首页 > 最新文献

Engineering Applications of Artificial Intelligence最新文献

英文 中文
Prediction and evaluation of key parameters in coalbed methane pre-extraction based on transformer and inversion model 基于变压器和反演模型的煤层气预抽取关键参数预测与评估
IF 7.5 2区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-11-15 DOI: 10.1016/j.engappai.2024.109661
Li Yan, Hu Wen, Zhenping Wang, Yongfei Jin, Jun Guo, Yin Liu, Shixing Fan
Accurate parameter prediction in the coalbed methane (CBM) pre-extraction process is crucial for formulating effective control measures and preventing CBM-related accidents. Traditional prediction methods rely on feature extraction or complex physical model parameter calculations, which require extensive manual intervention and have limited practical applicability. Additionally, simple neural network methods are prone to overfitting and gradient vanishing when handling parameters, and they lack the capability to dynamically monitor gas pressure during extraction, leading to inefficient and blind extraction operations. This study proposes a CBM pre-extraction parameter and completion time prediction method based on the Transformer model. By integrating autoregressive models and wavelet denoising techniques, the approach effectively captures temporal features and long-term dependencies in CBM data. Experimental results demonstrate that the proposed model outperforms traditional methods in short-, medium-, and long-term predictions, with a median R2 value of 0.99072, and 76% of the training results exceeding 0.9. Furthermore, a CBM pressure inversion model was developed, combining dimensional analysis and physical similarity principles with the Transformer model, enabling the dynamic detection of high- and low-pressure regions in coal seams. In single borehole compliance time predictions, the median compliance time for the first stage is 4 days, with an average of 49 days and a maximum of 277 days, providing adjustment guidance for boreholes with extended compliance times. The proposed model significantly improves prediction accuracy and stability, offering critical support for developing scientifically sustainable pre-extraction plans and advancing intelligent CBM management.
煤层气预抽取过程中的精确参数预测对于制定有效的控制措施和防止煤层气相关事故至关重要。传统的预测方法依赖于特征提取或复杂的物理模型参数计算,需要大量的人工干预,实际适用性有限。此外,简单的神经网络方法在处理参数时容易出现过拟合和梯度消失的问题,而且缺乏在抽采过程中动态监测瓦斯压力的能力,导致抽采作业效率低下和盲目性。本研究提出了一种基于变压器模型的煤层气预抽采参数和完井时间预测方法。通过整合自回归模型和小波去噪技术,该方法能有效捕捉煤层气数据中的时间特征和长期依赖关系。实验结果表明,所提出的模型在短、中、长期预测方面均优于传统方法,R2 中值为 0.99072,76% 的训练结果超过 0.9。此外,结合变压器模型的尺寸分析和物理相似性原理,建立了煤层气压力反演模型,实现了煤层高低压区域的动态检测。在单个井眼达标时间预测中,第一阶段达标时间中位数为 4 天,平均为 49 天,最长为 277 天,为达标时间延长的井眼提供了调整指导。所提出的模型大大提高了预测的准确性和稳定性,为制定科学可持续的预抽采计划和推进煤层气智能管理提供了重要支持。
{"title":"Prediction and evaluation of key parameters in coalbed methane pre-extraction based on transformer and inversion model","authors":"Li Yan,&nbsp;Hu Wen,&nbsp;Zhenping Wang,&nbsp;Yongfei Jin,&nbsp;Jun Guo,&nbsp;Yin Liu,&nbsp;Shixing Fan","doi":"10.1016/j.engappai.2024.109661","DOIUrl":"10.1016/j.engappai.2024.109661","url":null,"abstract":"<div><div>Accurate parameter prediction in the coalbed methane (CBM) pre-extraction process is crucial for formulating effective control measures and preventing CBM-related accidents. Traditional prediction methods rely on feature extraction or complex physical model parameter calculations, which require extensive manual intervention and have limited practical applicability. Additionally, simple neural network methods are prone to overfitting and gradient vanishing when handling parameters, and they lack the capability to dynamically monitor gas pressure during extraction, leading to inefficient and blind extraction operations. This study proposes a CBM pre-extraction parameter and completion time prediction method based on the Transformer model. By integrating autoregressive models and wavelet denoising techniques, the approach effectively captures temporal features and long-term dependencies in CBM data. Experimental results demonstrate that the proposed model outperforms traditional methods in short-, medium-, and long-term predictions, with a median R<sup>2</sup> value of 0.99072, and 76% of the training results exceeding 0.9. Furthermore, a CBM pressure inversion model was developed, combining dimensional analysis and physical similarity principles with the Transformer model, enabling the dynamic detection of high- and low-pressure regions in coal seams. In single borehole compliance time predictions, the median compliance time for the first stage is 4 days, with an average of 49 days and a maximum of 277 days, providing adjustment guidance for boreholes with extended compliance times. The proposed model significantly improves prediction accuracy and stability, offering critical support for developing scientifically sustainable pre-extraction plans and advancing intelligent CBM management.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"139 ","pages":"Article 109661"},"PeriodicalIF":7.5,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659094","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
Health evaluation of shield tunnel lining using combination weighting and finite interval cloud model 使用组合加权和有限区间云模型对盾构隧道衬砌进行健康评估
IF 7.5 2区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-11-15 DOI: 10.1016/j.engappai.2024.109645
Yu-Wei Zhang , De-Sai Guo , Zhan-Ping Song , Yi-Duo Zhang , Lei Ruan , Zhao-Bo Yan
To solve the problem of inaccurate and unreasonable health evaluation of shield tunnel lining, a novel health evaluation model of shield tunnel lining based on the combination weighting method and finite interval cloud model is proposed. A health evaluation index system including 6 level-Ⅰ indexes and 15 level-II indexes and evaluation criteria are established for the shield tunnel lining. The weights of evaluation indexes are calculated by the game theory combination weighting method. The finite interval cloud model is used to evaluate the health of shield tunnel lining, which considers the uncertainty of various information within the interval. To verify the applicability of the proposed approach, it was applied to the shield construction section from Bei Chen Station to the Olympic Sports Center Station of Xi'an Metro Line 14. The results show that: (1) The health evaluation grade of shield tunnel lining in Samples 1–3 is level II. The result is in agreement with the actual situation which validates the practicality of the employed methodology. (2) The change in the evaluation index has little influence on the evaluation results, and the evaluation results are level II. The key risk factors were identified as U32, U31, and U12 by sensitivity analysis. Corresponding measures should be taken to ensure the stability of these three indexes and to ensure the safety of shield tunnel operation. Therefore, the proposed approach maximizes the assurance of the rationality of the evaluation results, which can be feasibly used in various applications and can provide guidance for other similar projects.
为解决盾构隧道衬砌健康评价不准确、不合理的问题,提出了一种基于组合加权法和有限区间云模型的新型盾构隧道衬砌健康评价模型。建立了盾构隧道衬砌健康评价指标体系,包括 6 个Ⅰ级指标和 15 个Ⅱ级指标及评价标准。评价指标权重采用博弈论组合权重法计算。采用有限区间云模型评价盾构隧道衬砌的健康状况,该模型考虑了区间内各种信息的不确定性。为验证所提方法的适用性,将其应用于西安地铁 14 号线北辰站至奥体中心站盾构区间。结果表明(1)样本 1-3 中盾构隧道衬砌的健康评价等级为二级。结果与实际情况相符,验证了所采用方法的实用性。(2)评价指标的变化对评价结果影响不大,评价结果为二级。通过敏感性分析,确定关键风险因素为 U32、U31 和 U12。应采取相应措施保证这三项指标的稳定性,确保盾构隧道运营安全。因此,所提出的方法最大限度地保证了评价结果的合理性,可在各种应用中进行可行性应用,并可为其他类似项目提供指导。
{"title":"Health evaluation of shield tunnel lining using combination weighting and finite interval cloud model","authors":"Yu-Wei Zhang ,&nbsp;De-Sai Guo ,&nbsp;Zhan-Ping Song ,&nbsp;Yi-Duo Zhang ,&nbsp;Lei Ruan ,&nbsp;Zhao-Bo Yan","doi":"10.1016/j.engappai.2024.109645","DOIUrl":"10.1016/j.engappai.2024.109645","url":null,"abstract":"<div><div>To solve the problem of inaccurate and unreasonable health evaluation of shield tunnel lining, a novel health evaluation model of shield tunnel lining based on the combination weighting method and finite interval cloud model is proposed. A health evaluation index system including 6 level-Ⅰ indexes and 15 level-II indexes and evaluation criteria are established for the shield tunnel lining. The weights of evaluation indexes are calculated by the game theory combination weighting method. The finite interval cloud model is used to evaluate the health of shield tunnel lining, which considers the uncertainty of various information within the interval. To verify the applicability of the proposed approach, it was applied to the shield construction section from Bei Chen Station to the Olympic Sports Center Station of Xi'an Metro Line 14. The results show that: (1) The health evaluation grade of shield tunnel lining in Samples 1–3 is level II. The result is in agreement with the actual situation which validates the practicality of the employed methodology. (2) The change in the evaluation index has little influence on the evaluation results, and the evaluation results are level II. The key risk factors were identified as <em>U</em><sub>32</sub>, <em>U</em><sub>31</sub>, and <em>U</em><sub>12</sub> by sensitivity analysis. Corresponding measures should be taken to ensure the stability of these three indexes and to ensure the safety of shield tunnel operation. Therefore, the proposed approach maximizes the assurance of the rationality of the evaluation results, which can be feasibly used in various applications and can provide guidance for other similar projects.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"139 ","pages":"Article 109645"},"PeriodicalIF":7.5,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659127","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 generative-adversarial-network-based temporal raw trace data augmentation framework for fault detection in semiconductor manufacturing 基于生成-对抗-网络的时间原始轨迹数据增强框架,用于半导体制造中的故障检测
IF 7.5 2区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-11-14 DOI: 10.1016/j.engappai.2024.109624
Shu-Kai S. Fan , Wei-Yu Chen
In modern semiconductor manufacturing, where sophisticated process control mechanisms are standard, processing tools are equipped with sensors that generate vast amounts of raw trace data for process monitoring and fault detection. However, one of the major challenges data scientists face is the scarcity of sufficient raw trace data for defective wafers, creating an imbalance that complicates the training of machine learning models for effective fault detection. To address this issue, this paper proposes novel data augmentation structures and strategies utilizing Cycle Generative Adversarial Networks (CycleGANs) as an artificial intelligence application to synthesize temporal raw trace data for defective wafers. The effectiveness of these methods is demonstrated using a real-world dataset from the thin-film process in semiconductor fabrication. Several machine learning classification models—Gaussian Naive Bayes, Adaptive Boosting, eXtreme Gradient Boosting, and Light Gradient Boosting Machine—are employed to evaluate the performance of the augmented data. The paper identifies the optimal augmentation structure and strategy to enhance classification performance within the CycleGAN-based framework. For the thin-film processing dataset under study, the best classification performance achieves an accuracy rate of up to 99.30%, with a notably low false negative rate of 6.45%.
在现代半导体制造业中,复杂的流程控制机制是标准配置,加工工具配备了传感器,可生成大量用于流程监控和故障检测的原始轨迹数据。然而,数据科学家面临的主要挑战之一是缺乏足够的缺陷晶圆原始跟踪数据,从而造成不平衡,使训练机器学习模型以进行有效故障检测变得更加复杂。为解决这一问题,本文提出了新颖的数据增强结构和策略,利用循环生成对抗网络(CycleGANs)作为人工智能应用,合成缺陷晶圆的时间原始轨迹数据。这些方法的有效性通过半导体制造中薄膜工艺的真实数据集得到了验证。本文采用了几种机器学习分类模型--高斯奈维贝叶斯模型、自适应提升模型、极梯度提升模型和轻梯度提升机模型--来评估增强数据的性能。本文确定了最佳增强结构和策略,以提高基于 CycleGAN 框架的分类性能。对于所研究的薄膜加工数据集,最佳分类性能的准确率高达 99.30%,假阴性率仅为 6.45%。
{"title":"A generative-adversarial-network-based temporal raw trace data augmentation framework for fault detection in semiconductor manufacturing","authors":"Shu-Kai S. Fan ,&nbsp;Wei-Yu Chen","doi":"10.1016/j.engappai.2024.109624","DOIUrl":"10.1016/j.engappai.2024.109624","url":null,"abstract":"<div><div>In modern semiconductor manufacturing, where sophisticated process control mechanisms are standard, processing tools are equipped with sensors that generate vast amounts of raw trace data for process monitoring and fault detection. However, one of the major challenges data scientists face is the scarcity of sufficient raw trace data for defective wafers, creating an imbalance that complicates the training of machine learning models for effective fault detection. To address this issue, this paper proposes novel data augmentation structures and strategies utilizing Cycle Generative Adversarial Networks (CycleGANs) as an artificial intelligence application to synthesize temporal raw trace data for defective wafers. The effectiveness of these methods is demonstrated using a real-world dataset from the thin-film process in semiconductor fabrication. Several machine learning classification models—Gaussian Naive Bayes, Adaptive Boosting, eXtreme Gradient Boosting, and Light Gradient Boosting Machine—are employed to evaluate the performance of the augmented data. The paper identifies the optimal augmentation structure and strategy to enhance classification performance within the CycleGAN-based framework. For the thin-film processing dataset under study, the best classification performance achieves an accuracy rate of up to 99.30%, with a notably low false negative rate of 6.45%.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"139 ","pages":"Article 109624"},"PeriodicalIF":7.5,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659042","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
An end-to-end deep convolutional neural network-based data-driven fusion framework for identification of human induced pluripotent stem cell-derived endothelial cells in photomicrographs 基于深度卷积神经网络的端到端数据驱动融合框架,用于识别显微照片中的人类诱导多能干细胞衍生内皮细胞
IF 7.5 2区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-11-14 DOI: 10.1016/j.engappai.2024.109573
Imran Iqbal , Imran Ullah , Tingying Peng , Weiwei Wang , Nan Ma
Deep learning is a very powerful analytic tool to recognize the patterns in data to make appropriate predictions. It has tremendous potential in data analyses, particularly for cell biology domain, caused by the growing scale and inherent complexity of biological data. The core purpose of this research work is to design, implement, and calibrate an efficient deep convolutional neural network (DCNN) architecture in the context of binary-class classification problem. This diversified network is developed to precisely identify human induced pluripotent stem cell-derived endothelial cells (hiPSC-derived EC) based on photomicrograph. The proposed architecture is cerebrally developed with numerous convolutional modules, multiple kernel sizes, various pooling layers, activation functions and strides, nevertheless fewer trainable parameters to strengthen the network and enhance its performance. The proposed feature fusion framework is compared with the classifier fusion approach in terms of Matthews’s correlation coefficient (MCC), training time, inference time, number of layers, number of parameters, graphics processing unit (GPU) memory utilization, and floating-point operations (FLOPS). Specifically, it achieves 94.6% sensitivity, 94.5% specificity, and 94.7% precision. Induced pluripotent stem cell (iPS) dataset is also introduced in this research work that has 16278 images which are labelled by three independent and experienced human experts of cell biology domain to facilitate future research. Experimental results show that the proposed framework offers an innovative and attainable algorithm for accelerating and systematizing the classification task along with saving time and effort.
深度学习是一种非常强大的分析工具,可以识别数据中的模式,从而做出适当的预测。由于生物数据的规模和内在复杂性不断增长,深度学习在数据分析方面具有巨大潜力,尤其是在细胞生物学领域。这项研究工作的核心目的是在二元分类问题中设计、实现和校准一个高效的深度卷积神经网络(DCNN)架构。开发的这一多样化网络可根据显微照片精确识别人类诱导多能干细胞衍生的内皮细胞(hiPSC-derived EC)。所提出的架构是通过大量卷积模块、多种内核大小、各种池化层、激活函数和步长等脑力开发出来的,但可训练参数较少,从而加强了网络并提高了其性能。从马修斯相关系数(MCC)、训练时间、推理时间、层数、参数数、图形处理器(GPU)内存利用率和浮点运算(FLOPS)等方面,对所提出的特征融合框架与分类器融合方法进行了比较。具体来说,它实现了 94.6% 的灵敏度、94.5% 的特异性和 94.7% 的精确度。这项研究工作还引入了诱导多能干细胞(iPS)数据集,该数据集有16278张图像,由三位独立且经验丰富的细胞生物学领域人类专家进行标注,以促进未来的研究。实验结果表明,所提出的框架提供了一种创新的、可实现的算法,可加速分类任务并使其系统化,同时节省时间和精力。
{"title":"An end-to-end deep convolutional neural network-based data-driven fusion framework for identification of human induced pluripotent stem cell-derived endothelial cells in photomicrographs","authors":"Imran Iqbal ,&nbsp;Imran Ullah ,&nbsp;Tingying Peng ,&nbsp;Weiwei Wang ,&nbsp;Nan Ma","doi":"10.1016/j.engappai.2024.109573","DOIUrl":"10.1016/j.engappai.2024.109573","url":null,"abstract":"<div><div>Deep learning is a very powerful analytic tool to recognize the patterns in data to make appropriate predictions. It has tremendous potential in data analyses, particularly for cell biology domain, caused by the growing scale and inherent complexity of biological data. The core purpose of this research work is to design, implement, and calibrate an efficient deep convolutional neural network (DCNN) architecture in the context of binary-class classification problem. This diversified network is developed to precisely identify human induced pluripotent stem cell-derived endothelial cells (hiPSC-derived EC) based on photomicrograph. The proposed architecture is cerebrally developed with numerous convolutional modules, multiple kernel sizes, various pooling layers, activation functions and strides, nevertheless fewer trainable parameters to strengthen the network and enhance its performance. The proposed feature fusion framework is compared with the classifier fusion approach in terms of Matthews’s correlation coefficient (MCC), training time, inference time, number of layers, number of parameters, graphics processing unit (GPU) memory utilization, and floating-point operations (FLOPS). Specifically, it achieves 94.6% sensitivity, 94.5% specificity, and 94.7% precision. Induced pluripotent stem cell (iPS) dataset is also introduced in this research work that has 16278 images which are labelled by three independent and experienced human experts of cell biology domain to facilitate future research. Experimental results show that the proposed framework offers an innovative and attainable algorithm for accelerating and systematizing the classification task along with saving time and effort.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"139 ","pages":"Article 109573"},"PeriodicalIF":7.5,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142652633","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
Rice leaf disease identification and classification using machine learning techniques: A comprehensive review 利用机器学习技术进行水稻叶病识别和分类:综述
IF 7.5 2区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-11-14 DOI: 10.1016/j.engappai.2024.109639
Rashmi Mukherjee , Anushri Ghosh , Chandan Chakraborty , Jayanta Narayan De , Debi Prasad Mishra
In recent times, various researchers attempted to develop artificial intelligence (AI) assisted techniques in the field of agriculture for early detection, surveillance and treatment related to plant leaf, seed, root, and stem diseases. Rice leaf disease detection is one of such important areas, where the crop is frequently affected by various diseases. Farmer inspects usually at a later stage causing enormous damage. This manual inspection is subjective, time-consuming and error prone. Under such situation, AI-enabled tools and techniques play crucial role for early and more precise prediction of rice diseases.
This paper demonstrates a comprehensive review on application of AI-assisted rice leaf disease detection in the last two decades. Research studies were searched using relevant keywords through the online databases [PubMed: 246; Science Direct: 100; Scopus: 56; Web of Science: 8; Willey online library:16; Cochrane:0; Cross references:20]. A total of 446 titles and abstracts were identified as suitable for this study and finally, 48 most-appropriate state-of-art articles were considered. Furthermore, this study summarizes the visual characteristics of rice leaf diseases, imaging modalities and image acquisition techniques. Various image processing techniques for infected leaf area segmentation and feature extraction were also summarized. Finally, the reported machine learning (ML) algorithms were discussed and compared in respect to their advantages and limitations. In addition, AI-enabled mobile applications for rice disease detection have been discussed.
近来,许多研究人员尝试在农业领域开发人工智能辅助技术,用于植物叶片、种子、根茎病害的早期检测、监控和治疗。水稻叶病检测就是其中一个重要领域,作物经常受到各种病害的影响。农民通常在后期才进行检查,造成巨大损失。这种人工检查主观、耗时且容易出错。在这种情况下,人工智能工具和技术在早期、更精确地预测水稻病害方面发挥着至关重要的作用。本文全面回顾了过去二十年中人工智能辅助水稻叶病检测的应用。本文通过在线数据库[PubMed: 246; Science Direct: 100; Scopus: 56; Web of Science:8;Willey 在线图书馆:16;Cochrane:0;交叉引用:20]。共确定 446 篇标题和摘要适合本研究,最后考虑了 48 篇最合适的最新文章。此外,本研究还总结了水稻叶片病害的视觉特征、成像模式和图像采集技术。还总结了用于感染叶区分割和特征提取的各种图像处理技术。最后,讨论并比较了所报告的机器学习(ML)算法的优势和局限性。此外,还讨论了用于水稻病害检测的人工智能移动应用。
{"title":"Rice leaf disease identification and classification using machine learning techniques: A comprehensive review","authors":"Rashmi Mukherjee ,&nbsp;Anushri Ghosh ,&nbsp;Chandan Chakraborty ,&nbsp;Jayanta Narayan De ,&nbsp;Debi Prasad Mishra","doi":"10.1016/j.engappai.2024.109639","DOIUrl":"10.1016/j.engappai.2024.109639","url":null,"abstract":"<div><div>In recent times, various researchers attempted to develop artificial intelligence (AI) assisted techniques in the field of agriculture for early detection, surveillance and treatment related to plant leaf, seed, root, and stem diseases. Rice leaf disease detection is one of such important areas, where the crop is frequently affected by various diseases. Farmer inspects usually at a later stage causing enormous damage. This manual inspection is subjective, time-consuming and error prone. Under such situation, AI-enabled tools and techniques play crucial role for early and more precise prediction of rice diseases.</div><div>This paper demonstrates a comprehensive review on application of AI-assisted rice leaf disease detection in the last two decades. Research studies were searched using relevant keywords through the online databases [<em>PubMed: 246; Science Direct: 100; Scopus: 56; Web of Science: 8; Willey online library:16; Cochrane:0; Cross references:20</em>]. A total of 446 titles and abstracts were identified as suitable for this study and finally, 48 most-appropriate state-of-art articles were considered. Furthermore, this study summarizes the visual characteristics of rice leaf diseases, imaging modalities and image acquisition techniques. Various image processing techniques for infected leaf area segmentation and feature extraction were also summarized. Finally, the reported machine learning (ML) algorithms were discussed and compared in respect to their advantages and limitations. In addition, AI-enabled mobile applications for rice disease detection have been discussed.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"139 ","pages":"Article 109639"},"PeriodicalIF":7.5,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659089","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
Cognitive Digital Twins of the natural environment: Framework and application 自然环境的认知数字双胞胎:框架与应用
IF 7.5 2区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-11-14 DOI: 10.1016/j.engappai.2024.109587
Jun Feng , Hailin Tang , Siyuan Zhou , Yang Cai , Jianxin Zhang
Digital Twin (DT) technology offers a method of creating digital models of natural systems to enhance their ability to withstand natural disasters. Currently, DT of the natural environment is in its initial phases, lacking adaptive capabilities and relying on human-assisted modeling. The key to endowing DT of the natural environment with greater autonomy lies in the integration of expert knowledge. Knowledge graphs can efficiently arrange and structurally store expert knowledge, thereby supporting the autonomous functionality of DT. This paper introduces the concept of Cognitive Digital Twin(CDT) derived from the industrial domain and presents a framework for CDT of the natural environment. This framework is centered around knowledge graph technology, aiming to provide more insights and guidance for system development. This framework integrates human cognition by constructing knowledge graphs of objects, models, events, and scene modes. Moreover, these knowledge graphs support agents for the dynamic adjustment of processes, as well as the adaptation and parameter optimization of related models. As a use case, we utilize this framework to implement digital twin watersheds. We develop appropriate ontologies and agents to facilitate the construction of cognitive digital watersheds for various regions. Cognitive digital watersheds effectively fulfill the application needs of integrated flood forecasting and control scheduling. This application validates the framework’s effectiveness and provides a reference for constructing CDTs of other natural systems.
数字孪生(DT)技术提供了一种创建自然系统数字模型的方法,以增强其抵御自然灾害的能力。目前,自然环境的数字孪生技术还处于初级阶段,缺乏自适应能力,依赖于人类辅助建模。赋予自然环境 DT 更大自主性的关键在于整合专家知识。知识图谱可以有效地排列和结构化地存储专家知识,从而支持 DT 的自主功能。本文介绍了源自工业领域的认知数字孪生(CDT)概念,并提出了自然环境 CDT 框架。该框架以知识图谱技术为核心,旨在为系统开发提供更多见解和指导。该框架通过构建对象、模型、事件和场景模式的知识图谱来整合人类认知。此外,这些知识图谱还支持代理对流程进行动态调整,以及对相关模型进行调整和参数优化。作为一个使用案例,我们利用这一框架实现了数字孪生流域。我们开发了适当的本体和代理,以促进为不同地区构建认知数字流域。认知数字流域有效地满足了综合洪水预报和控制调度的应用需求。该应用验证了该框架的有效性,并为构建其他自然系统的认知数字孪生流域提供了参考。
{"title":"Cognitive Digital Twins of the natural environment: Framework and application","authors":"Jun Feng ,&nbsp;Hailin Tang ,&nbsp;Siyuan Zhou ,&nbsp;Yang Cai ,&nbsp;Jianxin Zhang","doi":"10.1016/j.engappai.2024.109587","DOIUrl":"10.1016/j.engappai.2024.109587","url":null,"abstract":"<div><div>Digital Twin (DT) technology offers a method of creating digital models of natural systems to enhance their ability to withstand natural disasters. Currently, DT of the natural environment is in its initial phases, lacking adaptive capabilities and relying on human-assisted modeling. The key to endowing DT of the natural environment with greater autonomy lies in the integration of expert knowledge. Knowledge graphs can efficiently arrange and structurally store expert knowledge, thereby supporting the autonomous functionality of DT. This paper introduces the concept of <em>Cognitive Digital Twin(CDT)</em> derived from the industrial domain and presents a framework for CDT of the natural environment. This framework is centered around knowledge graph technology, aiming to provide more insights and guidance for system development. This framework integrates human cognition by constructing knowledge graphs of objects, models, events, and scene modes. Moreover, these knowledge graphs support agents for the dynamic adjustment of processes, as well as the adaptation and parameter optimization of related models. As a use case, we utilize this framework to implement digital twin watersheds. We develop appropriate ontologies and agents to facilitate the construction of cognitive digital watersheds for various regions. Cognitive digital watersheds effectively fulfill the application needs of integrated flood forecasting and control scheduling. This application validates the framework’s effectiveness and provides a reference for constructing CDTs of other natural systems.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"139 ","pages":"Article 109587"},"PeriodicalIF":7.5,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659090","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
MFLSCI: Multi-granularity fusion and label semantic correlation information for multi-label legal text classification MFLSCI:用于多标签法律文本分类的多粒度融合和标签语义相关信息
IF 7.5 2区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-11-14 DOI: 10.1016/j.engappai.2024.109604
Chunyun Meng , Yuki Todo , Cheng Tang , Li Luan , Zheng Tang
Multi-label text classification tasks face challenges such as sample diversity, complexity, and the need for effective utilization of label correlations. In this paper, we propose a model that integrates multi-granularity fusion of text sequence features and label semantic correlation information. Our model leverages graph convolutional networks to extract label semantic correlation, which enhances classification performance for samples with similar labels and addresses label omission issues. Additionally, text convolutional neural networks are employed to extract multi-granularity sense group features from text sequences, calculate their similarity with semantic correlation label distributions, and dynamically adjust the similarity between text context and label information. This approach tackles the limitations of feature extraction in short texts and label confusion. We replace the original multi-hot label encoding in model training with a label distribution that fuses text multi-granularity sense group features and label correlation information, using a more precise encoding method for soft alignment based on label probability distributions. This enhances the model’s resilience to noisy data, avoiding the issue of assigning high-confidence probabilities to incorrect categories due to hard-coded supervision. Our model’s performance improvement on noisy datasets significantly surpasses that achieved by label smoothing. Extensive experiments on three legal text datasets and two generalized multi-label datasets demonstrate the model’s excellent performance. Our approach is applicable in various real-world scenarios, such as legal judgment prediction, news categorization, and recommendation systems, where accurate multi-label classification is crucial. Ablation and experiments on noisy datasets validate the model’s effectiveness and robustness.
多标签文本分类任务面临着样本多样性、复杂性以及需要有效利用标签相关性等挑战。在本文中,我们提出了一种将文本序列特征和标签语义相关信息进行多粒度融合的模型。我们的模型利用图卷积网络提取标签语义相关性,从而提高了具有相似标签的样本的分类性能,并解决了标签遗漏问题。此外,我们还利用文本卷积神经网络从文本序列中提取多粒度感知组特征,计算它们与语义相关标签分布的相似性,并动态调整文本上下文和标签信息之间的相似性。这种方法解决了短文本特征提取和标签混淆的局限性。在模型训练中,我们用一种融合了文本多粒度感知组特征和标签相关性信息的标签分布取代了原来的多热标签编码,并使用一种基于标签概率分布的更精确的软对齐编码方法。这增强了模型对噪声数据的适应能力,避免了由于硬编码监督而将高置信度概率分配给错误类别的问题。我们的模型在嘈杂数据集上的性能改进大大超过了标签平滑法。在三个法律文本数据集和两个通用多标签数据集上的广泛实验证明了该模型的卓越性能。我们的方法适用于法律判决预测、新闻分类和推荐系统等各种实际场景,在这些场景中,准确的多标签分类至关重要。对噪声数据集的消解和实验验证了模型的有效性和鲁棒性。
{"title":"MFLSCI: Multi-granularity fusion and label semantic correlation information for multi-label legal text classification","authors":"Chunyun Meng ,&nbsp;Yuki Todo ,&nbsp;Cheng Tang ,&nbsp;Li Luan ,&nbsp;Zheng Tang","doi":"10.1016/j.engappai.2024.109604","DOIUrl":"10.1016/j.engappai.2024.109604","url":null,"abstract":"<div><div>Multi-label text classification tasks face challenges such as sample diversity, complexity, and the need for effective utilization of label correlations. In this paper, we propose a model that integrates multi-granularity fusion of text sequence features and label semantic correlation information. Our model leverages graph convolutional networks to extract label semantic correlation, which enhances classification performance for samples with similar labels and addresses label omission issues. Additionally, text convolutional neural networks are employed to extract multi-granularity sense group features from text sequences, calculate their similarity with semantic correlation label distributions, and dynamically adjust the similarity between text context and label information. This approach tackles the limitations of feature extraction in short texts and label confusion. We replace the original multi-hot label encoding in model training with a label distribution that fuses text multi-granularity sense group features and label correlation information, using a more precise encoding method for soft alignment based on label probability distributions. This enhances the model’s resilience to noisy data, avoiding the issue of assigning high-confidence probabilities to incorrect categories due to hard-coded supervision. Our model’s performance improvement on noisy datasets significantly surpasses that achieved by label smoothing. Extensive experiments on three legal text datasets and two generalized multi-label datasets demonstrate the model’s excellent performance. Our approach is applicable in various real-world scenarios, such as legal judgment prediction, news categorization, and recommendation systems, where accurate multi-label classification is crucial. Ablation and experiments on noisy datasets validate the model’s effectiveness and robustness.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"139 ","pages":"Article 109604"},"PeriodicalIF":7.5,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659125","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
Time-aware cross-domain point-of-interest recommendation in social networks 社交网络中的时间感知跨域兴趣点推荐
IF 7.5 2区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-11-13 DOI: 10.1016/j.engappai.2024.109630
Malika Acharya, Krishna Kumar Mohbey
Point-of-Interest recommendation within the single domain is quite easy compared to the cross-domain recommendation, as there is an acute dearth of check-in records for the target regions, aggravating the cold start problem. We propose a self-ensembled contextual Thompson sampling for cross-domain Point-of-Interest recommendation to solve this. This approach utilizes user preference transfer and user preference drift in the target domain for enhanced recommendation by deploying enhanced contextual sampling. As the user-context pairs of the target domain are not labeled for the given user, domain adaptation is highly sought. The approach has four major steps: i) Mining Point-of-Interests based on the long-term preferences of the target user and the user with a similar trajectory in the source domain, ii) Computing rewards for the Point-of-Interests in the source domain using multi-layer perceptron, iii) Estimate the rewards for unlabeled Point-of-Interests in the target domain and iv) Form the ensemble of rewards that are used to decide the final arm pulls. The rewards obtained for Point-of-Interests in the source and target domain are combined to form an ensemble of rewards with the help of self ensembling domain adaptation technique. Each Point-of-Interest in the ensemble rewards is termed an arm of action. We use this ensemble of rewards to control the diversity measure and the switching probability of the various arms, potential Point-of-Interests, in the contextual Thompson Sampling. Contextual Thompson sampling is modified to incorporate exploitation-exploration tradeoffs using this reward ensemble. The implicit weight measure of the different arms decides the probability of exploitation or exploration. The final arm pulls results in the final Point-of-Interest recommendation. For experimentation, we have used two real-world datasets, namely, Gowalla and Foursquare, and extracted the data for seven domains. We have obtained an accuracy of approximately 65% for Point-of-Interest recommendations on cold-start users.
与跨域推荐相比,单域内的兴趣点推荐相当容易,因为目标区域的签到记录非常缺乏,加剧了冷启动问题。为了解决这个问题,我们提出了一种用于跨域兴趣点推荐的自组装上下文汤普森采样方法。这种方法通过部署增强型上下文抽样,利用目标域的用户偏好转移和用户偏好漂移来增强推荐。由于目标域的用户-上下文对没有为给定用户贴标签,因此需要高度寻求域适应性。该方法有四个主要步骤:i) 根据目标用户和源领域中轨迹相似的用户的长期偏好挖掘兴趣点;ii) 使用多层感知器计算源领域中兴趣点的奖励;iii) 估算目标领域中未标记的兴趣点的奖励;iv) 形成用于决定最终臂拉的奖励组合。在自集合域自适应技术的帮助下,源域和目标域中兴趣点获得的奖励被组合在一起,形成一个奖励集合。集合奖励中的每个兴趣点被称为一个行动臂。我们利用这种奖励集合来控制多样性度量以及上下文汤普森采样中各种臂(潜在兴趣点)的切换概率。对情境汤普森采样进行了修改,以便利用这种奖励组合来权衡开发与探索之间的关系。不同臂的隐含权重衡量决定了开发或探索的概率。最后的臂拉结果就是最终的兴趣点推荐。在实验中,我们使用了两个真实世界的数据集,即 Gowalla 和 Foursquare,并提取了七个领域的数据。我们对冷启动用户的兴趣点推荐准确率约为 65%。
{"title":"Time-aware cross-domain point-of-interest recommendation in social networks","authors":"Malika Acharya,&nbsp;Krishna Kumar Mohbey","doi":"10.1016/j.engappai.2024.109630","DOIUrl":"10.1016/j.engappai.2024.109630","url":null,"abstract":"<div><div>Point-of-Interest recommendation within the single domain is quite easy compared to the cross-domain recommendation, as there is an acute dearth of check-in records for the target regions, aggravating the cold start problem. We propose a self-ensembled contextual Thompson sampling for cross-domain Point-of-Interest recommendation to solve this. This approach utilizes user preference transfer and user preference drift in the target domain for enhanced recommendation by deploying enhanced contextual sampling. As the user-context pairs of the target domain are not labeled for the given user, domain adaptation is highly sought. The approach has four major steps: i) Mining Point-of-Interests based on the long-term preferences of the target user and the user with a similar trajectory in the source domain, ii) Computing rewards for the Point-of-Interests in the source domain using multi-layer perceptron, iii) Estimate the rewards for unlabeled Point-of-Interests in the target domain and iv) Form the ensemble of rewards that are used to decide the final arm pulls. The rewards obtained for Point-of-Interests in the source and target domain are combined to form an ensemble of rewards with the help of self ensembling domain adaptation technique. Each Point-of-Interest in the ensemble rewards is termed an arm of action. We use this ensemble of rewards to control the diversity measure and the switching probability of the various arms, potential Point-of-Interests, in the contextual Thompson Sampling. Contextual Thompson sampling is modified to incorporate exploitation-exploration tradeoffs using this reward ensemble. The implicit weight measure of the different arms decides the probability of exploitation or exploration. The final arm pulls results in the final Point-of-Interest recommendation. For experimentation, we have used two real-world datasets, namely, Gowalla and Foursquare, and extracted the data for seven domains. We have obtained an accuracy of approximately 65% for Point-of-Interest recommendations on cold-start users.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"139 ","pages":"Article 109630"},"PeriodicalIF":7.5,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659276","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 framework for robust glaucoma detection: A confidence-aware deep uncertainty quantification approach with a comprehensive assessment for enhanced clinical decision-making 稳健青光眼检测框架:可信度感知的深度不确定性量化方法与综合评估,促进临床决策
IF 7.5 2区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-11-13 DOI: 10.1016/j.engappai.2024.109651
Javad Zarean , AmirReza Tajally , Reza Tavakkoli-Moghaddam , Seyed Mojtaba Sajadi , Niaz Wassan
Glaucoma poses a significant threat to public health worldwide, as it can result in irreversible vision loss. Timely identification is vital for halting the progression of visual field deterioration. In recent years, deep neural networks (DNNs) have become increasingly popular in medical imaging due to their ability to identify patterns. As a result, this study introduces a new computer-aided diagnosis (CAD) system based on deep learning (DL) algorithms for glaucoma detection that extracts meaningful features from retinal fundus images (RFIs) and employs uncertainty quantification (UQ) models, including Monte Carlo dropout (MCD), ensemble Bayesian, and ensemble Monte Carlo dropout (EMCD), to generate both point estimates and confidence values for the outputs, thereby capturing the uncertainty associated with the classifications. The proposed framework is validated using well-known clinical datasets, and the reliability of the outputs is evaluated using comprehensive performance metrics such as expected calibration error (ECE), entropy analysis, and a multi-criteria UQ assessment. Experimental results demonstrate the superiority of the ensemble model, with uncertainty accuracies registering at 97.64%, 97.26%, and 98.97% for the “ACRIMA”, “RIM-ONE-DL”, and “ORIGA” datasets, respectively. Moreover, the proposed algorithms can alert users to the majority of erroneous diagnoses by assigning uncertainty labels, providing valuable insights for clinicians in glaucoma detection. Such tools can assist healthcare professionals in reducing the probability of misdiagnosis and ensuring that patients receive timely and appropriate treatment.
青光眼可导致不可逆转的视力丧失,对全球公众健康构成重大威胁。及时识别对于阻止视野恶化的进展至关重要。近年来,深度神经网络(DNN)凭借其识别模式的能力在医学成像领域越来越受欢迎。因此,本研究介绍了一种基于深度学习(DL)算法的新型计算机辅助诊断(CAD)系统,该系统用于青光眼检测,可从视网膜眼底图像(RFIs)中提取有意义的特征,并采用不确定性量化(UQ)模型,包括蒙特卡罗剔除(MCD)、集合贝叶斯(Bayesian)和集合蒙特卡罗剔除(EMCD)模型,为输出结果生成点估计和置信度值,从而捕捉与分类相关的不确定性。利用著名的临床数据集对所提出的框架进行了验证,并利用预期校准误差 (ECE)、熵分析和多标准 UQ 评估等综合性能指标对输出的可靠性进行了评估。实验结果表明了集合模型的优越性,"ACRIMA"、"RIM-ONE-DL "和 "ORIGA "数据集的不确定性准确率分别为 97.64%、97.26% 和 98.97%。此外,所提出的算法还能通过分配不确定性标签,提醒用户注意大多数错误诊断,为临床医生检测青光眼提供有价值的见解。这些工具可以帮助医护人员降低误诊概率,确保患者得到及时、适当的治疗。
{"title":"A framework for robust glaucoma detection: A confidence-aware deep uncertainty quantification approach with a comprehensive assessment for enhanced clinical decision-making","authors":"Javad Zarean ,&nbsp;AmirReza Tajally ,&nbsp;Reza Tavakkoli-Moghaddam ,&nbsp;Seyed Mojtaba Sajadi ,&nbsp;Niaz Wassan","doi":"10.1016/j.engappai.2024.109651","DOIUrl":"10.1016/j.engappai.2024.109651","url":null,"abstract":"<div><div>Glaucoma poses a significant threat to public health worldwide, as it can result in irreversible vision loss. Timely identification is vital for halting the progression of visual field deterioration. In recent years, deep neural networks (DNNs) have become increasingly popular in medical imaging due to their ability to identify patterns. As a result, this study introduces a new computer-aided diagnosis (CAD) system based on deep learning (DL) algorithms for glaucoma detection that extracts meaningful features from retinal fundus images (RFIs) and employs uncertainty quantification (UQ) models, including Monte Carlo dropout (MCD), ensemble Bayesian, and ensemble Monte Carlo dropout (EMCD), to generate both point estimates and confidence values for the outputs, thereby capturing the uncertainty associated with the classifications. The proposed framework is validated using well-known clinical datasets, and the reliability of the outputs is evaluated using comprehensive performance metrics such as expected calibration error (ECE), entropy analysis, and a multi-criteria UQ assessment. Experimental results demonstrate the superiority of the ensemble model, with uncertainty accuracies registering at 97.64%, 97.26%, and 98.97% for the <em>“ACRIMA”</em>, <em>“RIM-ONE-DL”</em>, and <em>“ORIGA”</em> datasets, respectively. Moreover, the proposed algorithms can alert users to the majority of erroneous diagnoses by assigning uncertainty labels, providing valuable insights for clinicians in glaucoma detection. Such tools can assist healthcare professionals in reducing the probability of misdiagnosis and ensuring that patients receive timely and appropriate treatment.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"139 ","pages":"Article 109651"},"PeriodicalIF":7.5,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659098","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
An intelligent model approach for leakage detection of modified atmosphere pillow bags 用于检测改良气氛枕袋泄漏的智能模型方法
IF 7.5 2区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS Pub Date : 2024-11-13 DOI: 10.1016/j.engappai.2024.109611
Xiangdong Guo , Jingfa Yao , Guoyu Yan , Guifa Teng
Modified atmosphere pillow bags have been widely used to package various food products due to their advantages for preservation and shipment. Sealing defects are statistically inevitable, although modern packaging machinery and manual inspection utilized by manufacturers continue reducing the leakage probability. Hence the bag contents may spoil if the seal is broken. Instead of manual inspection and various destructive methods utilized by factories, this study introduces non-destructive leakage detection using deep learning methods. Firstly, a squeezing method is developed to aggravate the feature difference between positive samples and negative samples without destroying the bag content, thus 2160 images of three different pillow bags are acquired to establish dataset. Secondly, the deep learning model Vision Transformer (ViT) is deployed and studied so that feasibility of computer vision method is verified. Then the Semantic segmentation and Contour Extraction model combining ViT (SCE-ViT) is proposed and improved to the Multi-dimensional Fusion model (SCE-MdF). The accuracies of SCE-MdF reached 97.5%, 97.5%, and 97.5%, respectively. The F1-scores of SCE-MdF reached 97.6%, 97.6%, and 97.4%, respectively. Compared to averaged accuracies of SCE-ViT, accuracies introduced in the ultimate model SCE-MdF improved by 19.17%, 5.84%, and 11.67%, respectively. Therefore, combination of unique squeezing method and Semantic segmentation Contour Extraction with Multi-dimensional Fused ViT, is eventually validated viable on leakage detection of modified atmosphere pillow bags. Hence a cost-effective, efficient and non-destructive leakage detection method for modified atmosphere pillow bags in relevant industry is introduced, filling a gap between artificial intelligence and food packaging industry.
改良气调枕式包装袋因其在保存和运输方面的优势而被广泛用于包装各种食品。尽管现代包装机械和制造商使用的人工检测不断降低泄漏概率,但从统计学角度看,密封缺陷是不可避免的。因此,如果封口被破坏,袋中物品可能会变质。本研究采用深度学习方法进行非破坏性泄漏检测,而不是工厂使用的人工检测和各种破坏性方法。首先,研究人员开发了一种挤压方法,在不破坏包装袋内容物的情况下加剧正样本和负样本之间的特征差异,从而获取 2160 张三种不同枕头包装袋的图像来建立数据集。其次,部署并研究了深度学习模型 Vision Transformer(ViT),从而验证了计算机视觉方法的可行性。然后,提出了结合 ViT 的语义分割和轮廓提取模型(SCE-ViT),并将其改进为多维融合模型(SCE-MdF)。SCE-MdF 的准确率分别达到 97.5%、97.5% 和 97.5%。SCE-MdF 的 F1 分数分别达到 97.6%、97.6% 和 97.4%。与 SCE-ViT 的平均精度相比,终极模型 SCE-MdF 引入的精度分别提高了 19.17%、5.84% 和 11.67%。因此,将独特的挤压方法和语义分割轮廓提取与多维融合 ViT 相结合,最终在改良气调枕袋的泄漏检测中得到了验证。因此,在相关行业中引入了一种经济、高效、无损的改性气调枕袋泄漏检测方法,填补了人工智能与食品包装行业之间的空白。
{"title":"An intelligent model approach for leakage detection of modified atmosphere pillow bags","authors":"Xiangdong Guo ,&nbsp;Jingfa Yao ,&nbsp;Guoyu Yan ,&nbsp;Guifa Teng","doi":"10.1016/j.engappai.2024.109611","DOIUrl":"10.1016/j.engappai.2024.109611","url":null,"abstract":"<div><div>Modified atmosphere pillow bags have been widely used to package various food products due to their advantages for preservation and shipment. Sealing defects are statistically inevitable, although modern packaging machinery and manual inspection utilized by manufacturers continue reducing the leakage probability. Hence the bag contents may spoil if the seal is broken. Instead of manual inspection and various destructive methods utilized by factories, this study introduces non-destructive leakage detection using deep learning methods. Firstly, a squeezing method is developed to aggravate the feature difference between positive samples and negative samples without destroying the bag content, thus 2160 images of three different pillow bags are acquired to establish dataset. Secondly, the deep learning model Vision Transformer (ViT) is deployed and studied so that feasibility of computer vision method is verified. Then the Semantic segmentation and Contour Extraction model combining ViT (SCE-ViT) is proposed and improved to the Multi-dimensional Fusion model (SCE-MdF). The accuracies of SCE-MdF reached 97.5%, 97.5%, and 97.5%, respectively. The F1-scores of SCE-MdF reached 97.6%, 97.6%, and 97.4%, respectively. Compared to averaged accuracies of SCE-ViT, accuracies introduced in the ultimate model SCE-MdF improved by 19.17%, 5.84%, and 11.67%, respectively. Therefore, combination of unique squeezing method and Semantic segmentation Contour Extraction with Multi-dimensional Fused ViT, is eventually validated viable on leakage detection of modified atmosphere pillow bags. Hence a cost-effective, efficient and non-destructive leakage detection method for modified atmosphere pillow bags in relevant industry is introduced, filling a gap between artificial intelligence and food packaging industry.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"139 ","pages":"Article 109611"},"PeriodicalIF":7.5,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659278","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