检索结果-内蒙古大学图书馆

Identification of Weather Phenomena Based on Lightweight Convolutional Neural Networks

computers, Materials & Continua 2020年第9期64卷 2043-2055页

作者： Congcong Wang Pengyu Liu Kebin Jia Xiaowei Jia Yaoyao Li Faculty of Information Technology Beijing University of TechnologyBeijing100124China Beijing Laboratory of Advanced Information Networks Beijing100124China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of TechnologyBeijing100124China Department of Computer Science and Engineering University of MinnesotaTwin CitiesUSA

Weather phenomenon recognition plays an important role in the field of ***,weather radars and weathers sensor have been widely used for weather ***,given the high cost in deploying and maintaining the devices,it is difficult to apply them to intensive weather phenomenon ***,advanced machine learning models such as Convolutional Neural Networks(CNNs)have shown a lot of promise in meteorology,but these models also require intensive computation and large memory,which make it difficult to use them in *** practice,lightweight models are often used to solve such ***,lightweight models often result in significant performance *** this end,after taking a deep dive into a large number of lightweight models and summarizing their shortcomings,we propose a novel lightweight CNNs model which is constructed based on new building *** experimental results show that the model proposed in this paper has comparable performance with the mainstream non-lightweight model while also saving 25 times of memory *** memory reduction is even better than that of existing lightweight models.

关键词： Deep learning convolution neural networks lightweight models weather identification

来源：评论

学校读者我要写书评

暂无评论

Two-Layer SVM, Towards Deep Statistical Learning

Two-Layer SVM, Towards Deep Statistical Learning

引用

Electrical, Energy, and Artificial Intelligence (EICEEAI), International engineering Conference on

作者： Alireza Kazemi Reza Boostani Mahmoud Odeh Mohammad Rasmi AL-Mousa Mathematics Department Faculty of Science Shiraz University Shiraz Fars Iran CSE&IT Dept. Electrical and Computer Engineering School Shiraz University Shiraz Fars Iran Department of Management Information System Zarqa University Jordan Department of Cyber Security Faculty of Information Technology Zarqa University Zarqa Jordan

Support Vector Machine (SVM) is originally a binary large-margin classifier emerged from the concept of structural risk minimization. Multiple solutions such as one-versus-one and one-versus-all have been proposed for creating multi-class SVM using elementary binary SVMs. Also multiple solutions have been proposed for SVM model selection, adjusting margin-parameter C and the Gaussian kernel variance. Here, an improved classifier named SVM-SVM is proposed for multi-class problems which increases accuracy and decreases dependency to margin-parameter selection. SVM-SVM adopts two K-class one-vs-one SVMs in a cascaded two-layer structure. In the first layer, input features are fed to one-vs-one SVM with non-linear kernels. We introduce this layer as a large-margin non-linear feature transform that maps input feature space to a discriminative K*(K-1)/2 dimensional space. To assess our hierarchical classifier, some datasets from the UCI repository are evaluated. Standard one-vs-one SVM and one-vs-one fuzzy SVM are used as reference classifiers in experiments. Results show significant improvements of our proposed method in terms of test accuracy and robustness to the model (margin and kernel) parameters in comparison with the reference classifiers. Our observations suggest that a multi-layer (deep) SVM structures can gain the same benefits as is seen in the deep neural nets (DNNs).

关键词： Support vector machines Electric potential Statistical learning Neural networks Transforms Nonhomogeneous media Robustness

来源：评论

学校读者我要写书评

暂无评论

Security prototype to determine critical information and improve the management of a public organization

Security prototype to determine critical information and imp...

引用

2020 Asia Conference on computers and Communications, ACCC 2020

作者： Toapanta, Segundo Moises Toapanta Maldonado, Nicole Monica Moran Gallegos, Luis Enrique Mafla Solis, Maximo Prado Quito Ecuador Department Computer Science Guayaquil Ecuador Faculty of Engineering System Quito Ecuador Universidad Técnica Luis Vargas Torres of Esmeraldas Career Social Sciences Esmeraldas Ecuador

ISBN: (纸本)9781728189673

The increase in cyber-attacks forced public institutions to design computer security mechanisms to prevent damage to equipment or loss of information, for private use. The objective is to present a security prototype that allows determining critical information and improves the management of a public organization. The deductive method and exploratory research were used. The result was a mixed information control model, a mixed security architecture with mechanisms that comprehensively protect the information, verifying the identity and correlating the risks produced with the application of Blockchain technology, the Magerit and Octave methodology, it was also It is possible to correlate the risks of the links and the data, applying an analysis to give an immediate response. It was concluded that the hybrid architecture allowed to verify the identity and correlate the risks, Blockchain provided control against malicious attacks, together with Magerit that made use of safeguards and Octave analyzed the threats to the security of the assets, used in public management. © 2020 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Smart Lighting system for Children's Therapy to Prevent Nyctophobia Syndrome at Bedtime

Smart Lighting System for Children's Therapy to Prevent Nyct...

引用

International Conference on Cybernetics and Intelligent system (ICORIS)

作者： Andi Pramono Badrul Munir Muchammad Farchan Satrio Arif Budiman Baskoro Azis Wahyu Waskito Putra Interior Design Department School of Design Bina Nusantara University Jakarta Indonesia Departemen of Neurology Brawijaya University Malang Indonesia Department of Electrical Engineering Faculty of Intelligent Electrical and Informatics Technology Institut Teknologi Sepuluh Nopember Surabaya Indonesia Information System Computer Science faculty Brawijaya University Malang Indonesia

ISBN: (纸本)9781665453967

Everyone has a fundamental desire for sleep. By sleeping, humans can conserve energy and replenish their stamina to optimal levels. Lighting is one component that influences the quality of a person's sleep. One of them is a person who sleeps with the lights on, suffers from nyctophobia, has poor sleep quality, and may be responsible for several illnesses. This study aims to develop a smart lighting device that will aid in treating youngsters with nyctophobia to get used to sleeping with the lights off to improve their sleep quality. The case study methodology used in this study entails the development of a prototype. This method employs an oximeter as a heart rate detector and a sensor comparison as the measurement device. Arduino Uno circuit and heart rate sensor are the main devices in this research. At the same time, the NRF 24L01 is a communication medium between the two Arduino Uno boards. The experimental measurements in normal conditions indicate that the heart rate sensor was nearly the same as the value displayed by the oximeter. Similarly, after running for 1 minute, both devices produced almost identical results, with an average difference of 1 Beats Per Minute (BPM). According to experiments with a heart rate sensor, the switch-off condition can be activated if the heart rate hits 90 BPM. In this case, the light will switch off once the heart rate hits 70 BPM, which might be used for sleeping individuals.

关键词： Heart rate Phase measurement Prototypes Medical treatment Switches Turning Nanoscale devices

来源：评论

学校读者我要写书评

暂无评论

Implementation Messaging Broker Middleware for Architecture of Public Transportation Monitoring system 6

Implementation Messaging Broker Middleware for Architecture ...

引用

6th International Conference on Interactive Digital Media, ICIDM 2020

作者： Pratama, Hafiyyan Putra Prihatmanto, Ary Setijadi Sukoco, Agus Universitas Pendidikan Indonesia Telecomunication System Bandung Indonesia Institut Teknologi Bandung Electrical and Informatics Engineering Bandung Indonesia Universitas Bandar Lampung Faculty of Computer Science Bandar Lampung Indonesia

ISBN: (纸本)9781728149288

Information technology becomes an important part of human life. World Wide Web is an example of an information technology success story. HyperText Transfer Protocol (HTTP) and HyperText Markup Language (HTML) used in web browsers have proven to be an effective way between human-computer interaction in internet scale. Web services are also used for communication between 2 systems such as communication between Automated Teller Machine (ATM) and server that all done in a synchronous way. There are 2 different ways to communicate between two systems, synchronous and asynchronous. In synchronous communication both parts must be online (for example a phone call), whereas in asynchronous communication only one part must be online (e.g. send email). Nowadays there are many devices that produce data continuously such as temperature sensors, Global Positioning system (GPS), humidity sensors, motion capture sensors. Due to the number of sensors available, the volume of data generated every second will make it difficult to manage in a good and easy way. This paper aims is to provide an overview of how an information technology role to manage data and then provide information on a particular problem. In Public Transportation Monitoring system there are system components that communicate in synchronous way. So, when one part does not work (i.e. web service) then the communication does not occur so that data such as geolocation is not stored. With the implementation of Message Broker Middleware architecture that works in asynchronous way on public transportation monitoring system, it is expected to solve the problems that occur with the synchronous way. Testing is conduct with multiple vehicles using mobile applications and some others with GPS Tracker module for 7 days to get raw location data and success stored in database. © 2020 IEEE.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

Scalable Method for Horizontal-Dipping Electrodeposition of Platinum Nanoparticles in Application to Dye-Sensitized Solar Cells

SSRN

引用

SSRN 2022年

作者： Augustowski, Dariusz Michalik, Maciej Wilgocki-Ślęzak, Jakub Kwaśnicki, Pawel Rysz, Jakub Department of Advanced Materials Engineering Faculty of Physics Astronomy and Applied Computer Science Jagiellonian University Lojasiewicza 11 Cracow30-348 Poland Research & Development Centre for Photovoltaics ML System S.A. Zaczernie 190G 36-062 Poland

Up-scaling is still a great opportunity to achieve in the third generation of solar cells. Described in this article novel method combine the electrodeposition with roll-to-roll technique and may be useful in future mass production of dye-sensitized solar cells. The results obtained showed that large areas of conductive substrates can easily be covered with platinum nanoparticles from a small amount of aqueous solution of the platinum precursor salt. The surface coverage could be controlled by applied current density, which has a direct impact on the power conversion efficiency of produced solar cells. The electrodeposition seems to be cheap, eco-friendly, and time-saving if compared with commonly used screen printing methods. Secondarily, the electrodeposited nanoparticles exhibited even higher electrocatalytic performance in cyclic voltametric measurements. The devices prepared with different deposition currents showed an efficiency in the range of 4.84-5.45%, while the referential screen printed solar cells had an average efficiency of 5.14%. © 2022, The Authors. All rights reserved.

关键词： Dye-sensitized solar cells

来源：评论

学校读者我要写书评

暂无评论

Hybrid Rider Optimization with Deep Learning Driven Biomedical Liver Cancer Detection and Classification

引用

Computational Intelligence and Neuroscience 2022年第0期2022卷 6162445页

作者： Al Duhayyim, Mesfer Mengash, Hanan Abdullah Marzouk, Radwa Nour, Mohamed K Mahgoub, Hany Althukair, Fahd Mohamed, Abdullah Department of Computer Science College of Sciences and Humanities-Aflaj Prince Sattam Bin Abdulaziz University Al-Kharj Saudi Arabia Department of Information Systems College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Department of Computer Sciences College of Computing and Information System Umm Al-Qura University Mecca Saudi Arabia Department of Computer Science College of Science & Art at Mahayel King Khalid University Abha Saudi Arabia Department of Computer Science Faculty of Computers and Information Menoufia University Shibin Al Kawm Egypt Department of Electrical Engineering and Computer Sciences College of Engineering University of CA Berkeley United States Research Center Future University in Egypt New Cairo11845 Egypt

Biomedical engineering is the application of the principles and problem-solving methods of engineering to biology along with medicine. Computation intelligence is the study of design of intelligent agents which are systems acting perceptively. The computation intelligence paradigm offers more advantages to the enhancement and maintenance of the field of biomedical engineering. Liver cancer is the major reason of mortality worldwide. Earlier-stage diagnosis and treatment might increase the survival rate of liver cancer patients. Manual recognition of the cancer tissue is a time-consuming and difficult task. Hence, a computer-aided diagnosis (CAD) is employed in decision making procedures for accurate diagnosis and effective treatment. In contrast to classical image-dependent "semantic"feature evaluation from human expertise, deep learning techniques could learn feature representation automatically from sample images using convolutional neural network (CNN). This study introduces a Hybrid Rider Optimization with Deep Learning Driven Biomedical Liver Cancer Detection and Classification (HRO-DLBLCC) model. The proposed HRO-DLBLCC model majorly focuses on the identification of liver cancer in the medical images. To do so, the proposed HRO-DLBLCC model employs preprocessing in two stages, namely, Gabor filtering (GF) based noise removal and watershed transform based segmentation. In addition, the proposed HRO-DLBLCC model involves NAdam optimizer with DenseNet-201 based feature extractor to generate an optimal set of feature vectors. Finally, the HRO algorithm with recurrent neural network-long short-term memory (RNN-LSTM) model is applied for liver cancer classification, in which the hyperparameters of the RNN-LSTM model are tuned by the use of HRO algorithm. The HRO-DLBLCC model is experimentally validated and compared with existing models. The experimental results assured the promising performance of the HRO-DLBLCC model over recent approaches. © 2022 Mesfer Al Duhayyi

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

A Global Asymptotically Stable Nonlinear Robust Bias Observer for MEMS Gyros

TechRxiv

引用

TechRxiv 2022年

作者： Tang, Ning Chang, Jieling Wang, Lingling Fu, Li Neusypin, Konstantin A. Selezneva, Maria S. Peng, Linping The School of Automation Science and Electrical Engineering Beihang University Beijing100191 China The Faculty of Computer Science and Control Systems Bauman Moscow State Technical University Moscow105005 Russia Experimental Teaching Demonstration Center of Mechanical and Control Engineering Beihang University Beijing100191 China The School of Mathematics and System Sciences Beihang University Beijing100191 China

In practical applications, commercial-grade Micro-Electro-Mechanical system (MEMS) gyros tend to exhibit dynamics sensitivities which are resistant to modeling by linear drift. To address the problem, a new nonlinear robust bias observer (NRBO) is proposed in this paper. Unlike the existing attitude and gyro bias nonlinear observers, we propose a dynamics-sensitive gyro bias decomposition method to tackle unknown nonlinear dynamic models of MEMS gyro bias. We expose the potential advantages of the proposed method: the global asymptotic stability of the NBRO and the robustness to the bias instability of MEMS gyros can be guaranteed through a rational design of the attitude-angular rate nonlinear dynamic coupling (AARNDC) term and the attitude-linear coupling (ALC) term. In addition, the attitude estimation with bias correction is given in the framework of NBRO. The experiment of a cable-parallel robot demonstrate the robustness to the bias instability and the accuracy improvement of MEMS gyros. © 2022, CC BY.

关键词： Gyroscopes

来源：评论

学校读者我要写书评

暂无评论

Location–allocation problem for green efficient two-stage vehicle-based logistics system: A type-2 neutrosophic multi-objective modeling approach

引用

Expert systems with Applications 2024年 238卷

作者： Das, Soumen Kumar Yu, Vincent F. Roy, Sankar Kumar Weber, Gerhard Wilhelm Department of Pure and Applied Sciences Midnapore City College Kuturia West Bengal Bhadutala721129 India Department of Applied Mathematics with Oceanology and Computer Programming Vidyasagar University West Bengal Midnapore721102 India Department of Industrial Management National Taiwan University of Science and Technology Taipei Taiwan Center for Cyber-Physical System Innovation National Taiwan University of Science and Technology Taipei Taiwan Faculty of Engineering Management Poznan University of Technology Poznan Poland IAM METU Ankara Turkey

In recent decades, global climate change has become one of the most critical environmental issues, leading to increased environmental and social concerns about the sustainability of logistics networks. This study proposes a novel multi-objective, multi-facility location–allocation model for a two-stage solid logistics network that supports green practices. To account for uncertainty in real-world problems, some parameters of the model are represented as triangular type-2 neutrosophic numbers to deal with hesitant situations. The fuzzy model is then converted into a deterministic one using a new ranking approach. Three conflicting objective functions – minimizing total financial costs, maximizing customers’ satisfaction levels, and ensuring sustainable and effective conveyances – are simultaneously optimized using the ϵ-constraint approach. The proposed model and solution approach are tested with two numerical examples. A comparative study is also presented, comparing the proposed approach with other Pareto-based multi-objective approaches, such as the global criterion approach, multi-objective fuzzy programming, and weighted Chebychev programming. Finally, the paper concludes with some remarks. © 2023

关键词： Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Evaluation of algorithms and security protocols to mitigate the risks in commercial transactions carried out by public companies

Evaluation of algorithms and security protocols to mitigate ...

引用

2020 Asia Conference on computers and Communications, ACCC 2020

作者： Toapanta, Segundo Moises Toapanta Gallegos, Luis Enrique Mafla Alvarado, Alex Enrique Aranda Solis, Maximo Prado Quito Ecuador Faculty of System Engineering Quito Ecuador Department of Computer Science Guayaquil Ecuador Universidad Técnica Luis Vargas Torres de Esmeraldas Career Social Sciences Esmeraldas Ecuador

ISBN: (纸本)9781728189673

The security problems in electronic commerce in transactions are very evident in public companies. The objective of this research is to analyze security algorithms and protocols to mitigate risks and vulnerabilities within commercial transactions that help us identify computer attacks, whether internal or external. Deductive method and exploratory research were used to analyze the information from the reference articles and information available online;regarding different types of protocols and algorithms that protect the information in its entirety and confidentiality, thus providing the respective security to the information of public companies. It resulted in a control of the security and privacy factors, by having RSA algorithms with formulas to encrypt and decrypt public keys, combinations of commercial transactions, asymmetric and symmetric cryptography and the SET protocol, which facilitates the algorithms in decision-making within the organizations. It was concluded that the SET protocol is the best in facilitating greater security to mitigate vulnerabilities, threats and risks of its processes in public organizations. © 2020 IEEE.

关键词： Decision making

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：