检索结果-内蒙古大学图书馆

22nd International Symposium INFOTEH-JAHORINA, INFOTEH 2023

作者： Filipović, Franjo Balen, Josip Damjanovic, Davor Rimal, Rajesh Azeem, Muhammad Moazam Shukla, Adamya Faculty of Electrical Engineering Computer Science and Information Technology Osijek Osijek Croatia TTTech Auto Osijek Croatia Qatar University Department of Computer Science and Engineering Doha Qatar Volvo Group Gto Gothenburg Sweden

ISBN: (纸本)9781665475464

Protecting equipment and objects from fire in warehouses and industry premises is essential due to a high number of people present, valuable equipment or inventory and possibly dangerous goods. It is mostly often conducted by using smoke and fire sensors along with extinguishing systems. Still, in facilities with valuable inventory and equipment, it is also necessary to protect equipment from damage caused by water. This paper proposes a multi-agent robotic fire extinguishing model consisted of autonomous robots divided into two groups: Patrol Robots and Fire Extinguishing (FE) robots, called PR-FER model. The main methodology of the PR-FER model is using small patrol autonomous robots as a surveillance robots that will first map the surveillance area, determine the patrol paths, and conduct surveillance according to the predefined schedule. They are equipped with the devices for detecting fire and high temperatures such as RGB, IR and Thermal Imaging cameras and various sensors. Furthermore, they will have high capacity batteries which will enable them a long autonomy. In case of a detection of too high temperatures and fire, patrol robots would map the dangerous location and call FE robots to extinguish it. The FE robots are more robust and heavier robots equipped with fire extinguishers. During the fire extinguishing procedure the patrol robots would notify the fire department and enable them a video streaming in order to get an early awareness of the situation on the field. © 2023 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

A Performance Study of Selected Machine Learning Techniques for Predicting Heart Diseases 2nd

A Performance Study of Selected Machine Learning Techniques ...

引用

2nd International Conference on Security and Information Technologies with AI, Internet Computing and Big-data Applications, SITAIBA 2023

作者： Olorunfemi, Blessing Oluwatobi Ogunde, Adewale Opeoluwa Adeniyi, Abidemi Emmanuel Awotunde, Joseph Bamidele Imoize, Agbotiname Lucky Li, Chun-Ta Faculty of Natural Sciences Department of Computer Science Redeemer’s University Osun Nigeria Department of Computer Science Bowen University Iwo Nigeria Faculty of Information and Communication Sciences Department of Computer Science University of Ilorin Ilorin240003 Nigeria Faculty of Engineering Department of Electrical and Electronics Engineering University of Lagos Lagos Akoka100213 Nigeria Bachelor’s Program of Artificial Intelligence and Information Security Fu Jen Catholic University New Taipei City24206 Taiwan

ISBN: (纸本)9789819777853

Heart Disease remains a leading cause of mortality worldwide. It alarmingly rises at a quick rate, making early heart disease prediction crucial for effective prevention and timely intervention. Heart disease diagnosis is a difficult process that requires technical skills and accuracy to complete. With improvements in technology, computing has lent its voice to simplify the diagnosis of various health problems. Machine learning uses past or existing history to predict future results. Various machine learning techniques have been developed over the years and used in predicting heart diseases with various levels of performance. Identifying the best-suited machine learning technique to use for prediction purposes can be a challenging task. This research work analyses the performance of seven (7) machine learning techniques, comprising AdaBoost Algorithm, KNN, Logistic Regression, Naïve Bayes Classifier, Random Forest, SVM, and XGBoost. The heart disease dataset was downloaded from the UCI repository and analysed using Python programming language in the Jupyter Notebook environment. A comparative analysis of the seven (7) techniques was performed based on Accuracy, Precision, and Recall. From the results obtained, KNN, Random Forest, and XGBoost showed superior performance over the others with an accuracy of 100%, AdaBoost Algorithm followed with an accuracy of 92.2%, SVM followed with an accuracy of 91.71%, Naïve Bayes Classifier followed with an accuracy of 88.29% while Logistic Regression has the least accuracy of 86.34%. KNN, RF, and XGBoost outperformed AdaBoost, SVN, and LR. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 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 Hybrid Algorithm ACS-GA for Solving the Traveling Salesman Problem 1

引用

15th International Conference on Genetic and Evolutionary Computing, ICGEC 2023

作者： Bai, Zhonghai Snášel, Václav Vo, Bay Kong, Lingping Wang, Xiaopeng Faculty of Electrical Engineering and Computer Science VŠB-Technical University of Ostrava Ostrava70800 Czech Republic Faculty of Information Technology HUTECH University Ho Chi Minh City Viet Nam

ISBN: (数字)9789819700684

ISBN: (纸本)9789819700677

Traveling Salesman Problem (TSP), a well-known combinatorial optimization problem, aims to find the shortest path for a salesman to visit all the given cities and return to the departure city, with each city visited once and only once. To solve the problem, we propose a hybrid metaheuristic algorithm that combines the ant colony system(ACS) and genetic algorithm(GA). Distinguishing from previous hybrid algorithms, the two algorithms in our proposed hybrid algorithm run independently in parallel, exchange each other’s optimal solutions in a fixed iteration cycle and incorporate the exchanged optimal solutions into the independently running algorithm through update pheromone or add to the candidate parent. The experimental part uses data instances with a city size distribution between 51 and 226. The results of running the ACS, GA, Tabu Search (TS), and hybrid algorithms ACS-GA were compared. The results show that our hybrid algorithm ACS-GA outperforms the results of the single algorithm in terms of solution quality and stability overall. This research provides a better solution to optimizing TSP by proposing a novel hybrid metaheuristic algorithm. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Determination of Parameters Affecting the Estimation of Iceberg Draft

引用

China Ocean engineering 2023年第1期37卷 62-72页

作者： Hamed AZIMI Masoud MAHDIANPARI Hodjat SHIRI Civil Engineering Department Faculty of Engineering and Applied ScienceMemorial University of NewfoundlandA1B 3X5St.John’sNLCanada Department of Electrical and Computer Engineering Faculty of Engineering and Applied ScienceMemorial University of NewfoundlandA1B 3X5St.John’sNLCanada C-CORE A1B 3X5St.John’sNLCanada

Recent offshore oil and gas loading facilities developed in the Arctic area have led to a considerable awareness of the iceberg draft approximation, where deep keel icebergs may gouge the ocean floor, and these submarine infrastructures would be damaged in the shallower waters. Developing reliable solutions to estimate the iceberg draft requires a profound understanding of the problem’s dominant parameters. As such, the dimensionless groups of the parameters affecting the iceberg draft estimation were determined for the first time in the present study. Using the dimensionless groups recognized and the linear regression(LR) analysis, nine LR models(i.e., LR 1 to LR 9) were developed and then validated using a comprehensive dataset, which has been constructed in this study. A sensitivity analysis distinguished the premium LR models and important dimensionless groups. The best LR model, as a function of all dimensionless parameters, was able to estimate the iceberg draft with the highest level of precision and correlation along with the lowest degree of complexity. The ratio of iceberg length to iceberg height as the “iceberg length ratio” and the ratio of iceberg width to iceberg height as the “iceberg width ratio” was detected as the important dimensionless groups in the estimation of the iceberg draft. An uncertainty analysis demonstrated that the best LR model was biased towards underestimating the iceberg drafts. The premium LR model outperformed the previous empirical ***, a set of LR-based relationships were derived for estimating the iceberg drafts for practical engineering applications, e.g., the early stages of the iceberg management projects.

关键词： dimensional analysis iceberg draft subsea assets linear regression(LR) sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Information-Bearing RIS Enabled NOMA System

引用

IEEE Transactions on Vehicular Technology 2025年第6期74卷 9904-9909页

作者： Han, Shuai Sun, Zeyang Xu, Sai Xie, Dan Li, Cheng Harbin Institute of Technology School of Electronics and Information Engineering Heilongjiang Harbin150001 China Southeast University National Mobile Communications Research Laboratory Nanjing211111 China Memorial University Electrical and Computer Engineering Faculty of Engineering and Applied Science St. John'sA1B 3X5 Canada

In this correspondence, we investigate an information-bearing reconfigurable intelligent surface (RIS) assisted non-orthogonal multiple access (NOMA) system. In this system, the RIS is segmented into multiple sub-RIS units, each serving as a passive transmitter to deliver information to users via extended backscatter modulation under the NOMA scheme. We aim to maximize the system's weighted sum rate (WSR) by jointly optimizing the active beamformer at the power beacon (PB) and the RIS coefficient vectors, while adhering to constraints related to PB transmission power, RIS coefficients, successive interference cancellation (SIC) decoding rate, and rate fairness. Extensive simulation results verify the feasibility and superiority of the proposed scheme. © 2025 IEEE.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

Decentralized Federated Learning Using the Metropolis-Hastings for Highly Dynamic UAVs 100

Decentralized Federated Learning Using the Metropolis-Hastin...

引用

100th IEEE Vehicular Technology Conference, VTC 2024-Fall

作者： Mynuddin, Mohammed Chowdhury, Zayed Uddin Ahmari, Reza Nabil, Mahmoud Alsharif, Ahmad Homaifar, Abdollah University of North Carolina A&t Department of Electrical and Computer Engineering NC27411 United States Happy Returns Llc GA30328 United States University of Alabama Department of Computer Science AL35487 United States Benha University Faculty of Engineering Department of Electrical Engineering Shoubra Egypt

ISBN: (纸本)9798331517786

Unmanned Aerial Vehicles (UAVs) are increasingly employed in cooperative surveillance missions where data collection across disparate areas is crucial. In such systems, data from all UAVs is collected and processed in a central server, making it vulnerable to breaches and unauthorized access. Federated Learning (FL) addresses these concerns by enabling collaborative model training without centralized data collection. In FL, each UAV trains a local model on its own data and only shares the model updates with a central server. The central server then aggregates these parameters to update a global model, which is redistributed to all participating UAVs. However, FL's reliance on a central server introduces challenges, especially in geographically highly dynamic and dispersed scenarios. The central server can become a single point of failure and may struggle with the communication overhead and latency issues inherent in such dynamic environments. To overcome these limitations, this paper proposes a decentralized federated learning framework for multi-agent UAV systems. This approach facilitates direct sharing of local deep learning (DL) model parameters among UAVs, eliminating the need for a central server. Our approach employs the Metropolis-Hastings algorithm to ensure UAVs achieve consensus on shared model parameters, ensuring balanced weight distribution and stable training processes. We validate our fully distributed DL model aggregation using the ResNet-18 model. Our results confirm DFL's effectiveness in achieving low RMSE values and rapid convergence, comparable to centralized FL, across dynamic UAV networks. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced 5G Device-to-Device (D2D) Security in Spectrum Sharing System 32

Enhanced 5G Device-to-Device (D2D) Security in Spectrum Shar...

引用

32nd International Conference on Software, Telecommunications and computer Networks, SoftCOM 2024

作者： Alrjoob, Ayat M. Ababnah, Ahmad A. Al-Mistarihi, Mamoun F. Darabkh, Khalid A. German-Jordanian University School of Electrical Engineering and Information Technology Electrical and Communication Engineering Department Amman11180 Jordan Jordan University of Science and Technology Faculty of Engineering Electrical Engineering Department P.o. Box 3030 Irbid22110 Jordan The University of Jordan School of Engineering Computer Engineering Department Amman11942 Jordan

ISBN: (纸本)9789532901382

This paper presents a six-node system comprising two transmitter-receiver pairs, an eavesdropper, and a relay. It evaluates the security of the primary pair while the secondary uses jamming to protect against eavesdropping. We provide a closed-form formula for intercept probability and demonstrate improved security through theoretical analysis and simulations, emphasizing the system's importance for secure communication in urban emergency scenarios involving first responders. In urban networks, D2D communication is crucial, especially in emergencies involving first responders. Our system ensures secure communication between command centers and field units, highlighting its importance in urban emergency scenarios. © 2024 University of Split, FESB.

关键词： Risk perception

来源：评论

学校读者我要写书评

暂无评论

An Optimized Algorithm for Renewable Energy Forecasting Based on Machine Learning

引用

Intelligent Automation & Soft Computing 2023年第1期35卷 755-767页

作者： Ziad M.Ali Ahmed M.Galal Salem Alkhalaf Imran Khan College of Engineering at Wadi Addawaser Prince Sattam bin Abdulaziz UniversityWadi Aldawaser11991Saudi Arabia Electrical Engineering Department Aswan Faculty of EngineeringAswan UniversityAswan81542Egypt Production Engineering and Mechanical Design Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Department of Computer College of Science and Arts in Ar RassQassim UniversityAr RassSaudi Arabia Department of Electrical Engineering University of Engineering and TechnologyPeshawar814Pakistan

The large-scale application of renewable energy power generation technology brings new challenges to the operation of traditional power grids andenergy management on the load side. Microgrid can effectively solve this problemby using its regulation and flexibility, and is considered to be an ideal *** traditional method of computing total transfer capability is difficult due tothe central integration of wind farms. As a result, the differential evolutionextreme learning machine is offered as a data mining approach for extractingoperating rules for the total transfer capability of tie-lines in wind-integratedpower systems. K-medoids clustering under the two-dimensional “wind power-load consumption” feature space is used to define representative operational scenarios initially. Then, using stochastic sampling and repetitive power flow, aknowledge base for total transfer capability operating rule mining is ***, a novel method is used to filter redundant characteristics and find featuresthat are closely associated to the total transfer capability in order to decrease theultra-high dimensionality of operational features. Finally, by feeding the trainingdata into the proposed algorithm, the total transfer capability operation rules arederived from the knowledge base. It can be seen that, the proposed algorithmcan optimize the system performance with good accuracy and generality, according to numerical data.

关键词： Load forecasting distribution network machine learning renewable energy

来源：评论

学校读者我要写书评

暂无评论

Crack Detection for Non-Metallic Material Using Split Ring Resonator-based Chipless RFID Sensor 20

Crack Detection for Non-Metallic Material Using Split Ring R...

引用

20th International Conference on electrical engineering/Electronics, computer, Telecommunications and Information Technology, ECTI-CON 2023

作者： Nongpromma, Sirisak Janin, Suwan Kaemarungsi, Kamol Boonpoonga, Akkarat Torrungrueng, Danai Bannawat, Lakkhana King Mongkut's University of Technology North Bangkok Faculty of Engineering Department of Electrical and Computer Engineering Bangkok Thailand Rajamangala University of Technology Lanna Lampang Faculty of Engineering Department of Engineering and Technology Lampang52000 Thailand National Electronics and Computer Technology Center National Science and Technology Development Agency Pathumthani Thailand Department of Electrical and Computer Engineering Bangkok Thailand Department of Teacher Training in Electrical Engineering Bangkok Thailand Rajamangala University of Technology Rattanakosin Faculty of Engineering Department of Computer Engineering Nakhon Pathom Thailand

ISBN: (纸本)9798350310467

The study presented a novel chipless RFID sensor designed for the detection of cracks in non-metallic materials. The sensor utilized square coplanar split-ring resonators (SRR) and was mounted on the material under test (MUT), including materials such as Teflon (PTFE), Polycarbonate, and Kapton (Polyimide), for detecting cracks. To assess the effectiveness of the sensor in detecting cracks, simulation experiments were conducted using the CST Microwave Studio software, which analyzed shifts in the resonant frequency. The resulting RCS spectra demonstrated a clear correlation between the size of the crack and the resonance frequencies of the chipless RFID sensor, confirming the sensor's ability to detect cracks in nonmetallic materials. © 2023 IEEE.

关键词： Nonmetallic materials

来源：评论

学校读者我要写书评

暂无评论

Natural Language Processing with Optimal Deep Learning Based Fake News Classification

引用

computers, Materials & Continua 2022年第11期73卷 3529-3544页

作者： Sara AAlthubiti Fayadh Alenezi Romany F.Mansour Department of Computer Science College of Computer and Information SciencesMajmaah UniversityAl-Majmaah11952Saudi Arabia Department of Electrical Engineering College of EngineeringJouf UniversitySaudi Arabia Department of Mathematics Faculty of ScienceNew Valley UniversityEl-Kharga72511Egypt

The recent advancements made in World Wide Web and social networking have eased the spread of fake news among people at a faster *** most of the times,the intention of fake news is to misinform the people and make manipulated societal *** spread of low-quality news in social networking sites has a negative influence upon people as well as the *** order to overcome the ever-increasing dissemination of fake news,automated detection models are developed using Artificial Intelligence(AI)and Machine Learning(ML)*** latest advancements in Deep Learning(DL)models and complex Natural Language Processing(NLP)tasks make the former,a significant solution to achieve Fake News Detection(FND).In this background,the current study focuses on design and development of Natural Language Processing with Sea Turtle Foraging Optimizationbased Deep Learning Technique for Fake News Detection and Classification(STODL-FNDC)*** aim of the proposed STODL-FNDC model is to discriminate fake news from legitimate news in an effectual *** the proposed STODL-FNDC model,the input data primarily undergoes pre-processing and Glove-based word ***,STODL-FNDC model employs Deep Belief Network(DBN)approach for detection as well as classification of fake ***,STO algorithm is utilized after adjusting the hyperparameters involved in DBN model,in an optimal *** novelty of the study lies in the design of STO algorithm with DBN model for *** order to improve the detection performance of STODL-FNDC technique,a series of simulations was carried out on benchmark *** experimental outcomes established the better performance of STODL-FNDC approach over other methods with a maximum accuracy of 95.50%.

关键词： Natural language processing text mining fake news detection deep belief network machine learning evolutionary algorithm

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：