首页 > 最新文献

Engineering Applications of Artificial Intelligence最新文献

英文 中文
A generative design method of airfoil based on conditional variational autoencoder 基于条件变异自动编码器的机翼生成设计方法
IF 7.5 2区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-10-23 DOI: 10.1016/j.engappai.2024.109461
Xu Wang , Weiqi Qian , Tun Zhao , Hai Chen , Lei He , Haisheng Sun , Yuan Tian
The challenges in multi-objective and multi-dimensional optimization design of airfoils, marked by prolonged optimization cycles and low accuracy, call for an efficient solution to expedite airfoil design. This study presents an innovative airfoil generative design model based on a conditional variational autoencoder (CVAE). Initially, to overcome the limitation of insufficient training data, the model leverages the variational autoencoder (VAE) to learn the spatial distribution of University of Illinois at Urbana-Champaign (UIUC) airfoils, enabling the generation of a diverse set of airfoils with similar distributions. Subsequently, two CVAE-based airfoil generation models, the airfoil freedom design model and the airfoil precision design model, are proposed, which can realize diverse airfoil design under different conditions, such as shape and aerodynamic conditions. Furthermore, two measurements of roughness and diversity are introduced to evaluate the quality of the generated airfoils. The impact of different conditions and network parameters on the model’s generation performance is thoroughly analyzed. Results indicate that our proposed model achieves a 65% lower error compared to physics-guided conditional Wasserstein generative adversarial networks (PG-cWGAN) when generating airfoils that satisfy a specific lift coefficient and a 99.99% lower error compared to airfoil pressure distributions generative adversarial networks (Airfoil-Cp-GAN) when generating airfoils that satisfy specific pressure distributions. This method introduces a more creative and accurate approach for aircraft designers in the realm of airfoil design. The code used for this paper is available at https://github.com/liujun39/airfoilvae.
机翼的多目标和多维优化设计面临着优化周期长和精度低的挑战,因此需要一种高效的解决方案来加快机翼设计。本研究提出了一种基于条件变异自动编码器(CVAE)的创新机翼生成设计模型。首先,为了克服训练数据不足的限制,该模型利用变异自动编码器(VAE)学习伊利诺伊大学香槟分校(UIUC)机翼的空间分布,从而生成具有相似分布的各种机翼。随后,提出了两个基于 CVAE 的机翼生成模型,即机翼自由度设计模型和机翼精度设计模型,可在形状和气动条件等不同条件下实现多样化的机翼设计。此外,还引入了粗糙度和多样性两种测量方法来评价生成机翼的质量。深入分析了不同条件和网络参数对模型生成性能的影响。结果表明,在生成满足特定升力系数的机翼时,我们提出的模型与物理引导条件瓦瑟斯坦生成式对抗网络(PG-cWGAN)相比,误差降低了 65%;在生成满足特定压力分布的机翼时,我们提出的模型与机翼压力分布生成式对抗网络(Airfoil-CP-GAN)相比,误差降低了 99.99%。这种方法为飞机设计师在机翼设计领域引入了一种更具创造性和准确性的方法。本文所用代码可在 https://github.com/liujun39/airfoilvae 网站上查阅。
{"title":"A generative design method of airfoil based on conditional variational autoencoder","authors":"Xu Wang ,&nbsp;Weiqi Qian ,&nbsp;Tun Zhao ,&nbsp;Hai Chen ,&nbsp;Lei He ,&nbsp;Haisheng Sun ,&nbsp;Yuan Tian","doi":"10.1016/j.engappai.2024.109461","DOIUrl":"10.1016/j.engappai.2024.109461","url":null,"abstract":"<div><div>The challenges in multi-objective and multi-dimensional optimization design of airfoils, marked by prolonged optimization cycles and low accuracy, call for an efficient solution to expedite airfoil design. This study presents an innovative airfoil generative design model based on a conditional variational autoencoder (CVAE). Initially, to overcome the limitation of insufficient training data, the model leverages the variational autoencoder (VAE) to learn the spatial distribution of University of Illinois at Urbana-Champaign (UIUC) airfoils, enabling the generation of a diverse set of airfoils with similar distributions. Subsequently, two CVAE-based airfoil generation models, the airfoil freedom design model and the airfoil precision design model, are proposed, which can realize diverse airfoil design under different conditions, such as shape and aerodynamic conditions. Furthermore, two measurements of roughness and diversity are introduced to evaluate the quality of the generated airfoils. The impact of different conditions and network parameters on the model’s generation performance is thoroughly analyzed. Results indicate that our proposed model achieves a 65% lower error compared to physics-guided conditional Wasserstein generative adversarial networks (PG-cWGAN) when generating airfoils that satisfy a specific lift coefficient and a 99.99% lower error compared to airfoil pressure distributions generative adversarial networks (Airfoil-Cp-GAN) when generating airfoils that satisfy specific pressure distributions. This method introduces a more creative and accurate approach for aircraft designers in the realm of airfoil design. The code used for this paper is available at <span><span>https://github.com/liujun39/airfoilvae</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":7.5,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533398","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
Optimization of underground mining production layouts considering geological uncertainty using deep reinforcement learning 利用深度强化学习优化考虑地质不确定性的地下采矿生产布局
IF 7.5 2区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-10-23 DOI: 10.1016/j.engappai.2024.109493
Roberto Noriega, Jeff Boisvert
Mineral extraction plays a key role in the global raw materials supply chain, however the exhaustion of shallow deposits and typical scarcity of sampled data during exploration activities creates challenges in mine planning and design, where decision-making is highly sensitive to uncertainty in geology and mineral grade prediction. Geostatistical techniques are commonly used to generate a set of equiprobable simulated numerical models to capture these uncertainties, however incorporating these simulated models within a mine planning and design framework remains a major challenge. The purpose of this paper is to propose a novel approach to decision-making in underground mine design that can use information from an ensemble of numerical realizations of a mineral resource to improve the financial performance of the asset. A deep reinforcement learning (DRL) framework, using the proximal policy optimization (PPO) algorithm, is developed for the design of underground mining production level layouts. A case study is presented using a gold mineral resource characterized by an ensemble of 100 numerical realizations to verify the advantages of the proposed method, considering a baseline consisting of an industry standard automated design method. The DRL approach achieved an 8.3% higher expected profit, a 3.4% more gold mined than the baseline, and has the added functionality of considering uncertainty in mineral grades.
矿物开采在全球原材料供应链中发挥着关键作用,然而浅层矿藏的枯竭和勘探活动中采样数据的典型匮乏给矿山规划和设计带来了挑战,决策对地质和矿物品位预测的不确定性高度敏感。地质统计技术通常用于生成一组可等价模拟的数值模型,以捕捉这些不确定性,但将这些模拟模型纳入矿山规划和设计框架仍是一项重大挑战。本文旨在提出一种新颖的地下矿山设计决策方法,该方法可利用矿产资源数值现实的集合信息来提高资产的财务绩效。本文开发了一种深度强化学习(DRL)框架,使用近端策略优化(PPO)算法,用于设计地下采矿生产水平布局。考虑到基线包括行业标准的自动设计方法,本报告介绍了一个案例研究,该案例研究使用了以 100 个数值实现集合为特征的黄金矿产资源,以验证所提议方法的优势。与基线相比,DRL 方法的预期利润提高了 8.3%,黄金开采量增加了 3.4%,并增加了考虑矿物品位不确定性的功能。
{"title":"Optimization of underground mining production layouts considering geological uncertainty using deep reinforcement learning","authors":"Roberto Noriega,&nbsp;Jeff Boisvert","doi":"10.1016/j.engappai.2024.109493","DOIUrl":"10.1016/j.engappai.2024.109493","url":null,"abstract":"<div><div>Mineral extraction plays a key role in the global raw materials supply chain, however the exhaustion of shallow deposits and typical scarcity of sampled data during exploration activities creates challenges in mine planning and design, where decision-making is highly sensitive to uncertainty in geology and mineral grade prediction. Geostatistical techniques are commonly used to generate a set of equiprobable simulated numerical models to capture these uncertainties, however incorporating these simulated models within a mine planning and design framework remains a major challenge. The purpose of this paper is to propose a novel approach to decision-making in underground mine design that can use information from an ensemble of numerical realizations of a mineral resource to improve the financial performance of the asset. A deep reinforcement learning (DRL) framework, using the proximal policy optimization (PPO) algorithm, is developed for the design of underground mining production level layouts. A case study is presented using a gold mineral resource characterized by an ensemble of 100 numerical realizations to verify the advantages of the proposed method, considering a baseline consisting of an industry standard automated design method. The DRL approach achieved an 8.3% higher expected profit, a 3.4% more gold mined than the baseline, and has the added functionality of considering uncertainty in mineral grades.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":7.5,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533287","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
Involution fused convolution for classifying eye-tracking patterns of children with Autism Spectrum Disorder 用于自闭症谱系障碍儿童眼动追踪模式分类的卷积融合卷积
IF 7.5 2区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-10-23 DOI: 10.1016/j.engappai.2024.109475
Md. Farhadul Islam , Meem Arafat Manab , Joyanta Jyoti Mondal , Sarah Zabeen , Fardin Bin Rahman , Md. Zahidul Hasan , Farig Sadeque , Jannatun Noor
Autism Spectrum Disorder (ASD) is a neurological condition that is challenging to diagnose. Numerous studies demonstrate that children diagnosed with autism struggle with maintaining attention spans and have less focused vision. The eye-tracking technology has drawn special attention in the context of ASD since anomalies in gaze have long been acknowledged as a defining feature of autism. Deep Learning (DL) approaches coupled with eye-tracking sensors are exploiting additional capabilities to advance the diagnostic and its applications. DL architectures like convolution have been dominating this domain. However, convolutions alone may be insufficient to capture the important spatial information in eye-tracking patterns, as these patterns are more likely to be localized. The dynamic kernel-based process known as involutions can improve the classification efficiency. In this study, we utilize two image-processing operations to see how these processes learn eye-tracking patterns. Since these patterns are primarily based on spatial information, we employ a hybrid of involution and convolution. Our study shows that adding a few involution layers reduces size and computational cost while enhancing location-specific capabilities, maintaining performance comparable to pure convolutional models. However, excessive involution layers lead to weaker performance. For comparisons, we experiment with two datasets and a combined version of both in ablation studies. Our proposed model, featuring three involution layers and three convolution layers, achieved 99.43% accuracy on the first dataset and 96.78% on the second, with a size of only 1.36 megabytes. These results showcase the effectiveness of combining involution and convolution layers which outperforms previous literature.
自闭症谱系障碍(ASD)是一种难以诊断的神经系统疾病。大量研究表明,被诊断为自闭症的儿童很难保持注意力集中,视力也不那么集中。眼球跟踪技术在 ASD 方面引起了特别关注,因为凝视异常早已被公认为自闭症的一个特征。深度学习(DL)方法与眼动跟踪传感器相结合,正在利用更多的功能来推进诊断及其应用。卷积等深度学习架构一直在这一领域占据主导地位。然而,仅靠卷积可能不足以捕捉眼动追踪模式中的重要空间信息,因为这些模式更有可能是局部的。基于动态核的渐开过程可以提高分类效率。在本研究中,我们利用两种图像处理操作来了解这些过程是如何学习眼动追踪模式的。由于这些模式主要基于空间信息,我们采用了内卷和卷积的混合方法。我们的研究表明,增加一些卷积层可以减少体积和计算成本,同时增强特定位置的能力,保持与纯卷积模型相当的性能。然而,过多的卷积层会导致性能减弱。为了进行比较,我们在消融研究中使用了两个数据集和两个数据集的组合版本。我们提出的模型具有三个卷积层和三个卷积层,在第一个数据集上的准确率达到 99.43%,在第二个数据集上的准确率达到 96.78%,而数据集的大小仅为 1.36 兆字节。这些结果展示了结合卷积层和卷积层的有效性,优于之前的文献。
{"title":"Involution fused convolution for classifying eye-tracking patterns of children with Autism Spectrum Disorder","authors":"Md. Farhadul Islam ,&nbsp;Meem Arafat Manab ,&nbsp;Joyanta Jyoti Mondal ,&nbsp;Sarah Zabeen ,&nbsp;Fardin Bin Rahman ,&nbsp;Md. Zahidul Hasan ,&nbsp;Farig Sadeque ,&nbsp;Jannatun Noor","doi":"10.1016/j.engappai.2024.109475","DOIUrl":"10.1016/j.engappai.2024.109475","url":null,"abstract":"<div><div>Autism Spectrum Disorder (ASD) is a neurological condition that is challenging to diagnose. Numerous studies demonstrate that children diagnosed with autism struggle with maintaining attention spans and have less focused vision. The eye-tracking technology has drawn special attention in the context of ASD since anomalies in gaze have long been acknowledged as a defining feature of autism. Deep Learning (DL) approaches coupled with eye-tracking sensors are exploiting additional capabilities to advance the diagnostic and its applications. DL architectures like convolution have been dominating this domain. However, convolutions alone may be insufficient to capture the important spatial information in eye-tracking patterns, as these patterns are more likely to be localized. The dynamic kernel-based process known as involutions can improve the classification efficiency. In this study, we utilize two image-processing operations to see how these processes learn eye-tracking patterns. Since these patterns are primarily based on spatial information, we employ a hybrid of involution and convolution. Our study shows that adding a few involution layers reduces size and computational cost while enhancing location-specific capabilities, maintaining performance comparable to pure convolutional models. However, excessive involution layers lead to weaker performance. For comparisons, we experiment with two datasets and a combined version of both in ablation studies. Our proposed model, featuring three involution layers and three convolution layers, achieved 99.43% accuracy on the first dataset and 96.78% on the second, with a size of only 1.36 megabytes. These results showcase the effectiveness of combining involution and convolution layers which outperforms previous literature.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":7.5,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533281","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
A novel multi-criteria decision making method to evaluate green innovation ecosystem resilience 评估绿色创新生态系统复原力的新型多标准决策方法
IF 7.5 2区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-10-23 DOI: 10.1016/j.engappai.2024.109528
Jiafu Su , Hongyu Liu , Yijun Chen , Na Zhang , Junjun Li
Green innovation ecosystem resilience evaluation is crucial for ensuring sustainable development in dynamic environments. By comprehensively assessing resilience, it helps identify risks and facilitate effective responses, thus promoting sustainable development. To effectively evaluate the resilience of green innovation ecosystems, this paper proposes a model based on the interval-valued intuitionistic fuzzy multi-criteria decision-making (MCDM) method, designed to support decision-makers (DMs) in resilience evaluation. In this model, we improve the Criteria Importance Through Intercriteria Correlation (CRITIC) method by introducing Spearman's correlation coefficient to more accurately determine the objective weights of various indicators based on their interrelationships. Furthermore, we propose an Interval-Valued Intuitionistic Fuzzy Hybrid Average Aggregation (IVIFHAA) operator, which considers both the subjective and objective weight order for aggregating expert evaluation results. Additionally, a scoring function is introduced to generate ranked evaluation results. We also establish a resilience evaluation criteria system covering interconnectivity, sustainability, and diversity within green innovation ecosystems to assist DMs in resilience evaluation. Finally, to validate this method, we apply it to assess the resilience of regional green innovation ecosystems and compare it with other methods. The results demonstrate that the improved operator effectively reduces information loss and improves evaluation efficiency, while the improved CRITIC method handles outliers during the evaluation process.
绿色创新生态系统复原力评估对于确保动态环境中的可持续发展至关重要。通过全面评估复原力,有助于识别风险并有效应对,从而促进可持续发展。为有效评估绿色创新生态系统的恢复力,本文提出了一种基于区间值直观模糊多标准决策(MCDM)方法的模型,旨在支持决策者(DMs)进行恢复力评估。在该模型中,我们通过引入斯皮尔曼相关系数来改进 "通过标准间相关性确定标准重要性"(CRITIC)方法,从而根据各种指标的相互关系更准确地确定其客观权重。此外,我们还提出了一种区间值直觉模糊混合平均聚合(IVIFHAA)算子,它同时考虑了主观和客观权重顺序,用于聚合专家评价结果。此外,我们还引入了一个评分函数来生成排序评价结果。我们还建立了一个复原力评价标准体系,涵盖绿色创新生态系统中的互联性、可持续性和多样性,以协助管理部门进行复原力评价。最后,为了验证该方法的有效性,我们将其用于评估区域绿色创新生态系统的复原力,并与其他方法进行比较。结果表明,改进的算子能有效减少信息丢失,提高评估效率,而改进的 CRITIC 方法能在评估过程中处理异常值。
{"title":"A novel multi-criteria decision making method to evaluate green innovation ecosystem resilience","authors":"Jiafu Su ,&nbsp;Hongyu Liu ,&nbsp;Yijun Chen ,&nbsp;Na Zhang ,&nbsp;Junjun Li","doi":"10.1016/j.engappai.2024.109528","DOIUrl":"10.1016/j.engappai.2024.109528","url":null,"abstract":"<div><div>Green innovation ecosystem resilience evaluation is crucial for ensuring sustainable development in dynamic environments. By comprehensively assessing resilience, it helps identify risks and facilitate effective responses, thus promoting sustainable development. To effectively evaluate the resilience of green innovation ecosystems, this paper proposes a model based on the interval-valued intuitionistic fuzzy multi-criteria decision-making (MCDM) method, designed to support decision-makers (DMs) in resilience evaluation. In this model, we improve the Criteria Importance Through Intercriteria Correlation (CRITIC) method by introducing Spearman's correlation coefficient to more accurately determine the objective weights of various indicators based on their interrelationships. Furthermore, we propose an Interval-Valued Intuitionistic Fuzzy Hybrid Average Aggregation (IVIFHAA) operator, which considers both the subjective and objective weight order for aggregating expert evaluation results. Additionally, a scoring function is introduced to generate ranked evaluation results. We also establish a resilience evaluation criteria system covering interconnectivity, sustainability, and diversity within green innovation ecosystems to assist DMs in resilience evaluation. Finally, to validate this method, we apply it to assess the resilience of regional green innovation ecosystems and compare it with other methods. The results demonstrate that the improved operator effectively reduces information loss and improves evaluation efficiency, while the improved CRITIC method handles outliers during the evaluation process.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":7.5,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533286","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
Designing an adaptive learning framework for predicting drug-target affinity using reinforcement learning and graph neural networks 利用强化学习和图神经网络设计预测药物靶点亲和力的自适应学习框架
IF 7.5 2区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-10-23 DOI: 10.1016/j.engappai.2024.109472
Jun Ma , Zhili Zhao , Yunwu Liu , Tongfeng Li , Ruisheng Zhang
In the field of biomedical engineering, predicting Drug-Target Affinities (DTA) is crucial. However, current affinity prediction models are predominantly manually designed, which is a complex, time-consuming process that may not effectively accommodate the diversity and complexity of datasets. To address this challenge, we propose an adaptive learning framework for predicting drug-target affinity, called Adaptive-DTA, which integrates reinforcement learning with graph neural networks to automate the design of affinity prediction models. Adaptive-DTA defines the architecture search space using directed acyclic graphs and employs an reinforcement learning algorithm to guide the architecture search, optimizing parameters based on the entropy of sampled architectures and model performance metrics. Additionally, we enhance efficiency with a two-stage training and validation strategy, incorporating low-fidelity and high-fidelity evaluations. Our framework not only alleviates the challenges associated with manual model design but also significantly improves model performance and generalization. To evaluate the performance of our method, we conducted extensive experiments on DTA benchmark datasets and compared the results with nine state-of-the-art methods. The experimental outcomes demonstrate that our proposed framework outperforms these methods, exhibiting outstanding performance in predicting drug-target affinities. Our innovative approach streamlines the design of affinity prediction model, reduces reliance on manual crafting, and enhances model generalization. Its ability to automatically optimize network architectures represents a major step forward in the automation of computational drug discovery processes.
在生物医学工程领域,预测药物-靶点亲和力(DTA)至关重要。然而,目前的亲和力预测模型主要是人工设计的,这是一个复杂、耗时的过程,可能无法有效地适应数据集的多样性和复杂性。为了应对这一挑战,我们提出了一种用于预测药物-靶点亲和力的自适应学习框架,称为自适应-DTA,它将强化学习与图神经网络整合在一起,实现了亲和力预测模型设计的自动化。Adaptive-DTA 使用有向无环图定义架构搜索空间,并采用强化学习算法指导架构搜索,根据采样架构的熵和模型性能指标优化参数。此外,我们还采用两阶段训练和验证策略,结合低保真和高保真评估,提高了效率。我们的框架不仅减轻了手动模型设计所带来的挑战,还显著提高了模型性能和泛化能力。为了评估我们方法的性能,我们在 DTA 基准数据集上进行了广泛的实验,并将实验结果与九种最先进的方法进行了比较。实验结果表明,我们提出的框架优于这些方法,在预测药物靶点亲和力方面表现突出。我们的创新方法简化了亲和力预测模型的设计,减少了对手工制作的依赖,并增强了模型的泛化能力。它自动优化网络架构的能力代表了计算药物发现过程自动化的一大进步。
{"title":"Designing an adaptive learning framework for predicting drug-target affinity using reinforcement learning and graph neural networks","authors":"Jun Ma ,&nbsp;Zhili Zhao ,&nbsp;Yunwu Liu ,&nbsp;Tongfeng Li ,&nbsp;Ruisheng Zhang","doi":"10.1016/j.engappai.2024.109472","DOIUrl":"10.1016/j.engappai.2024.109472","url":null,"abstract":"<div><div>In the field of biomedical engineering, predicting Drug-Target Affinities (DTA) is crucial. However, current affinity prediction models are predominantly manually designed, which is a complex, time-consuming process that may not effectively accommodate the diversity and complexity of datasets. To address this challenge, we propose an adaptive learning framework for predicting drug-target affinity, called Adaptive-DTA, which integrates reinforcement learning with graph neural networks to automate the design of affinity prediction models. Adaptive-DTA defines the architecture search space using directed acyclic graphs and employs an reinforcement learning algorithm to guide the architecture search, optimizing parameters based on the entropy of sampled architectures and model performance metrics. Additionally, we enhance efficiency with a two-stage training and validation strategy, incorporating low-fidelity and high-fidelity evaluations. Our framework not only alleviates the challenges associated with manual model design but also significantly improves model performance and generalization. To evaluate the performance of our method, we conducted extensive experiments on DTA benchmark datasets and compared the results with nine state-of-the-art methods. The experimental outcomes demonstrate that our proposed framework outperforms these methods, exhibiting outstanding performance in predicting drug-target affinities. Our innovative approach streamlines the design of affinity prediction model, reduces reliance on manual crafting, and enhances model generalization. Its ability to automatically optimize network architectures represents a major step forward in the automation of computational drug discovery processes.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":7.5,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533393","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
Dynamically Adaptive Deformable Feature Fusion for multi-scale character detection in ancient documents 动态自适应可变形特征融合用于古文献中的多尺度字符检测
IF 7.5 2区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-10-23 DOI: 10.1016/j.engappai.2024.109458
Mauricio Bermudez-Gonzalez , Amin Jalali , Minho Lee
Robust character detection of various sizes in ancient East-Asian handwritten documents is essential for accurate classification and translation. While prior studies have addressed various challenges associated with the writing styles and page layouts of historical documents, they struggle to detect small-sized characters, especially with an area below 32 square units due to their limited presence in the data corpus. Furthermore, the physical degradation, presence of artifacts, and inconsistencies in text density complicate character detection of historical documents across multiple scales. In this study, we propose a novel multi-scale character detection named Dynamically Adaptive Deformable Feature Fusion (DAF). This approach leverages deformable convolutions to improve feature extraction for the complex and irregular shapes found in ancient East-Asian manuscripts. We also present an innovative Adaptive Weight Module that dynamically adjusts top-down features across different levels by utilizing trainable weights. This enhances the detection of multi-scale characters and effectively identifies small-sized characters within documents. Further, we contribute to existing research by proposing a set of detection metrics, specifically designed to evaluate both general and scale-specific detection scenarios. Extensive experiments conducted on several datasets of ancient handwritten documents including the Nancho dataset, Multiple Tripitaka in Han dataset (MTHv2), and Kuzushiji dataset demonstrate the superior performance of our proposed DAF framework over existing multi-scale detection methods.
对古代东亚手写文件中各种大小的字符进行可靠检测,对于准确分类和翻译至关重要。虽然之前的研究已经解决了与历史文献的书写风格和页面布局相关的各种难题,但由于数据语料库中的字符数量有限,这些研究在检测小尺寸字符,尤其是面积低于 32 平方英寸的字符方面仍存在困难。此外,物理退化、人工痕迹的存在以及文本密度的不一致性也使历史文献的多尺度字符检测变得更加复杂。在这项研究中,我们提出了一种名为动态自适应变形特征融合(DAF)的新型多尺度字符检测方法。这种方法利用可变形卷积来改进对古代东亚手稿中复杂和不规则形状的特征提取。我们还提出了一种创新的自适应权重模块,利用可训练的权重动态调整不同层次的自上而下特征。这增强了多尺度字符的检测能力,并能有效识别文档中的小尺寸字符。此外,我们还提出了一套检测指标,专门用于评估一般和特定尺度的检测情况,为现有研究做出了贡献。我们在多个古代手写文档数据集(包括 Nancho 数据集、Multiple Tripitaka in Han 数据集 (MTHv2) 和 Kuzushiji 数据集)上进行了广泛的实验,证明我们提出的 DAF 框架的性能优于现有的多尺度检测方法。
{"title":"Dynamically Adaptive Deformable Feature Fusion for multi-scale character detection in ancient documents","authors":"Mauricio Bermudez-Gonzalez ,&nbsp;Amin Jalali ,&nbsp;Minho Lee","doi":"10.1016/j.engappai.2024.109458","DOIUrl":"10.1016/j.engappai.2024.109458","url":null,"abstract":"<div><div>Robust character detection of various sizes in ancient East-Asian handwritten documents is essential for accurate classification and translation. While prior studies have addressed various challenges associated with the writing styles and page layouts of historical documents, they struggle to detect small-sized characters, especially with an area below 32 square units due to their limited presence in the data corpus. Furthermore, the physical degradation, presence of artifacts, and inconsistencies in text density complicate character detection of historical documents across multiple scales. In this study, we propose a novel multi-scale character detection named Dynamically Adaptive Deformable Feature Fusion (DAF). This approach leverages deformable convolutions to improve feature extraction for the complex and irregular shapes found in ancient East-Asian manuscripts. We also present an innovative Adaptive Weight Module that dynamically adjusts top-down features across different levels by utilizing trainable weights. This enhances the detection of multi-scale characters and effectively identifies small-sized characters within documents. Further, we contribute to existing research by proposing a set of detection metrics, specifically designed to evaluate both general and scale-specific detection scenarios. Extensive experiments conducted on several datasets of ancient handwritten documents including the Nancho dataset, Multiple Tripitaka in Han dataset (MTHv2), and Kuzushiji dataset demonstrate the superior performance of our proposed DAF framework over existing multi-scale detection methods.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":7.5,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533395","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
A novel time-delay multivariable grey model and its application in predicting oil production 新型时延多变量灰色模型及其在预测石油产量中的应用
IF 7.5 2区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-10-23 DOI: 10.1016/j.engappai.2024.109505
Huiming Duan , Guan Wang , Yuxin Song , Hongli Chen
An accurate prediction of oil production can provide a scientific basis for planning the production of the Qinghai oilfield and help in rationally arranging resources. To address the time-delay of related factors in the oil production system and how this problem affects oil production, this paper classifies the different degrees of time-delay of related factors and establishes a time-delay multivariable grey model with multiple parameters. This model not only reflects the characteristics of a Logistic model with strong historical recurrence ability and high prediction accuracy in the short and medium terms but also compensates for the defects of existing grey models that do not consider the time-delay of related factors; this is a new idea for grey modelling. Moreover, the parameter estimation of the new model is obtained via the least squares technique, the time response of the new model is obtained via a mathematical method, and the modelling steps of the new model are also obtained. Finally, the new model is applied to the prediction of production of the Qinghai oilfield in China, the effectiveness of the model is analysed according to two different correlation sequences, and six types of the same modelling objects are tested. Results of two types of twelve experiments each show that the total mean absolute percentage error is less than 5%, the lowest is 1.2580%, and the highest is only 4.0087%. This shows that the new model has a good effect and results of six technical indicators show that the new model is better than the other five multivariable grey models.
准确预测石油产量可以为青海油田的生产规划提供科学依据,有助于合理安排资源。针对采油系统中相关因素的时滞性以及这一问题对石油产量的影响,本文对相关因素的不同时滞程度进行了分类,建立了一个多参数的时滞性多变量灰色模型。该模型既体现了 Logistic 模型历史重现能力强、中短期预测精度高的特点,又弥补了现有灰色模型不考虑相关因素时滞性的缺陷,是灰色建模的一个新思路。此外,新模型的参数估计是通过最小二乘法技术获得的,新模型的时间响应是通过数学方法获得的,新模型的建模步骤也是通过数学方法获得的。最后,将新模型应用于中国青海油田的产量预测,根据两种不同的相关序列分析了模型的有效性,并对六种相同的建模对象进行了测试。两种类型各十二次实验结果表明,总平均绝对百分误差小于 5%,最低为 1.2580%,最高仅为 4.0087%。这表明新模型具有良好的效果,六项技术指标的结果表明,新模型优于其他五种多变量灰色模型。
{"title":"A novel time-delay multivariable grey model and its application in predicting oil production","authors":"Huiming Duan ,&nbsp;Guan Wang ,&nbsp;Yuxin Song ,&nbsp;Hongli Chen","doi":"10.1016/j.engappai.2024.109505","DOIUrl":"10.1016/j.engappai.2024.109505","url":null,"abstract":"<div><div>An accurate prediction of oil production can provide a scientific basis for planning the production of the Qinghai oilfield and help in rationally arranging resources. To address the time-delay of related factors in the oil production system and how this problem affects oil production, this paper classifies the different degrees of time-delay of related factors and establishes a time-delay multivariable grey model with multiple parameters. This model not only reflects the characteristics of a Logistic model with strong historical recurrence ability and high prediction accuracy in the short and medium terms but also compensates for the defects of existing grey models that do not consider the time-delay of related factors; this is a new idea for grey modelling. Moreover, the parameter estimation of the new model is obtained via the least squares technique, the time response of the new model is obtained via a mathematical method, and the modelling steps of the new model are also obtained. Finally, the new model is applied to the prediction of production of the Qinghai oilfield in China, the effectiveness of the model is analysed according to two different correlation sequences, and six types of the same modelling objects are tested. Results of two types of twelve experiments each show that the total mean absolute percentage error is less than 5%, the lowest is 1.2580%, and the highest is only 4.0087%. This shows that the new model has a good effect and results of six technical indicators show that the new model is better than the other five multivariable grey models.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":7.5,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533396","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
Enhanced Cross Layer Refinement Network for robust lane detection across diverse lighting and road conditions 增强型跨层细化网络可在各种照明和路况条件下实现强大的车道检测功能
IF 7.5 2区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-10-23 DOI: 10.1016/j.engappai.2024.109473
Weilong Dai , Zuoyong Li , Xiaofeng Xu , Xiaobo Chen , Huanqiang Zeng , Rong Hu
With the rapid development of autonomous driving technology, lane detection, a key component of intelligent vehicle systems, is crucial for ensuring road safety and efficient vehicle navigation. In this paper, a new lane detection method is proposed to address the problem of degraded performance of existing lane detection methods when dealing with complex road environments. The proposed method evolves from the original Cross Layer Refinement Network (CLRNet) by incorporating two of our carefully designed core components: the Global Feature Optimizer (GFO) and the Adaptive Lane Geometry Aggregator (ALGA). The GFO is a multi-scale attention mechanism that mimics the human visual focusing ability, effectively filtering out unimportant information and focusing on the image regions most relevant to the task. The ALGA is a shape feature-aware aggregation module that utilizes the shape prior of lanes to enhance the correlation of anchor points in an image, better fusing global and local information. By integrating both components into CLRNet, an enhanced version called Enhanced CLRNet (E-CLRNet) is presented, which exhibits higher performance stability in complex roadway scenarios. Experiments on the CULane dataset reveal that E-CLRNet demonstrates superior performance stability over the original CLRNet in complex scenarios, including curves, shadows, missing lines, and dazzling light conditions. In particular, in the curves, the F1 score of E-CLRNet is improved by almost 3% over the original CLRNet. This study not only improves the accuracy and performance stability of lane detection but also provides a new solution for the application of autonomous driving technology in complex environments, which promotes the development of intelligent vehicle systems.
随着自动驾驶技术的快速发展,车道检测作为智能车辆系统的关键组成部分,对于确保道路安全和车辆高效导航至关重要。本文提出了一种新的车道检测方法,以解决现有车道检测方法在处理复杂道路环境时性能下降的问题。所提出的方法从最初的跨层细化网络(CLRNet)演化而来,融入了我们精心设计的两个核心组件:全局特征优化器(GFO)和自适应车道几何聚合器(ALGA)。GFO 是一种多尺度注意力机制,可模仿人类的视觉聚焦能力,有效过滤掉不重要的信息,将注意力集中在与任务最相关的图像区域。ALGA 是一个形状特征感知聚合模块,它利用车道的形状先验来增强图像中锚点的相关性,从而更好地融合全局和局部信息。通过将这两个组件集成到 CLRNet 中,一个名为增强型 CLRNet(E-CLRNet)的增强版本问世了,它在复杂的道路场景中表现出更高的性能稳定性。在 CULane 数据集上进行的实验表明,E-CLRNet 在复杂场景(包括弯道、阴影、缺线和眩光条件)中的性能稳定性优于原始 CLRNet。特别是在曲线中,E-CLRNet 的 F1 分数比原始 CLRNet 提高了近 3%。这项研究不仅提高了车道检测的准确性和性能稳定性,而且为自动驾驶技术在复杂环境中的应用提供了新的解决方案,促进了智能汽车系统的发展。
{"title":"Enhanced Cross Layer Refinement Network for robust lane detection across diverse lighting and road conditions","authors":"Weilong Dai ,&nbsp;Zuoyong Li ,&nbsp;Xiaofeng Xu ,&nbsp;Xiaobo Chen ,&nbsp;Huanqiang Zeng ,&nbsp;Rong Hu","doi":"10.1016/j.engappai.2024.109473","DOIUrl":"10.1016/j.engappai.2024.109473","url":null,"abstract":"<div><div>With the rapid development of autonomous driving technology, lane detection, a key component of intelligent vehicle systems, is crucial for ensuring road safety and efficient vehicle navigation. In this paper, a new lane detection method is proposed to address the problem of degraded performance of existing lane detection methods when dealing with complex road environments. The proposed method evolves from the original Cross Layer Refinement Network (CLRNet) by incorporating two of our carefully designed core components: the Global Feature Optimizer (GFO) and the Adaptive Lane Geometry Aggregator (ALGA). The GFO is a multi-scale attention mechanism that mimics the human visual focusing ability, effectively filtering out unimportant information and focusing on the image regions most relevant to the task. The ALGA is a shape feature-aware aggregation module that utilizes the shape prior of lanes to enhance the correlation of anchor points in an image, better fusing global and local information. By integrating both components into CLRNet, an enhanced version called Enhanced CLRNet (E-CLRNet) is presented, which exhibits higher performance stability in complex roadway scenarios. Experiments on the CULane dataset reveal that E-CLRNet demonstrates superior performance stability over the original CLRNet in complex scenarios, including curves, shadows, missing lines, and dazzling light conditions. In particular, in the curves, the F1 score of E-CLRNet is improved by almost 3% over the original CLRNet. This study not only improves the accuracy and performance stability of lane detection but also provides a new solution for the application of autonomous driving technology in complex environments, which promotes the development of intelligent vehicle systems.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":7.5,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533394","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
Denoising diffusion probabilistic model-enabled data augmentation method for intelligent machine fault diagnosis 用于智能机器故障诊断的去噪扩散概率模型数据增强方法
IF 7.5 2区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-10-22 DOI: 10.1016/j.engappai.2024.109520
Pengcheng Zhao , Wei Zhang , Xiaoshan Cao , Xiang Li
Bearing fault is one of the main causes of rotating machinery failure. However, collecting sufficient failure data proves challenging in real-world industrial environments due to their complexity. Owing to this constraint, the majority of current methods fail to accurately identify fault types with limited data, thereby impeding timely maintenance efforts. To address this issue, we propose a bearing fault diagnosis method utilizing diffusion model data enhancement in this study. Following data collection, we employ the continuous wavelet transform to convert various one-dimensional vibration data into two-dimensional time series graphs. Subsequently, these feature graphs are partitioned into sets of fault samples. Then, the diffusion model is employed to augment the training samples. These augmented samples are then fed into the convolutional neural network for fault diagnosis, and their diagnostic accuracy is compared with that of the original dataset. The comparative analysis demonstrates that the data augmentation technique, founded on the diffusion model, enhances fault diagnosis accuracy within a small sample training dataset. Ultimately, the efficacy of the proposed method is validated utilizing the Paderborn bearing dataset and juxtaposed against alternative data augmentation techniques. The findings indicate that the diffusion model-based data augmentation method outperforms other techniques in terms of both training accuracy and stability, particularly in scenarios with small sample.
轴承故障是旋转机械故障的主要原因之一。然而,由于其复杂性,在实际工业环境中收集足够的故障数据具有挑战性。由于这种限制,目前的大多数方法都无法通过有限的数据准确识别故障类型,从而阻碍了及时的维护工作。针对这一问题,我们在本研究中提出了一种利用扩散模型数据增强的轴承故障诊断方法。在收集数据后,我们采用连续小波变换将各种一维振动数据转换为二维时间序列图。随后,将这些特征图划分为故障样本集。然后,利用扩散模型来增强训练样本。然后将这些增强样本输入卷积神经网络进行故障诊断,并将其诊断准确率与原始数据集的诊断准确率进行比较。对比分析表明,基于扩散模型的数据增强技术提高了小样本训练数据集的故障诊断准确性。最后,利用帕德博恩轴承数据集对所提出方法的有效性进行了验证,并与其他数据增强技术进行了对比。研究结果表明,基于扩散模型的数据增强方法在训练准确性和稳定性方面都优于其他技术,尤其是在小样本情况下。
{"title":"Denoising diffusion probabilistic model-enabled data augmentation method for intelligent machine fault diagnosis","authors":"Pengcheng Zhao ,&nbsp;Wei Zhang ,&nbsp;Xiaoshan Cao ,&nbsp;Xiang Li","doi":"10.1016/j.engappai.2024.109520","DOIUrl":"10.1016/j.engappai.2024.109520","url":null,"abstract":"<div><div>Bearing fault is one of the main causes of rotating machinery failure. However, collecting sufficient failure data proves challenging in real-world industrial environments due to their complexity. Owing to this constraint, the majority of current methods fail to accurately identify fault types with limited data, thereby impeding timely maintenance efforts. To address this issue, we propose a bearing fault diagnosis method utilizing diffusion model data enhancement in this study. Following data collection, we employ the continuous wavelet transform to convert various one-dimensional vibration data into two-dimensional time series graphs. Subsequently, these feature graphs are partitioned into sets of fault samples. Then, the diffusion model is employed to augment the training samples. These augmented samples are then fed into the convolutional neural network for fault diagnosis, and their diagnostic accuracy is compared with that of the original dataset. The comparative analysis demonstrates that the data augmentation technique, founded on the diffusion model, enhances fault diagnosis accuracy within a small sample training dataset. Ultimately, the efficacy of the proposed method is validated utilizing the Paderborn bearing dataset and juxtaposed against alternative data augmentation techniques. The findings indicate that the diffusion model-based data augmentation method outperforms other techniques in terms of both training accuracy and stability, particularly in scenarios with small sample.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":7.5,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533402","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
Enhancing interpretability and generalizability in extended isolation forests 增强扩展隔离林的可解释性和可推广性
IF 7.5 2区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-10-22 DOI: 10.1016/j.engappai.2024.109409
Alessio Arcudi , Davide Frizzo , Chiara Masiero , Gian Antonio Susto
Anomaly Detection (AD) focuses on identifying unusual patterns in complex datasets and systems. While Machine Learning and Decision Support Systems (DSS) are effective for this, simply detecting anomalies often falls short in real-world scenarios, especially in engineering contexts where diagnostics and maintenance are essential. Users need clear explanations behind anomaly predictions to understand the root causes and trust the model. The unsupervised nature of AD complicates the development of interpretable tools. To address this, we propose the Extended Isolation Forest Feature Importance (ExIFFI), a new approach that explains the predictions of the Extended Isolation Forest (EIF), applicable to all Isolation Forest models that split using hyperplanes. ExIFFI provides both global and local explanations by analyzing feature importance.
Additionally, we introduce Enhanced Extended Isolation Forest (EIF+), an improved version of EIF, designed to better detect unseen anomalies by modifying the splitting strategy of hyperplanes. We compare various unsupervised AD methods across five synthetic and eleven real-world datasets using the Average Precision metric. EIF+consistently outperforms EIF in all scenarios, demonstrating superior generalization. To validate the interpretability, we propose a new metric — AUCFS (Area Under the Curve of Feature Selection) — which uses feature selection as a performance indicator. ExIFFI proves more effective than other unsupervised interpretation methods, excelling in 8 out of 11 real-world datasets and correctly identifying anomalous features in synthetic datasets. Finally, we provide open-source code to encourage further research and reproducibility.
异常检测(AD)侧重于识别复杂数据集和系统中的异常模式。虽然机器学习和决策支持系统(DSS)在这方面很有效,但在现实世界中,特别是在诊断和维护至关重要的工程领域,仅仅检测异常情况往往是不够的。用户需要异常预测背后的清晰解释,以了解根本原因并信任模型。AD 的无监督特性使可解释工具的开发变得更加复杂。为了解决这个问题,我们提出了扩展隔离林特征重要性(ExIFFI),这是一种解释扩展隔离林(EIF)预测的新方法,适用于所有使用超平面分割的隔离林模型。此外,我们还引入了增强型扩展隔离森林(EIF+),它是 EIF 的改进版本,旨在通过修改超平面的分割策略更好地检测未见异常。我们使用平均精度指标,在五个合成数据集和十一个真实数据集上比较了各种无监督 AD 方法。在所有场景中,EIF+ 的表现始终优于 EIF,显示出卓越的泛化能力。为了验证可解释性,我们提出了一个新指标--AUCFS(特征选择曲线下面积),它使用特征选择作为性能指标。事实证明,ExIFFI 比其他无监督解释方法更有效,在 11 个真实世界数据集中的 8 个数据中表现出色,并能正确识别合成数据集中的异常特征。最后,我们提供了开放源代码,以鼓励进一步研究和再现。
{"title":"Enhancing interpretability and generalizability in extended isolation forests","authors":"Alessio Arcudi ,&nbsp;Davide Frizzo ,&nbsp;Chiara Masiero ,&nbsp;Gian Antonio Susto","doi":"10.1016/j.engappai.2024.109409","DOIUrl":"10.1016/j.engappai.2024.109409","url":null,"abstract":"<div><div>Anomaly Detection (AD) focuses on identifying unusual patterns in complex datasets and systems. While Machine Learning and Decision Support Systems (DSS) are effective for this, simply detecting anomalies often falls short in real-world scenarios, especially in engineering contexts where diagnostics and maintenance are essential. Users need clear explanations behind anomaly predictions to understand the root causes and trust the model. The unsupervised nature of AD complicates the development of interpretable tools. To address this, we propose the Extended Isolation Forest Feature Importance (ExIFFI), a new approach that explains the predictions of the Extended Isolation Forest (EIF), applicable to all Isolation Forest models that split using hyperplanes. ExIFFI provides both global and local explanations by analyzing feature importance.</div><div>Additionally, we introduce Enhanced Extended Isolation Forest (<span><math><msup><mrow><mtext>EIF</mtext></mrow><mrow><mo>+</mo></mrow></msup></math></span>), an improved version of EIF, designed to better detect unseen anomalies by modifying the splitting strategy of hyperplanes. We compare various unsupervised AD methods across five synthetic and eleven real-world datasets using the Average Precision metric. <span><math><msup><mrow><mtext>EIF</mtext></mrow><mrow><mo>+</mo></mrow></msup></math></span>consistently outperforms EIF in all scenarios, demonstrating superior generalization. To validate the interpretability, we propose a new metric — <span><math><mrow><mi>A</mi><mi>U</mi><msub><mrow><mi>C</mi></mrow><mrow><mi>F</mi><mi>S</mi></mrow></msub></mrow></math></span> (Area Under the Curve of Feature Selection) — which uses feature selection as a performance indicator. ExIFFI proves more effective than other unsupervised interpretation methods, excelling in 8 out of 11 real-world datasets and correctly identifying anomalous features in synthetic datasets. Finally, we provide open-source code to encourage further research and reproducibility.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":7.5,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142534335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
Engineering Applications of Artificial Intelligence
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1