检索结果-内蒙古大学图书馆

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

作者： Song, Haohao Xiang, Qiao Shu, Jiwu Institute of Artificial Intelligence Xiamen University China Xiamen Key Laboratory of Intelligent Storage and Computing School of Informatics Xiamen University China Minjiang University China

ISBN: (纸本)9798350368741

Label noise model is a technique to construct controlled noisy datasets for evaluating noise-robust algorithms. However, the quality of the generated noise has not been evaluated thoroughly. In this paper, we propose a novel research question: Do the constructed datasets with the same noise rate have equal effects? We answer this question through a carefully designed experiment: We sequentially generate a series of noisy datasets with equal noise rate by excluding the previous noisy samples while controlling the clean samples. Models trained on these datasets show discrepancy generalization performance, indicating the inequality of noise. Our in-depth analysis reveals that the reasons come from (1) the introduction of non-hard samples and (2) the inequality between hard samples. We propose a primary equal-quality instance-dependent label noise model termed EQ-IDN, which alleviates both issues based on the identification of hard samples and stratified sampling. We compare the noise quality generated by EQ-IDN and other models. Experimental results demonstrate that the noise generated by EQ-IDN has lower difference and more stable quality. © 2025 IEEE.

关键词： label noise quality

来源：评论

学校读者我要写书评

暂无评论

P4GCN: Vertical Federated Social Recommendation with Privacy-Preserving Two-Party Graph Convolution Network 25

P4GCN: Vertical Federated Social Recommendation with Privacy...

引用

34th ACM Web Conference, WWW 2025

作者： Wang, Zheng Wang, Wanwan Huang, Yimin Peng, Zhaopeng Yang, Ziqi Yao, Ming Wang, Cheng Fan, Xiaoliang Fujian Key Laboratory of Sensing and Computing for Smart Cities School of Informatics Xiamen University Xiamen China Insightone Tech Co. Ltd Beijing China

ISBN: (纸本)9798400712746

In recent years, graph neural networks (GNNs) have been commonly utilized for social recommendation systems. However, real-world scenarios often present challenges related to user privacy and business constraints, inhibiting direct access to valuable social information from other platforms. While many existing methods have tackled matrix factorization-based social recommendations without direct social data access, developing GNN-based federated social recommendation models under similar conditions remains largely unexplored. To address this issue, we propose a novel vertical federated social recommendation method leveraging privacy-preserving two-party graph convolution networks (P4GCN) to enhance recommendation accuracy without requiring direct access to sensitive social information. First, we introduce a Sandwich-Encryption module to ensure comprehensive data privacy during the collaborative computing process. Second, we provide a thorough theoretical analysis of the privacy guarantees, considering the participation of both curious and honest parties. Extensive experiments on four real-world datasets demonstrate that P4GCN outperforms state-of-the-art methods in terms of recommendation accuracy. © 2025 Copyright held by the owner/author(s).

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Secure IIoT networks with hybrid CNN-GRU model using Edge-IIoTset 15

Secure IIoT networks with hybrid CNN-GRU model using Edge-II...

引用

15th International Conference on Innovations in Information Technology, IIT 2023

作者： Saadouni, Rafika Khacha, Amina Harbi, Yasmine Gherbi, Chirihane Harous, Saad Aliouat, Zibouda Ferhat Abbas University of Setif 1 LRSD Laboratory Setif Algeria University of Sharjah College of Computing and Informatics Sharjah United Arab Emirates

ISBN: (纸本)9798350382396

Industrial Internet of Things (IIoT), or Industry 4.0, is an application of IoT in the industrial sector. Its main objective is to enhance product quality and optimize production costs by leveraging advanced technologies such as edge/fog/cloud computing, 5G/6G, and artificial intelligence. In the context of Industry 4.0, numerous devices and systems are interconnected to provide seamless services to users. However, with this interconnection comes the need to protect these devices and the information they transmit from cyberthreats and intrusions. In order to tackle this challenge, our proposed solution involves the utilization of deep learning (DL) models to develop an anomaly-based detection system. Our approach involves two powerful DL models, namely Convolutional Neural Networks (CNN) and Gated Recurrent Units (GRU). The proposed model's performance is studied within binary and multiclass classification using a new real-world industrial traffic dataset called Edge-IIoTset. The outcomes of our experiments showcased the efficacy of the CNN-GRU model that we proposed, surpassing the performance of recent related works in terms of performance metrics, including accuracy, precision, false positive rate, and detection cost. The combination of the two models CNN and GRU outperforms the GRU model with 88% of detection cost in multiclass classification for one traffic flow. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Integrative Analysis of Open Datasets for Stress Prediction

引用

Journal of Medical and Biological Engineering 2025年 1-15页

作者： Ladakis, Ioannis Fotopoulos, Dimitris Chouvarda, Ioanna Laboratory of Computing Medical Informatics and Biomedical—Imaging Technologies School of Medicine Aristotle University of Thessaloniki Thessaloniki Greece

Stress is the physiological or psychological response to internal or external stressors. By causing physiological and behavioral changes, persistent stress affects psychological and physiological functionality, potentially reducing the quality of life. Therefore, it is of great interest to systematically monitor individuals daily to investigate their physiological reactions to potential stressors. The aim of this study is to investigate the potential of training reliable and accurate ML and DL models for the prediction of acute stress based on available open datasets. The open datasets include physiological signals collected using wearable sensors during stress characterization experiments and made available to the public. Various machine and deep learning (ML/DL) models were tested and compared based on their accuracy (ACC). Harmonizing techniques were also included to increase the generalizability of the models and reduce their dependence on sensors and experimental protocols variations. The models achieved test-set accuracies over 80% for different classification problems, while the combination of the available data led to more accurate models for the binary classification problem (over 90%). Harmonizing differences between participants and datasets led to more generalizable models with encouraging initial results (around 70% accuracy) when evaluated with unseen subjects. The extracted models can all be used depending on the classification problem and the experimental settings/protocols. All models could play a significant role towards forming and developing a stress prediction ‘service’, taking into account the impact of using different sensors, and, thus, having to proceed to required adjustments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Intrusion Detection for IoT Networks: An Integrated CNN-LSTM-GRU Approach 6

Robust Intrusion Detection for IoT Networks: An Integrated C...

引用

6th International Conference on Networking and Advanced Systems, ICNAS 2023

作者： Khacha, Amina Saadouni, Rafika Harbi, Yasmine Gherbi, Chirihane Harous, Saad Aliouat, Zibouda Ferhat Abbas University of Setif 1 LRSD Laboratory Setif Algeria College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates

ISBN: (纸本)9798350319170

Ensuring IoT security is of utmost importance in today's interconnected world. IoT devices are prone to various security threats and vulnerabilities, making it essential to implement robust security measures. Intrusion detection plays an instrumental role in safeguarding network information security. However, traditional machine learning techniques face challenges when dealing with large volumes of data and diverse intrusion classes. Consequently, their detection accuracy becomes inadequate, especially when encountering unknown or novel intrusions. In this paper, we introduce a novel Intrusion Detection System (IDS) using Deep Learning (DL) models. The proposed system integrates three powerful DL models, namely Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRU). Different combination sequences are presented to enhance the system's performance in detecting intrusions by leveraging the strengths of each model. We utilized two datasets: Edge-IIoTset that accurately depicts a network traffic environment consisting of IoT and IIoT applications, and NSL KDD that contains simulated non-real traffic data. We employed several metrics, including accuracy, precision, false positive rate, and detection cost, to assess the system's performance. The experimental results show that our model achieves a perfect accuracy of 100% using Edge-IIoTset in binary classification and an accuracy of 99.95% using the NSL-KDD dataset in multi-class classification. Furthermore, it has an improved detection cost compared to single LSTM and GRU models. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A LoRa-Based Emotion Estimation Scheme for Smart Home Automated Actions Using ELMs 8

A LoRa-Based Emotion Estimation Scheme for Smart Home Automa...

引用

8th IEEE International Smart Cities Conference, ISC2 2022

作者： Karras, Christos Karras, Aristeidis Drakopoulos, Georgios Tsolis, Dimitrios Mylonas, Phivos Sioutas, Spyros Decentralized Systems Computing Group University of Patras Computer Engineering and Informatics Department Greece Ionian University Humanistic and Social Informatics Laboratory Department of Informatics Greece

ISBN: (数字)9781665485616

ISBN: (纸本)9781665485616

Emotion detection is crucial in many IoT deployments from an operational perspective with examples ranging from digital health to smart cities. This is particularly true in smart homes where the interaction between the local IoT ecosystem and the inhabitants are continuous, pervasive, and nuanced. More specifically, emotion estimation from human speech attributes is an integral architectural component of such ecosystems. In this work, we survey the emerging LPWAN technologies and after selecting the most optimal for our use-case, we propose an emotion estimation scheme based on LoRa wireless technology for automated actions in smart home environments. In particular, a voice recognition module coupled with a transmitter are installed in a car. Then, depending on the estimation outcome, the smart home may undertake one or more preemptive actions according to its configuration as the car passenger approaches. The prototype LoRa system has been tested with the widely-used TESS dataset with encouraging results as expressed in the emotion confusion matrix obtained from a extreme learning machine with various kernels. The preceding paves the way for adaptive smart homes tailored to the needs of their inhabitants. © 2022 IEEE.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Diverse Consensuses Paired with Motion Estimation-Based Multi-Model Fitting 24

Diverse Consensuses Paired with Motion Estimation-Based Mult...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Yin, Wenyu Lin, Shuyuan Lu, Yang Wang, Hanzi Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen University Xiamen China Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University Xiamen China College of Cyber Security College of Information Science and Technology Jinan University Guangzhou China

ISBN: (纸本)9798400706868

Multi-model fitting aims to robustly estimate the parameters of various model instances in data contaminated by noise and outliers. Most previous works employ only a single type of consensus or implicit fusion model to represent the correlation between data points and model hypotheses. This approach often results in unrealistic and incorrect model fitting in the presence of noise and uncertainty. In this paper, we propose a novel method of diverse Consensuses paired with Motion estimation-based multi-Model Fitting (CMMF), which leverages three types of diverse consensuses along with inter-model collaboration to enhance the effectiveness of multi-model fusion. We design a Tangent Consensus Residual Reconstruction (TCRR) module to capture motion structure information of two points at the pixel level. Additionally, we introduce a Cross Consensus Affinity (CCA) framework to strengthen the correlation between data points and model hypotheses. To address the challenge of multi-body motion estimation, we propose a Nested Consensus Clustering (NCC) strategy, which formulates multi-model fitting as a motion estimation problem. It explicitly establishes motion collaboration between models and ensures that multiple models are well-fitted. Extensive quantitative and qualitative experiments are conducted on four public datasets (i.e., AdelaideRMF-F, Hopkins155, KITTI, MTPV62), and the results demonstrate that our proposed method outperforms several state-of-the-art methods. © 2024 ACM.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Spam Review Detection in E-Commerce Using Machine Learning 6

Spam Review Detection in E-Commerce Using Machine Learning

引用

6th IEEE International Conference on Artificial Intelligence in Engineering and Technology, IICAIET 2024

作者： Rizali, Muhammad Na'im Rosli, Marshima Mohd Abdullah, Nur Atiqah Sia College of Computing Informatics & Mathematics Universiti Teknologi Mara Selangor 40450 Malaysia Institute for Pathology Laboratory and Forensic Medicine University Teknologi Mara Selangor Sungai Buloh47000 Malaysia

ISBN: (纸本)9798350389692

Reviews pose a significant challenge for e-commerce platforms that rely on online reviews to attract customers. The reviews may contain spam that resembles actual genuine reviews while current spam detection methods lack integration of linguistic and behavioural features. In this study, we propose a machine learning-based approach for detecting spam reviews using classification techniques. We explore various feature extraction methods, including n-grams and sentiment analysis, to represent the textual content of reviews. We evaluate the performance of three classifiers, including Support Vector Machines (SVM), Random Forest, and Naive Bayes, on a dataset of Shopee reviews. Our results show that SVM performs the best in terms of accuracy, precision, and recall, achieving an F1-score of 0.96. We also investigate the impact of different feature extraction methods on classification performance and find that sentiment analysis provides valuable information for detecting spam reviews. Our approach offers a promising solution for automatically identifying spam reviews, which can help e-commerce to maintain the integrity of their online reputation and enhance customer trust. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Learning to Reconnect Interrupted Trajectories for Weakly Supervised Multi-Object Tracking 48

Learning to Reconnect Interrupted Trajectories for Weakly Su...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Li, Yu-Lei Lu, Yang Li, Jie Wang, Hanzi Xiamen University Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics China Xidian University Video and Image Processing System Laboratory School of Electronic Engineering China

ISBN: (纸本)9781728163277

Recently, some weakly supervised multi-object tracking (MOT) methods learn identity embedding features with pseudo identity labels rather than the high-cost manual ones. However, these pseudo identity labels may contain many false or missing identities, which adversely affect the optimization of tracking networks, resulting in interrupted trajectories of occluded targets. To effectively reconnect the interrupted trajectories caused by noisy pseudo labels, we propose a novel weakly supervised MOT method based on a Trajectory-Reconnecting Transformer (TRTMOT). TRT-MOT performs feature decoupling to extract discriminative embedding features for reconnecting trajectories of occluded targets. Experimental results show that TRTMOT outperforms previous weakly supervised MOT methods by at least +3.6 and +5.6 on MOTA for the MOT17 and MOT20 datasets, respectively. © 2023 IEEE.

关键词： Feature Decoupling Pseudo Identity Labels Trajectory-Reconnecting Transformer Weakly Supervised Multi-Object Tracking

来源：评论

学校读者我要写书评

暂无评论

Identity-Based Signature from Lattices Without Trapdoors 26th

Identity-Based Signature from Lattices Without Trapdoors

引用

26th International Conference on Information and Communications Security, ICICS 2024

作者： Luo, Pingbin Chen, Xinjian Susilo, Willy Huang, Qiong College of Mathematics and Informatics South China Agricultural University Guangzhou China Guangzhou Key Laboratory of Intelligent Agriculture Guangzhou510642 China School of Computing and Information Technology University of Wollongong Wollongong Australia

ISBN: (纸本)9789819788002

Currently, the majority of lattice-base identity-based signature (LB-IBS) schemes rely on lattice trapdoor technique introduced by Gentry, Peikert, and Vaikuntanathan. However, this approach significantly impacts computational efficiency. In light of this, we present an alternative method for constructing LB-IBS that does not rely on lattice trapdoors and preimage sampling function. We construct an IBS scheme by employing Lyubashevsky’s signature twice, which is essentially a public key delegation from concatenated Schnorr signatures. In order to optimize the signature size, we describe an adaptation of our scheme in module lattices setting and compression technique. Moreover, our new LB-IBS can combine with Dilithium naturally so that it could carry the advantages of the latter such as side-channel attacks protection. We demonstrate that our construction is provably secure against existential forgery on adaptively chosen message and identity attacks in random oracle model. In comparison with the most efficient LB-IBS scheme (to the best of our knowledge), the signature size of our scheme is 52% smaller and runtime of our scheme is up to 32% faster. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Quantum cryptography

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：