检索结果-内蒙古大学图书馆

10th International Conference on Signal and information Processing, network and Computers, ICSINC 2022

作者： Zhang, Rui Song, Yuhui Du, Tao School of Information Engineering Shandong Management University No. 3500 Dingxiang Road Changqing District Shandong Jinan250357 China School of Information Science and Engineering University of Jinan Jinan China Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan China

ISBN: (纸本)9789811999673

Since the outbreak of the COVID-19 in early 2020, the prevention and control of infectious diseases has been raised to a higher level. However, tuberculosis still ranks in the forefront of the incidence rate of various infectious diseases in China. The tuberculosis epidemic has also brought great economic pressure and negative social impact to the society every year. Therefore, we have always been very concerned about how to effectively prevent and control the spread of tuberculosis. However, the diagnostic data of tuberculosis are often high-dimensional, huge, messy and difficult to be used effectively. How to extract knowledge from the data to help medical staff find the incidence trend of tuberculosis to assist decision-making has become a practical topic. In this paper, after clarifying and standardizing the original data, the density peak clustering (DPC) algorithm is used for deep mining. The knowledge is extracted through clustering analysis and visualization. Finally, analysis results can intuitively illustrate the effectiveness and practical research significance of this work. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

A DPC Based Recommendation Algorithm for Internship Positions 10th

A DPC Based Recommendation Algorithm for Internship Position...

引用

10th International Conference on Signal and information Processing, network and Computers, ICSINC 2022

作者： Zhang, Rui Bi, Lingyun Du, Tao School of Information Engineering Shandong Management University No.3500 Dingxiang Road Shandong Changqing District Jinan250357 China School of Information Science and Engineering University of Jinan Jinan China Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan China

ISBN: (纸本)9789811999673

In the graduation internship activities, the choice of centralized internship based on school-enterprise cooperation units is limited, and the independent internship method will inevitably lead to the problem of blind job selection due to students' lack of social experience. In this paper, we mine historical practice data and propose a recommendation algorithm based on binomial association rules and density peak clustering analysis named DPC-RA. Through binomial association rules, students' internship results in different units are associated with the classification data of unit names, and the internship unit name data is numerically realized. DPC (density peak clustering) algorithm is used to cluster and mine internship data, and obtain multiple clusters. This method can provide accurate personalized work recommendations and improve the quality of internship. Experiments show that this method is effective. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Association rules

来源：评论

学校读者我要写书评

暂无评论

Open-vocabulary 3D Semantic Understanding via Affinity Neural Radiance Fields

Open-vocabulary 3D Semantic Understanding via Affinity Neura...

引用

Next Generation Data-driven networks (NGDN), International Conference on

作者： Yujie Fan Huan Luo Computer and Data Science Fuzhou University Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China

ISBN: (数字)9798350388374

ISBN: (纸本)9798350388381

Three-dimensional semantic understanding using only several multi-view images can largely reduce the communication burden on the network. In addition, while point clouds are extensively studied for 3D scene understanding, utilization of multi-view image data offers rich visual details and texture information. However, challenges persist in lifting 2D semantic features to 3D space and leveraging language for segmentation. Inspired by recent advancements, this paper proposes a method that combines CLIP features and SAM masks to create a feature field capable of segmenting objects via natural language text across 2D multi-view and 3D Gaussian splatting. It offers a promising function for extracting 3D assets for game engines and the metaverse. Our method involves mask generation from video frames, extracting physical scales via RGB Nerf with masks, and organizing hierarchical information for semantic comprehension. In the training process, affinity features maintain scale properties and guide CLIP feature generation with auto weights blending for semantic robustness. A straightforward 3D splatting CLIP feature approach and canonical text methodology enhance query robustness across 2D multi-view and 3D splatting through relevance score calculation based on text CLIP features for inference. Experimental results demonstrate promising improvements in semantic understanding of 3D scenes.

关键词： Training Image segmentation Vocabulary Visualization Three-dimensional displays Semantics Natural languages Neural radiance field Feature extraction Robustness

来源：评论

学校读者我要写书评

暂无评论

An Encryption Algorithm Cycle Identification Method Based on Bit Execution

An Encryption Algorithm Cycle Identification Method Based on...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Yunge Sun Gaolei Du Junpeng Qu Yong Fu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology(Shandong Academy of Sciences) Jinan China Quan Cheng Laboratory Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

Ransomware uses symmetric encryption algorithms to lock user files to extort money. This paper proposes a cryptographic algorithm loop identification method based on bit-precise execution, aiming to solve the problem of identifying unknown loops. The structure of the loop body of encryption algorithms is fixed and usually includes nonlinear operations and linear operations. This article converts the loop body in the unknown software into a set of Boolean formulas, and converts the malware into a register data flow through the symbolic executor, thereby converting it into a set of Boolean formulas for execution. Execute known encryption algorithms with bit accuracy and establish a Boolean formula input-output relationship library for cryptographic components. The two sets of Boolean formulas are passed through a designed input matrix to achieve the Boolean formula mapping and input variable mapping of the confirmation algorithm, which can effectively judge the encryption algorithms in some malware.

关键词： Deformation Input variables Software algorithms Merging Data science Libraries Encryption Registers Ransomware Matrix converters

来源：评论

学校读者我要写书评

暂无评论

An automated construction method for symmetric encryption round function models based on dynamic analysis

An automated construction method for symmetric encryption ro...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Gaolei Du Yunge Sun Junpeng Qu Yong Fu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Quan Cheng Laboratory Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

With the deepening of informatization, the incidence of cybercrimes utilizing malicious software for attacks is on the rise. This paper addresses the detection issue of symmetric encryption in malicious software from the perspective of cryptography, proposing an automated method for constructing a symmetric encryption round function model based on dynamic analysis. This method tracks data flow at the granularity of registers to characterize Directed Acyclic Graph (DAG) construction of round function models. Initially, dynamic execution traces of binary files are captured using Intel Pin, identifying loops within them. Data flow tracking at the register level within loops is performed, creating DAG, and analyzing whether the loops exhibit characteristics of symmetric cipher round functions, thus constructing the round function model. This approach enables the detection of symmetric encryption within binary files and the construction of round function models, offering a novel solution for fine-grained symmetric cipher recognition and laying a foundation for detecting malicious software containing symmetric encryption.

关键词： Analytical models Ciphers Tracking loops XML Data models Malware Encryption Registers Trajectory Pins

来源：评论

学校读者我要写书评

暂无评论

Dynamic detection technology of encryption algorithm based on Pin

Dynamic detection technology of encryption algorithm based o...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Junpeng Qu Gaolei Du Yunge Sun Yong Fu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Quan Cheng Laboratory Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

Aiming at the problem that malicious software uses encryption algorithm to hide its own malicious code and avoid detection, a dynamic detection technology based on Pin encryption algorithm is proposed. Use Pin to get the instruction flow of executable file running, then identify the function call in the instruction flow to get the function call framework, find the loop body in the calling function, and then carry out the encryption algorithm instruction detection and encryption algorithm constant detection on the loop body. If the detection passes, it can be considered that a component of the encryption algorithm is found. Then the complete encryption algorithm is found according to the generated function call framework. Experiments show that this method can effectively identify the encryption algorithms hidden in executable files.

关键词： Heuristic algorithms Software algorithms Cyberspace Data science Feature extraction Malware Encryption Pins

来源：评论

学校读者我要写书评

暂无评论

TDMF: Text-Guided Denoising and Interactive Medical Image Fusion

TDMF: Text-Guided Denoising and Interactive Medical Image Fu...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Aimei Dong Jingyuan Xu Long Wang Guohua Lv Guixin Zhao Jinyong Cheng Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Faculty of Computer Science and Technology Qilu University of Technology(Shandong Academy of Sciences) Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Multimodal image fusion aims to merge features from different modalities to create a comprehensively representative image. However, existing medical image fusion methods often struggle to handle noise generated during image acquisition, significantly diminishing their impact on visual quality. To address these challenges, we propose a semantically text-guided medical image fusion model, named TDMF. Specifically, TDMF guides classical image fusion through textual semantics and effectively coordinates the resolution of degradation and interaction issues during the fusion process. By integrating text encoders and interactive fusion modules, TDMF establishes a unified framework for denoising and interactive fusion of medical images. Extensive experiments have demonstrated that our proposed text-guided image fusion strategy offers significant advantages over state-of-the-art methods in medical image fusion performance.

关键词： Visualization Image resolution Semantics Noise reduction Noise Pipelines Noise measurement Speech processing Image fusion Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Offloading Mode Hidden for Delay Sensitive Tasks in Edge computing networks

Offloading Mode Hidden for Delay Sensitive Tasks in Edge Com...

引用

Artificial Intelligence, networking and information Technology (AINIT), International Seminar on

作者： Guowei Zhang Jiayuan Du School of Cyber Science and Engineering Qufu Normal University Qufu China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798350385557

ISBN: (纸本)9798350385564

Edge computing has been developed to support local services with lower burden to the core network. However, privacy issues deteriorate when terminal users enjoy the high-quality services with the price of sending their data to multiple service nodes (SNs) scattered throughout the network. Existing researches concerning this problem are almost all based on the traditional security technologies including encryption and authentication, which are too complicated to be well supported by the terminal nodes (TNs) in edge networks due to the poor local processing capabilities. In view of the above, this article proposes an offloading mode hidden (OMH) algorithm, which reduces the risk level by equalizing the task offloading modes of different TNs. Gaming process is adopted to achieve the risk-minimized offloading solutions for TNs. Numerical results demonstrate that comparing with the Greedy algorithm, the proposed OMH algorithm can achieve lower task offloading risk with higher efficiency and provide more TNs with satisfied services.

关键词： Greedy algorithms Seminars Privacy Risk minimization Processor scheduling Scheduling Delays

来源：评论

学校读者我要写书评

暂无评论

Safe and Reliable Diffusion Models via Subspace Projection

arXiv

引用

arXiv 2025年

作者： Chen, Huiqiang Zhu, Tianqing Wang, Linlin Yu, Xin Gao, Longxiang Zhou, Wanlei Faculty of Data Science City University of Macau China School of Computer Science University of Queensland QLD Australia Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences Jinan China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China

Large-scale text-to-image (T2I) diffusion models have revolutionized image generation, enabling the synthesis of highly detailed visuals from textual descriptions. However, these models may inadvertently generate inappropriate content, such as copyrighted works or offensive images. While existing methods attempt to eliminate specific unwanted concepts, they often fail to ensure complete removal—allowing the concept to reappear in subtle forms. For instance, a model may successfully avoid generating images in Van Gogh’s style when explicitly prompted with "Van Gogh", yet still reproduce his signature artwork when given the prompt "Starry Night". In this paper, we propose SAFER, a novel and efficient approach for thoroughly removing target concepts from diffusion models. At a high level, SAFER is inspired by the observed low-dimensional structure of the text embedding space. The method first identifies a concept-specific subspace Sc associated with the target concept c. It then projects the prompt embeddings onto the complementary subspace of Sc, effectively erasing the concept from the generated images. Since concepts can be abstract and difficult to fully capture using natural language alone, we employ textual inversion to learn an optimized embedding of the target concept from a reference image. This enables more precise subspace estimation and enhances removal performance. Furthermore, we introduce a subspace expansion strategy to ensure comprehensive and robust concept erasure. Extensive experiments demonstrate that SAFER consistently and effectively erases unwanted concepts from diffusion models while preserving generation quality. © 2025, CC BY.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

RMSLRS: Real-Time Multi-terminal Sign Language Recognition System 13th

RMSLRS: Real-Time Multi-terminal Sign Language Recognition S...

引用

13th International Conference on Innovations in Bio-Inspired computing and Applications, IBICA 2022, and 12th World Congress on information and Communication Technologies, WICT 2022

作者： Zhao, Yilin Zhang, Biao Ma, Kun Business School of Jinan University University of Jinan Jinan250022 China School of Computer and Information Hefei University of Technology Hefei230009 China Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan250022 China

ISBN: (纸本)9783031274985

Sign language is commonly used by deaf or speech-impaired people to convey meaning. Sign language recognition (SLR) aims to help users learn and use sign language by recognizing the signs from given videos. Although sign language has gained social acceptance, few sign language recognition systems have been developed with educational purposes. Current SLR system has a single form of expression and lacks real-time interaction and feedback with an expensive cost. And videos captured in real scenes are complex, which has impact on the performance of models. To this end, this paper has proposed a novel real-time multi-terminal sign language recognition system (RMSLRS). Specifically, a lightweight sign language recognition model based on MediaPipe Holistic is proposed to perform sign language inference by sensing multi-dimensional information such as pose, facial expression, and hand tracking, achieving near real-time performance on mobile and desktop devices. Then, a novel pre-processing module is proposed to reduce the adverse effects of background noise in videos through the YOLO model and OpenCv. Furthermore, a novel technical architecture for front-end and back-end separation and multi-terminal deployment is designed, including WeChat applet, desktop application and website. Finally, this system has been deployed with gratifying success in practice. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep learning

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：