检索结果-内蒙古大学图书馆

Genetic and evolutionary Computation Conference (GECCO)

作者： Shyju, Saurav Murali, Ritwik Amrita Vishwa Vidyapeetham Amrita Sch Comp Dept Comp Sci & Engn Coimbatore Tamil Nadu India

ISBN: (纸本)9798400701207

Generative Adversarial Networks (GANs) have gained popularity due to their ability to produce realistic examples from existing data without any supervision. However, they are dependent on their hyperparameters, the tuning of which is usually a manual task. Additionally, the computing resources required for such training are also extremely high. In this paper, ATLAS - a Cloud-based Co-evolutionary Framework for training such adversarial networks using evolutionary algorithms is proposed. ATLAS views the GAN components (generator and discriminator) as in a predator-prey relationship and involves co-evolution as a method to address the challenges of overfitting, exploding/vanishing gradients and tunes the hyperparameters of both the components of the GAN. The ATLAS framework is designed to be customizable, and resource flexible to allow for set-up and easy usage for training complex adversarial networks in both distributed and cloud environments. Experiments testing ATLAS capability for anomaly detection were performed and the results show that ATLAS can consistently evolve and produce high-performance GAN models.

关键词： Generative Adversarial Networks Co-Evolution evolutionary algorithms Genetic algorithms Cloud Computing Distributed Computing Hyperparameter Tuning NeuroEvolution

来源：评论

学校读者我要写书评

暂无评论

A Review of Depth-Based Human Motion Enhancement: Past and Present

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2024年第2期28卷 633-644页

作者： Zhou, Le Lannan, Nate Fan, Guoliang Fan Oklahoma State Univ Elect Engn Dept Stillwater OK 74078 USA

In this article, we survey the current research trends of enhancement and denoising of depth-based motion capture data (D-Mocap) and also discuss possible future research issues. We first present the commonly used problem formulation for human motion enhancement. We then review related work and cover a broad set of methodologies including filtering based, learning based, and evolutionary based approaches. In addition, we present some important experiments-related issues, such as data creation or collection, reference data generation, and the metrics used for performance evaluation. It is our intent to provide a comprehensive tutorial and survey on the recent efforts on D-Mocap improvement, both methodologically and experimentally. By comparing the state-of-the-art methods, we also propose future research needs that could make D-Mocap more useful and relevant for real-world clinical applications.

关键词： Cameras Sensors Filtering Noise reduction Bioinformatics Data collection Optical sensors Mocap depth sensors D-mocap motion denoising motion filtering evolutionary algorithms deep learning

来源：评论

学校读者我要写书评

暂无评论

Parameters Extraction of Single Diode and Double Diode Models Using Analytical and Numerical Approach: A Comparative Study

引用

INTERNATIONAL JOURNAL OF MODELLING AND SIMULATION 2025年第2期45卷 569-598页

作者： Saadaoui, Driss Elyaqouti, Mustapha Assalaou, Khalid Hmamou, Dris Ben Lidaighbi, Souad Arjdal, El Hanafi Choulli, Imade Elhammoudy, Abdelfattah Ibn Zohr Univ Lab Mat Signals Syst & Phys Modelling Agadir Morocco

This review paper provides a comparative study between analytical and numerical approaches. The purpose is to estimate the unknown parameters of the single diode and dual diode models. Nine of the most common models are examined in depth, detailing the parameter calculated, the most important approximations characterizing each model, and the calculation process. The effectiveness of the methods studied is assessed under various temperatures and solar irradiation conditions for three types of PV modules using various technologies, such as single-crystalline (CS6V225M), multi-crystalline (CS6P265), and thin film (ST40). The quality of the models fitting to the measured data is assessed by statistical analysis. Results of the study indicate that(1) the temperature exhibits a fairly low impact on the key points of the I-V characteristics of the solar panel, particularly under short and open-circuit conditions, and that(2) the open-circuit voltage at low solar irradiance, as shown in I-V curves, is underestimated. The results of the simulation show that the performance in terms of accuracy varies from one technology to another and the same technology varies with the conditions of temperature and solar irradiation. It is expected that this work will be useful to update the knowledge in the field of PV modeling and simulation.

关键词： Single diode PV model parameter extraction analytical approach numerical approach meta-heuristic evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

PSO-optimized fractional order CNNs for enhanced breast cancer detection

引用

RESULTS IN ENGINEERING 2025年 26卷

作者： Yadav, A. Rajasekhar Kumar, Vaegae Naveen Vellore Inst Technol Sch Elect Engn Vellore 632014 Tamil Nadu India

Breast cancer remains a leading cause of cancer-related deaths in women worldwide;its early and accurate detection will increase survival. The inevitable challenges of this traditional diagnostic approach include relatively high false-positive and false-negative rates when screening dense breast tissue. These unavoidable challenges need to be overcome. In this regard, an effective approach in the area of detection of breast cancer has been presented with advanced filtering image techniques that integrate Fractional Order Convolutional Neural Network (Frac-CNN) and are further optimized with Particle Swarm Optimization (PSO). This would be towards designing a reliable and efficient tool for early breast cancer detection. Adaptive filtering helps reduce noise significantly by using this process of advanced image preprocessing for enhanced image quality. Hyperparameter optimization using PSO ensures that only the best configurations for the model are considered. The fractional calculus adopted by the Frac-CNN architecture is helpful in capturing intricate patterns in mammograms for improved detection accuracy. This proposed work evaluates the method more rigorously compared to state-ofthe-art techniques and shows that it reaches very high levels of accuracy, specificity, and sensitivity. The method obtained an accuracy of 99.35%, a specificity of 98.2%, and a sensitivity of 99%, which outperforms traditional methods. This proposed work will improve patient outcomes and treatment strategies by providing a reliable and efficient tool for early breast cancer diagnosis.

关键词： Adaptive median filtering Mean filtering AI-based diagnostics Breast cancer detection Deep learning evolutionary algorithms Fractional order convolutional neural networks Hyperparameter optimization Image filtering Medical imaging Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

A collaborative decomposition-based evolutionary algorithm integrating normal and penalty-based boundary intersection methods for many-objective optimization

引用

INFORMATION SCIENCES 2022年 616卷 505-525页

作者： Wu, Yu Wei, Jianle Ying, Weiqin Lan, Yanqi Cui, Zhen Wang, Zhenyu Guangzhou Univ Sch Comp Sci & Cyber Engn Guangzhou 510006 Peoples R China South China Univ Technol Sch Software Engn Guangzhou 510006 Peoples R China

Decomposition-based evolutionary algorithms have recently become fairly popular for many-objective optimization owing to their excellent selection pressure. However, existing decomposition methods are still quite sensitive to the various shapes of the frontiers of many-objective optimization problems (MaOPs). On the one hand, the penalty-based boundary intersection (PBI) method is incapable of acquiring uniform frontiers for MaOPs with very convex frontiers due to the radial distribution of the reference lines. On the other hand, the parallel reference lines of the normal boundary intersection (NBI) method often result in poor diversity for MaOPs with concave frontiers because of under-sampling near the boundaries. In this paper, a collaborative decomposition (CoD) method is first proposed to integrate the advantages of the PBI and NBI methods to overcome their respective disadvantages. This method inherits the NBI-style Tchebycheff function as a convergence measure to improve the convergence and uniformity of the distribution of the PBI method. Moreover, this method also adaptively tunes the extent to which an NBI reference line is rotated towards a PBI reference line for every boundary subproblem to enhance the diversity of the distribution of the NBI method. Furthermore, a CoD-based evolutionary algorithm (CoDEA) is presented for many-objective optimization. A CoD-based ranking strategy is primarily designed in the CoDEA to rank all the individuals associated with every boundary subproblem according to the CoD aggregation function and determine the best ranks. The proposed algorithm is compared with several popular many-objective evolutionary algorithms on 85 benchmark test instances. The experimental results show that the CoDEA achieves high competitiveness, benefiting from the CoD method. (c) 2022 Elsevier Inc. All rights reserved.

关键词： many-objective optimization evolutionary algorithms decomposition penalty-based boundary intersection normal boundary intersection

来源：评论

学校读者我要写书评

暂无评论

Use of evolutionary algorithms to play the game of checkers: Historical developments, challenges and future prospects 1

引用

3rd International Conference on Soft Computing for Problem Solving, SocProS 2013

作者： Singh, Amarjeet Deep, Kusum Department of Mathematics Indian Institute of Technology Roorkee Roorkee Uttarakhand247667 India

ISBN: (数字)9788132217688

ISBN: (纸本)9788132217671

The objective of this paper is to study the historical development of computer programmers for playing the game of checkers. Since the game-playing is a NP-hard problem, it would be interesting to use evolutionary algorithms to solve them. The question is can a programme be developed which can beat humans with complete success, it may appears that some challenges may also be formed which may substantiate the argument of the paper. Further, these challenges also form a part of this study. © Springer India 2014.

关键词： evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Personalized Group Itinerary Recommendation using a Knowledge-based evolutionary Approach

Personalized Group Itinerary Recommendation using a Knowledg...

引用

Genetic and evolutionary Computation Conference (GECCO)

作者： Jouyandeh, Farzaneh Zadeh, Pooya Moradian Sch Comp Sci Windsor ON Canada

ISBN: (纸本)9798400701207

The problem of recommending a group itinerary is considered to be NP-hard and can be defined as an optimization problem. The goal is to recommend the best series of points of interest (POIs) to a group of people who are visiting a destination based on their preferences and past experiences. This paper proposes an evolutionary approach based on cultural algorithms to address this problem. Our objective is to maximize the group's satisfaction by recommending an itinerary comprised of the optimal series of visiting POIs, considering the interests of all members, total travel time, and visit duration while minimizing the travel costs within their assigned budget. The proposed algorithm uses historical and normative knowledge to create a belief space used later to guide the search direction and decision-making. The belief space is a knowledge repository that tracks the evolution of decisions during the search process. We evaluated the performance of the proposed algorithm on a set of real-world datasets and compared that with state-of-the-art approaches. We also conducted non-parametric tests to analyze the results. Compared with other algorithms, the proposed approach is capable of recommending efficient and satisfactory itineraries to groups with diverse interests.

关键词： Itinerary recommendation Cultural algorithms evolutionary algorithms Recommendation Systems

来源：评论

学校读者我要写书评

暂无评论

Optimizing Deep Learning for Computer-Aided Diagnosis of Lung Diseases: An Automated Method Combining evolutionary Algorithm and Transfer Learning 15th

Optimizing Deep Learning for Computer-Aided Diagnosis of Lun...

引用

15th International Conference on Computational Collective Intelligence (ICCCI)

作者： Louati, Hassen Louati, Ali Kariri, Elham Bechikh, Slim Univ Tunis SMART Lab ISG Tunis Tunisia Prince Sattam bin Abdulaziz Univ Dept Informat Syst Coll Comp Engn & Sci Al Kharj 11942 Saudi Arabia

ISBN: (纸本)9783031417733;9783031417740

Recent advancements in Computer Vision have opened up new opportunities for addressing complex healthcare challenges, particularly in the area of lung disease diagnosis. Chest X-rays, a commonly used radiological technique, hold great potential in this regard. To leverage this potential, researchers have proposed the use of deep learning methods for building computer-aided diagnostic systems. However, the design and compression of these systems remains a challenge, as it depends heavily on the expertise of the data scientists. To address this, we propose an automated method that utilizes an evolutionary algorithm (EA) to optimize the design and compression of a convolutional neural network (CNN) for X-Ray image classification. This method is capable of accurately classifying radiography images and detecting possible chest abnormalities and infections, including COVID-19. Additionally, the method incorporates transfer learning, where a pre-trained CNN model on a large dataset of chest X-ray images is fine-tuned for the specific task of detecting COVID-19. This approach can help to reduce the amount of labeled data required for the specific task and improve the overall performance of the model. Our method has been validated through a series of experiments against relevant state-of-the-art architectures.

关键词： Computer-Aided Diagnosis Deep Learning evolutionary algorithms Transfer Learning

来源：评论

学校读者我要写书评

暂无评论

Multi-objective intelligent detailed design for prefabricated composite slabs using two-level multi-population co-evolution algorithm

引用

JOURNAL OF BUILDING ENGINEERING 2025年 107卷

作者： Zhang, Chao Zhou, Xuhong Liu, Jiepeng Xu, Chengran Zheng, Xiaolei Qi, Hongtuo Chen, Y. Frank Chongqing Univ Sch Civil Engn 174 Shazheng St Chongqing 400044 Peoples R China Chongqing Univ Sch Automat 174 Shazheng St Chongqing 400044 Peoples R China Chongqing Univ Inst Smart City Chongqing Univ Liyang Liyang 213300 Jiangsu Peoples R China Penn State Univ Dept Civil Engn Middletown PA 17057 USA

The prefabricated composite slab (PCS) is an essential horizontal component of precast buildings. The detailed design process for PCS is extremely complex and challenging due to the need for considering multi-disciplinary and cross-stage collaborations. Traditionally, rule-based methods for PCS design are time-consuming and labor-intensive to provide high-quality and error-free solutions. Therefore, an intelligent detailed design framework is developed to provide necessary manufacturing information for each PCS and its rebar mesh. Specifically, a two-level multipopulation co-evolution algorithm (MPCEA) is proposed to solve the high-dimensional optimization problem associated with big-scale PCS design. In the rebar layout, a non-uniform sampling strategy is utilized to generate the high-quality initial population, and a greedy selection method is utilized to obtain the optimal co-evolutionary solutions. The first-level adjusts the positions and dimensions of all PCSs to reduce the number of slab specifications and quantities of slabs, and the second-level ensures collision-free rebar meshes with fewer specifications. Two different examples are illustrated to validate the feasibility of the proposed framework. The experimental results demonstrate that the multi-population differential evolution (MPDE) and multi-population grey wolf optimization (MPGWO) methods perform better compared to other methods.

关键词： Prefabricated composite slabs (PCSs) Detailed design Layout optimization problem Multi-population co-evolution algorithm (MPCEA) evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Winning the CityLearn Challenge: Adaptive Optimization with evolutionary Search under Trajectory-Based Guidance 37

Winning the CityLearn Challenge: Adaptive Optimization with ...

引用

37th AAAI Conference on Artificial Intelligence (AAAI) / 35th Conference on Innovative Applications of Artificial Intelligence / 13th Symposium on Educational Advances in Artificial Intelligence

作者： Khattar, Vanshaj Jin, Ming Virginia Tech Dept Elect & Comp Engn Blacksburg VA 24061 USA

ISBN: (纸本)9781577358800

Modern power systems will have to face difficult challenges in the years to come: frequent blackouts in urban areas caused by high power demand peaks, grid instability exacerbated by intermittent renewable generation, and global climate change amplified by rising carbon emissions. While current practices are growingly inadequate, the path to widespread adoption of artificial intelligence (AI) methods is hindered by missing aspects of trustworthiness. The CityLearn Challenge is an exemplary opportunity for researchers from multiple disciplines to investigate the potential of AI to tackle these pressing issues in the energy domain, collectively modeled as a reinforcement learning (RL) task. Multiple real-world challenges faced by contemporary RL techniques are embodied in the problem formulation. In this paper, we present a novel method using the solution function of optimization as policies to compute actions for sequential decision-making, while notably adapting the parameters of the optimization model from online observations. Algorithmically, this is achieved by an evolutionary algorithm under a novel trajectory-based guidance scheme. Formally, the global convergence property is established. Our agent ranked first in the latest 2021 CityLearn Challenge, being able to achieve superior performance in almost all metrics while maintaining some key aspects of interpretability.

关键词： evolutionary algorithms

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：