Engineering Applications of Artificial Intelligence最新文献_第7页

Personalized hierarchical heterogeneous federated learning for thermal comfort prediction in smart buildings 智能建筑热舒适度预测的个性化分层异构联合学习

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

Engineering Applications of Artificial Intelligence

Pub Date : 2024-10-25 DOI: 10.1016/j.engappai.2024.109464

Federated Learning (FL) is gaining significant traction due to its ability to provide security and privacy. In the FL paradigm, the global model is learned at the cloud through the consolidation of local model parameters instead of collecting local training data at the central node. This approach mitigates privacy leakage caused by the collection of sensitive information. However, it poses challenges to the convergence of the global model due to system and statistical heterogeneity. In this study, we propose a two-fold Personalized Hierarchical Heterogeneous FL (PHHFL) approach. It leverages a hierarchical structure to handle statistical heterogeneity and a normal distribution-based client selection to control model divergence in FL environment. PHHFL aims to use a maximum number of local features of each client and assign specific level in the hierarchy. Furthermore, to address model divergence caused by the nodes’ statistical heterogeneity, we propose a novel client selection strategy based on the performance distribution of the nodes. Experiments are conducted on thermal comfort datasets and a synthetic dataset with 12 and 10 clients, respectively. The results show that the proposed PHHFL outperforms in terms of accuracy, F1 score, and class-wise precision on both thermal comfort and synthetic datasets. The source code of the PHHFL model and datasets is available on GitHub.

联邦学习（Federated Learning，FL）因其提供安全性和隐私性的能力而备受关注。在联合学习模式中，全局模型是通过整合本地模型参数在云端学习的，而不是在中心节点收集本地训练数据。这种方法可以减少因收集敏感信息而造成的隐私泄露。然而，由于系统和统计异质性，这种方法对全局模型的收敛性提出了挑战。在本研究中，我们提出了一种双重个性化分层异构 FL（PHHFL）方法。它利用分层结构来处理统计异质性，并利用基于正态分布的客户端选择来控制 FL 环境中的模型分歧。PHHFL 旨在使用每个客户端的最大局部特征数量，并在层次结构中分配特定级别。此外，为了解决节点统计异质性引起的模型发散问题，我们提出了一种基于节点性能分布的新型客户端选择策略。我们在热舒适数据集和分别有 12 个和 10 个客户端的合成数据集上进行了实验。结果表明，在热舒适度数据集和合成数据集上，所提出的 PHHFL 在准确度、F1 分数和类精确度方面都表现出色。PHHFL 模型和数据集的源代码可在 GitHub 上获取。

{"title":"Personalized hierarchical heterogeneous federated learning for thermal comfort prediction in smart buildings","authors":"","doi":"10.1016/j.engappai.2024.109464","DOIUrl":"10.1016/j.engappai.2024.109464","url":null,"abstract":"<div><div>Federated Learning (FL) is gaining significant traction due to its ability to provide security and privacy. In the FL paradigm, the global model is learned at the cloud through the consolidation of local model parameters instead of collecting local training data at the central node. This approach mitigates privacy leakage caused by the collection of sensitive information. However, it poses challenges to the convergence of the global model due to system and statistical heterogeneity. In this study, we propose a two-fold Personalized Hierarchical Heterogeneous FL (PHHFL) approach. It leverages a hierarchical structure to handle statistical heterogeneity and a normal distribution-based client selection to control model divergence in FL environment. PHHFL aims to use a maximum number of local features of each client and assign specific level in the hierarchy. Furthermore, to address model divergence caused by the nodes’ statistical heterogeneity, we propose a novel client selection strategy based on the performance distribution of the nodes. Experiments are conducted on thermal comfort datasets and a synthetic dataset with 12 and 10 clients, respectively. The results show that the proposed PHHFL outperforms in terms of accuracy, F1 score, and class-wise precision on both thermal comfort and synthetic datasets. The source code of the PHHFL model and datasets is available on <span><span>GitHub</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":"2024-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533157","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

Fault diagnosis of driving gear in battery swapping system based on auditory bionics 基于听觉仿生学的电池更换系统驱动装置故障诊断

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

Engineering Applications of Artificial Intelligence

Pub Date : 2024-10-25 DOI: 10.1016/j.engappai.2024.109525

Rack and pinion drives (RPD) are widely used in battery swapping system (BSS) for electric heavy trucks (EHT), and due to the continuous heavy-load and high-intensity operation, along with the electric erosion, the gears in the RPD are always damaged, which causes unexpected consequences such as downtime or safety incidents. The working conditions of the RPD in BSS include uncertain noises, fluctuant and low speed, which pose steep challenges to accurate fault diagnosis. Considering the auditory resistance of interference, the low-frequency sensitivity of auditory perception, and the auditory saliency mechanism, to leverage the advantages of auditory perceptual mechanism in addressing the above challenges, as the contribution in artificial intelligence, we propose an entire vibration signal processing scheme based on auditory bionics, including some mathematical models for auditory mechanisms. For the application in engineering, the proposed scheme is employed for fault diagnosis of RPD in BSS in unique working conditions. First, adaptive resampling is used to smooth the speed fluctuation, then, Gammatone filters are employed to transform vibration signals to cochleograms, after that, based on auditory stream segregation and selective attention mechanisms, effective frequency channels and salient features are extracted from the cochleograms, besides, to improve the diagnosis accuracy, binaural features are also extracted, finally, based on (sectional) sparse representation and fusion, fault diagnosis is achieved. The effectiveness of the fault diagnosis scheme is demonstrated using a BSS prototype system.

齿轮齿条传动装置（RPD）广泛应用于电动重型卡车（EHT）的电池交换系统（BSS）中，由于连续的重负荷和高强度运行，再加上电能的侵蚀，RPD 中的齿轮总是会损坏，从而导致停机或安全事故等意想不到的后果。在 BSS 中，RPD 的工作条件包括不确定噪声、波动和低速，这给准确的故障诊断带来了巨大挑战。考虑到听觉的抗干扰性、听觉感知的低频灵敏性以及听觉突出机制，为了利用听觉感知机制的优势应对上述挑战，作为人工智能领域的贡献，我们提出了基于听觉仿生学的整体振动信号处理方案，包括一些听觉机制的数学模型。在工程应用方面，所提出的方案被用于在特殊工作条件下对 BSS 中的 RPD 进行故障诊断。首先，使用自适应重采样来平滑速度波动，然后，使用伽马通滤波器将振动信号转换为耳蜗图，之后，基于听觉流分离和选择性注意机制，从耳蜗图中提取有效频率通道和显著特征，此外，为了提高诊断准确性，还提取了双耳特征，最后，基于（截面）稀疏表示和融合，实现故障诊断。故障诊断方案的有效性通过一个 BSS 原型系统得到了验证。

{"title":"Fault diagnosis of driving gear in battery swapping system based on auditory bionics","authors":"","doi":"10.1016/j.engappai.2024.109525","DOIUrl":"10.1016/j.engappai.2024.109525","url":null,"abstract":"<div><div>Rack and pinion drives (RPD) are widely used in battery swapping system (BSS) for electric heavy trucks (EHT), and due to the continuous heavy-load and high-intensity operation, along with the electric erosion, the gears in the RPD are always damaged, which causes unexpected consequences such as downtime or safety incidents. The working conditions of the RPD in BSS include uncertain noises, fluctuant and low speed, which pose steep challenges to accurate fault diagnosis. Considering the auditory resistance of interference, the low-frequency sensitivity of auditory perception, and the auditory saliency mechanism, to leverage the advantages of auditory perceptual mechanism in addressing the above challenges, as the contribution in artificial intelligence, we propose an entire vibration signal processing scheme based on auditory bionics, including some mathematical models for auditory mechanisms. For the application in engineering, the proposed scheme is employed for fault diagnosis of RPD in BSS in unique working conditions. First, adaptive resampling is used to smooth the speed fluctuation, then, Gammatone filters are employed to transform vibration signals to cochleograms, after that, based on auditory stream segregation and selective attention mechanisms, effective frequency channels and salient features are extracted from the cochleograms, besides, to improve the diagnosis accuracy, binaural features are also extracted, finally, based on (sectional) sparse representation and fusion, fault diagnosis is achieved. The effectiveness of the fault diagnosis scheme is demonstrated using a BSS prototype system.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":7.5,"publicationDate":"2024-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533291","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

RMFDNet: Redundant and Missing Feature Decoupling Network for salient object detection RMFDNet：用于突出物体检测的冗余和缺失特征解耦网络

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

Engineering Applications of Artificial Intelligence

Pub Date : 2024-10-25 DOI: 10.1016/j.engappai.2024.109459

Recently, many salient object detection methods have utilized edge contours to constrain the solution space. This approach aims to reduce the omission of salient features and minimize the inclusion of non-salient features. To further leverage the potential of edge-related information, this paper proposes a Redundant and Missing Feature Decoupling Network (RMFDNet). RMFDNet primarily consists of a segment decoder, a complement decoder, a removal decoder, and a recurrent repair encoder. The complement and removal decoders are designed to directly predict the missing and redundant features within the segmentation features. These predicted features are then processed by the recurrent repair encoder to refine the segmentation features. Experimental results on multiple Red–Green–Blue (RGB) and Red–Green–Blue-Depth (RGB-D) benchmark datasets, as well as polyp segmentation datasets, demonstrate that RMFDNet significantly outperforms previous state-of-the-art methods across various evaluation metrics. The efficiency, robustness, and generalization capability of RMFDNet are thoroughly analyzed through a carefully designed ablation study. The code will be made available upon paper acceptance.

最近，许多突出物体检测方法都利用边缘轮廓来限制求解空间。这种方法旨在减少突出特征的遗漏，尽量减少非突出特征的包含。为了进一步发挥边缘相关信息的潜力，本文提出了冗余和缺失特征解耦网络（RMFDNet）。RMFDNet 主要由分段解码器、补码解码器、移除解码器和递归修复编码器组成。补码解码器和去除解码器旨在直接预测分割特征中的缺失和冗余特征。这些预测的特征随后由递归修复编码器处理，以完善分割特征。在多个红-绿-蓝（RGB）和红-绿-蓝-深度（RGB-D）基准数据集以及息肉分割数据集上的实验结果表明，RMFDNet 在各种评估指标上都明显优于以前的先进方法。通过精心设计的消融研究，对 RMFDNet 的效率、鲁棒性和泛化能力进行了深入分析。代码将在论文被接受后提供。

{"title":"RMFDNet: Redundant and Missing Feature Decoupling Network for salient object detection","authors":"","doi":"10.1016/j.engappai.2024.109459","DOIUrl":"10.1016/j.engappai.2024.109459","url":null,"abstract":"<div><div>Recently, many salient object detection methods have utilized edge contours to constrain the solution space. This approach aims to reduce the omission of salient features and minimize the inclusion of non-salient features. To further leverage the potential of edge-related information, this paper proposes a Redundant and Missing Feature Decoupling Network (RMFDNet). RMFDNet primarily consists of a segment decoder, a complement decoder, a removal decoder, and a recurrent repair encoder. The complement and removal decoders are designed to directly predict the missing and redundant features within the segmentation features. These predicted features are then processed by the recurrent repair encoder to refine the segmentation features. Experimental results on multiple Red–Green–Blue (RGB) and Red–Green–Blue-Depth (RGB-D) benchmark datasets, as well as polyp segmentation datasets, demonstrate that RMFDNet significantly outperforms previous state-of-the-art methods across various evaluation metrics. The efficiency, robustness, and generalization capability of RMFDNet are thoroughly analyzed through a carefully designed ablation study. The code will be made available upon paper acceptance.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":7.5,"publicationDate":"2024-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533292","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 integrated prediction method using adaptive mode decomposition, attention mechanism and deep learning for coking products prices 利用自适应模式分解、注意力机制和深度学习的新型焦化产品价格综合预测方法

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

Engineering Applications of Artificial Intelligence

Pub Date : 2024-10-24 DOI: 10.1016/j.engappai.2024.109504

Accurate prediction of coking product prices is crucial for enhancing production efficiency, cost optimization, and profit maximization in smart coking facilities. To address the volatility caused by nonlinear factors such as raw material costs, substitutes, macroeconomic indicators, sudden events, policy changes, and market behaviors, we propose a novel integrated prediction method for coking product price prediction. This method combines Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) for signal decomposition, Bidirectional Encoder Representations from Transformers (BERT) for natural language processing, attention mechanisms (AT) to weigh feature importance, and an ensemble of Bidirectional Gated Recurrent Unit, Bidirectional Long Short-Term Memory, and Gated Recurrent Unit, abbreviated BBG, for robust feature extraction. We design a feature selection strategy to avoid data leakage and improve the predictive ability of the model, and describe a method to maintain textual data information integrity when combining data from different sources. Experimental results on coke and methanol datasets show that our approach retains multi-source text richness improves predictive capability, and outperforms other state-of-the-art methods, providing an effective tool for developing smart coke plants.

准确预测焦化产品价格对于提高智能焦化设施的生产效率、成本优化和利润最大化至关重要。针对原材料成本、替代品、宏观经济指标、突发事件、政策变化和市场行为等非线性因素造成的波动，我们提出了一种新的焦化产品价格预测综合预测方法。该方法结合了用于信号分解的自适应噪声完全集合经验模式分解（CEEMDAN）、用于自然语言处理的变压器双向编码器表征（BERT）、用于权衡特征重要性的注意机制（AT），以及用于鲁棒特征提取的双向门控递归单元、双向长短时记忆和门控递归单元（简称 BBG）集合。我们设计了一种特征选择策略，以避免数据泄漏并提高模型的预测能力，还介绍了一种在组合不同来源的数据时保持文本数据信息完整性的方法。焦炭和甲醇数据集的实验结果表明，我们的方法保留了多源文本的丰富性，提高了预测能力，并优于其他最先进的方法，为开发智能焦化厂提供了有效的工具。

{"title":"A novel integrated prediction method using adaptive mode decomposition, attention mechanism and deep learning for coking products prices","authors":"","doi":"10.1016/j.engappai.2024.109504","DOIUrl":"10.1016/j.engappai.2024.109504","url":null,"abstract":"<div><div>Accurate prediction of coking product prices is crucial for enhancing production efficiency, cost optimization, and profit maximization in smart coking facilities. To address the volatility caused by nonlinear factors such as raw material costs, substitutes, macroeconomic indicators, sudden events, policy changes, and market behaviors, we propose a novel integrated prediction method for coking product price prediction. This method combines Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) for signal decomposition, Bidirectional Encoder Representations from Transformers (BERT) for natural language processing, attention mechanisms (AT) to weigh feature importance, and an ensemble of Bidirectional Gated Recurrent Unit, Bidirectional Long Short-Term Memory, and Gated Recurrent Unit, abbreviated BBG, for robust feature extraction. We design a feature selection strategy to avoid data leakage and improve the predictive ability of the model, and describe a method to maintain textual data information integrity when combining data from different sources. Experimental results on coke and methanol datasets show that our approach retains multi-source text richness improves predictive capability, and outperforms other state-of-the-art methods, providing an effective tool for developing smart coke plants.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":7.5,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533403","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

Diverse policy generation for the flexible job-shop scheduling problem via deep reinforcement learning with a novel graph representation 通过新型图表示的深度强化学习为灵活的作业车间调度问题生成多样化策略

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

Engineering Applications of Artificial Intelligence

Pub Date : 2024-10-24 DOI: 10.1016/j.engappai.2024.109488

In scheduling problems common in the industry and various real-world scenarios, responding in real-time to disruptive events is important. Recent methods propose the use of deep reinforcement learning (DRL) to learn policies capable of generating solutions under this constraint. However, current DRL approaches struggle with large instances, which are common in real-world scenarios. The objective of this paper is to introduce a new DRL method for solving the flexible job-shop scheduling problem, with a focus on these type of instances. The approach is based on the use of heterogeneous graph neural networks to a more informative graph representation of the problem. This novel modeling of the problem enhances the policy’s ability to capture state information and improve its decision-making capacity. Additionally, we introduce two novel approaches to enhance the performance of the DRL approach: the first involves generating a diverse set of scheduling policies, while the second combines DRL with dispatching rules (DRs) constraining the action space, with a variable degree of freedom depending on the chosen policy. Experimental results on two public benchmarks show that our approach outperforms DRs and achieves superior results compared to three state-of-the-art DRL methods, particularly for large instances.

在行业中常见的调度问题和各种现实世界场景中，实时应对干扰事件非常重要。最近的方法建议使用深度强化学习（DRL）来学习能够在此约束条件下生成解决方案的策略。然而，目前的 DRL 方法在处理大型实例时很吃力，而大型实例在现实世界的场景中很常见。本文旨在介绍一种新的 DRL 方法，用于解决灵活的作业车间调度问题，重点关注这类实例。该方法基于使用异构图神经网络来对问题进行更翔实的图表示。这种新颖的问题建模增强了策略捕捉状态信息的能力，提高了决策能力。此外，我们还引入了两种新方法来提高 DRL 方法的性能：第一种方法涉及生成一组多样化的调度策略，第二种方法则将 DRL 与调度规则 (DR) 结合起来，对行动空间进行约束，根据所选策略的不同，自由度也不同。在两个公共基准上的实验结果表明，我们的方法优于 DRs，与三种最先进的 DRL 方法相比，我们的方法取得了更优越的结果，尤其是在大型实例方面。

{"title":"Diverse policy generation for the flexible job-shop scheduling problem via deep reinforcement learning with a novel graph representation","authors":"","doi":"10.1016/j.engappai.2024.109488","DOIUrl":"10.1016/j.engappai.2024.109488","url":null,"abstract":"<div><div>In scheduling problems common in the industry and various real-world scenarios, responding in real-time to disruptive events is important. Recent methods propose the use of deep reinforcement learning (DRL) to learn policies capable of generating solutions under this constraint. However, current DRL approaches struggle with large instances, which are common in real-world scenarios. The objective of this paper is to introduce a new DRL method for solving the flexible job-shop scheduling problem, with a focus on these type of instances. The approach is based on the use of heterogeneous graph neural networks to a more informative graph representation of the problem. This novel modeling of the problem enhances the policy’s ability to capture state information and improve its decision-making capacity. Additionally, we introduce two novel approaches to enhance the performance of the DRL approach: the first involves generating a diverse set of scheduling policies, while the second combines DRL with dispatching rules (DRs) constraining the action space, with a variable degree of freedom depending on the chosen policy. Experimental results on two public benchmarks show that our approach outperforms DRs and achieves superior results compared to three state-of-the-art DRL methods, particularly for large instances.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":7.5,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533280","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

A multi-criteria decision-making method based on discrete Z-numbers and Aczel-Alsina aggregation operators and its application on early diagnosis of depression 基于离散 Z 数和 Aczel-Alsina 聚合算子的多标准决策方法及其在抑郁症早期诊断中的应用

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

Engineering Applications of Artificial Intelligence

Pub Date : 2024-10-24 DOI: 10.1016/j.engappai.2024.109484

In mental health diagnostics, the questionnaire is an effective and cost-effective method. However, the traditional questionnaire test methods for depression and anxiety have great ambiguity. The discrete Z-numbers (DZs) provide solutions for describing and resolving complex fuzzy issues in the intelligent multi-criteria decision-making (MCDM) process. However, large-scale datasets are not suited for the present MCDM techniques due to their extremely high computational cost. Additionally, these techniques are less stable and flexible. To address the above issues, a novel MCDM method is introduced, which is based on the DZs theory and the Aczel-Alsina (AA) aggregation operator (AO) for large-scale datasets. To begin with, centroid points are calculated for DZs, and a series of novel AOs are introduced. And then a score function with a parameter is introduced to balance the influence between the possibility restriction and the fuzzy restriction of DZs. Thirdly, a new MCDM method under DZs is presented based on the proposed AA AOs and score function. Finally, to support the early diagnosis of depression and anxiety, we apply our method to the real-life online Depression, Anxiety, and Stress Scale (DASS) which can be transformed into DZs by our proposed preprocessing method. According to experimental results, our method is applicable to large-scale datasets and has much lower complexity as well as higher flexibility and stability.

在心理健康诊断中，问卷调查是一种有效且经济的方法。然而，传统的抑郁和焦虑问卷测试方法存在很大的模糊性。离散 Z 数（DZ）为智能多标准决策（MCDM）过程中复杂模糊问题的描述和解决提供了解决方案。然而，由于计算成本极高，大规模数据集并不适合目前的 MCDM 技术。此外，这些技术的稳定性和灵活性也较差。为解决上述问题，本文介绍了一种新型 MCDM 方法，该方法基于 DZs 理论和适用于大规模数据集的 Aczel-Alsina (AA) 聚合算子 (AO)。首先，计算 DZs 的中心点，并引入一系列新型 AO。然后，引入一个带有参数的评分函数，以平衡 DZ 的可能性限制和模糊限制之间的影响。第三，基于所提出的 AA AOs 和评分函数，提出了一种新的 DZs 下的 MCDM 方法。最后，为了支持抑郁和焦虑的早期诊断，我们将我们的方法应用于现实生活中的在线抑郁、焦虑和压力量表（DASS），并通过我们提出的预处理方法将其转化为 DZs。实验结果表明，我们的方法适用于大规模数据集，具有更低的复杂度、更高的灵活性和稳定性。

{"title":"A multi-criteria decision-making method based on discrete Z-numbers and Aczel-Alsina aggregation operators and its application on early diagnosis of depression","authors":"","doi":"10.1016/j.engappai.2024.109484","DOIUrl":"10.1016/j.engappai.2024.109484","url":null,"abstract":"<div><div>In mental health diagnostics, the questionnaire is an effective and cost-effective method. However, the traditional questionnaire test methods for depression and anxiety have great ambiguity. The discrete Z-numbers (DZs) provide solutions for describing and resolving complex fuzzy issues in the intelligent multi-criteria decision-making (MCDM) process. However, large-scale datasets are not suited for the present MCDM techniques due to their extremely high computational cost. Additionally, these techniques are less stable and flexible. To address the above issues, a novel MCDM method is introduced, which is based on the DZs theory and the Aczel-Alsina (AA) aggregation operator (AO) for large-scale datasets. To begin with, centroid points are calculated for DZs, and a series of novel AOs are introduced. And then a score function with a parameter is introduced to balance the influence between the possibility restriction and the fuzzy restriction of DZs. Thirdly, a new MCDM method under DZs is presented based on the proposed AA AOs and score function. Finally, to support the early diagnosis of depression and anxiety, we apply our method to the real-life online Depression, Anxiety, and Stress Scale (DASS) which can be transformed into DZs by our proposed preprocessing method. According to experimental results, our method is applicable to large-scale datasets and has much lower complexity as well as higher flexibility and stability.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":7.5,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533285","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 geometric model with stochastic error for abnormal motion detection of portal crane bucket grab 用于门式起重机斗抓斗异常运动检测的随机误差几何模型

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

Engineering Applications of Artificial Intelligence

Pub Date : 2024-10-24 DOI: 10.1016/j.engappai.2024.109481

Abnormal swing angle detection of bucket grabs is crucial for efficient harbor operations. In this study, we develop a practically convenient swing angle detection method for crane operation, requiring only a single standard surveillance camera at the fly-jib head, without the need for sophisticated sensors or markers on the payload. Specifically, our algorithm takes the video images from the camera as input. Next, a fine-tuned ‘the fifth version of the You Only Look Once algorithm’ (YOLOv5) model is used to automatically detect the position of the bucket grab on the image plane. Subsequently, a novel geometric model is constructed, which takes the pixel position of the bucket grab, the steel rope length provided by the Programmable Logic Controller (PLC) system, and the optical lens information of the camera into consideration. The key parameters of this geometric model are statistically estimated by a novel iterative algorithm. Once the key parameters are estimated, the algorithm can automatically detect swing angles from video streams. Being analytically simple, the computation of our algorithm is fast, as it takes about 0.01 s to process one single image generated by the surveillance camera. Therefore, we are able to obtain an accurate and fast estimation of the swing angle of an operating crane in real-time applications. Simulation studies are conducted to validate the model and algorithm. Real video examples from Qingdao Seaport under various weather conditions are analyzed to demonstrate its practical performance.

斗式抓斗的异常摆角检测对于高效的港口作业至关重要。在本研究中，我们开发了一种方便实用的起重机操作摆角检测方法，只需在飞臂头部安装一个标准监控摄像头，而无需在有效载荷上安装复杂的传感器或标记。具体来说，我们的算法将摄像头的视频图像作为输入。然后，使用经过微调的 "第五版只看一次算法"（YOLOv5）模型来自动检测图像平面上抓斗的位置。随后，构建了一个新颖的几何模型，该模型将抓斗的像素位置、可编程逻辑控制器（PLC）系统提供的钢绳长度以及摄像机的光学镜头信息考虑在内。该几何模型的关键参数通过一种新颖的迭代算法进行统计估算。一旦估算出关键参数，该算法就能自动检测视频流中的摆动角度。由于分析简单，我们的算法计算速度很快，处理监控摄像头生成的单张图像大约需要 0.01 秒。因此，我们能够在实时应用中准确、快速地估计运行中起重机的摆动角度。为验证模型和算法，我们进行了仿真研究。分析了青岛港在各种天气条件下的真实视频示例，以证明其实用性能。

{"title":"A geometric model with stochastic error for abnormal motion detection of portal crane bucket grab","authors":"","doi":"10.1016/j.engappai.2024.109481","DOIUrl":"10.1016/j.engappai.2024.109481","url":null,"abstract":"<div><div>Abnormal swing angle detection of bucket grabs is crucial for efficient harbor operations. In this study, we develop a practically convenient swing angle detection method for crane operation, requiring only a single standard surveillance camera at the fly-jib head, without the need for sophisticated sensors or markers on the payload. Specifically, our algorithm takes the video images from the camera as input. Next, a fine-tuned ‘the fifth version of the You Only Look Once algorithm’ (YOLOv5) model is used to automatically detect the position of the bucket grab on the image plane. Subsequently, a novel geometric model is constructed, which takes the pixel position of the bucket grab, the steel rope length provided by the Programmable Logic Controller (PLC) system, and the optical lens information of the camera into consideration. The key parameters of this geometric model are statistically estimated by a novel iterative algorithm. Once the key parameters are estimated, the algorithm can automatically detect swing angles from video streams. Being analytically simple, the computation of our algorithm is fast, as it takes about 0.01 s to process one single image generated by the surveillance camera. Therefore, we are able to obtain an accurate and fast estimation of the swing angle of an operating crane in real-time applications. Simulation studies are conducted to validate the model and algorithm. Real video examples from Qingdao Seaport under various weather conditions are analyzed to demonstrate its practical performance.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":7.5,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533284","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

Adaptive multimodal control of trans-media vehicle based on deep reinforcement learning 基于深度强化学习的跨媒体车辆自适应多模式控制

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

Engineering Applications of Artificial Intelligence

Pub Date : 2024-10-23 DOI: 10.1016/j.engappai.2024.109524

To solve the problem that the control system is prone to instability due to the sudden change of physical characteristics, strong interference, and nonlinear in the process of multimodal movement of trans-media vehicle, an adaptive control method combining the Deep Deterministic Policy Gradient (DDPG) and traditional Proportional-Integral-Derivative (PID) controller is proposed in this paper. In this approach, the upper-level DDPG controller continuously monitors the vehicle's state and environmental conditions, dynamically adjusting the PID parameters in real-time. The lower-level PID controller then utilizes these updated parameters to modulate the output thrust of the vehicle's motors, thereby achieving excellent control over the vehicle's entire movement. Firstly, according to the hydrodynamic analysis, the kinematics and dynamics mathematical model of the self-designed trans-media vehicle is constructed. This model includes the multi-stage motion modal process of aerial flight, underwater navigation, and cross-media motion, which is suitable for the simulation and verification of the control method. Then, an adaptive controller called RL-PID combining DDPG and PID is built, so that PID can adjust parameters in real-time according to the changes in the external environment. Finally, after theoretical stability proof, a comparison study is performed across three approaches, namely the novel RL-PID, Fuzzy PID, and PID. The experimental results illustrate the superiority of the proposed approach over the competing ones and the generalization of the proposed approach under different interference.

为了解决跨媒体车辆在多模式运动过程中由于物理特性突变、强干扰、非线性等原因导致控制系统容易不稳定的问题，本文提出了一种结合深度确定性策略梯度（DDPG）和传统比例-积分-微分（PID）控制器的自适应控制方法。在这种方法中，上层 DDPG 控制器持续监控车辆状态和环境条件，实时动态调整 PID 参数。然后，下层 PID 控制器利用这些更新的参数来调节车辆电机的输出推力，从而实现对车辆整个运动过程的良好控制。首先，根据流体力学分析，构建了自主设计的跨媒体飞行器的运动学和动力学数学模型。该模型包括空中飞行、水下导航和跨媒体运动的多阶段运动模态过程，适合控制方法的仿真和验证。然后，建立了结合 DDPG 和 PID 的自适应控制器 RL-PID，使 PID 可以根据外部环境的变化实时调整参数。最后，在理论稳定性证明之后，对新型 RL-PID、模糊 PID 和 PID 三种方法进行了比较研究。实验结果表明，所提出的方法优于其他竞争方法，并且在不同干扰下具有通用性。

{"title":"Adaptive multimodal control of trans-media vehicle based on deep reinforcement learning","authors":"","doi":"10.1016/j.engappai.2024.109524","DOIUrl":"10.1016/j.engappai.2024.109524","url":null,"abstract":"<div><div>To solve the problem that the control system is prone to instability due to the sudden change of physical characteristics, strong interference, and nonlinear in the process of multimodal movement of trans-media vehicle, an adaptive control method combining the Deep Deterministic Policy Gradient (DDPG) and traditional Proportional-Integral-Derivative (PID) controller is proposed in this paper. In this approach, the upper-level DDPG controller continuously monitors the vehicle's state and environmental conditions, dynamically adjusting the PID parameters in real-time. The lower-level PID controller then utilizes these updated parameters to modulate the output thrust of the vehicle's motors, thereby achieving excellent control over the vehicle's entire movement. Firstly, according to the hydrodynamic analysis, the kinematics and dynamics mathematical model of the self-designed trans-media vehicle is constructed. This model includes the multi-stage motion modal process of aerial flight, underwater navigation, and cross-media motion, which is suitable for the simulation and verification of the control method. Then, an adaptive controller called RL-PID combining DDPG and PID is built, so that PID can adjust parameters in real-time according to the changes in the external environment. Finally, after theoretical stability proof, a comparison study is performed across three approaches, namely the novel RL-PID, Fuzzy PID, and PID. The experimental results illustrate the superiority of the proposed approach over the competing ones and the generalization of the proposed approach under different interference.</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":"142533401","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

Weak saliency ensemble network for person Re-identification using infrared light images 利用红外光图像进行人物再识别的弱显著性集合网络

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

Engineering Applications of Artificial Intelligence

Pub Date : 2024-10-23 DOI: 10.1016/j.engappai.2024.109517

In recent years, person re-identification (re-id) has primarily been studied using visible light (VL) images. However, the challenges of employing VL images in nighttime environments have prompted research into using infrared light (IR) images. Yet, the utilization of both VL and IR images in person re-id has resulted in increased computational cost and processing time in multi-modality systems, leading to studies focusing solely on IR images. Nevertheless, IR images, lacking color and texture information, generally yield lower recognition performance in existing person re-id studies. In addition, previous studies have shown that person re-id performance suffers in the presence of complex background noise. To tackle these challenges, this study proposes a new weak saliency ensemble network (WSE-Net) for person re-id using IR images. WSE-Net incorporates a channel reduction of feature (CRF) method to reduce computational cost in the ensemble network, a technique for converting input images into group of patch images and feeding them into the ensemble model to enhance the reduced feature information, and a grouped convolution ensemble network (GCE-Net) that enables the fusion of features extracted from original and attention-guided ensemble models.

The performance of person re-id using WSE-Net was evaluated on the Dongguk body-based person recognition database version 1 (DBPerson-Recog-DB1) and the Sun Yat-sen university multiple modality re-identification version 1 (SYSU-MM01). Experimental results demonstrated that on DBPerson-Recog-DB1, WSE-Net achieved 93.65% in rank 1, 95.28% in mean average precision (mAP), and 93.52% in the harmonic mean of precision and recall. Additionally, on SYSU-MM01, WSE-Net achieved 86.85% in rank 1, 44.58% in mAP, and 40.06% in the harmonic mean of precision and recall. Furthermore, the accuracy of WSE-Net on both datasets surpassed that of state-of-the-art methods.

近年来，对人员重新识别（re-id）的研究主要使用可见光（VL）图像。然而，在夜间环境中使用可见光图像所面临的挑战促使人们开始研究使用红外图像。然而，在人员重新识别中同时使用可见光和红外图像会增加多模态系统的计算成本和处理时间，导致研究只关注红外图像。然而，红外图像缺乏颜色和纹理信息，在现有的人员重识别研究中识别率通常较低。此外，以往的研究表明，在存在复杂背景噪声的情况下，人物再识别性能也会受到影响。为了应对这些挑战，本研究提出了一种新的弱显著性集合网络（WSE-Net），用于利用红外图像进行人物重识别。WSE-Net 采用了一种通道特征还原（CRF）方法来降低集合网络的计算成本；一种将输入图像转换为一组补丁图像并将其输入集合模型以增强还原特征信息的技术；以及一种分组卷积集合网络（GCE-Net），该网络可将从原始集合模型和注意力引导集合模型中提取的特征进行融合。使用 WSE-Net 进行的人物再识别性能评估是在基于人体的东国人物识别数据库第一版（DBPerson-Recog-DB1）和中山大学多模态再识别第一版（SYSU-MM01）上进行的。实验结果表明，在 DBPerson-Recog-DB1 上，WSE-Net 取得了 93.65% 的排名第一、95.28% 的平均精确度 (mAP)，以及 93.52% 的精确度和召回率谐波平均值。此外，在 SYSU-MM01 上，WSE-Net 的排名第一的准确率为 86.85%，mAP 为 44.58%，精确度和召回率的调和平均值为 40.06%。此外，WSE-Net 在这两个数据集上的准确率都超过了最先进的方法。

{"title":"Weak saliency ensemble network for person Re-identification using infrared light images","authors":"","doi":"10.1016/j.engappai.2024.109517","DOIUrl":"10.1016/j.engappai.2024.109517","url":null,"abstract":"<div><div>In recent years, person re-identification (re-id) has primarily been studied using visible light (VL) images. However, the challenges of employing VL images in nighttime environments have prompted research into using infrared light (IR) images. Yet, the utilization of both VL and IR images in person re-id has resulted in increased computational cost and processing time in multi-modality systems, leading to studies focusing solely on IR images. Nevertheless, IR images, lacking color and texture information, generally yield lower recognition performance in existing person re-id studies. In addition, previous studies have shown that person re-id performance suffers in the presence of complex background noise. To tackle these challenges, this study proposes a new weak saliency ensemble network (WSE-Net) for person re-id using IR images. WSE-Net incorporates a channel reduction of feature (CRF) method to reduce computational cost in the ensemble network, a technique for converting input images into group of patch images and feeding them into the ensemble model to enhance the reduced feature information, and a grouped convolution ensemble network (GCE-Net) that enables the fusion of features extracted from original and attention-guided ensemble models.</div><div>The performance of person re-id using WSE-Net was evaluated on the Dongguk body-based person recognition database version 1 (DBPerson-Recog-DB1) and the Sun Yat-sen university multiple modality re-identification version 1 (SYSU-MM01). Experimental results demonstrated that on DBPerson-Recog-DB1, WSE-Net achieved 93.65% in rank 1, 95.28% in mean average precision (mAP), and 93.52% in the harmonic mean of precision and recall. Additionally, on SYSU-MM01, WSE-Net achieved 86.85% in rank 1, 44.58% in mAP, and 40.06% in the harmonic mean of precision and recall. Furthermore, the accuracy of WSE-Net on both datasets surpassed that of state-of-the-art 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":"142533397","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

Bernstein-based oppositional-multiple learning and differential enhanced exponential distribution optimizer for real-world optimization problems 基于伯恩斯坦的对立多重学习和差分增强指数分布优化器，用于解决现实世界的优化问题

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

Engineering Applications of Artificial Intelligence

Pub Date : 2024-10-23 DOI: 10.1016/j.engappai.2024.109370

Meta-heuristic algorithms play an essential role in solving real-world optimization problems. However, their performance is limited by the complexity and variability of the problems. Hence, various efficient algorithms are being actively explored. The exponential distribution optimizer (EDO), having attracted attention for its efficient search performance, has been extended to several applications. However, it suffers from falling into local optima and weak exploitation. Meanwhile, it cannot be directly applied to solve binary optimization problems. To address these challenges, this paper proposes an enhanced EDO called BOMLDEDO. The Bernstein-assisted oppositional-multiple learning strategy is proposed to avoid falling into local optimality. The Bernstein-based adaptive differential strategy is developed to improve exploitation capability. Moreover, by introducing a transfer function, repair method, and binary-to-real operation, BOMLDEDO is extended to a binary version. The IEEE (Institute of Electrical and Electronics Engineers) CEC (Congress on Evolutionary Computation) test functions and engineering problems are used to evaluate BOMLDEDO's optimization performance for continuous problems. Compared to its competitors, BOMLDEDO ranks first on more than 8 out of 10 IEEE CEC 2020 functions and more than 10 out of 12 IEEE CEC 2022 functions. Meanwhile, it achieves the global optimum in 91% of engineering problems. Furthermore, the 0–1 knapsack problems are applied to verify BOMLDEDO's binary optimization capabilities, and the results show that BOMLDEDO is successfully utilized in 14 knapsack instances. The above results demonstrate that incorporating multiple strategies helps improve the performance of BOMLDEDO, making it more reliable and applicable in solving continuous optimization problems and 0–1 knapsack problems.

元启发式算法在解决现实世界的优化问题中发挥着至关重要的作用。然而，由于问题的复杂性和多变性，元启发式算法的性能受到了限制。因此，人们正在积极探索各种高效算法。指数分布优化器（EDO）因其高效的搜索性能而备受关注，并已推广到多个应用领域。然而，它也存在陷入局部最优和开发能力弱的问题。同时，它不能直接用于解决二元优化问题。为了解决这些难题，本文提出了一种名为 BOMLDEDO 的增强型 EDO。本文提出了伯恩斯坦辅助对立多重学习策略，以避免陷入局部最优。开发了基于伯恩斯坦的自适应差分策略，以提高利用能力。此外，通过引入传递函数、修复方法和二进制到实数的操作，BOMLDEDO 被扩展为二进制版本。IEEE（电气和电子工程师协会）CEC（进化计算大会）测试函数和工程问题用于评估 BOMLDEDO 对连续问题的优化性能。与竞争对手相比，BOMLDEDO 在 10 个 IEEE CEC 2020 函数中的 8 个函数上排名第一，在 12 个 IEEE CEC 2022 函数中的 10 个函数上排名第一。同时，它在 91% 的工程问题中实现了全局最优。此外，为了验证 BOMLDEDO 的二元优化能力，我们还应用了 0-1 包问题，结果表明 BOMLDEDO 在 14 个包实例中都取得了成功。上述结果表明，采用多种策略有助于提高 BOMLDEDO 的性能，使其在解决连续优化问题和 0-1 包问题时更加可靠和适用。

{"title":"Bernstein-based oppositional-multiple learning and differential enhanced exponential distribution optimizer for real-world optimization problems","authors":"","doi":"10.1016/j.engappai.2024.109370","DOIUrl":"10.1016/j.engappai.2024.109370","url":null,"abstract":"<div><div>Meta-heuristic algorithms play an essential role in solving real-world optimization problems. However, their performance is limited by the complexity and variability of the problems. Hence, various efficient algorithms are being actively explored. The exponential distribution optimizer (EDO), having attracted attention for its efficient search performance, has been extended to several applications. However, it suffers from falling into local optima and weak exploitation. Meanwhile, it cannot be directly applied to solve binary optimization problems. To address these challenges, this paper proposes an enhanced EDO called BOMLDEDO. The Bernstein-assisted oppositional-multiple learning strategy is proposed to avoid falling into local optimality. The Bernstein-based adaptive differential strategy is developed to improve exploitation capability. Moreover, by introducing a transfer function, repair method, and binary-to-real operation, BOMLDEDO is extended to a binary version. The IEEE (Institute of Electrical and Electronics Engineers) CEC (Congress on Evolutionary Computation) test functions and engineering problems are used to evaluate BOMLDEDO's optimization performance for continuous problems. Compared to its competitors, BOMLDEDO ranks first on more than 8 out of 10 IEEE CEC 2020 functions and more than 10 out of 12 IEEE CEC 2022 functions. Meanwhile, it achieves the global optimum in 91% of engineering problems. Furthermore, the 0–1 knapsack problems are applied to verify BOMLDEDO's binary optimization capabilities, and the results show that BOMLDEDO is successfully utilized in 14 knapsack instances. The above results demonstrate that incorporating multiple strategies helps improve the performance of BOMLDEDO, making it more reliable and applicable in solving continuous optimization problems and 0–1 knapsack problems.</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":"142534333","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