检索结果-内蒙古大学图书馆

19th International Conference on Web Information Systems and Technologies, WEBIST 2023

作者： Nikolaou, Michalis Drakopoulos, Georgios Mylonas, Phivos Sioutas, Spyros Computer Engineering and Informatics Department University of Patras Patras Greece Department of Informatics Ionian Univerity Kerkyra Greece Informatics and Computer Engineering Department University of West Attica Athens Greece

ISBN: (纸本)9789897586729

Intelligent agents (IAs) are highly autonomous software applications designed for performing tasks in a broad spectrum of virtual environments by circulating freely around them, possibly in numerous copies, and taking actions as needed, therefore increasing human digital awareness. Consequently, IAs are indispensable for large scale digital infrastructure across fields so diverse as logistics and long supply chains, smart cities, enterprise and Industry 4.0 settings, and Web services. In order to achieve their objectives, frequently IAs rely on machine learning algorithms. One such prime example, which lies in the general direction of evaluating the network structure integrity, is link prediction, which depending on the context may denote growth potential or a malfunction. IAs employing machine learning algorithms and local structural graph attributes pertaining to connectivity patterns are presented. Their performance is evaluated with metrics including the F1 score and the ROC curve on a benchmark dataset of scientific citations provided by Neo4j containing ground truth. Copyright © 2023 by SCITEPRESS - Science and Technology Publications, Lda. Under CC license (CC BY-NC-ND 4.0)

关键词： Intelligent agents

来源：评论

学校读者我要写书评

暂无评论

Credit card default prediction using ML and DL techniques

引用

Internet of Things and Cyber-Physical Systems 2024年第1期4卷 293-306页

作者： Wahab, Fazal Khan, Imran Sabada, Sneha Corvit Systems Peshawar Pakistan Department of Informatics University of Sussex United Kingdom Department of Engineering and Computer Science University of Hertfordshire United Kingdom

The banking sector is widely acknowledged for its intrinsic unpredictability and susceptibility to risk. Bank loans have emerged as one of the most recent services offered over the past several decades. Banks typically serve as intermediaries for loans, investments, short-term loans, and other types of credit. The usage of credit cards is experiencing a steady increase, thereby leading to a rise in the default rate that banks encounter. Although there has been much research investigating the efficacy of conventional Machine Learning (ML) models, there has been relatively less emphasis on Deep Learning (DL) techniques. The application of DL approaches to credit card default prediction has not been extensively researched despite their considerable potential in numerous fields. Moreover, the current literature frequently lacks particular information regarding the DL structures, hyperparameters, and optimization techniques employed. To predict credit card default, this study evaluates the efficacy of a DL model and compares it to other ML models, such as Decision Tree (DT) and Adaboost. The objective of this research is to identify the specific DL parameters that contribute to the observed enhancements in the accuracy of credit card default prediction. This research makes use of the UCI ML repository to access the credit card defaulted customer dataset. Subsequently, various techniques are employed to preprocess the unprocessed data and visually present the outcomes through the use of exploratory data analysis (EDA). Furthermore, the algorithms are hypertuned to evaluate the enhancement in prediction. We used standard evaluation metrics to evaluate all the models. The evaluation indicates that the AdaBoost and DT exhibit the highest accuracy rate of 82 % in predicting credit card default, surpassing the accuracy of the ANN model, which is 78 %. © 2024 The Authors

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

IoT: Communication protocols and security threats

引用

Internet of Things and Cyber-Physical Systems 2023年第1期3卷 1-13页

作者： Gerodimos, Apostolos Maglaras, Leandros Ferrag, Mohamed Amine Ayres, Nick Kantzavelou, Ioanna School of Computer Science and Informatics University of Thessaly Lamia Greece School of Computing at Edinburgh Napier University Edinburgh United Kingdom Technology Innovation Institute Abu Dhabi United Arab Emirates School of Computer Science and Informatics De Montfort University Leicester United Kingdom School of Engineering Dept.of Informatics and Computer Engineering University of West Attica Athens Greece

In this study, we review the fundamentals of IoT architecture and we thoroughly present the communication protocols that have been invented especially for IoT technology. Moreover, we analyze security threats, and general implementation problems, presenting several sectors that can benefit the most from IoT development. Discussion over the findings of this review reveals open issues and challenges and specifies the next steps required to expand and support IoT systems in a secure framework. © 2023 The Authors

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Optimizing Power Allocation and Beamforming in mmWave-NOMA Downlink with Deep Reinforcement Learning

Optimizing Power Allocation and Beamforming in mmWave-NOMA D...

引用

2024 IEEE Middle East Conference on Communications and Networking, MECOM 2024

作者： Kasgari, Abbas Akbarpour Chrysostomou, Chrysostomos Frederick University and Frederick Research Center Computer Engineering and Informatics Department of Electrical Engineering Nicosia Cyprus

ISBN: (纸本)9798350376715

The high demand for data rates in the fifth generation (5G) and beyond of wireless communication can be met by the Non-Orthogonal Multiple Access (NOMA) approach in the millimeter-wave (mmWave) frequency band. Joint power allocation and beamforming for 5 G and beyond mmWave-NOMA systems are essential, which can be achieved through optimization approaches. To this end, we have employed a Deep Reinforcement Learning (DRL) approach for policy generation, leading to an optimized sum-rate for users. Unlike existing methods, our approach is not susceptible to channel impulse response (CIR) estimation errors. The actor-critic framework is utilized to measure the immediate reward and provide new actions to maximize the overall Q-value of the network. The immediate reward is defined based on the summation of the rates of two users, considering the minimum guaranteed rate for each user and the total consumed power as constraints. The simulation results demonstrate the superiority of the proposed approach compared to state-of-the-art counterparts, including Time-Division Multiple Access (TDMA) and NLOS-NOMA optimization strategies, in terms of sum-rate of users, while considering both perfect and imperfect channel state information (CSI) at the receiver. This work can also be beneficial for communications in vehicular networks, particularly in applications involving Collective Perception Messages (CPMs) dissemination for autonomous driving. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

(POSTER) A Holistic IoT-Enabled Approach for Indoor Air Quality Control 19

(POSTER) A Holistic IoT-Enabled Approach for Indoor Air Qual...

引用

19th Annual International Conference on Distributed Computing in Smart Systems and the Internet of Things, DCOSS-IoT 2023

作者： Kalioras, Fotios Filios, Gabriel Karatzas, Stylianos Nikoletseas, Sotiris University of Patras Department of Computer Engineering and Informatics Greece University of Patras Computer Technology Institute and Press Diophantus Department of Computer Engineering and Informatics Greece University of Patras Department of Civil Engineering Greece

ISBN: (纸本)9798350346497

Indoor air quality (IAQ) is an important yet often overlooked aspect of public health, with poor IAQ contributing to a significant number of diverse health problems worldwide. Existing air quality standards have failed to fully address the problem, however emerging technologies in the field of IoT have demonstrated promise in effectively addressing this issue. This concept paper advocates a hybrid hierarchy system for IAQ monitoring that incorporates both offline and online connectivity. The system utilizes sensing elements that can perform a wide range of functions, including autocalibration, pollution event detection, and more, autonomously from the network. By combining a gateway device, the system's capabilities are enhanced, providing increased data granularity, additional calibration and sensing options as well as connection with Building Management Systems (BMS). Furthermore, by connecting the gateway to the cloud, the system can perform more advanced data analysis and machine learning, providing users with insights into not only air quality but also general environmental quality. Key features of the envisioned system include the integration of subjective perception of pollution via crowdsourcing, a TinyML technology at the edge, digital twins, and an optimised redundancy of sensors that can alleviate poor accuracy and drift as well as capture the spatial dispersion of pollution. © 2023 IEEE.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Optimized Price Prediction of Cryptocurrencies using Deep Learning on High-Volume Time Series Data 15

Optimized Price Prediction of Cryptocurrencies using Deep Le...

引用

15th International Conference on Information, Intelligence, Systems and Applications, IISA 2024

作者： Vonitsanos, Gerasimos Kanavos, Andreas Grivokostopoulou, Foteini Sioutas, Spyros University of Patras Computer Engineering and Informatics Department Patras Greece Ionian University Department of Informatics Corfu Greece Computer Technology Institute and Press 'Diophantus' Patras Greece

ISBN: (纸本)9798350368833

Statistical models, enhanced by deep learning techniques, have become pivotal in various predictive tasks, including financial forecasting. This paper addresses the challenge of predicting cryptocurrency prices, utilizing a dataset comprising various cryptocurrencies treated as time series. We employ several deep neural network architectures-including Multilayer Perceptrons (MLP), Recurrent Neural Networks (RNN), Long Short-Term Memory networks (LSTM), and Bidirectional LSTM networks-to forecast future prices. Our methodology involves a detailed analysis of cryptocurrency time series to inform the design of these networks. The performance of each model is rigorously compared, highlighting their predictive capabilities in the context of cryptocurrency markets. This study not only contributes to the empirical literature by applying advanced neural networks to high-volume financial data but also provides a comparative analysis that may guide future applications of deep learning in economic forecasting. © 2024 IEEE.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Improved Accuracy of Decision Tree with XGBoost Technique in Cat Skin Disease Diagnosis 4

Improved Accuracy of Decision Tree with XGBoost Technique in...

引用

4th International Conference of Science and Information Technology in Smart Administration, ICSINTESA 2024

作者： Safrina, Nanda Lydia, Maya Silvi Nasution, Benny Benyamin Universitas Sumatera Utara Master of Informatics Faculty of Computer Science and Information Technology Medan Indonesia Politeknik Negeri Medan Department of Computer Engineering and Informatics Medan Indonesia

ISBN: (纸本)9798350376111

This research aims to develop an expert system for initial diagnoses of skin diseases in cats using the Decision Tree method. It assists cat owners in identifying skin diseases based on observed symptoms. Data from expert veterinarian drh. Ismi Azima, including various types of cat skin diseases and their symptoms, were used. The research employs 80% training data and 20% testing data to develop the classification model. Testing results indicate the Decision Tree model achieves up to 90% average accuracy in diagnosing cat skin diseases based on 50 datasets. This expert system aids in diagnosis and provides treatment and prevention solutions, beneficial for cat owners, especially in areas with limited veterinary access. In conclusion, this Decision Tree-based expert system effectively provides initial diagnoses of skin diseases in cats with high accuracy. © 2024 IEEE.

关键词： Cat Skin Diseases Decision Tree Expert System XGBoost

来源：评论

学校读者我要写书评

暂无评论

Developing phoneme-based lip-reading sentences system for silent speech recognition

引用

CAAI Transactions on Intelligence Technology 2023年第1期8卷 129-138页

作者： Randa El-Bialy Daqing Chen Souheil Fenghour Walid Hussein Perry Xiao Omar HKaram Bo Li School of Engineering London South Bank UniversityLondonUK Faculty of Informatics and Computer Science British University in EgyptCairoEgypt School of Electronics and Informatics Northwestern Polytechnical UniversityXi'anChina

Lip-reading is a process of interpreting speech by visually analysing lip *** research in this area has shifted from simple word recognition to lip-reading sentences in the *** paper attempts to use phonemes as a classification schema for lip-reading sentences to explore an alternative schema and to enhance system *** classification schemas have been investigated,including characterbased and visemes-based *** visual front-end model of the system consists of a Spatial-Temporal(3D)convolution followed by a 2D *** utilise multi-headed attention for phoneme recognition *** the language model,a Recurrent Neural Network is *** performance of the proposed system has been testified with the BBC Lip Reading Sentences 2(LRS2)benchmark *** with the state-of-the-art approaches in lip-reading sentences,the proposed system has demonstrated an improved performance by a 10%lower word error rate on average under varying illumination ratios.

关键词： deep learning deep neural networks lip-reading phoneme-based lip-reading spatial-temporal convolution,transformers

来源：评论

学校读者我要写书评

暂无评论

Temperature and Humidity Control System to Address Filament Brittleness in 3D Printers 2

Temperature and Humidity Control System to Address Filament ...

引用

2nd International Symposium on Information Technology and Digital Innovation, ISITDI 2024

作者： Erlina, Tati Violani, Salsa Kiki Suwandi, Rifki Nugroho, Yusuf Sulistyo Islam, Syful Universitas Andalas Computer Engineering Department Padang Indonesia Universitas Muhammadiyah Surakarta Informatics Engineering Surakarta Indonesia BSMRSTU Computer Science and Engineering Gopalganj Bangladesh

ISBN: (纸本)9798350389241

Additive manufacturing, mainly 3D printing, has emerged as a transformative technology with widespread applications across various industries. Despite its advancements, filament brittleness remains a significant challenge, undermining the quality and reliability of printed objects. In order to address this challenge, this study built a specialized temperature and humidity management system specifically for 3D printing applications. The system utilizes a Proportional-Integral-Derivative (PID) control technique to regulate the temperature within the filament storage environment, mitigating the impact of thermal fluctuations and moisture absorption. The system has been carefully developed and tested to assure optimal printing conditions, exceptional filament quality, and uniform print accuracy and precision. Since hardware testing confirms minimum disparities between sensor readings and reference measurements, reliability in environmental management is ensured for optimized print outcomes. Moreover, software testing ensures the PID controller's efficient functionality by providing real-time monitoring and control capabilities. Functional testing reveals the system's effectiveness in maintaining optimal storage conditions for various filament types, improving the quality of prints, and minimizing waste. Incorporating essential components such as sensors, actuators, and user interface elements guarantees seamless operation and intuitive engagement. © 2024 IEEE.

关键词： Humidity control

来源：评论

学校读者我要写书评

暂无评论

A MLP-Mixer and mixture of expert model for remaining useful life prediction of lithium-ion batteries

引用

Frontiers of computer Science 2024年第5期18卷 1-10页

作者： Lingling ZHAO Shitao SONG Pengyan WANG Chunyu WANG Junjie WANG Maozu GUO Faculty of Computing Harbin Institute of TechnologyHarbin 150001China School of Electrical Engineering Liaoning University of TechnologyJinzhou 121004China School of Computer Science Northeast Electric Power UniversityJilin 132000China Department of Medical Informatics School of Biomedical Engineering and InformaticsNanjing Medical UniversityNanjing 211166China School of Electrical and Information Engineering Beijing University of Civil Engineering and ArchitectureBeijing 100044China

Accurately predicting the Remaining Useful Life(RUL)of lithium-ion batteries is crucial for battery management *** learning-based methods have been shown to be effective in predicting RUL by leveraging battery capacity time series ***,the representation learning of features such as long-distance sequence dependencies and mutations in capacity time series still needs to be *** address this challenge,this paper proposes a novel deep learning model,the MLP-Mixer and Mixture of Expert(MMMe)model,for RUL *** MMMe model leverages the Gated Recurrent Unit and Multi-Head Attention mechanism to encode the sequential data of battery capacity to capture the temporal features and a re-zero MLP-Mixer model to capture the high-level ***,we devise an ensemble predictor based on a Mixture-of-Experts(MoE)architecture to generate reliable RUL *** experimental results on public datasets demonstrate that our proposed model significantly outperforms other existing methods,providing more reliable and precise RUL predictions while also accurately tracking the capacity degradation *** code and dataset are available at the website of github.

关键词： lithium-ion battery remaining useful life deep learning MLP-Mixer mixture-of-experts

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：