PROBLEM Recent years have witnessed the rapid progress of self-supervised language models (LMs)[1],especially large language models (LLMs)[2].LLMs not only achieved state-of-the-art performance on many natural languag...
PROBLEM Recent years have witnessed the rapid progress of self-supervised language models (LMs)[1],especially large language models (LLMs)[2].LLMs not only achieved state-of-the-art performance on many natural language processing tasks,but also captured widespread attention from the public due to their great potential in a variety of real-world applications (***,search engines,writing assistants,etc.)through providing general-purpose intelligent services.A few of the LLMs are becoming foundation models,an analogy to infrastructure,that empower hundreds of downstream applications.
Cyber Threat Intelligence(CTI)is a valuable resource for cybersecurity defense,but it also poses challenges due to its multi-source and heterogeneous *** personnel may be unable to use CTI effectively to understand th...
详细信息
Cyber Threat Intelligence(CTI)is a valuable resource for cybersecurity defense,but it also poses challenges due to its multi-source and heterogeneous *** personnel may be unable to use CTI effectively to understand the condition and trend of a cyberattack and respond *** address these challenges,we propose a novel approach that consists of three ***,we construct the attack and defense analysis of the cybersecurity ontology(ADACO)model by integrating multiple cybersecurity ***,we develop the threat evolution prediction algorithm(TEPA),which can automatically detect threats at device nodes,correlate and map multisource threat information,and dynamically infer the threat evolution *** leverages knowledge graphs to represent comprehensive threat scenarios and achieves better performance in simulated experiments by combining structural and textual features of ***,we design the intelligent defense decision algorithm(IDDA),which can provide intelligent recommendations for security personnel regarding the most suitable defense *** outperforms the baseline methods in the comparative experiment.
Software trustworthiness is an essential criterion for evaluating software quality. In componentbased software, different components play different roles and different users give different grades of trustworthiness af...
详细信息
Software trustworthiness is an essential criterion for evaluating software quality. In componentbased software, different components play different roles and different users give different grades of trustworthiness after using the software. The two elements will both affect the trustworthiness of software. When the software quality is evaluated comprehensively, it is necessary to consider the weight of component and user feedback. According to different construction of components, the different trustworthiness measurement models are established based on the weight of components and user feedback. Algorithms of these trustworthiness measurement models are designed in order to obtain the corresponding trustworthiness measurement value automatically. The feasibility of these trustworthiness measurement models is demonstrated by a train ticket purchase system.
Machine learning has been massively utilized to construct data-driven solutions for predicting the lifetime of rechargeable batteries in recent years, which project the physical measurements obtained during the early ...
详细信息
Machine learning has been massively utilized to construct data-driven solutions for predicting the lifetime of rechargeable batteries in recent years, which project the physical measurements obtained during the early charging/discharging cycles to the remaining useful lifetime. While most existing techniques train the prediction model through minimizing the prediction error only, the errors associated with the physical measurements can also induce negative impact to the prediction accuracy. Although total-least-squares(TLS) regression has been applied to address this issue, it relies on the unrealistic assumption that the distributions of measurement errors on all input variables are equivalent, and cannot appropriately capture the practical characteristics of battery degradation. In order to tackle this challenge, this work intends to model the variations along different input dimensions, thereby improving the accuracy and robustness of battery lifetime prediction. In specific, we propose an innovative EM-TLS framework that enhances the TLS-based prediction to accommodate dimension-variate errors, while simultaneously investigating the distributions of them using expectation-maximization(EM). Experiments have been conducted to validate the proposed method based on the data of commercial Lithium-Ion batteries, where it reduces the prediction error by up to 29.9 % compared with conventional TLS. This demonstrates the immense potential of the proposed method for advancing the R&D of rechargeable batteries.
Due to the security and scalability features of hybrid cloud architecture,it can bettermeet the diverse requirements of users for cloud *** a reasonable resource allocation solution is the key to adequately utilize th...
详细信息
Due to the security and scalability features of hybrid cloud architecture,it can bettermeet the diverse requirements of users for cloud *** a reasonable resource allocation solution is the key to adequately utilize the hybrid ***,most previous studies have not comprehensively optimized the performance of hybrid cloud task scheduling,even ignoring the conflicts between its security privacy features and other *** on the above problems,a many-objective hybrid cloud task scheduling optimization model(HCTSO)is constructed combining risk rate,resource utilization,total cost,and task completion ***,an opposition-based learning knee point-driven many-objective evolutionary algorithm(OBL-KnEA)is proposed to improve the performance of model *** algorithm uses opposition-based learning to generate initial populations for faster ***,a perturbation-based multipoint crossover operator and a dynamic range mutation operator are designed to extend the search *** comparing the experiments with other excellent algorithms on HCTSO,OBL-KnEA achieves excellent results in terms of evaluation metrics,initial populations,and model optimization effects.
Diabetic Retinopathy (DR) is a common and significant complication in patients with diabetes, and severely affecting their quality of life. Image segmentation plays a crucial role in the early diagnosis and treatment ...
详细信息
In recent years,the demand for real-time data processing has been increasing,and various stream processing systems have *** the amount of data input to the stream processing system fluctuates,the computing resources r...
详细信息
In recent years,the demand for real-time data processing has been increasing,and various stream processing systems have *** the amount of data input to the stream processing system fluctuates,the computing resources required by the stream processing job will also *** resources used by stream processing jobs need to be adjusted according to load changes,avoiding the waste of computing *** present,existing works adjust stream processing jobs based on the assumption that there is a linear relationship between the operator parallelism and operator resource consumption(e.g.,throughput),which makes a significant deviation when the operator parallelism *** paper proposes a nonlinear model to represent operator *** divide the operator performance into three stages,the Non-competition stage,the Non-full competition stage,and the Full competition *** our proposed performance model,given the parallelism of the operator,we can accurately predict the CPU utilization and operator *** with actual experiments,the prediction error of our model is below 5%.We also propose a quick accurate auto-scaling(QAAS)method that uses the operator performance model to implement the auto-scaling of the operator parallelism of the Flink *** to previous work,QAAS is able to maintain stable job performance under load changes,minimizing the number of job adjustments and reducing data backlogs by 50%.
Partial-label learning(PLL) is a typical problem of weakly supervised learning, where each training instance is annotated with a set of candidate labels. Self-training PLL models achieve state-of-the-art performance b...
详细信息
Partial-label learning(PLL) is a typical problem of weakly supervised learning, where each training instance is annotated with a set of candidate labels. Self-training PLL models achieve state-of-the-art performance but suffer from error accumulation problems caused by mistakenly disambiguated instances. Although co-training can alleviate this issue by training two networks simultaneously and allowing them to interact with each other, most existing co-training methods train two structurally identical networks with the same task, i.e., are symmetric, rendering it insufficient for them to correct each other due to their similar limitations. Therefore, in this paper, we propose an asymmetric dual-task co-training PLL model called AsyCo,which forces its two networks, i.e., a disambiguation network and an auxiliary network, to learn from different views explicitly by optimizing distinct tasks. Specifically, the disambiguation network is trained with a self-training PLL task to learn label confidence, while the auxiliary network is trained in a supervised learning paradigm to learn from the noisy pairwise similarity labels that are constructed according to the learned label confidence. Finally, the error accumulation problem is mitigated via information distillation and confidence refinement. Extensive experiments on both uniform and instance-dependent partially labeled datasets demonstrate the effectiveness of AsyCo.
In the realm of underwater robotics,optical imaging plays a pivotal role in many scientific *** to the effects of absorption and scattering,images captured in turbid water are severely ***,enhancing the quality of und...
详细信息
In the realm of underwater robotics,optical imaging plays a pivotal role in many scientific *** to the effects of absorption and scattering,images captured in turbid water are severely ***,enhancing the quality of underwater optical images stands paramount in ensuring the continued advancement and efficacy of underwater robots across its multifarious applications.
Author Profiling (AP) is a subsection of digital forensics that focuses on the detection of the author’s personalinformation, such as age, gender, occupation, and education, based on various linguistic features, e.g....
详细信息
Author Profiling (AP) is a subsection of digital forensics that focuses on the detection of the author’s personalinformation, such as age, gender, occupation, and education, based on various linguistic features, e.g., stylistic,semantic, and syntactic. The importance of AP lies in various fields, including forensics, security, medicine, andmarketing. In previous studies, many works have been done using different languages, e.g., English, Arabic, French,***, the research on RomanUrdu is not up to the ***, this study focuses on detecting the author’sage and gender based on Roman Urdu text messages. The dataset used in this study is Fire’18-MaponSMS. Thisstudy proposed an ensemble model based on AdaBoostM1 and Random Forest (AMBRF) for AP using multiplelinguistic features that are stylistic, character-based, word-based, and sentence-based. The proposed model iscontrasted with several of the well-known models fromthe literature, including J48-Decision Tree (J48),Na飗e Bays(NB), K Nearest Neighbor (KNN), and Composite Hypercube on Random Projection (CHIRP), NB-Updatable,RF, and AdaboostM1. The overall outcome shows the better performance of the proposed AdaboostM1 withRandom Forest (ABMRF) with an accuracy of 54.2857% for age prediction and 71.1429% for gender predictioncalculated on stylistic features. Regarding word-based features, age and gender were considered in 50.5714% and60%, respectively. On the other hand, KNN and CHIRP show the weakest performance using all the linguisticfeatures for age and gender prediction.
暂无评论