Engineering Applications of Artificial Intelligence最新文献_第2页

An improved reinforcement learning-based differential evolution algorithm for combined economic and emission dispatch problems 经济与排放联合调度问题的改进强化学习差分进化算法

IF 7.5 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Engineering Applications of Artificial Intelligence

Pub Date : 2024-11-29 DOI: 10.1016/j.engappai.2024.109709

Yuan Wang , Xiaobing Yu , Wen Zhang

To overcome challenges posed by escalating environmental pollution and climate change, the combined economic and emission dispatch problem is proposed to balance economic efficiency with emission cost. The primary objective of the problem is to ensure that emissions are minimized while optimal economic costs are achieved simultaneously. However, due to the nonlinear and nonconvex characteristics of the model, the optimization is confronted with many difficulties. Hence, an innovative improved reinforcement learning-based differential evolution algorithm is proposed in this article, with reinforcement learning seamlessly integrated into the differential evolution algorithm. Q-learning from reinforcement learning technique is utilized to dynamically adjust parameter settings and select appropriate mutation strategies, thereby boosting the algorithm's adaptability and overall performance. The effectiveness of the proposed algorithm is tested on thirty testing functions and combined economic and emission dispatch problems in comparison with the other five algorithms. According to the experimental results of testing functions, superior performance is consistently achieved by the proposed algorithm, with the highest adaptability exhibited and an average ranking of 1.4167. Its superiority is further demonstrated through Wilcoxon tests on results of testing functions and combined economic and emission dispatch problems with the proportion of 100%, and the proposed algorithm is significantly better than other algorithms at a 0.05 significance level. The superiority of the proposed algorithm in optimizing combined economic and emission dispatch problems demonstrates that the proposed algorithm is shown to be adaptable to complex optimization environments, which proves useful for industrial applications and artificial intelligence.

为了应对日益严重的环境污染和气候变化带来的挑战，提出了经济与排放联合调度问题，以平衡经济效率与排放成本。该问题的主要目标是确保排放量最小化，同时实现最佳经济成本。然而，由于模型的非线性和非凸特性，优化面临着许多困难。因此，本文提出了一种创新的改进的基于强化学习的差分进化算法，将强化学习无缝集成到差分进化算法中。利用强化学习技术中的Q-learning动态调整参数设置，选择合适的突变策略，提高算法的适应性和整体性能。通过30个测试函数，结合经济和排放调度问题，与其他5种算法进行对比，验证了该算法的有效性。从测试函数的实验结果来看，本文提出的算法始终具有优异的性能，表现出最高的适应性，平均排名为1.4167。通过对测试函数结果的Wilcoxon检验，结合经济和排放调度问题，以100%的比例进一步证明了该算法的优越性，在0.05的显著性水平上，该算法显著优于其他算法。该算法在优化经济与排放联合调度问题上的优越性表明，该算法能够适应复杂的优化环境，可用于工业应用和人工智能。

{"title":"An improved reinforcement learning-based differential evolution algorithm for combined economic and emission dispatch problems","authors":"Yuan Wang , Xiaobing Yu , Wen Zhang","doi":"10.1016/j.engappai.2024.109709","DOIUrl":"10.1016/j.engappai.2024.109709","url":null,"abstract":"<div><div>To overcome challenges posed by escalating environmental pollution and climate change, the combined economic and emission dispatch problem is proposed to balance economic efficiency with emission cost. The primary objective of the problem is to ensure that emissions are minimized while optimal economic costs are achieved simultaneously. However, due to the nonlinear and nonconvex characteristics of the model, the optimization is confronted with many difficulties. Hence, an innovative improved reinforcement learning-based differential evolution algorithm is proposed in this article, with reinforcement learning seamlessly integrated into the differential evolution algorithm. Q-learning from reinforcement learning technique is utilized to dynamically adjust parameter settings and select appropriate mutation strategies, thereby boosting the algorithm's adaptability and overall performance. The effectiveness of the proposed algorithm is tested on thirty testing functions and combined economic and emission dispatch problems in comparison with the other five algorithms. According to the experimental results of testing functions, superior performance is consistently achieved by the proposed algorithm, with the highest adaptability exhibited and an average ranking of 1.4167. Its superiority is further demonstrated through Wilcoxon tests on results of testing functions and combined economic and emission dispatch problems with the proportion of 100%, and the proposed algorithm is significantly better than other algorithms at a 0.05 significance level. The superiority of the proposed algorithm in optimizing combined economic and emission dispatch problems demonstrates that the proposed algorithm is shown to be adaptable to complex optimization environments, which proves useful for industrial applications and artificial intelligence.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"140 ","pages":"Article 109709"},"PeriodicalIF":7.5,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142743973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Low-cost language models: Survey and performance evaluation on Python code generation 低成本语言模型：Python代码生成的调查和性能评估

IF 7.5 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Engineering Applications of Artificial Intelligence

Pub Date : 2024-11-29 DOI: 10.1016/j.engappai.2024.109490

Jessica López Espejel, Mahaman Sanoussi Yahaya Alassan, Merieme Bouhandi, Walid Dahhane, El Hassane Ettifouri

Large Language Models (LLMs) have become a popular choice for many Natural Language Processing (NLP) tasks due to their versatility and ability to produce high-quality results. Specifically, they are increasingly used for automatic code generation to help developers tackle repetitive coding tasks. However, LLMs’ substantial computational and memory requirements often make them inaccessible to users with limited resources. This paper focuses on very low-cost models which offer a more accessible alternative to resource-intensive LLMs. We notably: (1) propose a thorough semi-manual evaluation of their performance in generating Python code, (2) introduce a Chain-of-Thought (CoT) prompting strategy to improve model reasoning and code quality, and (3) propose a new dataset of 60 programming problems, with varied difficulty levels, designed to extend existing benchmarks like HumanEval and EvalPlus. Our findings show that some low-cost compatible models achieve competitive results compared to larger models like ChatGPT despite using significantly fewer resources. We will make our dataset and prompts publicly available to support further research.

大型语言模型（llm）由于其通用性和产生高质量结果的能力，已成为许多自然语言处理（NLP）任务的热门选择。具体来说，它们越来越多地用于自动代码生成，以帮助开发人员处理重复的编码任务。然而，llm的大量计算和内存需求往往使资源有限的用户无法访问它们。本文的重点是非常低成本的模型，它为资源密集型法学硕士提供了一个更容易获得的替代方案。我们值得注意的是：(1)提出了一个全面的半手动评估它们在生成Python代码方面的性能，(2)引入了一个思维链（CoT）提示策略，以提高模型推理和代码质量，(3)提出了一个包含60个编程问题的新数据集，具有不同的难度级别，旨在扩展现有的基准，如HumanEval和EvalPlus。我们的研究结果表明，尽管使用的资源少得多，但与ChatGPT等大型模型相比，一些低成本兼容模型获得了具有竞争力的结果。我们将公开我们的数据集和提示，以支持进一步的研究。

{"title":"Low-cost language models: Survey and performance evaluation on Python code generation","authors":"Jessica López Espejel, Mahaman Sanoussi Yahaya Alassan, Merieme Bouhandi, Walid Dahhane, El Hassane Ettifouri","doi":"10.1016/j.engappai.2024.109490","DOIUrl":"10.1016/j.engappai.2024.109490","url":null,"abstract":"<div><div>Large Language Models (LLMs) have become a popular choice for many Natural Language Processing (NLP) tasks due to their versatility and ability to produce high-quality results. Specifically, they are increasingly used for automatic code generation to help developers tackle repetitive coding tasks. However, LLMs’ substantial computational and memory requirements often make them inaccessible to users with limited resources. This paper focuses on very low-cost models which offer a more accessible alternative to resource-intensive LLMs. We notably: (1) propose a thorough semi-manual evaluation of their performance in generating Python code, (2) introduce a Chain-of-Thought (CoT) prompting strategy to improve model reasoning and code quality, and (3) propose a new dataset of 60 programming problems, with varied difficulty levels, designed to extend existing benchmarks like HumanEval and EvalPlus. Our findings show that some low-cost compatible models achieve competitive results compared to larger models like ChatGPT despite using significantly fewer resources. We will make our dataset and prompts publicly available to support further research.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"140 ","pages":"Article 109490"},"PeriodicalIF":7.5,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142744064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Supporting multi-criteria decision-making processes with unknown criteria weights 支持未知标准权重的多准则决策过程

IF 7.5 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Engineering Applications of Artificial Intelligence

Pub Date : 2024-11-29 DOI: 10.1016/j.engappai.2024.109699

Jakub Więckowski , Wojciech Sałabun

Decision support systems are crucial in today’s tech-driven world, assisting decision-makers with complex choices. Determining criteria weights is a paramount aspect, significantly influencing outcomes. Traditionally, criteria weights are derived from objective measures, subjective expert knowledge, or a combination of both, each with its own strengths and limitations. This paper presents a novel approach for addressing unknown criteria relevance by systematically generating weight vectors, thus exploring a broader decision problem space. The proposed methodology is adaptable to various multi-criteria methods, enhancing its applicability across different scenarios. Its effectiveness is empirically validated through two practical examples: Glomerular Filtration Rate (GFR) evaluation and bridge construction method selection, demonstrating its broad applicability. Comparative analysis with existing objective weighting techniques reveals the limitations of current approaches and highlights the improved decision-making capabilities enabled by the proposed method. This research addresses a critical gap in the reliability and robustness of existing methods, particularly in situations with unknown criteria weights. Key contributions include a new decision-making methodology and an innovative ranking formulation using fuzzy sets, with empirical verification strengthening the utility of the approach. This paper offers a promising solution for advancing multi-criteria decision analysis, especially in complex scenarios with uncertain criteria relevance.

决策支持系统在当今技术驱动的世界中至关重要，它可以帮助决策者做出复杂的选择。确定标准权重是最重要的方面，会显著影响结果。传统上，标准权重来源于客观度量、主观专家知识或两者的结合，每一个都有自己的优点和局限性。本文提出了一种通过系统地生成权重向量来解决未知标准相关性的新方法，从而探索了更广泛的决策问题空间。该方法适用于各种多准则方法，增强了其在不同场景中的适用性。通过肾小球滤过率（Glomerular Filtration Rate， GFR）评价和桥梁施工方法选择两个实例，实证验证了该方法的有效性，显示了其广泛的适用性。与现有客观加权技术的比较分析揭示了当前方法的局限性，并突出了所提出的方法所能提高的决策能力。本研究解决了现有方法在可靠性和鲁棒性方面的关键差距，特别是在未知标准权重的情况下。主要贡献包括新的决策方法和使用模糊集的创新排名公式，经验验证加强了该方法的实用性。本文为推进多准则决策分析提供了一个有希望的解决方案，特别是在具有不确定准则相关性的复杂场景中。

{"title":"Supporting multi-criteria decision-making processes with unknown criteria weights","authors":"Jakub Więckowski , Wojciech Sałabun","doi":"10.1016/j.engappai.2024.109699","DOIUrl":"10.1016/j.engappai.2024.109699","url":null,"abstract":"<div><div>Decision support systems are crucial in today’s tech-driven world, assisting decision-makers with complex choices. Determining criteria weights is a paramount aspect, significantly influencing outcomes. Traditionally, criteria weights are derived from objective measures, subjective expert knowledge, or a combination of both, each with its own strengths and limitations. This paper presents a novel approach for addressing unknown criteria relevance by systematically generating weight vectors, thus exploring a broader decision problem space. The proposed methodology is adaptable to various multi-criteria methods, enhancing its applicability across different scenarios. Its effectiveness is empirically validated through two practical examples: Glomerular Filtration Rate (GFR) evaluation and bridge construction method selection, demonstrating its broad applicability. Comparative analysis with existing objective weighting techniques reveals the limitations of current approaches and highlights the improved decision-making capabilities enabled by the proposed method. This research addresses a critical gap in the reliability and robustness of existing methods, particularly in situations with unknown criteria weights. Key contributions include a new decision-making methodology and an innovative ranking formulation using fuzzy sets, with empirical verification strengthening the utility of the approach. This paper offers a promising solution for advancing multi-criteria decision analysis, especially in complex scenarios with uncertain criteria relevance.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"140 ","pages":"Article 109699"},"PeriodicalIF":7.5,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142744065","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Quantum-inspired semantic matching based on neural networks with the duality of density matrices 基于密度矩阵对偶的神经网络的量子启发语义匹配

IF 7.5 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Engineering Applications of Artificial Intelligence

Pub Date : 2024-11-29 DOI: 10.1016/j.engappai.2024.109667

Chenchen Zhang , Qiuchi Li , Dawei Song , Prayag Tiwari

Social media text can be semantically matched in different ways, viz paraphrase identification, answer selection, community question answering, and so on. The performance of the above semantic matching tasks depends largely on the ability of language modeling. Neural network based language models and probabilistic language models are two main streams of language modeling approaches. However, few prior work has managed to unify them in a single framework on the premise of preserving probabilistic features during the neural network learning process. Motivated by recent advances of quantum-inspired neural networks for text representation learning, we fill the gap by resorting to density matrices, a key concept describing a quantum state as well as a quantum probability distribution. The state and probability views of density matrices are mapped respectively to the neural and probabilistic aspects of language models. Concretizing this state-probability duality to the semantic matching task, we build a unified neural-probabilistic language model through a quantum-inspired neural network. Specifically, we take the state view to construct a density matrix representation of sentence, and exploit its probabilistic nature by extracting its main semantics, which form the basis of a legitimate quantum measurement. When matching two sentences, each sentence is measured against the main semantics of the other. Such a process is implemented in a neural structure, facilitating an end-to-end learning of parameters. The learned density matrix representation reflects an authentic probability distribution over the semantic space throughout the training process. Experiments show that our model significantly outperforms a wide range of prominent classical and quantum-inspired baselines.

社交媒体文本可以通过不同的方式进行语义匹配，如释义识别、答案选择、社区问答等。上述语义匹配任务的性能在很大程度上取决于语言建模的能力。基于神经网络的语言模型和概率语言模型是语言建模方法的两大主流。然而，在神经网络学习过程中，在保留概率特征的前提下，很少有先前的工作将它们统一在一个框架中。受量子启发的神经网络用于文本表示学习的最新进展的激励，我们通过求助于密度矩阵来填补这一空白，密度矩阵是描述量子状态和量子概率分布的关键概念。密度矩阵的状态视图和概率视图分别映射到语言模型的神经和概率方面。将这种状态-概率对偶性具体到语义匹配任务中，通过量子启发神经网络构建统一的神经概率语言模型。具体而言，我们采用状态视图构建句子的密度矩阵表示，并通过提取句子的主要语义来利用句子的概率性质，从而构成合法量子测量的基础。当匹配两个句子时，每个句子都是根据另一个句子的主要语义来衡量的。这样的过程在神经结构中实现，促进了端到端的参数学习。学习到的密度矩阵表示在整个训练过程中反映了语义空间上的真实概率分布。实验表明，我们的模型明显优于许多著名的经典和量子启发基线。

{"title":"Quantum-inspired semantic matching based on neural networks with the duality of density matrices","authors":"Chenchen Zhang , Qiuchi Li , Dawei Song , Prayag Tiwari","doi":"10.1016/j.engappai.2024.109667","DOIUrl":"10.1016/j.engappai.2024.109667","url":null,"abstract":"<div><div>Social media text can be semantically matched in different ways, viz paraphrase identification, answer selection, community question answering, and so on. The performance of the above semantic matching tasks depends largely on the ability of language modeling. Neural network based language models and probabilistic language models are two main streams of language modeling approaches. However, few prior work has managed to unify them in a single framework on the premise of preserving probabilistic features during the neural network learning process. Motivated by recent advances of quantum-inspired neural networks for text representation learning, we fill the gap by resorting to density matrices, a key concept describing a quantum state as well as a quantum probability distribution. The state and probability views of density matrices are mapped respectively to the neural and probabilistic aspects of language models. Concretizing this state-probability duality to the semantic matching task, we build a unified neural-probabilistic language model through a quantum-inspired neural network. Specifically, we take the state view to construct a density matrix representation of sentence, and exploit its probabilistic nature by extracting its main semantics, which form the basis of a legitimate quantum measurement. When matching two sentences, each sentence is measured against the main semantics of the other. Such a process is implemented in a neural structure, facilitating an end-to-end learning of parameters. The learned density matrix representation reflects an authentic probability distribution over the semantic space throughout the training process. Experiments show that our model significantly outperforms a wide range of prominent classical and quantum-inspired baselines.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"140 ","pages":"Article 109667"},"PeriodicalIF":7.5,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142744076","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Reliable federated learning based on delayed gradient aggregation for intelligent connected vehicles 基于延迟梯度聚合的智能网联车辆可靠联邦学习

IF 7.5 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Engineering Applications of Artificial Intelligence

Pub Date : 2024-11-29 DOI: 10.1016/j.engappai.2024.109719

Zhigang Yang, Cheng Cheng, Zixuan Li, Ruyan Wang, Xuhua Zhang

As an organic combination of the Internet of Vehicles and intelligent vehicles, Intelligent Connected Vehicles (ICVs) have very high research and application value. Traditional data application methods require the local aggregation of sensitive user data, which poses a threat to user data privacy. Federated learning (FL) is a promising machine learning method that leverages distributed, personalized datasets to enhance performance while preserving user privacy. However, in mobile environments, unreliable client data can degrade the global model, reducing accuracy. Additionally, the mobility of ICVs can destabilize the training process, prolonging model updates and diminishing aggregation accuracy. To address these challenges, this paper proposes a dynamic asynchronous aggregation method that improves both reliability and training efficiency in FL for mobile networks. Therefore, it becomes crucial to find reliable aggregation of mobile device participation in FL tasks. To this end, we propose a reliable FL scheme, which only selects reliable mobile devices to participate in model aggregation to improve the generalization ability of the model. In addition, we design a dynamic asynchronous aggregation method based on reputation scores without affecting the model. Reduce model training time without compromising performance. Through experimental analysis, it is proved that this method can improve the reliability and effectiveness of FL tasks in mobile networks.

智能网联汽车作为车联网与智能汽车的有机结合，具有很高的研究和应用价值。传统的数据应用方法需要对用户敏感数据进行局部聚合，这对用户数据隐私构成了威胁。联邦学习（FL）是一种很有前途的机器学习方法，它利用分布式、个性化的数据集来提高性能，同时保护用户隐私。然而，在移动环境中，不可靠的客户端数据会降低全局模型的准确性。此外，icv的移动性会破坏训练过程的稳定性，延长模型更新时间，降低聚合精度。为了解决这些挑战，本文提出了一种动态异步聚合方法，提高了移动网络FL的可靠性和训练效率。因此，寻找移动设备参与FL任务的可靠聚合就变得至关重要。为此，我们提出了一种可靠的FL方案，该方案只选择可靠的移动设备参与模型聚合，提高模型的泛化能力。此外，在不影响模型的情况下，设计了一种基于信誉分数的动态异步聚合方法。在不影响性能的情况下减少模型训练时间。通过实验分析，证明该方法可以提高移动网络中FL任务的可靠性和有效性。

{"title":"Reliable federated learning based on delayed gradient aggregation for intelligent connected vehicles","authors":"Zhigang Yang, Cheng Cheng, Zixuan Li, Ruyan Wang, Xuhua Zhang","doi":"10.1016/j.engappai.2024.109719","DOIUrl":"10.1016/j.engappai.2024.109719","url":null,"abstract":"<div><div>As an organic combination of the Internet of Vehicles and intelligent vehicles, Intelligent Connected Vehicles (ICVs) have very high research and application value. Traditional data application methods require the local aggregation of sensitive user data, which poses a threat to user data privacy. Federated learning (FL) is a promising machine learning method that leverages distributed, personalized datasets to enhance performance while preserving user privacy. However, in mobile environments, unreliable client data can degrade the global model, reducing accuracy. Additionally, the mobility of ICVs can destabilize the training process, prolonging model updates and diminishing aggregation accuracy. To address these challenges, this paper proposes a dynamic asynchronous aggregation method that improves both reliability and training efficiency in FL for mobile networks. Therefore, it becomes crucial to find reliable aggregation of mobile device participation in FL tasks. To this end, we propose a reliable FL scheme, which only selects reliable mobile devices to participate in model aggregation to improve the generalization ability of the model. In addition, we design a dynamic asynchronous aggregation method based on reputation scores without affecting the model. Reduce model training time without compromising performance. Through experimental analysis, it is proved that this method can improve the reliability and effectiveness of FL tasks in mobile networks.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"140 ","pages":"Article 109719"},"PeriodicalIF":7.5,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142743970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Performance evaluation of uranium enrichment cascades using fuzzy based harmony search algorithm 基于模糊协调搜索算法的铀浓缩级联性能评价

IF 7.5 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Engineering Applications of Artificial Intelligence

Pub Date : 2024-11-29 DOI: 10.1016/j.engappai.2024.109710

S. Dadashzadeh, M. Aghaie

The production of energy in nuclear reactors needs enrichment of fuels. There is some interest in taking the fuel enrichment level to 3–5% by cascades. Optimization of the isotopic cascades is essential to make this process economic. This study presents a Fuzzy-based Harmony Search (FHS) algorithm aimed at dynamic parameter adaptation as well as establishing a balance between exploration and exploitation, which significantly increases the convergence speed of the algorithm. Accelerating the convergence of the algorithm is demonstrated in the Sphere, Schwefel, Ackley, and Drop-Waves benchmarks at first. This approach also enhances performance in several test cases of optimum cascade problems, with results validated through comparisons with conventional methods. According to the results, the total number of centrifuges using FHS reached 6306 in test case 1, which was reduced 44 pieces compared to the method used by Palkin, and 55 pieces compared to the real coded genetic algorithm. The total number of centrifuges using FHS reached 2808 in test case 4 with a different type of gas centrifuge, which decreased 27 pieces compared to the direct search method. Similar results were obtained in other test cases, indicating the effectiveness of the FHS algorithm in minimizing the total number of centrifuges and total flow rates.

在核反应堆中生产能源需要对燃料进行浓缩。有人对通过级联将燃料浓缩水平提高到3-5%很感兴趣。同位素级联的优化是使这一过程经济有效的关键。本文提出了一种基于模糊的和谐搜索（FHS）算法，该算法旨在动态自适应参数，并在探索和利用之间建立平衡，显著提高了算法的收敛速度。首先在Sphere， Schwefel， Ackley和Drop-Waves基准测试中演示了加速算法的收敛性。该方法还在几个最优级联问题的测试用例中提高了性能，并通过与传统方法的比较验证了结果。结果表明，在测试用例1中，使用FHS的离心机总数达到6306台，比Palkin方法减少44台，比真实编码遗传算法减少55台。在不同型号气体离心机的试验用例4中，使用FHS的离心机总数达到2808台，比直接搜索法减少27台。在其他测试用例中也得到了类似的结果，表明FHS算法在最小化离心机总数和总流速方面是有效的。

{"title":"Performance evaluation of uranium enrichment cascades using fuzzy based harmony search algorithm","authors":"S. Dadashzadeh, M. Aghaie","doi":"10.1016/j.engappai.2024.109710","DOIUrl":"10.1016/j.engappai.2024.109710","url":null,"abstract":"<div><div>The production of energy in nuclear reactors needs enrichment of fuels. There is some interest in taking the fuel enrichment level to 3–5% by cascades. Optimization of the isotopic cascades is essential to make this process economic. This study presents a Fuzzy-based Harmony Search (FHS) algorithm aimed at dynamic parameter adaptation as well as establishing a balance between exploration and exploitation, which significantly increases the convergence speed of the algorithm. Accelerating the convergence of the algorithm is demonstrated in the Sphere, Schwefel, Ackley, and Drop-Waves benchmarks at first. This approach also enhances performance in several test cases of optimum cascade problems, with results validated through comparisons with conventional methods. According to the results, the total number of centrifuges using FHS reached 6306 in test case 1, which was reduced 44 pieces compared to the method used by Palkin, and 55 pieces compared to the real coded genetic algorithm. The total number of centrifuges using FHS reached 2808 in test case 4 with a different type of gas centrifuge, which decreased 27 pieces compared to the direct search method. Similar results were obtained in other test cases, indicating the effectiveness of the FHS algorithm in minimizing the total number of centrifuges and total flow rates.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"140 ","pages":"Article 109710"},"PeriodicalIF":7.5,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142744063","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Semantic segmentation model based on edge information for rock structural surface traces detection 基于边缘信息的岩石结构表面轨迹检测语义分割模型

IF 7.5 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Engineering Applications of Artificial Intelligence

Pub Date : 2024-11-29 DOI: 10.1016/j.engappai.2024.109706

Xiaofeng Yuan , Dun Wu , Yalin Wang , Chunhua Yang , Weihua Gui , Shuqiao Cheng , Lingjian Ye , Feifan Shen

Fast and accurate detection of rock structural surface traces is crucial for geology and engineering fields. In recent years, deep learning techniques like U-Net (UNet) have been applied to rock structural surface traces detection by virtue of its high accuracy and strong robustness. However, the loss of important information during the downsampling process may hinder the model performance for rock structural surface traces detection. To alleviate this problem, this paper proposes a semantic segmentation model based on edge information (Edge-UNet) for rock structural surface traces detection. In Edge-UNet, an edge pooling method is designed, which can retain more trace features rich in edge information in the downsampling process, so as to enhance the learning of the model for traces. Then, an edge semantic enhancement structure based on edge pooling is designed to strengthen the edge information in Edge-UNet's encoder. In addition, a channel space attention gate based on edge information is incorporated in Edge-UNet's decoder, which facilitates the model to capture fine trace features. These designs clarify the retention and utilization of edge information in principle which enhances the interpretability of the model. Finally, Convolutional neural network -based and Transformer-based semantic segmentation models were selected for comparison experiments with Edge-UNet, respectively. From the experimental results, Edge-UNet outperforms the other models in three performance metrics, which verifies the superior performance of Edge-UNet in rock structural surface trace detection task.

快速、准确地探测岩石构造表面轨迹在地质和工程领域具有重要意义。近年来，U-Net （UNet）等深度学习技术以其精度高、鲁棒性强的特点被应用于岩石结构表面轨迹检测。然而，在降采样过程中，重要信息的丢失可能会影响岩石结构表面轨迹检测模型的性能。为了解决这一问题，本文提出了一种基于边缘信息的语义分割模型（edge - unet）用于岩石结构表面轨迹检测。在edge - unet中，设计了一种边缘池化方法，可以在降采样过程中保留更多富含边缘信息的迹特征，从而增强模型对迹的学习能力。然后，设计了一种基于边缘池的边缘语义增强结构来增强edge - unet编码器中的边缘信息。此外，在edge - unet的解码器中加入了基于边缘信息的通道空间注意门，使模型能够捕获精细的跟踪特征。这些设计从原则上阐明了边缘信息的保留和利用，增强了模型的可解释性。最后，分别选择基于卷积神经网络和基于transformer的语义分割模型与Edge-UNet进行对比实验。从实验结果来看，Edge-UNet在三个性能指标上都优于其他模型，验证了Edge-UNet在岩石结构表面轨迹检测任务中的优越性能。

{"title":"Semantic segmentation model based on edge information for rock structural surface traces detection","authors":"Xiaofeng Yuan , Dun Wu , Yalin Wang , Chunhua Yang , Weihua Gui , Shuqiao Cheng , Lingjian Ye , Feifan Shen","doi":"10.1016/j.engappai.2024.109706","DOIUrl":"10.1016/j.engappai.2024.109706","url":null,"abstract":"<div><div>Fast and accurate detection of rock structural surface traces is crucial for geology and engineering fields. In recent years, deep learning techniques like U-Net (UNet) have been applied to rock structural surface traces detection by virtue of its high accuracy and strong robustness. However, the loss of important information during the downsampling process may hinder the model performance for rock structural surface traces detection. To alleviate this problem, this paper proposes a semantic segmentation model based on edge information (Edge-UNet) for rock structural surface traces detection. In Edge-UNet, an edge pooling method is designed, which can retain more trace features rich in edge information in the downsampling process, so as to enhance the learning of the model for traces. Then, an edge semantic enhancement structure based on edge pooling is designed to strengthen the edge information in Edge-UNet's encoder. In addition, a channel space attention gate based on edge information is incorporated in Edge-UNet's decoder, which facilitates the model to capture fine trace features. These designs clarify the retention and utilization of edge information in principle which enhances the interpretability of the model. Finally, Convolutional neural network -based and Transformer-based semantic segmentation models were selected for comparison experiments with Edge-UNet, respectively. From the experimental results, Edge-UNet outperforms the other models in three performance metrics, which verifies the superior performance of Edge-UNet in rock structural surface trace detection task.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"140 ","pages":"Article 109706"},"PeriodicalIF":7.5,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142743976","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Semantic graph neural network with multi-measure learning for semi-supervised classification 基于多度量学习的半监督分类语义图神经网络

IF 7.5 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Engineering Applications of Artificial Intelligence

Pub Date : 2024-11-29 DOI: 10.1016/j.engappai.2024.109647

Junchao Lin , Yuan Wan , Jingwen Xu , Xingchen Qi

Graph Neural Networks (GNNs) have attracted increasing attention in recent years and have achieved excellent performance in semi-supervised node classification tasks. The success of most GNNs is attributed to the availability of the original graph structure. However, recent studies have shown that GNNs are vulnerable to the complex underlying structure of the graph, making it necessary to learn comprehensive and robust graph structures for downstream tasks, rather than relying only on the raw graph structure. In light of this, we seek to learn optimal graph structures for downstream tasks and propose a novel framework for semi-supervised classification. Specifically, based on the structural context information of graph and node representations, we encode the complex interactions in semantics and generate semantic graphs to preserve the global structure. Moreover, we develop a novel multi-measure attention layer to optimize the similarity rather than prescribing it a priori, so that the similarity can be adaptively evaluated by integrating measures. These graphs are fused and optimized together with GNN towards semi-supervised classification objective. Extensive experiments and ablation studies on six real-world datasets clearly demonstrate the effectiveness of our proposed model and the contribution of each component. The proposed model not only addresses the inherent vulnerabilities of GNNs to complex graph structures, but also introduces a pioneering approach to learning comprehensive and robust graph representations for semi-supervised classification tasks.

近年来，图神经网络（Graph Neural Networks, gnn）在半监督节点分类任务中取得了优异的成绩，受到越来越多的关注。大多数gnn的成功归因于原始图结构的可用性。然而，最近的研究表明，gnn容易受到图的复杂底层结构的影响，这使得下游任务需要学习全面和鲁棒的图结构，而不是仅仅依赖于原始图结构。鉴于此，我们寻求学习下游任务的最优图结构，并提出一种新的半监督分类框架。具体而言，我们基于图和节点表示的结构上下文信息，对复杂的交互进行语义编码，生成语义图，以保持全局结构。此外，我们开发了一种新的多度量关注层来优化相似性，而不是先验地规定相似性，从而可以通过综合度量自适应地评估相似性。将这些图与GNN进行融合和优化，以实现半监督分类目标。在六个真实世界数据集上进行的大量实验和消融研究清楚地证明了我们提出的模型的有效性以及每个组件的贡献。所提出的模型不仅解决了gnn对复杂图结构的固有脆弱性，而且还引入了一种开创性的方法来学习半监督分类任务的全面和鲁棒图表示。

{"title":"Semantic graph neural network with multi-measure learning for semi-supervised classification","authors":"Junchao Lin , Yuan Wan , Jingwen Xu , Xingchen Qi","doi":"10.1016/j.engappai.2024.109647","DOIUrl":"10.1016/j.engappai.2024.109647","url":null,"abstract":"<div><div>Graph Neural Networks (GNNs) have attracted increasing attention in recent years and have achieved excellent performance in semi-supervised node classification tasks. The success of most GNNs is attributed to the availability of the original graph structure. However, recent studies have shown that GNNs are vulnerable to the complex underlying structure of the graph, making it necessary to learn comprehensive and robust graph structures for downstream tasks, rather than relying only on the raw graph structure. In light of this, we seek to learn optimal graph structures for downstream tasks and propose a novel framework for semi-supervised classification. Specifically, based on the structural context information of graph and node representations, we encode the complex interactions in semantics and generate semantic graphs to preserve the global structure. Moreover, we develop a novel multi-measure attention layer to optimize the similarity rather than prescribing it a priori, so that the similarity can be adaptively evaluated by integrating measures. These graphs are fused and optimized together with GNN towards semi-supervised classification objective. Extensive experiments and ablation studies on six real-world datasets clearly demonstrate the effectiveness of our proposed model and the contribution of each component. The proposed model not only addresses the inherent vulnerabilities of GNNs to complex graph structures, but also introduces a pioneering approach to learning comprehensive and robust graph representations for semi-supervised classification tasks.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"140 ","pages":"Article 109647"},"PeriodicalIF":7.5,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142743977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Predefined time convergence guaranteed performance control for uncertain systems based on reinforcement learning 基于强化学习的不确定系统的预定义时间收敛保证性能控制

IF 7.5 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Engineering Applications of Artificial Intelligence

Pub Date : 2024-11-29 DOI: 10.1016/j.engappai.2024.109734

Chun-Wu Yin

The prescribed performance control method (PPCM) is commonly employed to ensure the guaranteed performance control of non-linear systems. However, traditional approaches suffer from certain drawbacks, such as the dependence of parameter settings for the performance constraint function on the initial tracking error value and the inability to specify the convergence time of tracking error according to engineering requirements. This paper focuses on designing a fault tolerant control strategy with prescribed convergence time and prescribed transient performance for uncertain systems, considering parameter perturbance, actuator faults, and unknown initial states. Firstly, we introduce an error conversion function that transforms the tracking error with any initial value into a new error variable starting from zero. This resolves the issue of depending on the initial value of tracking error in setting parameters for the performance constraint function in prescribed performance control methods. Subsequently, we derive a novel Lyapunov stability criterion for predefined time (PDT) convergence and design a fault-tolerant control strategy using backstepping control method while ensuring prescribed convergence time and prescribed performance. In this approach, we propose a new online reinforcement learning intelligent algorithm to estimate compound interference caused by actuator faults, control saturation constraint increment, system parameter perturbation, and external interference. The theoretical proof establishes predefined time convergence of the closed-loop system. Finally, numerical simulations are conducted on industrial robots with actuator faults to validate the effectiveness of our designed control strategy.

一般采用规定性能控制方法（PPCM）来保证非线性系统的保性能控制。然而，传统方法存在性能约束函数的参数设置依赖于初始跟踪误差值，不能根据工程要求指定跟踪误差的收敛时间等缺点。针对不确定系统，考虑参数扰动、执行器故障和初始状态未知等因素，设计了一种收敛时间和暂态性能均为规定的容错控制策略。首先，引入误差转换函数，将具有任意初始值的跟踪误差转换为从零开始的新误差变量。这就解决了在规定的性能控制方法中，对性能约束函数的参数设置依赖于跟踪误差初始值的问题。在此基础上，提出了一种新的PDT收敛Lyapunov稳定性判据，并在保证规定收敛时间和规定性能的前提下，采用后退控制方法设计了容错控制策略。在该方法中，我们提出了一种新的在线强化学习智能算法来估计由执行器故障、控制饱和约束增量、系统参数摄动和外部干扰引起的复合干扰。理论证明建立了闭环系统的预定义时间收敛性。最后，对存在执行器故障的工业机器人进行了数值仿真，验证了所设计控制策略的有效性。

{"title":"Predefined time convergence guaranteed performance control for uncertain systems based on reinforcement learning","authors":"Chun-Wu Yin","doi":"10.1016/j.engappai.2024.109734","DOIUrl":"10.1016/j.engappai.2024.109734","url":null,"abstract":"<div><div>The prescribed performance control method (PPCM) is commonly employed to ensure the guaranteed performance control of non-linear systems. However, traditional approaches suffer from certain drawbacks, such as the dependence of parameter settings for the performance constraint function on the initial tracking error value and the inability to specify the convergence time of tracking error according to engineering requirements. This paper focuses on designing a fault tolerant control strategy with prescribed convergence time and prescribed transient performance for uncertain systems, considering parameter perturbance, actuator faults, and unknown initial states. Firstly, we introduce an error conversion function that transforms the tracking error with any initial value into a new error variable starting from zero. This resolves the issue of depending on the initial value of tracking error in setting parameters for the performance constraint function in prescribed performance control methods. Subsequently, we derive a novel Lyapunov stability criterion for predefined time (PDT) convergence and design a fault-tolerant control strategy using backstepping control method while ensuring prescribed convergence time and prescribed performance. In this approach, we propose a new online reinforcement learning intelligent algorithm to estimate compound interference caused by actuator faults, control saturation constraint increment, system parameter perturbation, and external interference. The theoretical proof establishes predefined time convergence of the closed-loop system. Finally, numerical simulations are conducted on industrial robots with actuator faults to validate the effectiveness of our designed control strategy.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"140 ","pages":"Article 109734"},"PeriodicalIF":7.5,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142744013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Benchmarking neural radiance fields for autonomous robots: An overview 自主机器人神经辐射场的基准测试：综述

IF 7.5 2区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

Engineering Applications of Artificial Intelligence

Pub Date : 2024-11-29 DOI: 10.1016/j.engappai.2024.109685

Yuhang Ming , Xingrui Yang , Weihan Wang , Zheng Chen , Jinglun Feng , Yifan Xing , Guofeng Zhang

Neural Radiance Field (NeRF) has emerged as a powerful paradigm for scene representation, offering high-fidelity renderings and reconstructions from a set of sparse and unstructured sensor data. In the context of autonomous robotics, where perception and understanding of the environment are pivotal, NeRF holds immense promise for improving performance. However, few survey has discussed such a potential. To fill this gap, we have collected over 200 papers since the publication of original NeRF in 2020 and present a thorough analysis of how NeRF can be used to enhance the capabilities of autonomous robots. We especially focus on the perception, localization and navigation, and decision-making modules of autonomous robots and delve into tasks crucial for autonomous operation, including 3-dimensional reconstruction, segmentation, pose estimation, simultaneous localization and mapping, navigation and planning, and interaction. Our survey meticulously benchmarks existing NeRF-based methods, comparing their reported performance, and providing insights into their strengths and limitations. Moreover, we target the existing challenges of applying NeRF in autonomous robots, including real-time processing, sparse input views, and explore promising avenues for future research and development in this domain. We especially discuss potential of integrating advanced deep learning techniques like 3-dimensional Gaussian splatting, large language models, and generative artificial intelligence. This survey serves as a roadmap for researchers seeking to leverage NeRF to empower autonomous robots, paving the way for innovative solutions that can navigate and interact seamlessly in complex environments.

神经辐射场（NeRF）已经成为场景表示的强大范例，从一组稀疏和非结构化的传感器数据中提供高保真的渲染和重建。在自主机器人的背景下，对环境的感知和理解是至关重要的，NeRF在提高性能方面有着巨大的希望。然而，很少有调查讨论过这种可能性。为了填补这一空白，自2020年原始NeRF出版以来，我们收集了200多篇论文，并对NeRF如何用于增强自主机器人的能力进行了全面分析。我们特别关注自主机器人的感知、定位和导航以及决策模块，并深入研究自主操作的关键任务，包括三维重建、分割、姿态估计、同步定位和映射、导航和规划以及交互。我们的调查对现有的基于nerf的方法进行了细致的基准测试，比较了它们的报告性能，并深入了解了它们的优势和局限性。此外，我们针对自主机器人中应用NeRF的现有挑战，包括实时处理，稀疏输入视图，并探索该领域未来研究和开发的有希望的途径。我们特别讨论了集成先进深度学习技术的潜力，如三维高斯飞溅、大型语言模型和生成式人工智能。这项调查为研究人员寻求利用NeRF来增强自主机器人的能力提供了路线图，为在复杂环境中无缝导航和交互的创新解决方案铺平了道路。

{"title":"Benchmarking neural radiance fields for autonomous robots: An overview","authors":"Yuhang Ming , Xingrui Yang , Weihan Wang , Zheng Chen , Jinglun Feng , Yifan Xing , Guofeng Zhang","doi":"10.1016/j.engappai.2024.109685","DOIUrl":"10.1016/j.engappai.2024.109685","url":null,"abstract":"<div><div>Neural Radiance Field (NeRF) has emerged as a powerful paradigm for scene representation, offering high-fidelity renderings and reconstructions from a set of sparse and unstructured sensor data. In the context of autonomous robotics, where perception and understanding of the environment are pivotal, NeRF holds immense promise for improving performance. However, few survey has discussed such a potential. To fill this gap, we have collected over 200 papers since the publication of original NeRF in 2020 and present a thorough analysis of how NeRF can be used to enhance the capabilities of autonomous robots. We especially focus on the perception, localization and navigation, and decision-making modules of autonomous robots and delve into tasks crucial for autonomous operation, including 3-dimensional reconstruction, segmentation, pose estimation, simultaneous localization and mapping, navigation and planning, and interaction. Our survey meticulously benchmarks existing NeRF-based methods, comparing their reported performance, and providing insights into their strengths and limitations. Moreover, we target the existing challenges of applying NeRF in autonomous robots, including real-time processing, sparse input views, and explore promising avenues for future research and development in this domain. We especially discuss potential of integrating advanced deep learning techniques like 3-dimensional Gaussian splatting, large language models, and generative artificial intelligence. This survey serves as a roadmap for researchers seeking to leverage NeRF to empower autonomous robots, paving the way for innovative solutions that can navigate and interact seamlessly in complex environments.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"140 ","pages":"Article 109685"},"PeriodicalIF":7.5,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142743972","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0