检索结果-内蒙古大学图书馆

A Multi-Step Multivariate Fuzzy-based Time Series Forecasting on Internet of Things Data

IEEE Internet of Things Journal 2025年

作者： Bitencourt, Hugo Vinicius Lucas, Patri-Cia de Oliveira Orang, Omid Silva, Petronio C. L. Guimaraes, Frederico Gadelha Universidade Federal de Minas Gerais -UFMG Graduate Program in Electrical Engineering MG Belo Horizonte31270-901 Brazil Federal Institute of Northern Minas Gerais IFNMG MG Salinas Brazil Universidade Federal de Minas Gerais -UFMG Computer Science MG Belo Horizonte31270-901 Brazil Federal Institute of Northern Minas Gerais IFNMG MG Januaria Brazil Universidade Federal de Minas Gerais -UFMG Department of Computer Science MG Belo Horizonte Brazil

Multi-step ahead time series forecasting is essential in Internet of Things (IoT) applications in smart cities and smart homes to make accurate future predictions and precise decision-making. Thus, this study introduces a novel multiple-input single-output (MISO) forecasting method called Multi-Step Embedding-based Fuzzy Time Series (MS-EFTS), designed to predict high-dimensional non-stationary time series data. As a first-order approach, it employs a direct strategy that integrates an embedding transformation with a weighted multivariate FTS (WMVFTS) model. This combination allows for effective predictions over long-term horizons within low-dimensional, learned continuous representations. The effectiveness of the proposed MS-EFTS is assessed using three high-dimensional IoT time series in this investigation. The obtained results showcase the superior performance of the proposed method compared to some deep learning forecasting methods, including LSTM, BiLSTM, TCN, and CNN-LSTM, in terms of accuracy, parsimony, and efficiency. © 2014 IEEE.

关键词： Smart homes

来源：评论

学校读者我要写书评

暂无评论

Reproducing ATT&CK Techniques and Lifecycles to Train Machine Learning Classifier

引用

IEEE Network 2025年

作者： Yudha, Fietyata Lin, Ying-Dar Lai, Yuan-Cheng Sudyana, Didik Hwang, Ren-Hung EECS International Graduate Program National Yang Ming Chiao Tung University Hsinchu City300 Taiwan Department of Computer Science National Yang Ming Chiao Tung University Hsinchu City300 Taiwan The Department of Information Management National Taiwan University of Science and Technology Tapei106 Taiwan The Computer and Network Center National Cheng Kung University Tainan701 Taiwan The College of Artificial Intelligence National Yang Ming Chiao Tung University Tainan711 Taiwan

he MITRE ATT&CK framework categorizes threat actor behaviors into a sequence of techniques called the attack lifecycle. Based on this, Our work introduces a dual-labeled dataset that is accurately labeled with distinct techniques and lifecycles defined by ATT&CK. The dataset offered a more thorough perspective than previous datasets that employed binary or attack classification. It encompassed 17 distinct techniques throughout five lifecycles and was generated through an automated method that guarantees reproducibility and learnability. Reproducibility guarantees the dataset’s consistency, whereas learnability signifies its use in training machine learning models. Our analysis produced a positive result. The dataset achieved a Pearson correlation coefficient of 0.7 for reproducibility. Regarding distinguishing classes, it exhibits an average AUC-ROC score of 0.92 for techniques and 0.82 for lifecycles. The model training yielded an average F1 score of 0.95 for technique classification and 0.9 for lifecycle classification, but only for the traffic dataset. © 1986-2012 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Visual Control and Mapping for UAV-Based Platform Inspection

Visual Control and Mapping for UAV-Based Platform Inspection

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Leonardo A. Fagundes Carlos M. Soria Raquel F. Vassallo Alexandre S. Brandão Department of Electrical Engineering Graduate Program on Computer Science Federal University of Viçosa Viçosa MG Brazil Facultad de Ingeniería Instituto de Automática Universidad Nacional de San Juan Argentine Department of Electric Engineering Federal University of Espirito Santo Vitória ES Brazil

ISBN: (数字)9798331513283

ISBN: (纸本)9798331513290

Autonomous take-off and landing capabilities are crucial in UAV vision-based missions, ensuring adaptive navigation, especially in challenging environments where realtime identification and interaction with a variety of landing platforms are required. In this context, this paper presents a servo-visual controller that uses pattern detection and color segmentation techniques to identify take-off/landing platforms and estimate their current orientation. The proposed system was subjected to experimental validation with four platforms positioned in different orientations, heights, and positions, demonstrating its versatility in various conditions. Our study addresses the Flying Robots Trial League challenge, which emulates mapping and inspection tasks in offshore platforms.

关键词： Visualization Offshore installations Navigation Color Inspection Autonomous aerial vehicles Aircraft Drones Aerospace control

来源：评论

学校读者我要写书评

暂无评论

Protecting host-based intrusion detectors through virtual machines

引用

computer NETWORKS 2007年第5期51卷 1275-1283页

作者： Laureano, M. Maziero, C. Jamhour, E. [a]Graduate Program in Applied Computer Science Pontifical Catholic University of Paran¨￠ Brazil

Intrusion detection systems continuously watch the activity on a network or computer, looking for attack and intrusion evidences. However, host-based intrusion detectors are particularly vulnerable, as they can be disabled or tampered by successful intruders. This work proposes and implements an architecture model aimed to protect host-based intrusion detectors, through the application of the virtual machine concept. Virtual machine environments are becoming an interesting alternative for several computing systems due to their advantages in terms of cost and portability. The architecture proposed here makes use of the execution spaces separation provided by a virtual machine monitor, in order to separate the intrusion detection system from the system under monitoring. As a consequence, the intrusion detector becomes invisible and inaccessible to intruders. The prototype implementation and the tests performed show the viability of this solution. (c) 2006 Elsevier B.V. All rights reserved.

关键词： security intrusion detection virtual machines

来源：评论

学校读者我要写书评

暂无评论

AVTENet: A Human-Cognition-Inspired Audio-Visual Transformer-Based Ensemble Network for Video Deepfake Detection

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min Taiwan International Graduate Program Academia Sinica Social Networks and Human-Centered Computing Program Taipei11529 Taiwan National Tsing Hua University Institute of Information Systems and Applications Hsinchu30013 Taiwan National Chengchi University Department of Computer Science Taipei11605 Taiwan National Tsing Hua University Department of Electrical Engineering Institute of Communications Engineering Hsinchu300044 Taiwan Academia Sinica Research Center for Information Technology Innovation Taipei11529 Taiwan

The recent proliferation of hyper-realistic deepfake videos has drawn attention to the threat of audio and visual forgeries. Most previous studies on detecting artificial intelligence-generated fake videos only utilize visual modality or audio modality. While some methods exploit audio and visual modalities to detect forged videos, they have not been comprehensively evaluated on multimodal datasets of deepfake videos involving acoustic and visual manipulations, and are mostly based on convolutional neural networks with low detection accuracy. Considering that human cognition instinctively integrates multisensory information including audio and visual cues to perceive and interpret content and the success of transformer in various fields, this study introduces the audio-visual transformer-based ensemble network (AVTENet). This innovative framework tackles the complexities of deepfake technology by integrating both acoustic and visual manipulations to enhance the accuracy of video forgery detection. Specifically, the proposed model integrates several purely transformer-based variants that capture video, audio, and audio-visual salient cues to reach a consensus in prediction. For evaluation, we use the recently released benchmark multimodal audio-video FakeAVCeleb dataset. For a detailed analysis, we evaluate AVTENet, its variants, and several existing methods on multiple test sets of the FakeAVCeleb dataset. Experimental results show that the proposed model outperforms all existing methods and achieves state-of-the-art performance on Testset-I and Testset-II of the FakeAVCeleb dataset. We also compare AVTENet against humans in detecting video forgery. The results show that AVTENet significantly outperforms humans. © 2016 IEEE.

关键词： audio-visual AVTENet Deepfake detection

来源：评论

学校读者我要写书评

暂无评论

Survey and Improvement Strategies for Gene Prioritization with Large Language Models

arXiv

引用

arXiv 2025年

作者： Neeley, Matthew B. Qi, Guantong Wang, Guanchu Tang, Ruixiang Mao, Dongxue Liu, Chaozhong Pasupuleti, Sasidhar Yuan, Bo Xia, Fan Liu, Pengfei Liu, Zhandong Hu, Xia Jan and Dan Duncan Neurological Research Institute Texas Children’s Hospital Houston United States Graduate School of Biomedical Sciences Program in Quantitative and Computational Biosciences Baylor College of Medicine Houston United States Graduate School of Biomedical Sciences Program in Genetics and Genomics Baylor College of Medicine Houston United States Department of Computer Science Rice University Houston United States Department of Computer Science Rutgers University NJ United States Department of Pediatrics Baylor College of Medicine Houston United States Department of Molecular and Human Genetics Baylor College of Medicine Houston United States Human Genome Sequencing Center Baylor College of Medicine Houston United States Baylor Genetics Houston United States

Background Rare diseases can be difficult to diagnose due to limited patient data and broad genetic diversity. Despite the advances in variant prioritization tools, many rare disease cases remain undiagnosed. While large language models (LLMs) have performed well in medical exams, their accuracy in diagnosing rare genetic diseases has not yet been evaluated. Methods To identify causal genes for genetic diseases, we benchmarked various LLMs for gene prioritization. We employed multi-agent and Human Phenotype Ontology (HPO) classification approaches to identify patient case groups based on phenotypes categorizing them into different levels of solvability. To address LLM limitations in ranking large gene sets, we used a divide-and-conquer strategy to break down the ranking task into smaller subsets. Mini-batching inputs and limiting the number of generated tokens improved efficiency. Results In its vanilla form, GPT-4 consistently outperformed the other LLMs with an accuracy around 30%. Multi-agent and HPO classification approaches aided us in distinguishing between confidently-solved and challenging cases. In addition, we observed bias towards well-studied genes and input order sensitivity which are drawbacks of LLMs in disease-causal gene prioritization. Our divide-and-conquer strategy enhanced accuracy by overcoming positional and gene frequency biases in literature. This framework, based on benchmarking insights and novel techniques, significantly optimizes the overall process when identifying disease-causal genes for genetic diseases when compared to our baseline evaluation, and thereby better enables the development of targeted diagnostic and therapeutic interventions. Conclusions Using HPO classification and our novel multi-agent techniques, and our LLM divide-and-conquer strategy (1) highlighted the importance of accounting for differences in patient case solvability and (2) yielded improved performance in identifying causal genes for rare diseases when compare

关键词： Gene Ontology

来源：评论

学校读者我要写书评

暂无评论

consexpressionR: an R package for consensus differential gene expression analysis

arXiv

引用

arXiv 2025年

作者： Costa-Silva, Juliana Menotti, David Lopes, Fabricio M. Department of Informatics Federal University of Paraná Rua Coronel Francisco Heráclito dos Santos 100 Paraná81531-990 Brazil Department of Computer Science Bioinformatics Graduate Program Federal University of Technology - Paraná Av. Alberto Carazzai 1640 - Cornélio Procópio ParanáPostal code: 86300-000 Brazil

Motivation: Bulk RNA-Seq is a widely used method for studying gene expression across a variety of contexts. The significance of RNA-Seq studies has grown with the advent of high-throughput sequencing technologies. Computational methods have been developed for each stage of the identification of differentially expressed genes. Nevertheless, there are few studies exploring the association between different types of methods. In this study, we evaluated the impact of the association of methodologies in the results of differential expression analysis. By adopting two data sets with qPCR data (to gold-standard reference), seven methods were implemented and assessed in R packages (EBSeq, edgeR, DESeq2, limma, SAMseq, NOISeq, and Knowseq), which was performed and assessed separately and in association. The results were evaluated considering the adopted qPCR data. Results: Here, we introduce consexpressionR, an R package that automates differential expression analysis using consensus of at least seven methodologies, producing more assertive results with a significant reduction in false positives. Availability: consexpressionR is an R package available via Source code and support are available at GitHub (https://***/costasilvati/consexpressionR). © 2025, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A business-oriented perspective for QoS management

A business-oriented perspective for QoS management

引用

2004 IEEE Workshop on IP Operations and Management Proceedings, IPOM 2004: Self-Measurement and Self-Management of IP Networks and Services

作者： Penna, Manoel Camillo Kaestner, Celso Wandresen, Rafael Romualdo Post Graduate Program in Computer Science Pontifical Catholic University of Parana Curitiba Brazil

ISBN: (纸本)0780388364

Research efforts in Quality of Service (QoS) management have usually addressed the problem under the network infrastructure perspective whereas a business-oriented perspective, named Service Quality Management (SQM), is being considered by industry. This paper point out differences and similarities between two approaches and addresses the main issues arising under SQM perspective. Here, QoS indicators and corresponding service levels are defined to provide a common understanding of service delivery, and a critical issue is to provide an effective way to evaluate them. Two evaluation modes are used: off-line and on-line. Off-line methods compute indicators values at the end of a pre-defined evaluation period, whereas on-line methods do it when a related event occurs. This work proposes an architecture for SQM systems and discusses the mechanisms for both off-line and on-line evaluation modes. ©2004 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

PERFORMANCE MODELING AND ANALYSIS OF BLOOD FLOW IN ELASTIC ARTERIES

引用

Applied Mathematics and Mechanics(English Edition) 2005年第3期26卷 345-354页

作者： Anil Kumar C.L.Varshney G.C.Sharma Department of Post-Graduate Studies and Research in Mathematics &Computer Science S.Varshney College Aligarh-202001 IndiaDepartment of Post-Graduate Studies and Research in Mathematics &Computer Science S.Varshney College Aligarh-202001 IndiaInstitute of Basic Science Khandari Agra-282002 India

Two different non_Newtonian models for blood flow are considered,first a simple power law model displaying shear thinning viscosity,and second a generalized Maxwell model displaying both shear thinning viscosity and oscillating flow viscous_*** models are used along with a Newtonian model to study sinusoidal flow of blood in rigid and elastic straight arteries in the presence of magnetic *** elasticity of blood does not appear to influence its flow behavior under physiological conditions in the large arteries,purely viscous shear thinning model should be quite realistic for simulating blood flow under these *** using the power law model with high shear rate for sinusoidal flow simulation in elastic arteries,the mean and amplitude of the flow rate were found to be lower for a power law fluid compared to Newtonian fluid for the same pressure *** governing equations have been solved by Crank_Niclson *** results are interpreted in the context of blood in the elastic arteries keeping the magnetic effects in *** physiological flow simulation in the aorta,an increase in mean wall shear stress,but a reduction in peak wall shear stress were observed for power law model compared to a Newtonian fluid model for matched flow rate wave *** flow in the presence of transverse magnetic field in an elastic artery is investigated and the influence of factors such as morphology and surface irregularity is evaluated.

关键词： elastic artery model Crank-Niclson scheme non-Newtonian fluid wall shear stress

来源：评论

学校读者我要写书评

暂无评论

COMPUTATIONAL TECHNIQUE FOR FLOW IN BLOODVESSELS WITH POROUS EFFECTS

引用

Applied Mathematics and Mechanics(English Edition) 2005年第1期26卷 63-72页

A finite element solution for the Navier-Stokes equations for steady flow under the porosity effects through a double branched two-dimensional section of a three-dimensional model of a canine aorta was obtained. The numerical solution involves transforming a physical coordinates to a curvilinear boundary fitted coordinate *** steady flow,branch flow and shear stress under the porous effects were discussed in detail. The shear stress at the wall was calculated for Reynolds number of 1 000 with branch to main aortic flow rate ratio as a parameter. The results are compared with earlier works involving experimental data and it has been observed that our results are very close to the exact *** work is in fact an improvement of the work of Sharma et al. (2001) in the sense that computational technique is economic and (Reynolds) number is large.

关键词： wall shear stress porosity Galerkin's technique blood vessel

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：