Cross-project defect prediction (CPDP) aims to predict software defects in a target project domain by leveraging information from different source project domains, allowing testers to identify defective modules quickly. However, CPDP models often underperform due to different data distributions between source and target domains, class imbalances, and the presence of noisy and irrelevant instances in both source and target projects. Additionally, standard features often fail to capture sufficient semantic and contextual information from the source project, leading to poor prediction performance in the target project. To address these challenges, this research proposes Smote Correlation and Attention Gated recurrent unit based Long Short-Term Memory optimization (SCAG-LSTM), which first employs a novel hybrid technique that extends the synthetic minority over-sampling technique (SMOTE) with edited nearest neighbors (ENN) to rebalance class distributions and mitigate the issues caused by noisy and irrelevant instances in both source and target domains. Furthermore, correlation-based feature selection (CFS) with best-first search (BFS) is utilized to identify and select the most important features, aiming to reduce the differences in data distribution among projects. Additionally, SCAG-LSTM integrates bidirectional gated recurrent unit (Bi-GRU) and bidirectional long short-term memory (Bi-LSTM) networks to enhance the effectiveness of the long short-term memory (LSTM) model. These components efficiently capture semantic and contextual information as well as dependencies within the data, leading to more accurate predictions. Moreover, an attention mechanism is incorporated into the model to focus on key features, further improving prediction performance. Experiments are conducted on apache_lucene, equinox, eclipse_jdt_core, eclipse_pde_ui, and mylyn (AEEEM) and predictor models in software engineering (PROMISE) datasets and compared with active learning-based method (ALTRA), multi-source-based cross-project defect prediction method (MSCPDP), the two-phase feature importance amplification method (TFIA) on AEEEM and the two-phase transfer learning method (TPTL), domain adaptive kernel twin support vector machines method (DA-KTSVMO), and generative adversarial long-short term memory neural networks method (GB-CPDP) on PROMISE datasets. The results demonstrate that the proposed SCAG-LSTM model enhances the baseline models by 33.03%, 29.15% and 1.48% in terms of F1- measure and by 16.32%, 34.41% and 3.59% in terms of Area Under the Curve (AUC) on the AEEEM dataset, while on the PROMISE dataset it enhances the baseline models’ F1- measure by 42.60%, 32.00% and 25.10% and AUC by 34.90%, 27.80% and 12.96%. These findings suggest that the proposed model exhibits strong predictive performance.
{"title":"Cross-Project Defect Prediction Based on Domain Adaptation and LSTM Optimization","authors":"Khadija Javed, Shengbing Ren, M. Asim, M. A. Wani","doi":"10.3390/a17050175","DOIUrl":"https://doi.org/10.3390/a17050175","url":null,"abstract":"Cross-project defect prediction (CPDP) aims to predict software defects in a target project domain by leveraging information from different source project domains, allowing testers to identify defective modules quickly. However, CPDP models often underperform due to different data distributions between source and target domains, class imbalances, and the presence of noisy and irrelevant instances in both source and target projects. Additionally, standard features often fail to capture sufficient semantic and contextual information from the source project, leading to poor prediction performance in the target project. To address these challenges, this research proposes Smote Correlation and Attention Gated recurrent unit based Long Short-Term Memory optimization (SCAG-LSTM), which first employs a novel hybrid technique that extends the synthetic minority over-sampling technique (SMOTE) with edited nearest neighbors (ENN) to rebalance class distributions and mitigate the issues caused by noisy and irrelevant instances in both source and target domains. Furthermore, correlation-based feature selection (CFS) with best-first search (BFS) is utilized to identify and select the most important features, aiming to reduce the differences in data distribution among projects. Additionally, SCAG-LSTM integrates bidirectional gated recurrent unit (Bi-GRU) and bidirectional long short-term memory (Bi-LSTM) networks to enhance the effectiveness of the long short-term memory (LSTM) model. These components efficiently capture semantic and contextual information as well as dependencies within the data, leading to more accurate predictions. Moreover, an attention mechanism is incorporated into the model to focus on key features, further improving prediction performance. Experiments are conducted on apache_lucene, equinox, eclipse_jdt_core, eclipse_pde_ui, and mylyn (AEEEM) and predictor models in software engineering (PROMISE) datasets and compared with active learning-based method (ALTRA), multi-source-based cross-project defect prediction method (MSCPDP), the two-phase feature importance amplification method (TFIA) on AEEEM and the two-phase transfer learning method (TPTL), domain adaptive kernel twin support vector machines method (DA-KTSVMO), and generative adversarial long-short term memory neural networks method (GB-CPDP) on PROMISE datasets. The results demonstrate that the proposed SCAG-LSTM model enhances the baseline models by 33.03%, 29.15% and 1.48% in terms of F1- measure and by 16.32%, 34.41% and 3.59% in terms of Area Under the Curve (AUC) on the AEEEM dataset, while on the PROMISE dataset it enhances the baseline models’ F1- measure by 42.60%, 32.00% and 25.10% and AUC by 34.90%, 27.80% and 12.96%. These findings suggest that the proposed model exhibits strong predictive performance.","PeriodicalId":502609,"journal":{"name":"Algorithms","volume":"55 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140662665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
To tackle the problem of the brain storm optimization (BSO) algorithm’s suboptimal capability for avoiding local optima, which contributes to its inadequate optimization precision, we developed a flock decision mutation approach that substantially enhances the efficacy of the BSO algorithm. Furthermore, to solve the problem of insufficient BSO algorithm population diversity, we introduced a strategy that utilizes the good point set to enhance the initial population’s quality. Simultaneously, we substituted the K-means clustering approach with spectral clustering to improve the clustering accuracy of the algorithm. This work introduced an enhanced version of the brain storm optimization algorithm founded on a flock decision mutation strategy (FDIBSO). The improved algorithm was compared against contemporary leading algorithms through the CEC2018. The experimental section additionally employs the AUV intelligence evaluation as an application case. It addresses the combined weight model under various dimensional settings to substantiate the efficacy of the FDIBSO algorithm further. The findings indicate that FDIBSO surpasses BSO and other enhanced algorithms for addressing intricate optimization challenges.
{"title":"Improved Brain Storm Optimization Algorithm Based on Flock Decision Mutation Strategy","authors":"Yanchi Zhao, Jia-Ping Cheng, Jing Cai","doi":"10.3390/a17050172","DOIUrl":"https://doi.org/10.3390/a17050172","url":null,"abstract":"To tackle the problem of the brain storm optimization (BSO) algorithm’s suboptimal capability for avoiding local optima, which contributes to its inadequate optimization precision, we developed a flock decision mutation approach that substantially enhances the efficacy of the BSO algorithm. Furthermore, to solve the problem of insufficient BSO algorithm population diversity, we introduced a strategy that utilizes the good point set to enhance the initial population’s quality. Simultaneously, we substituted the K-means clustering approach with spectral clustering to improve the clustering accuracy of the algorithm. This work introduced an enhanced version of the brain storm optimization algorithm founded on a flock decision mutation strategy (FDIBSO). The improved algorithm was compared against contemporary leading algorithms through the CEC2018. The experimental section additionally employs the AUV intelligence evaluation as an application case. It addresses the combined weight model under various dimensional settings to substantiate the efficacy of the FDIBSO algorithm further. The findings indicate that FDIBSO surpasses BSO and other enhanced algorithms for addressing intricate optimization challenges.","PeriodicalId":502609,"journal":{"name":"Algorithms","volume":"12 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140666986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Bo Jiang, Guofu Ding, Jianlin Fu, Jian Zhang, Yong Zhang
The research on baggage flow plays a pivotal role in achieving the efficient and intelligent allocation and scheduling of airport service resources, as well as serving as a fundamental element in determining the design, development, and process optimization of airport baggage handling systems. This paper examines baggage checked in by departing passengers at airports. The crrent state of the research on baggage flow demand is first reviewed and analyzed. Then, using examples of objective data, it is concluded that while there is a significant correlation between airport passenger flow and baggage flow, an increase in passenger flow does not necessarily result in a proportional increase in baggage flow. According to the existing research results on the influencing factors of baggage flow sorting and classification, the main influencing factors of baggage flow are divided into two categories: macro-influencing factors and micro-influencing factors. When studying the relationship between the economy and baggage flow, it is recommended to use a comprehensive analysis that includes multiple economic indicators, rather than relying solely on GDP. This paper provides a brief overview of prevalent transportation flow prediction methods, categorizing algorithmic models into three groups: based on mathematical and statistical models, intelligent algorithmic-based models, and combined algorithmic models utilizing artificial neural networks. The structures, strengths, and weaknesses of various transportation flow prediction algorithms are analyzed, as well as their application scenarios. The potential advantages of using artificial neural network-based combined prediction models for baggage flow forecasting are explained. It concludes with an outlook on research regarding the demand for baggage flow. This review may provide further research assistance to scholars in airport management and baggage handling system development.
{"title":"An Overview of Demand Analysis and Forecasting Algorithms for the Flow of Checked Baggage among Departing Passengers","authors":"Bo Jiang, Guofu Ding, Jianlin Fu, Jian Zhang, Yong Zhang","doi":"10.3390/a17050173","DOIUrl":"https://doi.org/10.3390/a17050173","url":null,"abstract":"The research on baggage flow plays a pivotal role in achieving the efficient and intelligent allocation and scheduling of airport service resources, as well as serving as a fundamental element in determining the design, development, and process optimization of airport baggage handling systems. This paper examines baggage checked in by departing passengers at airports. The crrent state of the research on baggage flow demand is first reviewed and analyzed. Then, using examples of objective data, it is concluded that while there is a significant correlation between airport passenger flow and baggage flow, an increase in passenger flow does not necessarily result in a proportional increase in baggage flow. According to the existing research results on the influencing factors of baggage flow sorting and classification, the main influencing factors of baggage flow are divided into two categories: macro-influencing factors and micro-influencing factors. When studying the relationship between the economy and baggage flow, it is recommended to use a comprehensive analysis that includes multiple economic indicators, rather than relying solely on GDP. This paper provides a brief overview of prevalent transportation flow prediction methods, categorizing algorithmic models into three groups: based on mathematical and statistical models, intelligent algorithmic-based models, and combined algorithmic models utilizing artificial neural networks. The structures, strengths, and weaknesses of various transportation flow prediction algorithms are analyzed, as well as their application scenarios. The potential advantages of using artificial neural network-based combined prediction models for baggage flow forecasting are explained. It concludes with an outlook on research regarding the demand for baggage flow. This review may provide further research assistance to scholars in airport management and baggage handling system development.","PeriodicalId":502609,"journal":{"name":"Algorithms","volume":"72 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140670501","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Michalis Pingos, Panayiotis Christodoulou, Andreas S. Andreou
Data meshes are an approach to data architecture and organization that treats data as a product and focuses on decentralizing data ownership and access. It has recently emerged as a field that presents quite a few challenges related to data ownership, governance, security, monitoring, and observability. To address these challenges, this paper introduces an innovative algorithmic framework leveraging data blueprints to enable the dynamic creation of data meshes and data products in response to user requests, ensuring that stakeholders have access to specific portions of the data mesh as needed. Ownership and governance concerns are addressed through a unique mechanism involving Blockchain and Non-Fungible Tokens (NFTs). This facilitates the secure and transparent transfer of data ownership, with the ability to mint time-based NFTs. By combining these advancements with the fundamental tenets of data meshes, this research offers a comprehensive solution to the challenges surrounding data ownership and governance. It empowers stakeholders to navigate the complexities of data management within a decentralized architecture, ensuring a secure, efficient, and user-centric approach to data utilization. The proposed framework is demonstrated using real-world data from a poultry meat production factory.
{"title":"Security and Ownership in User-Defined Data Meshes","authors":"Michalis Pingos, Panayiotis Christodoulou, Andreas S. Andreou","doi":"10.3390/a17040169","DOIUrl":"https://doi.org/10.3390/a17040169","url":null,"abstract":"Data meshes are an approach to data architecture and organization that treats data as a product and focuses on decentralizing data ownership and access. It has recently emerged as a field that presents quite a few challenges related to data ownership, governance, security, monitoring, and observability. To address these challenges, this paper introduces an innovative algorithmic framework leveraging data blueprints to enable the dynamic creation of data meshes and data products in response to user requests, ensuring that stakeholders have access to specific portions of the data mesh as needed. Ownership and governance concerns are addressed through a unique mechanism involving Blockchain and Non-Fungible Tokens (NFTs). This facilitates the secure and transparent transfer of data ownership, with the ability to mint time-based NFTs. By combining these advancements with the fundamental tenets of data meshes, this research offers a comprehensive solution to the challenges surrounding data ownership and governance. It empowers stakeholders to navigate the complexities of data management within a decentralized architecture, ensuring a secure, efficient, and user-centric approach to data utilization. The proposed framework is demonstrated using real-world data from a poultry meat production factory.","PeriodicalId":502609,"journal":{"name":"Algorithms","volume":"29 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140673025","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
María Guijarro, Juan Bayon, Daniel Martín-Carabias, Joaquín Recas
A logotype is a rectangular region defined by a set of characteristics, which come from the pixel information and region shape, that differ from those of the text. In this paper, a new method for automatic logo detection is proposed and tested using the public Tobacco800 database. Our method outputs a set of regions from an official document with a high probability to contain a logo using a new approach based on the variation of the feature rectangles method available in the literature. Candidate regions were computed using the longest increasing run algorithm over the document blank lines’ indices. Those regions were further refined by using a feature-rectangle-expansion method with forward checking, where the rectangle expansion can occur in parallel in each region. Finally, a C4.5 decision tree was trained and tested against a set of 1291 official documents to evaluate its performance. The strategic combination of the three previous steps offers a precision and recall for logo detention of 98.9% and 89.9%, respectively, being also resistant to noise and low-quality documents. The method is also able to reduce the processing area of the document while maintaining a low percentage of false negatives.
{"title":"A Multi-Stage Method for Logo Detection in Scanned Official Documents Based on Image Processing","authors":"María Guijarro, Juan Bayon, Daniel Martín-Carabias, Joaquín Recas","doi":"10.3390/a17040170","DOIUrl":"https://doi.org/10.3390/a17040170","url":null,"abstract":"A logotype is a rectangular region defined by a set of characteristics, which come from the pixel information and region shape, that differ from those of the text. In this paper, a new method for automatic logo detection is proposed and tested using the public Tobacco800 database. Our method outputs a set of regions from an official document with a high probability to contain a logo using a new approach based on the variation of the feature rectangles method available in the literature. Candidate regions were computed using the longest increasing run algorithm over the document blank lines’ indices. Those regions were further refined by using a feature-rectangle-expansion method with forward checking, where the rectangle expansion can occur in parallel in each region. Finally, a C4.5 decision tree was trained and tested against a set of 1291 official documents to evaluate its performance. The strategic combination of the three previous steps offers a precision and recall for logo detention of 98.9% and 89.9%, respectively, being also resistant to noise and low-quality documents. The method is also able to reduce the processing area of the document while maintaining a low percentage of false negatives.","PeriodicalId":502609,"journal":{"name":"Algorithms","volume":"48 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140676252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Niels Wessel, M. Sprincean, Ludmila Sidorenko, N. Revenco, S. Hadjiu
Childhood stroke can lead to lifelong disability. Developing algorithms for timely recognition of clinical and paraclinical signs is crucial to ensure prompt stroke diagnosis and minimize decision-making time. This study aimed to characterize clinical and paraclinical symptoms of childhood and neonatal stroke as relevant diagnostic criteria encountered in clinical practice, in order to develop algorithms for prompt stroke diagnosis. The analysis included data from 402 pediatric case histories from 2010 to 2016 and 108 prospective stroke cases from 2017 to 2020. Stroke cases were predominantly diagnosed in newborns, with 362 (71%, 95% CI 68.99–73.01) cases occurring within the first 28 days of birth, and 148 (29%, 95% CI 26.99–31.01) cases occurring after 28 days. The findings of the study enable the development of algorithms for timely stroke recognition, facilitating the selection of optimal treatment options for newborns and children of various age groups. Logistic regression serves as the basis for deriving these algorithms, aiming to initiate early treatment and reduce lifelong morbidity and mortality in children. The study outcomes include the formulation of algorithms for timely recognition of newborn stroke, with plans to adopt these algorithms and train a fuzzy classifier-based diagnostic model using machine learning techniques for efficient stroke recognition.
儿童中风可导致终身残疾。制定及时识别临床和辅助临床症状的算法对于确保及时诊断中风和减少决策时间至关重要。本研究旨在描述儿童和新生儿卒中的临床和副临床症状，作为临床实践中遇到的相关诊断标准，从而开发出及时诊断卒中的算法。分析包括 2010 年至 2016 年的 402 例儿科病历数据和 2017 年至 2020 年的 108 例前瞻性中风病例数据。脑卒中病例主要在新生儿中确诊，其中362例（71%，95% CI 68.99-73.01）发生在出生后28天内，148例（29%，95% CI 26.99-31.01）发生在28天后。研究结果有助于制定及时识别中风的算法，为新生儿和各年龄组儿童选择最佳治疗方案提供便利。逻辑回归是推导这些算法的基础，旨在启动早期治疗，降低儿童的终生发病率和死亡率。研究成果包括制定了及时识别新生儿中风的算法，并计划采用这些算法，利用机器学习技术训练基于模糊分类器的诊断模型，以高效识别中风。
{"title":"Pediatric Ischemic Stroke: Clinical and Paraclinical Manifestations—Algorithms for Diagnosis and Treatment","authors":"Niels Wessel, M. Sprincean, Ludmila Sidorenko, N. Revenco, S. Hadjiu","doi":"10.3390/a17040171","DOIUrl":"https://doi.org/10.3390/a17040171","url":null,"abstract":"Childhood stroke can lead to lifelong disability. Developing algorithms for timely recognition of clinical and paraclinical signs is crucial to ensure prompt stroke diagnosis and minimize decision-making time. This study aimed to characterize clinical and paraclinical symptoms of childhood and neonatal stroke as relevant diagnostic criteria encountered in clinical practice, in order to develop algorithms for prompt stroke diagnosis. The analysis included data from 402 pediatric case histories from 2010 to 2016 and 108 prospective stroke cases from 2017 to 2020. Stroke cases were predominantly diagnosed in newborns, with 362 (71%, 95% CI 68.99–73.01) cases occurring within the first 28 days of birth, and 148 (29%, 95% CI 26.99–31.01) cases occurring after 28 days. The findings of the study enable the development of algorithms for timely stroke recognition, facilitating the selection of optimal treatment options for newborns and children of various age groups. Logistic regression serves as the basis for deriving these algorithms, aiming to initiate early treatment and reduce lifelong morbidity and mortality in children. The study outcomes include the formulation of algorithms for timely recognition of newborn stroke, with plans to adopt these algorithms and train a fuzzy classifier-based diagnostic model using machine learning techniques for efficient stroke recognition.","PeriodicalId":502609,"journal":{"name":"Algorithms","volume":"4 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140675248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Transformer architecture has gained widespread acceptance in image segmentation. However, it sacrifices local feature details and necessitates extensive data for training, posing challenges to its integration into computer-aided medical image segmentation. To address the above challenges, we introduce CCFNet, a collaborative cross-fusion network, which continuously fuses a CNN and Transformer interactively to exploit context dependencies. In particular, when integrating CNN features into Transformer, the correlations between local and global tokens are adaptively fused through collaborative self-attention fusion to minimize the semantic disparity between these two types of features. When integrating Transformer features into the CNN, it uses the spatial feature injector to reduce the spatial information gap between features due to the asymmetry of the extracted features. In addition, CCFNet implements the parallel operation of Transformer and the CNN and independently encodes hierarchical global and local representations when effectively aggregating different features, which can preserve global representations and local features. The experimental findings from two public medical image segmentation datasets reveal that our approach exhibits competitive performance in comparison to current state-of-the-art methods.
{"title":"CCFNet: Collaborative Cross-Fusion Network for Medical Image Segmentation","authors":"Jialu Chen, Baohua Yuan","doi":"10.3390/a17040168","DOIUrl":"https://doi.org/10.3390/a17040168","url":null,"abstract":"The Transformer architecture has gained widespread acceptance in image segmentation. However, it sacrifices local feature details and necessitates extensive data for training, posing challenges to its integration into computer-aided medical image segmentation. To address the above challenges, we introduce CCFNet, a collaborative cross-fusion network, which continuously fuses a CNN and Transformer interactively to exploit context dependencies. In particular, when integrating CNN features into Transformer, the correlations between local and global tokens are adaptively fused through collaborative self-attention fusion to minimize the semantic disparity between these two types of features. When integrating Transformer features into the CNN, it uses the spatial feature injector to reduce the spatial information gap between features due to the asymmetry of the extracted features. In addition, CCFNet implements the parallel operation of Transformer and the CNN and independently encodes hierarchical global and local representations when effectively aggregating different features, which can preserve global representations and local features. The experimental findings from two public medical image segmentation datasets reveal that our approach exhibits competitive performance in comparison to current state-of-the-art methods.","PeriodicalId":502609,"journal":{"name":"Algorithms","volume":"121 16","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140677907","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We develop decision support and automation for the task of ultrasonic non-destructive evaluation data analysis. First, we develop a probabilistic model for the task and then implement the model as a series of neural networks based on Conditional Score-Based Diffusion and Denoising Diffusion Probabilistic Model architectures. We use the neural networks to generate estimates for peak amplitude response time of flight and perform a series of tests probing their behavior, capacity, and characteristics in terms of the probabilistic model. We train the neural networks on a series of datasets constructed from ultrasonic non-destructive evaluation data acquired during an inspection at a nuclear power generation facility. We modulate the partition classifying nominal and anomalous data in the dataset and observe that the probabilistic model predicts trends in neural network model performance, thereby demonstrating a principled basis for explainability. We improve on previous related work as our methods are self-supervised and require no data annotation or pre-processing, and we train on a per-dataset basis, meaning we do not rely on out-of-distribution generalization. The capacity of the probabilistic model to predict trends in neural network performance, as well as the quality of the estimates sampled from the neural networks, support the development of a technical justification for usage of the method in safety-critical contexts such as nuclear applications. The method may provide a basis or template for extension into similar non-destructive evaluation tasks in other industrial contexts.
{"title":"Evaluating Diffusion Models for the Automation of Ultrasonic Nondestructive Evaluation Data Analysis","authors":"Nick Torenvliet, John Zelek","doi":"10.3390/a17040167","DOIUrl":"https://doi.org/10.3390/a17040167","url":null,"abstract":"We develop decision support and automation for the task of ultrasonic non-destructive evaluation data analysis. First, we develop a probabilistic model for the task and then implement the model as a series of neural networks based on Conditional Score-Based Diffusion and Denoising Diffusion Probabilistic Model architectures. We use the neural networks to generate estimates for peak amplitude response time of flight and perform a series of tests probing their behavior, capacity, and characteristics in terms of the probabilistic model. We train the neural networks on a series of datasets constructed from ultrasonic non-destructive evaluation data acquired during an inspection at a nuclear power generation facility. We modulate the partition classifying nominal and anomalous data in the dataset and observe that the probabilistic model predicts trends in neural network model performance, thereby demonstrating a principled basis for explainability. We improve on previous related work as our methods are self-supervised and require no data annotation or pre-processing, and we train on a per-dataset basis, meaning we do not rely on out-of-distribution generalization. The capacity of the probabilistic model to predict trends in neural network performance, as well as the quality of the estimates sampled from the neural networks, support the development of a technical justification for usage of the method in safety-critical contexts such as nuclear applications. The method may provide a basis or template for extension into similar non-destructive evaluation tasks in other industrial contexts.","PeriodicalId":502609,"journal":{"name":"Algorithms","volume":"114 50","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140678145","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The early diagnosis of diabetic retinopathy (DR) can effectively prevent irreversible vision loss and assist ophthalmologists in providing timely and accurate treatment plans. However, the existing methods based on deep learning have a weak perception ability of different scale information in retinal fundus images, and the segmentation capability of subtle lesions is also insufficient. This paper aims to address these issues and proposes MLNet for DR lesion segmentation, which mainly consists of the Multi-Scale Attention Block (MSAB) and the Lesion Perception Block (LPB). The MSAB is designed to capture multi-scale lesion features in fundus images, while the LPB perceives subtle lesions in depth. In addition, a novel loss function with tailored lesion weight is designed to reduce the influence of imbalanced datasets on the algorithm. The performance comparison between MLNet and other state-of-the-art methods is carried out in the DDR dataset and DIARETDB1 dataset, and MLNet achieves the best results of 51.81% mAUPR, 49.85% mDice, and 37.19% mIoU in the DDR dataset, and 67.16% mAUPR and 61.82% mDice in the DIARETDB1 dataset. The generalization experiment of MLNet in the IDRiD dataset achieves 59.54% mAUPR, which is the best among other methods. The results show that MLNet has outstanding DR lesion segmentation ability.
{"title":"Diabetic Retinopathy Lesion Segmentation Method Based on Multi-Scale Attention and Lesion Perception","authors":"Ye Bian, Chengyong Si, Lei Wang","doi":"10.3390/a17040164","DOIUrl":"https://doi.org/10.3390/a17040164","url":null,"abstract":"The early diagnosis of diabetic retinopathy (DR) can effectively prevent irreversible vision loss and assist ophthalmologists in providing timely and accurate treatment plans. However, the existing methods based on deep learning have a weak perception ability of different scale information in retinal fundus images, and the segmentation capability of subtle lesions is also insufficient. This paper aims to address these issues and proposes MLNet for DR lesion segmentation, which mainly consists of the Multi-Scale Attention Block (MSAB) and the Lesion Perception Block (LPB). The MSAB is designed to capture multi-scale lesion features in fundus images, while the LPB perceives subtle lesions in depth. In addition, a novel loss function with tailored lesion weight is designed to reduce the influence of imbalanced datasets on the algorithm. The performance comparison between MLNet and other state-of-the-art methods is carried out in the DDR dataset and DIARETDB1 dataset, and MLNet achieves the best results of 51.81% mAUPR, 49.85% mDice, and 37.19% mIoU in the DDR dataset, and 67.16% mAUPR and 61.82% mDice in the DIARETDB1 dataset. The generalization experiment of MLNet in the IDRiD dataset achieves 59.54% mAUPR, which is the best among other methods. The results show that MLNet has outstanding DR lesion segmentation ability.","PeriodicalId":502609,"journal":{"name":"Algorithms","volume":" 57","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140683403","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. F. Sánchez-Rada, Raquel Vila-Rodríguez, Jesús Montes, Pedro J. Zufiria
Predicting vehicle mobility is crucial in domains such as ride-hailing, where the balance between offer and demand is paramount. Since city road networks can be easily represented as graphs, recent works have exploited graph neural networks (GNNs) to produce more accurate predictions on real traffic data. However, a better understanding of the characteristics and limitations of this approach is needed. In this work, we compare several GNN aggregated mobility prediction schemes to a selection of other approaches in a very restricted and controlled simulation scenario. The city graph employed represents roads as directed edges and road intersections as nodes. Individual vehicle mobility is modeled as transitions between nodes in the graph. A time series of aggregated mobility is computed by counting vehicles in each node at any given time. Three main approaches are employed to construct the aggregated mobility predictors. First, the behavior of the moving individuals is assumed to follow a Markov chain (MC) model whose transition matrix is inferred via a least squares estimation procedure; the recurrent application of this MC provides the aggregated mobility prediction values. Second, a multilayer perceptron (MLP) is trained so that—given the node occupation at a given time—it can recursively provide predictions for the next values of the time series. Third, we train a GNN (according to the city graph) with the time series data via a supervised learning formulation that computes—through an embedding construction for each node in the graph—the aggregated mobility predictions. Some mobility patterns are simulated in the city to generate different time series for testing purposes. The proposed schemes are comparatively assessed compared to different baseline prediction procedures. The comparison illustrates several limitations of the GNN approaches in the selected scenario and uncovers future lines of investigation.
在诸如打车等领域，预测车辆的流动性至关重要，因为在这些领域，供需平衡是最重要的。由于城市道路网络可以很容易地表示为图，最近的研究利用图神经网络（GNN）对真实交通数据进行了更准确的预测。然而，我们需要更好地了解这种方法的特点和局限性。在这项工作中，我们在一个非常受限和受控的模拟场景中，将几种 GNN 聚合流动性预测方案与其他一些方法进行了比较。采用的城市图将道路表示为有向边，将道路交叉口表示为节点。单个车辆的流动性被模拟为图中节点之间的转换。通过计算任意给定时间内每个节点上的车辆数，计算出总流动性的时间序列。构建综合流动性预测器主要采用三种方法。首先，假定移动个体的行为遵循马尔可夫链（MC）模型，该模型的转换矩阵通过最小二乘估算程序进行推断；该 MC 的循环应用提供了聚集移动预测值。其次，对多层感知器（MLP）进行训练，使其能够根据给定时间内的节点占据情况，递归预测时间序列的下一个值。第三，我们通过有监督的学习方法，用时间序列数据训练一个 GNN（根据城市图），通过对图中每个节点的嵌入构造，计算出综合流动预测值。在城市中模拟一些流动模式，生成不同的时间序列进行测试。建议的方案与不同的基准预测程序进行了比较评估。比较结果说明了 GNN 方法在所选场景中的一些局限性，并揭示了未来的研究方向。
{"title":"Predicting the Aggregate Mobility of a Vehicle Fleet within a City Graph","authors":"J. F. Sánchez-Rada, Raquel Vila-Rodríguez, Jesús Montes, Pedro J. Zufiria","doi":"10.3390/a17040166","DOIUrl":"https://doi.org/10.3390/a17040166","url":null,"abstract":"Predicting vehicle mobility is crucial in domains such as ride-hailing, where the balance between offer and demand is paramount. Since city road networks can be easily represented as graphs, recent works have exploited graph neural networks (GNNs) to produce more accurate predictions on real traffic data. However, a better understanding of the characteristics and limitations of this approach is needed. In this work, we compare several GNN aggregated mobility prediction schemes to a selection of other approaches in a very restricted and controlled simulation scenario. The city graph employed represents roads as directed edges and road intersections as nodes. Individual vehicle mobility is modeled as transitions between nodes in the graph. A time series of aggregated mobility is computed by counting vehicles in each node at any given time. Three main approaches are employed to construct the aggregated mobility predictors. First, the behavior of the moving individuals is assumed to follow a Markov chain (MC) model whose transition matrix is inferred via a least squares estimation procedure; the recurrent application of this MC provides the aggregated mobility prediction values. Second, a multilayer perceptron (MLP) is trained so that—given the node occupation at a given time—it can recursively provide predictions for the next values of the time series. Third, we train a GNN (according to the city graph) with the time series data via a supervised learning formulation that computes—through an embedding construction for each node in the graph—the aggregated mobility predictions. Some mobility patterns are simulated in the city to generate different time series for testing purposes. The proposed schemes are comparatively assessed compared to different baseline prediction procedures. The comparison illustrates several limitations of the GNN approaches in the selected scenario and uncovers future lines of investigation.","PeriodicalId":502609,"journal":{"name":"Algorithms","volume":" 35","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140684257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：