检索结果-内蒙古大学图书馆

10th IEEE Conference on Big data Security on Cloud, BigdataSecurity 2024

作者： Xu, Wenjing Song, Yulun Liang, Haochen Sun, Lin Xie, Yunlong Unicom Digital Tech Data Intelligence Department Beijing100081 China Beijing Institute of Technology School of Cyberspace Science and Technology Beijing100081 China Yangtze Delta Region Academy of Beijing Institute of Technology Zhejiang Jiaxing314000 China

ISBN: (纸本)9798350389524

Interconnected systems have given rise to a surge in data sharing among multiple organizations, highlighting the growing necessity for cross-organizational collaboration. However, due to a lack of trust, there are security concerns due to different organizations located in different security and privacy legislative jurisdictions and culture. On the other hand, an organization may have many different departments or sub companies, all using one identity to conduct data sharing and exchanging may cause management confusion and unclear responsibilities. Therefore, in a data sharing system, people should introduce strengthened but efficient identity control mechanisms to provide fine-grained cross organizational data access and exchange requests. Due to higher security costs, modern identity control schemes typically focus on protecting a single target rather than multiple parties, and multiple parities always have a strong demand to connect other systems. In this article, we present a blockchain-based identity control scheme aimed at promoting lightweight data sharing among diverse organizations. Furthermore, we have conducted a comprehensive evaluation of the system model to confirm the efficacy of the proposed scheme presented in this paper. © 2024 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Sentiment Analysis Methods for Detecting Fake Reviews in E-Commerce

HighTech and Innovation Journal

引用

HighTech and Innovation Journal 2023年第2期4卷 349-363页

作者： Puttarattanamanee, Maneerat Boongasame, Laor Thammarak, Karanrat KMITL-Digital Analytics and Intelligence Center Faculty of Science King Mongkut’s Institute of Technology Ladkrabang Bangkok10520 Thailand Department of Mathematics Faculty of Science King Mongkut’s Institute of Technology Ladkrabang Bangkok10520 Thailand Business Innovation and Investment Laboratory: B2I-Lab School of Science King Mongkut’s Institute of Technology Ladkrabang Bangkok10520 Thailand Department of Computer Engineering and Electronics School of Engineering and Technology Walailak University Nakhon Si Thammarat80160 Thailand

The popularity of the e-commerce system has increased, especially under the COVID scenario. Consumer product reviews from the past have had a significant impact on influencing consumers' purchasing decisions. Fake reviews—those written by humans and computers that engage in dishonest behavior—are consequently generated to increase product sales. The fake reviews hurt consumers and are dishonest. The goal of this research is to examine and evaluate the performance of various methods for identifying fake reviews. The well-known and widely-used Amazon Review data (2018) dataset was used for this research. The first 10 product categories on *** with favorable feedback will be provided in the data section. After that, perform fundamental data preparation procedures such as special character trimming, bag of words, TF-IDF, etc. The models are trained to create a dataset for detecting fake reviews. This research compares the performance of four different models: GPT-2, NBSVM, BiLSTM, and RoBERTa. The hyperparameters of the models are also tuned to find the optimal values. The research concludes that the RoBERTa model performs the best overall, with an accuracy of 97%. GPT-2 has an overall accuracy of 82%, NBSVM has an overall accuracy of 95%, and BiLSTM has an overall accuracy of 92%. The research also calculates the Area Under the Curve (AUC) for each model and finds that RoBERTa has an AUC of 0.9976, NBSVM has an AUC of 0.9888, BiLSTM has an AUC of 0.9753, and GPT-2 has an AUC of 0.9226. It can be observed that the RoBERTa model has the highest AUC value, which is close to 1. Therefore, it can be concluded that this model provides the most accurate prediction for detecting fake reviews, which is the main focus of this research. © 2023, Ital Publication. All rights reserved..

关键词： Fake detection

来源：评论

学校读者我要写书评

暂无评论

Efficient Approach Towards Detection and Classification for Image Forgery by Using Machine Learning Technique 3

Efficient Approach Towards Detection and Classification for ...

引用

3rd IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2023

作者： Hussein, Abbas Hameed Abdul Kavitha, R. Kumar, Bura Vijay Issa, Ali Ashoor Al-Attabi, Kassem College of Pharmacy Ahl Al Bayt University Karbala Iraq Department of ECE Tiruchengode India School of Computer Science and Artificial Intelligence SR University Telangana Warangal India National University of Science and Technology Dhi Qar Iraq The Islamic University Najaf Iraq

ISBN: (纸本)9798350317022

Copy-move forgery (CMF) is one of the most malicious forgery attacks often manipulated to spread misinformation and influence security. In the paper, utilized Machine Learning techniques specifically, a Multiclass Support Vector Machine (MSVM)-based Particle Swarm Optimization (PSO) algorithm was utilized for image forgery. PSO is an optimization algorithm in which a group of particles representing individual solutions moves through a search space to find the best solution. The objective function that the PSO algorithm seeks to minimize or maximize is typically related to the MSVM's performance on a validation dataset. The MICC-F200 dataset was used to verify the uniqueness of CMF and evaluate the model's image classification performance. It's important to note that MSVM based PSO can become computationally expensive and memory-intensive when dealing with a large number of classes. They are also sensitive to noisy or mislabeled data points, which can potentially lead to suboptimal performance. The results obtained from this study reveal that the MSVM-based PSO model achieves a high accuracy of 0.9936 on the MICC-F200 dataset, outperforming other existing models such as VGG16 and Mobile Net, thereby ensuring accurate image classification. © 2023 IEEE.

关键词： Copy-Move Forgery Gray Scale Technique Machine Learning Particle Swarm Optimization and Support Vector Machine

来源：评论

学校读者我要写书评

暂无评论

Autonomous Vehicle Lane Detection Using Hyperbolic Neural Network with Bi-Directional Long Short-Term Memory 3

Autonomous Vehicle Lane Detection Using Hyperbolic Neural Ne...

引用

3rd IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2023

作者： Alzubaidi, Laith H. Almoussawi, Zainab Abed Jagadish, Sripelli Madhavan, Sowmya Alassedi, Zainab The Islamic University Najaf Iraq College of Islamic Science Ahl Al Bayt University Karbala Iraq School of Computer Science & Artificial Intelligence SR University Telangana Warangal India Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India National University of Science and Technology Dhi Qar Iraq

ISBN: (纸本)9798350317022

Lane detection is a feature of autonomous vehicles and is an essential technology for environmental awareness. While many academics have successfully used Deep Learning (DL) for lane detection, their application cases were rather straightforward. When a lane is blocked, lost, or has other problems, the accuracy of lane recognition diminishes significantly. In this paper, to solve the above-mentioned problems, a Hyperbolic Neural Network (HNN) with a Bi-directional Long Short-Term Memory (B-LSTM) model is proposed for efficient autonomous vehicle lane detection. At first, hyperbolic space is used to identify the space changes in the frame, and the HNN is used to extract the spatial information in the frames. Then, finally, the B-LSTM is used to perform the sequential data to detect the autonomous vehicle lane in an effective way. The implemented HNN with the B-LSTM model demonstrates superior performance, achieving a Precision of 0.0311, Recall of 0.0253, F1-Score of 97.57%, and Accuracy of 96.74%. When compared to previous models like the Lightweight Attention Deep Neural Network (LA-DNN), ResNest and Self-attention Distillation (RS-Lane), and Convolutional Neural Network-Multi Layer Perceptron (CNN-MLP). © 2023 IEEE.

关键词： Autonomous Vehicle Deep Learning Hyperbolic Neural Network Long Short-Term Memory Spatial Information

来源：评论

学校读者我要写书评

暂无评论

Enhancing Multi-View Classification Reliability with Adaptive Rejection 39

Enhancing Multi-View Classification Reliability with Adaptiv...

引用

39th Annual AAAI Conference on artificial intelligence, AAAI 2025

作者： Liu, Wei Chen, Yufei Yue, Xiaodong School of Computer Science and Technology Tongji University Shanghai China Artificial Intelligence Institute of Shanghai University Shanghai University Shanghai China

ISBN: (纸本)157735897X

Multi-view classification based on evidence theory aims to enhance result reliability by effectively quantifying prediction uncertainty at the evidence level, particularly when dealing with low-quality views. However, these methods face limitations in real-world applications due to the sensitivity of estimated uncertainty to view distribution, leading to two main issues: 1) difficulty in making clear judgments about whether to trust predictions based on vague uncertainty scores, and 2) the potential negative impact of integrating information from low-quality views on multi-view classification performance. Both limitations compromise the reliability of multi-view decisions. To address these challenges, we introduce an adaptive rejection mechanism based on estimated uncertainty, which is free of data distribution constraints. By integrating this adaptive rejection mechanism into the fusion of multiple views, our method not only indicates whether predictions should be adopted or rejected at the view level but also enhances classification performance by minimizing the impact of unreliable information. The effectiveness of our method is demonstrated through comprehensive theoretical analysis and empirical experiments on various multi-view datasets, establishing its superiority in enhancing the reliability of multi-view classification. Copyright © 2025, Association for the Advancement of artificial intelligence (***). All rights reserved.

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

Social Influence on Shopping Using Ant Colony Optimization Technique

Social Influence on Shopping Using Ant Colony Optimization T...

引用

Advanced Computing and Emerging Technologies (ACET), International Conference on

作者： Polapelly Srihitha Bimireddy Sanjana Tula Karthikeya Rajesh Kumar Singh Anshu Kumar Dwivedi School of Computer Science And Artificial Intelligence SR University Warangal India Dept. of CSE KIPM-College of Engg & Technology Gorakhpur School of Computer Science Engineering and Technology Bennett University Greater Noida India

ISBN: (数字)9798350367720

ISBN: (纸本)9798350367737

Understanding how social influence on purchasing affects customers is critical for businesses looking to increase customer engagement, sales, and the shopping experience. This project's main objective is the development of a model that would identify the market segment that will react effectively to attractive approaches to marketing, such as influence marketing, social mediapromotions, and specific advertisements. To do this, to predict customer responsiveness, we used a variety of regression models, including Random Forest, Support Vector Machine, Ant Colony Optimization, and Normalization. The results of this research provide important details about how various customer categories respond to social influence strategies. In conclusion, Organizations must understand which market segments respond best to these techniques. It enables them to properly manage resources and target particular groups with their marketing initiatives, optimizing their return on investment. Our experiment helps organizations to improve their marketing tactics with the aid of this study. For instance, if a certaincustomer category is shown to be extremely sensitive to influence marketing, a business might commit more resources to this channelto efficiently target that segment.

关键词： Support vector machines Ant colony optimization Social networking (online) Organizations Machine learning Forestry Predictive models Vectors Object recognition Investment

来源：评论

学校读者我要写书评

暂无评论

Enhancing Secret Image Authentication Through Encryption-Based Steganography with Reversible Watermarking 3

Enhancing Secret Image Authentication Through Encryption-Bas...

引用

3rd IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2023

作者： Lakshmi, P.V. Sunil, G. Issa, Ali Ashoor Al-Attabi, Kassem Ramadan, Ghazi Mohamad Dept CSE Visakhapatnam India School of Computer Science & Artificial Intelligence SR University Telangana Warangal India National University of Science and Technology Dhi Qar Iraq The Islamic University Najaf Iraq College of MLT Ahl Al Bayt University Karbala Iraq

ISBN: (纸本)9798350317022

Reversible data hiding is a special technique primarily used for embedding a secret image that can be later restored from the watermarked image. The image encryption algorithms have been developed based on the Chaotic Logistic-Sine Coupling map (CLSM) While these algorithms perform well in the steganography process there is still room for further development to enhance the level of security they offer. The implementation of the algorithm and its security have been partially analysed using statistical measures like sensitivity to the key space and pixel correlation. Depending on the specific application the CLSM can be computationally intensive making it less suitable for real-time image processing on low-resource devices. To ensure authentication, the MATLAB standard image is exclusively utilized for converting the secret image and embedding it using the Multi-Region Watermark Mechanism (MRWM) designed for color images. In this paper, the Histogram Equalization is utilized feature region is selected and processed and watermarking is performed multiple times due to overlapping feature regions. Comparatively, the results obtained using CLSM show a PSNR of 65.99, MSE of 0.0120, and SSIM of 0.9998 on the MATLAB standard image, surpassing other existing models like Pixel Value Ordering (PVO) and Discrete Cosine Transform (DCT) demonstrating superior image performance. © 2023 IEEE.

关键词： Chaotic Logistic-Sin Coupling Map Discrete Cosine Transform Image Authentication Multi-Region Watermark Mechanism and Prediction Error Extension

来源：评论

学校读者我要写书评

暂无评论

Back to the Color: Learning Depth to Specific Color Transformation for Unsupervised Depth Estimation

arXiv

引用

arXiv 2024年

作者： Zhu, Yufan Ran, Chongzhi Feng, Mingtao Wu, Fangfang Dong, Le Dong, Weisheng López, Antonio M. Shi, Guangming The School of Artificial Intelligence Xidian University Xi’an710071 China The School of Computer Science and Technology Xidian University Xi’an710071 China The Department of Computer Science Spain Barcelona Bellaterra08193 Spain

Virtual engines can generate dense depth maps for various synthetic scenes, making them invaluable for training depth estimation models. However, discrepancies between synthetic and real-world colors pose significant challenges for depth estimation in real-world scenes, especially in complex and uncertain environments encountered in unsupervised monocular depth estimation tasks. To address this issue, we propose Back2Color, a framework that predicts realistic colors from depth using a model trained on real-world data, thus transforming synthetic colors into their real-world counterparts. Additionally, we introduce the Syn-Real CutMix method for joint training with both real-world unsupervised and synthetic supervised depth samples, enhancing monocular depth estimation performance in real-world scenes. Furthermore, to mitigate the impact of nonrigid motions on depth estimation, we present an auto-learning uncertainty temporal-spatial fusion method (Auto-UTSF), which leverages the strengths of unsupervised learning in both temporal and spatial dimensions. We also designed VADepth, based on the Visual Attention Network, which offers lower computational complexity and higher accuracy than transformers. Our Back2Color framework achieves state-of-the-art performance on the Kitti dataset, as evidenced by improvements in performance metrics and the production of fine-grained details. This is particularly evident on more challenging datasets such as Cityscapes for unsupervised depth estimation. Code is available at https://***/BlueEg/back2color/. © 2024, CC BY.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

FedSTG: Breaking through Spatio-Temporal data Silos with Federated Graph Learning 25

FedSTG: Breaking through Spatio-Temporal Data Silos with Fed...

引用

Companion Proceedings of the ACM on Web Conference 2025

作者： Yudong Zhang Xu Wang Xuan Yu Kuo Yang Zhengyang Zhou Yang Wang School of Artificial Intelligence and Data Science University of Science and Technology of China Hefei Anhui China School of Software Engineering University of Science and Technology of China Hefei Anhui China and Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou Jiangsu China School of Software Engineering University of Science and Technology of China Hefei Anhui China

ISBN: (纸本)9798400713316

Spatio-temporal graph (STG) forecasting plays a crucial role in various urban computing applications driven by Web systems. However, conventional STG forecasting methods, which rely on centralized data processing, have posed obstacles to real-world applications in numerous data silo scenarios. Given this, some researchers have preliminarily explored incorporating federated learning into STG forecasting. Though promising, the existing methods encounter two critical issues, i.e., dynamics and heterogeneity in STGs. To this end, we propose a novel personalized Federated learning framework for Spatio-Temporal Graph forecasting (called FedSTG), along with an evolutionary graph learning module and a personalized federated aggregation algorithm based on evolving temporal patterns in the framework. Our approach enhances the STG learning capabilities in the federated paradigm, yield addressing the problem of STG forecasting in data silo scenarios. Extensive experiments on four real-world datasets in STG forecasting have been conducted to demonstrate the superiority of our approach.

关键词： data silos

来源：评论

学校读者我要写书评

暂无评论

Multi-dimensional Attention Feature Alignment for High Resolution Saliency Detection

Multi-dimensional Attention Feature Alignment for High Resol...

引用

science and technology Innovation (IAECST), International Academic Exchange Conference on

作者： Biao Tong Xiaoning Song School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China

In the context of saliency object detection, semantic information within images plays a crucial role. However, convolutional structures are constrained by their receptive fields, limiting their ability to model long-range dependencies effectively. On the other hand, Vision Transformer (ViT) networks excel at capturing global contextual information within images but come with the drawback of significant computational demands, particularly when handling high-resolution photos. This paper introduces a dual-branch multi-dimensional attention feature pyramid fusion network to address this contradiction. This network leverages a convolutional encoder to extract fine-grained details from high-resolution images and a ViT encoder to extract semantic information from corresponding low-resolution images. Additionally, it employs pre-trained weights generated using the MAE self-supervision method to enhance ViT structure’s understanding of salient objects and feature extraction capabilities. Within the decoding structure, a multi-dimensional attention fusion enhancement module is designed to weigh and integrate features across multiple dimensions simultaneously. This module effectively suppresses noise and reinforces prominent features. Furthermore, a pyramid feature refinement module is introduced to fine-tune features during the multi-scale fusion process, focusing on enhancing edge details. Experimental results on datasets, including HRSOD, DAVIS, UHRSD, DUT-OMRON, and DUTS, demonstrate the network’s superior performance.

关键词：

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：