Pub Date : 2024-08-15DOI: 10.1007/s10462-024-10910-3
Michał Budnik, Jakub Wawrzyniak, Łukasz Grala, Miłosz Kadziński, Natalia Szóstak
The discovery of non-coding RNAs (ncRNAs) has expanded our comprehension of RNAs’ inherent nature and capabilities. The intricate three-dimensional structures assumed by RNAs dictate their specific functions and molecular interactions. However, the limited number of mapped structures, partly due to experimental constraints of methods such as nuclear magnetic resonance (NMR), highlights the importance of in silico prediction solutions. This is particularly crucial in potential applications in therapeutic drug discovery. In this context, machine learning (ML) methods have emerged as prominent candidates, having previously demonstrated prowess in solving complex challenges across various domains. This review focuses on analyzing the development of ML-based solutions for RNA structure prediction, specifically oriented toward recent advancements in the deep learning (DL) domain. A systematic analysis of 33 works reveals insights into the representation of RNA structures, secondary structure motifs, and tertiary interactions. The review highlights current trends in ML methods used for RNA structure prediction, demonstrates the growing research involvement in this field, and summarizes the most valuable findings.
非编码 RNA(ncRNA)的发现拓展了我们对 RNA 固有性质和功能的理解。RNA 复杂的三维结构决定了它们的特定功能和分子相互作用。然而,部分由于核磁共振(NMR)等方法的实验限制,绘制的结构图数量有限,这凸显了硅预测解决方案的重要性。这对于治疗药物发现的潜在应用尤为重要。在这种情况下,机器学习(ML)方法已成为重要的候选方法,它们以前曾在解决各个领域的复杂挑战方面表现出卓越的能力。本综述重点分析基于 ML 的 RNA 结构预测解决方案的发展情况,特别是深度学习(DL)领域的最新进展。通过对 33 篇论文的系统分析,我们可以深入了解 RNA 结构、二级结构主题和三级相互作用的表征。综述重点介绍了用于 RNA 结构预测的 ML 方法的当前趋势,展示了该领域日益增长的研究参与,并总结了最有价值的发现。
{"title":"Deep dive into RNA: a systematic literature review on RNA structure prediction using machine learning methods","authors":"Michał Budnik, Jakub Wawrzyniak, Łukasz Grala, Miłosz Kadziński, Natalia Szóstak","doi":"10.1007/s10462-024-10910-3","DOIUrl":"10.1007/s10462-024-10910-3","url":null,"abstract":"<div><p>The discovery of non-coding RNAs (ncRNAs) has expanded our comprehension of RNAs’ inherent nature and capabilities. The intricate three-dimensional structures assumed by RNAs dictate their specific functions and molecular interactions. However, the limited number of mapped structures, partly due to experimental constraints of methods such as nuclear magnetic resonance (NMR), highlights the importance of in silico prediction solutions. This is particularly crucial in potential applications in therapeutic drug discovery. In this context, machine learning (ML) methods have emerged as prominent candidates, having previously demonstrated prowess in solving complex challenges across various domains. This review focuses on analyzing the development of ML-based solutions for RNA structure prediction, specifically oriented toward recent advancements in the deep learning (DL) domain. A systematic analysis of 33 works reveals insights into the representation of RNA structures, secondary structure motifs, and tertiary interactions. The review highlights current trends in ML methods used for RNA structure prediction, demonstrates the growing research involvement in this field, and summarizes the most valuable findings.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":null,"pages":null},"PeriodicalIF":10.7,"publicationDate":"2024-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-10910-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142222104","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}
Pub Date : 2024-08-14DOI: 10.1007/s10462-024-10909-w
Xiangling Ding, Yuchen Nie, Jizhou Yao, Jia Tang, Yubo Lang
Satellite imagery is a significant and attractive area in remote sensing applications, widely applied in monitoring, managing, and tracking natural disasters. Due to the proliferation of commercial satellites, there is an increasing availability of high-resolution satellite images. However, the ubiquity of image editing tools and the advancement of image processing technologies have made satellite image forgery relatively easy, allowing for the arbitrary addition, removal, or modification of target objects. In recent years, satellite image forgery has caused significant negative effects and potential threats to the nation, society, and individuals, drawing the attention of many scholars. Although forensics of satellite image tampering is an emerging research field that offers new insights into the field of information security, there has been a scarcity of comprehensive surveys in this area. This paper aims to fill this gap and investigates recent advances in satellite image forensics, focusing on tampering strategies and forensic methodologies. First, we discuss the concept of satellite images, the definition of satellite image forgery from global and local perspectives, and the datasets commonly used for satellite image forensics. We then detail each tampering detection and localization method, including their characteristics, advantages, disadvantages, and performance in detection or localization across various notable datasets. We also compare some representative forensic networks using evaluation metrics and public datasets. Finally, the anticipated future directions for satellite image forgery forensics are discussed.
{"title":"Forensic research of satellite images forgery: a comprehensive survey","authors":"Xiangling Ding, Yuchen Nie, Jizhou Yao, Jia Tang, Yubo Lang","doi":"10.1007/s10462-024-10909-w","DOIUrl":"10.1007/s10462-024-10909-w","url":null,"abstract":"<div><p>Satellite imagery is a significant and attractive area in remote sensing applications, widely applied in monitoring, managing, and tracking natural disasters. Due to the proliferation of commercial satellites, there is an increasing availability of high-resolution satellite images. However, the ubiquity of image editing tools and the advancement of image processing technologies have made satellite image forgery relatively easy, allowing for the arbitrary addition, removal, or modification of target objects. In recent years, satellite image forgery has caused significant negative effects and potential threats to the nation, society, and individuals, drawing the attention of many scholars. Although forensics of satellite image tampering is an emerging research field that offers new insights into the field of information security, there has been a scarcity of comprehensive surveys in this area. This paper aims to fill this gap and investigates recent advances in satellite image forensics, focusing on tampering strategies and forensic methodologies. First, we discuss the concept of satellite images, the definition of satellite image forgery from global and local perspectives, and the datasets commonly used for satellite image forensics. We then detail each tampering detection and localization method, including their characteristics, advantages, disadvantages, and performance in detection or localization across various notable datasets. We also compare some representative forensic networks using evaluation metrics and public datasets. Finally, the anticipated future directions for satellite image forgery forensics are discussed.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":null,"pages":null},"PeriodicalIF":10.7,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-10909-w.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142222107","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}
Pub Date : 2024-08-13DOI: 10.1007/s10462-024-10876-2
Nurul Athirah Nasarudin, Fatma Al Jasmi, Richard O. Sinnott, Nazar Zaki, Hany Al Ashwal, Elfadil A. Mohamed, Mohd Saberi Mohamad
A fundamental obstacle to healthcare transformation continues to be the acquisition of knowledge and insightful data from complex, high dimensional, and heterogeneous biological data. As technology has improved, a wide variety of data sources, including omics data, imaging data, and health records, have been available for use in healthcare research contexts. Electronic health records (EHRs), which are digitalized versions of medical records, have given researchers a significant chance to create computational methods for analyzing healthcare data. EHR systems typically keep track of all the data relating to a patient’s medical history, including clinical notes, demographic background, and diagnosis details. EHR data can offer valuable insights and support doctors in making better decisions related to disease and diagnostic forecasts. As a result, several academics use deep learning to forecast diseases and track health trajectories in EHR. Recent advances in deep learning technology have produced innovative and practical paradigms for building end-to-end learning models. However, scholars have limited access to online HER databases, and there is an inherent need to address this issue. This research examines deep learning models, their architectures, and readily accessible EHR online databases. The goal of this paper is to examine how various architectures, models, and databases differ in terms of features and usability. It is anticipated that the outcomes of this review will lead to the development of more robust deep learning models that facilitate medical decision-making processes based on EHR data and inform efforts to support the selection of architectures, models, and databases for specific research purposes.
从复杂、高维和异构的生物数据中获取知识和有洞察力的数据,仍然是医疗保健转型的根本障碍。随着技术的进步,各种数据源,包括全息数据、成像数据和健康记录,都可用于医疗保健研究。电子健康记录(EHR)是医疗记录的数字化版本,它为研究人员提供了创建医疗数据分析计算方法的重要机会。电子病历系统通常会记录与病人病史有关的所有数据,包括临床笔记、人口统计背景和诊断细节。电子病历数据可以提供有价值的见解,帮助医生做出更好的疾病决策和诊断预测。因此,一些学者利用深度学习来预测疾病并跟踪电子病历中的健康轨迹。深度学习技术的最新进展为建立端到端学习模型提供了创新而实用的范例。然而,学者们对在线 HER 数据库的访问有限,因此有必要解决这一问题。本研究探讨了深度学习模型、其架构以及易于访问的电子病历在线数据库。本文的目的是研究各种架构、模型和数据库在功能和可用性方面有何不同。预计本综述的结果将有助于开发更强大的深度学习模型,以促进基于电子病历数据的医疗决策过程,并为支持为特定研究目的选择架构、模型和数据库的工作提供信息。
{"title":"A review of deep learning models and online healthcare databases for electronic health records and their use for health prediction","authors":"Nurul Athirah Nasarudin, Fatma Al Jasmi, Richard O. Sinnott, Nazar Zaki, Hany Al Ashwal, Elfadil A. Mohamed, Mohd Saberi Mohamad","doi":"10.1007/s10462-024-10876-2","DOIUrl":"10.1007/s10462-024-10876-2","url":null,"abstract":"<div><p>A fundamental obstacle to healthcare transformation continues to be the acquisition of knowledge and insightful data from complex, high dimensional, and heterogeneous biological data. As technology has improved, a wide variety of data sources, including omics data, imaging data, and health records, have been available for use in healthcare research contexts. Electronic health records (EHRs), which are digitalized versions of medical records, have given researchers a significant chance to create computational methods for analyzing healthcare data. EHR systems typically keep track of all the data relating to a patient’s medical history, including clinical notes, demographic background, and diagnosis details. EHR data can offer valuable insights and support doctors in making better decisions related to disease and diagnostic forecasts. As a result, several academics use deep learning to forecast diseases and track health trajectories in EHR. Recent advances in deep learning technology have produced innovative and practical paradigms for building end-to-end learning models. However, scholars have limited access to online HER databases, and there is an inherent need to address this issue. This research examines deep learning models, their architectures, and readily accessible EHR online databases. The goal of this paper is to examine how various architectures, models, and databases differ in terms of features and usability. It is anticipated that the outcomes of this review will lead to the development of more robust deep learning models that facilitate medical decision-making processes based on EHR data and inform efforts to support the selection of architectures, models, and databases for specific research purposes.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":null,"pages":null},"PeriodicalIF":10.7,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-10876-2.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142222084","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}
Pub Date : 2024-08-13DOI: 10.1007/s10462-024-10880-6
Mariam Essam, Mohanad A. Deif, Rania Elgohary
This survey reviews different research on question analysis, including other comparative studies of question analysis approaches and an evaluation of the questions by different NLP techniques that are used in question interpretation and categorization. Among these key findings noted includes the assessment of deep learning models such as M-BiGRU-CNN and M-TF-IDF, which come with high precision and accuracy when applied with the effectiveness of use in dealing with the complexities involved in a language. Some of the most mature machine learning algorithms, for example, SVM or logistic regression, remain powerful models, especially on the classification task, meaning that the latter continues to be relevant. This study further underlines the applicability of rule-based or hybrid methodologies in certain linguistic situations, and it must be said that custom design solutions are required. We could recommend, on this basis, directing future work towards the integration of these hybrid systems and towards the definition of more general methodologies of evaluation that are in line with the constant evolution of NLP technologies. It revealed that the underlying challenges and barriers in the domain are very complex syntactic and dialectic variations, unavailability of software tools, very critical standardization in Arabic datasets, benchmark creation, handling of translated data, and the integration of Large Language Models (LLMs). The paper discusses the lack of identity and processing of such structures through online systems for comparison. This comprehensive review highlights not only the diversified potential for the capabilities of NLP techniques in refining question analysis but also the potential way of great promises for further enhancements and improvements in this progressive domain.
{"title":"Deciphering Arabic question: a dedicated survey on Arabic question analysis methods, challenges, limitations and future pathways","authors":"Mariam Essam, Mohanad A. Deif, Rania Elgohary","doi":"10.1007/s10462-024-10880-6","DOIUrl":"10.1007/s10462-024-10880-6","url":null,"abstract":"<div><p>This survey reviews different research on question analysis, including other comparative studies of question analysis approaches and an evaluation of the questions by different NLP techniques that are used in question interpretation and categorization. Among these key findings noted includes the assessment of deep learning models such as M-BiGRU-CNN and M-TF-IDF, which come with high precision and accuracy when applied with the effectiveness of use in dealing with the complexities involved in a language. Some of the most mature machine learning algorithms, for example, SVM or logistic regression, remain powerful models, especially on the classification task, meaning that the latter continues to be relevant. This study further underlines the applicability of rule-based or hybrid methodologies in certain linguistic situations, and it must be said that custom design solutions are required. We could recommend, on this basis, directing future work towards the integration of these hybrid systems and towards the definition of more general methodologies of evaluation that are in line with the constant evolution of NLP technologies. It revealed that the underlying challenges and barriers in the domain are very complex syntactic and dialectic variations, unavailability of software tools, very critical standardization in Arabic datasets, benchmark creation, handling of translated data, and the integration of Large Language Models (LLMs). The paper discusses the lack of identity and processing of such structures through online systems for comparison. This comprehensive review highlights not only the diversified potential for the capabilities of NLP techniques in refining question analysis but also the potential way of great promises for further enhancements and improvements in this progressive domain.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":null,"pages":null},"PeriodicalIF":10.7,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-10880-6.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142222106","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}
Pub Date : 2024-08-13DOI: 10.1007/s10462-024-10862-8
Vinod Kumar Chauhan, Jiandong Zhou, Ping Lu, Soheila Molaei, David A. Clifton
Hypernetworks, or hypernets for short, are neural networks that generate weights for another neural network, known as the target network. They have emerged as a powerful deep learning technique that allows for greater flexibility, adaptability, dynamism, faster training, information sharing, and model compression. Hypernets have shown promising results in a variety of deep learning problems, including continual learning, causal inference, transfer learning, weight pruning, uncertainty quantification, zero-shot learning, natural language processing, and reinforcement learning. Despite their success across different problem settings, there is currently no comprehensive review available to inform researchers about the latest developments and to assist in utilizing hypernets. To fill this gap, we review the progress in hypernets. We present an illustrative example of training deep neural networks using hypernets and propose categorizing hypernets based on five design criteria: inputs, outputs, variability of inputs and outputs, and the architecture of hypernets. We also review applications of hypernets across different deep learning problem settings, followed by a discussion of general scenarios where hypernets can be effectively employed. Finally, we discuss the challenges and future directions that remain underexplored in the field of hypernets. We believe that hypernetworks have the potential to revolutionize the field of deep learning. They offer a new way to design and train neural networks, and they have the potential to improve the performance of deep learning models on a variety of tasks. Through this review, we aim to inspire further advancements in deep learning through hypernetworks.
{"title":"A brief review of hypernetworks in deep learning","authors":"Vinod Kumar Chauhan, Jiandong Zhou, Ping Lu, Soheila Molaei, David A. Clifton","doi":"10.1007/s10462-024-10862-8","DOIUrl":"10.1007/s10462-024-10862-8","url":null,"abstract":"<div><p>Hypernetworks, or hypernets for short, are neural networks that generate weights for another neural network, known as the target network. They have emerged as a powerful deep learning technique that allows for greater flexibility, adaptability, dynamism, faster training, information sharing, and model compression. Hypernets have shown promising results in a variety of deep learning problems, including continual learning, causal inference, transfer learning, weight pruning, uncertainty quantification, zero-shot learning, natural language processing, and reinforcement learning. Despite their success across different problem settings, there is currently no comprehensive review available to inform researchers about the latest developments and to assist in utilizing hypernets. To fill this gap, we review the progress in hypernets. We present an illustrative example of training deep neural networks using hypernets and propose categorizing hypernets based on five design criteria: inputs, outputs, variability of inputs and outputs, and the architecture of hypernets. We also review applications of hypernets across different deep learning problem settings, followed by a discussion of general scenarios where hypernets can be effectively employed. Finally, we discuss the challenges and future directions that remain underexplored in the field of hypernets. We believe that hypernetworks have the potential to revolutionize the field of deep learning. They offer a new way to design and train neural networks, and they have the potential to improve the performance of deep learning models on a variety of tasks. Through this review, we aim to inspire further advancements in deep learning through hypernetworks.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":null,"pages":null},"PeriodicalIF":10.7,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-10862-8.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142222103","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}
Pub Date : 2024-08-13DOI: 10.1007/s10462-024-10904-1
Cem Bulut, Emel Arslan
Credit risk assessment (CRA) plays an important role in credit decision-making process of financial institutions. Today, developing big data analysis and machine learning methods have marked a new era in credit risk estimation. In recent years, using machine learning methods in credit risk estimation has emerged as an alternative method for financial institutions. The past demographic and financial data of the person whose CRA will be performed is important for creating an automatic artificial intelligence credit score prediction model based on machine learning. It is also necessary to use features correctly to create accurate machine learning models. This article aims to investigate the effects of dimensionality reduction and data splitting steps on the performance of classification algorithms widely used in the literature. In our study, dimensionality reduction was performed using Principal Component Analysis (PCA). Random Forest (RF), Logistic Regression (LR), Decision Tree (DT), Naive Bayes (NB) algorithms were chosen for classification. Percentage splitting (PER, 66–34%) and k-fold (k = 10) cross-validation techniques were used when dividing the data set into training and test data. The results obtained were evaluated with accuracy, recall, F1 score, precision, and AUC metrics. German data set was used in this study. The effect of data splitting and dimension reduction on the classification of CRA systems was examined. The highest ACC in PER and CV data splitting was obtained with the RF algorithm. Using data splitting methods and PCA, the highest accuracy was observed with RF and the highest AUC with NB, with 13 PCs in which 80% of the variance was obtained. As a result, the data set consisting of a total of 20 features, expressed by 13 PCs, achieved similar or higher success than the results obtained from the original data set.
信用风险评估(CRA)在金融机构的信贷决策过程中发挥着重要作用。如今,大数据分析和机器学习方法的发展标志着信用风险评估进入了一个新时代。近年来,使用机器学习方法进行信用风险评估已成为金融机构的一种替代方法。要创建一个基于机器学习的人工智能信用评分自动预测模型,将被执行 CRA 的人过去的人口和财务数据非常重要。要创建准确的机器学习模型,还必须正确使用特征。本文旨在研究降维和数据拆分步骤对文献中广泛使用的分类算法性能的影响。在我们的研究中,采用主成分分析法(PCA)进行降维。分类算法选择了随机森林(RF)、逻辑回归(LR)、决策树(DT)和奈夫贝叶斯(NB)算法。在将数据集分为训练数据和测试数据时,使用了百分比分割(PER,66-34%)和 k 倍(k = 10)交叉验证技术。获得的结果通过准确率、召回率、F1 分数、精确度和 AUC 指标进行评估。本研究使用的是德国数据集。研究考察了数据分割和降维对 CRA 系统分类的影响。RF 算法在 PER 和 CV 数据拆分中获得了最高的 ACC。在使用数据拆分方法和 PCA 时,RF 算法的准确率最高,NB 算法的 AUC 最高,有 13 个 PC,其中 80% 的方差是通过 PC 获得的。因此,由 13 个 PC 表示的共 20 个特征组成的数据集取得了与原始数据集相似或更高的成功率。
{"title":"Comparison of the impact of dimensionality reduction and data splitting on classification performance in credit risk assessment","authors":"Cem Bulut, Emel Arslan","doi":"10.1007/s10462-024-10904-1","DOIUrl":"10.1007/s10462-024-10904-1","url":null,"abstract":"<div><p>Credit risk assessment (CRA) plays an important role in credit decision-making process of financial institutions. Today, developing big data analysis and machine learning methods have marked a new era in credit risk estimation. In recent years, using machine learning methods in credit risk estimation has emerged as an alternative method for financial institutions. The past demographic and financial data of the person whose CRA will be performed is important for creating an automatic artificial intelligence credit score prediction model based on machine learning. It is also necessary to use features correctly to create accurate machine learning models. This article aims to investigate the effects of dimensionality reduction and data splitting steps on the performance of classification algorithms widely used in the literature. In our study, dimensionality reduction was performed using Principal Component Analysis (PCA). Random Forest (RF), Logistic Regression (LR), Decision Tree (DT), Naive Bayes (NB) algorithms were chosen for classification. Percentage splitting (PER, 66–34%) and k-fold (k = 10) cross-validation techniques were used when dividing the data set into training and test data. The results obtained were evaluated with accuracy, recall, F1 score, precision, and AUC metrics. German data set was used in this study. The effect of data splitting and dimension reduction on the classification of CRA systems was examined. The highest ACC in PER and CV data splitting was obtained with the RF algorithm. Using data splitting methods and PCA, the highest accuracy was observed with RF and the highest AUC with NB, with 13 PCs in which 80% of the variance was obtained. As a result, the data set consisting of a total of 20 features, expressed by 13 PCs, achieved similar or higher success than the results obtained from the original data set.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":null,"pages":null},"PeriodicalIF":10.7,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-10904-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142222108","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}
The study of insect behavior, particularly that of honey bees, has a broad scope and significance. Tracking bee flying patterns grants much helpful information about bee behavior. However, tracking a small yet fast-moving object, such as a bee, is difficult. Hence, we present artificial intelligence, machine-learning-based bee recognition, and tracking systems to assist the researcher in studying the bee’s behavior. To develop a machine learning system, a labeled database is required for model training. To address this, we implemented an automated system for analyzing and labeling bee videos. This labeled database served as the foundation for two distinct bee-tracking solutions. The first solution (planar bee tracking system) tracked individual bees in closed mazes using a neural network. The second solution (spatial bee tracking system) utilized a neural network and a tracking algorithm to identify and track flying bees in open environments. Both systems tackle the challenge of tracking small-bodied creatures with rapid and diverse movement patterns. Although we applied these systems to entomological cognition research in this paper, their relevance extends to general insect research and developing tracking solutions for small organisms with swift movements. We present the complete architecture and detailed methodologies to facilitate the utilization of these models in future research endeavors. Our approach is a simple and inexpensive method that contributes to the growing number of image-analysis tools used for tracking animal movement, with future potential applications under less sterile field conditions. The tools presented in this paper could assist the study of movement ecology, specifically in insects, by providing accurate movement specifications. Following the movement of pollinators or natural enemies, for example, greatly contributes to the study of pollination or biological control, respectively, in natural and agro-ecosystems.
{"title":"Machine learning-based bee recognition and tracking for advancing insect behavior research","authors":"Erez Rozenbaum, Tammar Shrot, Hadassa Daltrophe, Yehuda Kunya, Sharoni Shafir","doi":"10.1007/s10462-024-10879-z","DOIUrl":"10.1007/s10462-024-10879-z","url":null,"abstract":"<div><p>The study of insect behavior, particularly that of honey bees, has a broad scope and significance. Tracking bee flying patterns grants much helpful information about bee behavior. However, tracking a small yet fast-moving object, such as a bee, is difficult. Hence, we present artificial intelligence, machine-learning-based bee recognition, and tracking systems to assist the researcher in studying the bee’s behavior. To develop a machine learning system, a labeled database is required for model training. To address this, we implemented an automated system for analyzing and labeling bee videos. This labeled database served as the foundation for two distinct bee-tracking solutions. The first solution (planar bee tracking system) tracked individual bees in closed mazes using a neural network. The second solution (spatial bee tracking system) utilized a neural network and a tracking algorithm to identify and track flying bees in open environments. Both systems tackle the challenge of tracking small-bodied creatures with rapid and diverse movement patterns. Although we applied these systems to entomological cognition research in this paper, their relevance extends to general insect research and developing tracking solutions for small organisms with swift movements. We present the complete architecture and detailed methodologies to facilitate the utilization of these models in future research endeavors. Our approach is a simple and inexpensive method that contributes to the growing number of image-analysis tools used for tracking animal movement, with future potential applications under less sterile field conditions. The tools presented in this paper could assist the study of movement ecology, specifically in insects, by providing accurate movement specifications. Following the movement of pollinators or natural enemies, for example, greatly contributes to the study of pollination or biological control, respectively, in natural and agro-ecosystems.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":null,"pages":null},"PeriodicalIF":10.7,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-10879-z.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141933377","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}
Pub Date : 2024-08-12DOI: 10.1007/s10462-024-10838-8
Abdelazim G. Hussien, Anas Bouaouda, Abdullah Alzaqebah, Sumit Kumar, Gang Hu, Heming Jia
A recently developed algorithm inspired by natural processes, known as the Artificial Gorilla Troops Optimizer (GTO), boasts a straightforward structure, unique stabilizing features, and notably high effectiveness. Its primary objective is to efficiently find solutions for a wide array of challenges, whether they involve constraints or not. The GTO takes its inspiration from the behavior of Gorilla Troops in the natural world. To emulate the impact of gorillas at each stage of the search process, the GTO employs a flexible weighting mechanism rooted in its concept. Its exceptional qualities, including its independence from derivatives, lack of parameters, user-friendliness, adaptability, and simplicity, have resulted in its rapid adoption for addressing various optimization challenges. This review is dedicated to the examination and discussion of the foundational research that forms the basis of the GTO. It delves into the evolution of this algorithm, drawing insights from 112 research studies that highlight its effectiveness. Additionally, it explores proposed enhancements to the GTO’s behavior, with a specific focus on aligning the geometry of the search area with real-world optimization problems. The review also introduces the GTO solver, providing details about its identification and organization, and demonstrates its application in various optimization scenarios. Furthermore, it provides a critical assessment of the convergence behavior while addressing the primary limitation of the GTO. In conclusion, this review summarizes the key findings of the study and suggests potential avenues for future advancements and adaptations related to the GTO.
{"title":"An in-depth survey of the artificial gorilla troops optimizer: outcomes, variations, and applications","authors":"Abdelazim G. Hussien, Anas Bouaouda, Abdullah Alzaqebah, Sumit Kumar, Gang Hu, Heming Jia","doi":"10.1007/s10462-024-10838-8","DOIUrl":"10.1007/s10462-024-10838-8","url":null,"abstract":"<div><p>A recently developed algorithm inspired by natural processes, known as the Artificial Gorilla Troops Optimizer (GTO), boasts a straightforward structure, unique stabilizing features, and notably high effectiveness. Its primary objective is to efficiently find solutions for a wide array of challenges, whether they involve constraints or not. The GTO takes its inspiration from the behavior of Gorilla Troops in the natural world. To emulate the impact of gorillas at each stage of the search process, the GTO employs a flexible weighting mechanism rooted in its concept. Its exceptional qualities, including its independence from derivatives, lack of parameters, user-friendliness, adaptability, and simplicity, have resulted in its rapid adoption for addressing various optimization challenges. This review is dedicated to the examination and discussion of the foundational research that forms the basis of the GTO. It delves into the evolution of this algorithm, drawing insights from 112 research studies that highlight its effectiveness. Additionally, it explores proposed enhancements to the GTO’s behavior, with a specific focus on aligning the geometry of the search area with real-world optimization problems. The review also introduces the GTO solver, providing details about its identification and organization, and demonstrates its application in various optimization scenarios. Furthermore, it provides a critical assessment of the convergence behavior while addressing the primary limitation of the GTO. In conclusion, this review summarizes the key findings of the study and suggests potential avenues for future advancements and adaptations related to the GTO.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":null,"pages":null},"PeriodicalIF":10.7,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-10838-8.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141933379","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}
Pub Date : 2024-08-12DOI: 10.1007/s10462-024-10885-1
Uchenna Akujuobi, Priyadarshini Kumari, Jihun Choi, Samy Badreddine, Kana Maruyama, Sucheendra K. Palaniappan, Tarek R. Besold
Over the last few years Literature-based Discovery (LBD) has regained popularity as a means to enhance the scientific research process. The resurgent interest has spurred the development of supervised and semi-supervised machine learning models aimed at making previously implicit connections between scientific concepts/entities within often extensive bodies of literature explicit—i.e., suggesting novel scientific hypotheses. In doing so, understanding the temporally evolving interactions between these entities can provide valuable information for predicting the future development of entity relationships. However, existing methods often underutilize the latent information embedded in the temporal aspects of the interaction data. Motivated by applications in the food domain—where we aim to connect nutritional information with health-related benefits—we address the hypothesis-generation problem using a temporal graph-based approach. Given that hypothesis generation involves predicting future (i.e., still to be discovered) entity connections, in our view the ability to capture the dynamic evolution of connections over time is pivotal for a robust model. To address this, we introduce THiGER, a novel batch contrastive temporal node-pair embedding method. THiGER excels in providing a more expressive node-pair encoding by effectively harnessing node-pair relationships. Furthermore, we present THiGER-A, an incremental training approach that incorporates an active curriculum learning strategy to mitigate label bias arising from unobserved connections. By progressively training on increasingly challenging and high-utility samples, our approach significantly enhances the performance of the embedding model. Empirical validation of our proposed method demonstrates its effectiveness on established temporal-graph benchmark datasets, as well as on real-world datasets within the food domain.
{"title":"Link prediction for hypothesis generation: an active curriculum learning infused temporal graph-based approach","authors":"Uchenna Akujuobi, Priyadarshini Kumari, Jihun Choi, Samy Badreddine, Kana Maruyama, Sucheendra K. Palaniappan, Tarek R. Besold","doi":"10.1007/s10462-024-10885-1","DOIUrl":"10.1007/s10462-024-10885-1","url":null,"abstract":"<div><p>Over the last few years Literature-based Discovery (LBD) has regained popularity as a means to enhance the scientific research process. The resurgent interest has spurred the development of supervised and semi-supervised machine learning models aimed at making previously implicit connections between scientific concepts/entities within often extensive bodies of literature explicit—i.e., suggesting novel scientific hypotheses. In doing so, understanding the temporally evolving interactions between these entities can provide valuable information for predicting the future development of entity relationships. However, existing methods often underutilize the latent information embedded in the temporal aspects of the interaction data. Motivated by applications in the food domain—where we aim to connect nutritional information with health-related benefits—we address the hypothesis-generation problem using a temporal graph-based approach. Given that hypothesis generation involves predicting future (i.e., still to be discovered) entity connections, in our view the ability to capture the dynamic evolution of connections over time is pivotal for a robust model. To address this, we introduce <i>THiGER</i>, a novel batch contrastive temporal node-pair embedding method. <i>THiGER</i> excels in providing a more expressive node-pair encoding by effectively harnessing node-pair relationships. Furthermore, we present <i>THiGER-A</i>, an incremental training approach that incorporates an active curriculum learning strategy to mitigate label bias arising from unobserved connections. By progressively training on increasingly challenging and high-utility samples, our approach significantly enhances the performance of the embedding model. Empirical validation of our proposed method demonstrates its effectiveness on established temporal-graph benchmark datasets, as well as on real-world datasets within the food domain.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":null,"pages":null},"PeriodicalIF":10.7,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-10885-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141933382","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}
Pub Date : 2024-08-12DOI: 10.1007/s10462-024-10817-z
Taki Hasan Rafi, Ratul Mahjabin, Emon Ghosh, Young-Woong Ko, Jeong-Gun Lee
Deep neural networks (DNNs) have proven explicit contributions in making autonomous driving cars and related tasks such as semantic segmentation, motion tracking, object detection, sensor fusion, and planning. However, in challenging situations, DNNs are not generalizable because of the inherent domain shift due to the nature of training under the i.i.d. assumption. The goal of semantic segmentation is to preserve information from a given image into multiple meaningful categories for visual understanding. Particularly for semantic segmentation, pixel-wise annotation is extremely costly and not always feasible. Domain generalization for semantic segmentation aims to learn pixel-level semantic labels from multiple source domains and generalize to predict pixel-level semantic labels on multiple unseen target domains. In this survey, for the first time, we present a comprehensive review of DG for semantic segmentation. we present a comprehensive summary of recent works related to domain generalization in semantic segmentation, which establishes the importance of generalizing to new environments of segmentation models. Although domain adaptation has gained more attention in segmentation tasks than domain generalization, it is still worth unveiling new trends that are adopted from domain generalization methods in semantic segmentation. We cover most of the recent and dominant DG methods in the context of semantic segmentation and also provide some other related applications. We conclude this survey by highlighting the future directions in this area.
{"title":"Domain generalization for semantic segmentation: a survey","authors":"Taki Hasan Rafi, Ratul Mahjabin, Emon Ghosh, Young-Woong Ko, Jeong-Gun Lee","doi":"10.1007/s10462-024-10817-z","DOIUrl":"10.1007/s10462-024-10817-z","url":null,"abstract":"<div><p>Deep neural networks (DNNs) have proven explicit contributions in making autonomous driving cars and related tasks such as semantic segmentation, motion tracking, object detection, sensor fusion, and planning. However, in challenging situations, DNNs are not generalizable because of the inherent domain shift due to the nature of training under the i.i.d. assumption. The goal of semantic segmentation is to preserve information from a given image into multiple meaningful categories for visual understanding. Particularly for semantic segmentation, pixel-wise annotation is extremely costly and not always feasible. Domain generalization for semantic segmentation aims to learn pixel-level semantic labels from multiple source domains and generalize to predict pixel-level semantic labels on multiple unseen target domains. In this survey, for the first time, we present a comprehensive review of DG for semantic segmentation. we present a comprehensive summary of recent works related to domain generalization in semantic segmentation, which establishes the importance of generalizing to new environments of segmentation models. Although domain adaptation has gained more attention in segmentation tasks than domain generalization, it is still worth unveiling new trends that are adopted from domain generalization methods in semantic segmentation. We cover most of the recent and dominant DG methods in the context of semantic segmentation and also provide some other related applications. We conclude this survey by highlighting the future directions in this area.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":null,"pages":null},"PeriodicalIF":10.7,"publicationDate":"2024-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-10817-z.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141933381","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}