检索结果-内蒙古大学图书馆

Large-Scale Traffic Flow Forecast with Lightweight LLM in Edge Intelligence

IEEE Internet of Things Magazine 2025年第1期8卷 12-18页

作者： Rong, Yi Mao, Yingchi He, Xiaoming Chen, Mingkai College of Computer and Software Hohai University China College of Internet of Things Nanjing University of Posts and Telecommunications China Nanjing University of Posts and Telecommunications Laboratory of Broadband Wireless Communication and Sensor Network Technology China

Large-scale traffic flow forecasting affiliated with the time is valuable for the management in Intelligent Transportation Systems (ITS). Recently, Large Language Models (LLMs) have shown the prominence on this issue. Unfortunately, the existing LLMs cannot forecast the entire road network, including two problems, i.e., (1) training the large-scale data generated by a road network on the central cloud can impose computational pressure. (2) LLMs fail to capture the spatiotemporal correlations in the road network. To overcome the challenges, we propose a novel architecture named Light-weight Spatio-temporal Generative Large Language Model on Edges (LSGLLM-E). Specifically, we first decompose the entire large-scale road network into several subparts, and deploy the Rode-side Unit (RSU) as an edge on each subpart, thus avoiding the computational pressure on the central cloud. In addition, we design an LLM-based method named Light-weight Spatio-temporal Generative Large Language Model (LSGLLM) to extract the spatiotemporal correlations, which compensates for the lack of spatiotemporal features. Finally, the experimental results illustrate that the LSGLLM-E is superior to some advanced baselines in terms of the accuracy and efficiency of the prediction. © 2025 IEEE.

关键词： Roads Cloud computing Correlation Training Predictive models Time series analysis Forecasting Edge computing Large language models Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Cross-graph Knowledge Exchange for Personalized Response Generation in Dialogue Systems

引用

IEEE Internet of Things Journal 2025年第10期12卷 13769-13789页

作者： Dong, Yuezhou Qin, Ke Ke, Pei Liang, Shuang Luo, Guangchun National Key Laboratory of Intelligent Collaborative Computing China University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu China University of Electronic Science and Technology of China National Key Laboratory of Intelligent Collaborative Computing Chengdu China University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu China

Recent advancements in language models have greatly improved dialogue systems, but they still face challenges in generating personalized responses that are consistent with the user's persona and dialogue context. Existing approaches typically model dialogue context and persona information together in a unified manner, but they lack fine-grained differentiation between the two, leading to inaccurate user modeling. This misalignment hinders the ability of dialogue systems to produce personalized responses. In this work, we propose CKE (Cross-Graph Knowledge Exchange), a novel algorithm designed to enhance personalized response generation in dialogue systems. CKE constructs separate dialogue user graphs for each party in the dialogue, representing both their dialogue context and persona information. These graphs are then utilized to perform cross-graph structured knowledge aggregation, where the aggregation is under supervised by both its own and the other party's persona and dialogue context, providing richer, more accurate representations. Furthermore, CKE introduces a hybrid prompt template that combines both discrete and continuous elements, improving the language model's ability to leverage graph-structured information. The experimental results demonstrate that CKE significantly outperforms existing baseline methods in generating more coherent, contextually appropriate, and personalized responses in dialogue systems. © 2014 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

YFLM: An Improved Levenberg-Marquardt Algorithm for Global Bundle Adjustment 41st

YFLM: An Improved Levenberg-Marquardt Algorithm for Global ...

引用

41st computer Graphics International Conference, CGI 2024

作者： Peng, Jiaxin Li, Tao Jiang, Qin Liu, Jie Wang, Ruibo Laboratory of Software Engineering for Complex Systems School of Computer Science National University of Defense Technology Hunan Changsha410073 China Parallel and Distributed Processing Laboratory School of Computer Science National University of Defense Technology Hunan Changsha410073 China

ISBN: (纸本)9783031820205

The conventional Levenberg-Marquardt (LM) algorithm is a state-of-the-art trust-region optimization method for solving bundle adjustment problems in the Structure-from-Motion community, which not only takes advantage of the fast convergence of the Gauss-Newton method, but also the stability of the gradient descent method when approaching optimal solutions. However, the damping ratio of LM is simply provided by trial-and-error, which causes slow convergence rate for large-scale problems. This paper proposes the Yamashita-Fukushima LM (YFLM) algorithm to reduce the time complexity for global bundle adjustment, where the damping factor is determined by Yamashita and Fukushima’s method. YFLM dynamically calculates a more reasonable and optimal damping ratio according to the newest reprojection error. The experimental results show that the YFLM algorithm outperforms the conventional LM algorithm for most public bundle adjustment datasets. Besides this, the convergence of the YFLM algorithm is also evaluated with different σ∈(0,2]. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Damping

来源：评论

学校读者我要写书评

暂无评论

MA-MFIF: When misaligned multi-focus Image fusion meets deep homography estimation

引用

Multimedia Tools and Applications 2025年第12期84卷 10877-10898页

作者： Zhao, Baojun Luo, Fei Fuentes, Joel Ding, Weichao Gu, Chunhua School of Information Science and Engineering East China University of Science and Technology Shanghai200237 China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China Department of Computer Science and Information Technologies Universidad del Bio-Bio Chillán3780000 Chile

Multi-focus image fusion is a technique that combines multiple out-of-focus images to enhance the overall image quality. It has gained significant attention in recent years, thanks to the advancements in deep learning. However, one of the persistent challenges in this field is the processing of misaligned data, which can negatively impact the fusion results. To overcome this problem, a novel fusion framework with pre-registration is proposed for the fusion of misaligned multi-focus images. For pre-registration, content-aware deep homography estimation is used, which performs transfer learning on a real multi-focus image dataset to adapt to registration under defocused conditions. For fusion, a fusion module with dual-branch feature interaction is utilized to avoid invalid feature fusion and trained on real light field dataset to achieve better fusion performance. Qualitative and quantitative experimental results show that the proposed method has a 2-3 percentage point improvement in multiple evaluation metrics compared to existing advanced registration and fusion methods, and a maximum improvement of 4.83 percentage points in fusion performance when tested independently on the Lytro dataset. Additionally, We find that the value of the Qcv metric is greatly influenced by the alignment status of the input images, leading to its inability to reflect the fusion quality of aligned images. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

RandoMix: a mixed sample data augmentation method with multiple mixed modes

引用

Multimedia Tools and Applications 2025年第8期84卷 4343-4359页

作者： Liu, Xiaoliang Shen, Furao Zhao, Jian Nie, Changhai National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science and Technology Nanjing University Nanjing China School of Artificial Intelligence Nanjing University Nanjing China School of Electronic Science and Engineering Nanjing University Nanjing China

Data augmentation plays a crucial role in enhancing the robustness and performance of machine learning models across various domains. In this study, we introduce a novel mixed-sample data augmentation method called RandoMix. RandoMix is specifically designed to simultaneously address robustness and diversity challenges. It leverages a combination of linear and mask mixed modes, introducing flexibility in candidate selection and weight adjustments. We evaluate the effectiveness of RandoMix on diverse datasets, including CIFAR-10/100, Tiny-ImageNet, ImageNet, and Google Speech Commands. Our results demonstrate its superior erformance compared to existing techniques such as Mixup, CutMix, Fmix, and ResizeMix. Notably, RandoMix excels in enhancing model robustness against adversarial noise, natural noise, and sample occlusion. The comprehensive experimental results and insights into parameter tuning underscore the potential of RandoMix as a versatile and effective data augmentation method. Moreover, it seamlessly integrates into the training pipeline. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Data augmentation Diversity Mixed-sample RandoMix Robustness

来源：评论

学校读者我要写书评

暂无评论

MARO: Enabling Full MPI Automatic Refactoring in DSL-Based Programming Framework 24th

MARO: Enabling Full MPI Automatic Refactoring in DSL-Based ...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Lei, Tong Chen, Zongjing Che, Yonggang Xu, Chuanfu Laboratory of Digitizing Software for Frontier Equipment National University of Defense Technology Changsha410073 China National Key Laboratory of Parallel and Distributed Computing College of Computer Science and Technology National University of Defense Technology Changsha410073 China

ISBN: (纸本)9789819615445

Currently, the landscape of computer hardware architecture presents the characteristics of heterogeneity and diversity, prompting widespread attention to cross-platform portable parallel programming techniques. Most existing portable programming approaches adopt the "MPI+X" strategy, focusing mainly on node-level "X" parallelism, while inter-node parallelization still relies on manual MPI programming. OP2 is a domain-specific language-based portable parallel programming framework for unstructured mesh applications that supports the automatic generation of MPI parallel code. However, programmers must manually write pre-processing code during code refactoring, such as handling the mapping relationship between global and process-local variables and the initial distribution of process-local data. In this paper, we propose MARO (MPI Automatic Refactoring for OP2), an automatic refactoring method for generating pre-processing code targeting MPI code generation within the OP2 programming framework for unstructured mesh applications. This method automatically generates the pre-processing code required for MPI parallelism through the source-to-source translator, enabling OP2 to generate MPI parallel code without requiring users to write MPI-related code manually. We compare the automatically refactored OP2 applications using the proposed method with those manually refactored to validate its effectiveness. The proposed method enhances OP2’s automatic parallel code generation capability, enabling it to achieve fully automatic MPI parallelization. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Automatic programming

来源：评论

学校读者我要写书评

暂无评论

DIG: Improved DINO for Graffiti Detection

引用

IEEE Transactions on Systems, Man, and Cybernetics: Systems 2025年第5期55卷 3557-3569页

作者： Wang, Bingshu Mao, Qianchen Liu, Aifei Chen, Long Chen, C. L. Philip Northwestern Polytechnical University School of Software Xi’an710129 China Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen518060 China University of Macao Department of Computer and Information Science China South China University of Technology School of Computer Science and Engineering Guangzhou510641 China

Graffiti detection is essential in historic building protection and urban neighborhood management. Graffiti detection has made significant progress in recent years based on the development of deep learning. However, small-scale graffiti, interference from the background, and the false detection of word parts in graffiti make it a challenging problem. This article proposes a Transformer-based high-precision graffiti detection method, namely DIG. Precisely, it consists of three modules: 1) Spatial query selection (SQS), scale-aware IoU loss (SIL);2) Denoising Task with binary contrastive denoising (BCDN);and 3) IoU-guided box denoising (IBD) modules. To detect small-scale graffiti, this paper proposes SIL to help the loss function to perceive small-scale graffiti and large-scale graffiti fairly. To reduce the false detection of word parts, this article presents the SQS module, which integrates spatial information into the query selection process of the Encoder to filter out falsely detected bounding boxes within the graffiti. To reduce the interference from the background, this article introduces a denoising task with BCDN and IBD modules, improving the model’s ability to distinguish graffiti from the background and accurately select appropriate bounding boxes. A large number of experimental results on the STORM dataset show that our method achieves state-of-the-art results with an AP50 of 87.9%. Moreover, DIG achieved competitive results on the FineFM dataset for mask detection. This indicates that DIG can also be conveniently transferred to detect other scenarios. © 2013 IEEE.

关键词： Historic preservation

来源：评论

学校读者我要写书评

暂无评论

Complementary Learning System Theory-based Active Learning for Audio Classification

Complementary Learning System Theory-based Active Learning f...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Geng, Hui Gao, Zijian Wan, Tianjiao Feng, Dawei Wang, Changjian Xu, Kele College of Computer Science and Technology National University of Defense Technology Changsha China State Key Laboratory of Complex & Critical Software Environment Changsha China

ISBN: (纸本)9798350368741

Deep learning has significantly advanced the audio classification, achieving remarkable results. However, these successes often rely on extensive manual annotation of audio, a labor-intensive and costly process. Active Learning (AL) presents a promising solution by minimizing the required amount of annotation through the iterative selection of the most informative audio samples. Current AL methods for audio classification typically depend solely on the latest model checkpoint, overlooking the dynamics of the entire training process. The Complementary Learning Systems (CLS) theory posits that the interplay between short-term and long-term memory systems can effectively measure sample uncertainty, offering a means to capture training dynamics. In this work, we introduce a novel AL framework for audio classification, termed CLS-AL, which addresses the limitations of existing methods by simultaneously maintaining both short-term and long-term memory models. This dual-memory approach allows for a more comprehensive consideration of training dynamics. The divergence in predictions between these memory models provides a new metric for evaluating the uncertainty of unlabeled samples, enhancing the effectiveness of the AL sample selection process. We demonstrate the effectiveness and generalizability of CLS-AL through extensive experiments on a diverse set of audio datasets, showing that CLS-AL obviously outperforms existing state-of-the-art methods. © 2025 IEEE.

关键词： Active Learning Audio Classification Complementary Learning System Uncertainty Estimation

来源：评论

学校读者我要写书评

暂无评论

ICCG:low-cost and efficient consistency with adaptive synchronization for metadata replication

引用

Frontiers of computer Science 2025年第1期19卷 53-70页

作者： Chenhao ZHANG Liang WANG Jing SHANG Zhiwen XIAO Limin XIAO Meng HAN Bing WEI Runnan SHEN Jinquan WANG State Key Laboratory of Software Development Environment Beihang UniversityBeijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China School of Cyberspace Security Hainan UniversityHaikou 570228China China Mobile Information Technology Center Beijing 100033China

The rapid growth in the storage scale of wide-area distributed file systems (DFS) calls for fast and scalable metadata management. Metadata replication is the widely used technique for improving the performance and scalability of metadata management. Because of the POSIX requirement of file systems, many existing metadata management techniques utilize a costly design for the sake of metadata consistency, leading to unacceptable performance overhead. We propose a new metadata consistency maintenance method (ICCG), which includes an incremental consistency guaranteed directory tree synchronization (ICGDT) and a causal consistency guaranteed replica index synchronization (CCGRI), to ensure system performance without sacrificing metadata consistency. ICGDT uses a flexible consistency scheme based on the state of files and directories maintained through the conflict state tree to provide an incremental consistency for metadata, which satisfies both metadata consistency and performance requirements. CCGRI ensures low latency and consistent access to data by establishing a causal consistency for replica indexes through multi-version extent trees and logical time. Experimental results demonstrate the effectiveness of our methods. Compared with the strong consistency policies widely used in modern DFSes, our methods significantly improve the system performance. For example, in file creation, ICCG can improve the performance of directory tree operations by at least 36.4 times.

关键词： metadata management metadata replication consistency directory tree replica index

来源：评论

学校读者我要写书评

暂无评论

MG+: Towards Efficient Context Inconsistency Detection by Minimized Link Generation

MG+: Towards Efficient Context Inconsistency Detection by Mi...

引用

作者： Chen, Chuyang Wang, Huiyan Zhang, Lingyu Xu, Chang Yu, Ping State Key Laboratory for Novel Software Technology Nanjing University Jiangsu Nanjing China School of Computer Science Nanjing University Jiangsu Nanjing China Software Institute Nanjing University Jiangsu Nanjing China

Self-adaptive applications are becoming increasingly attractive, with the ability to smartly understand their runtime environments (or contexts) and deliver adaptive services, for example, location-aware navigation or resource-sensitive suggestions. However, due to inherent noises in the process of sensing and interpreting environmental information, there is a growing demand for guarding the consistency of collected contexts to avoid application misbehaviour and, at the same time, minimize extra costs. Existing work attempted to achieve this by speeding up the kernel constraint checking module inside the consistency guarding process. Most of these efforts were spent on reusing previous checking results or parallelizing the checking process, but they all leave one central step of constraint checking, that is, link generation, untouched. In this step, the checking engine provides reasons to explain the violation of constraints under check. It occupies a substantial part of the total time cost. Focusing on this key link generation step, we proposed MG, which deploys a rigourous analysis to automatically identify and avoid redundancy in the link generation without harming any correctness of the checking results. MG has been proven sound (always guaranteeing correctness) and complete (entirely removing redundancy). Moreover, based on our observation that MG's redundancy elimination also assists another core step of constraint checking to reduce unnecessary computation further, we additionally enhance MG with an escape-condition optimization to escape unnecessary evaluation of truth values to further improve the efficiency of constraint checking in an aspect other than link generation. We call it MG+ for distinguishing. Our experiments with synthesized and real-world consistency constraints reported that, compared with existing work, MG eliminates all link redundancy (83% to 0%), and based on it, MG+ further reduces significant truth value calculations (e.g., 49.74% reduc

关键词： constraint checking context inconsistency link redundancy

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：