检索结果-内蒙古大学图书馆

AutoDiagn: An Automated Real-Time Diagnosis Framework for Big data Systems

ieee TRANSACTIONS ON COMPUTERS 2022年第5期71卷 1035-1048页

作者： Demirbaga, Umit Wen, Zhenyu Noor, Ayman Mitra, Karan Alwasel, Khaled Garg, Saurabh Zomaya, Albert Y. Ranjan, Rajiv Newcastle Univ Newcastle Upon Tyne NE1 7RU Tyne & Wear England Bartin Univ TR-74110 Bartin Turkey Taibah Univ Medina 42353 Saudi Arabia Lulea Univ Technol S-97187 Lulea Sweden Saudi Elect Univ Riyadh 11564 Saudi Arabia Univ Tasmania Hobart Tas 7005 Australia Univ Sydney Camperdown NSW 2006 Australia

Big data processing systems, such as Hadoop and Spark, usually work in large-scale, highly-concurrent, and multi-tenant environments that can easily cause hardware and software malfunctions or failures, thereby leading to performance degradation. Several systems and methods exist to detect big data processing systems' performance degradation, perform root-cause analysis, and even overcome the issues causing such degradation. However, these solutions focus on specific problems such as stragglers and inefficient resource utilization. There is a lack of a generic and extensible framework to support the real-time diagnosis of big data systems. In this article, we propose, develop and validate AutoDiagn. This generic and flexible framework provides holistic monitoring of a big data system while detecting performance degradation and enabling root-cause analysis. We present an implementation and evaluation of AutoDiagn that interacts with a Hadoop cluster deployed on a public cloud and tested with real-world benchmark applications. Experimental results show that AutoDiagn can offer a high accuracy root-cause analysis framework, at the same time as offering a small resource footprint, high throughput, and low latency.

关键词： Big data Monitoring Task analysis Real-time systems Degradation Measurement data visualization Root-cause analysis big data systems QoS hadoop performance

来源：评论

学校读者我要写书评

暂无评论

Developer Behaviors in Validating and Repairing LLM-Generated Code Using IDE and Eye Tracking

Developer Behaviors in Validating and Repairing LLM-Generate...

引用

ieee symposium on Visual Languages and Human-Centric Computing (VL/HCC)

作者： Tang, Ningzhi Chen, Meng Ning, Zheng Bansal, Aakash Huang, Yu McMillan, Collin Li, Toby Jia-Jun Univ Notre Dame Notre Dame IN 46556 USA Vanderbilt Univ 221 Kirkland Hall Nashville TN 37235 USA

ISBN: (纸本)9798350376920;9798350366136

The increasing use of large language model (LLM)-powered code generation tools, such as GitHub Copilot, is transforming software engineering practices. This paper investigates how developers validate and repair code generated by Copilot and examines the impact of code provenance awareness during these processes. We conducted a lab study with 28 participants tasked with validating and repairing Copilot-generated code in three software projects. Participants were randomly divided into two groups: one informed about the provenance of LLM-generated code and the other not. We collected data on IDE interactions, eye-tracking, cognitive workload assessments, and conducted semi-structured interviews. Our results indicate that, without explicit information, developers often fail to identify the LLM origin of the code. Developers exhibit LLM-specific behaviors such as frequent switching between code and comments, different attentional focus, and a tendency to delete and rewrite code. Being aware of the code's provenance led to improved performance, increased search efforts, more frequent Copilot usage, and higher cognitive workload. These findings enhance our understanding of developer interactions with LLM-generated code and inform the design of tools for effective human-LLM collaboration in software development.

关键词： GitHub Copilot developer behavior analysis debugging strategy eye tracking IDE tracking

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Food Retrieval: Learning a Joint Embedding of Food Images and Recipes With Semantic Consistency and Attention Mechanism

引用

ieee TRANSACTIONS ON MULTIMEDIA 2022年 24卷 2515-2525页

作者： Wang, Hao Sahoo, Doyen Liu, Chenghao Shu, Ke Achananuparp, Palakorn Lim, Ee-peng Hoi, Steven C. H. Nanyang Technol Univ Singapore 639798 Singapore Singapore Management Univ Singapore 188065 Singapore Salesforce Res Asia Singapore 038985 Singapore

Food retrieval is an important task to perform analysis of food-related information, where we are interested in retrieving relevant information about the queried food item such as ingredients, cooking instructions, etc. In this paper, we investigate cross-modal retrieval between food images and cooking recipes. The goal is to learn an embedding of images and recipes in a common feature space, such that the corresponding image-recipe embeddings lie close to one another. Two major challenges in addressing this problem are 1) large intra-variance and small inter-variance across cross-modal food data;and 2) difficulties in obtaining discriminative recipe representations. To address these two problems, we propose Semantic-Consistent and Attention-based Networks (SCAN), which regularize the embeddings of the two modalities through aligning output semantic probabilities. Besides, we exploit a self-attention mechanism to improve the embedding of recipes. We evaluate the performance of the proposed method on the large-scale Recipe1M dataset, and show that we can outperform several state-of-the-art cross-modal retrieval strategies for food images and cooking recipes by a significant margin.

关键词： Semantics Task analysis data models Correlation visualization Training Sugar Deep learning cross-modal retrieval vision-and-language

来源：评论

学校读者我要写书评

暂无评论

analysis of Spatio-Temporal Fishing Status of large purse seine fishery Using AIS data 13

Analysis of Spatio-Temporal Fishing Status of Large purse se...

引用

Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International symposium on Advanced Intelligent Systems, SCIS and ISIS 2024

作者： Kim, Kwang-Il Song, Eun-A Kim, Hye-Min Jeong, Jung-Sik Jeju National University Department of Marine Industry and Maritime Police Jeju Korea Republic of Jeju National University Department of Fishery Jeju Korea Republic of Mokpo National Maritime University Division of Maritime Transportation Mokpo Korea Republic of

ISBN: (纸本)9798350373332

Globally., fishery resources are declining due to changes in the marine environment and overfishing. The methods used today have limitations in accurately identifying actual fishing areas. This study uses AIS trajectory data to identify the actual fishing areas of large purse seines and estimate spatio-temporal catch. AIS data from July 2019 to June 2022 were analyzed., and CPUE (Catch Per Unit Effort) was calculated using fish landing report data. Results indicated a southward shift in fishing grounds from 2019 to 2021, with increased CPUE in southwestern Jeju waters. This study highlights the effectiveness of AIS data in accurately estimating fishing patterns and catch, suggesting future research to incorporate environmental data for comprehensive analysis. © 2024 ieee.

关键词： Fisheries

来源：评论

学校读者我要写书评

暂无评论

Towards Adaptive Refinement for Multivariate Functional Approximation of Scientific data

Towards Adaptive Refinement for Multivariate Functional Appr...

引用

ieee symposium on large data analysis and visualization (LDAV)

作者： Tom Peterka David Lenz Iulian Grindeanu Vijay S. Mahadevan Argonne National Laboratory

We investigate a data model for adaptive refinement in multivariate functional approximation of scientific data, based on a mesh of varying-resolution tensor products, and offering reduced size compared with a single tensor product representation. The mesh of tensor products adjoins in irregular fashion to tessellate the entire domain, with high-degree continuity across tensor product boundaries. The result is that regions of refinement, with additional knots and control points, are localized to individual tensor products rather than extending throughout the entire domain. The model attains similar accuracy with fewer total control points than a single tensor product model, at the cost of added computational complexity to manage the continuity and accuracy across tensor products. We describe our high-dimensional data organization and demonstrate how to approximate scientific datasets using our data model. Size and speed are compared between a single tensor product and our representation. Initial results demonstrate correct functionality and modest reduction in the number of control points required to attain comparable accuracy as a single tensor, with increased computation time as expected. Our initial findings indicate two avenues for future research: additional tuning of the adaptive refinement algorithm to reduce size further, and accelerating computation through parallelism.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual-View Curricular Optimal Transport for Cross-Lingual Cross-Modal Retrieval

引用

ieee TRANSACTIONS ON IMAGE PROCESSING 2024年 33卷 1522-1533页

作者： Wang, Yabing Wang, Shuhui Luo, Hao Dong, Jianfeng Wang, Fan Han, Meng Wang, Xun Wang, Meng Xi An Jiao Tong Univ Natl Key Lab Human Machine Hybrid Augmented Intell Natl Engn Res Ctr Visual Informat & Applicat Xian 710049 Shaanxi Peoples R China Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot Xian 710049 Shaanxi Peoples R China Zhejiang Gongshang Univ Coll Comp Sci & Technol Hangzhou 310035 Peoples R China Chinese Acad Sci Inst Comp Technol Beijing 100190 Peoples R China Alibaba Grp Hangzhou 310052 Peoples R China Hupan Lab Hangzhou 310058 Zhejiang Peoples R China Zhejiang Key Lab E Commerce Zhoushan 311121 Peoples R China Zhejiang Univ Coll Comp Sci & Technol Hangzhou 310058 Peoples R China Hefei Univ Technol Sch Comp Sci & Informat Engn Hefei 230009 Peoples R China

Current research on cross-modal retrieval is mostly English-oriented, as the availability of a large number of English-oriented human-labeled vision-language corpora. In order to break the limit of non-English labeled data, cross-lingual cross-modal retrieval (CCR) has attracted increasing attention. Most CCR methods construct pseudo-parallel vision-language corpora via Machine Translation (MT) to achieve cross-lingual transfer. However, the translated sentences from MT are generally imperfect in describing the corresponding visual contents. Improperly assuming the pseudo-parallel data are correctly correlated will make the networks overfit to the noisy correspondence. Therefore, we propose Dual-view Curricular Optimal Transport (DCOT) to learn with noisy correspondence in CCR. In particular, we quantify the confidence of the sample pair correlation with optimal transport theory from both the cross-lingual and cross-modal views, and design dual-view curriculum learning to dynamically model the transportation costs according to the learning stage of the two views. Extensive experiments are conducted on two multilingual image-text datasets and one video-text dataset, and the results demonstrate the effectiveness and robustness of the proposed method. Besides, our proposed method also shows a good expansibility to cross-lingual image-text baselines and a decent generalization on out-of-domain data.

关键词： visualization Noise measurement Estimation Costs Transportation Training Task analysis Cross-modal retrieval noise correspondence learning cross-lingual transfer optimal transport machine translation

来源：评论

学校读者我要写书评

暂无评论

Bibliometric analysis and visualization of Machine Learning-Based Credit Card Fraud Detection

Bibliometric Analysis and Visualization of Machine Learning-...

引用

2024 International Conference on Information Technology Research and Innovation, ICITRI 2024

作者： Suhartono Zaman, Syahiduz Chamidy, Totok UIN Maulana Malik Ibrahim Malang Department of information engineering Malang Indonesia

ISBN: (纸本)9798350376210

Machine learning is often used in credit card fraud detection. Its ability to analyze large amounts of transaction data and identify patterns of fraudulent activity. The aim of this study is to provide insights into the research status, mapping process and annual topics of machine learning research on credit card fraud detection, and to provide relevant references for future research. Research phases with three approaches. The first approach is descriptive statistical analysis for data collection using Scopus web and Herzing's Publish or Perish. The second approach uses quantitative methods for citation analysis with a bibliometric approach using Vos Viewer application. The research findings are related to the analysis of credit card fraud research divided into three clusters, the first cluster is the research stream using machine learning in data mining, the second cluster is the research stream using machine learning to detect credit card fraud, the third cluster is the research stream using machine learning to classify credit card fraud. The second cluster can resolve the complexity of credit card transaction data and increase the accuracy of the fraud detection system, for the third cluster, we can build a more effective classification in resolving imbalanced data and limited transaction records. A growing research trend is in the third cluster, research related to the performance of credit card fraud classification based on unbalanced data and limited fraud data. Further research is recommended to examine the evolution of the literature on the use of machine learning to detect credit card fraud and to conduct comparative studies between the Scopus, Web of Science and ScienceDirect databases to expand the literature. © 2024 ieee.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Roofline Performance analysis of DNN Architectures on CPU and GPU Systems 25

Roofline Performance Analysis of DNN Architectures on CPU an...

引用

25th International symposium on Quality Electronic Design (ISQED)

作者： Prashanth, H. C. Rao, Madhav Int Inst Informat Technol Bangalore Bangalore Karnataka India IIIT Bangalore Bangalore Karnataka India

ISBN: (纸本)9798350309270;9798350309287

The significance of prior characterizations of Deep Neural Network (DNN) Architectures on CPU and GPU is likely to benefit in understanding the resources and timing constraints for the large-scale adoption and deployment. The paper focuses on 43 popular DNN workloads profiling on two different segments of CPU and GPUs, each, including Workstation and mobile class. The roof-line performance analysis model aids in picking the optimal architectural configurations for the real-time resource-constrained design with respect to the Arithmetic Intensity of the model run and throughput extracted from the system. The selected DNNs ranging from MobileNet to VGGNet models showcase a wide characteristics in terms of the number of MAC operations per inference, data movement, and parameter size. The average throughput improvement of around 10x was reported for DNNs when configured to run on 48 multiple threads over single threaded execution on CPU Workstation, but no direct improvement of throughput was reported for changes in batch size. The DNN models when run on GPU Workstation showed 98x improvement in throughput for batch size of 16 over size of 1, whereas it remains insensitive to changes for multi-threaded execution.

关键词： DNNs Roofline Model Throughput CPU GPU Mobile Compute

来源：评论

学校读者我要写书评

暂无评论

Weak Signal Underwater Acoustic Target Recognition Based on large Vision Model 4

Weak Signal Underwater Acoustic Target Recognition Based on ...

引用

4th International symposium on Computer Technology and Information Science, ISCTIS 2024

作者： Gong, Xuefang Liu, Chengtao Xu, Wude Zheng, Bo Ma, Fanglan Nie, Yingying Gansu Academy of Sciences Institute of Sensor Technology Lanzhou China Xi'an Polytechnic University Xi'an China

ISBN: (纸本)9798350354560

The accurate recognition of underwater acoustic targets in environments characterized by weak signals presents a significant challenge for naval defense and marine research. Traditional methods often struggle with the low signal-to-noise ratio inherent in underwater acoustics, leading to decreased accuracy and reliability. We introduce an innovative approach to underwater acoustic target recognition by leveraging the capabilities of the large vision model DINOv2, originally developed for visual data processing. We propose a novel method that adapts DINOv2 for the analysis of underwater acoustic signals, transforming the auditory data into a visual-like representation that the model can effectively process. Our approach first employs a feature extraction process that transforms the acoustic data into spectrogram images, thereby amplifying the weak signals. These spectrogram images serve as inputs for the DINOv2 model, which has been fine-tuned to recognize specific underwater acoustic targets. With the excellent feature capabilities of the large visual model DINOv2, it is possible to accurately identify weak signal underwater target recognition (such as various ships) with high precision. Experiments on public datasets have shown that our recognition accuracy significantly surpasses existing methods, demonstrating the effectiveness of the proposed approach. © 2024 ieee.

关键词： Spectrographs

来源：评论

学校读者我要写书评

暂无评论

Protected or Porous: A Comparative analysis of Threat Detection Capability of IoT Safeguards 44

Protected or Porous: A Comparative Analysis of Threat Detect...

引用

44th ieee symposium on Security and Privacy (SP)

作者： Mandalari, Anna Maria Haddadi, Hamed Dubois, Daniel J. Choffnes, David UCL London England Imperial Coll London London England Northeastern Univ Boston MA 02115 USA

ISBN: (纸本)9781665493369

Consumer Internet of Things (IoT) devices are increasingly common, from smart speakers to security cameras, in homes. Along with their benefits come potential privacy and security threats. To limit these threats a number of commercial services have become available (IoT safeguards). The safeguards claim to provide protection against IoT privacy risks and security threats. However, the effectiveness and the associated privacy risks of these safeguards remains a key open question. In this paper, we investigate the threat detection capabilities of IoT safeguards for the first time. We develop and release an approach for automated safeguards experimentation to reveal their response to common security threats and privacy risks. We perform thousands of automated experiments using popular commercial IoT safeguards when deployed in a large IoT testbed. Our results indicate not only that these devices may be ineffective in preventing risks, but also their cloud interactions and data collection operations may introduce privacy risks for the households that adopt them.

关键词： anomaly-detection IDS Internet-of-Things IPS privacy security

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：