检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Tian, Jiyu Li, Mingchu Wang, Zumin Chen, Liming Qin, Jing Zhang, Runfa The School of Software Technology Dalian University of Technology Dalian China The School of Computer and Information Engineering Jiangxi Normal University Jiangxi Nanchang China The College of Information Engineering Dalian University Dalian China The School of Computer Science and Technology Dalian University of Technology Dalian China The School of Software Engineering Dalian University Dalian China The School of Automation and Software Engineering Shanxi University Taiyuan China

Log anomaly detection (LAD) is essential to ensure safe and stable operation of software systems. Although current LAD methods exhibit significant potential in addressing challenges posed by unstable log events and temporal sequence patterns, their limitations in detection efficiency and generalization ability present a formidable challenge when dealing with evolving systems. To construct a real-time and reliable online log anomaly detection model, we propose OMLog, a semi-supervised online meta-learning method, to effectively tackle the distribution shift issue caused by changes in log event types and frequencies. Specifically, we introduce a maximum mean discrepancy-based distribution shift detection method to identify distribution changes in unseen log sequences. Depending on the identified distribution gap, the method can automatically trigger online fine-grained detection or offline fast inference. Furthermore, we design an online learning mechanism based on meta-learning, which can effectively learn the highly repetitive patterns of log sequences in the feature space, thereby enhancing the generalization ability of the model to evolving data. Extensive experiments conducted on two publicly available log datasets, HDFS and BGL, validate the effectiveness of the OMLog approach. When trained using only normal log sequences, the proposed approach achieves the F1-Score of 93.7% and 64.9%, respectively, surpassing the performance of the state-of-the-art (SOTA) LAD methods and demonstrating superior detection efficiency. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Reinforcement Learning for Out-of-Distribution Recovery via Auxiliary Reward

Self-Supervised Reinforcement Learning for Out-of-Distributi...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yufeng Xie Yinan Wang Han Wang Qingshan Li Xi’an Key Laboratory of Intelligent Software Engineering Xidian University Xi’an China School of Computer Science and Technology Xidian University Xi’an China

Recently, the real-world applications of reinforcement learning (RL) have seen the problem of taking actions in an out-of-distribution (OOD) state. However, most existing research is limited to take actions to narrow the visited training distribution and OOD, and does not consider the efficiency to choose such actions. In this paper, we propose a novel approach, called Self-Supervised Reinforcement Learning for OOD recovery via Auxiliary Reward (SRL-AR), to address this issue. By leveraging cumulative reward, we force the representations to discriminate state-action pairs with different returns as auxiliary task. Then, the auxiliary reward calculated from the auxiliary loss is used to generate a new policy that can effectively handle OOD situations. Moreover, we show that our method outperforms prior works in terms of asymptotic performance and sample efficiency on MuJoCo tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Inherent-attribute-aware dual-graph autoencoder for rating prediction

引用

Journal of Information and Intelligence 2024年第1期2卷 82-97页

作者： Yangtao Zhou Qingshan Li Hua Chu Jianan Li Lejia Yang Biaobiao Wei Luqiao Wang Wanqiang Yang School of Computer Science and Technology Xidian UniversityXi'an 710071China Intelligent Financial Software Engineering New Technology Joint Laboratory Xidian UniversityXi'an 710071China Shanghai Fairyland Software Corp. Ltd.Shanghai 200233China

Autoencoder-based rating prediction methods with external attributes have received wide attention due to their ability to accurately capture users'***,existing methods still have two significant limitations:i)External attributes are often unavailable in the real world due to privacy issues,leading to low quality of representations;and ii)existing methods lack considering complex associations in users'rating behaviors during the encoding *** meet these challenges,this paper innovatively proposes an inherent-attribute-aware dual-graph autoencoder,named IADGAE,for rating *** address the low quality of representations due to the unavailability of external attributes,we propose an inherent attribute perception module that mines inductive user active patterns and item popularity patterns from users'rating behaviors to strengthen user and item *** exploit the complex associations hidden in users’rating behaviors,we design an encoder on the item-item co-occurrence graph to capture the co-occurrence frequency features among ***,we propose a dual-graph feature encoder framework to simultaneously encode and fuse the high-order representations learned from the user-item rating graph and item-item co-occurrence *** experiments on three real datasets demonstrate that IADGAE is effective and outperforms existing rating prediction methods,which achieves a significant improvement of 4.51%~41.63%in the RMSE metric.

关键词： Rating prediction Graph convolutional network Autoencoder Inherent attribute aware

来源：评论

学校读者我要写书评

暂无评论

Genealogical Relationship Extraction from Unstructured Text Using Fine-Tuned Transformer Models

Genealogical Relationship Extraction from Unstructured Text ...

引用

International Conference on Semantic Computing

作者： Carloangello Parrolivelli Lubomir Stanchev Computer Science and Software Engineering Department California Polytechnic State University San Luis Obispo CA USA

The paper tackles the task of extracting genealogical relationships, such as "sibling-of", "parent-of", "child-of", and "spouse-of", from unstructured, free-form text. In order ...

The paper tackles the task of extracting genealogical relationships, such as "sibling-of", "parent-of", "child-of", and "spouse-of", from unstructured, free-form text. In order to solve the problem, we propose a three-stage pipeline consisting of Named Entity Recognition (NER), Coreference Resolution (CR), and Relationship Classification (RC). NER identifies tokens in the text that refer to people, such as proper nouns or nicknames, using the SpaCy software. CR maps multiple tokens representing pronouns to their antecedents. For example, CR could map "She", "His sister", and "Maria" to the antecedent "Maria Johnson". CR allows us to transform a genealogical relationship between two tokens, such as the sibling relationship between "him" and "his sister", to a relationship between the corresponding antecedents, for example, "Bob Johnson" and "Maria Johnson". Our novel algorithm for coreference resolution is based on the AllenNLP software. The last step is the RC, which classifies the relationship between two sets of tokens given adjacent context. We use the LUKE transformer deep-learning model to extract the genealogical relationships. The end-to-end pipeline can extract and correctly classify genealogical relationships from our hand-labeled testing set of Wikipedia documents with macro precision, recall, and F1 scores of 0.794, 0.616, and 0.676, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Wireless Data Transmission: A GAN-based Approach for Time Series Data Restoration

Enhancing Wireless Data Transmission: A GAN-based Approach f...

引用

International Conference on Information Networking

作者： Daejin Han Woongsoo Na Dept. of Computer Science and Engineering Kongju National University Cheonan Korea Dept. of Software Kongju National University Cheonan Korea

ISBN: (数字)9798350330946

ISBN: (纸本)9798350330953

Recent technological advancements have led to a significant increase in the use of wireless communication for data transmission, particularly in sensor networks and device-to-device communications, necessitating not only rapid but also reliable data exchange. In conventional wireless communication, if a packet is lost in transmission due to retransmission, it is retransmitted. In this case, the subsequent packets will wait for them so that the order of the packets is not reversed, which is called Head of Line (HOL) Blocking. This problem can lead to overall transmission delays and losses, and is one of the reasons for inconsistent data transfer times. In this paper, we propose a technique to significantly reduce the retransmission rate of the sender and data loss by retransmission using Generative Adversarial Net (GAN). To evaluate the performance of this study, we applied our technique to a portion of SolarCube solar data assuming that it was corrupted, such as NaN processing, value change, and sign change, and the average recovery rate was 92.36%, demonstrating that it is possible to detect and recover losses in the data transmission process. This research is expected to have applications in data loss detection and recovery during transmission of time series data.

关键词： Wireless communication Wireless sensor networks Time series analysis Propagation losses Generative adversarial networks Data transfer Device-to-device communication

来源：评论

学校读者我要写书评

暂无评论

Classification of Human Physical Activities and Postures During Everyday Life

Classification of Human Physical Activities and Postures Dur...

引用

International Conference on Emerging Technologies, ICET

作者： Sheharyar Khan Sadam Hussain Noorani Aamir Arsalan Awais Mahmood Usman Rauf Zohaib Ali Department of Computer Engineering University of Engineering & Technology Taxila Pakistan Department of Software Engineering Fatima Jinnah Women University Rawalpindi Pakistan Department of Computer Science SZABIST University Islamabad Pakistan Department of Computer Science Bahria University Islamabad Pakistan

Nowadays Wearable sensor-based Human Activity Recognition (HAR) is gaining popularity for its affordability and low computational demands. These sensors are widely used in healthcare and surveillance. However, using smartphone sensors for HAR can be inaccurate due to their non-fixed position. This study uses the publicly available Human Activity Recognition Trondheim dataset (HARTH) to develop a HAR model. The proposed HAR model is capable to recognize diverse human daily life activities in the free-living environment. Identifying individual natural behaviour in the wild (free living) remains challenging because humans engage in unscripted daily activities. While working with controlled conditions (scripted data) can produce optimal results, this system often struggles when applied in real-life scenario. Multiple machine learning classifiers are tested on time domain features extracted from sensor data, with the Multilayer Perceptron (MLP) classifier achieving an impressive 92.92% accuracy, making a significant contribution to the HAR field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Leveraging Multimodal Ensemble Fusion-Based Deep Learning for COVID-19 on Chest Radiographs

引用

computer Systems science & engineering 2023年第10期47卷 873-889页

作者： Mohamed Yacin Sikkandar K.Hemalatha M.Subashree S.Srinivasan Seifedine Kadry Jungeun Kim Keejun Han Department of Medical Equipment Technology College of Applied Medical SciencesMajmaah UniversityAl Majmaah11952Saudi Arabia Department of Biomedical Engineering Bannari Amman Institute of TechnologySathyamangalam638401India Department of Computer Science and Engineering K.Ramakrishnan College of EngineeringTiruchirappalli621112India Institute of Biomedical Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesSaveetha UniversityChennai602105India Department of Applied Data Science Noroff University CollegeKristiansandNorway Artificial Intelligence Research Center(AIRC) College of Engineering and Information TechnologyAjman UniversityAjmanUnited Arab Emirates Department of Electrical and Computer Engineering Lebanese American UniversityByblosLebanon Department of Software Kongju National UniversityCheonan31080Korea Division of Computer Engineering Hansung UniversitySeoul02876Korea

Recently,COVID-19 has posed a challenging threat to researchers,scientists,healthcare professionals,and administrations over the globe,from its diagnosis to its *** researchers are making persistent efforts to derive probable solutions formanaging the pandemic in their *** of the widespread and effective ways to detect COVID-19 is to utilize radiological images comprising X-rays and computed tomography(CT)*** the same time,the recent advances in machine learning(ML)and deep learning(DL)models show promising results in medical ***,the convolutional neural network(CNN)model can be applied to identifying abnormalities on chest *** the epidemic of COVID-19,much research is led on processing the data compared with DL techniques,particularly *** study develops an improved fruit fly optimization with a deep learning-enabled fusion(IFFO-DLEF)model for COVID-19 detection and *** major intention of the IFFO-DLEF model is to investigate the presence or absence of *** do so,the presented IFFODLEF model applies image pre-processing at the initial *** addition,the ensemble of three DL models such as DenseNet169,EfficientNet,and ResNet50,are used for feature ***,the IFFO algorithm with a multilayer perceptron(MLP)classification model is utilized to identify and classify *** parameter optimization of the MLP approach utilizing the IFFO technique helps in accomplishing enhanced classification *** experimental result analysis of the IFFO-DLEF model carried out on the CXR image database portrayed the better performance of the presented IFFO-DLEF model over recent approaches.

关键词： COVID-19 computer vision deep learning image classification fusion model

来源：评论

学校读者我要写书评

暂无评论

Pseudo-Inverted Bottleneck Convolution for Darts Search Space

Pseudo-Inverted Bottleneck Convolution for Darts Search Spac...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Arash Ahmadian Louis S.P. Liu Yue Fei Konstantinos N. Plataniotis Mahdi S. Hosseini The Edward S. Rogers Sr. Department of Electrical & Computer Engineering University of Toronto Canada Computer Science and Software Engineering (CSSE) Concordia University Canada

Differentiable Architecture Search (DARTS) has attracted considerable attention as a gradient-based neural architecture search method. Since the introduction of DARTS, there has been little work done on adapting the action space based on state-of-art architecture design principles for CNNs. In this work, we aim to address this gap by incrementally augmenting the DARTS search space with micro-design changes inspired by ConvNeXt and studying the trade-off between accuracy, evaluation layer count, and computational cost. We introduce the Pseudo-Inverted Bottleneck Conv (PIBConv) block intending to reduce the computational footprint of the inverted bottleneck block proposed in ConvNeXt. Our proposed architecture is much less sensitive to evaluation layer count and outperforms a DARTS network with similar size significantly, at layer counts as small as 2. Furthermore, with less layers, not only does it achieve higher accuracy with lower computational footprint (measured in GMACs) and parameter count, GradCAM comparisons show that our network can better detect distinctive features of target objects compared to DARTS. Code is available from https://***/mahdihosseini/PIBConv.

关键词： Representation learning Performance evaluation Visualization Convolution Microprocessors computer architecture Search problems

来源：评论

学校读者我要写书评

暂无评论

Training-Free Robust Neural Network Search Via Pruning

Training-Free Robust Neural Network Search Via Pruning

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Qiancheng Yang Yong Luo Bo Du National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China Hubei Luojia Laboratory Wuhan China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Adversarial examples widely exist in visual tasks, which look almost the same as normal images but can induce neural networks to make completely wrong predictions. This exposes significant risks to deploying deep learning to visual tasks. The robustness of neural networks to adversarial images is shaped by multiple factors entangled together, including adversarial training strategies, model architectures, hyper-parameters, and optimization algorithms. This makes searching for robust architectures a significantly complex task. In this paper, we propose a Robust Training-free Pruning neural architecture search (RTP-NAS) framework that endeavors to disentangle the influence of architectures from other factors. We adopt Universal Adversarial Perturbations (UAPs) to construct a transferable adversarial data space across different network architectures. RTP-NAS further employs two adversarial training-free indicators, the condition number of the neural tangent kernel (NTK) and the number of linear regions calculated on the adversarial data space, to measure the intrinsic adversarial robustness of candidate architectures. Comprehensive experiments show that the proposed method achieves superior performance to other existing approaches, with a significantly lower computational cost. The code will be released publicly.

关键词： Training Visualization Analytical models Perturbation methods Neural networks computer architecture Network architecture

来源：评论

学校读者我要写书评

暂无评论

A study on the impact of pre-trained model on Just-In-Time defect prediction

arXiv

引用

arXiv 2023年

作者： Guo, Yuxiang Gao, Xiaopeng Zhang, Zhenyu Chan, W.K. Jiang, Bo State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China Department of Computer Science City University of Hong Kong Hong Kong

Previous researchers conducting Just-In-Time (JIT) defect prediction tasks have primarily focused on the performance of individual pre-trained models, without exploring the relationship between different pre-trained models as backbones. In this study, we build six models: RoBERTaJIT, CodeBERTJIT, BARTJIT, PLBARTJIT, GPT2JIT, and CodeGPTJIT, each with a distinct pre-trained model as its backbone. We systematically explore the differences and connections between these models. Specifically, we investigate the performance of the models when using Commit code and Commit message as inputs, as well as the relationship between training efficiency and model distribution among these six models. Additionally, we conduct an ablation experiment to explore the sensitivity of each model to inputs. Furthermore, we investigate how the models perform in zero-shot and few-shot scenarios. Our findings indicate that each model based on different backbones shows improvements, and when the backbone’s pre-training model is similar, the training resources that need to be consumed are closer. We also observe that Commit code plays a significant role in defect detection, and different pre-trained models demonstrate better defect detection ability with a balanced dataset under few-shot scenarios. These results provide new insights for optimizing JIT defect prediction tasks using pre-trained models and highlight the factors that require more attention when constructing such models. Additionally, CodeGPTJIT and GPT2JIT achieved better performance than DeepJIT and CC2Vec on the two datasets respectively under 2000 training samples. These findings emphasize the effectiveness of transformer-based pre-trained models in JIT defect prediction tasks, especially in scenarios with limited training data. Copyright © 2023, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：