检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Xu, Ziqiang Ahmad, Salehi S. Chilamkurti, Naveen Department of Computer Science and Information Technology La Trobe University Melbourne Australia

Permissionless blockchain technology offers numerous potential benefits for decentralised applications, such as security, transparency, and openness. BFT-based consensus mechanisms are widely adopted in the permissioned blockchain to meet the high scalability requirements of the network. Sybil attacks are one of the most potential threats when applying BFT-based consensus mechanisms in permissionless blockchain due to the lack of effective verification mechanisms for participants’ identities. This paper presents a novel endorsement-based bootstrapping protocol with a signature algorithm that offers a streamlined, scalable identity endorsement and verification process. This approach effectively safeguards the BFT-based consensus mechanism against Sybil attacks. Using our proposed method, we have conducted thorough security analyses and simulation experiments to assess security, robustness, and scalability advantages in large-scale networks. Our results demonstrate that the scheme can effectively address the identity verification challenges when applying BFT-based consensus in a permissionless blockchain. Copyright © 2024, The Authors. All rights reserved.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

The Integration of Knowledge Graph Convolution Network with Denoising Autoencoder

SSRN

引用

SSRN 2024年

作者： Kaur, Gurinder Liu, Fei Chen, Yi-Ping Phoebe Department of Computer Science and Information Technology La Trobe University VIC Australia

One of the primary objectives of recommender systems is to win users' trust by estimating the interest of user through monitoring their transactional activities in order to deliver an instantaneous and highly personalized collection of top recommendations among hundreds of products. Knowledge graph convolution network (KGCN) is such a recommendation model that provides a set of top recommendations on the basis of knowledge graph developed between users, items and their attributes. In this study, we integrate the KGCN model with denoising autoencoder to improve its recommendation performance. A trained denoising autoencoder (DAE) is used to sample K-dimensional latent representation for each user, which then transforms that representation to generate a probability distribution over items. The relationship between acquired latent representation and the meta features is modelled using multivariate multiple regression (MMR) kernel. As a result, without the need for new configuration assessments, performance estimation of new data is pursued directly through MMR and the decoder of DAE. Empirically, we demonstrate that on real-world datasets, the proposed method substantially outperforms other state-of-the-art baselines. Movie-Lens 100K (ML-100K) and Movie-Lens 1M (ML-1M), two common MovieLens datasets, are used to verify the accuracy of the proposed approach. The proposed framework outperforms other state-of-the-art frameworks on Recall@K and normalized discounted cumulative gain (NDCG@K) metrics by achieving higher scores for Recall@5, Recall@10, NDCG@1 and NDCG@10. © 2024, The Authors. All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

LSTM Network Assisted Content Caching at the Edge for Video on Demand 5

LSTM Network Assisted Content Caching at the Edge for Video ...

引用

5th IEEE International Conference on Cybernetics, Cognition and Machine Learning Applications, ICCCMla 2023

作者： Darwich, Mahmoud Bayoumi, Magdy University of Mount Union Department of Mathematics and Computer Science AllianceOH44601 United States University of Louisiana Department of Electrical and Computer Engineering LafayetteLA70504 United States

ISBN: (纸本)9798350338287

Video-on-demand (VoD) services often suffer from long start-up delays and poor streaming quality due to distance from centralized data centers. In this work, we develop a long short-term memory (LSTM) network to predict future video requests and intelligently cache content at the edge for optimized VoD delivery. We train the LSTM model on a large proprietary dataset of VoD access logs capturing real-world sequential patterns. Using caching simulations, our approach increases cache hit ratios by 56% compared to recency-based caching and 41% over popularity-based schemes. By proactively caching predicted videos at the edge, our method reduces average video startup time by 32% and decreases upstream bandwidth consumption by 48%. These substantial gains demonstrate the value of forecasting VoD popularity using LSTMs and harnessing edge computing to cache content closer to viewers. Our intelligent edge caching system can improve quality of experience for users and lower costs for providers. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

FSD: Fully-Specialized Detector via Neural Architecture Search 5

FSD: Fully-Specialized Detector via Neural Architecture Sear...

引用

5th International Conference on computer Communication and the Internet, ICCCI 2023

作者： Huang, Zhe Li, Yudian University of Wisconsin-Madison Department of Computer Sciences MadisonWI United States University of California Computer Science & Engineering Department La Jolla San DiegoCA United States

ISBN: (纸本)9798350326956

Most generic object detectors are mainly built for 'standard' object detection tasks such as COCO [1] and PAS-CAL VOC [2]. They might not work well and/or efficiently on tasks of other domains consisting of images that are visually different from standard datasets. To this end, many advances have been focused on adapting a general-purposed object detector with limited domain-specific designs. However, designing a successful task-specific detector requires extraneous manual experiments and parameter tuning through trial and error. In this paper, we first propose and examine a fully-automatic pipeline to design a fully-specialized detector (FSD) which mainly incorporates a neural-architectural-searched model by exploring ideal network structures over the backbone and task-specific head. On the DeepLesion dataset, extensive results show that FSD can achieve 3.1 mAP gain while using approximately 40% fewer parameters on binary lesion detection task and improved the mAP by around 10% on multi-type lesion detection task via our region-aware graph modeling compared with existing general-purposed medical lesion detection networks. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Cryptography-Based Bootstrapping Scheme for Permissionless Sharding Blockchain

Cryptography-Based Bootstrapping Scheme for Permissionless S...

引用

IEEE/IFIP International Conference on Dependable Systems and Networks â€“ Supplemental Volume (DSN-S)

作者： Ziqiang Xu S. Ahmad Salehi Naveen Chilamkurti Department of Computer Science and Information Technology La Trobe University Melbourne Australia

ISBN: (数字)9798350395709

ISBN: (纸本)9798350395716

This paper proposes a secured bootstrapping protocol based on BLS aggregated signatures. The protocol provides a secure, efficient identity endorsement and verification scheme for permissionless sharding blockchain and effectively prevents the Sybil attack during the bootstrapping process. Our results show that our scheme is secure and supports large-scale networks. Our scheme performs better than the current methods in preventing the Sybil attack.

关键词： Sharding Protocols Blockchains

来源：评论

学校读者我要写书评

暂无评论

Automatic Learning for Commercial Registration Renewal - The Case of Camara de Comercio of Barranquilla-Colombia

引用

IEEE engineering Management Review 2023年第1期51卷 26-40页

作者： Rios-Henao, Cristian Ariza-Colpas, Paola Patricia De-la-Hoz-Franco, Emiro Aziz, Shariq Butt Melo, Marlon Alberto Pineres Perez-Coronell, Leidy Universidad de la Costa Cuc Department of Computer Science and Electronics Barranquilla08002 Colombia University of South Asia Department of Computer Science Lahore54000 Pakistan Universidad Del Norte Department of Systems Engineering Barranquilla081001 Colombia Universidad Simón Bolívar Facultad de Ingenierías Barranquilla08002 Colombia

This article shows the implementation of a prediction model of the payment behavior of the renewal concept of companies registered in the commercial registry of the Barranquilla Chamber of Commerce using machine learning techniques in a multilevel classification scenario, where it will offer the organization a tool that allows it to know in advance the behavior of the payment of the renewal of a company in such a way that it is able to design strategies to increase the success indicators in terms of the number of registration renewals, mercantile, and of the income collected for this concept. © 1973-2011 IEEE.

关键词： Behavioral research

来源：评论

学校读者我要写书评

暂无评论

Super-resolved Estimation of White Matter Microstructure via 3D Conditional latent Diffusion Model

Super-resolved Estimation of White Matter Microstructure via...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jiquan Ma Yihang Gao Haotian Jiang Jing Gu Diliara Khairullina Hui Cui Geng Chen Department of Computer Science and Technology Heilongjiang University Harbin China School of Computer Science and Engineering Northwestern Polytechnical University Xi’an China Department of Computer Science and Information Technology La Trobe University Melbourne Australia

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

As a powerful microstructural imaging technique, neurite orientation dispersion and density imaging (NODDI) provides detailed insights into brain microstructures. Its clinical application is often restricted by the necessity for high-quality scanning, which can be challenging to achieve in practical settings. To overcome this limitation, we propose an innovative 3D conditional latent diffusion model (3D-CLDM) to generate high-quality NODDI index maps from low-resolution diffusion magnetic resonance imaging data. The 3D-CLDM is a two-stage super-resolved microstructure estimation model that includes training a vector quantized generative adversarial network and a diffusion model. It leverages the sophisticated high-dimensional data modeling capabilities of the conditional latent diffusion model to effectively capture and represent intricate microstructural features that are difficult to detect with conventional techniques. We conducted comprehensive experiments using data from the human connectome project to rigorously assess our model’s performance. The results reveal that our approach not only significantly improves the quality of super-resolved microstructural estimation but also surpasses current state-of-the-art models in both qualitative and quantitative evaluations. This highlights the potential of 3D-CLDM to advance brain microstructure imaging, making it more feasible and effective for clinical applications.

关键词： Three-dimensional displays Estimation Diffusion models Brain modeling Encoding Vectors Microstructure Indexes Spatial resolution White matter

来源：评论

学校读者我要写书评

暂无评论

Improving Prediction of Need for Mechanical Ventilation using Cross-Attention 46

Improving Prediction of Need for Mechanical Ventilation usin...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Mohanty, Anwesh Shashikumar, Supreeth P. lam, Jonathan Y. Nemati, Shamim University of California San Diego Department of Computer Science and Engineering La Jolla United States University of California San Diego Division of Biomedical Informatics La Jolla United States

ISBN: (纸本)9798350371499

In the intensive care unit, the capability to predict the need for mechanical ventilation (MV) facilitates more timely interventions to improve patient outcomes. Recent works have demonstrated good performance in this task utilizing machine learning models. This paper explores the novel application of a deep learning model with multi-head attention (FFNN-MHA) to make more accurate MV predictions and reduce false positives by learning personalized contextual information of individual patients. Utilizing the publicly available MIMIC-IV dataset, FFNN-MHA demonstrates an improvement of 0.0379 in AUC and a 17.8% decrease in false positives compared to baseline models such as feed-forward neural networks. Our results highlight the potential of the FFNN-MHA model as an effective tool for accurate prediction of the need for mechanical ventilation in critical care settings. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent Model Hotel Energy Demand Forecasting by Means of LSTM and GRU Neural Networks 19th

Intelligent Model Hotel Energy Demand Forecasting by Means ...

引用

19th International Symposium on Distributed Computing and Artificial Intelligence, DCAI 2022

作者： López, Víctor Casteleiro-Roca, José-Luis Gato, Francisco Zayas Perez, Juan Albino Mendez Calvo-Rolle, Jose Luis Department of Industrial Engineering University of A Coruña. CTC A Coruña Spain Department of Computer Science and System Engineering University of La Laguna Tenerife Spain

ISBN: (纸本)9783031232091

The hotel business consumes a significant amount of energy, requiring effective management solutions to ensure its performance and sustainability. The increased position of hotels as prosumers plus the renewable energy technologies, complicate the design of these systems, which depends on the use of reliable predict6ions for energy load. Based on artificial neural networks (ANN), regression approaches such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit networks (GRU), this research proposes an intelligent model for predicting energy demand in a hotel. Validation was performed using real hotel data likened to time-series models. The resulting forecasts were remarkable, indicating a promising potential for its usage in hotel energy management systems. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

HDCGD-CBAM:Satellite Interference Recognition Algorithm Based on Improved CLDNN and CBAM

引用

China Communications 2024年第12期21卷 257-274页

作者： Duan Ruifeng Chen Ziyu Meng Wei Wang Xu Yang Guoting Cheng Peng Li Yonghui School of Information Science and Technology Beijing Forestry UniversityBeijing 100083China Engineering Research Center for Forestry-Oriented Intelligent Information Processing of National Forestry and Grassland Administration Beijing 100083China Jining Economic and Social Development Research Center Jining 272000China School of Electrical and Information Engineering the University of SydneySydneyNSW 2006Australia Department of Computer Science and Information Technology La Trobe UniversityMelbourneVIC 3086Australia

Satellite communication systems are facing serious electromagnetic interference,and interference signal recognition is a crucial foundation for targeted *** this paper,we propose a novel interference recognition algorithm called HDCGD-CBAM,which adopts the time-frequency images(TFIs)of signals to effectively extract the temporal and spectral *** the proposed method,we improve the Convolutional Long Short-Term Memory Deep Neural Network(CLDNN)in two ***,the simpler Gate Recurrent Unit(GRU)is used instead of the Long Short-Term Memory(LSTM),reducing model parameters while maintaining the recognition ***,we replace convolutional layers with hybrid dilated convolution(HDC)to expand the receptive field of feature maps,which captures the correlation of time-frequency data on a larger spatial ***,Convolutional Block Attention Module(CBAM)is introduced before and after the HDC layers to strengthen the extraction of critical features and improve the recognition *** experiment results show that the HDCGD-CBAM model significantly outper-forms existing methods in terms of recognition accuracy and *** Jamming-to-Signal Ratio(JSR)varies from-30dB to 10dB,it achieves an average accuracy of 78.7%and outperforms the CLDNN by 7.29%while reducing the Floating Point Operations(FLOPs)by 79.8%to ***,the proposed model has fewer parameters with 301k compared to several state-of-the-art methods.

关键词： attention mechanism CLDNN HDC interference recognition satellite communication

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：