检索结果-内蒙古大学图书馆

IEEE Latin American Symposium on Circuits and Systems (LASCAS)

作者： Andrew Fritsch Wagner Savaris Adahil Muniz Giovanna Borba Rodrigo Girardi Jarbas Silveira César Marcon Graduate Program in Computer Science (PPGCC) Pontifical Catholic University of Rio Grande do Sul (PUCRS) Brazil Graduate Program in Teleinformatics Engineering (PPGETI) Federal University of Ceará (UFC) Brazil

ISBN: (数字)9798331522124

ISBN: (纸本)9798331522131

The continuous advancement of communication systems necessitates the development of algorithms capable of identifying and correcting errors that may arise during data transmission and storage. This pursuit of reliability is particularly crucial in critical systems and sectors that are challenging to access, such as space exploration, passenger transportation, and financial services. In this context, the Error Correction Code (ECC) is a fundamental tool for providing a certain degree of reliability to these systems. This research proposes a novel technique to enhance the error correction capacity of ECCs by leveraging region overlapping. Specifically, we propose correcting data areas protected by more than one ECC, which allows for the inference of logical correlations between ECCs, thereby augmenting their error detection and correction capability. Our focus is bidimensional codeword structures, commonly known as 2D-ECCs, which entail a hierarchical arrangement of ECCs. We evaluated the ECC proposal, comparing its error correction and detection capabilities. Through this evaluation, we aim to demonstrate the technique's efficacy in bolstering the reliability and resilience of communication systems, particularly in critical domains where precision and accuracy are paramount.

关键词： Fault tolerance Fault tolerant systems Transportation Error correction codes Error correction Space exploration Proposals Integrated circuit reliability Financial services Resilience

来源：评论

学校读者我要写书评

暂无评论

Security Authentication on the Edge: A Step Further to Defense in Depth for Internet of Battle Things 11

Security Authentication on the Edge: A Step Further to Defen...

引用

11th IEEE International Conference on Software Defined Systems, SDS 2024

作者： Lawisch, Marcio Antonio Dos Anjos, Julio Cesar S. De Freitas, Edison Pignaton Institute of Informatics RS Brazil Federal University of Ceara Campus Itapaje Graduate Program in Teleinformatics Engineering PPGETI CE Brazil

ISBN: (纸本)9798331518325

Currently, the demand for the security of network assets in companies grows dramatically because of several factors, including the growth of the attack surface combined with the variety of connection standards and correlated to the emerging Internet of Things (IoT) related devices and services. This reality is also evident regarding nodes connected to military networks, especially Tactical Edge (TE) devices. Due to the wide variety of equipment connected to the networks (from small sensors to powerful radars) and their possible limitations in resources and transmission means, mainly caused by the terrain and operational conditions, these networks called the Internet of Battle Things (IoBT), also face important security challenges. In this context full of many intentional and unintentional security challenges, this work proposes using blockchain technology as a network access security solution within an in-depth defense concept at three levels: hardware, network, and application. Tests for attacks against the network layer resulted in high resistance rates without consuming significant resources. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Novel virtual nasal endoscopy system based on computed tomography scans

引用

Virtual Reality & Intelligent Hardware 2022年第4期4卷 359-379页

作者： Fábio de O.SOUSA Daniel S.da SILVA Tarique da S.CAVALCANTE Edson C.NETO Victor JoséT.GONDIM Ingrid C.NOGUEIRA Auzuir Ripardo de ALEXANDRIA Victor Hugo C.de ALBUQUERQUE Federal Institute of Ceará-IFCE Telecommunication Engineering ProgramBrazil Graduate Program on Teleinformatics Engineering Federal University of CearáFortaleza/CEBrazil Centro Universitário Christus-UniChristus Brazil Centro Universitário Sete de Setembro-Uni7 Brazil

Background Currently,many simulator systems for medical procedures are under *** systems can provide new solutions for training,planning,and testing medical practices,improve performance,and optimize the time of the ***,to achieve the best results,certain premises must be followed and applied to the model under development,such as usability,control,graphics realism,and interactive and dynamic *** This study presents a system for simulating a medical examination procedure in the nasal cavity for training and research purposes,using a patient′s accurate computed tomography(CT)as a *** pathologies that are used as a guide for the development of the system are ***,an overview of current studies covering bench medical mannequins,3D printing,animals,hardware,software,and software that use hardware to boost user interaction,is ***,a comparison with similar state-of-the-art studies is *** The main result of this work is interactive gamification techniques to propose an experience of simulation of an immersive exam by identifying pathologies present in the nasal cavity such as hypertrophy of turbinates,septal deviation adenoid hypertrophy,nasal polyposis,and tumor.

关键词： Virtual nasal endoscopy Computed tomography Gamification Endoscopy teaching

来源：评论

学校读者我要写书评

暂无评论

Online sparse correntropy kernel learning for outlier-robust system identification ⁎

引用

IFAC-PapersOnLine 2019年第1期52卷 430-435页

作者： Michael S. Duarte Guilherme A. Barreto Federal University of Ceará Graduate Program in Teleinformatics Engineering Center of Technology Fortaleza Ceará Brazil

In this paper, we introduce a sparse variant of the Correntropy Kernel Learning (CKL) model for online system identification in the presence of outliers. The proposed Online Sparse CKL (OS-CKL) improves the original CKL in three important aspects. Firstly, it is modified to operate as a kernel adaptive filter, i.e. model-building is a continuous process and executed on-the-fly for each new incoming sample. Secondly, a sparsification procedure is used in order to build a parsimonious model with time. Finally, we reduce the computational complexity of the proposed algorithm with respect to CKL by computing inverse matrices recursively instead of in batch mode. We evaluate the proposed model using four benchmarking datasets, two synthetic and two related to process industry (CSTR and pH neutralization), for different levels of outlier contamination. The consistent results achieved by the proposed model reveal its ability to keep high predictive power under an online learning regime with a reduced dictionary size in comparison to several state-of-the-art alternatives.

关键词： Correntropy kernel learning adaptive filtering outlier robustness sparsity

来源：评论

学校读者我要写书评

暂无评论

Neural fractional order PID controller embedded in an 8-bit microcontroller for neonatal incubator

Neural fractional order PID controller embedded in an 8-bit ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Igor R. Sousa Guilherme A. Barreto Graduate Program on Teleinformatics Engineering Federal University of Ceara Fortaleza Ceará

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

In this work, a fractional order PID controller for temperature of a neonatal incubator is implemented through a neural network in an embedded system with an 8-bit microcontroller. Using real data from a retrofitted commercial incubator, the plant transfer function is obtained, achieving RMSE = 0.0598. The fractional order PID controller parameters were obtained through particle swarm optimization metaheuristics using the Grunwald–Letnikov definition to calculate the control system fractional derivatives and integrals. The multilayer perceptron neural network is used in order to mitigate the loss of optimality that occurs in discretization methods of fractional order PID controllers, since they are infinite order filters. The neural fractional order PID controller in a simulated environment achieved RMSE = 0.0660 and was compared to the Merrikh-Bayat discretization technique, which obtained RMSE = 0.6578. The neural controller, with only 4 neurons in the hidden layer, was embedded in an 8-bit microcontroller to control the system, requiring only 6.511 ms to execute the MLP, occupying 1556 bytes of program memory and 241 bytes of RAM.

关键词： Pediatrics Filters Embedded systems Microcontrollers Neurons Memory management Random access memory

来源：评论

学校读者我要写书评

暂无评论

Recursive System Identification Using Outlier-Robust Local Models

引用

IFAC-PapersOnLine 2019年第1期52卷 436-441页

作者： Jessyca A. Bessa Guilherme A. Barreto Federal University of Ceará Graduate Program on Teleinformatics Engineering Campus of Pici Fortaleza Ceará Brazil

In this paper we revisit the design of neural-network based local linear models for dynamic system identification aiming at extending their use to scenarios contaminated with outliers. To this purpose, we modify well-known local linear models by replacing their original recursive rules with outlier-robust variants developed from the M-estimation framework. The performances of the proposed variants are evaluated in free simulation tasks over 3 benchmarking datasets. The obtained results corroborate the considerable improvement in the performance of the proposed models in the presence of outliers.

关键词： System identification neural networks local linear models outliers M-estimation

来源：评论

学校读者我要写书评

暂无评论

On self-organizing feature map (SOFM) formation by direct optimization through a genetic algorithm

On self-organizing feature map (SOFM) formation by direct op...

引用

8th International Conference on Hybrid Intelligent Systems, HIS 2008

作者： Maia, José Everardo B. Barreto, Guilherme A. Coelho, André L. V. State Univ. of Ceará Department of Statistics and Computing Fortaleza Ceará Brazil Federal Univ. of Ceará Department of Teleinformatics Engineering Fortaleza Ceará Brazil University of Fortaleza Graduate Program in Applied Informatics Fortaleza Ceará Brazil

ISBN: (纸本)9780769533261

This paper examines the formation of self-organizing feature maps (SOFM) by the direct optimization of a cost function through a genetic algorithm (GA). The resulting SOFM is expected to produce simultaneously a topologically correct mapping between input and output spaces and a low quantization error. The proposed approach adopts a cost (fitness) function which is a weighted combination of indices that measure these two aspects of the map quality, specifically, the quantization error and the Pearson correlation coefficient between the corresponding distances in input and output spaces. The resulting maps are compared with those generated by the Kohonen's self-organizing map (SOM) algorithm in terms of the Quantization Error (QE), the Weighted Topological Error (WTE) and the Pearson correlation coefficient (PCC) indices. The experiments show the proposed approach produces better values of the quality indices as well as is more robust to outliers. © 2008 IEEE.

关键词： Self organizing maps

来源：评论

学校读者我要写书评

暂无评论

Churn Prediction in Financial Risk Management using Deep Learning Techniques 2

Churn Prediction in Financial Risk Management using Deep Lea...

引用

2nd IEEE International Conference on Advanced Technologies in Intelligent Control, Environment, Computing and Communication engineering, ICATIECE 2022

作者： Kumar, V Sunil Sowmyashree, S. Pareek, Piyush Kumar Khanna, Ashish Costa De Albuquerque, Victor Hugo Gupta, Deepak Nitte Meenakshi Institute of Technology Department of Artificial Intelligence & Machine Learning Bengaluru India Computer Science & Engineering East West Institute of Technology Bengaluru India Graduate Program in Telecommunication Engineering Federal Institute of Education Science and Technology of Cearά Fortaleza Brazil Maharaja Agrasen Institute of Technology GGSIPU CSE Dept India Federal University of Cearά Department of Teleinformatics Engineering Brazil

ISBN: (纸本)9781665493963

It is essential to develop an efficient Client Relationship Model in order to make use of the estimations about customer turnover (CRM). Finding and breaking down the facts surrounding the business information understanding is necessary for client produce prediction, which should be made possible effectively by altering the strategies used for business insight. The tools that are provided by company insight allow for the historical, current, and prospective perspectives of business activity to be anticipated and dissected. It is possible to deal with it in an efficient way by providing the information mining approaches that choose the data from the created informative index that is the most helpful. Fundamental leadership should be possible to achieve in a fruitful way if one has this information. The actions that consumers have taken in the recent past are going to be analyzed, and an accurate forecast is going to be formed about those customers who are likely going to get unhappy in the near future based on the results of that prediction. The problem is that deciding on a certain period to investigate the client's activities and also establishing on a specific day and age for each of the clients won't be appropriate6. This is due to the fact that the problem is caused by the fact that deciding on a certain period to investigate the client's activities will take too long. The challenge lies just in this aspect. How to decide on a certain amount of time to spend researching the activities of the customer. For instance, when planning a model, 100 customers are used, 70 of those customers are considered 'active,' which indicates that they are still conducting business with the organisation, and the remaining 30 customers are considered 'agitate,' which indicates that they have severed their ties with the organisation. The primary purpose of the work that has been suggested is to carry out exploratory research and management as a multicriteria basic leadership issue, a

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Detection of Leukemia from Histopathological Image using Deep Learning Techniques 2

Detection of Leukemia from Histopathological Image using Dee...

引用

2nd IEEE International Conference on Advanced Technologies in Intelligent Control, Environment, Computing and Communication engineering, ICATIECE 2022

作者： Kumar, V Sunil Renukadevi, S. Pareek, Piyush Kumar De Albuquerque, Victor Hugo Costa Gupta, Deepak Khanna, Ashish Nitte Meenakshi Institute of Technology Department Artificial Intelligence and Machine Learning Bengaluru India Dayananda Sagar College of Engineering Department of Artificial Intelligence and Machine Learning Bengaluru India Graduate Program in Telecommunication Engineering Federal Institute of Education Science and Technology of Ceará Fortaleza Brazil Federal University of Ceará Department of Teleinformatics Engineering Brazil Maharaja Agrasen Institute of Technology GGSIPU CSE Dept India

ISBN: (纸本)9781665493963

Leukemia is a kind of cancer that is brought on by abnormalities in the body's white blood cells. An inspection of a blood smear that has been collected from the peripheral blood and then seen under a microscope is the method that is considered to be the gold standard for diagnosing leukemia. Techniques such as counting the cells in the blood and doing morphological analysis are two examples of methods that may be used to identify and diagnose leukemia. It is necessary to carefully examine a stained blood smear or an aspiration of bone marrow in order to correctly detect and diagnose leukemia. Both of these procedures involve the removal of bone marrow. This requires prior training and specialized expertise on the subject matter. A tedious and time-consuming operation, the manual evaluation of microscopic pictures of blood samples is one of the steps in the diagnostic procedure. The results are highly dependent on the degree of knowledge and experience that the laboratory worker has. Pathologists are often burdened with an excessive quantity of such data that has to be properly evaluated in order to arrive at a decision. This may be a time-consuming and difficult process. Red blood cells, white blood cells, and blood platelets are the three primary cell types that make up human blood. Platelets are also present in blood. Erythrocyte disease might refer to a collection of diseases that have an effect on hemoglobin. Hemoglobin is a protein found in red blood cells that is responsible for transporting oxygen to cells located throughout the body. This condition is referred to as sickle cell anemia. In sickle cell anemia, the blood contains abnormal hemoglobin molecules known as hemoglobin S. These molecules distort the structure of red blood cells, causing them to take on the form of a crescent or a reaping hook. There is a genetic form of anemia known as sickle cell anemia. This kind of anemia is caused by defective hemoglobin, which causes red blood cells to take on t

关键词： Hemoglobin

来源：评论

学校读者我要写书评

暂无评论

Cognitive Informatics and Soft Computing 1

引用

丛书名： Advances in Intelligent Systems and Computing

1000年

作者： Pradeep Kumar Mallick Akash Kumar Bhoi Gonçalo Marques Victor Hugo C. de Albuquerque

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：