检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Wiebke Günther Oana-Iuliana Popescu Martin Rabel Urmi Ninad Andreas Gerhardus Jakob Runge German Aerospace Center (DLR) Institute of Data Science Jena Germany and Technische Universität Berlin Institute of Computer Engineering and Microelectronics Berlin Germany German Aerospace Center (DLR) Institute of Data Science Jena Germany and Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig Germany and Technische Universität Dresden Faculty of Computer Science Dresden Germany German Aerospace Center (DLR) Institute of Data Science Jena Germany German Aerospace Center (DLR) Institute of Data Science Jena Germany and Technische Universität Berlin Institute of Computer Engineering and Microelectronics Berlin Germany and Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig Germany and Technische Universität Dresden Faculty of Computer Science Dresden Germany

ISBN: (纸本)9798331314385

Causal systems often exhibit variations of the underlying causal mechanisms between the variables of the system. Often, these changes are driven by different environments or internal states in which the system operates, and we refer to context variables as those variables that indicate this change in causal mechanisms. An example are the causal relations in soil moisture-temperature interactions and their dependence on soil moisture regimes: Dry soil triggers a dependence of soil moisture on latent heat, while environments with wet soil do not feature such a feedback, making it a context-specific property. Crucially, a regime or context variable such as soil moisture need not be exogenous and can be influenced by the dynamical system variables - precipitation can make a dry soil wet - leading to joint systems with endogenous context variables. In this work we investigate the assumptions for constraint-based causal discovery of context-specific information in systems with endogenous context variables. We show that naive approaches such as learning different regime graphs on masked data, or pooling all data, can lead to uninformative results. We propose an adaptive constraint-based discovery algorithm and give a detailed discussion on the connection to structural causal models, including sufficiency assumptions, which allow to prove the soundness of our algorithm and to interpret the results causally. Numerical experiments demonstrate the performance of the proposed method over alternative baselines, but they also unveil current limitations of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multiclass Cucumber Leaf Diseases Recognition Using Best Feature Selection

引用

computers, Materials & Continua 2022年第2期70卷 3281-3294页

作者： Nazar Hussain Muhammad Attique Khan Usman Tariq Seifedine Kadry Muhammad Asfand E.Yar Almetwally M.Mostafa Abeer Ali Alnuaim Shafiq Ahmad Department of Computer Science HITEC University TaxilaTaxilaPakistan College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz UniversityAl-KhrajSaudi Arabia Department of Applied Data Science Noroff University CollegeNorway Department of Computer Science Bahria UniversityIslamabadPakistan Department of Information Systems College of Computer and Information SciencesKing Saud UniversityRiyadh11543KSASaudi Arabia Department of natural and engineering sciences College of Applied Studies and Community ServiceKing Saud UniversityRiyadh11421Saudi Arabia Faculty of Engineering Industrial Engineering DepartmentKing Saud UniversityRiyadh11421Saudi Arabia

Agriculture is an important research area in the field of visual recognition by *** diseases affect the quality and yields of ***-stage identification of crop disease decreases financial losses and positively impacts crop *** manual identification of crop diseases,which aremostly visible on leaves,is a very time-consuming and costly *** this work,we propose a new framework for the recognition of cucumber leaf *** proposed framework is based on deep learning and involves the fusion and selection of the best *** the feature extraction phase,VGG(Visual Geometry Group)and Inception V3 deep learning models are considered and *** fine-tuned models are trained using deep transfer *** are extracted in the later step and fused using a parallel maximum fusion *** the later step,best features are selected usingWhale Optimization *** best-selected features are classified using supervised learning algorithms for the final classification *** experimental process was conducted on a privately collected dataset that consists of five types of cucumber disease and achieved accuracy of 96.5%.A comparison with recent techniques shows the significance of the proposed method.

关键词： Cucumber diseases database preparation deep learning parallel fusion features selection

来源：评论

学校读者我要写书评

暂无评论

An Integrated Edge Computing Framework for Enhancing Cyber-Physical System Security through Network Traffic Anomaly Detection in Industrial IoT

An Integrated Edge Computing Framework for Enhancing Cyber-P...

引用

2024 Global Congress on Emerging Technologies, GCET 2024

作者： Zhukabayeva, Tamara Ahmad, Zulfiqar Karabayev, Nurdaulet Abdildayeva, Assel L.N. Gumilyov Eurasian National University Faculty of Information Technology Astana Kazakhstan Hazara University Department of Computer Science and Information Technology Mansehra21300 Pakistan Al-Farabi Kazakh National University Department of Artificial Intelligence and Big Data Almaty Kazakhstan

ISBN: (纸本)9798331542603

With the expansion of the Industrial Internet of Things (IIoT), the protection of Cyber-Physical System (CPS) is worth consideration. This research presents an integrated edge computing framework that aims at enhancing security by improving network traffic anomaly detection. It is done based on three advanced anomaly detection algorithms, namely Principal Component Analysis (PCA), isolation forest, and autoencoder. PCA is applied to the data to bring it in a compressed form where one is able to detect the outliers by having the most important features of the data extracted. The isolation forest algorithm, which was applied with the contamination factor of 0, is depicted below: 1, is used for the detection of the anomalies in the traffic, and, in fact, it was able to categorize several threats. However, the autoencoder model relies on reconstruction loss to decide if something is wrong with the data, with the 95th percentile as the standard for identifying activities that are odd. Edge computing increases the effectiveness of a framework for real-time anomaly detection and mitigation. The objective of this research is to evaluate PCA, isolation forest, and autoencoder methods and the outcome on the feasibility of the methods to enhance the security of IIoT systems. © 2024 IEEE.

关键词： Industrial internet of things (IIoT)

来源：评论

学校读者我要写书评

暂无评论

CaFe DBSCAN: A Density-based Clustering Algorithm for Causal Feature Learning

CaFe DBSCAN: A Density-based Clustering Algorithm for Causal...

引用

International Conference on data science and Advanced Analytics (DSAA)

作者： Pascal Weber Lukas Miklautz Akshey Kumar Moritz Grosse-Wentrup Claudia Plant Doctoral School of the University of Vienna Vienna Austria Data Science@Uni Vienna Faculty of Computer Science University of Vienna Vienna Austria

Causal Feature Learning (CFL) infers macro-level causes (e.g., an aggregation of pixels in a traffic light image) from micro-level data (e.g., pixels of the image) by clustering the predicted probabilities of effect states (e.g., state of the traffic light). The current method for CFL uses a two-step procedure. First, a classifier for the effect states is trained, and afterwards, the predicted effect state probabilities are clustered. With CaFe DBSCAN, we present a novel density-based clustering method that conducts CFL directly by estimating conditional probabilities during clustering. To this end, we introduce the notion of clustering regions with similar conditional probabilities of the effect states given their micro-level data points. Our single-step approach has the following benefits: (1) CaFe DBSCAN introduces a comprehensive approach to Causal Feature Learning. Unlike existing methods, CaFe DBSCAN uses a probabilistic framework and does not require separate classification and clustering steps implemented by different algorithms relying on various assumptions, parameter settings, and optimization goals. (2) We do not need to train and tune a classifier first, hence the algorithm is more runtime-efficient than the current approach. (3) Due to the properties of density-based clustering algorithms, CaFe DBSCAN is robust against noise and outliers, which leads to purer clusters. (4) Our algorithm automatically infers a reasonable number of clusters, i.e., macro-level causes. We demonstrate the benefits of CaFe DBSCAN on synthetic and real-world data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Railway Safety with an IoT Based System for Real Time Fault Detection and Crack Monitoring

Enhancing Railway Safety with an IoT Based System for Real T...

引用

Information Technology and Digital Applications (ICITDA), IEEE International Conference on

作者： Rajermani Thinakaran Somasekar Jalari Vikram Neerugatti Madhusudana Rao Nalluri Santhaiah Chukka Ravindra Raman Cholla Faculty of Data Science and Information Technology INTI International University Malaysia Department of Computer Science and Engineering Faculty of Engineering and technology Jain (Deemed-to-be University) Bangalore India Department of Computer Science and Engineering ICFAI Foundation for Higher Education Hyderabad Telangana India Department of Computer Science and Engineering S V College of Engineering Tirupati Andhra Pradesh India

ISBN: (数字)9798331510732

ISBN: (纸本)9798331510749

Safety of railway is the major problem worldwide. It has problems like cracks or any fault in the railway tracks. These problems can cause severe accidents if it is not detected regularly and early. In traditional fault finding and crack detecting method, the manual method is involved which is very slow and consist of many errors. By considering all these challenges and issues in track detection method, we have implemented an advanced IoT based railway crack and fault-finding system. It uses advanced sensors, microcontroller, GPS and GSM module which can detect and report faults of the railway track. The system uses real time mechanism. The system is implemented and tested on a prototype railway track to detect crack or any fault. The internet of things technology added modern and accurate fault-finding feature in the system. The IoT plays an important role in implementing advance technologies, as it uses sensors and advance microcontroller. The accuracy rate of fault and crack detection is around 97%, which is for 2 mm crack. Along with this GPS module accurately track fault location. GSM module successfully send the alert message quickly after detecting the fault in the track. Hence the response time is very less and accurate. This system is implemented in order to ensure safety for the railway track and prevent the accidents. Hence the system is useful for improving overall transport safety.

关键词： GSM Accuracy Microcontrollers Fault location Rail transportation Real-time systems Sensors Safety Internet of Things Global Positioning System

来源：评论

学校读者我要写书评

暂无评论

Heart Diseases Prediction Using Machine Learning Techniques: A Case Study from Jordan

Heart Diseases Prediction Using Machine Learning Techniques:...

引用

Information Technology (ACIT)

作者： Raed Alazaidah Mohammed Abu Safaqah Haneen Alzoubi Hani Omar Maram Y. Al-Safarini Esraa Abu Elsoud Ali Elrashidi Mo’Ath Alluwaici Suhaila Abu Owaida Department of Data Science and AI Faculty of IT Zarqa University Zarqa Jordan Department of Mechanical Engineering Global College of Engineering and Technology (GCET) Muscat Sultanate of Oman Department of Computer Science Faculty of IT Applied Science Private University Amman Jordan Department of Computer Science Faculty of IT Zarqa University Zarqa Jordan Department of Electrical Engineering University of Business and Technology Jeddah Saudi Arabia Department of Computer Science Faculty of Information Technology Al-al-Bayt University Mafraq Jordan

ISBN: (数字)9798331540012

ISBN: (纸本)9798331540029

Heart disease is one of the most common diseases in Jordan. It is a major reason of death among Jordanian adult citizens. Worldwide, an average of 56,000 people dies each day or one death every 1.5 seconds. Hence, this research is interested in the early prediction of this disease among Jordanian people. To achieve this main objective, Machine Learning (ML) is utilized through a large number of classification models and considering five well-known evaluation metrics. These classification models have been trained on a primary dataset that has been collected for the purpose of the research. The results revealed that RandomForest and RandomCommittee are the best classification models to handle the task of the early prediction of Heart disease in Jordan.

关键词： Heart Measurement Machine learning Predictive models Information technology Diseases

来源：评论

学校读者我要写书评

暂无评论

Optimizing Clustering Approaches in Cloud Environments

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2023年第19期17卷 70-94页

作者： Al-Ghuwairi, Abdel-Rahman Al-Fraihat, Dimah Sharrab, Yousef Kreishan, Yazeed Alsarhan, Ayoub Idhaim, Hasan Qahmash, Ayman Department of Software Engineering Faculty of Prince Al-Hussein Bin Abdallah II for Information Technology The Hashemite University Zarqa Jordan Department of Software Engineering Faculty of Information Technology Isra University Amman Jordan Department of Data Science and Artificial Intelligence Faculty of Information Technology Isra University Amman Jordan Department of Information Technology Faculty of Prince Al-Hussein Bin Abdallah II for Information Technology The Hashemite University Zarqa Jordan Department of Information Systems Faculty of Prince Al-Hussein Bin Abdallah II for Information Technology The Hashemite University Zarqa Jordan Department of Information Systems Computer Science College King Khalid University Abha Saudi Arabia

This study focuses on the challenge of developing abstract models to differentiate various cloud resources. It explores the advancements in cloud products that offer specialized services to meet specific external needs. The study proposes a new approach to request processing in clusters, improving downtime, load distribution, and overall performance. A comparison of three clustering approaches is conducted: local single cluster, local multiple clusters, and multiple cloud clusters. Performance, scalability, fault tolerance, resource allocation, availability, and cost-effectiveness are evaluated through experiments with 50 requests. All three approaches achieve a 100% success rate, but processing times vary. The local single cluster has the longest duration, while the local multiple clusters and multiple cloud clusters perform better and offer faster processing, scalability, fault tolerance, and availability. From a cost perspective, the local single cluster and local multiple clusters incur capital and operational expenses, while the multiple cloud clusters follow a pay-as-you-go model. Overall, the local multiple clusters and multiple cloud clusters outperform the local single cluster in terms of performance, scalability, fault tolerance, resource allocation, availability, and cost-effectiveness. These findings provide valuable insights for selecting appropriate clustering strategies in cloud environments. © 2023 by the authors of this article. Published under CC-BY.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

ATTACKING GRAPH NEURAL NETWORKS WITH BIT FLIPS: WEISFEILER AND LEHMAN GO INDIFFERENT

arXiv

引用

arXiv 2023年

作者： Kummer, Lorenz Moustafa, Samir Kriege, Nils M. Gansterer, Wilfried N. Faculty of Computer Science University of Vienna Vienna Austria UniVie Doctoral School Computer Science University of Vienna Vienna Austria Research Network Data Science University of Vienna Vienna Austria

Prior attacks on graph neural networks have mostly focused on graph poisoning and evasion, neglecting the network’s weights and biases. Traditional weight-based fault injection attacks, such as bit flip attacks used for convolutional neural networks, do not consider the unique properties of graph neural networks. We propose the Injectivity Bit Flip Attack, the first bit flip attack designed specifically for graph neural networks. Our attack targets the learnable neighborhood aggregation functions in quantized message passing neural networks, degrading their ability to distinguish graph structures and losing the expressivity of the Weisfeiler-Lehman test. Our findings suggest that exploiting mathematical properties specific to certain graph neural network architectures can significantly increase their vulnerability to bit flip attacks. Injectivity Bit Flip Attacks can degrade the maximal expressive Graph Isomorphism Networks trained on various graph property prediction datasets to random output by flipping only a small fraction of the network’s bits, demonstrating its higher destructive power compared to a bit flip attack transferred from convolutional neural networks. Our attack is transparent and motivated by theoretical insights which are confirmed by extensive empirical results. © 2023, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

HVQ-VAE: Variational auto-encoder with hyperbolic vector quantization

引用

computer Vision and Image Understanding 2025年 258卷

作者： Chen, Shangyu Fang, Pengfei Harandi, Mehrtash Le, Trung Cai, Jianfei Phung, Dinh Faculty of Information Technology Department of Data Science and AI Monash University Exhibition Walk ClaytonVIC3168 Australia School of Computer Science and Engineering Southeast University Nanjing210096 China Faculty of Engineering Department of Electrical and Computer Systems Engineering Monash University Exhibition Walk ClaytonVIC3168 Australia

Vector quantized-variational autoencoder (VQ-VAE) and its variants have made significant progress in creating discrete latent space via learning a codebook. Previous works on VQ-VAE have focused on discrete latent spaces in Euclidean or in spherical spaces. This paper studies the geometric prior of hyperbolic spaces as a way to improve the learning capacity of VQ-VAE. That being said, working with the VQ-VAE in the hyperbolic space is not without difficulties, and the benefits of using hyperbolic space as the geometric prior for the latent space have never been studied in VQ-VAE. We bridge this gap by developing the VQ-VAE with hyperbolic vector quantization. To this end, we propose the hyperbolic VQ-VAE (HVQ-VAE), which learns the latent embedding of data and the codebook in the hyperbolic space. Specifically, we endow the discrete latent space in the Poincaré ball, such that the clustering algorithm can be formulated and optimized in the Poincaré ball. Thorough experiments against various baselines are conducted to evaluate the superiority of the proposed HVQ-VAE empirically. We show that HVQ-VAE enjoys better image reconstruction, effective codebook usage, and fast convergence than baselines. We also present evidence that HVQ-VAE outperforms VQ-VAE in low-dimensional latent space. © 2025 Elsevier Inc.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Moving towards FAIR mappings and crosswalks

Moving towards FAIR mappings and crosswalks

引用

2024 Joint Ontology Workshops - Episode X: The Tukker Zomer of Ontology, and Satellite Events, JOWO 2024

作者： Martínková, Jana Juty, Nick Beltran, Alejandra Gonzalez Goble, Carole Le Franc, Yann e-Science Data Factory S.A.S.U. Montpellier France Czech Technical University in Prague Faculty of Information Technology Prague160 00 Czech Republic The University of Manchester Department of Computer Science Oxford Road ManchesterM13 9PL United Kingdom Scientific Computing Science and Technology Facilities Council Harwell Campus OX11 0QX United Kingdom

Mappings and crosswalks are key elements to ensure semantic interoperability as well as metadata and data integration between different information systems. Designing FAIR compliant systems requires making sure all the elements that constitute the systems are themselves FAIR to support machine-actionability and automation. This paper describes the ongoing European and international effort to build a framework for FAIR mappings and crosswalks. This framework aims to be generic enough to capture the diverse set of use cases and methodologies across domains and communities. It should be composed of a set of technical recommendations to aid compliance with FAIR principles, a set of models for machine-actionable mappings and crosswalks as well as a practical framework with aligned good practices to support the creation of mappings by scientific communities. Developed in the context of FAIR IMPACT, a Horizon Europe project, this work will be pursued within a more international context as a Research data Alliance Working Group. © 2024 Copyright for this paper by its authors.

关键词： Mapping

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：