PeerJ Computer Science最新文献_第9页

SentinelFusion based machine learning comprehensive approach for enhanced computer forensics 基于 SentinelFusion 的机器学习综合方法增强计算机取证能力

IF 3.8 4区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

PeerJ Computer Science

Pub Date : 2024-08-06 DOI: 10.7717/peerj-cs.2183

Umar Islam, Abeer Abdullah Alsadhan, Hathal Salamah Alwageed, Abdullah A. Al-Atawi, Gulzar Mehmood, Manel Ayadi, Shrooq Alsenan

In the rapidly evolving landscape of modern technology, the convergence of blockchain innovation and machine learning advancements presents unparalleled opportunities to enhance computer forensics. This study introduces SentinelFusion, an ensemble-based machine learning framework designed to bolster secrecy, privacy, and data integrity within blockchain systems. By integrating cutting-edge blockchain security properties with the predictive capabilities of machine learning, SentinelFusion aims to improve the detection and prevention of security breaches and data tampering. Utilizing a comprehensive blockchain-based dataset of various criminal activities, the framework leverages multiple machine learning models, including support vector machines, K-nearest neighbors, naive Bayes, logistic regression, and decision trees, alongside the novel SentinelFusion ensemble model. Extensive evaluation metrics such as accuracy, precision, recall, and F1 score are used to assess model performance. The results demonstrate that SentinelFusion outperforms individual models, achieving an accuracy, precision, recall, and F1 score of 0.99. This study’s findings underscore the potential of combining blockchain technology and machine learning to advance computer forensics, providing valuable insights for practitioners and researchers in the field.

在快速发展的现代技术领域，区块链创新与机器学习进步的融合为加强计算机取证带来了无与伦比的机遇。本研究介绍了 SentinelFusion，这是一种基于集合的机器学习框架，旨在加强区块链系统的保密性、隐私性和数据完整性。通过将最先进的区块链安全特性与机器学习的预测能力相结合，SentinelFusion 旨在改进对安全漏洞和数据篡改的检测和预防。利用基于区块链的各种犯罪活动的综合数据集，该框架利用了多种机器学习模型，包括支持向量机、K-近邻、奈夫贝叶斯、逻辑回归和决策树，以及新颖的SentinelFusion集合模型。准确率、精确度、召回率和 F1 分数等广泛的评估指标被用来评估模型的性能。结果表明，SentinelFusion 的准确度、精确度、召回率和 F1 分数均达到 0.99，优于单个模型。这项研究的结果凸显了区块链技术与机器学习相结合推动计算机取证的潜力，为该领域的从业人员和研究人员提供了宝贵的见解。

{"title":"SentinelFusion based machine learning comprehensive approach for enhanced computer forensics","authors":"Umar Islam, Abeer Abdullah Alsadhan, Hathal Salamah Alwageed, Abdullah A. Al-Atawi, Gulzar Mehmood, Manel Ayadi, Shrooq Alsenan","doi":"10.7717/peerj-cs.2183","DOIUrl":"https://doi.org/10.7717/peerj-cs.2183","url":null,"abstract":"In the rapidly evolving landscape of modern technology, the convergence of blockchain innovation and machine learning advancements presents unparalleled opportunities to enhance computer forensics. This study introduces SentinelFusion, an ensemble-based machine learning framework designed to bolster secrecy, privacy, and data integrity within blockchain systems. By integrating cutting-edge blockchain security properties with the predictive capabilities of machine learning, SentinelFusion aims to improve the detection and prevention of security breaches and data tampering. Utilizing a comprehensive blockchain-based dataset of various criminal activities, the framework leverages multiple machine learning models, including support vector machines, K-nearest neighbors, naive Bayes, logistic regression, and decision trees, alongside the novel SentinelFusion ensemble model. Extensive evaluation metrics such as accuracy, precision, recall, and F1 score are used to assess model performance. The results demonstrate that SentinelFusion outperforms individual models, achieving an accuracy, precision, recall, and F1 score of 0.99. This study’s findings underscore the potential of combining blockchain technology and machine learning to advance computer forensics, providing valuable insights for practitioners and researchers in the field.","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"77 1","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141936234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Early detection of abiotic stress in plants through SNARE proteins using hybrid feature fusion model 利用混合特征融合模型通过 SNARE 蛋白早期检测植物的非生物胁迫

IF 3.8 4区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

PeerJ Computer Science

Pub Date : 2024-08-05 DOI: 10.7717/peerj-cs.2149

Bhargavi T., Sumathi D.

Agriculture is the main source of livelihood for most of the population across the globe. Plants are often considered life savers for humanity, having evolved complex adaptations to cope with adverse environmental conditions. Protecting agricultural produce from devastating conditions such as stress is essential for the sustainable development of the nation. Plants respond to various environmental stressors such as drought, salinity, heat, cold, etc. Abiotic stress can significantly impact crop yield and development posing a major threat to agriculture. SNARE proteins play a major role in pathological processes as they are vital proteins in the life sciences. These proteins act as key players in stress responses. Feature extraction is essential for visualizing the underlying structure of the SNARE proteins in analyzing the root cause of abiotic stress in plants. To address this issue, we developed a hybrid model to capture the hidden structures of the SNAREs. A feature fusion technique has been devised by combining the potential strengths of convolutional neural networks (CNN) with a high dimensional radial basis function (RBF) network. Additionally, we employ a bi-directional long short-term memory (Bi-LSTM) network to classify the presence of SNARE proteins. Our feature fusion model successfully identified abiotic stress in plants with an accuracy of 74.6%. When compared with various existing frameworks, our model demonstrates superior classification results.

农业是全球大多数人口的主要生计来源。植物通常被认为是人类的救星，它们进化出复杂的适应能力来应对不利的环境条件。保护农产品免受压力等破坏性条件的影响对国家的可持续发展至关重要。植物会对干旱、盐碱、高温、严寒等各种环境胁迫做出反应。非生物胁迫会严重影响作物的产量和生长发育，对农业构成重大威胁。SNARE 蛋白在病理过程中发挥着重要作用，因为它们是生命科学中的重要蛋白质。这些蛋白质在应激反应中扮演着关键角色。在分析植物非生物胁迫的根本原因时，特征提取对于可视化 SNARE 蛋白的底层结构至关重要。为了解决这个问题，我们开发了一种混合模型来捕捉 SNARE 的隐藏结构。通过结合卷积神经网络（CNN）和高维径向基函数（RBF）网络的潜在优势，我们设计了一种特征融合技术。此外，我们还采用了双向长短期记忆（Bi-LSTM）网络来对 SNARE 蛋白质的存在进行分类。我们的特征融合模型成功识别了植物的非生物胁迫，准确率高达 74.6%。与现有的各种框架相比，我们的模型显示出更优越的分类结果。

{"title":"Early detection of abiotic stress in plants through SNARE proteins using hybrid feature fusion model","authors":"Bhargavi T., Sumathi D.","doi":"10.7717/peerj-cs.2149","DOIUrl":"https://doi.org/10.7717/peerj-cs.2149","url":null,"abstract":"Agriculture is the main source of livelihood for most of the population across the globe. Plants are often considered life savers for humanity, having evolved complex adaptations to cope with adverse environmental conditions. Protecting agricultural produce from devastating conditions such as stress is essential for the sustainable development of the nation. Plants respond to various environmental stressors such as drought, salinity, heat, cold, etc. Abiotic stress can significantly impact crop yield and development posing a major threat to agriculture. SNARE proteins play a major role in pathological processes as they are vital proteins in the life sciences. These proteins act as key players in stress responses. Feature extraction is essential for visualizing the underlying structure of the SNARE proteins in analyzing the root cause of abiotic stress in plants. To address this issue, we developed a hybrid model to capture the hidden structures of the SNAREs. A feature fusion technique has been devised by combining the potential strengths of convolutional neural networks (CNN) with a high dimensional radial basis function (RBF) network. Additionally, we employ a bi-directional long short-term memory (Bi-LSTM) network to classify the presence of SNARE proteins. Our feature fusion model successfully identified abiotic stress in plants with an accuracy of 74.6%. When compared with various existing frameworks, our model demonstrates superior classification results.","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"43 1","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141936174","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Maize plant height automatic reading of measurement scale based on improved YOLOv5 lightweight model 基于改进型 YOLOv5 轻量级模型的玉米株高自动读取测量标尺

IF 3.8 4区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

PeerJ Computer Science

Pub Date : 2024-08-05 DOI: 10.7717/peerj-cs.2207

Jiachao Li, Ya’nan Zhou, He Zhang, Dayu Pan, Ying Gu, Bin Luo

BackgroundPlant height is a significant indicator of maize phenotypic morphology, and is closely related to crop growth, biomass, and lodging resistance. Obtaining the maize plant height accurately is of great significance for cultivating high-yielding maize varieties. Traditional measurement methods are labor-intensive and not conducive to data recording and storage. Therefore, it is very essential to implement the automated reading of maize plant height from measurement scales using object detection algorithms. MethodThis study proposed a lightweight detection model based on the improved YOLOv5. The MobileNetv3 network replaced the YOLOv5 backbone network, and the Normalization-based Attention Module attention mechanism module was introduced into the neck network. The CioU loss function was replaced with the EioU loss function. Finally, a combined algorithm was used to achieve the automatic reading of maize plant height from measurement scales. ResultsThe improved model achieved an average precision of 98.6%, a computational complexity of 1.2 GFLOPs, and occupied 1.8 MB of memory. The detection frame rate on the computer was 54.1 fps. Through comparisons with models such as YOLOv5s, YOLOv7 and YOLOv8s, it was evident that the comprehensive performance of the improved model in this study was superior. Finally, a comparison between the algorithm’s 160 plant height data obtained from the test set and manual readings demonstrated that the relative error between the algorithm’s results and manual readings was within 0.2 cm, meeting the requirements of automatic reading of maize height measuring scale.

背景株高是玉米表型形态的重要指标，与作物生长、生物量和抗倒伏性密切相关。准确获取玉米株高对培育高产玉米品种具有重要意义。传统的测量方法劳动强度大，且不利于数据记录和存储。因此，利用物体检测算法实现从测量秤上自动读取玉米株高是非常必要的。方法本研究提出了一种基于改进型 YOLOv5 的轻量级检测模型。MobileNetv3 网络取代了 YOLOv5 骨干网络，并在颈部网络中引入了基于归一化注意力模块的注意力机制模块。CioU 损失函数被替换为 EioU 损失函数。最后，使用组合算法实现了从测量秤上自动读取玉米株高。结果改进后的模型平均精确度达到 98.6%，计算复杂度为 1.2 GFLOPs，占用内存 1.8 MB。计算机的检测帧频为 54.1 fps。通过与 YOLOv5s、YOLOv7 和 YOLOv8s 等模型的比较，可以看出本研究中改进模型的综合性能更胜一筹。最后，将算法从测试集中获得的 160 个植株高度数据与人工读数进行比较，结果表明算法结果与人工读数的相对误差在 0.2 厘米以内，符合玉米高度测量秤自动读数的要求。

{"title":"Maize plant height automatic reading of measurement scale based on improved YOLOv5 lightweight model","authors":"Jiachao Li, Ya’nan Zhou, He Zhang, Dayu Pan, Ying Gu, Bin Luo","doi":"10.7717/peerj-cs.2207","DOIUrl":"https://doi.org/10.7717/peerj-cs.2207","url":null,"abstract":"Background\u0000Plant height is a significant indicator of maize phenotypic morphology, and is closely related to crop growth, biomass, and lodging resistance. Obtaining the maize plant height accurately is of great significance for cultivating high-yielding maize varieties. Traditional measurement methods are labor-intensive and not conducive to data recording and storage. Therefore, it is very essential to implement the automated reading of maize plant height from measurement scales using object detection algorithms. Method\u0000This study proposed a lightweight detection model based on the improved YOLOv5. The MobileNetv3 network replaced the YOLOv5 backbone network, and the Normalization-based Attention Module attention mechanism module was introduced into the neck network. The CioU loss function was replaced with the EioU loss function. Finally, a combined algorithm was used to achieve the automatic reading of maize plant height from measurement scales. Results\u0000The improved model achieved an average precision of 98.6%, a computational complexity of 1.2 GFLOPs, and occupied 1.8 MB of memory. The detection frame rate on the computer was 54.1 fps. Through comparisons with models such as YOLOv5s, YOLOv7 and YOLOv8s, it was evident that the comprehensive performance of the improved model in this study was superior. Finally, a comparison between the algorithm’s 160 plant height data obtained from the test set and manual readings demonstrated that the relative error between the algorithm’s results and manual readings was within 0.2 cm, meeting the requirements of automatic reading of maize height measuring scale.","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"255 1","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141936236","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Hybrid quantum search with genetic algorithm optimization 混合量子搜索与遗传算法优化

IF 3.8 4区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

PeerJ Computer Science

Pub Date : 2024-08-05 DOI: 10.7717/peerj-cs.2210

Sebastian Mihai Ardelean, Mihai Udrescu

Quantum genetic algorithms (QGA) integrate genetic programming and quantum computing to address search and optimization problems. The standard strategy of the hybrid QGA approach is to add quantum resources to classical genetic algorithms (GA), thus improving their efficacy (i.e., quantum optimization of a classical algorithm). However, the extent of such improvements is still unclear. Conversely, Reduced Quantum Genetic Algorithm (RQGA) is a fully quantum algorithm that reduces the GA search for the best fitness in a population of potential solutions to running Grover’s algorithm. Unfortunately, RQGA finds the best fitness value and its corresponding chromosome (i.e., the solution or one of the solutions of the problem) in exponential runtime, O(2n/2), where n is the number of qubits in the individuals’ quantum register. This article introduces a novel QGA optimization strategy, namely a classical optimization of a fully quantum algorithm, to address the RQGA complexity problem. Accordingly, we control the complexity of the RQGA algorithm by selecting a limited number of qubits in the individuals’ register and fixing the remaining ones as classical values of ‘0’ and ‘1’ with a genetic algorithm. We also improve the performance of RQGA by discarding unfit solutions and bounding the search only in the area of valid individuals. As a result, our Hybrid Quantum Algorithm with Genetic Optimization (HQAGO) solves search problems in O(2(n−k)/2) oracle queries, where k is the number of fixed classical bits in the individuals’ register.

量子遗传算法（QGA）整合了遗传编程和量子计算，以解决搜索和优化问题。混合量子遗传算法的标准策略是为经典遗传算法（GA）添加量子资源，从而提高其功效（即经典算法的量子优化）。然而，这种改进的程度尚不明确。相反，还原量子遗传算法（RQGA）是一种全量子算法，它将在潜在解群中寻找最佳适应度的遗传算法简化为运行格罗弗算法。遗憾的是，RQGA 在指数级运行时间（O(2n/2)，其中 n 是个体量子寄存器中的量子比特数）内找到最佳适配值及其对应的染色体（即问题的解决方案或解决方案之一）。本文介绍了一种新颖的 QGA 优化策略，即对全量子算法进行经典优化，以解决 RQGA 复杂性问题。因此，我们通过在个体寄存器中选择有限数量的量子位，并用遗传算法将其余量子位固定为经典的 "0 "和 "1 "值，来控制 RQGA 算法的复杂度。我们还通过丢弃不合适的解决方案和只在有效个体区域内进行搜索来提高 RQGA 的性能。因此，我们的遗传优化混合量子算法（HQAGO）只需 O(2(n-k)/2) 次神谕查询就能解决搜索问题，其中 k 是个体寄存器中固定经典位的数量。

{"title":"Hybrid quantum search with genetic algorithm optimization","authors":"Sebastian Mihai Ardelean, Mihai Udrescu","doi":"10.7717/peerj-cs.2210","DOIUrl":"https://doi.org/10.7717/peerj-cs.2210","url":null,"abstract":"Quantum genetic algorithms (QGA) integrate genetic programming and quantum computing to address search and optimization problems. The standard strategy of the hybrid QGA approach is to add quantum resources to classical genetic algorithms (GA), thus improving their efficacy (i.e., quantum optimization of a classical algorithm). However, the extent of such improvements is still unclear. Conversely, Reduced Quantum Genetic Algorithm (RQGA) is a fully quantum algorithm that reduces the GA search for the best fitness in a population of potential solutions to running Grover’s algorithm. Unfortunately, RQGA finds the best fitness value and its corresponding chromosome (i.e., the solution or one of the solutions of the problem) in exponential runtime, O(2n/2), where n is the number of qubits in the individuals’ quantum register. This article introduces a novel QGA optimization strategy, namely a classical optimization of a fully quantum algorithm, to address the RQGA complexity problem. Accordingly, we control the complexity of the RQGA algorithm by selecting a limited number of qubits in the individuals’ register and fixing the remaining ones as classical values of ‘0’ and ‘1’ with a genetic algorithm. We also improve the performance of RQGA by discarding unfit solutions and bounding the search only in the area of valid individuals. As a result, our Hybrid Quantum Algorithm with Genetic Optimization (HQAGO) solves search problems in O(2(n−k)/2) oracle queries, where k is the number of fixed classical bits in the individuals’ register.","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"22 1","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141936306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Cardiotoxicity detection tool for breast cancer chemotherapy: a retrospective study. 乳腺癌化疗的心脏毒性检测工具：一项回顾性研究。

IF 3.5 4区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

PeerJ Computer Science

Pub Date : 2024-08-02 eCollection Date: 2024-01-01 DOI: 10.7717/peerj-cs.2230

Ahmad Alenezi, Fergus McKiddie, Mintu Nath, Ali Mayya, Andy Welch

Background: Patients with breast cancer undergoing biological therapy and/or chemotherapy perform multiple radionuclide angiography (RNA) or multigated acquisition (MUGA) scans to assess cardiotoxicity. The association between RNA imaging parameters and left ventricular (LV) ejection fraction (LVEF) remains unclear.

Objectives: This study aimed to extract and evaluate the association of several novel imaging biomarkers to detect changes in LVEF in patients with breast cancer undergoing chemotherapy.

Methods: We developed and optimized a novel set of MATLAB routines called the "RNA Toolbox" to extract parameters from RNA images. The code was optimized using various statistical tests (e.g., ANOVA, Bland-Altman, and intraclass correlation tests). We quantitatively analyzed the images to determine the association between these parameters using regression models and receiver operating characteristic (ROC) curves.

Results: The code was reproducible and showed good agreement with validated clinical software for the parameters extracted from both packages. The regression model and ROC results were statistically significant in predicting LVEF (R² = 0.40, P < 0.001) (AUC = 0.78). Some time-based, shape-based, and count-based parameters were significantly associated with post-chemotherapy LVEF (β = 0.09, P < 0.001), LVEF of phase image (β = 4, P = 0.030), approximate entropy (ApEn) (β = 11.6, P = 0.001), ApEn (diastolic and systolic) (β = 39, P = 0.002) and LV systole size (β = 0.03, P = 0.010).

Conclusions: Despite the limited sample size, we observed evidence of associations between several parameters and LVEF. We believe that these parameters will be more beneficial than the current methods for patients undergoing cardiotoxic chemotherapy. Moreover, this approach can aid physicians in evaluating subclinical cardiac changes during chemotherapy, and in understanding the potential benefits of cardioprotective drugs.

背景：接受生物治疗和/或化疗的乳腺癌患者需要进行多次放射性核素血管造影（RNA）或多显像采集（MUGA）扫描，以评估心脏毒性。RNA成像参数与左心室射血分数（LVEF）之间的关系仍不清楚：本研究旨在提取和评估几种新型成像生物标志物与检测化疗中乳腺癌患者左心室射血分数变化之间的关联：我们开发并优化了一套名为 "RNA 工具箱 "的新型 MATLAB 程序，用于从 RNA 图像中提取参数。通过各种统计检验（如方差分析、Bland-Altman 和类内相关检验）对代码进行了优化。我们使用回归模型和接收者操作特征曲线（ROC）对图像进行了定量分析，以确定这些参数之间的关联：结果：代码的可重复性很好，从两个软件包中提取的参数与经过验证的临床软件显示出良好的一致性。回归模型和 ROC 结果在预测 LVEF 方面具有统计学意义（R2 = 0.40，P < 0.001）（AUC = 0.78）。一些基于时间、形状和计数的参数与化疗后LVEF（β = 0.09，P < 0.001）、相位图像的LVEF（β = 4，P = 0.030）、近似熵（ApEn）（β = 11.6，P = 0.001）、ApEn（舒张期和收缩期）（β = 39，P = 0.002）和左心室收缩期大小（β = 0.03，P = 0.010）显著相关：尽管样本量有限，但我们观察到多个参数与 LVEF 之间存在关联。我们相信，这些参数对接受心脏毒性化疗的患者比目前的方法更有益。此外，这种方法还能帮助医生评估化疗期间亚临床心脏变化，了解心脏保护药物的潜在益处。

{"title":"Cardiotoxicity detection tool for breast cancer chemotherapy: a retrospective study.","authors":"Ahmad Alenezi, Fergus McKiddie, Mintu Nath, Ali Mayya, Andy Welch","doi":"10.7717/peerj-cs.2230","DOIUrl":"10.7717/peerj-cs.2230","url":null,"abstract":"Background: Patients with breast cancer undergoing biological therapy and/or chemotherapy perform multiple radionuclide angiography (RNA) or multigated acquisition (MUGA) scans to assess cardiotoxicity. The association between RNA imaging parameters and left ventricular (LV) ejection fraction (LVEF) remains unclear.Objectives: This study aimed to extract and evaluate the association of several novel imaging biomarkers to detect changes in LVEF in patients with breast cancer undergoing chemotherapy.Methods: We developed and optimized a novel set of MATLAB routines called the \"RNA Toolbox\" to extract parameters from RNA images. The code was optimized using various statistical tests (e.g., ANOVA, Bland-Altman, and intraclass correlation tests). We quantitatively analyzed the images to determine the association between these parameters using regression models and receiver operating characteristic (ROC) curves.Results: The code was reproducible and showed good agreement with validated clinical software for the parameters extracted from both packages. The regression model and ROC results were statistically significant in predicting LVEF (R2 = 0.40, P < 0.001) (AUC = 0.78). Some time-based, shape-based, and count-based parameters were significantly associated with post-chemotherapy LVEF (β = 0.09, P < 0.001), LVEF of phase image (β = 4, P = 0.030), approximate entropy (ApEn) (β = 11.6, P = 0.001), ApEn (diastolic and systolic) (β = 39, P = 0.002) and LV systole size (β = 0.03, P = 0.010).Conclusions: Despite the limited sample size, we observed evidence of associations between several parameters and LVEF. We believe that these parameters will be more beneficial than the current methods for patients undergoing cardiotoxic chemotherapy. Moreover, this approach can aid physicians in evaluating subclinical cardiac changes during chemotherapy, and in understanding the potential benefits of cardioprotective drugs.","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"12 ","pages":"e2230"},"PeriodicalIF":3.5,"publicationDate":"2024-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11323080/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141983917","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Enhanced analysis of large-scale news text data using the bidirectional-Kmeans-LSTM-CNN model 利用双向均值-LSTM-CNN 模型加强对大规模新闻文本数据的分析

IF 3.8 4区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

PeerJ Computer Science

Pub Date : 2024-08-01 DOI: 10.7717/peerj-cs.2213

Qingxiang Zeng

Traditional methods may be inefficient when processing large-scale data in the field of text mining, often struggling to identify and cluster relevant information accurately and efficiently. Additionally, capturing nuanced sentiment and emotional context within news text is challenging with conventional techniques. To address these issues, this article introduces an improved bidirectional-Kmeans-long short-term memory network-convolutional neural network (BiK-LSTM-CNN) model that incorporates emotional semantic analysis for high-dimensional news text visual extraction and media hotspot mining. The BiK-LSTM-CNN model comprises four modules: news text preprocessing, news text clustering, sentiment semantic analysis, and the BiK-LSTM-CNN model itself. By combining these components, the model effectively identifies common features within the input data, clusters similar news articles, and accurately analyzes the emotional semantics of the text. This comprehensive approach enhances both the accuracy and efficiency of visual extraction and hotspot mining. Experimental results demonstrate that compared to models such as Transformer, AdvLSTM, and NewRNN, BiK-LSTM-CNN achieves improvements in macro accuracy by 0.50%, 0.91%, and 1.34%, respectively. Similarly, macro recall rates increase by 0.51%, 1.24%, and 1.26%, while macro F1 scores improve by 0.52%, 1.23%, and 1.92%. Additionally, the BiK-LSTM-CNN model shows significant improvements in time efficiency, further establishing its potential as a more effective approach for processing and analyzing large-scale text data

在文本挖掘领域处理大规模数据时，传统方法可能效率低下，往往难以准确高效地识别和聚类相关信息。此外，传统技术难以捕捉新闻文本中细微的情感和情绪背景。为解决这些问题，本文介绍了一种改进的双向-均值-长短期记忆网络-卷积神经网络（BiK-LSTM-CNN）模型，该模型结合了情感语义分析，可用于高维新闻文本视觉提取和媒体热点挖掘。BiK-LSTM-CNN 模型包括四个模块：新闻文本预处理、新闻文本聚类、情感语义分析和 BiK-LSTM-CNN 模型本身。通过结合这些组件，该模型能有效识别输入数据中的共同特征，聚类相似的新闻文章，并准确分析文本的情感语义。这种综合方法提高了视觉提取和热点挖掘的准确性和效率。实验结果表明，与 Transformer、AdvLSTM 和 NewRNN 等模型相比，BiK-LSTM-CNN 的宏观准确率分别提高了 0.50%、0.91% 和 1.34%。同样，宏观召回率提高了 0.51%、1.24% 和 1.26%，宏观 F1 分数提高了 0.52%、1.23% 和 1.92%。此外，BiK-LSTM-CNN 模型在时间效率方面也有显著提高，进一步证实了其作为处理和分析大规模文本数据的更有效方法的潜力。

{"title":"Enhanced analysis of large-scale news text data using the bidirectional-Kmeans-LSTM-CNN model","authors":"Qingxiang Zeng","doi":"10.7717/peerj-cs.2213","DOIUrl":"https://doi.org/10.7717/peerj-cs.2213","url":null,"abstract":"Traditional methods may be inefficient when processing large-scale data in the field of text mining, often struggling to identify and cluster relevant information accurately and efficiently. Additionally, capturing nuanced sentiment and emotional context within news text is challenging with conventional techniques. To address these issues, this article introduces an improved bidirectional-Kmeans-long short-term memory network-convolutional neural network (BiK-LSTM-CNN) model that incorporates emotional semantic analysis for high-dimensional news text visual extraction and media hotspot mining. The BiK-LSTM-CNN model comprises four modules: news text preprocessing, news text clustering, sentiment semantic analysis, and the BiK-LSTM-CNN model itself. By combining these components, the model effectively identifies common features within the input data, clusters similar news articles, and accurately analyzes the emotional semantics of the text. This comprehensive approach enhances both the accuracy and efficiency of visual extraction and hotspot mining. Experimental results demonstrate that compared to models such as Transformer, AdvLSTM, and NewRNN, BiK-LSTM-CNN achieves improvements in macro accuracy by 0.50%, 0.91%, and 1.34%, respectively. Similarly, macro recall rates increase by 0.51%, 1.24%, and 1.26%, while macro F1 scores improve by 0.52%, 1.23%, and 1.92%. Additionally, the BiK-LSTM-CNN model shows significant improvements in time efficiency, further establishing its potential as a more effective approach for processing and analyzing large-scale text data","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"89 1","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141880736","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Integrating international Chinese visualization teaching and vocational skills training: leveraging attention-connectionist temporal classification models 国际汉语可视化教学与职业技能培训的整合：利用注意力-连接主义时序分类模型

IF 3.8 4区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

PeerJ Computer Science

Pub Date : 2024-07-31 DOI: 10.7717/peerj-cs.2223

Yuan Yao, Zhujun Dai, Muhammad Shahbaz

The teaching of Chinese as a second language has become increasingly crucial for promoting cross-cultural exchange and mutual learning worldwide. However, traditional approaches to international Chinese language teaching have limitations that hinder their effectiveness, such as outdated teaching materials, lack of qualified instructors, and limited access to learning facilities. To overcome these challenges, it is imperative to develop intelligent and visually engaging methods for teaching international Chinese language learners. In this article, we propose leveraging speech recognition technology within artificial intelligence to create an oral assistance platform that provides visualized pinyin-formatted feedback to learners. Additionally, this system can identify accent errors and provide vocational skills training to improve learners’ communication abilities. To achieve this, we propose the Attention-Connectionist Temporal Classification (CTC) model, which utilizes a specific temporal convolutional neural network to capture the location information necessary for accurate speech recognition. Our experimental results demonstrate that this model outperforms similar approaches, with significant reductions in error rates for both validation and test sets, compared with the original Attention model, Claim, Evidence, Reasoning (CER) is reduced by 0.67%. Overall, our proposed approach has significant potential for enhancing the efficiency and effectiveness of vocational skills training for international Chinese language learners.

汉语作为第二语言的教学对于促进世界范围内的跨文化交流和相互学习越来越重要。然而，传统的国际汉语教学方法存在一些局限性，如教材陈旧、缺乏合格的教师、学习设施有限等，这些都阻碍了教学效果。为了克服这些挑战，当务之急是为国际汉语学习者开发智能化、可视化的教学方法。在本文中，我们建议利用人工智能中的语音识别技术来创建一个口语辅助平台，为学习者提供可视化的拼音反馈。此外，该系统还能识别口音错误，并提供职业技能培训，以提高学习者的交流能力。为实现这一目标，我们提出了注意力-连接主义时态分类（CTC）模型，该模型利用特定的时态卷积神经网络捕捉准确语音识别所需的位置信息。我们的实验结果表明，该模型优于同类方法，在验证集和测试集上的错误率都显著降低，与原始注意力模型相比，声称、证据、推理（CER）降低了 0.67%。总之，我们提出的方法在提高汉语国际学习者职业技能培训的效率和效果方面具有巨大潜力。

{"title":"Integrating international Chinese visualization teaching and vocational skills training: leveraging attention-connectionist temporal classification models","authors":"Yuan Yao, Zhujun Dai, Muhammad Shahbaz","doi":"10.7717/peerj-cs.2223","DOIUrl":"https://doi.org/10.7717/peerj-cs.2223","url":null,"abstract":"The teaching of Chinese as a second language has become increasingly crucial for promoting cross-cultural exchange and mutual learning worldwide. However, traditional approaches to international Chinese language teaching have limitations that hinder their effectiveness, such as outdated teaching materials, lack of qualified instructors, and limited access to learning facilities. To overcome these challenges, it is imperative to develop intelligent and visually engaging methods for teaching international Chinese language learners. In this article, we propose leveraging speech recognition technology within artificial intelligence to create an oral assistance platform that provides visualized pinyin-formatted feedback to learners. Additionally, this system can identify accent errors and provide vocational skills training to improve learners’ communication abilities. To achieve this, we propose the Attention-Connectionist Temporal Classification (CTC) model, which utilizes a specific temporal convolutional neural network to capture the location information necessary for accurate speech recognition. Our experimental results demonstrate that this model outperforms similar approaches, with significant reductions in error rates for both validation and test sets, compared with the original Attention model, Claim, Evidence, Reasoning (CER) is reduced by 0.67%. Overall, our proposed approach has significant potential for enhancing the efficiency and effectiveness of vocational skills training for international Chinese language learners.","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"22 1","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141867365","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Wireless sensor localization based on distance optimization and assistance by mobile anchor nodes: a novel algorithm 基于距离优化和移动锚节点辅助的无线传感器定位：一种新型算法

IF 3.8 4区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

PeerJ Computer Science

Pub Date : 2024-07-31 DOI: 10.7717/peerj-cs.2179

Hui Yang

Wireless sensor networks (WSNs) have wide applications in healthcare, environmental monitoring, and target tracking, relying on sensor nodes that are joined cooperatively. The research investigates localization algorithms for both target and node in WSNs to enhance accuracy. An innovative localization algorithm characterized as an asynchronous time-of-arrival (TOA) target is proposed by implementing a differential evolution algorithm. Unlike available approaches, the proposed algorithm employs the least squares criterion to represent signal-sending time as a function of the target position. The target node’s coordinates are estimated by utilizing a differential evolution algorithm with reverse learning and adaptive redirection. A hybrid received signal strength (RSS)-TOA target localization algorithm is introduced, addressing the challenge of unknown transmission parameters. This algorithm simultaneously estimates transmitted power, path loss index, and target position by employing the RSS and TOA measurements. These proposed algorithms improve the accuracy and efficiency of wireless sensor localization, boosting performance in various WSN applications.

无线传感器网络（WSN）在医疗保健、环境监测和目标跟踪方面有着广泛的应用，它依赖于合作连接的传感器节点。这项研究探讨了 WSN 中目标和节点的定位算法，以提高精确度。通过实施差分进化算法，提出了一种创新的定位算法，其特点是异步到达时间（TOA）目标。与现有方法不同的是，所提出的算法采用最小二乘法准则，将信号发送时间表示为目标位置的函数。目标节点的坐标是通过采用反向学习和自适应重定向的差分进化算法估算出来的。引入了一种混合接收信号强度（RSS）-TOA 目标定位算法，以应对未知传输参数的挑战。该算法利用 RSS 和 TOA 测量同时估算传输功率、路径损耗指数和目标位置。这些建议的算法提高了无线传感器定位的准确性和效率，提升了各种 WSN 应用的性能。

{"title":"Wireless sensor localization based on distance optimization and assistance by mobile anchor nodes: a novel algorithm","authors":"Hui Yang","doi":"10.7717/peerj-cs.2179","DOIUrl":"https://doi.org/10.7717/peerj-cs.2179","url":null,"abstract":"Wireless sensor networks (WSNs) have wide applications in healthcare, environmental monitoring, and target tracking, relying on sensor nodes that are joined cooperatively. The research investigates localization algorithms for both target and node in WSNs to enhance accuracy. An innovative localization algorithm characterized as an asynchronous time-of-arrival (TOA) target is proposed by implementing a differential evolution algorithm. Unlike available approaches, the proposed algorithm employs the least squares criterion to represent signal-sending time as a function of the target position. The target node’s coordinates are estimated by utilizing a differential evolution algorithm with reverse learning and adaptive redirection. A hybrid received signal strength (RSS)-TOA target localization algorithm is introduced, addressing the challenge of unknown transmission parameters. This algorithm simultaneously estimates transmitted power, path loss index, and target position by employing the RSS and TOA measurements. These proposed algorithms improve the accuracy and efficiency of wireless sensor localization, boosting performance in various WSN applications.","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"46 1","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141867354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

HCGAN: hierarchical contrast generative adversarial network for unpaired sketch face synthesis HCGAN：用于无配对素描人脸合成的分层对比生成对抗网络

IF 3.8 4区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

PeerJ Computer Science

Pub Date : 2024-07-31 DOI: 10.7717/peerj-cs.2184

Kangning Du, Zhen Wang, Lin Cao, Yanan Guo, Shu Tian, Fan Zhang

Transforming optical facial images into sketches while preserving realism and facial features poses a significant challenge. The current methods that rely on paired training data are costly and resource-intensive. Furthermore, they often fail to capture the intricate features of faces, resulting in substandard sketch generation. To address these challenges, we propose the novel hierarchical contrast generative adversarial network (HCGAN). Firstly, HCGAN consists of a global sketch synthesis module that generates sketches with well-defined global features and a local sketch refinement module that enhances the ability to extract features in critical areas. Secondly, we introduce local refinement loss based on the local sketch refinement module, refining sketches at a granular level. Finally, we propose an association strategy called “warmup-epoch” and local consistency loss between the two modules to ensure HCGAN is effectively optimized. Evaluations of the CUFS and SKSF-A datasets demonstrate that our method produces high-quality sketches and outperforms existing state-of-the-art methods in terms of fidelity and realism. Compared to the current state-of-the-art methods, HCGAN reduces FID by 12.6941, 4.9124, and 9.0316 on three datasets of CUFS, respectively, and by 7.4679 on the SKSF-A dataset. Additionally, it obtained optimal scores for content fidelity (CF), global effects (GE), and local patterns (LP). The proposed HCGAN model provides a promising solution for realistic sketch synthesis under unpaired data training.

将光学面部图像转化为素描，同时保持逼真度和面部特征是一项重大挑战。目前依赖配对训练数据的方法成本高昂、资源密集。此外，这些方法往往无法捕捉人脸的复杂特征，导致草图生成不达标。为了应对这些挑战，我们提出了新颖的分层对比生成对抗网络（HCGAN）。首先，HCGAN 由一个全局草图合成模块和一个局部草图细化模块组成，前者用于生成具有明确全局特征的草图，后者用于增强提取关键区域特征的能力。其次，我们在局部草图细化模块的基础上引入了局部细化损失，对草图进行细化。最后，我们提出了一种名为 "预热-时序 "的关联策略，以及两个模块之间的局部一致性损失，以确保 HCGAN 得到有效优化。对 CUFS 和 SKSF-A 数据集的评估表明，我们的方法能生成高质量的草图，在逼真度和真实感方面优于现有的先进方法。与目前最先进的方法相比，HCGAN 在 CUFS 三个数据集上的 FID 分别降低了 12.6941、4.9124 和 9.0316，在 SKSF-A 数据集上降低了 7.4679。此外，它还在内容保真度（CF）、全局效应（GE）和局部模式（LP）方面获得了最佳分数。所提出的 HCGAN 模型为无配对数据训练下的现实草图合成提供了一种有前途的解决方案。

{"title":"HCGAN: hierarchical contrast generative adversarial network for unpaired sketch face synthesis","authors":"Kangning Du, Zhen Wang, Lin Cao, Yanan Guo, Shu Tian, Fan Zhang","doi":"10.7717/peerj-cs.2184","DOIUrl":"https://doi.org/10.7717/peerj-cs.2184","url":null,"abstract":"Transforming optical facial images into sketches while preserving realism and facial features poses a significant challenge. The current methods that rely on paired training data are costly and resource-intensive. Furthermore, they often fail to capture the intricate features of faces, resulting in substandard sketch generation. To address these challenges, we propose the novel hierarchical contrast generative adversarial network (HCGAN). Firstly, HCGAN consists of a global sketch synthesis module that generates sketches with well-defined global features and a local sketch refinement module that enhances the ability to extract features in critical areas. Secondly, we introduce local refinement loss based on the local sketch refinement module, refining sketches at a granular level. Finally, we propose an association strategy called “warmup-epoch” and local consistency loss between the two modules to ensure HCGAN is effectively optimized. Evaluations of the CUFS and SKSF-A datasets demonstrate that our method produces high-quality sketches and outperforms existing state-of-the-art methods in terms of fidelity and realism. Compared to the current state-of-the-art methods, HCGAN reduces FID by 12.6941, 4.9124, and 9.0316 on three datasets of CUFS, respectively, and by 7.4679 on the SKSF-A dataset. Additionally, it obtained optimal scores for content fidelity (CF), global effects (GE), and local patterns (LP). The proposed HCGAN model provides a promising solution for realistic sketch synthesis under unpaired data training.","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"5 1","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141867353","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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 anomaly detection model for multivariate time series with anomaly perception 具有异常感知的多变量时间序列异常检测模型

IF 3.8 4区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

PeerJ Computer Science

Pub Date : 2024-07-31 DOI: 10.7717/peerj-cs.2172

Dong Wei, Wu Sun, Xiaofeng Zou, Dan Ma, Huarong Xu, Panfeng Chen, Chaoshu Yang, Mei Chen, Hui Li

Multivariate time series anomaly detection is a crucial data mining technique with a wide range of applications in areas such as IT applications. Currently, the majority of anomaly detection methods for time series data rely on unsupervised approaches due to the rarity of anomaly labels. However, in real-world scenarios, obtaining a limited number of anomaly labels is feasible and affordable. Effective usage of these labels can offer valuable insights into the temporal characteristics of anomalies and play a pivotal role in guiding anomaly detection efforts. To improve the performance of multivariate time series anomaly detection, we proposed a novel deep learning model named EDD (Encoder-Decoder-Discriminator) that leverages limited anomaly samples. The EDD model innovatively integrates a graph attention network with long short term memory (LSTM) to extract spatial and temporal features from multivariate time series data. This integrated approach enables the model to capture complex patterns and dependencies within the data. Additionally, the model skillfully maps series data into a latent space, utilizing a carefully crafted loss function to cluster normal data tightly in the latent space while dispersing abnormal data randomly. This innovative design results in distinct probability distributions for normal and abnormal data in the latent space, enabling precise identification of anomalous data. To evaluate the performance of our EDD model, we conducted extensive experimental validation across three diverse datasets. The results demonstrate the significant superiority of our model in multivariate time series anomaly detection. Specifically, the average F1-Score of our model outperformed the second-best method by 2.7% and 73.4% in both evaluation approaches, respectively, highlighting its superior detection capabilities. These findings validate the effectiveness of our proposed EDD model in leveraging limited anomaly samples for accurate and robust anomaly detection in multivariate time series data.

多变量时间序列异常检测是一种重要的数据挖掘技术，在信息技术应用等领域有着广泛的应用。目前，由于异常标签的稀缺性，大多数时间序列数据异常检测方法都依赖于无监督方法。然而，在现实世界中，获取数量有限的异常标签是可行且经济实惠的。有效利用这些标签可以为了解异常的时间特征提供有价值的见解，并在指导异常检测工作中发挥关键作用。为了提高多元时间序列异常检测的性能，我们提出了一种名为 EDD（编码器-解码器-判别器）的新型深度学习模型，该模型可利用有限的异常样本。EDD 模型创新性地将图注意网络与长短期记忆（LSTM）整合在一起，从多元时间序列数据中提取空间和时间特征。这种集成方法使模型能够捕捉数据中的复杂模式和依赖关系。此外，该模型还能将序列数据巧妙地映射到潜在空间中，利用精心设计的损失函数将正常数据紧密聚类到潜在空间中，同时随机分散异常数据。这种创新设计使潜空间中正常数据和异常数据的概率分布截然不同，从而实现了对异常数据的精确识别。为了评估 EDD 模型的性能，我们在三个不同的数据集上进行了广泛的实验验证。结果表明，我们的模型在多变量时间序列异常检测方面具有明显的优势。具体来说，在两种评估方法中，我们的模型的平均 F1 分数分别比第二好的方法高出 2.7% 和 73.4%，凸显了其卓越的检测能力。这些发现验证了我们提出的 EDD 模型在利用有限的异常样本对多元时间序列数据进行准确、稳健的异常检测方面的有效性。

{"title":"An anomaly detection model for multivariate time series with anomaly perception","authors":"Dong Wei, Wu Sun, Xiaofeng Zou, Dan Ma, Huarong Xu, Panfeng Chen, Chaoshu Yang, Mei Chen, Hui Li","doi":"10.7717/peerj-cs.2172","DOIUrl":"https://doi.org/10.7717/peerj-cs.2172","url":null,"abstract":"Multivariate time series anomaly detection is a crucial data mining technique with a wide range of applications in areas such as IT applications. Currently, the majority of anomaly detection methods for time series data rely on unsupervised approaches due to the rarity of anomaly labels. However, in real-world scenarios, obtaining a limited number of anomaly labels is feasible and affordable. Effective usage of these labels can offer valuable insights into the temporal characteristics of anomalies and play a pivotal role in guiding anomaly detection efforts. To improve the performance of multivariate time series anomaly detection, we proposed a novel deep learning model named EDD (Encoder-Decoder-Discriminator) that leverages limited anomaly samples. The EDD model innovatively integrates a graph attention network with long short term memory (LSTM) to extract spatial and temporal features from multivariate time series data. This integrated approach enables the model to capture complex patterns and dependencies within the data. Additionally, the model skillfully maps series data into a latent space, utilizing a carefully crafted loss function to cluster normal data tightly in the latent space while dispersing abnormal data randomly. This innovative design results in distinct probability distributions for normal and abnormal data in the latent space, enabling precise identification of anomalous data. To evaluate the performance of our EDD model, we conducted extensive experimental validation across three diverse datasets. The results demonstrate the significant superiority of our model in multivariate time series anomaly detection. Specifically, the average F1-Score of our model outperformed the second-best method by 2.7% and 73.4% in both evaluation approaches, respectively, highlighting its superior detection capabilities. These findings validate the effectiveness of our proposed EDD model in leveraging limited anomaly samples for accurate and robust anomaly detection in multivariate time series data.","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"282 1","pages":""},"PeriodicalIF":3.8,"publicationDate":"2024-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141867370","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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