检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Mangi, Fawad Ali Su, Guoxin Zhang, Minjie Liu, Li School of Computing and Information Technology University of Wollongong Wollongong2522 Australia Department of Computer Systems Engineering Mehran University of Engineering and Technology Sindh Jamshoro76062 Pakistan School of Big Data and Software Engineering Chongqing University Chongqing400030 China

Process mining is a rapidly growing research field that uses data science techniques to analyse business processes and extract insights about their performance, efficiency, and compliance. The process mining approach begins with process discovery, which involves creating process models based on event logs;and depending on the type of models discovered, the correctness of models needs to be guaranteed. Verification is paramount to ensure the accuracy and reliability of discovered process models in process mining, the current research lacks to model the stochastic nature of process mining models. This paper introduces a novel technique for verification of process mining models, leveraging continuous time Markov chain (CTMC) model of probabilistic model checking technique. The proposed method aims to address the inherent uncertainties and dynamic nature of real-world processes, providing a more robust and comprehensive verification framework compared to traditional methods. The technique employs CTMC to represent the stochastic behavior of processes, allowing for the incorporation of time and probability in the analysis of process models. This approach enables the evaluation of process models under various conditions and scenarios, considering the probabilistic aspects and temporal characteristics inherent in business processes. The paper presents a detailed methodology of the proposed technique, illustrating its application through a case study of loan application process performed in a financial institution, and empirical evaluations. © 2024, The Authors. All rights reserved.

关键词： Model checking

来源：评论

学校读者我要写书评

暂无评论

Classic4Children: Adapting Chinese Literary Classics for Children with Large Language Model

arXiv

引用

arXiv 2025年

作者： Chen, Jiali Hei, Xusen Xue, Yuqi Wu, Zihan Xie, Jiayuan Cai, Yi Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China School of Software Engineering South China University of Technology China The Hong Kong Polytechnic University Hong Kong

Chinese literary classics hold significant cultural and educational value, offering deep insights into morality, history, and human nature. These works often include classical Chinese and complex narratives, making them difficult for children to read. To bridge this gap, we introduce a child-friendly literary adaptation (CLA) task to adapt the Chinese literary classic into engaging and accessible text for children. However, recent large language models (LLMs) overlook children’s reading preferences (i.e., vivid character portrayals, concise narrative structures, and appropriate readability), which poses challenges in CLA. In this paper, we propose a method called InstructChild, which augments the LLM with these preferences for adaptation. Specifically, we first obtain the characters’ personalities and narrative structure as additional information for fine-grained instruction tuning. Then, we devise a readability metric as the reward to align the LLM with the children’s reading level. Finally, a lookahead decoding strategy is applied to improve the readability of the generated text during inference. To support the evaluation of CLA task, we construct the Classic4Children dataset, which comprises both the original and child-friendly versions of the Four Great Classical Novels of Chinese literature. Experimental results show that our InstructChild significantly improves automatic and human evaluation performance. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CEGRL-TKGR: A Causal Enhanced Graph Representation Learning Framework for Temporal Knowledge Graph Reasoning

arXiv

引用

arXiv 2024年

作者： Sun, Jinze Sheng, Yongpan He, Lirong Qin, Yongbin Liu, Ming Jia, Tao College of Computer and Information Science Southwest University Chongqing400715 China School of Big Data & Software Engineering Chongqing University Chongqing401331 China School of Information Science and Engineering Chongqing Jiaotong University Chongqing400074 China College of Computer Science and Technology The State Key Laboratory of Public Big Data Guizhou University China Deakin University VIC3125 Australia

Temporal knowledge graph reasoning (TKGR) is increasingly gaining attention for its ability to extrapolate new events from historical data, thereby enriching the inherently incomplete temporal knowledge graphs. Existing graph-based representation learning frameworks have made significant strides in developing evolving representations for both entities and relational embeddings. Despite these achievements, there’s a notable tendency in these models to inadvertently learn biased data representations and mine spurious correlations, consequently failing to discern the causal relationships between events. This often leads to incorrect predictions based on these false correlations. To address this, we propose an innovative Causal Enhanced Graph Representation Learning framework for TKGR (named CEGRL-TKGR). This framework introduces causal structures in graph-based representation learning to unveil the essential causal relationships between events, ultimately enhancing the performance of the TKGR task. Specifically, we first disentangle the evolutionary representations of entities and relations in a temporal knowledge graph sequence into two distinct components, namely causal representations and confounding representations. Then, drawing on causal intervention theory, we advocate the utilization of causal representations for predictions, aiming to mitigate the effects of erroneous correlations caused by confounding features, thus achieving more robust and accurate predictions. Finally, extensive experimental results on six benchmark datasets demonstrate the superior performance of our model in the link prediction task. © 2024, CC BY.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

As Pseudo-label Free As Possible: Leveraging Adaptive Feature Generation for Sparsely Annotated Object Detection 39

As Pseudo-label Free As Possible: Leveraging Adaptive Featur...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yao, Shuilian Liu, Yu Jia, Qi Chen, Sihong Zhuo, Wei School of Software Technology DUT-RU International School of Information Science & Engineering Dalian University of Technology Dalian China AILab Tencent Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

ISBN: (纸本)157735897X

Compared to fully supervised object detection, training with sparse annotations typically leads to a decline in performance due to insufficient feature diversity. Existing sparsely annotated object detection (SAOD) methods often rely on pseudo-labeling strategies, but these pseudo-labels tend to introduce noise under extreme sparsity. To simultaneously avoid the impact of pseudo-label noise and enhance feature diversity, we propose a novel Adaptive Feature Generation (AdaptFG) model that generates features based on class names. This model integrates a pre-trained CLIP into a VAE-based feature generator, with its core innovation being an Adaptor that adaptively maps CLIP semantic embeddings to the object detector domain. Additionally, we introduce inter-class relationship reasoning in detector, which effectively mitigates misclassifications stemming from similar features. Extensive experimental results demonstrate that AdaptFG consistently outperforms state-of-the-art SAOD methods on the PASCAL VOC and MS COCO benchmarks. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Symmetry Classification of Partial Differential Equations Based on Wu's Method

引用

Journal of Donghua University(English Edition) 2021年第2期38卷 187-192页

作者： TIAN Yi WAN Jianxiong College of Data Science and Application Inner Mongolia University of TechnologyHohhot 010080China Inner Mongolia Autonomous Region Engineering&Technology Research Center of Big Data Based Software Service Hohhot 010080China

Lie algorithm combined with differential form Wu's method is used to complete the symmetry classification of partial differential equations(PDEs)containing arbitrary *** process can be reduced to solve a large system of determining equations,which seems rather difficult to solve,then the differential form Wu's method is used to decompose the determining equations into a series of equations,which are easy to *** illustrate the usefulness of this method,we apply it to some test problems,and the results show the performance of the present work.

关键词： Lie algorithm differential form Wu's method determining equation symmetry classification partial differential equation(PDE)

来源：评论

学校读者我要写书评

暂无评论

Development of a blood pressure estimation hybrid deep learning system for wearable devices based on photoplethysmography

引用

Transactions of the Korean Institute of Electrical Engineers 2021年第8期70卷 1208-1214页

作者： Jeong, Seungmin Kim, Young Jo, Eun Hye Min, Se Dong Dept. of Software Convergence Soonchunhyang University Korea Republic of BK21 FOUR Well-Life Big Data Institute Soonchunhyang University Korea Republic of Dept. of Medical IT Engineering Soonchunhyang University Korea Republic of

In this work, we developed a PPG-based blood pressure estimation hybrid deep learning model built into wearable devices and used by hypertension patients to monitor blood pressure in real-time in their daily lives. The model is a deep-learning model that combines data preprocessing, Autoencoder deep learning model for feature extraction, and RAN regression model developed by this research team. We conducted experiments to compare the blood pressure prediction performance of the proposed model with other deep learning models and find out how the objective blood pressure prediction performance is. We conducted experiments on an open dataset with the vital signs of 32 subjects. After models trained on 24 subjects' data and are tested on eight other people's data, we could see that using deep-learning regression models combined with an Autoencoder (hybrid deep-learning) performs better than using a deep learning model alone, and RAN accurately predicts blood pressure than the comparable deep-learning models. The study found that the average error for actual and predicted blood pressure in the proposed hybrid deep-learning models was 4.67 mmHg, and the standard deviation of error was 6.37 mmHg. It satisfies the accuracy criteria presented by the Korean National Institute of Food and Drug Safety Evaluation. © 2021 Korean Institute of Electrical Engineers. All rights reserved.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Differential Game Approach for Modelling Attack and Defense Strategies in Distributed Denial-of-Service Attacks

SSRN

引用

SSRN 2024年

作者： Zhang, Chunming Luo, Fengji Bi, Jichao the School of Biomedical Engineering Guangdong Medical University Dongguan523808 China the School of Civil Engineering The University of Sydney NSW2006 Australia the Faculty of Engineering The University of Sydney NSW2006 Australia the School of Big Data and Software Engineering Chongqing University Chongqing China

Distributed Denial-of-Service (DDoS) attack is a cyberattack that increasingly threats modern communication networks. In a typical DDoS attack and defense process, the attacker aims at maximizing the attack success while minimizing the associated cost, while the defender aims to exhibit the most effective defense at minimum defense cost. This paper proposes a differential game approach to address this gaming interaction between the attacker and defender in a DDoS attack process. In the first part of the paper, a dynamic system is established to model the evolution of communication networks with complex topologies in a DDoS attack event. With this approach, the attack threshold and stability of the network are analytically described. The proposed differential game model is capable of depicting the DDoS attack process (with the interactions between attacker and defender) and is used to establish the game equilibrium that depicts the optimal attack and defense strategies for both attacker and defender. Extensive experiments are conducted on 3 types of benchmark networks to validate the effectiveness of the proposed model. © 2024, The Authors. All rights reserved.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

DBSSL: A Scheme to Detect Backdoor Attacks in Self-Supervised Learning Models

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Huang, Yuxian Yang, Geng Yuan, Dong Yu, Shui Nanjing University of Posts and Telecommunication College of Computer Science and Software China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing China University of Sydney School of Electrical and Information Engineering Australia University of Technology Sydney School of Computer Science Australia

Recently, self-supervised learning has garnered significant attention for its ability to extract high-quality features from unlabeled data. However, existing research indicates that backdoor attacks can pose significant threats to self-supervised learning. Additionally, due to the substantial training overhead, traditional backdoor detection methods in supervised learning, such as meta-learning, are not well-suited for self-supervised learning. Current backdoor detection methods for self-supervised learning can only defend against backdoor attacks triggered by patch. To address this challenge, we proposes DBSSL, a scheme that can efficiently detect backdoor attacks in self-supervised learning models. In DBSSL, we connect backdoor attacks with adversarial attacks and use adversarial perturbations for detection. Specifically, we first conduct targeted adversarial attacks on the samples, classifying them into different classes. Then, we employ the Z-Score method to analyze these adversarial perturbations. If outliers are present, we can infer that the self-supervised learning model has been backdoored. Unlike previous works, our scheme is better suited for downstream users with constrained computation resources and exhibits excellent detection capabilities for backdoor attacks caused by patch -type or global triggers. Abundant theoretical analysis has demonstrated the feasibility of our scheme. Moreover, extensive experiments show that our method performs well in detecting prevalent backdoor attacks in self-supervised learning, achieving detection accuracy exceeding 95%. © 2004-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Research on Classification Label Denoising Algorithm Based on Granular Ball 7

Research on Classification Label Denoising Algorithm Based o...

引用

7th International Conference on Cloud Computing and big data Analytics, ICCCBDA 2022

作者： Kong, Weiyu Wu, Yanmin Qi, Jinli Chen, Yanyi Chongqing Key Lab. of Comp. Sci. and Technology Chongqing University of Posts and Telecommunications ChongQing China ChongQing College of Electronic Engineering Department of Artificial Intelligence and Big Data ChongQing China Chongqing University of Posts and Telecommunications Department of Software Engineering ChongQing China

ISBN: (纸本)9781665487115

This paper presents a granular ball denoising method (GBD) which can effectively improve the accuracy and robustness of classification algorithm. GBD method first uses the self-Adaptive hypersphere to cover the data space, then eliminates the data not contained in the hypersphere and the noise data in the sphere, and finally uses only the hypersphere data for training, so as to reduce the sample data and improve the data quality. Experiments show that using the data obtained by this method for training can greatly improve the accuracy of the classification algorithm. In addition, because the hypersphere has good adaptive ability, GBD also has excellent robustness. The experiment shows that GBD sampling data training can still get good results after adding noise to the data set. Therefore, GBD is an efficient and robust denoising method. © 2022 IEEE.

关键词： Training Cloud computing data integrity Noise reduction big data Robustness Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

DarkSAM: fooling segment anything model to segment nothing 24

DarkSAM: fooling segment anything model to segment nothing

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Ziqi Zhou Yufei Song Minghui Li Shengshan Hu Xianlong Wang Leo Yu Zhang Dezhong Yao Hai Jin National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Cluster and Grid Computing Lab and School of Computer Science and Technology Huazhong University of Science and Technology School of Cyber Science and Engineering Huazhong University of Science and Technology School of Software Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Hubei Engineering Research Center on Big Data Security and Hubei Key Laboratory of Distributed System Security and School of Cyber Science and Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University

ISBN: (纸本)9798331314385

Segment Anything Model (SAM) has recently gained much attention for its outstanding generalization to unseen data and tasks. Despite its promising prospect, the vulnerabilities of SAM, especially to universal adversarial perturbation (UAP) have not been thoroughly investigated yet. In this paper, we propose DarkSAM, the first prompt-free universal attack framework against SAM, including a semantic decoupling-based spatial attack and a texture distortion-based frequency attack. We first divide the output of SAM into foreground and background. Then, we design a shadow target strategy to obtain the semantic blueprint of the image as the attack target. DarkSAM is dedicated to fooling SAM by extracting and destroying crucial object features from images in both spatial and frequency domains. In the spatial domain, we disrupt the semantics of both the foreground and background in the image to confuse SAM. In the frequency domain, we further enhance the attack effectiveness by distorting the high-frequency components (i.e., texture information) of the image. Consequently, with a single UAP, DarkSAM renders SAM incapable of segmenting objects across diverse images with varying prompts. Experimental results on four datasets for SAM and its two variant models demonstrate the powerful attack capability and transferability of DarkSAM. Our codes are available at: https://***/CGCL-codes/DarkSAM.

关键词：

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：