检索结果-内蒙古大学图书馆

4th International Conference on data-Driven Optimization of Complex Systems, DOCS 2022

作者： Liu, Wenting Zuo, Yi Li, Tieshan Philip Chen, C.L. Dalian Maritime University Collaborative Innovation Center of Maritime Big Data & Artificial General Intelligence Navigation College Dalian China University of Electronic Science and Technology of China School of Automatic Engineering Chengdu China

ISBN: (数字)9781665459822

ISBN: (纸本)9781665459822

Based on broad learning system (BLS), this paper monitors and identifies the behavior of crew members on ships. The main recognition scenarios include both of on deck and in the cabin, and the main recognition tasks include crew tracking and identification. In this paper, the video data is divided into frames and images are segmented. In the preprocessing of images, the filter is used to enhance the information and reduce the noise of the images. Finally, the recognition model is established by the BLS. In the experiment, we use BP neural network (BPNN) and support vector machine (SVM) as comparisons. The proposed method in this paper has achieved the best results in terms of recognition accuracy and training time. © 2022 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

CLOUDY WITH A CHANCE OF ANOMALIES: DYNAMIC GRAPH NEURAL NETWORK FOR EARLY DETECTION OF CLOUD SERVICES’ USER ANOMALIES

arXiv

引用

arXiv 2024年

作者： Marbel, Revital Cohen, Yanir Dubin, Ran Dvir, Amit Hajaj, Chen Israel Department of Computer Science Ariel Cyber Innovation Center Ariel University Kiryat Hamada 3 Ariel Israel Department of Industrial Engineering and Management Data Science and Artificial Intelligence Research Center Ariel University Israel

Ensuring the security of cloud environments is imperative for sustaining organizational growth and operational efficiency. As the ubiquity of cloud services continues to rise, the inevitability of cyber threats underscores the importance of preemptive detection. This paper introduces a pioneering time-based embedding approach for Cloud Services Graph-based Anomaly Detection (CS-GAD), utilizing a Graph Neural Network (GNN) to discern anomalous user behavior during interactions with cloud services. Our method employs a dynamic tripartite graph representation to encapsulate the evolving interactions among cloud services, users, and their activities over time. Leveraging GNN models in each time frame, our approach generates a graph embedding wherein each user is assigned a score based on their historical activity, facilitating the identification of unusual behavior. Results demonstrate a notable reduction in false positive rates (2-9%) compared to prevailing methods, coupled with a commendable true positive rate (100%). The contributions of this work encompass early detection capabilities, a low false positive rate, an innovative tripartite graph representation incorporating action types, the introduction of a new cloud services dataset featuring various user attacks, and an open-source implementation for community collaboration in advancing cloud service security. © 2024, CC BY-NC-ND.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Path Planning of Mission-driven USVs Based on Stochastic Schemata Exploiter 4

Path Planning of Mission-driven USVs Based on Stochastic Sch...

引用

4th International Conference on data-Driven Optimization of Complex Systems, DOCS 2022

作者： Zhi, Liwei Zuo, Yi Li, Tieshan Dalian Maritime University Collaborative Innovation Center of Maritime Big Data & Artificial General Intelligence Navigation College Dalian China University of Electronic Science and Technology of China School of Automatic Engineering Chengdu China

ISBN: (数字)9781665459822

ISBN: (纸本)9781665459822

In recent years, the research on unmanned surface vessels (USVs) has become a new hot spot in the development of intelligent applications in the shipping industry of various countries. With the gradual maturity and popularization of modern information technologies such as computer technology and artificial intelligence, the research on USVs has scientific and technological support, and is developing from theoretical research to application practice. Among them, the autonomous assignment and decision-making coordination of multi-target tasks is one of the important research topics for autonomous navigation of USVs. At the same time, the path planning of UAVs also plays a crucial role in autonomous assignment and navigation. In view of the above points, this paper proposes a heuristic optimization algorithm based on stochastic schemata exploiter (SSE). It is used to solve the path optimization problem of USVs for mission requirements. In the experiment, two combinations of two USVs are considered, and the paths are optimized in the two cases of jointly completing the task and cooperatively completing the task. The algorithm combines the heuristic information of the distribution structure of static obstacles in the environment, expands the obstacles and optimizes the node selection of the USV, so that the USV can avoid the obstacles with a higher probability and find an excellent feasible path, and improve the global search ability. Compared with the genetic algorithm (GA) through simulation experiments, the proposed algorithm presents a significant improvement in timeliness and path optimization. © 2022 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Gradual Further Pre-training Architecture for Economics/Finance Domain Adaptation of Language Model

Gradual Further Pre-training Architecture for Economics/Fina...

引用

2022 IEEE International Conference on Big data, Big data 2022

作者： Sakaji, Hiroki Suzuki, Masahiro Izumi, Kiyoshi Mitsugi, Hiroyuki The University of Tokyo School of Engineering Department of Systems Innovation Tokyo Japan Daiwa Institute of Research Ltd. Frontier Technologies Research Center. Data-driven Science Dept. Tokyo Japan

ISBN: (纸本)9781665480451

We propose a new pre-trained architecture for economics/finance domain adaptation of language models in this paper. Pre-trained language models have become commonplace in a wide range of language processing applications. Because they learn from generic documents such as Wikipedia, many pre-trained language models are not fully adapted to the domain. As a result, there are two approaches: one is to develop a domain-specific pre-trained language model, and the other is to adapt the model learned on general documents to the domain through further pre-training with domain texts. However, no definitive better method has been discovered, and each project is working on it in different ways. As a result, this study focuses on the Japanese language's economics/financial domains and investigates how pre-trained language models can be better adapted to domain-specific tasks. © 2022 IEEE.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Multiple Unmanned Armored Vehicle Formation Transform

Multiple Unmanned Armored Vehicle Formation Transform

引用

Chinese Intelligent Systems Conference, CISC 2020

作者： Huang, Miqi Tian, Daxin Duan, Xuting Beijing Advanced Innovation Center for Big Data and Brain Computing School of Transport Science and Engineering Beihang University Beijing China

ISBN: (纸本)9789811584572

The formation of armored vehicle formation achievement and transforming are important research contents of vehicle formation control. Especially for the situation of unmanned armored vehicle formation. This paper combines the virtual navigator method and the behavior-based bait-predator method, and applies it to the formation achievement and transforming control of four unmanned armored vehicle formations. The target position is used as a bait to realize flexible transforming between linear, triangular and diamond formations. This method can prevent the formation leader from losing control due to the incapacitation of the formation leader, and does not specify the fixed position of the vehicle in the formation, which greatly guarantees the stability of the formation and the flexibility of formation transforming. The simulation experiment also proves that the method has good effect on the formation and formation transforming of vehicle formation. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Armored vehicles

来源：评论

学校读者我要写书评

暂无评论

TOWARDS FAITHFUL XAI EVALUATION VIA GENERALIZATION-LIMITED BACKDOOR WATERMARK 12

TOWARDS FAITHFUL XAI EVALUATION VIA GENERALIZATION-LIMITED B...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Ya, Mengxi Li, Yiming Dai, Tao Wang, Bin Jiang, Yong Xia, Shu-Tao Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China The State Key Laboratory of Blockchain and Data Security Zhejiang University China ZJU-Hangzhou Global Scientific and Technological Innovation Center China College of Computer Science and Software Engineering Shenzhen University China Guangzhou Intelligence Communications Technology Co. Ltd. China

Saliency-based representation visualization (SRV) (e.g., Grad-CAM) is one of the most classical and widely adopted explainable artificial intelligence (XAI) methods for its simplicity and efficiency. It can be used to interpret deep neural networks by locating saliency areas contributing the most to their predictions. However, it is difficult to automatically measure and evaluate the performance of SRV methods due to the lack of ground-truth salience areas of samples. In this paper, we revisit the backdoor-based SRV evaluation, which is currently the only feasible method to alleviate the previous problem. We first reveal its implementation limitations and unreliable nature due to the trigger generalization of existing backdoor watermarks. Given these findings, we propose a generalization-limited backdoor watermark (GLBW), based on which we design a more faithful XAI evaluation. Specifically, we formulate the training of watermarked DNNs as a min-max problem, where we find the 'worst' potential trigger (with the highest attack effectiveness and differences from the ground-truth trigger) via inner maximization and minimize its effects and the loss over benign and poisoned samples via outer minimization in each iteration. In particular, we design an adaptive optimization method to find desired potential triggers in each inner maximization. Extensive experiments on benchmark datasets are conducted, verifying the effectiveness of our generalization-limited watermark. Our codes are available at https://***/yamengxi/GLBW. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Geometric Latent Diffusion Model for Graph Generation 41

Hyperbolic Geometric Latent Diffusion Model for Graph Genera...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Fu, Xingcheng Gao, Yisen Wei, Yuecen Sun, Qingyun Peng, Hao Li, Jianxin Li, Xianxian Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Institute of Artificial Intelligence Beihang University Beijing China School of Software Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University Beijing China

Diffusion models have made significant contributions to computer vision, sparking a growing interest in the community recently regarding the application of them to graph generation. Existing discrete graph diffusion models exhibit heightened computational complexity and diminished training efficiency. A preferable and natural way is to directly diffuse the graph within the latent space. However, due to the non-Euclidean structure of graphs is not isotropic in the latent space, the existing latent diffusion models effectively make it difficult to capture and preserve the topological information of graphs. To address the above challenges, we propose a novel geometrically latent diffusion framework HypDiff. Specifically, we first establish a geometrically latent space with interpretability measures based on hyperbolic geometry, to define anisotropic latent diffusion processes for graphs. Then, we propose a geometrically latent diffusion process that is constrained by both radial and angular geometric properties, thereby ensuring the preservation of the original topological properties in the generative graphs. Extensive experimental results demonstrate the superior effectiveness of HypDiff for graph generation with various topologies. Copyright 2024 by the author(s)

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Our Way to Better Classifiers: Leveraging Synthetic data with Generative Models for Encrypted Network Traffic Classification

SSRN

引用

SSRN 2023年

作者： Zion, Yehonatan Hajaj, Chen Dvir, Amit Artzi, Gil Ben Mahpod, Shahar Dubin, Ran Department of Computer Science Ariel University Ariel Cyber Innovation Center Israel Department of Industrial Engineering & Management Data Science and Artificial Intelligence Research Center Ariel University Israel

Encrypted traffic classification has become a popular research topic due to the fact that it plays a vital part in Quality of Service (QoS), Quality of Experience (QoE), and network security. Moreover, by using ML-based and DL-based classification, it is possible to provide information without the need to decrypt it. While recent works have shown great innovation and contribution to the field, there is still a significant problem when it comes to the datasets in use. Most researchers use well-known open-source datasets that suffer from a lack of diversity (i.e., low number of classes or samples per class), which are quite often imbalanced. This paper aims to answer the question, "Is it possible to solve these datasets’ limitations by using generative models?" Specifically, we provide a survey of some known solutions in the field of generative models, assess their fit to the encrypted traffic classification domain, and evaluate their contribution to balancing the datasets and improving the classification metrics of different classifiers. Another contribution of this paper lies in the fact that we do not limit ourselves to the natural representation of network traffic as a time series. Since generative adversarial models (GANs) have proven to be very effective in the image processing domain, we transform the raw traffic data into an image representation of the signal. Our initial results, reported in this paper, show the applicability of such methods to an improvement of more than 30% in the accuracy of a network classification model by including synthetic samples generated by the GANs in their training set. © 2023, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

ASGEA: Exploiting Logic Rules from Align-Subgraphs for Entity Alignment

arXiv

引用

arXiv 2024年

作者： Luo, Yangyifei Chen, Zhuo Guo, Lingbing Li, Qian Zeng, Wenxuan Cai, Zhixin Li, Jianxin School of Computer Science and Engineering Beihang University China College of Computer Science and Technology Zhejiang University China Bejing Advanced Innovation Center for Big Data and Brain Computing Beihang University China

Entity alignment (EA) aims to identify entities across different knowledge graphs that represent the same real-world objects. Recent embedding-based EA methods have achieved state-of-the-art performance in EA yet faced interpretability challenges as they purely rely on the embedding distance and neglect the logic rules behind a pair of aligned entities. In this paper, we propose the Align-Subgraph Entity Alignment (ASGEA) framework to exploit logic rules from Align-Subgraphs. ASGEA uses anchor links as bridges to construct Align-Subgraphs and spreads along the paths across KGs, which distinguishes it from the embedding-based methods. Furthermore, we design an interpretable Path-based Graph Neural Network, ASGNN, to effectively identify and integrate the logic rules across KGs. We also introduce a node-level multi-modal attention mechanism coupled with multi-modal enriched anchors to augment the Align-Subgraph. Our experimental results demonstrate the superior performance of ASGEA over the existing embedding-based methods in both EA and Multi-Modal EA (MMEA) tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Computer circuits

来源：评论

学校读者我要写书评

暂无评论

Small Object Detection Algorithm for Unmanned Aerial Vehicle Based on Multifaceted Feature Information Extraction and Fusion

Small Object Detection Algorithm for Unmanned Aerial Vehicle...

引用

International Symposium on Computer science and Intelligent Controls (ISCSIC)

作者： Shasha Yin Yueran Ge Lingling Tian School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin China Control Engineering Technology Innovation Center of Hebei Province Hebei University of Technology Tianjin China

ISBN: (数字)9798350380286

ISBN: (纸本)9798350380293

Unmanned Aerial Vehicle (UAV) image object detection has been widely applied in security and disaster relief and other aspects. For the sake of solving the problem of many small objects, this paper proposes a Multifaceted feature information extraction and fusion algorithm (MFIEF). Firstly, the multi-information feature extraction convolution module (MFECM) is adopted, which retains more small object feature information and surrounding spatial information. Secondly, the optimized FPN structure (OFPN) is used, the fusion of horizontal and vertical information avoids the loss of information, and the addition of lightweight attention convolution module (LACM) reduces the number of parameters while improving attention to key object information. The experimental results on the VisDrone datasets demonstrate that the MFIEF algorithm achieves a obvious improvement in performance compared to the benchmark algorithm. Specifically, the mAP@0.5 value of MFIEF is 9.7 percentage points higher, while the mAP@0.5:0.95 value of MFIEF is 6.7 percentage points higher than the benchmark algorithm. These findings highlight the superior performance of MFIEF in object detection tasks on the VisDrone datasets.

关键词： YOLO Accuracy Convolution Benchmark testing Feature extraction Autonomous aerial vehicles Information retrieval Real-time systems Security Intelligent control

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：