检索结果-内蒙古大学图书馆

RMHSForest: Relative Mass and Half-Space Tree Based Forest for Anomaly Detection

Chinese Journal of Electronics 2020年第6期29卷 1093-1101页

作者： LYU Yanxia LI Wenjie WANG Yue SUN Siqi WANG Cuirong School of Computer Science and Engineering Northeastern University Information Systems Faculty of EngineeringThe University of Melbourne

Anomaly detection refers to identify the true anomalies from a given data *** present an ensemble anomaly detection method called Relative mass and half-space tree based forest(RMHSForest),which detect anomalies,including global and local anomalies,based on relative mass estimation and halfspace *** from density or distance based measure,RMHSForest utilizes a novel relative mass estimation to improve the detection of local ***,half-space tree based on augmented mass can estimate a mass distribution efficiently without density or distance calculations or *** empirical results show that RMHSForest outperforms the current popular anomaly detection algorithms in terms of AUC and processing time in the test data sets.

关键词： pattern clustering security of data trees (mathematics) AUC data set relative mass estimation popular anomaly detection algorithms mass distribution augmented mass local anomaly halfspace tree local anomalies global anomalies ensemble anomaly detection method half-space tree RMHSForest Relative mass Half-space tree Anomaly detection Ensemble methods

来源：评论

学校读者我要写书评

暂无评论

High isolation and gain metamaterial based MIMO antenna for 5G millimiter wave applications

High isolation and gain metamaterial based MIMO antenna for ...

引用

2024 International Conference on Circuit, systems and Communication, ICCSC 2024

作者： Elalaouy, Ouafae Aghoutane, Bilal El Ghzaoui, Mohammed Das, Sudipta Foshi, Jaouad El Faylali, Hanan University of Moulay Ismail Faculty of Sciences and Techniques Errachidia Errachidia Morocco Faculty of Sciences IbnTofail University Informatics Systems and Optimization Laboratory Department of Computer Science Kenitra Morocco Sidi Mohamed Ben Abdellah University Faculty of Sciences Dhar El Mahraz Fes Morocco Imps College of Engineering and Technology Department of Electronics and Communication Engineering W.B Malda India

ISBN: (纸本)9798350365306

In the contemporary era, harnessing millimeter-wave frequencies emerges as a compelling strategy to fulfill the swift data transfer requirements for 5G communications. Consequently, this study involves designing a metamaterial-based multiple-input multiple-output (MIMO) antenna with a focus on achieving high isolation and gain within the millimeter-wave spectrum. The suggested MIMO is printed on a Rogers RT5800 measuring 18 × 38 × 0.8 mm3. The single antenna element demonstrates a broad frequency coverage from 27.2 to 28.72GHz. To elevate the antenna's effectiveness, a two-port MIMO configuration is implemented by introducing a second antenna element parallel to benchmark antenna. However, the isolation between the two elements is deemed satisfactory. To address this, a 4 × 1 metamaterial unit cell is introduced, significantly enhancing isolation from 31 dB to 39 dB at 28 GHz. Furthermore, it improves the gain by 0.5 dBi at 28 GHz, elevating it from 8.5 to 9 dBi. The collective features of the suggested two ports MIMO antenna, encompassing its compactness and simplicity, position it as an excellent option for upcoming portable and shrink devices in Internet of Things uses. © 2024 IEEE.

关键词： Microwave antennas

来源：评论

学校读者我要写书评

暂无评论

Maximizing the Utilization of Demand Response in Multi-Microgrids: A Game-Theoretic Approach

Maximizing the Utilization of Demand Response in Multi-Micro...

引用

IEEE General Meeting Power& Energy Society

作者： Soheil Mohseni Alan C. Brent Sustainable Energy Systems School of Engineering and Computer Science Wellington Faculty of Engineering Victoria University of Wellington Wellington New Zealand

ISBN: (数字)9798350381832

ISBN: (纸本)9798350381849

The existing body of literature pertaining to incentive-based demand-side management within microgrids, driven by market dynamics, has predominantly concentrated on the minimization of operational expenses. This focus, however, has omitted a comprehensive analysis of the competitive dynamics inherent in decentralized energy markets. As a result, discernible indications of sub-optimal performance in practice has surfaced. To address this gap, this study employs principles rooted in non-cooperative game theory to elucidate behavioral uncertainties. The present paper introduces an anticipatory, aggregator-mediated framework for demand response scheduling, fully integrated into an optimal dispatching problem governing interconnected multi-microgrids. Through application to an illustrative multi-microgrid system, the outcomes underscore the efficacy of this proposed model in achieving an optimal equilibrium between internal demand response utilization and electricity importation. Notably, the model addresses the epistemological uncertainties stemming from an incomplete understanding of behavioral patterns exhibited by key stakeholders – utilities, load aggregators, and end-consumers. Numerical findings highlight the potential of the model to curtail the daily operational costs of the case study system by a24%.

关键词： Electric potential Uncertainty Electricity Microgrids Minimization Demand response Numerical models Stakeholders Game theory Load modeling

来源：评论

学校读者我要写书评

暂无评论

Optimal Deep Learning Model Enabled Secure UAV Classification for Industry 4.0

引用

computers, Materials & Continua 2023年第3期74卷 5349-5367页

作者： Khalid A.Alissa Mohammed Maray Areej A.Malibari Sana Alazwari Hamed Alqahtani Mohamed K.Nour Marwa Obbaya Mohamed A.Shamseldin Mesfer Al Duhayyim SAUDI ARAMCO Cybersecurity Chair Networks and Communications DepartmentCollege of Computer Science and Information TechnologyImam Abdulrahman bin Faisal UniversityP.O.Box 1982Dammam31441Saudi Arabia Department of Information Systems College of Computer ScienceKing Khalid UniversityAbhaSaudi Arabia Department of Industrial and Systems Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information Technology College of Computers and Information TechnologyTaif UniversityTaif P.O.Box 11099Taif21944Saudi Arabia Department of Information Systems College of Computer ScienceCenter of Artificial IntelligenceUnit of CybersecurityKing Khalid UniversityAbhaSaudi Arabia Department of Computer Sciences College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Biomedical Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Mechanical Engineering Faculty of Engineering and TechnologyFuture University in EgyptNew Cairo11835Egypt Department of Computer Science College of Sciences and Humanities-AflajPrince Sattam bin Abdulaziz UniversitySaudi Arabia

Emerging technologies such as edge computing,Internet of Things(IoT),5G networks,big data,Artificial Intelligence(AI),and Unmanned Aerial Vehicles(UAVs)empower,Industry 4.0,with a progressive production methodology that shows attention to the interaction between machine and human *** the literature,various authors have focused on resolving security problems in UAV communication to provide safety for vital *** current research article presents a Circle Search Optimization with Deep Learning Enabled Secure UAV Classification(CSODL-SUAVC)model for Industry 4.0 *** suggested CSODL-SUAVC methodology is aimed at accomplishing two core objectives such as secure communication via image steganography and image ***,the proposed CSODL-SUAVC method involves the following methods such as Multi-Level Discrete Wavelet Transformation(ML-DWT),CSO-related Optimal Pixel Selection(CSO-OPS),and signcryption-based *** proposed model deploys the CSO-OPS technique to select the optimal pixel points in cover *** secret images,encrypted by signcryption technique,are embedded into cover ***,the image classification process includes three components namely,Super-Resolution using Convolution Neural Network(SRCNN),Adam optimizer,and softmax *** integration of the CSO-OPS algorithm and Adam optimizer helps in achieving the maximum performance upon UAV *** proposed CSODLSUAVC model was experimentally validated using benchmark datasets and the outcomes were evaluated under distinct *** simulation outcomes established the supreme better performance of the CSODL-SUAVC model over recent approaches.

关键词： Unmanned Aerial Vehicles Artificial Intelligence emerging technologies Deep Learning Industry 4.0 image steganography

来源：评论

学校读者我要写书评

暂无评论

Identifying Appropriate Probability Density Function for Wind Speed Profiles of Two Coastal Cities in Pakistan for Better Wind Power Assessment 3

Identifying Appropriate Probability Density Function for Win...

引用

3rd International Conference on Emerging Trends in Electrical, Control, and Telecommunication engineering, ETECTE 2024

作者： Abbas, Ghulam Ali, Arshad Zubair, Muhammad Mushtaq, Zohaib Farooq, Umar Khan, Irfan A. Department of Electrical Engineering The University of Lahore Lahore Pakistan Faculty of Computer and Information Systems Islamic University of Madinah Madinah Saudi Arabia College of Engineering and Technology University of Doha for Science and Technology Doha Qatar Department of Electrical Electronics and Computer Systems University of Sargodha Sargodha Pakistan IEECE University of the Punjab Lahore Pakistan Lab Texas A&M University GalvestonTX77553-1675 United States

ISBN: (纸本)9798331504861

To assess the wind power potential of a specific wind site, a suitable distribution function that best suits the wind data needs to be known. In this study, we employ four probability density functions (PDFs), namely Weibull, Rayleigh, Log-Normal, and Gamma, on wind speed data obtained from two coastal cities in Pakistan, Gwadar and Karachi, to check which one is the best suited. Cities along the coastline of Pakistan offer greater wind speeds and, thus, greater wind power potential. The maximum likelihood technique is used to estimate the parameters of the density distributions. Three statistical measures—Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R2)—are used to assess the goodness of fit for every distribution. These measures give a complete picture of every distribution's correctness in terms of reflecting the recorded wind speed patterns. Numerical results reveal that the Weibull distribution fits well with the wind speeds of the two coastal cities compared to the other three probability distributions, providing insightful analysis for the evaluation of wind resources and possible local energy generation. The MATLAB environment is used to compare the distributions and validate the effectiveness of the proposed methodology. ©2024 IEEE.

关键词： Windmill

来源：评论

学校读者我要写书评

暂无评论

Evaluating Multi-Sensor Placement and Neural Network Architectures for Physical Activity Level Classification

arXiv

引用

arXiv 2025年

作者： Cui, Bo Song, Xiaowen Monique, Tabak van Beijnum, Bert-Jan Wang, Ying Faculty of Biomedical Signals and Systems Electrical Engineering Mathematics and Computer Science University of Twente Enschede7500 AE Netherlands

Accurate physical activity level (PAL) classification could be beneficial for osteoarthritis (OA) management. This study examines the impact of sensor placement and deep learning models on AL classification using Metabolic Equivalent of Task values. The results show that the addition of an ankle sensor (WA) significantly improves the classification of high intensity activities compared to wrist-only configuration (53% to 86.2%). The CNN-LSTM model achieves the highest accuracy (95.09%). Statistical analysis confirms multi-sensor setups outperform single-sensor configurations (p © 2025, CC BY-NC-ND.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Office Building Energy Community: A Case Study on Optimal Market Operation and Grid Impact 9

Office Building Energy Community: A Case Study on Optimal Ma...

引用

9th IEEE International Smart Cities Conference, ISC2 2023

作者： Lepisto, Juhani Forcan, Jovana Forcan, Miodrag Heine, Pirjo Helen Electricity Network Helsinki Finland University of East Sarajevo Faculty of Philosophy Department of Computer Science and Systems East Sarajevo Bosnia and Herzegovina University of East Sarajevo Faculty of Electrical Engineering Department of Electroenergetics East Sarajevo Bosnia and Herzegovina

ISBN: (纸本)9798350397758

In this paper, we study an office building connected to an urban distribution network from an energy community perspective. The office building and its electrical equipment have a real-world counterpart from which we construct synthetic time series based on the historical measurement data. The office building involves three stakeholders and their assets. The central stakeholders are the owner and the tenant of the building. The third stakeholder is the operator of flexible assets. The smartness of the office building is related to the control capabilities of its assets. These controllable assets are the battery energy storage system (BESS) and the electric vehicles (EV) charging system (EVCS) that both can operate in a flexible manner in response to energy price fluctuations and participate in a reserve market. We proposed different cases where either the owner or the tenant is paying the EV charging, and where the flexibility of the EV charging is either active or not. We show that, when the owner pays for the energy usage of the EVCS and the tenant is using it, there is a beneficial case to form a coalition between them and share the benefits from the flexibility, as otherwise there is no incentive for the tenant to be flexible in the first place. We conducted operative cost-benefit calculations where we shared the community benefits according to the Shapley value and simulated the power flows at the building's connection point based on the market operations. We found that harnessing benefits from the two market operations had significant effects on the power flows at the connection point. This was true when operating under the variable energy prices and in the reserve market. © 2023 IEEE.

关键词： Office buildings

来源：评论

学校读者我要写书评

暂无评论

Shedding Light on Glowapp: A Usability Test Evaluation for Enhanced User Experience 9

Shedding Light on Glowapp: A Usability Test Evaluation for E...

引用

9th International Conference on Information Management and Technology, ICIMTech 2024

作者： Sergio Saputro, Immanuela Puspasari Prabowo, Yulius Denny Ticoalu, Voice Esther Mahardini, Karunia Agung BINUS Online Learning Bina Nusantara University Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Bina Nusantara University Information Systems Department Jakarta11480 Indonesia Bina Nusantara University Faculty of Engineering Industrial Engineering Department Jakarta11480 Indonesia

ISBN: (纸本)9798350390025

Cosmetics is one of the emerging industries in Indonesia. Cosmetology is the practice of using cosmetics and cosmetic products to alter the appearance of the face. When applying makeup, it is essential to tailor it to the occasion and consider the facial structure. Applying appropriate cosmetics may enhance self-assurance. According to the questionnaire findings, women apply makeup more than twice. However, not all of them possess the talent to apply makeup on themselves. They struggle to locate a makeup artist with a style and availability that meets their requirements. Glowapp was developed with booking functionalities. Customers will find it more convenient to schedule an appointment. Blackbox testing was utilized to assess the functionality of the system. The results indicate that the features performed effectively and satisfied user requirements. The usability test is conducted by integrating the eight golden guidelines and ISO-9241-11. The goal is to reduce the time respondents spend filling questionnaires while maintaining usability principles to ensure more accurate answers. Glowapp has a performance score of 93%, with efficiency scoring the highest and effectiveness scoring the lowest. © 2024 IEEE.

关键词： Black-box testing

来源：评论

学校读者我要写书评

暂无评论

Interpretable Arabic Hate Speech Detection using Large Language Model

Interpretable Arabic Hate Speech Detection using Large Langu...

引用

Advanced Innovations in Smart Cities (ICAISC), International Conference on

作者： Majed Alwateer Ibrahim Gad Mahmoud Elmarhomy Ghada Elmarhomy Hasan Hashim Malik Almaliki El-Sayed Atlam Department of Computer Science College of Computer Science and Engineering Taibah University Saudi Arabia Computer Science Department Faculty of Science Tanta University Tanta Egypt Computer Science and Information College of Applied Taibah University Saudi Arabia Department of Information Systems College of Computer Science and Engineering Taibah University Saudi Arabia

ISBN: (数字)9798331506995

ISBN: (纸本)9798331507008

Social media platforms serve as significant spaces for users to have conversations, discussions and express their opinions. However, anonymity provided to users on these platforms allows the spread of hate speech and other offensive material. Due to the wide-ranging nature of these platforms, there is a critical need to automatically detect and report occurrences of hate speech. There are various detection methods, but many of them operate as black boxes, lacking interpretability and explainability by design. To address the lack of interpretability, this study explores the development of an interpretable framework to detect hate speech in Arabic using large language models (LLMs). The proposed approach combines advanced natural language processing techniques with interpretable machine learning methods to enhance understanding of model decisions. The experimental results demonstrate that the model achieves high accuracy while maintaining interpretability, enabling users to understand the reasoning behind the detections. The proposed method achieves an accuracy of 0.846%, with a precision of 0.843% and a recall of 0.846%, outperforming existing Arabic hate speech detection models. These results show the effectiveness of combining LLM with interpretability for this critical task, providing a reliable and transparent solution for automated moderation of harmful content.

关键词： Technological innovation Accuracy Social networking (online) Smart cities Large language models Hate speech Text categorization Writing Reliability Stakeholders

来源：评论

学校读者我要写书评

暂无评论

Development of an "Artificial Lung" System for Use in Indoor Air Quality Testing 21st

Development of an "Artificial Lung" System for Use in Indoor...

引用

21st Polish Control Conference, PCC 2023

作者： Kozyra, Andrzej Lipczynska, Aleksandra Koper, Piotr Babisz, Radoslaw Madej, Damian Nowakowski, Konrad Karwatka, Jakub Tomczok, Dominik Department of Measurements and Control Systems Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland Department of Heating Ventilation and Dust Removal Technology Faculty of Energy and Environmental Engineering Silesian University of Technology Gliwice Poland

ISBN: (纸本)9783031351693

"Artificial lung" is a device that simulates breathing process of occupants in a room. This allows you to safely test, e.g., the impact of HVAC systems on the spread of pathogens. The paper describes the concept of the device, its construction and performed tests. The project was implemented by students of two faculties: Automatic Control, Electronics and computer science, and Energy and Environmental engineering. Project supervisors from both faculties provided substantive supervision and support for students. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Air quality

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：