检索结果-南通市图书馆

An Online Algorithm Based on Replication for Using Spot Instances in IaaS Clouds

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2024年第1期39卷 103-115页

作者：许志伟潘丽刘士军 school of software Shandong UniversityJinan 250101China

Infrastructure-as-a-Service(IaaS)cloud platforms offer resources with diverse buying options.Users can run an instance on the on-demand market which is stable but expensive or on the spot market with a significant discount.However,users have to carefully weigh the low cost of spot instances against their poor availability.Spot instances will be revoked when the revocation event occurs.Thus,an important problem that an IaaS user faces now is how to use spot in-stances in a cost-effective and low-risk way.Based on the replication-based fault tolerance mechanism,we propose an on-line termination algorithm that optimizes the cost of using spot instances while ensuring operational stability.We prove that in most cases,the cost of our proposed online algorithm will not exceed twice the minimum cost of the optimal of-fline algorithm that knows the exact future a priori.Through a large number of experiments,we verify that our algorithm in most cases has a competitive ratio of no more than 2,and in other cases it can also reach the guaranteed competitive ratio.

关键词： Infrastructure-as-a-Service(IaaS)cloud cost management competitive analysis online algorithm spot instance

Key points and visible part fusion attention network for occluded pedestrian detection in traffic environments

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Optoelectronics Letters 2024年第7期20卷 430-436页

作者： LIU Peiyu MA Yixuan school of software Engineering Beijing Jiaotong University

Aiming at the problem of low detection accuracy of occluded pedestrian in traffic environments,this paper proposes a key points and visible part fusion network for occluded pedestrian detection.The proposed algorithm constructs two attention modules by introducing human key points and the bounding box of visible parts respectively,which suppresses the occluded parts in the channel features and spatial features of pedestrian features respectively.Experimental results on CityPersons and Caltech datasets demonstrate the effectiveness of the proposed algorithm.The missing rate(MR) is reduced to 40.78 on the Heavy subset of the CityPersons dataset and surpasses many outstanding methods.

关键词： A

An Empirical Study on the Effectiveness of Adversarial Examples in Malware Detection

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第6期139卷 3535-3563页

作者： Younghoon Ban Myeonghyun Kim Haehyun Cho school of software Soongsil UniversitySeoul06978Korea

Antivirus vendors and the research community employ Machine Learning(ML)or Deep Learning(DL)-based static analysis techniques for efficient identification of new threats,given the continual emergence of novel malware variants.On the other hand,numerous researchers have reported that Adversarial Examples(AEs),generated by manipulating previously detected malware,can successfully evade ML/DL-based classifiers.Commercial antivirus systems,in particular,have been identified as vulnerable to such AEs.This paper firstly focuses on conducting black-box attacks to circumvent ML/DL-based malware classifiers.Our attack method utilizes seven different perturbations,including Overlay Append,Section Append,and Break Checksum,capitalizing on the ambiguities present in the PE format,as previously employed in evasion attack research.By directly applying the perturbation techniques to PE binaries,our attack method eliminates the need to grapple with the problem-feature space dilemma,a persistent challenge in many evasion attack studies.Being a black-box attack,our method can generate AEs that successfully evade both DL-based and ML-based classifiers.Also,AEs generated by the attack method retain their executability and malicious behavior,eliminating the need for functionality verification.Through thorogh evaluations,we confirmed that the attack method achieves an evasion rate of 65.6%against well-known ML-based malware detectors and can reach a remarkable 99%evasion rate against well-known DL-based malware detectors.Furthermore,our AEs demonstrated the capability to bypass detection by 17%of vendors out of the 64 on VirusTotal(VT).In addition,we propose a defensive approach that utilizes Trend Locality Sensitive Hashing(TLSH)to construct a similarity-based defense model.Through several experiments on the approach,we verified that our defense model can effectively counter AEs generated by the perturbation techniques.In conclusion,our defense model alleviates the limitation of the most promising defense method,adversarial training,

关键词： Malware classification machine learning adversarial examples evasion attack cybersecurity

Stationary Almost Markov ε-Equilibria for Discounted Stochastic Games with Borel Spaces and Unbounded Payoffs

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2024年第4期37卷 1672-1684页

作者： WU Yiting ZHANG Junyu HUANG Song school of Mathematics Sun Yat-Sen University school of software and Microelectronics Peking University

This paper is concerned with nonzero-sum discrete-time stochastic games in Borel state and action spaces under the expected discounted payoff criterion. The payoff function can be unbounded.The transition probability is a convex combination of finite probability measures that are dominated by a probability measure on the state space and depend on the state variable. Under suitable conditions,the authors establish the existence of stationary almost Markov ε-equilibria and give an approximation method via some stochastic games with bounded payoffs. Finally, a production game is introduced to illustrate the applications of the main result, which generalizes the bounded payoff case.

关键词： Almost Markov ε -equilibrium Borel state space expected discounted payoff criterion nonzero-sum stochastic games unbounded payoffs

IoTDQ: An Industrial IoT Data Analysis Library for Apache IoTDB

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Big Data Mining and Analytics 2024年第1期7卷 29-41页

作者： Pengyu Chen Wendi He Wenxuan Ma Xiangdong Huang Chen Wang school of software Tsinghua UniversityBeijing 100084China National Engineering Research Center for Big Data software(NERCBDS) Tsinghua UniversityBeijing 100084China

There is a growing demand for time series data analysis in industry areas.Apache loTDB is a time series database designed for the Internet of Things(loT)with enhanced storage and I/O performance.With User-Defined Functions(UDF)provided,computation for time series can be executed on Apache loTDB directly.To satisfy most of the common requirements in industrial time series analysis,we create a UDF library,loTDQ,on Apache loTDB.This library integrates stream computation functions on data quality analysis,data profiling,anomaly detection,data repairing,etc.loTDQ enables users to conduct a wide range of analyses,such as monitoring,error diagnosis,equipment reliability analysis.It provides a framework for users to examine loT time series with data quality problems.Experiments show that loTDQ keeps the same level of performance compared to mainstream alternatives,and shortens I/O consumption for Apache loTDB users.

关键词： industrial big data data quality data mining and analytics

HTDcr:a job execution framework for high-throughput computing on supercomputers

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第1期67卷 69-85页

作者： Jiazhi JIANG Dan HUANG Hu CHEN Yutong LU Xiangke LIAO school of Computer Science and Engineering Sun Yat-sen University school of software Engineering South China University of Technology

High-throughput computing(HTC) is a computing paradigm that aims to accomplish jobs by easily breaking them into smaller,independent components.However,it requires a large amount of computing power for a long time.Most existing HTC frameworks are job-oriented without support for coscheduling with hardware architecture and task-level execution.Also,most of the frameworks reach a limited scale,and their usability needs further improvement.Herein,we present HTDcr,a job execution framework for the HTC on supercomputers.This study aims to improve the throughput,task dispatching,and usability of the framework.In detail,the throughput optimizations include a sophisticated designed task management system,a hierarchical scheduler,and the co-optimization of the task-scheduling strategy with the application and hardware characteristics.The optimizations for usability include a programable execution workflow,mechanisms for more robust and reliable service qualities,and a fine-grained resource allocation system for the colocation of multiple jobs.According to our evaluations,HTDcr can achieve outstanding scalability and high throughput on large-scale clusters for the HTC workload.We evaluate HTDcr with several microbenchmarks and real-world applications on Tianhe-2 and Sunway TaihuLight to demonstrate its effects on existing design mechanisms.For instance,the task scheduling for two real-world applications integrated with the application and hardware characteristics achieves 1.7× and 1.9× speedups over the basic task-scheduling strategy.

关键词： high-throughput computing supercomputer task scheduling middleware password guessing

MCR-YOLO model for underwater target detection based on multi-color spatial features

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Optoelectronics Letters 2024年第5期20卷 313-320页

作者： LIU Peiyu XING Weiwei MA Yixuan school of software Engineering Beijing Jiaotong UniversityBeijing 100044China

Within the fields of underwater robotics and ocean information processing, computer vision-based underwater target detection is an important area of research. Underwater target detection is made more difficult by a number of problems with underwater imagery, such as low contrast, color distortion, fuzzy texture features, and noise interference, which are caused by the limitations of the unique underwater imaging environment. In order to solve the above challenges, this paper proposes a multi-color space residual you only look once(MCR-YOLO) model for underwater target detection. First, the RGB image is converted into YCb Cr space, and the brightness channel Y is used to extract the non-color features of color-biased images based on improved Res Net50. Then, the output features of three scales are combined between adjacent scales to exchange information. At the same time, the image features integrated with low-frequency information are obtained via the low-frequency feature extraction branch and the three-channel RGB image, and the features from the three scales of the two branches are fused at the corresponding scales. Finally, multi-scale fusion and target detection are accomplished utilizing the path aggregation network(PANet) framework. Experiments on relevant datasets demonstrate that the method can improve feature extraction of critical targets in underwater environments and achieve good detection accuracy.

关键词： underwater image utilizing

维普期刊数据库

Cross-Project software Defect Prediction Based on SMOTE and Deep Canonical Correlation Analysis

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第2期78卷 1687-1711页

作者： Xin Fan Shuqing Zhang Kaisheng Wu Wei Zheng Yu Ge school of software Nanchang Hangkong UniversityNanchang330063China software Testing and Evaluation Center Nanchang Hangkong UniversityNanchang330063China

Cross-Project Defect Prediction(CPDP)is a method that utilizes historical data from other source projects to train predictive models for defect prediction in the target project.However,existing CPDP methods only consider linear correlations between features(indicators)of the source and target projects.These models are not capable of evaluating non-linear correlations between features when they exist,for example,when there are differences in data distributions between the source and target projects.As a result,the performance of such CPDP models is compromised.In this paper,this paper proposes a novel CPDP method based on Synthetic Minority Oversampling Technique(SMOTE)and Deep Canonical Correlation Analysis(DCCA),referred to as S-DCCA.Canonical Correlation Analysis(CCA)is employed to address the issue of non-linear correlations between features of the source and target projects.S-DCCA extends CCA by incorporating the MlpNet model for feature extraction from the dataset.The redundant features are then eliminated by maximizing the correlated feature subset using the CCA loss function.Finally,cross-project defect prediction is achieved through the application of the SMOTE data sampling technique.Area Under Curve(AUC)and F1 scores(F1)are used as evaluation metrics.This paper conducted experiments on 27 projects from four public datasets to validate the proposed method.The results demonstrate that,on average,our method outperforms all baseline approaches by at least 1.2%in AUC and 5.5%in F1 score.This indicates that the proposed method exhibits favorable performance characteristics.

关键词： Cross-project defect prediction deep canonical correlation analysis feature similarity

Incremental Data Stream Classification with Adaptive Multi-Task Multi-View Learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Big Data Mining and Analytics 2024年第1期7卷 87-106页

作者： Jun Wang Maiwang Shi Xiao Zhang Yan Li Yunsheng Yuan Chengei Yang Dongxiao Yu school of Computer Science and Technology Shandong UniversityQingdao 266237China school of software Shandong UniversityJinan 250101China

With the enhancement of data collection capabilities,massive streaming data have been accumulated in numerous application scenarios.Specifically,the issue of classifying data streams based on mobile sensors can be formalized as a multi-task multi-view learning problem with a specific task comprising multiple views with shared features collected from multiple sensors.Existing incremental learning methods are often single-task single-view,which cannot learn shared representations between relevant tasks and views.An adaptive multi-task multi-view incremental learning framework for data stream classification called MTMVIS is proposed to address the above challenges,utilizing the idea of multi-task multi-view learning.Specifically,the attention mechanism is first used to align different sensor data of different views.In addition,MTMVIS uses adaptive Fisher regularization from the perspective of multi-task multi-view learning to overcome catastrophic forgetting in incremental learning.Results reveal that the proposed framework outperforms state-of-the-art methods based on the experiments on two different datasets with other baselines.

关键词： data stream classification mobile sensors multi-task multi-view learning incremental learning