检索结果-内蒙古大学图书馆

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Shi, Yujie Wang, Yongli Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798350330717

While fusing label outputs from multiple classification models, simply averaging the results can no longer meet the needs of accuracy in use, so probability-based methods, such as D-S Evidence Theory, Bayesian Models, etc., are used to fuse and fix the outcome vectors from the models. The traditional D-S Evidence Theory has a good interpretability, but faces the problems of invalidation or distortion of results because of conflicting evidences. Existing works always focus on the weights calculated by evidences, however, the analysis of evidence sources, namely the classification models in our case, are ignored in those methods. Therefore, A novel label fusion method based on D-S Evidence Theory that adds subjective weights on the basis of former works is proposed in this paper. The prior knowledge can be shown in the fusion result by comprehensively analyzing subjective and objective parameters, e.g. evidence distributions, evidence sources and even application environments. The experiments proved that our method can effectively handle highly conflicting evidences, the label probability distribution is more concentrated, meaning the uncertainty of the result is lower and the accuracy is higher than other methods. © 2023 IEEE.

关键词： conflict evidence D-S Evidence Theory label fusion subjective weight

来源：评论

学校读者我要写书评

暂无评论

Topology-Aware Debiased Self-Supervised Graph Learning for Recommendation

Topology-Aware Debiased Self-Supervised Graph Learning for R...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Han, Lei Yan, Hui Qiao, Zhicheng School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9798350337020

In recommendation, graph-based Collaborative Filtering (CF) methods mitigate the data sparsity by introducing Graph Contrastive Learning (GCL). However, the random negative sampling strategy in these GCL-based CF models neglects the semantic structure of users (items), which not only introduces false negatives (negatives that are similar to anchor user (item)) but also ignores the potential positive samples. To tackle the above issues, we propose Topology-aware Debiased Self-supervised Graph Learning (TDSGL) for recommendation, which constructs contrastive pairs according to the semantic similarity between users (items). Specifically, since the original user-item interaction data commendably reflects the purchasing intent of users and certain characteristics of items, we calculate the semantic similarity between users (items) on interaction data. Then, given a user (item), we construct its negative pairs by selecting users (items) which embed different semantic structures to ensure the semantic difference between the given user (item) and its negatives. Moreover, for a user (item), we design a feature extraction module that converts other semantically similar users (items) into an auxiliary positive sample to acquire a more informative representation. Experimental results show that the proposed model outperforms the state-of-the-art models significantly on three public datasets. Our model implementation codes are available at https://***/malajikuai/TDSGL. © 2023 IEEE.

关键词： collaborative filtering contrastive learning false negatives recommender system

来源：评论

学校读者我要写书评

暂无评论

Construction of Semantic Point Cloud Based on Dynamic Object Recognition 5

Construction of Semantic Point Cloud Based on Dynamic Object...

引用

5th International Conference on Robotics and computer Vision, ICRCV 2023

作者： Cheng, Lei Sun, Tian Hu, Yaqi Liu, Yong School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9798350326369

Simultaneous localization and mapping (SLAM) is considered to be a fundamental function of intelligent mobile robots. However, some V-SLAM algorithms lack robustness in dynamic environments for the reason of the strong assumption of static world. Meanwhile, these algorithms are relatively simple to map dynamic objects, which generates error images and leads to map clutter. In this paper, we develop a semantic RGBD SLAM system. The system uses object detection and priori semantics, for high-precision localization and accurate scene reconstruction. Firstly, we introduce a dynamic object detection method that combines geometric computation and semantics. Secondly, by using detection and semantics, dynamic feature points are removed to optimize camera poses for improving the accuracy of trajectory estimation and reconstructing dynamic dense point clouds. Finally, we evaluate the SLAM system in public datasets environments. The results show that our system can achieve precise localization in dynamic environments while building a clear dynamic semantic point cloud map. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

FDRS: Federated Diversified Recommender System Based on Heterogeneous Graph Convolutional Network 25

FDRS: Federated Diversified Recommender System Based on Hete...

引用

25th IEEE International Conferences on High Performance Computing and Communications, 9th International Conference on Data science and Systems, 21st IEEE International Conference on Smart City and 9th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC/DSS/SmartCity/DependSys 2023

作者： Li, Nianzhe Liu, Hanwen Meng, Shunmei Li, Qianmu School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9798350330014

Currently, researchers are working to improve the accuracy of recommender systems. However, recommender systems ignore users' diversity requirements in recommendation lists, thus reducing user satisfaction. Additionally, in the big data environment, users' data information is scattered in different enterprises or organizations, but these enterprises or organizations are reluctant to share users' data information due to the existing laws and regulations, which leads to the recommendation process facing the problem of the sparsity of users' available data. Based on the above research, we propose a novel framework of a federated diversified recommender system, i.e., FDRS, which is a diversified recommendation method following the principle of vertical federation learning. Specifically, FD RS first constructs a heterogeneous users-items graph, then uses a heterogeneous graph convolutional network to learn user representations based on heterogeneous information, and finally, based on vertical federation learning, FDRS performs model parameter aggre-gation, rating prediction, and diversity recommendation. We compare our approach with existing recommendation methods on the Epinions dataset. The experimental results show that our proposal greatly alleviates the accuracy and diversity dilemmas while preserving data privacy. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Run Away from the Original Example and Towards Transferability

Run Away from the Original Example and Towards Transferabili...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Yang, Rongbo Li, Qianmu Meng, Shunmei School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9798350337020

Transfer-based attacks against black-box neural network models have received increasing attention because they are more realistic scenarios, but how to produce highly transferable adversarial examples on the surrogate model becomes critical. In this work, we find that if the attack direction of the original example is controlled from the beginning, the produced adversarial examples will be more transferable. Specifically, we propose the Output Direction Controller (ODC) to initialize the example direction so that the example starts off with a deviation from the true direction or toward the target direction. ODC is a simple and extensible component that can be combined with various transfer-based attack methods and significantly improve the transferability of the adversarial examples. On the ImageNet dataset, we optimize the baseline method by ODC to improve the success rate of untargeted attacks by an average of 11.79% and targeted attacks by an average of 3.38%. Code is available at https://***/yangrongbo/ODC. © 2023 IEEE.

关键词： Adversarial Examples Output Direction Controller Transferability

来源：评论

学校读者我要写书评

暂无评论

Time-Graph Adjustive Graph Convolutional Recurrent Network for Traffic Forecasting

Time-Graph Adjustive Graph Convolutional Recurrent Network f...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Qingyuan, Shao Hui, Yan Yuxin, Chen School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9798350337020

Traffic forecasting is a crucial undertaking in the transportation domain. Current practices rely heavily on Recurrent Neural Networks (RNNs) and Temporal Convolutional Networks (TCNs) to model temporal dependencies in traffic forecasting. However, these approaches tend to overlook the interdependence of multi-hop time steps, impeding their ability to capture long-term dependencies and ultimately limiting their effectiveness in long-term forecasting. To address this issue, we present a novel method, the Time-Graph Adjustive Graph Convolutional Recurrent Network (TAGRN), for traffic forecasting. Our approach employs a Time-Graph model on the temporal domain, treating each time step of the traffic series as a graph node. We incorporate the similarity between time steps as weighted edges, enabling the Time-Graph to capture correlations between multi-hop time steps and model long-term dependencies through graph convolution. We utilize the Simple Graph Convolution (SGC) technique for information propagation due to its simplicity, linearity, and efficiency. Additionally, we introduce an adaptive semantic graph to enhance the capture of spatial information on the spatial domain. Experimental results on various real traffic datasets demonstrate the effectiveness of our proposed method. Compared to existing approaches, TAGRN achieves superior performance in long-term traffic forecasting, highlighting its potential for practical applications. The code is available at https://***/sqy123qwer/TAGRN. © 2023 IEEE.

关键词： graph convolutional network spatial-temporal data traffic forecasting

来源：评论

学校读者我要写书评

暂无评论

Cross-contrast Fusion and Aggregation Network for Multi-contrast MRI Super-resolution 23

Cross-contrast Fusion and Aggregation Network for Multi-cont...

引用

9th International Conference on Computing and Artificial Intelligence, ICCAI 2023

作者： Ding, Yue Zhou, Tao Wu, Ye School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9781450399029

Magnetic resonance imaging (MRI) super-resolution (SR) can restore high-quality high-resolution (HR) images from low-resolution (LR) ones, which is helpful for clinical diagnosis and treatment. Different from SR restoration using a single-contrast, multi-contrast SR restoration has received increasing attention because different modalities can provide complementary information to improve the SR quality. However, fusing multi-contrast features as well as capturing cross-level correlations among different layers are still challenging. In this paper, we propose a Cross-contrast Fusion and Aggregation Network (CFA-Net) for multi-contrast MRI super-resolution, which can effectively explore complementary information from multi-contrast images to improve target-image SR quality. Specifically, the multi-contrast images are passed through multiple residual Swin Transformer blocks (RSTB) to learn hierarchical feature representations at different layers. Then, we present a Cross-contrast Fusion Module (CFM) to fuse the cross-contrast features in a layer-wise strategy, which can capture the complementary information from multi-contrast MR images. Moreover, a cross-level Feature Aggregation Module (FAM) is proposed to integrate cross-level features from CFMs for exploring the interaction between different layers. Experimental results on three multi-contrast MR datasets demonstrate that our method performs better than other state-of-the-art SR methods. © 2023 Copyright held by the owner/author(s).

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Towards Interpretable Machine-Learning-Based DDoS Detection

引用

SN computer science 2024年第1期5卷 115页

作者： Zhou, Qianru Li, Rongzhen Xu, Lei Nallanathan, Arumugam Yang, Jian Fu, Anmin School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Electronic Engineering and Computer Science Queen Mary University of London London E1 4NS United Kingdom

The Internet is the most complex machine humankind has ever built, and thus, it is difficult to defend it from attacks. The most common attack to the Internet is DDoS attacks. With the growing popularity for QUIC protocol, DDoS detection tasks are increasingly rely on machine learning (ML), which is based on black-box model and cannot explain its decision. A interpretable and transparent ML model is the foundation of a trustworthy ML-based DDoS attack detection. Current ML interpretation methodologies in cyber intrusion detection are heuristic, which is neither accurate nor sufficient. This paper proposed a rigorous interpretable ML-driven omnipotent DDoS detection approach, based on knowledge compilation technologies. Details of rigorous interpretation calculation process for the ML model are presented, which include an accelerated prime implicant calculation method driven by knowledge compilation for the DDoS detection ML model, and a map, combine, and merge (M &M) algorithm to discretize continuous features into Boolean expression. The proposed Prime implicant reasons calculation algorithm has been tested on a DDoS LOIC and HOIC attack detection ML model with 100% accuracy, trained with real-life DDoS data. An exhaust list of explanations are given in detail as rules for the omnipotent DDoS intrusion detection learnt by the ML model used. As the ML interpretation method is an SAT problem-solving process, the explanations are rigorous and sufficient reasons for the ML model for DDoS attack detection, and are believed to shade light on DDoS detection research work in cybersecurity community. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： DDoS attack Explainable artificial intelligence Intrusion detection system Knowledge compilation Prime implicate

来源：评论

学校读者我要写书评

暂无评论

MA-Net: Multi-Scale Adaptive Network for Oriented Object Detection in Remote Sensing Images

MA-Net: Multi-Scale Adaptive Network for Oriented Object Det...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Pan, Jiahao Zhang, Chongyang School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9798350337020

The remote sensing image detection task faces significant challenges, e.g. complex background, dense distribution, widely varied target scale, and diverse target directions. This paper proposes a remote sensing image Oriented object detection network (MA-Net) that integrates parallel multi-scale feature extraction and adaptive dynamic label assignment. The network is based on the FCOS object detection algorithm, which introduces a parallel multi-scale feature extraction module to enhance the model's understanding of multi-scale objects. The adaptive dynamic label assignment algorithm is introduced to enable the model to select samples that are more worthy of learning. According to the number of positive samples at different levels, hierarchical supervision reweighting is used to help the model focus on more important levels and improve detection accuracy. Experiments are conducted on two public datasets, DOTA and HRSC2016. Compared with the original FCOS algorithm, the detection accuracy of our algorithm was improved by 2.45% and 4.44%. And its performance is comparable to that of state-of-the-art detection methods. © 2023 IEEE.

关键词： Label assignment Object detection Remote sensing images

来源：评论

学校读者我要写书评

暂无评论

Contour Refinement for Box Based Interactive Object Segmentation

Contour Refinement for Box Based Interactive Object Segmenta...

引用

2023 International Conference on Communications, Computing and Artificial Intelligence, CCCAI 2023

作者： Ma, Jing Shi, Ran Shen, Xiaobo Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China

ISBN: (纸本)9798350311297

As the development of interactive object segmentation, the optimization of the segmented contour draws much attention. Inspired by current interactive object segmentation and contour-based methods, this paper proposes an end-to-end framework for contour refinement for box based interactive object segmentation. Compared with traditional interactive object segmentation approaches, our method not only constrains the scope of segmentation in terms of region, but also controls and optimizes the deformational results of the contour, which achieves the goal of refined interactive object segmentation. We build a complete system including a contour extraction model and a contour deformation model. The initial contour extracted from the result of segmentation by the contour extraction model is fed to the contour deformation model for vertices offset and contour deformation. Meanwhile, we perform dynamic dilation for the initial contour before contour refinement to improve the feature information provided by the contour extraction model. In addition, we put the compactness of each contour as a reference factor into the point set sampled on the contour to solve the problem of over-sharp boundary. Experiments show that the proposed method achieves advanced performance for interactive object segmentation. © 2023 IEEE.

关键词： Extraction

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：