检索结果-内蒙古大学图书馆

2nd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2023

作者： Deepika, P. Arthi, B. SRM Institute of Science and Technology Chennai India Easwari Engineering College Department of Information Technology TN Chennai India College of Engineering and Technology Faculty of Engineering and Technology SRM Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350397635

Tomato is most widely used and important crop in India. It plays a significant role in agriculture. Tomato plant grows in short period of time yields more tomatoes. Tomato is good in both nutrition and income. It can be grown in any soil condition and temperature. There are various diseases that affect tomato. To increase the production of tomato early detection of disease is important. There are various diseases in tomato plant like bacterial wilt, early blight, Late blight, Leaf, septorial leaf spot, leaf mold, bacterial spot etc. Deep Learning technologies provides better result in disease identification and detection. Deep learning architectures AlexNet, ResNet50, DenseNet121, EfficientNetB5, Inception-Resnet-V2, InceptionV3, MobileNet, VGG16 and VGG19 are tested against tomato plant diseases. The implementation is done by taking the tomato leaf images from real environment. The nine architectures are compared and in which DenseNet121 and MobileNet provides better accuracy than other deep learning architectures. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Mobile IP-based protocol for wireless personal area networks in critical environments

Mobile IP-based protocol for wireless personal area networks...

引用

作者： Jara, Antonio J. Silva, Ricardo M. Silva, Jorge S. Zamora, Miguel A. Skarmeta, Antonio F. G. Department of Information and Communications Engineering Computer Science Faculty University of Murcia Murcia Spain Department of Informatics Engineering Faculty of Sciences and Technology University of Coimbra Coimbra Portugal

Low-power Wireless Personal Area Networks (LoWPANs) are still in their early stage of development, but the range of conceivable usage scenarios and applications is tremendous. That range is extended by its inclusion in Internet with IPv6 Low-Power Personal Area Networks (6LoWPANs). This makes it obvious that multi-technology topologies, security and mobility support will be prevalent in 6LoWPAN. Mobility based communication increases the connectivity, and allows extending and adapting LoWPANs to changes in their location and environment infrastructure. However, the required mobility is heavily dependent on the individual service scenario and the LoWPAN architecture. In this context, an optimized solution is proposed for critical applications, such as military, fire rescue or healthcare, where people need to frequently change their position. Our scenario is health monitoring in an oil refinery where many obstacles have been found to the effective use of LoWPANs in these scenarios, mainly due to transmission medium features i.e. high losses, high latency and low reliability. Therefore, it is very difficult to provide continuous health monitoring with such stringent requirements on mobility. In this paper, a paradigm is proposed for mobility over 6LoWPAN for critical environments. On the one hand the intra-mobility is supported by GinMAC, which is an extension of IEEE 802.15.4 to support a topology control algorithm, which offers intra-mobility transparently, and Movement Direction Determination (MDD) of the Mobile Node (MN). On the other hand, the inter-mobility is based on pre-set-up of the network parameters in the visited networks, such as Care of Address and channel, to reach a fast and smooth handoff. Pre-set-up is reached since MDD allows discovering the next 6LoWPAN network towards which MN is moving. The proposed approach has been simulated, prototyped, evaluated, and is being studied in a scenario of wearable physiological monitoring in hazardous industrial a

关键词： Personal communication systems

来源：评论

学校读者我要写书评

暂无评论

Incremental discovery of crowd from evolving trajectory data 4

Incremental discovery of crowd from evolving trajectory data

引用

4th International Conference on engineering, Applied Sciences and technology, ICEAST 2018

作者： Shein, Thi Thi Puntheeranurak, Sutheera Imamura, Makoto Faculty of Engineering King Mongkut's Institute of Technology Ladkrabang Department of Computer Engineering Bangkok Thailand Tokai University Department of Embedded Technology Tokyo Japan

ISBN: (纸本)9781538649565

Discovering the useful knowledge from the evolving trajectory data stream contributes to real-world applications such as animal movement behavior analysis, traffic monitoring, and weather forecasting. Among these explorations, moving objects' crowd detection is a challenging task and enabling to find anomalies in the traffic system. In a real application, a large volume of trajectory data stream arrives continuously for immediate data analysis. Due to the changes of these trajectory data, there is a remaining challenge to discover crowd efficiently. In this paper, we propose incremental crowd discovery framework over evolving data stream to reduce computational time complexity. In our framework, firstly we discover the group by proposing micro-group based clustering, and then we incrementally detect the crowd structure form. Experiments of our proposed system will conduct on real taxi trajectory data and synthetic data. © 2018 IEEE.

关键词： Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

Design of Ultra-Wideband and Constant Gain Antipodal Vivaldi Antenna with Corrugations

Design of Ultra-Wideband and Constant Gain Antipodal Vivaldi...

引用

2022 International Electrical engineering Congress, iEECON 2022

作者： Thaiwirot, Wanwisa Kamoldej, Dechawat Detchporn, Phongsapuk Thongdit, Preecha Tangwachirapan, Shalermchon King Mongkut's University of Technology North Bangkok Faculty of Engineering Department of Electrical and Computer Engineering Bangkok Thailand Nakhon Pathom Rajabhat University Faculty of Science and Technology Department of Telecommunication Engineering Nakhon Pathom Thailand

ISBN: (纸本)9781665402064

This paper presents the design of ultra-wideband and constant gain antipodal Vivaldi antenna with corrugations. The both side edges of proposed antenna are corrugated by slots along the y-axis in order to enhance the gain, especially at lower frequencies. The corrugations are elliptical slots with varying length by exponential function. In addition, bottom edges of conducting arms are also corrugated by elliptical slots along the x-axis. With combination of corrugations on both side edges and bottom edges of conducting arms, the gain of proposed antenna significantly increases, especially at lower end of operating frequency band. By using corrugations, the gain and radiation patterns are improved without increasing the antenna size. Therefore, the overall size of proposed antenna remains compact with dimension of 45 mm × 45 mm. From simulated results, the proposed antenna can operate within the bandwidth covering from 2.97 GHz to above 10 GHz with maximum gain of 6.57 dBi and 1.17 dBi gain variation. © 2022 IEEE.

关键词： Exponential functions

来源：评论

学校读者我要写书评

暂无评论

Optimizing Multi-Hop Quantum Communication using Bidirectional Quantum Teleportation Protocol

arXiv

引用

arXiv 2025年

作者： Ikken, N. Kumar, P. Slaoui, A. Kar, B. Laamara, R. Ahl Almousa, M. El-Latif, A.A. Abd LPHE-Modeling and Simulation Faculty of Sciences Mohammed V University Rabat Morocco Department of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei Taiwan Centre of Physics and Mathematics CPM Faculty of Sciences Mohammed V University in Rabat Rabat Morocco EIAS Data Science Lab College of Computer and Information Sciences Center of Excellence in Quantum and Intelligent Computing Prince Sultan University Riyadh11586 Saudi Arabia Department of Information Technology College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh11671 Saudi Arabia Department of Mathematics and Computer Science Faculty of Science Menoufia University Shebin El-Koom32511 Egypt

In this paper, we introduce a new method for Bidirectional Quantum Teleportation called Bidirectional Quantum Teleportation using the Modified Dijkstra Algorithm and Quantum Walk (BQT-MDQW). This method uses different types of entangled states, such as the GHZ-Bell state, W-Bell state, and Cluster-Bell state, to improve quantum communication in multi-hop quantum wireless networks. We focus on the W-Bell state and compare the quantum Dijkstra algorithm with the classical Dijkstra method to see which one works better. We apply both versions to quantum and classical simulators, measuring their performance through fidelity, memory utilization, and throughput calculations. Our results show that the shortest path problem may be solved with significantly reduced computer complexity using the quantum Dijkstra algorithm based on quantum walks. The introduction of a quantum walk, which permits dynamic transitions between quantum channels and the effective exploration of quantum network states, is an important part of the protocol. Using the capacity of the quantum walk to adjust to changing quantum states, we also introduce a method for successfully identifying unitary matrices under varying quantum channels. The bidirectional teleportation structure of the protocol is designed to solve the multi-hop teleportation problem in quantum wireless networks. In addition, we present quantum Dijkstra’s algorithm, which uses quantum gates to significantly decrease computational complexity and solve the networking problem by building on the quantum walk framework. This method shows how quantum computing may be used to solve arbitrary optimization issues such as the shortest path problem. Finally, we present a novel multi-hop quantum teleportation system encompassing both unidirectional and bidirectional communication, as introduced in the quantum Dijkstra algorithm system. This system significantly enhances communication in quantum networks by enabling efficient and reliable information

关键词： Quantum channel

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Channel State Estimators for 5G Wireless Communication Systems

引用

computer Modeling in engineering & Sciences 2023年第4期135卷 755-778页

作者： Mohamed Hassan Essai Ali Fahad Alraddady Mo’ath Y.Al-Thunaibat Shaima Elnazer Department of Electrical Engineering Faculty of EngineeringAl-Azhar UniversityQena83513Egypt Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Management Information Systems Taif UniversityTaif21944Saudi Arabia

For a 5G wireless communication system,a convolutional deep neural network(CNN)is employed to synthesize a robust channel state estimator(CSE).The proposed CSE extracts channel information from transmit-and-receive pairs through offline training to estimate the channel state ***,it utilizes pilots to offer more helpful information about the communication *** proposedCNN-CSE performance is compared with previously published results for Bidirectional/long short-term memory(BiLSTM/LSTM)NNs-based *** CNN-CSE achieves outstanding performance using sufficient pilots only and loses its functionality at limited pilots compared with BiLSTM and LSTM-based *** three different loss function-based classification layers and the Adam optimization algorithm,a comparative study was conducted to assess the performance of the presented DNNs-based *** BiLSTM-CSE outperforms LSTM,CNN,conventional least squares(LS),and minimum mean square error(MMSE)*** addition,the computational and learning time complexities for DNN-CSEs are *** estimators are promising for 5G and future communication systems because they can analyze large amounts of data,discover statistical dependencies,learn correlations between features,and generalize the gotten knowledge.

关键词： DLNNs channel state estimator 5G and beyond communication systems robust loss functions

来源：评论

学校读者我要写书评

暂无评论

Residual-driven Fuzzy C-Means Clustering for Image Segmentation

引用

IEEE/CAA Journal of Automatica Sinica 2021年第4期8卷 876-889页

作者： Cong Wang Witold Pedrycz ZhiWu Li MengChu Zhou Department of Electrical and Computer Engineering University of AlbertaEdmontonAB T6R 2V4Canada School of Electro-Mechanical Engineering Xidian UniversityXi’an 710071China the Faculty of Engineering King Abdulaziz UniversityJeddah 21589Saudi Arabia School of Electro-Mechanical Engineering Xidian UniversityXi’an 710071and also with the Institute of Systems EngineeringMacao University of Science and TechnologyMacaoChina Institute of Systems Engineering Macao University of Science and TechnologyMacao 999078China the Helen and John C.Hartmann Department of Electrical and Computer Engineering New Jersey Institute of TechnologyNewarkNJ 07102 USA

In this paper,we elaborate on residual-driven Fuzzy C-Means(FCM)for image segmentation,which is the first approach that realizes accurate residual(noise/outliers)estimation and enables noise-free image to participate in *** propose a residual-driven FCM framework by integrating into FCM a residual-related regularization term derived from the distribution characteristic of different types of *** on this framework,a weighted?2-norm regularization term is presented by weighting mixed noise distribution,thus resulting in a universal residual-driven FCM algorithm in presence of mixed or unknown ***,with the constraint of spatial information,the residual estimation becomes more reliable than that only considering an observed image *** experiments on synthetic,medical,and real-world images are *** results demonstrate the superior effectiveness and efficiency of the proposed algorithm over its peers.

关键词： Fuzzy C-Means image segmentation mixed or unknown noise residual-driven weighted regularization

来源：评论

学校读者我要写书评

暂无评论

Comparison of two optical image encryption techniques 4

Comparison of two optical image encryption techniques

引用

4th International Conference on Fuzzy Systems and Data Mining, FSDM 2018

作者： Elshamy, Ahmed M. Hussein, Aziza I. Hamed, Hesham F.A. Abdelghany, M.A. Kelash, Hamdy M. College of Information Technology Fujairah University Fujairah United Arab Emirates Department of Electrical and Computer Engineering Effat University Jeddah KSA and Department of Computer and Systems Engineering Faculty of Engineering Minia University Minia Egypt Department of Communication and Electronics Faculty of Engineering Minia University Minia Egypt Department of Computer Science and Engineering Faculty of Electronic Engineering Menoufia University Menouf Egypt

ISBN: (纸本)9781614999270

It is necessary to identify the latest and newest techniques that proposed in order to fulfill the specific requirements and use it in the field of information security. There are some chaos techniques in image encryption and phase modulation encryption technique have been suggested. In the present paper the discrete Fourier transform was used to create phase modulation for a grayscale image. The image to encrypt is placed by one of chaos maps, Baker and Arnold cat maps, then combined with two random phase modulation based on the discrete Fourier transform. However, to decrypt the encrypted image required to have three keys, one for chaotic map and other two keys for removing phase modulation. The use of the discrete Fourier transform, phase modulation and chaos in image encryption add much more complexity to the decryption of the image for unauthorized person. The main contribution of this paper to compare between our two proposed in performance and efficiency. Numerical simulation results by Matlab have been executed to validate the two proposals. Furthermore, second proposal which implements by Arnold cat map and phase modulation achieved good test results in encryption quality metrics and noise immunity which is most optimal. © 2018 The authors and IOS Press. All rights reserved.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Wire grounding electrode near vertical cylindrical non-homogeneity 21

Wire grounding electrode near vertical cylindrical non-homog...

引用

21st International Symposium on Electrical Apparatus and Technologies, SIELA 2020

作者： Jovanovic, Dragana B. Jovanovic, Dejan B. Zivaljevic, Dragana U. Cvetkovic, Nenad N. Hederic, Zeljko University of Nis Faculty of Electronic Engineering Nis Serbia J.J. Strossmayer University Faculty of Electrical Engineering Computer Science and Information Technology Osijek Croatia

ISBN: (纸本)9781728143460

Satisfactorily accurate approximation of soil inhomogeneity providing simple determination of the soil structure influence on grounding system characteristics is important part of the procedure for grounding system analysis. Very often, ground non-homogeneity can be approximated as vertical cylinder tube (wells, various tubes, pillar foundation etc.). The method based on using of Method on Moments and Green's function, applicable for analysis of grounding systems placed in the surrounding soil of this type non-homogeneity is presented in the paper. © 2020 IEEE.

关键词： Electric grounding

来源：评论

学校读者我要写书评

暂无评论

SNPE-SRGAN: Lightweight Generative Adversarial Networks for Single-Image Super-Resolution on Mobile Using SNPE Framework 5

SNPE-SRGAN: Lightweight Generative Adversarial Networks for ...

引用

5th International Conference on Computing and Applied Informatics, ICCAI 2020

作者： Tampubolon, Hendrik Setyoko, Aji Purnamasari, Fanindia Department of Information System Faculty of Engineering and Computer Science Krida Wacana Christian University Jakarta Indonesia Department of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei Taiwan Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan20155 Indonesia

An image resulting from a low-resolution (LR) camera on the mobile phone has lower quality than a high-resolution(HR) camera on a DSLR. Meanwhile, the HR camera is pricing if compared with the LR camera. How to achieve a single-image quality on LR camera likewise on HR camera becomes essential research in the past years. Addressing this issue can be done by upscaling a single LR image. Recently, the super-resolution generative adversarial network (SRGAN) model is one of the state-of-the-art super-resolution(SR)models employed on single-image SR. However, implementing a deep learning model like SRGAN on a mobile device is challenging in computation power and resources. This study aims to develop a smaller and lower resources model while preserving single-image SR quality on mobile devices. To meet these objectives, we convert, quantize, and compress the SRGAN model on Snapdragon Neural Processing Engine (SNPE) as an example. We then validate the SRGAN on the DIV2K dataset on which improves the model performances. Besides, we conduct experiments on GPU, DSP environment. The experimental result confirmed that SNPE-SRGAN capable of achieves not only HR images' quality but also low latency by 0.06 second and smaller model by 1.7 Mb size running on DSP. Also, the SRGAN-DLC-Quantized running on GPU has a smaller size by 1.7 Mb and lower latency by 1.151 seconds compared with Non-quantized SRGAN-TensorFlow by 9.1 Mb and 1.608 seconds latency. © Published under licence by IOP Publishing Ltd.

关键词： Generative adversarial 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：