检索结果-内蒙古大学图书馆

Ontologies and Machine Learning Models to Enhance Health Informatics: A Survey, Challenges and Future Directions

IAENG International Journal of Applied Mathematics 2025年第3期55卷 475-499页

作者： Tiaiba, Hafida Sabri, Lyazid Kazar, Okba Department of Computer Science Mohamed El Bachir El Ibrahimi University Bordj Bou Arreridj Algeria Laboratory Mohamed El Bachir El Ibrahimi University Bordj Bou Arreridj Algeria College of Arts Sciences and Information Technology Department of Computer Science University of Kalba Sharjah United Arab Emirates

Medical reports and narratives especially present considerable challenges due to their complicated medical terminology, frequent use of abbreviations, and diversity of language structures. As a result of these complexities, it can be hard to extract and interpret meaningful information straightforwardly and consistently. It is essential for a comprehensive understanding of healthcare data in the medical domain to identify patterns, recognize subtle cues, and distill critical information from different sources. Natural language processing, machine learning, and semantic analysis play fundamental roles in overcoming these obstacles. These tools streamline the information retrieval process and enable the discovery of hidden correlations and trends within medical texts, as a result, more informed decision-making is enabled and healthcare insights are enhanced. This study analyzes a range of academic publications, including books, doctoral theses, and articles, and it conducts a comparative study of recent survey papers to address limitations in prior research. While previous surveys have focused on specific areas like named entity recognition (NER), relationship extraction, text vectorization, and classification methods, this research adopts a broader perspective by exploring various aspects of information extraction and medical document classification. The study highlights the critical purpose of ontologies, especially medical ones, in knowledge representation. These ontologies ensure semantic interpretation, reduce ambiguity, and enhance information sharing among researchers and healthcare professionals. Additionally, the research emphasizes the benefits of integrating multiple datasets and combining machine learning methods with ontologies to improve the accuracy and efficiency of medical text analysis providing better decision-making opportunities. © (2025), (International Association of Engineers). All rights reserved.

关键词： Knowledge representation

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Blockchain Platforms for Adapting Proof of Authentication in IoT 7

Comparative Analysis of Blockchain Platforms for Adapting Pr...

引用

7th International Conference on Advanced Communication Technologies and Networking, CommNet 2024

作者： Aghroud, Mohamed Elgountery, Yassin Oualla, Mohamed Bermi, Lahcen El Sadiq, Abdelalim My Ismail University GLISI Team FST Errachidia Department Computer Science Errachidia Morocco Ibn Tofail University LaRI Laboratory Department of Computer Science Faculty of Science Kenitra Morocco

ISBN: (纸本)9798350367027

Blockchain technology, a decentralized and tamper-resistant framework, has gained significant attention for its potential to enhance trust, transparency, and security in digital interactions. When integrated with the Internet of Things (IoT)-a network of interconnected devices that exchange data autonomously-it unlocks new opportunities for secure, scalable, and efficient systems. Selecting the right blockchain platform is crucial to developing robust blockchain-based applications tailored to IoT's unique demands. This paper provides a comparative study of five leading blockchain platforms: Multichain, Hyperledger Besu, Open Ethereum, Go Ethereum, and Substrate. The evaluation focuses on their adaptability to IoT environments and their ability to implement proof of authentication (PoAh) as a consensus algorithm. By examining key aspects such as scalability, flexibility, interoperability, resource efficiency, and ease of integration, this study aims to identify the most suitable platform for IoT-centric blockchain solutions. The findings highlight the strengths and limitations of each platform, offering practical insights to guide the selection of a blockchain platform optimized for IoT applications and consensus algorithm proof of authentication. © 2024 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Filtering With Sample-Based Approximation Under Constrained Communication:Progress, Insights and Trends

引用

IEEE/CAA Journal of Automatica Sinica 2024年第7期11卷 1539-1556页

作者： Weihao Song Zidong Wang Zhongkui Li Jianan Wang Qing-Long Han IEEE the State Key Laboratory for Turbulence and Complex Systems Department of Mechanics and Engineering ScienceCollege of Engineering Peking University the Department of Computer Science Brunel University London the School of Aerospace Engineering Beijing Institute of Technology the School of Science Computing and Engineering Technologies Swinburne University of Technology

The nonlinear filtering problem has enduringly been an active research topic in both academia and industry due to its ever-growing theoretical importance and practical *** main objective of nonlinear filtering is to infer the states of a nonlinear dynamical system of interest based on the available noisy measurements. In recent years, the advance of network communication technology has not only popularized the networked systems with apparent advantages in terms of installation,cost and maintenance, but also brought about a series of challenges to the design of nonlinear filtering algorithms, among which the communication constraint has been recognized as a dominating concern. In this context, a great number of investigations have been launched towards the networked nonlinear filtering problem with communication constraints, and many samplebased nonlinear filters have been developed to deal with the highly nonlinear and/or non-Gaussian scenarios. The aim of this paper is to provide a timely survey about the recent advances on the sample-based networked nonlinear filtering problem from the perspective of communication constraints. More specifically, we first review three important families of sample-based filtering methods known as the unscented Kalman filter, particle filter,and maximum correntropy filter. Then, the latest developments are surveyed with stress on the topics regarding incomplete/imperfect information, limited resources and cyber ***, several challenges and open problems are highlighted to shed some lights on the possible trends of future research in this realm.

关键词： Communication constraints maximum correntropy filter networked nonlinear filtering particle filter sample-based approximation unscented Kalman filter

来源：评论

学校读者我要写书评

暂无评论

Leveraging Data Efficient Image Transformer (DeIT) for Road Crack Detection and Classification

Leveraging Data Efficient Image Transformer (DeIT) for Road ...

引用

2024 International Conference on Advances in Computing, Communication, Electrical, and Smart Systems, iCACCESS 2024

作者： Anzum, Humaira Sammo, Md. Nabil Sadd Akhter, Shamim Ahsanullah University of Science and Technology Aisip Laboratory Department of Computer Science and Engineering Dhaka1208 Bangladesh Department of Computer Science and Engineering Bangladesh University of Engineering and Technology Dhaka1000 Bangladesh

ISBN: (纸本)9798350350289

Accurate detection and classification of road faults such as cracks is critical for transportation infrastructure maintenance. Road cracks impede comfortable traveling, endanger passenger safety, and create incidents. In this paper, we propose a new Data Efficient Image Transformer (DeIT)-based Road crack identification system that can distinguish between cracks and non-cracks in road surfaces. This study also evaluates how well DeIT performs in comparison with YOLOv5, YOLOv8, Xception, ResNet50 and MobileNetV2 deep learning algorithms. We have used a publicly available dataset consisting of road images from Kaggle Concrete Data to train and test our model. For identifying cracked and non-cracked road surfaces, our proposed model achieved the highest 99.75 % accuracy on the test dataset using DeIT algorithm. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An Intrusion Detection System Based on HiTar-2024 Dataset Generation from LOG Files for Smart Industrial Internet-of-Things Environment

引用

computers, Materials & Continua 2025年第3期82卷 4535-4554页

作者： Tarak Dhaouadi Hichem Mrabet Adeeb Alhomoud Abderrazak Jemai SER’Com Laboratory Tunisia Polytechnic SchoolUniversity of CarthageTunis2078Tunisia Computer Sciences Department Faculty of Sciences of TunisUniversity of Tunis El ManarTunis1001Tunisia Department of Science College of Science and Theoretical StudiesSaudi Electronic UniversityRiyadh11673Saudi Arabia Computer Sciences Department INSATUniversity of CarthageTunis1080Tunisia

The increasing adoption of Industrial Internet of Things(IIoT)systems in smart manufacturing is leading to raise cyberattack numbers and pressing the requirement for intrusion detection systems(IDS)to be ***,existing datasets for IDS training often lack relevance to modern IIoT environments,limiting their applicability for research and *** address the latter gap,this paper introduces the HiTar-2024 dataset specifically designed for IIoT *** a consequence,that can be used by an IDS to detect imminent ***,HiTar-2024 was generated using the AREZZO simulator,which replicates realistic smart manufacturing *** generated dataset includes five distinct classes:Normal,Probing,Remote to Local(R2L),User to Root(U2R),and Denial of Service(DoS).Furthermore,comprehensive experiments with popular Machine Learning(ML)models using various classifiers,including BayesNet,Logistic,IBK,Multiclass,PART,and J48 demonstrate high accuracy,precision,recall,and F1-scores,exceeding 0.99 across all ML *** latter result is reached thanks to the rigorous applied process to achieve this quite good result,including data pre-processing,features extraction,fixing the class imbalance problem,and using a test option for model *** comprehensive approach emphasizes meticulous dataset construction through a complete dataset generation process,a careful labelling algorithm,and a sophisticated evaluation method,providing valuable insights to reinforce IIoT system ***,the HiTar-2024 dataset is compared with other similar datasets in the literature,considering several factors such as data format,feature extraction tools,number of features,attack categories,number of instances,and ML metrics.

关键词： Intrusion detection system industrial IoT machine learning security cyber-attacks dataset

来源：评论

学校读者我要写书评

暂无评论

引用

Multimedia Tools and Applications 2024年第13期84卷 12141-12162页

作者： Darraz, Nossayba Karabila, Ikram El-Ansari, Anas Alami, Nabil El Mallahi, Mostafa IPI Laboratory Department of Mathematics and Computer Sciences High Normal School Sidi Mohamed Ben Abdellah University Fez Morocco MASI Laboratory Computer Science Department Polydisciplinary Faculty Mohammed 1st University Nador Morocco MASI Laboratory Mohammed First University Higher School of Technology Nador Morocco

Trend detection is the process of identifying patterns in data over time. It is used to identify trends in various fields, such as business, finance, marketing, healthcare, and others. For example, in e-commerce, trend detection can be used to identify changes in consumer purchasing behavior, such as an increase in demand for a particular product. Combining trend detection with Sentiment Analysis (SA) can give e-commerce businesses a deeper understanding of customer sentiment over time, allowing them to make more informed decisions about how to improve the customer experience. Our proposed system integrates both the Machine Learning approach and Moving Average (MA) method for sentiment classification of product reviews and trend detection, respectively. To begin, we preprocess the product reviews to facilitate sentiment analysis. We compare the effectiveness of Lexicon-based analysis with machine learning algorithms to identify the optimal approach. The preprocessed reviews are transformed into a vector representation to enable the application of Machine Learning (ML) techniques. Multiple ML algorithms are trained and evaluated based on metrics such as accuracy, F1 score, precision, and recall to determine the best-performing model for sentiment classification. Additionally, we employ clustering techniques to identify the most favorable product. Finally, the MA technique is applied to detect trending products. Our findings indicate that the SVM classifier with BOW achieved an impressive accuracy of 89.26% for sentiment classification. Furthermore, by utilizing K-Means clustering, we obtained a high silhouette score, outperforming other clustering methods, in identifying trending products. Our study highlights that the combination of sentiment analysis and trend detection can provide valuable insights for e-commerce businesses. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

LibMTL: A Python Library for Deep Multi-Task Learning

引用

Journal of Machine Learning Research 2023年第1期24卷 1-7页

作者： Lin, Baijiong Zhang, Yu The Hong Kong University of Science and Technology Guangzhou China Department of Computer Science and Engineering Southern University of Science and Technology Peng Cheng Laboratory China

This paper presents LibMTL, an open-source Python library built on PyTorch, which provides a unified, comprehensive, reproducible, and extensible implementation framework for Multi-Task Learning (MTL). LibMTL considers different settings and approaches in MTL, and it supports a large number of state-of-the-art MTL methods, including 13 optimization strategies and 8 architectures. Moreover, the modular design in LibMTL makes it easy to use and well extensible, thus users can easily and fast develop new MTL methods, compare with existing MTL methods fairly, or apply MTL algorithms to real-world applications with the support of LibMTL. The source code and detailed documentations of LibMTL are available at https://***/median-research-group/LibMTL and https://***, respectively. ©2023 Baijiong Lin and Yu Zhang.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Meteorological Downscaling Based on Dual Learning and Subgrid-scale Auxiliary Information

引用

Advances in Atmospheric sciences 2025年第1期42卷 53-66页

作者： Jing HU Jialing MU Xiaomeng HUANG Xi WU Department of Computer Science Chengdu University of Information TechnologyChengdu 610225China Department of Earth System Science Ministry of Education Key Laboratory for Earth System ModelingInstitute for Global Change StudiesTsinghua UniversityBeijing 100084China

Climate downscaling is used to transform large-scale meteorological data into small-scale data with enhanced detail,which finds wide applications in climate modeling,numerical weather forecasting,and renewable *** deeplearning-based downscaling methods effectively capture the complex nonlinear mapping between meteorological data of varying scales,the supervised deep-learning-based downscaling methods suffer from insufficient high-resolution data in practice,and unsupervised methods struggle with accurately inferring small-scale specifics from limited large-scale inputs due to small-scale *** article presents DualDS,a dual-learning framework utilizing a Generative Adversarial Network–based neural network and subgrid-scale auxiliary information for climate *** a learning method is unified in a two-stream framework through up-and downsamplers,where the downsampler is used to simulate the information loss process during the upscaling,and the upsampler is used to reconstruct lost details and correct errors incurred during the *** dual learning strategy can eliminate the dependence on high-resolution ground truth data in the training process and refine the downscaling results by constraining the mapping *** findings demonstrate that DualDS is comparable to several state-of-the-art deep learning downscaling approaches,both qualitatively and ***,for a single surface-temperature data downscaling task,our method is comparable with other unsupervised algorithms with the same dataset,and we can achieve a 0.469 dB higher peak signal-to-noise ratio,0.017 higher structural similarity,0.08 lower RMSE,and the best correlation *** summary,this paper presents a novel approach to addressing small-scale uncertainty issues in unsupervised downscaling processes.

关键词： downscaling unsupervised deep learning dual learning auxiliary information

来源：评论

学校读者我要写书评

暂无评论

Autonomous Data Tiering Using Reinforcement Learning for 3-Tier Hierarchical Storage 8th

Autonomous Data Tiering Using Reinforcement Learning for 3-...

引用

8th International Symposium on Modelling and Implementation of Complex Systems, MISC 2024

作者： Oussama, Nedjah Omar, Mokhtari Fatima, Boumahdi Yasmine, Mancer LRDSI Laboratory Department of Computer Science Faculty of Sciences University of Blida 1 Blida Algeria

ISBN: (纸本)9783031821110

In today’s data-driven world, organizations must efficiently store and manage massive amounts of information. As data generation keeps increasing, the demand for scalable and cost-effective storage solutions becomes critical. Data tiering appears to be a strategic solution to this problem by categorizing data based on access frequency and storing it across multiple storage tiers. This paper presents a new solution for autonomous data tiering using reinforcement learning (RL) within a 3-tier hierarchical storage system. By utilizing the adaptability and learning capabilities of RL, our approach dynamically optimizes data placement, ensuring high-performance access for frequently used data while lowering costs for infrequently accessed data. Our solution integrates an RL agent that is trained to recognize access patterns and make data placement decisions in real-time. This dynamic tiering strategy reduces latency while maintaining low costs. Through extensive experimentation and analysis, we show the effectiveness of our approach, highlighting its potential to transform the way data is handled in large-scale storage systems. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Semantic Framework for Monitoring Wheat Grain Warehouses 13

A Semantic Framework for Monitoring Wheat Grain Warehouses

引用

13th International Conference on Research in ComputIng at Feminine, RIF 2024

作者： Lynda, Djakhdjakha Brahim, Farou Imane, Bouacida Aya, Meguellatni LabSTIC Laboratory Computer Science Department 8 Mai 1945 Guelma University Guelma24000 Algeria Computer Science Department 8 Mai 1945 Guelma University Guelma24000 Algeria

The grain storage ecosystem involves multifaceted interactions among diverse elements responsible for preserving, managing, and utilizing stored grains. In recent years, there has been a notable upsurge in research focused on enhancing the management of grain warehouses. While existing approaches often relied on limited data sources or narrow information scopes, in this paper we diverge significantly by harnessing a broad spectrum of data streams to provide a more comprehensive understanding. Our research endeavors to develop a groundbreaking framework tailored for managing wheat grain warehouses, placing a significant emphasis on integrating heterogeneous data sources. This integration aims to achieve a thorough comprehension of grain historical data, grain storage conditions, insect behavior, and disease dynamics based on a new ontology that encapsulates domain-specific knowledge and offers a structured representation of essential concepts, relationships, and entities. Additionally, our framework implements image processing algorithms designed to detect disease symptoms based on the proposed ontology, thereby enhancing the capability of the system to identify and respond to potential threats to stored grain quality and safety. © 2024 Copyright for this paper by its authors.

关键词： Ontology

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：