检索结果-内蒙古大学图书馆

International Conference on Signal Processing Proceedings (ICSP)

作者： Guo Hongxing Su Lei Yu Shengsheng Zhou Jingli Department of Computer Science and Engineering Key Laboratory of Data Storage System of Ministry of Education Huazhong University of Science and Technology Wuhan Hubei China

This paper analyses the mathematical properties of four famous wavelets and evaluates their coding performance for different kinds of images in EZW image coders. It can be found that although the 9/7 biorthogonal wavelets, which obtain better tradeoff among incompatible mathematical properties, give the best performance. But it still can't code edges and textures efficiently due to existing ringing and smearing artifacts at low bit rates. The harmonic decomposition must follow the uncertainty principle that prevents any atom perfectly, which is well localized in the space domain to retain frequency localization. It gives an opportunity to develop new paradigms to efficiently representing and coding structures very well localized in the space domain, but with large frequency band such as edges and textures.

关键词： Wavelet analysis Low pass filters Image coding Filter bank Image analysis Frequency Computer science data storage systems Computer science education Bit rate

来源：评论

学校读者我要写书评

暂无评论

A modified particle swarm optimization for combining forecasting

A modified particle swarm optimization for combining forecas...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： X.Y. Feng L.M. Wan Y.C. Liang Y.F. Sun H.P. Lee Y. Wang Kollege of Computer Science and Technology Key Laboratory for Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China College of Computer Science and Technology Key Laboratory for Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun China The 8th Research Institute of Air Force Beijing China Institute of High Performance Computing Singapore Singapore

A modified particle swarm optimization (PSO) algorithm is proposed. Linear constraints in the PSO are added to satisfy the normalization conditions for different problems. A hybrid algorithm based on the modified PSO and combining forecasting is presented. Combining forecasting can improve the forecasting accuracy through combining different forecasting methods. The effectiveness of the algorithm is demonstrated through the prediction on the sunspots and the stocks data. Simulated results show that the hybrid algorithm can improve the forecasting accuracy to a great extent.

关键词： Particle swarm optimization Computational modeling Computer science educational technology Laboratories Military computing knowledge engineering Computer science education High performance computing Predictive models

来源：评论

学校读者我要写书评

暂无评论

Searching for closed itemset with formal concept analysis

Searching for closed itemset with formal concept analysis

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Hong Qi Da-You Liu Cheng-Quan Hu Ming Lu Liang Zhao Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China Jilin University Changchun Jilin CN Coll. of Comput. Sci. & Technol. Jilin Univ. Changchun China College of Computer Science and Technology Jilin University Changchun China

ISBN: (纸本)0780384032

The problem of mining frequent patterns plays an essential role in many important data mining tasks. However, it often generates a very large number of frequent itemsets. The set of frequent closed itemsets uniquely determines the exact frequency of all itemsets, yet it can be orders of magnitude smaller than the set of all frequent itemsets. An algorithm Closearcher based on formal concept analysis for closed itemset searching is proposed. This algorithm divides the whole search space of closed itemsets into several subspaces in accordance with criterions prescribed ahead, and introduces an efficient scheme to recognize the valid ones, in which the search for closed itemsets is bounded. An intermediate structure is employed to judge the validity of a subspace and search closed itemsets more efficiently. The algorithm is experimental evaluated and compared with the famous NextClosure algorithm proposed by Ganter for random generated data, as well as for real application data. The results show that our algorithm performs much better than the later.

关键词： Itemsets data mining Machine learning algorithms Pattern analysis Frequency Algorithm design and analysis databases educational institutions Computer science educational technology

来源：评论

学校读者我要写书评

暂无评论

Spatio-temporal representation for multi-dimensional occlusion relation

Spatio-temporal representation for multi-dimensional occlusi...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Sheng-Sheng Wang Da-You Liu Xiao-Dong Liu Bo Yang College of Computer Science and Technology Key Laboratory of Symbolic Computing and Knowledge Engineering of Ministry of Education Jilin University Changchun China

ISBN: (纸本)0780378652

Occlusion relation is the topological relation between the images of two bodies from a viewpoint. Qualitative representation of occlusion relation has been investigated in qualitative spatial reasoning. This research is important for computer vision and robot navigation. The previous models such as LOS and ROC-20 are all based on RCC (the famous topological theory). But those models couldn't support abstract objects such as point and line which are very common in real applications. To deal with this, multi-dimensional spatial occlusion relation (MSO) is put forward. The foundation of MSO is MRCC which is the multi-dimensional extension of RCC. So MSO is suitable for both real and abstract objects. The conception neighborhood and composition of MSO is given. Finally MSO is extended to spatio-temporal relation by adding time feature. MSO is an appropriate frame to express spatio-temporal knowledge.

关键词： Computer vision Navigation Topology educational institutions Computer science Laboratories knowledge engineering Computer science education Robot vision systems Application software

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Graph Pattern Matching via Tumor knowledge Graph

引用

ACM Transactions on Probabilistic Machine Learning 1000年

作者： Lei Li Houdie Tu Zhenchao Tao Chenyang Bu Xindong Wu Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei University of Technology Hefei 230601 China and School of Computer Science and Information Engineering Hefei University of Technology Hefei 230601 China School of Computer Science and Information Engineering Hefei University of Technology Hefei 230601 China School of Data Science University of Science and Technology of China Hefei 230052 China and West District of the First Affiliated Hospital of University of Science and Technology of China Hefei 230031 China Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei University of Technology Hefei 230601 China

Graph Pattern Matching (GPM) entails the identification of subgraphs within a larger graph structure that either precisely mirror or closely parallel a predefined pattern graph. Despite the fact that research on GPM in large-scale graph data has been largely centered on social network analysis or enhancing the precision and efficiency of matching algorithms for expeditious subgraph retrieval, there is a noticeable absence of studies committed to probing GPM in medical domains. To rectify this shortcoming and probe the potential of GPM in clinical contexts, particularly in aiding patients with the selection of optimal tumor treatment plans, this paper introduces the concept of probabilistic graph pattern matching specifically modified for the Tumor knowledge Graph (TKG). We propose a multi-constraint graph pattern matching algorithm, hereinafter designated as TKG-McGPM, customized for the Tumor knowledge Graph. Through experimental verification, we establish that TKG-McGPM can facilitate more efficient and informed decision-making in tumor treatment planning.

关键词： Graph Pattern Matching Probabilistic Graph Pattern Matching Tumor knowledge Graph Monte Carlo Method

来源：评论

学校读者我要写书评

暂无评论

Deceiving LLM through Compositional Instruction with Hidden Attacks

引用

ACM Transactions on Autonomous and Adaptive Systems 1000年

作者： Shuyu Jiang Xingshu Chen Rui Tang School of Cyber Science and Engineering Sichuan University China School of Cyber Science and Engineering Sichuan University Key Laboratory of Data Protection and Intelligent Management (Sichuan University) Ministry of Education Cyber Science Research Institute Sichuan University China

Recently, large language models (LLMs) have demonstrated promising applications in the autonomous driving (AD) domain, including language-based interactions and decision-making. Ensuring they safely handle harmful inputs is crucial before formal deployment. However, research reveals emerging hand-crafted jailbreak attacks, which pack harmful prompts into harmless instructions, can bypass LLMs’ security mechanisms and elicit harmful responses. To deeply understand such jailbreaks, this paper introduces a Compositional Instruction Attack (CIA) framework to generalize them, and develop two CIA jailbreaking methods to automatically generate tailored jailbreak prompts for each harmful prompt. Then, this paper builds the first CIA question-answering (CIAQA) dataset with 2.7K multiple-choice questions of 900 successful jailbreaks, for assessing LLMs’ ability to identify underlying harmful intents, harmfulness, and task priority in CIA jailbreaks. Combined with experimental analysis on CIAQA and other datasets, this paper concludes three possible reasons for the failure of LLM defenses against CIAs. Finally, we propose an intent-based defense paradigm (IBD), enabling LLMs to defend against CIA by leveraging its capability to identify intents. Experimental results show CIA can achieve attack success rates (ASR) of 95%+ and 85%+ in AD and common harmful scenarios for three well-known LLMs (GPT-4, GPT-3.5, and Llama2-70b-chat), and IBD reduces ASR by 74%+.

关键词： Large language model autonomous driving adversarial attack harmful prompt

来源：评论

学校读者我要写书评

暂无评论

Enhancing Sequential Personalized Product Search with External Out-of-sequence knowledge

引用

ACM Transactions on Information Systems 1000年

作者： Jiongnan Liu Zhicheng Dou Jian-Yun Nie Zhenlin Chen Guoyu Tang Sulong Xu Ji-Rong Wen Gaoling School of Artificial Intelligence Renmin University of China China DIRO University de Montreal Canada *** Inc China Gaoling School of Artificial Intelligence Renmin University of China China Engineering Research Center of Next-Generation Intelligent Search and Recommendation Ministry of Education China and Beijing Key Laboratory of Big Data Management and Analysis Methods China

A key challenge in personalized product search is to capture user’s preferences. Recent work attempted to model sequences of user historical behaviors, i.e., product purchase histories, to build user profiles and to personalize results accordingly. Although these approaches have demonstrated promising retrieval performances, we notice that most of them focus solely on the intra-sequence interactions between items. However, as there is usually a small amount of historical behavior data, the user profiles learned by these approaches could be very sensitive to the noise included in it. To tackle this problem, we propose incorporating out-of-sequence external information to enhance user modeling. More specifically, we inject the external item-item relations (e.g., belonging to the same brand), and query-query relations (e.g., the semantic similarities between them), into the intra-sequence interaction to learn better user profiles. In addition, we devise two auxiliary decoders, with the historical item sequence reconstruction task and the global item similarity prediction task, to further improve the reliability of user modeling. Experimental results on two datasets from simulated and real user search logs respectively show that the proposed personalized product search method outperforms existing approaches.

关键词： personalized product search sequential model graph

来源：评论

学校读者我要写书评

暂无评论

Conceptual Modeling for Advanced Application Domains 1

引用

丛书名： Lecture Notes in Computer Science

1000年

作者： Shan Wang Katsumi Tanaka Shuigeng Zhou Tok-Wang Ling Jihong Guan Dong-qing Yang Fabio Grandi Eleni E. Mangina Il-Yeol Song Heinrich C. Mayr

来源：评论

学校读者我要写书评

暂无评论

A Relation-Constraint Link Prediction Model for Dynamic knowledge Graphs with Entity Drift

引用

ACM Transactions on knowledge Discovery from data 1000年

作者： Xiulin Zheng Peipei Li Zan Zhang Jia Wu Xindong Wu Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei University of Technology China and School of Computer Science and Information Engineering Hefei University of Technology China School of Computing Faculty of Science and Engineering Macquarie University Australia

knowledge Graphs (KGs) often suffer from incompleteness and this issue motivates the task of knowledge Graph Completion (KGC). Traditional KGC models mainly concentrate on static KGs with a fixed set of entities and relations, or dynamic KGs with temporal characteristics, faltering in their generalization to constantly evolving KGs with possible irregular entity drift. Thus, in this paper, we propose a novel link prediction model based on the embedding representation to handle the incompleteness of KGs with entity drift, termed as DCEL. Unlike traditional link prediction, DCEL could generate precise embeddings for drifted entity without imposing any regular temporal characteristic. The drifted entity is added into the KG with its links to the existing entity predicted in an incremental fashion with no requirement to retrain the whole KG for computational efficiency. In terms of DCEL model, it fully takes advantages of unstructured textual description, and is composed of four modules, namely MRC (Machine Reading Comprehension), RCAA (Relation Constraint Attentive Aggregator), RSA (Relation Specific Alignment) and RCEO (Relation Constraint Embedding Optimization). Specifically, the MRC module is first employed to extract short texts from long and redundant descriptions. Then, RCAA is used to aggregate the embeddings of textual description of drifted entity and the pre-trained word embeddings learned from corpus to a single text-based entity embedding while shielding the impact of noise and irrelevant information. After that, RSA is applied to align the text-based entity embedding to graph-based space to obtain the corresponding graph-based entity embedding, and then the learned embeddings are fed into the gate structure to be optimized based on the RCEO to improve the accuracy of representation learning. Finally, the graph-based model TransE is used to perform link prediction for drifted entity. Extensive experiments conducted on benchmark datasets in terms of evaluat

关键词： dynamic knowledge graph entity drift link prediction relation constraint

来源：评论

学校读者我要写书评

暂无评论

EnIter: Enhancing Iterative Multi-View Depth Estimation with Universal Contextual Hints

引用

ACM Transactions on Multimedia Computing, Communications, and Applications 1000年

作者： Qianqian Du Hui Yin Lang Nie Yanting Liu Jin Wan State Key Laboratory of Advanced Rail Autonomous Operation Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence Beijing Jiaotong University Beijing China State Key Laboratory of Advanced Rail Autonomous Operation Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence Frontiers Science Center for Smart High-speed Railway System Beijing Jiaotong University Beijing China School of Computer Science and Technology Beijing Jiaotong University Beijing China Key Laboratory of Beijing for Railway Engineering School of Computer Science and Technology Beijing Jiaotong University Beijing China Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan) Qilu University of Technology Shandong Academy of Sciences) Jinan China

Iterative inference approaches have shown promising success in the task of multi-view depth estimation. However, these methods put excessive emphasis on the universal inter-view correspondences while neglecting the correspondence ambiguity in regions of low texture and depth discontinuous areas. Thus, they are prone to produce inaccurate or even erroneous depth estimations, which is further exacerbated cumulative errors especially in the iterative pipeline, providing unreliable information in many real-world scenarios. In this paper, we revisit this issue from the intra-view Contextual Hints and introduce a novel enhancing iterative approach, named EnIter. Concretely, at the beginning of each iteration, we present a Depth Intercept (DI) modulator to provide more accurate depth by aggregating neighbor uncertainty, correlation volume of reference and normal. This plug and play modulator is effective at intercepting the erroneous depth estimations with implicit guidance from the universal correlation contextual hints, especially for the challenging regions. Furthermore, at the end of each iteration, we refine the depth map with another plug and play modulator termed as Depth Refine (DR). It mines the latent structure knowledge of reference Contextual Hints and establishes one-way dependency using local attention from reference features to depth, yielding delicate depth in details. Extensive experiment demonstrates that our method not only achieves state-of-the-art performance over existing models but also exhibits remarkable universality in popular iterative pipelines, e.g., CasMVS, UCSNet, TransMVS, UniMVS.

关键词： Depth estimation Contextual hints Iterative inference Cumulative errors

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：