检索结果-内蒙古大学图书馆

2023 International Russian Automation Conference, RusAutoCon 2023

作者： Filianin, Ivan Bogatyrev, Vladimir Lesonen, Matvey Itmo University Faculty of Software Engineering and Computer Engineering St. Petersburg Russia Saint-Petersburg State University of Aerospace Instrumentation Department of Information Systems Security St. Petersburg Russia Itmo University Faculty of Infocommunication Technologies St. Petersburg Russia

ISBN: (纸本)9798350345551

This paper reviews the use of Minikube in multi-node mode to work with the ETSI MEC Sandbox as a lightweight multi-access edge computing platform simulator (LWMECPS). The work included a comparative analysis of MEC platforms in terms of functionality, cost of deployment, and complexity of adoption. An experiment was also conducted to test LWMECPS as a MEC platform using a Python3 test application. The experiment confirmed the feasibility of using LWMECPS as a MEC platform by deploying a Kubernetes deployment based on the number of users on the simulated 4g-macro network service zones from the ETSI MEC Sandbox. Particular attention was paid to the analysis of existing scientific literature on the use of multi-access edge computing platforms in various use cases. © 2023 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

A Novel Multiobjective Fireworks Algorithm and Its Applications to Imbalanced Distance Minimization Problems

引用

IEEE/CAA Journal of Automatica Sinica 2022年第8期9卷 1476-1489页

作者： Shoufei Han Kun Zhu MengChu Zhou Xiaojing Liu Haoyue Liu Yusuf Al-Turki Abdullah Abusorrah College of Computer Science and Technology Nanjing University of Aeronautics and Astronauticsand also with the Collaborative Innovation Center of Novel Software Technology and IndustrializationNanjing 211106China Department of Electrical and Computer Engineering New Jersey Institute of TechnologyNewark NJ 07102 USA Center of Research Excellence in Renewable Energy and Power Systems Department of Electrical and Computer EngineeringFaculty of Engineeringand also with the K.A.CARE Energy Research and Innovation CenterKing Abdulaziz UniversityJeddah 21589Saudi Arabia

Recently,multimodal multiobjective optimization problems(MMOPs)have received increasing *** goal is to find a Pareto front and as many equivalent Pareto optimal solutions as *** some evolutionary algorithms for them have been proposed,they mainly focus on the convergence rate in the decision space while ignoring solutions *** this paper,we propose a new multiobjective fireworks algorithm for them,which is able to balance exploitation and exploration in the decision *** first extend a latest single-objective fireworks algorithm to handle *** we make improvements by incorporating an adaptive strategy and special archive guidance into it,where special archives are established for each firework,and two strategies(i.e.,explosion and random strategies)are adaptively selected to update the positions of sparks generated by fireworks with the guidance of special ***,we compare the proposed algorithm with eight state-of-the-art multimodal multiobjective algorithms on all 22 MMOPs from CEC2019 and several imbalanced distance minimization *** results show that the proposed algorithm is superior to compared algorithms in solving ***,its runtime is less than its peers'.

关键词： Adaptive strategy fireworks algorithm multimodal multiobjective optimization problems(MMOP)

来源：评论

学校读者我要写书评

暂无评论

Determining the Critical Factors of Antenatal Care Follow-Up Using Two-Phase Machine Learning

Determining the Critical Factors of Antenatal Care Follow-Up...

引用

International Conference on Soft Computing and Measurements (SCM)

作者： Igor A. Bessmertny Bidru C. Enkomaryam Adane L. Mamuye Faculty of Software Engineering and Computer Systems ITMO University Saint Petersburg Russia Department of Computer Science University of Gondar Gondar Ethiopia

ISBN: (数字)9798350363708

ISBN: (纸本)9798350363715

Determining the critical factors affecting antenatal visits will greatly contribute to reducing maternal and infant mortality. This study, thus attempted to construct a cluster-based predictive model to determine the critical factors of antenatal care follow-up among women in Ethiopia using two-step machine learning techniques. The 5,990 preprocessed obstetric dataset with 13 selected attributes were used that was collected from the Dabat Research Center at the University of Gondar, Ethiopia. To solve the study problem, six cluster models were developed using K-means, Expectation Maximization and Make Density clustering algorithms, which are well-suited for analyzing health datasets, providing scalability, flexibility, robustness to noise, and the ability to handle uneven cluster sizes. K-means out-formers Density based and Expectation Maximization clustering algorithms with minimum number of sum of square errors (17094) and number of iteration (3). Then, output of the K-means cluster model was used as input to segment the dataset and build a total of 21 predictive models using the tree-based J48 classifier, PART and JRip rule generators while adjusting their parameters. The model for predicting antenatal care follow-up is constructed by induction of the truncated PART rule (accuracy of 99.93%) and extracts attributes of interest such as antenatal care attendance, antenatal care location, antenatal care frequency, current vaccination, woman’s age, and HIV testing to predict antenatal care follow-up in the study area.

关键词： Machine learning algorithms Accuracy Scalability Clustering algorithms Machine learning Predictive models Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Building a Full-text Search Index Using "Transformer" Neural Network

Building a Full-text Search Index Using "Transformer" Neural...

引用

International Conference on Application of Information and Communication Technologies (AICT)

作者： Vyacheslav Dobrynin Roman Abramovich Alexey Platonov Faculty of Software Engineering and Computer Systems ITMO University Saint Petersburg Russian Federation

The use of deep neural networks in information retrieval significantly improves its effectiveness, but negatively affects the performance of the process. To deal with this, we propose a new ranking model that uses the deep neural network of the "Transformer" architecture (in particular, BERT) for efficient information retrieval. In accordance with the proposed approach, contextualized vector representations are extracted from documents during indexing, after which these representations are clustered for each independent token. The resulting clusters reflect different meanings of the words and are indirectly used as inverted index keys. The values represent the documents in which these contextualized word meanings occur, along with the distances from each document to the contextualized embedding. Thus, after the indexing process, we obtain an index containing pre-calculated distances between the contextualized meanings of dictionary elements and documents. This approach helps us avoid the performance overhead of calculating distances online. At the search stage, the query is transformed into a set of contextualized vectors representing each query token, which allows us to use these vectors to retrieve most semantically close neighbor-tokens and use them to extract relevant documents from the index. This way of searching for contextualized embeddings consumes less memory and is more performant due to the use of an inverted index.

关键词：

来源：评论

学校读者我要写书评

暂无评论

How to Improve IT Specialists Training for Designing Cyber-Physical systems 10

How to Improve IT Specialists Training for Designing Cyber-P...

引用

10th Mediterranean Conference on Embedded Computing, MECO 2021

作者： Pinkevich, Vasiliy Platunov, Alexey Kluchev, Arkady ITMO University Faculty of Software Engineering and Computer Systems Saint Petersburg Russia

ISBN: (纸本)9780738133614

Many universities today offer special courses or entire master programs for cyber-physical systems (CPS) developers training. A multi-aspect design route of the CPS creation is considered as the methodological vector, which should provide a parallel, balanced, and integrated movement from the task to the product. The most important part is knowledge and skills in computing, aimed at designing computing platforms and CPS application software. However, the ongoing segmentation in computing reduces the interdisciplinary interaction effectiveness. We consider the development of an integral perception of a computing system based on a multi-level and multi-domain representation model and a deep understanding of the fundamental universal mechanisms of its functioning as a way to improve the quality of design and the efficiency of interaction between computer specialists. This can be achieved by the development of microarchitectural descriptions of a computing system and its components, filling the gap between architectural representation and implementation-level documents. These principles should be implemented even during specialists training. The means of creating such models and descriptions, as well as the educational laboratory complex of distance learning, which supports the proposed approach, are demonstrated. © 2021 IEEE.

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

Synthesis Method for CGRA Processors based on Imitation Model 10

Synthesis Method for CGRA Processors based on Imitation Mode...

引用

10th Mediterranean Conference on Embedded Computing, MECO 2021

作者： Penskoi, Aleksandr ITMO University Software Engineering and Computer Systems Faculty Saint Petersburg Russia

ISBN: (纸本)9780738133614

The article considers the problem of designing a synthesis method for Coarse-Grained Reconfigurable Array (CGRA) architectures. The author observes several general problems of such architecture and demonstrates how they can be solved using the NITTA project example. NITTA - the CAD for generating and programming CGRA processors for cyclic execution of control or signal/data processing algorithms. Target system work principles from hardware, algorithm, and transport points of view provided. The principles of building a target system imitation model and synthesis method based on interaction with that model in dialog form are described. All ideas were demonstrated on the simple algorithm example. © 2021 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Hands and Palms Recognition by Transfer Learning for Forensics: A Comparative Study 23

Hands and Palms Recognition by Transfer Learning for Forensi...

引用

23rd International Conference on New Trends in Intelligent software Methodologies, Tools and Techniques, SoMeT 2024

作者： Fattahi, Jaouhar Fkiri, Obeb Mejri, Mohamed Ghayoula, Ridha Department of Computer Science and Software Engineering Laval University 2325 rue de l'Université QuebecQCG1V 0A6 Canada Department of Computer Science National School of Engineers of Carthage University of Carthage Tunis Tunisia Faculty of Engineering Information Systems Department University of Moncton New Brunswick Canada

ISBN: (纸本)9781643685380

In the realm of forensic science, precise identification of individuals holds paramount importance in both investigative procedures and legal proceedings. Hands and palms recognition has emerged as a valuable biometric modality within forensic applications, owing to the distinct and intricate features inherent to these anatomical regions. The elaborate patterns of veins, creases, and ridges present on palms and fingers serve as rich sources of biometric data, crucial for accurate identification purposes. Furthermore, given the frequent involvement of hands and palms in criminal activities such as theft and assault, their recognition becomes imperative for establishing links between suspects and crime scenes. However, developing robust recognition systems tailored for forensic applications poses notable challenges, including variations in hand poses, lighting conditions, and image quality. To address these hurdles, sophisticated deep learning techniques, notably transfer learning, have been employed. By harnessing pre-trained deep learning models namely NasNetLarge, NasNetMobile, and EfficientNet, initially trained on expansive datasets for general image recognition tasks, we can adapt these models to the specific task of hands and palms recognition in forensic contexts. Our findings reveal that all three models consistently achieved over 92% accuracy across all metrics evaluated, demonstrating their efficacy as strong contenders for the hands-and-palms recognition task. Notably, the EfficientNet model exhibited superior performance compared to its counterparts, boasting more than 95.8% accuracy, precision, F1-score and recall, along with more than 98.6% specificity and 99.4% AUC. © 2024 IOS Press. All rights reserved.

关键词： Palmprint recognition

来源：评论

学校读者我要写书评

暂无评论

Hyper-Heuristic Strategy for Input-Output-Based Interaction Testing

Hyper-Heuristic Strategy for Input-Output-Based Interaction ...

引用

Innovative Manufacturing, Mechatronics and Materials Forum, iM3F 2020

作者： Din, Fakhrud Zamli, Kamal Z. Faculty of Computer Systems and Software Engineering Universiti Malaysia Pahang Kuantan Pahang26300 Malaysia Department of Computer Science & IT University of Malakand Lower Dir District KPK Pakistan

ISBN: (纸本)9789813345966

software testing aims at exploring faults within software in order to ensure it meets all necessary specifications. Test case design strategies play key role in software testing. Classical test case design strategies, however, do not sufficiently include support for exploration of faults due to interaction between parameter values. New strategies known as t-way strategies (where t expresses interaction strength) have been developed for finding interaction faults. However, existing t-way strategies for input-output-based relationship (IOR) interaction testing mostly adopt greedy algorithms which often generate poor quality test data. Therefore, this paper presents the design of a new IOR test suite generation strategy called IOR_HH based on the exponential Monte Carlo with counter (EMCQ) hyper-heuristic. EMCQ is a parameter free hyper-heuristic which works as controller of the three implemented low-level meta-heuristic operators, namely crossover, peer learning and global pollination in the proposed IOR_HH strategy. Experimental results demonstrate the impact of the proposed strategy against existing computational strategies for IOR interaction testing. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

Design of Deep CNN Model for Effective Traffic Signs Recognition

Design of Deep CNN Model for Effective Traffic Signs Recogni...

引用

2021 International Russian Automation Conference, RusAutoCon 2021

作者： Sichkar, Valentyn N. Lyamin, Andrey V. Itmo University Faculty of Software Engineering and Computer Systems Saint-Petersburg Russia

ISBN: (纸本)9780738131566

In this paper, the method to design deep Convolutional Neural Network (CNN) architecture for the problem of traffic signs classification is proposed. The approach incorporates five main stages followed by each other: selecting the deepness of the network via the number of convolutional-pooling pairs, choosing the needed number of feature maps in every convolutional layer, identifying the sufficient number of neurons in the hidden fully connected layer, estimating the needed percentage of dropout after every layer. The last stage is aimed to analyse if replacing max pooling by convolution with strides 2 or by average pooling improves designed architecture. At each stage, every designed model is trained and evaluated 100 times. The choice of the best model to continue with at the next stage is based on the highest of the most frequent accuracy. The obtained final architecture is trained and tested with the original German Traffic Sign Recognition Benchmark (GTSRB) and its augmented version via geometric transformations: rotation around the centre point and projection to different sides that imitates capturing of images by the camera with some skew angle. Experimental results showed testing accuracy of more than 99.9% that enables to use designed architecture in real-life applications. © 2021 IEEE.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

Identification of Anomaly Scenes in Videos Using Graph Neural Networks

引用

computers, Materials & Continua 2023年第3期74卷 5417-5430页

作者： Khalid Masood Mahmoud M.Al-Sakhnini Waqas Nawaz Tauqeer Faiz Abdul Salam Mohammad Hamza Kashif Department of Software Engineering Lahore Garrison UniversityLahore54000Pakistan School of Business Skyline University CollegeSharjahUAE Al-Madinah International University–Faculty of Computer and Information Technology Kuala LumpurMalaysia College of Computer and Information Systems Islamic University of MadinahMadinahKingdom of Saudi Arabia School of IT Skyline University CollegeSharjahUAE Faculty of Engineering Computing and Science(FECS)-Swinburne University of TechnologySarawak Department of General Education Skyline University CollegeUniversity City of SharjahUAE Department of Computer Science Lahore Garrison UniversityLahore54000Pakistan

Generally,conventional methods for anomaly detection rely on clustering,proximity,or *** themassive growth in surveillance videos,outliers or anomalies find ingenious ways to obscure themselves in the network and make conventional techniques *** research explores the structure of Graph neural networks(GNNs)that generalize deep learning frameworks to graph-structured *** node in the graph structure is labeled and anomalies,represented by unlabeled nodes,are predicted by performing random walks on the node-based graph *** to their strong learning abilities,GNNs gained popularity in various domains such as natural language processing,social network analytics and *** detection is a challenging task in computer vision but the proposed algorithm using GNNs efficiently performs the identification of *** Graph-based deep learning networks are designed to predict unknown objects and *** our case,they detect unusual objects in the form of malicious *** edges between nodes represent a relationship of nodes among each *** case of anomaly,such as the bike rider in Pedestrians data,the rider node has a negative value for the edge and it is identified as an *** encoding and decoding layers are crucial for determining how statistical measurements affect anomaly identification and for correcting the graph path to the best possible *** show that the proposed framework is a step ahead of the traditional approaches in detecting unusual activities,which shows a huge potential in automatically monitoring surveillance *** autonomous monitoring of CCTV,crime control and damage or destruction by a group of people or crowd can be identified and alarms may be triggered in unusual activities in streets or public *** suggested GNN model improves accuracy by 4%for the Pedestrian 2 dataset and 12%for the Pedestrian 1 dataset compared to a few state-of the-art techniq

关键词： Graph neural network deep learning anomaly detection auto encoders

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：