy Taha, Radwa Baig, Mirza Ullah, Ehsan Gholam Hosseini, Hamid Hassanein, Sally I. Computer Science and Engineering Department Faculty of Media Engineering and Technology German University Cairo11835 Egypt Biochemistry Department Faculty of Science Helwan University Cairo11795 Egypt Digital Media and Engineering Department Faculty of Media Engineering and Technology German University Cairo11835 Egypt Digital Front Door Orion Health Auckland1010 New Zealand Department of Pathology and Laboratory Medicine Health New Zealand Te Toka Tumai Auckland1061 New Zealand School of Engineering Computer and Mathematical Sciences Auckland University of Technology Private Bag 92006 Auckland1142 New Zealand Biochemistry Department Faculty of Pharmacy and Biotechnology German University Cairo11835 Egypt

This review investigates the effectiveness of exploiting the massive Artificial Intelligence (AI) technology in the diagnosis of prostate cancer histopathological images. It focuses on studying and analyzing the current state and practice for utilizing AI tools, including significant machine learning and deep learning models in the histopathological image analysis process. The preferred reporting items for systematic reviews and meta-Analyses (PRISMA) methodology was adopted for conducting this systematic review to include recent research articles that have been published since 2017. Leveraging novel deep learning models and advanced imaging techniques, AI demonstrates promising capabilities in improving accuracy and efficiency in detecting and classifying prostate cancer. A comprehensive comparison of existing works has been presented with in-depth discussions around current limitations and key challenges while proposing some future advancements. This study aims to pave the way for future research and further integration of AI into the diagnostic processes toward early detection, personalized treatment strategies, and enhanced patient outcomes in the context of a prostate cancer diagnosis. Copyright © 2025 by ASME.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Secure THz Communication in 6G: A Two-Stage DRL Approach for IRS-Assisted NOMA

引用

IEEE Access 2025年 13卷 85294-85306页

作者： Shahwar, Muhammad Ahmed, Manzoor Hussain, Touseef Sheraz, Muhammad Khan, Wali Ullah Chuah, Teong Chee Qingdao University College of Computer Science and Technology Qingdao266071 China Hubei Engineering University School of Computer and Information Science Institute for AI Industrial Technology Research Xiaogan City432000 China Beijing University of Posts and Telecommunications School of Electronic Engineering Beijing100876 China Multimedia University Faculty of Engineering Selangor Cyberjaya63100 Malaysia LuxembourgL-4365 Luxembourg

The rapid evolution of 6G networks demands innovative solutions to address the dual challenges of ensuring robust physical layer security (PLS) and optimizing energy efficiency. This paper introduces an innovative framework based on deep reinforcement learning (DRL) for enhancing security and energy efficiency in terahertz (THz) communication within intelligent reflecting surface (IRS)-assisted non-orthogonal multiple access (NOMA) systems. Utilizing the deep deterministic policy gradient (DDPG) algorithm, we introduce a two-stage policy learning approach designed to optimize secrecy energy efficiency (SEE) while ensuring secure communication, even in the presence of multiple eavesdroppers (Eves). The first stage focuses on optimizing the secrecy rate (SR) by dynamically adjusting IRS phase shifts and transmit power allocation, ensuring secure communication links. The second stage refines the policy to minimize energy consumption without compromising the achieved security. Our framework addresses the challenges of imperfect channel state information (CSI) and inherent uncertainties in THz communication, making it highly adaptable to real-world scenarios. Through extensive simulations, we demonstrate that the proposed DDPG-based approach outperforms traditional methods such as advantage actor-critic (A2C) and alternating optimization (AO) in terms of convergence speed, stability, and final SEE performance. The results highlight the effectiveness of IRS in enhancing signal reflection and coverage, significantly improving both security and energy efficiency in THz-based 6G networks. This work provides a scalable and sustainable solution for next-generation wireless communication systems, paving the way for secure, energy-efficient, and high-capacity 6G networks. © 2013 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Load Balancing in Cloud Computing based on Ant Colony Optimization and Crow Search Algorithm 27

Load Balancing in Cloud Computing based on Ant Colony Optimi...

引用

27th International Conference on Advanced Communications Technology, ICACT 2025

作者： Alsheavi, Amar N. Wang, Xingfu Zhao, Wei Hawbani, Ammar Alhusaini, Naji Ahmed, Ibrahim Abdulrab Ismail, A.S. School of Computer Science and Technology University of Science and Technology of China Anhui Hefei230027 China School of Computer Science and Technology Anhui University of Technology Anhui China School of Computer Science Shenyang Aerospace University Shenyang110136 China School of Computer and Information Engineering Chuzhou University Anhui Chuzhou239000 China Computer Department Applied College Najran University Najran66462 Saudi Arabia College of Life Sciences and Oceanography Shenzhen University Shenzhen518060 China Faculty of Science Zagazig University Zagazig44519 Egypt

ISBN: (纸本)9791188428137

With the rapid increase in cloud services and the increasing shift toward them, balancing the cloud load has become a critical research issue. The increasing demand from customers for technology services worldwide is largely due to its direct impact on performance quality. Therefore, to provide better service quality, it is essential to consider reducing response time and cost in load balancing. This paper addresses the load-balancing problem by optimizing response time and computing cost in cloud computing systems. Specifically, we first formulated the load balancing problem in cloud computing mathematically by designing an objective function that optimizes response time and cost, including constraints to ensure task assignment to a single virtual machine (VM) and resource limits are not exceeded. To solve this optimization problem, we proposed a hybrid algorithm, ACOCSA, that combines Ant Colony Optimization (ACO) and Crow Search Algorithm (CSA). We implemented the ACOCSA algorithm, evaluated the response time, cost, and load balancing metrics, and found that our algorithm performed better in terms of response time and computational cost, and showed good fairness among VMs. © 2025 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

A Type-1 Fuzzy Logic Framework for Early Risk Assessment of Gestational Diabetes Mellitus Using Clinical Risk Factors 2

A Type-1 Fuzzy Logic Framework for Early Risk Assessment of ...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Suman, Saurabh Pacharaney, Utkarsha Gote, Pradnyawant M. Faculty of Engineering and - Technology Department of Computer Science & Design Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Artificial Intelligence & Machine Learning Maharashtra Wardha442001 India

ISBN: (纸本)9798331505745

Gestational Diabetes Mellitus (GDM) is a condition that can put at risk both mother and fetus but early and proper risk assessment need to be carried out for effective management. This paper discloses a Mamdani-kind Fuzzy Inference System to evaluate GDM risk dependent on clinical parameters like age, parity, glucose levels, body mass index (BMI), and insulin levels. The system can simulate all the numerous risk factors in a more gentle way by the utilization of the triangular membership function that converts accurate clinical data into a fuzzy format. A clear rule base, got from the knowledge maps in the clinical field, is put together from the input data to determining the GDM risk levels. This is neither then defuzzied via the centroid method to generate a determinable score. Results show that this system can be used along with the experts, thus yielding the same results as them, meanwhile, it is capable of providing an intelligible output. It lends further credence to the role of fuzzy logic in uncertainties in medical data and their potential by decision support systems in clinical context. While reasonably beneficial results from the system are reported, the static nature of the membership functions implies, for the future, adaptability in methodologies for relative accuracy. This study still emphasizes that fuzzy logic finds application in settings of clinical delineation, which are distinctly more complex for their intended usefulness for conditions such as GDM here. © 2025 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Rethinking Transferable Adversarial Attacks With Double Adversarial Neuron Attribution

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第2期6卷 354-364页

作者： Zhu, Zhiyu Jin, Zhibo Wang, Xinyi Zhang, Jiayu Chen, Huaming Choo, Kim-Kwang Raymond University of Sydney School of Electrical and Computer Engineering DarlingtonNSW2008 Australia University of Malaya Faculty of Computer Science and Information Technology KualaLumpur50603 Malaysia SuZhou Yierqi Jiangsu Suzhou215000 China The University of Texas at San Antonio San AntonioTX78249 United States

Transferable adversarial attacks are a threat to deep neural networks, in particular, for black-box scenarios where access to model information is limited. One can, for example, exploit the intermediate layer neurons to generate transferable adversarial samples. However, current works show limitations in providing feature-level attack mechanisms across multiple victim models. In light of the attribution methods, in this article, we investigate the attribution similarity across different models. We leverage the similarity to incorporate different attribution properties to enhance the sample transferability, for the first time, formulating a novel neuron attribution-based transferable attack termed DANAA++. Specifically, we utilize a range of adversarial attack methods to generate different baseline points through adversarial training. The attribution results are thus obtained along both linear and nonlinear integration paths. In our experiments, the baseline points and integration paths significantly help improve the transferability of adversarial samples. Our approach provides novel insights for building effective attribution-based feature-level adversarial attacks. https://***/LMBTough/DANAAPP. © 2020 IEEE.

关键词： Iterative methods

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：