检索结果-内蒙古大学图书馆

Using log analytics and process mining to enable self-healing in the Internet of Things

Environment Systems and Decisions 2022年第2期42卷 234-250页

作者： Singh, Prasannjeet Saman Azari, Mehdi Vitale, Francesco Flammini, Francesco Mazzocca, Nicola Caporuscio, Mauro Thornadtsson, Johan Department of Computer Science and Media Technology Linnaeus University Växjö Sweden Department of Electrical Engineering and Information Technologies University of Naples Federico II Naples Italy School of Innovation Design and Engineering Mälardalen University Västerås Sweden Information Sigma Technology Gothenburg Sweden

The Internet of Things (IoT) is rapidly developing in diverse and critical applications such as environmental sensing and industrial control systems. IoT devices can be very heterogeneous in terms of hardware and software architectures, communication protocols, and/or manufacturers. Therefore, when those devices are connected together to build a complex system, detecting and fixing any anomalies can be very challenging. In this paper, we explore a relatively novel technique known as Process Mining, which—in combination with log-file analytics and machine learning—can support early diagnosis, prognosis, and subsequent automated repair to improve the resilience of IoT devices within possibly complex cyber-physical systems. Issues addressed in this paper include generation of consistent Event Logs and definition of a roadmap toward effective Process Discovery and Conformance Checking to support Self-Healing in IoT. © 2022, The Author(s).

关键词： Anomaly detection Cyber-physical systems Data driven Resilience Self-diagnostics Self-repair

来源：评论

学校读者我要写书评

暂无评论

Enhanced Artificial Algae Algorithm based Distributed Generation Placement for Voltage Profile Enhancement 2

Enhanced Artificial Algae Algorithm based Distributed Genera...

引用

2nd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2023

作者： Hussain, K. Mulani, Umar Mubarak Kumar, B.Suresh Parte, Smita Athanere Patra, Jyoti Prasad Kumar Reddy, P. Naresh Department of Electrical Engineering Maharashtra Kolhapur India Padmabhooshan Vasantraodada Patil Institute of Technology Department of Computer Science and Engineering Maharashtra Budhgaon India Chaitanya Bharathi Institute of Technology Department of Eee Telangana Hyderabad India Mits Gwalior Department of Cse Madhya Pradesh India Faculty Electrical Odisha University of Technology and Research Outr Govt of Odisha Mahalaxmi Vihar Techno Campus Ghatikia odisha Bhubaneswar India Mohan Babu University Department of Liberal Arts and Science Andhra Pradesh Tirupathi India

ISBN: (纸本)9781665456302

Power loss and voltage variability are main challenges in distribution systems. But, these difficulties are normally reduced by effectual network reconfiguration comprising the fusion of distributed generation (DG) units from the distribution network. Accordingly, the optimum size and placement of DGs are fundamental. Then, the network efficacy is reduced. This study was conducted to optimal place and size of DGs as a radial distribution network after and before reconfigurations. This study designs an Enhanced Artificial Algae Algorithm based Distributed Generation Placement for Voltage Profile Enhancement (EAAADG-VPE) technique. The presented EAAADG-VPE technique initially designs the EAAA by the integration of AAA with quasi-oppositional based learning (QOBL) concept. The presented EAAADG-VPE technique aims to regularize voltage, and minimizes power losses and penalty costs. For examining the real power system situation, the penalty factor was considered which roles a vital part in the minimized of power loss and increment of voltage profile. The performance validation of the EAAADG-VPE technique stated the enhanced performance over other recent state of art approaches. © 2023 IEEE.

关键词： Algae

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Grey Wolf Optimization Algorithm for Solving Real-World BLDC Motor Design Problem

引用

computers, Materials & Continua 2022年第2期70卷 2435-2452页

作者： M.Premkumar Pradeep Jangir B.Santhosh Kumar Mohammad A.Alqudah Kottakkaran Sooppy Nisar Department of Electrical and Electronics Engineering GMR Institute of TechnologyRajam532127Andhra PradeshIndia Rajasthan Rajya Vidyut Prasaran Nigam Sikar332025RajasthanIndia Department of Computer Science and Engineering GMR Institute of TechnologyRajam532127Andhra PradeshIndia German Jordanian University Amman11180Jordan Department of Mathematics College of Arts and SciencesPrince Sattam Bin Abdulaziz UniversityWadi Aldawaser11991Saudi Arabia

The first step in the design phase of the Brushless Direct Current(BLDC)motor is the formulation of the mathematical framework and is often used due to its analytical ***,the BLDC motor design problem is considered to be an optimization *** this paper,the analytical model of the BLDC motor is presented,and it is considered to be a basis for emphasizing the optimization *** analytical model used for the experimentation has 78 non-linear equations,two objective functions,five design variables,and six non-linear constraints,so the BLDC motor design problem is considered as highly non-linear in electromagnetic ***-objective optimization becomes the forefront of the current research to obtain the global best solution using metaheuristic *** bio-inspired multi-objective grey wolf optimizer(MOGWO)is presented in this paper,and it is formulated based on Pareto optimality,dominance,and archiving *** performance of theMOGWO is verified on standard multi-objective unconstraint benchmark functions and applied to the BLDC motor design *** results proved that the proposedMOGWO algorithm could handle nonlinear constraints in electromagnetic optimization *** performance comparison in terms of Generational Distance,inversion GD,Hypervolume-matrix,scattered-matrix,and coverage metrics proves that the MOGWO algorithm can provide the best solution compared to other selected *** source code of this paper is backed up with extra online support at https://***/mysite and https://***/matlabcentral/fileexchange/75259-multiobjective-non-sorted-grey-wolf-mogwo-nsgwo.

关键词： BLDC motor electromagnetics metaheuristic multi-objective grey wolf optimizer

来源：评论

学校读者我要写书评

暂无评论

BHGSO:Binary Hunger Games Search Optimization Algorithm for Feature Selection Problem

引用

computers, Materials & Continua 2022年第1期70卷 557-579页

作者： R.Manjula Devi M.Premkumar Pradeep Jangir B.Santhosh Kumar Dalal Alrowaili Kottakkaran Sooppy Nisar Department of Computer Science and Engineering Kongu Engineering CollegePerundurai638060Tamil NaduIndia Department of Electrical and Electronics Engineering Dayananda Sagar College of EngineeringBengaluru560078KarnatakaIndia Rajasthan Rajya Vidyut Prasaran Nigam Sikar332025RajasthanIndia Department of Computer Science and Engineering Guru Nanak Institute of TechnologyHyderabad501506TelanganaIndia Mathematics Department College of ScienceJouf UniversitySakakaP.O.Box:2014Saudi Arabia Department of Mathematics College of Arts and SciencesPrince Sattam bin Abdulaziz UniversityWadi Aldawaser11991Saudi Arabia

In machine learning and data mining,feature selection(FS)is a traditional and complicated optimization *** the run time increases exponentially,FS is treated as an NP-hard *** researcher’s effort to build a new FS solution was inspired by the ongoing need for an efficient FS framework and the success rates of swarming outcomes in different optimization *** paper presents two binary variants of a Hunger Games Search Optimization(HGSO)algorithm based on V-and S-shaped transfer functions within a wrapper FS model for choosing the best features from a large *** proposed technique transforms the continuous HGSO into a binary variant using V-and S-shaped transfer functions(BHGSO-V and BHGSO-S).To validate the accuracy,16 famous UCI datasets are considered and compared with different state-of-the-art metaheuristic binary *** findings demonstrate that BHGSO-V achieves better performance in terms of the selected number of features,classification accuracy,run time,and fitness values than other state-of-the-art *** results demonstrate that the BHGSO-V algorithm can reduce dimensionality and choose the most helpful features for classification *** proposed BHGSO-V achieves 95%average classification accuracy for most of the datasets,and run time is less than 5 *** low and medium dimensional datasets and less than 10 sec for high dimensional datasets.

关键词： Binary optimization feature selection machine learning hunger games search optimization

来源：评论

学校读者我要写书评

暂无评论

Optimization of Multi-Channel Quartz Crystal Microbalance for Gas Sensing Application 8

Optimization of Multi-Channel Quartz Crystal Microbalance fo...

引用

8th IEEE International Conference on Recent Advances and Innovations in engineering, ICRAIE 2023

作者： Zainuddin, Ahmad Anwar Bhattacharjee, Soumik Md Ralib, Aliza Aini Mohd Sukri, Nurain Sufi Sabreena Binti Kamarudin, Saidatul Izyanie Subramaniam, Krishnan Handayani, Dini Reyasudin Basir Khan, M. Muhammad Saifudin, Nik Nor International Islamic University Malaysia Computer Science Kuliyyah of Information Communication Technology Kuala Lumpur Malaysia Universitat Bremen Digital Media Masters Germany International Islamic University Malaysia Department of Electrical and Computer Engineering Kuala Lumpur Malaysia Selangor Shah Alam Malaysia Mila University Department of Mechanical Engineering Nilai Negeri Sembilan Malaysia Kuala Lumpur Malaysia

ISBN: (纸本)9798350315516

Mass detection sensor Quartz Crystal Microbalance (QCM) measures mass sensitivity by piezoelectric, high frequency shaving on nanograms these sensors detect with high precise geometry, low cost and ease of production. Conventional QCM sensors are limited to one electrode structure that minimizes the range of sensing. On a single quartz crystal substrate, three new QCM Multi-Channel sensors are developed and optimized that include 2-channel, 3-channel and 4-channel QCM sensors the COMSOL Multiphysics software is used to design and simulate the multi-channel sensors to enhance the device structure for applications with less interference frequency. From the results, it shows that the least interferences exhibit frequency values of 9.58MHz as both QCMs for the 5mm centre-to-centre (c2c). However, due to small c2c distances that decrease accuracy and operating disadvantages, this design was not selected. For 3 channel sensors, however, three resonant peaks show a similar value of 9.58MHz when c2c is maintained at 7mm. With the highest c2c distance this design shows less interference. Finally, for 4-channel sensors, a distance of 6 mm c2c also has a minimum interference with a 9.58 MHz resonance frequency. This shows that 4 channel sensors with the highest c2c can provide greater operational convenience and less interference at frequencies and thus maximize measurement accuracy. Multi-sensor arrays are advantageous when detecting a large number of analytes at the same time or when only selective coatings (coatings that respond to more than one analyte at the same time) are available these sensor arrays, which use only one sensor and combine it with enhanced signal evaluation methods or prior sample separation to achieve the results of multi-sensor arrays, are becoming increasingly popular. © 2023 IEEE.

关键词： Quartz crystal microbalances

来源：评论

学校读者我要写书评

暂无评论

A Review on the Application of Radiomics and Deep Learning for Disease Identification in Musculoskeletal Radiography 5

A Review on the Application of Radiomics and Deep Learning f...

引用

5th International Conference on Inventive Research in Computing Applications, ICIRCA 2023

作者： Das, Shyamali Rama Devi, C. Nayagam, M. Gomathy Suganthi, D. Thachamkode, Fidha Senthil, K. Manoj Cmr Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India St.Joseph's College of Engineering Electrical and Electronics Engineering India Ramco Institute of Technology Department of Computer Science and Engineering Rajapalayam India Saveetha College of Liberal Arts and Sciences Saveetha Institute of Medical and Technical Sciences Department of Computer Science Chennai602105 India Kmct Dental College Department of Oral Medicine and Radiology Kerala Kozhikode673602 India Kongu Engineering College Electronics and Communication Engineering Erode638 060 India

ISBN: (纸本)9798350321425

Musculoskeletal disorders cause most disability worldwide. Musculoskeletal (MSK) issues are diagnosed, predicted, and treated utilizing imaging methods, magnetic resonance imaging (MRI), and ultrasound, and their precise interpretation by specialized radiologists. Radiological scanning aids metabolic health, aging, and diabetes assessment. Proposed research shows how machine learning, specifically deep learning, may be used to analyze MRI data quickly and reliably, addressing a crucial clinical need in MSK radiology. As primary care radiography services grow, so does interest in how AI, and especially deep learning, might help radiologists and primary care physicians make accurate diagnoses and enhance patient treatment. Chronic pain impairs mobility, dexterity, and function. Diagnosis requires bone X-rays. Deep learning algorithms are increasingly used in musculoskeletal radiology, with promising outcomes. The proposed method uses a calibrated ensemble of deep learners to musculoskeletal radiograph recognition. In the suggested model uses three deep neural networks, which are commonly utilized in deep learning-based solutions for this problem domain. Publicly available dataset to demonstrates the suggested strategy outperforms three individual models and a standard ensemble learner. This study strongly supports the use of a calibrated ensemble approach for identifying abnormalities in musculoskeletal X-rays, where the greatest radiologist accuracy is between 0.95 and 0.98 in Cohen's kappa statistic. © 2023 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

A Novel Way of Finding the Irregularity Present in the System Through Design of CPS System 4

A Novel Way of Finding the Irregularity Present in the Syste...

引用

4th IEEE International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2024

作者： Santosh, J. Dhananjaya Babu, K. Nair, Jayashree Agarwal, Swathi Sakr, Dalal Kadim Al-Azzawi, Waleed Sri Krishna Adithya College of Arts and Science Department of Computer Applications Coimbatore India Department of Electrical and Electronics Engineering Rajampet India Acharya Institute of Management & Sciences School of It Bangalore India Cvr College of Engineering It Department Hyderabad India National University of Science and Technology Dalal Kadim Sakr Collage of Nursing Dhi Qar64001 Iraq Al-Farahidi University Baghdad Iraq

ISBN: (纸本)9798350360165

Strong security measures are required as Cyber-Physical Systems (CPSs) have developed into extremely sophisticated and complicated systems. However, classic anomaly detection approaches are facing difficulties because to the increase of sophisticated assaults and the growing complexity of CPSs. Furthermore, a major obstacle is the increase in data volume, which necessitates domain-specific expertise for efficient analysis. To address these issues, several deep learning-based anomaly detection systems have been created. In this work, we provide a unique approach to anomaly detection by the combination of a powerful deep learning technique, Convolutional Neural Network (CNN), with a Gaussian-Mixture Model (GMM) based on the Kalman Filter and ontology (KF). Our proposed method seeks to detect and distinguish odd behavior in CPSs. The framework has two crucial processes. The first stage in data preparation is to securely prepare the original data for usage in a new format. We provide our second introduction, the GMM-KF-BiLSTM integrated deep CNN model for anomaly detection, which enables precise estimation of posterior probability for both anomalous and normal events in CPSs. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Hunter Prey Optimization with Hybrid Deep Learning for Fake News Detection on Arabic Corpus

引用

computers, Materials & Continua 2023年第5期75卷 4255-4272页

作者： Hala J.Alshahrani Abdulkhaleq Q.A.Hassan Khaled Tarmissi Amal S.Mehanna Abdelwahed Motwakel Ishfaq Yaseen Amgad Atta Abdelmageed Mohamed I.Eldesouki Department of Applied Linguistics College of LanguagesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of English College of Science and Arts at MahayilKing Khalid UniversityMuhayil63763Saudi Arabia Department of Computer Sciences College of Computing and Information SystemUmm Al-Qura UniversityMakkah24211Saudi Arabia Department of Digital Media Faculty of Computers and Information TechnologyFuture University in EgyptNew Cairo11845Egypt Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia Department of Information System College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

Nowadays,the usage of socialmedia platforms is rapidly increasing,and rumours or false information are also rising,especially among Arab *** false information is harmful to society and *** and detecting the spread of fake news in Arabic becomes *** artificial intelligence(AI)methods,including contemporary transformer techniques,BERT,were used to detect fake ***,fake news in Arabic is identified by utilizing AI *** article develops a new hunterprey optimization with hybrid deep learning-based fake news detection(HPOHDL-FND)model on the Arabic *** HPOHDL-FND technique undergoes extensive data pre-processing steps to transform the input data into a useful ***,the HPOHDL-FND technique utilizes long-term memory with a recurrent neural network(LSTM-RNN)model for fake news detection and ***,hunter prey optimization(HPO)algorithm is exploited for optimal modification of the hyperparameters related to the LSTM-RNN *** performance validation of the HPOHDL-FND technique is tested using two Arabic *** outcomes exemplified better performance over the other existing techniques with maximum accuracy of 96.57%and 93.53%on Covid19Fakes and satirical datasets,respectively.

关键词： Arabic corpus fake news detection deep learning hunter prey optimizer classification model

来源：评论

学校读者我要写书评

暂无评论

mediating The Marginal: A Quantitative Analysis of Curated LGBTQ+ Content on Instagram 25

Mediating The Marginal: A Quantitative Analysis of Curated L...

引用

Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems

作者： Garrett Souza Nina Lutz Katlyn M Turner Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge Massachusetts USA Department of Human Centered Design and Engineering University of Washington Seattle Washington USA Media Lab Massachusetts Institute of Technology Cambridge Massachusetts USA

ISBN: (纸本)9798400713941

Control and curation of dominant visual culture - rendering who and what is visible - is central to identity formation, particularly for LGBTQ+ communities relying on digital spaces for safe self-expression. In this work, we analyze Instagram as a site of algorithmic visual curation, performing a quantitative analysis of algorithmically mediated image feeds delivered to a gay-coded user. Our persona account exclusively followed #gay and #instagay feeds, and engaged in content within these discursive spaces to seed algorithmic content promotion to a normative gay user. We present an analysis of skin tone presentations, emoji usage, and engagement metrics alongside analysis of generative outputs of dominant visual trends within the #gay search and Explore feeds. We observe content depicting darker-skinned individuals has higher engagement yet less algorithmic promotion relative to lighter skin tones, while hypermasculine and homonormative content is heavily promoted. These results suggest that, while marginalized positionalities have certainly been rendered more visible through social media platforms, this visibility is increasingly contingent on assimilation to normative ideals through algorithmically determined modes that are not necessarily consistent with user choices, preferences, or realities. © 2025 Copyright held by the owner/author(s).

关键词： Social Networks

来源：评论

学校读者我要写书评

暂无评论

Jellyfish Search Algorithm for UWSNs Energy Management

Jellyfish Search Algorithm for UWSNs Energy Management

引用

2024 IEEE International Conference on Communication, Computing and Signal Processing, IICCCS 2024

作者： Senthilkumar, K.K. Manhas, Saloni Gnanapriya, K.Mythili Alsalami, Zaid Rai, Avinash Kumar Praveenkumar, C. Prince Shri Venkateshwara Padmavathy Engineering College Chennai India Chandigarh Group of Colleges Department of Computer Application Chandigarh Engineering College Punjab Mohali India Nehru Arts and Science College Department of Mathematics Coimbatore India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq The Islamic University of Al Diwaniyah College of Technical Engineering Department of Computers Techniques Engineering Al Diwaniyah Iraq Ies College of Technology Department of Electrical & Electronics Engineering M.P. Bhopal India Sri Ramakrishna Engineering College Department of Eee Coimbatore India

ISBN: (纸本)9798350390759

The results of this research measures the efficacy of JSA in managing energy resources of UWSNs. Thus, it has been observed that JSA has better performance than the LEACH algorithm with to some extent since the energy used by cluster heads by JSA is approximately 27. 8J and a network lifespan of 810 rounds, whereas LEACH's protocol only succeeds in 31 rounds. 5J and 750 rounds. This demonstrates that JSA can also achieve better clustering with less electrical power for the clusters to handle and for the cluster heads consuming 16J of energy. Based on the outcomes presented in this paper, we can conclude that JSA is a beneficial approach for increasing the energy efficiency and network durability in the UWSNs. © 2024 IEEE.

关键词： Wireless sensor networks

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：