检索结果-内蒙古大学图书馆

LLM4TAP: LLM-Enhanced TAP Rule Recommendation

IEEE Internet of Things Journal 2025年第10期12卷 13157-13169页

作者： Wu, Gang Hu, Liang Hu, Yuxiao Xiong, Xingbo Wang, Feng Jilin University College of Computer Science and Technology Changchun130012 China Changchun University College of Computer Science and Technology Changchun130022 China

Trigger-action programming (TAP) is an Internet of Things (IoT) paradigm that enables nonprofessional end-users to automate smart devices by formulating rules, such as "IF you leave home, THEN turn off lights." As the number of possible rules increases, manually browsing these rules becomes increasingly time-consuming for users. Recently, graph-based recommendation systems have shown promise in automatically suggesting rules, yet they face two issues. First, these studies struggle to identify and differentiate users’ demands (e.g., turning off lights) and intentions (e.g., energy saving). Second, they overlook the issue of sparse user-rule interactions. In this article, we propose LLM4TAP, a large language model (LLM) enhanced TAP rule recommendation framework, to address these issues. Prior to LLM4TAP, a user-rule graph is constructed to represent the interactions between users and rules. Within LLM4TAP, singular value decomposition is first employed to generate an augmented graph, strengthening global structural relationships between users and rules. Next, the reasoning capabilities of LLMs are utilized to infer users’ demands and intentions from the textual descriptions of rules and user-rule interactions, producing representations of these inferred demands and intentions. Finally, a dual representation alignment method is introduced, integrating user demands and intentions derived from LLMs with the global structural information from the augmentation graph within a contrastive learning framework to enhance representation performance. Extensive experiments demonstrate the effectiveness of LLM4TAP, achieving the maximum improvements of 8.96% and 4.72% over the strongest compared methods on the IFTTT and Wyze datasets, respectively. © 2014 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

PBCounter:weighted model counting on pseudo-boolean formulas

引用

Frontiers of computer science 2025年第3期19卷 55-63页

作者： Yong LAI Zhenghang XU Minghao YIN College of Computer Science and Technology Jilin UniversityChangchun 130012China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin UniversityChangchun 130012China School of Computer Science and Information Technology Northeast Normal UniversityChangchun 130017China

In Weighted Model Counting(WMC),we assign weights to literals and compute the sum of the weights of the models of a given propositional formula where the weight of an assignment is the product of the weights of its *** current WMC solvers work on Conjunctive Normal Form(CNF)***,CNF is not a natural representation for human-being in many *** by the stronger expressive power of Pseudo-Boolean(PB)formulas than CNF,we propose to perform WMC on PB *** on a recent dynamic programming algorithm framework called ADDMC for WMC,we implement a weighted PB counting tool *** compare PBCounter with the state-of-the-art weighted model counters SharpSAT-TD,ExactMC,D4,and ADDMC,where the latter tools work on CNF with encoding methods that convert PB constraints into a CNF *** experiments on three domains of benchmarks show that PBCounter is superior to the model counters on CNF formulas.

关键词： weighted model counting pseudo-boolean constraint algebraic decision diagrams preprocessing techniques

来源：评论

学校读者我要写书评

暂无评论

ConvGRU: A Lightweight Intrusion Detection System for Vehicle Networks Based on Shallow CNN and GRU

引用

IEEE Access 2025年 13卷 73297-73318页

作者： Wang, Shaoqiang Cheng, Jiahui Wang, Yizhe Li, Shutong Kang, Lei Dai, Yinfei Changchun University School of Computer Science and Technology Changchun130022 China Jilin University College of Computer Science and Technology Changchun130012 China

The rapid proliferation of connected vehicles has significantly expanded the attack surface of the Internet of Vehicles (IoV), introducing severe security risks. In such resource-constrained environments, developing lightweight solutions is crucial to ensuring real-time detection and efficient deployment. To address these challenges, this study proposes ConvGRU, a lightweight vehicular network intrusion detection model that integrates a shallow Convolutional Neural Network (CNN) with a Gated Recurrent Unit (GRU). By employing optimizations such as small convolutional kernels and depthwise separable convolutions, the model significantly reduces the number of parameters and computational overhead, making it well-suited for resource-limited IoV environments. The shallow CNN effectively captures spatial features, while the GRU extracts temporal dependencies, enhancing the model’s generalization ability. ConvGRU achieves an accuracy, precision, recall, and F1-score exceeding 0.99 on the HCRL-Car-hacking, OTIDS, and CICIDS-2018 datasets, with only 112.55K parameters and a memory footprint of merely 0.43 MB. Experimental results demonstrate that this intrusion detection solution substantially improves malicious traffic detection accuracy while ensuring efficient operation in resource-constrained vehicular environments. © 2013 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Fluorinated poly(p-triphenylene isatin)anion exchange membranes based on hydrophilic hydroxyl side chain modulation for fuel cells

引用

Journal of Energy Chemistry 2025年第1期100卷 702-709页

作者： Yiman Gu Yanchao Zhang Zhanyu Li Yijia Lei Baozeng Sun Xiaoyu Yu Zhe Wang College of Chemistry and Life Science Changchun University of TechnologyChangchun 130012JilinChina College of Chemical Engineering Changchun University of TechnologyChangchun 130012JilinChina School of Materials Science and Engineering Changchun University of TechnologyChangchun 130012JilinChina Key Laboratory of Advanced Functional Polymer Membrane Materials of Jilin Province Changchun 130012JilinChina

The development of alkaline fuel cells is moving forward at an accelerated pace,and the application of ether-free bonded polymers to anion exchange membranes(AEMs)has been widely ***,the question of the“trade-off”between AEM ionic conductivity and dimensional stability remains *** strategy of inducing microphase separation to improve the performance of AEM has attracted much attention recently,but the design of optimal molecular structures is still being ***,this work introduced different ratios of 3-bromo-1,1,1-trifluoroacetone(x=40,50,and 60)into the main chain of poly(p-terphenylene isatin).Because fluorinated groups have excellent hydrophobicity,hydrophilic hydroxyl-containing side chains are introduced to jointly adjust the formation of phase separation *** results show that PTI-PTF_(50)-NOH AEM with the appropriate fluorinated group ratio has the best ionic conductivity and alkali stability under the combined effect of *** has an ionic conductivity of 133.83 mS cm^(-1)at 80°*** addition,the OH-conductivity remains at 89%of the initial value at 80°C and 3 M KOH for 1056 h of *** cell polarization curve based on PTI-PTF_(50)-NOH shows a power density of 734.76 mW cm^(-2)at a current density of 1807.7 mA cm^(-2).

关键词： Anion exchange membranes Poly(p-terphenylene isatin) Hydrophilic-hydrophobic phase separation Fluorinated group

来源：评论

学校读者我要写书评

暂无评论

Container cluster placement in edge computing based on reinforcement learning incorporating graph convolutional networks scheme

引用

Digital Communications and Networks 2025年第1期11卷 60-70页

作者： Zhuo Chen Bowen Zhu Chuan Zhou College of Computer Science and Engineering Chongqing University of TechnologyChongqing400054China

Container-based virtualization technology has been more widely used in edge computing environments recently due to its advantages of lighter resource occupation, faster startup capability, and better resource utilization efficiency. To meet the diverse needs of tasks, it usually needs to instantiate multiple network functions in the form of containers interconnect various generated containers to build a Container Cluster(CC). Then CCs will be deployed on edge service nodes with relatively limited resources. However, the increasingly complex and timevarying nature of tasks brings great challenges to optimal placement of CC. This paper regards the charges for various resources occupied by providing services as revenue, the service efficiency and energy consumption as cost, thus formulates a Mixed Integer Programming(MIP) model to describe the optimal placement of CC on edge service nodes. Furthermore, an Actor-Critic based Deep Reinforcement Learning(DRL) incorporating Graph Convolutional Networks(GCN) framework named as RL-GCN is proposed to solve the optimization problem. The framework obtains an optimal placement strategy through self-learning according to the requirements and objectives of the placement of CC. Particularly, through the introduction of GCN, the features of the association relationship between multiple containers in CCs can be effectively extracted to improve the quality of *** experiment results show that under different scales of service nodes and task requests, the proposed method can obtain the improved system performance in terms of placement error ratio, time efficiency of solution output and cumulative system revenue compared with other representative baseline methods.

关键词： Edge computing Network virtualization Container cluster Deep reinforcement learning Graph convolutional network

来源：评论

学校读者我要写书评

暂无评论

Multimodal Fusion for Android Malware Detection Based on Large Pre-Trained Models

引用

IEEE Transactions on Software engineering 2025年第5期51卷 1569-1590页

作者： Li, Xun Liu, Lei Liu, Yuzhou Zhao, Yu Zhang, Peng Liu, Huaxiao Jilin University College of Computer Science and Technology Changchun130012 China Northeast Electric Power University School of Computer Science Jilin132012 China Jilin University College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun130012 China

Malware detection is a critical issue in software engineering as it directly threatens user information security. Existing approaches often focus on individual modality (either source code or binary code) for the detection, but it ignores to effectively exploit the complementary information between them. This limits the detection performance, especially in complex and evasive malware scenarios. In this paper, we take Android applications written in Java as objects, and provide a novel fine-grained multimodal fusion method with large pre-trained models to combine the features from source and binary codes for the malware detection. For the source code modality, we employ the graphical user interface (GUI) as a framework to segment the source code into snippets, and use a pre-trained programming language model to extract feature representations. For the binary code modality, we convert binary code into grayscale images and fine-tune a pre-trained vision model to extract features indirectly. We then implement cross-modal attention and devise a contrastive loss to align features across modalities, supplementing this with supervised classification loss to refine the multimodal fusion process specifically for malware detection. Our experiments, conducted using the Data-MD and Data-MC benchmarks, demonstrate that our approach achieves a precision of 0.977 and a recall of 0.984 in detecting malware. This underscores the advantages of using large pre-trained models for feature representation and the fusion of information across different modalities for effective malware detection. © 1976-2012 IEEE.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

Research on Fault Detection of Traction System Based on Multi-task Learning

Research on Fault Detection of Traction System Based on Mult...

引用

International Conference on Artificial Intelligence and Autonomous Transportation, AIAT 2024

作者： Guo, Xingang Rao, Guibin Cheng, Chao College of Computer Science and Engineering Changchun University of Technology Changchun130012 China

ISBN: (纸本)9789819639601

Under the background of high-speed train production performance degradation, aiming at the problem of insufficient sensitivity of high-speed train traction system for early fault detection, we propose an early fault detection method based on multi-task learning. By using the multi-task network structure, this method obtains the probability density function of the data with the help of kernel density estimation and detects the fault from the data and the probability density function value. By comparing and analyzing the detection results of two fault detection indexes, Hotelling’s T2 statistic and Kullback-Leibler divergence statistic, the identifiability of fault indexes is enhanced. In addition, the adopted multi-task learning network structure enables the networks between two different tasks to share information effectively so that the performance of the overall network for fault detection is improved. Finally, the traction drive control system platform developed by Central South university is used to verify the effectiveness of the proposed method. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Railroads

来源：评论

学校读者我要写书评

暂无评论

Target Detection-Oriented RGCN Inference Enhancement Method

引用

computers, Materials & Continua 2025年第4期83卷 1219-1237页

作者： Lijuan Zhang Xiaoyu Wang Songtao Zhang Yutong Jiang Dongming Li Weichen Sun School of Internet of Things Engineering Wuxi UniversityWuxi214105China College of Computer Science and Engineering Changchun University of TechnologyChangchun130012China Computer Science and Technology at Guohao Academy Tongji UniversityShanghai200092China China North Vehicle Research Institute Beijing100072China

In this paper,a reasoning enhancement method based on RGCN(Relational Graph Convolutional Network)is proposed to improve the detection capability of UAV(Unmanned Aerial Vehicle)on fast-moving military targets in urban battlefield *** combining military images with the publicly available VisDrone2019 dataset,a new dataset called VisMilitary was built and multiple YOLO(You Only Look Once)models were tested on *** to the low confidence problem caused by fuzzy targets,the performance of traditional YOLO models on real battlefield images decreases ***,we propose an improved RGCN inference model,which improves the performance of the model in complex environments by optimizing the data processing and graph network *** results show that the proposed method achieves an improvement of 0.4%to 1.7%on mAP@0.50,which proves the effectiveness of the model in military target *** research of this paper provides a new technical path for UAV target detection in urban battlefield,and provides important enlightenment for the application of deep learning in military field.

关键词： RGCN target detection urban battlefield YOLO visual reasoning

来源：评论

学校读者我要写书评

暂无评论

Face Reconstruction-Based Generalized Deepfake Detection Model with Residual Outlook Attention

引用

ACM Transactions on Multimedia Computing, Communications and Applications 2025年第4期21卷 1-19页

作者： Shi, Zenan Liu, Wenyu Chen, Haipeng College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

With the continuous development of deep counterfeiting technology, the information security in our daily life is under serious threat. While existing face forgery detection methods exhibit impressive accuracy when applied to datasets such as FaceForensics++ and Celeb-DF, they falter significantly when confronted with out-of-domain scenarios. This causes specialization of learned representations to known forgery patterns presented in the training set, rendering it difficult to detect forgeries with unknown patterns. To address this challenge, we propose a novel end-to-end Face Reconstruction-Based Generalized Deepfake Detection (FRG2D) model with Residual Outlook Attention (ROA), which emphasizes the robust visual representations of genuine faces and discerns the subtle differences between authentic and manipulated facial images. Our methodology entails reconstructing authentic face images using an encoder-decoder architecture based on U-net, facilitating a deeper understanding of disparities between genuine and manipulated facial images. Furthermore, we integrate the convolutional block attention module (CBAM) and channel attention block (CAB) to selectively focus the network's attention on salient features within real face images. Furthermore, we employ ROA to guide the network's focus towards precise features within manipulated facial images. Simultaneously, the computed reconstruction differences obtained through ROA serves as the ultimate representation fed into the classifier for face forgery detection. Both the reconstruction and classification learning processes are optimized end-to-end. Through extensive experimentation, our model demonstrated a substantial improvement in deepfake detection across unknown domains, while maintaining a high accuracy within the known domain. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

TRE-DSP: A traceable and revocable CP-ABE based data sharing scheme for IoV with partially hidden policy

引用

Digital Communications and Networks 2025年第2期11卷 455-464页

作者： Yousheng Zhou Rundong Peng Yuanni Liu Pandi Vijayakumar Brij Gupta College of Computer Science and Technology Chongqing University of Posts and Telecommunications College of Cyber Security and Information Law Chongqing University of Posts and Telecommunications Department of Computer Science and Engineering University College of Engineering Department of Computer Engineering National Institute of Technology Kurukshetra

With the popularity of the Internet of Vehicles(IoV), a large amount of data is being generated every day. How to securely share data between the IoV operator and various value-added service providers becomes one of the critical issues. Due to its flexible and efficient fine-grained access control feature, Ciphertext-Policy Attribute-Based Encryption(CP-ABE) is suitable for data sharing in IoV. However, there are many flaws in most existing CP-ABE schemes, such as attribute privacy leakage and key misuse. This paper proposes a Traceable and Revocable CP-ABE-based Data Sharing with Partially hidden policy for IoV(TRE-DSP). A partially hidden access structure is adopted to hide sensitive user attribute values, and attribute categories are sent along with the ciphertext to effectively avoid privacy exposure. In addition, key tracking and malicious user revocation are introduced with broadcast encryption to prevent key misuse. Since the main computation task is outsourced to the cloud, the burden of the user side is relatively low. Analysis of security and performance demonstrates that TRE-DSP is more secure and practical for data sharing in IoV.

关键词： Privacy-preserving Attribute-based encryption Partially hidden policy Traceability User revocation Internet of vehicles

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：