检索结果-内蒙古大学图书馆

High Coupling Efficiency Grating Couplers for Silicon Photonics

High Coupling Efficiency Grating Couplers for Silicon Photon...

2023 Asia Communications and Photonics Conference/2023 International Photonics and Optoelec.ronics Meetings, ACP/POEM 2023

作者： Petropoulos, P. Vitali, V. Marchetti, R. Bucio, T. Dominguez Gardes, F.Y. Lacava, C. Optoelectronics Research Centre University of Southampton Southampton United Kingdom Optoelectronics Res. Ctr. Univ. of Southampton Southampton U. Kingdom and Elec. Univ. of Pavia Computer and Biomedical Engineering Department Pavia Italy University of Pavia Electrical Computer and Biomedical Engineering Department Pavia Italy

We present techniques for optimizing the coupling efficiency between silicon photonic and optical fibre systems based on the adoption of back-end-of-line CMOS-compatible waveguide grating couplers. © 2023 IEEE.

ISBN: (纸本)9798350312614

关键词： grating couplers silicon photonics

来源：评论

学校读者我要写书评

暂无评论

An Edge Computing Enabled Internet of Medical Things Device for Remote Patient Health Monitoring Applications

An Edge Computing Enabled Internet of Medical Things Device ...

引用

2024 IEEE Students Conference on engineering and Systems, SCES 2024

作者： Manoj, Ashwin Paramasivam, A. Vijayalakshmi, S. Bhaskar, K.B. Thriumbiga, S.K. Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Biomedical Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Elect. Comm. Engg. Chennai India Adhi College of Engineering and Technology Department of Elec. and Electro. Engg. Kanchipuram India

ISBN: (纸本)9798350374711

Recent days, Patient Monitoring helps the medical professionals to monitor patient throughout the day. Also, the use of Internet of Medical Things (IoMT) enables this process to be done remotely. IoMT is a subset of Internet of Things, specialized in medical applications. Moreover, Artificial Intelligence (AI) based image classification algorithms can be incorporated to improvise and automate the process, to detect the patients' health state. In this work, an edge computing enabled Internet of Medical Things (IoMT) device is designed and developed for remote health monitoring applications. Further, a less expensive ESP32 CAM device is utilized as an edge computing enabled IoMT device in which a MobileNetV2 version 0.35 model Algorithm is integrated to predict two different patient activities such as asleep and critical conditions. Results demonstrate that the MobileNetV2 version 0.35 model has a better classification accuracy of 97.5%. Also, it is observed that the proposed AI-enabled edge computing device is capable of identifying the patient's conditions and it alerts the physician about the patient's critical conditions using Short Messaging Service (SMS). This work appears to be of high societal relevance since the proposed device helps the physician to monitor the patient's conditions in a remote manner. © 2024 IEEE.

关键词： elec.ronic health record

来源：评论

学校读者我要写书评

暂无评论

Edge Computing-based Intelligent Garbage Classification and Recognition Application 4

Edge Computing-based Intelligent Garbage Classification and ...

引用

4th International Conference on computers and Artificial Intelligence Technology, CAIT 2023

作者： Yu, Liang Mo, Fu Lai, Yangbing Tian, Liwei Guangdong University of Science and Technology College of Computer Science and AIoT Edge Computing Engineering Technology Research Center of Dongguan City DongGuan China Guangdong University of Science and Technology Coll. of Mech. and Elec. Eng. and Intelligent Mfg. and Environ. Monitoring Engineering Technology Research Center of Dongguan City DongGuan China

ISBN: (纸本)9798350326710

As the standard of living improves, there is a corresponding increase in the variety of materials, leading to a rise in household garbage. Dealing with the challenge of classifying numerous types of garbage can be a daunting task. The accuracy of waste separation cannot be effectively improved solely by relying on individuals' common sense perception, knowledge propaganda, and training. A more comprehensive and efficient approach is needed. This paper proposes an intelligent waste classification and recognition application based on edge computing to address the aforementioned issues. The edge mobile intelligent waste classification and recognition application utilizes a small-sample lightweight machine learning model for training compressed quantization on the Edge Impulse Platform (EI). The application is built using the MobileNetV2 model and migration learning theory. When a user scans a trash image by running the application through a mobile edge device, the tiny machine learning model is invoked to perform edge computation and identify the class of trash. System testing on the EI platform and field applications demonstrates that the average response time for intelligent waste classification and recognition is 0.66 seconds. Additionally, the average inference time is less than 5 milliseconds, and the application achieves an average recognition accuracy of 97% or higher. This intelligent waste classification and recognition system exhibits excellent overall performance and offers great convenience for individuals in their daily waste classification tasks. © 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 Multi-Classification Approach for Drugs Based on ANN and Other ML Algorithms with Hyper Parameter Tuning

A Novel Multi-Classification Approach for Drugs Based on ANN...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Mohd Firoz Warsi Nitin Kumar Chauhan Shiv Narain Gupta Rahul Dev Ashish Choudhary Department of Computer Science (AIDS) Greater Noida Institute of Technology Greater Noida India Department of Elec. and Comm. Engg. Indore Institute of Science and Technology Indore India Department of Elec. and Comm. Engg. Greater Noida Institute of Technology Greater Noida India Department of Elec. and Comm. Engg. G.L. Bajaj Institute of Technology & Management Greater Noida Uttar Pradesh India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

In the realm of pharmaceutical research and development, accurate classification of drugs is of paramount importance for effective therapeutic interventions. This paper proposes a novel approach to drug classification utilizing a combination of Machine Learning (ML) and Artificial Neural Networks (ANN) algorithms. By harnessing the power of ANN's ability to learn complex patterns and ML's versatility in handling diverse datasets, our approach aims to enhance the accuracy and efficiency of drug classification tasks. Furthermore, we incorporate hyper parameter tuning techniques to optimize model performance, thereby maximizing predictive capabilities. Through comprehensive experimentation and evaluation on real-world drug datasets, our proposed methodology demonstrates promising results, showcasing superior classification accuracy compared to traditional methods. This research advances drug discovery and development by providing a robust framework for accurate drug classification in biomedical and pharmaceutical fields. In this study we have applied ten ML technique: Logistic Regression, Decision tree, Random forest, Catboost classifier, Adaboost classifier, Ensemble classifier, Gradient boosting classifier, LGBM classifier, Soft voting classifier, ANN with hyper parameter tuning and Support vector machine on the drugs classification dataset. The evaluation of classification outcomes was conducted both with and without the implementation of hyper parameter tuning. Notably, upon applying hyper parameter tuning, the ANN classifier emerged as the top performer, surpassing all other classifiers. RFC and DTC have also attained good accuracy of 96%. Impressively, ANN attained an accuracy rate of 99.29%, showcasing its superior performance in the dataset.

关键词： Drugs Support vector machines Logistic regression Accuracy Machine learning algorithms Artificial neural networks Classification algorithms Drug discovery Tuning Random forests

来源：评论

学校读者我要写书评

暂无评论

Physics-Informed Machine Learning for elec.ricity Markets: A NYISO Case Study

IEEE Transactions on Energy Markets, Policy and Regulation

引用

IEEE Transactions on Energy Markets, Policy and Regulation 2024年第1期2卷 40-51页

作者： Ferrando, Robert Pagnier, Laurent Mieth, Robert Liang, Zhirui Dvorkin, Yury Bienstock, Daniel Chertkov, Michael University of Arizona Program in Applied Mathematics and Department of Mathematics TucsonAZ85721 United States Department of Industrial and Systems Engineering at Rutgers University PiscatawayNJ08854 United States Johns Hopkins University Department of Electrical and Computer Engineering BaltimoreMD21218-2625 United States Elec. and Comp. Eng. and Ralph o'Connor Sustainable Energy Institute Department of Civil and Systems Engineering Johns Hopkins University BaltimoreMD21218-2625 United States Columbia University IEOR New YorkNY10027 United States

This article addresses the challenge of efficiently recovering exact solutions to the optimal power flow problem in real-time elec.ricity markets. The proposed solution, named Physics-Informed Market-Aware Active Set learning OPF (PIMA-AS-OPF), leverages physical constraints and market properties to ensure physical and economic feasibility of market-clearing outcomes. Specifically, PIMA-AS-OPF employs the active set learning technique and expands its capabilities to account for curtailment in load or renewable power generation, which is a common challenge in real-world power systems. The core of PIMA-AS-OPF is a fully-connected neural network that takes the net load and the system topology as input. The outputs of this neural network include active constraints such as saturated generators and transmission lines, as well as non-zero load shedding and wind curtailments. These outputs allow for reducing the original market-clearing optimization to a system of linear equations, which can be solved efficiently and yield both the dispatch decisions and the locational marginal prices (LMPs). The dispatch decisions and LMPs are then tested for their feasibility with respect to the requirements for efficient market-clearing results. The accuracy and scalability of the proposed method is tested on a realistic 1814-bus NYISO system with current and future renewable energy penetration levels. © 2023 IEEE.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Joint alignment and steering to manage interference

引用

Digital Communications and Networks 2024年第2期10卷 429-438页

作者： Zhao Li Xiujuan Liang Yinghou Liu Jia Liu Zheng Yan School of Cyber Engineering Xidian UniversityXi'an710126China Technol.on Commun.Net.Lab. The 54th Research Inst.of China Elec.Technol.Group Corp.Shijiazhuang050081China School of Computer Science and Technology Xidian UniversityXi'an710126China The Department of Communications and Networking(Comnet) Aalto University02150EspooFinland

In wireless communication networks,mobile users in overlapping areas may experience severe interference,therefore,designing effective Interference Management(IM)methods is crucial to improving network ***,when managing multiple disturbances from the same source,it may not be feasible to use existing IM methods such as Interference Alignment(IA)and Interference Steering(IS)*** is because with IA,the aligned interference becomes indistinguishable at its desired Receiver(Rx)under the cost constraint of Degrees-of-Freedom(DoF),while with IS,more transmit power will be consumed in the direct and repeated application of IS to each *** remedy these deficiencies,Interference Alignment Steering(IAS)is proposed by incorporating IA and IS and exploiting their advantages in *** IAS,the interfering Transmitter(Tx)first aligns one interference incurred by the transmission of one data stream to a one-dimensional subspace orthogonal to the desired transmission at the interfered Rx,and then the remaining interferences are treated as a whole and steered to the same subspace as the aligned ***,two improved versions of IAS,i.e.,IAS with Full Adjustment at the Interfering Tx(IAS-FAIT)and Interference Steering and Alignment(ISA),are *** former considers the influence of IA on the interfering user-pair's *** orthogonality between the desired signals at the interfered Rx can be maintained by adjusting the spatial characteristics of all interferences and the aligned interference components,thus ensuring the Spectral Efficiency(SE)of the interfering communication *** ISA,the power cost for IS at the interfered Tx is minimized,hence improving SE performance of the interfered *** the proposed methods are realized at the interfering and interfered Txs cooperatively,the expenses of IM are shared by both *** in-depth simulation results show that joint use of IA and

关键词： Interference Interference management Interference alignment Interference steering Spectral efficiency

来源：评论

学校读者我要写书评

暂无评论

CDP: Selec.ive Influential Nodes Based on Cliques in the Diffusion Process in Social Networks 9

CDP: Selective Influential Nodes Based on Cliques in the Dif...

引用

9th International Conference on Web Research, ICWR 2023

作者： Yazdanifar, Fatemeh Beni, Hamid Ahmadi Salimi, Nikoo Bouyer, Asgarali Amirkabir University of Technology Dept. of Mathematics and Computer Science Tehran Iran Madani University Dept. Software Engineering Azarbijan Shahid Tabriz Iran University of Genoa Dept. of the Elec. Electronics Electronics and Telecommunication Eng. and Naval Architecture Genoa Italy Azarbaijan Shahid Madani University Dept. of Computer Engineering Tabriz Iran

ISBN: (纸本)9798350399691

Influence maximization techniques emphasize selec.ing a set of influential nodes in order to maximize influence. Because the algorithms presented in this field ignore the topology of cliques for diffusion, there are two major challenges in influence maximization algorithms: optimal diffusion and computational overhead reduction. As a result, the CDP algorithm is presented in this article to address these issues. This algorithm first selec.s suitable cliques for diffusion based on their position and strategy in social networks. Furthermore, for each clique, a score is calculated based on the topological criteria of the clique, and suitable cliques are selec.ed for diffusion by applying a threshold limit. The seed nodes are chosen from the cliques in the second step. To avoid the rich club phenomenon, only a few nodes from each clique are chosen as seed candidate nodes. Finally, the seed nodes are chosen based on the node's topology and the strength of the node's level one neighbor. In the experiment section, the CDP algorithm significantly outperforms the best algorithms presented in recent years in terms of influence spread rate and execution time. © 2023 IEEE.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Based Joint Resource Allocation and User Fairness Optimization in mmWave-NOMA HetNets 31

Reinforcement Learning Based Joint Resource Allocation and U...

引用

31st International Conference on elec.rical engineering, ICEE 2023

作者： Sobhi-Givi, Sima Nouri, Mahdi Shayesteh, Mahrokh G. Kalbkhani, Hashem Ding, Zhiguo Urmia University Electrical and Computer Engineering Department Urmia Iran Sharif University of Technology Elect. Eng. Dep. Iran Iran Tehran Iran Sharif University of Technology Wireless Research Lab Acri Elec. Eng. Dep. Tehran Iran Urmia University of Technology Faculty of Elec. Eng. Urmia Iran School of Electrical and Electronic Engineering The University of Manchester ManchesterM13 9PL United Kingdom

ISBN: (纸本)9798350312560

In this paper, we propose heterogeneous network (HetNet) with mmWave and hybrid non-orthogonal multiple access (NOMA) and orthogonal multiple access (OMA) transmission, where uplink (UL) of macrocell users (MCUs) and downlink (DL) of small cell users (SCUs) share the same resource block (RB) to increase the network capacity. Also, an imperfect successive interference cancelation (I-SIC) decoding is considered due to hardware impairment of the real-world NOMA systems. We formulate the problem of joint power and resource block (RB) allocation to maximize rate-fairness and sum-rate by considering minimum quality of service (QoS) requirements. Reinforcement learning (RL) named Q-learning (QL) and deep Q-learning network (DQN) algorithms are employed to solve these problems. The results indicate that the proposed QL and DQN algorithms increase the fairness and sum-rate while low number of iterations is required. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

HRPE-Enhanced AI-Based 5G Indoor Localization in Presence of Specular and Dense Multipaths

HRPE-Enhanced AI-Based 5G Indoor Localization in Presence of...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Yuchen Shi Xiaoxiao Yang Yuying Sun José Rodríguez-Piñeiro Xueming Hong Tomás Domínguez-Bolaño Xuefeng Yin College of Electronics and Information Engineering Tongji University Shanghai China School of Elec. Science and Engineering Xiamen University China School of Informatics Xiamen University China CITIC Research Center & Department of Computer Engineering University of A Coruña Spain

Fifth generation (5G) communication systems are expected to provide an ubiquitous solution for indoor positioning, and deep neural networks (DNNs) have been recently proposed for this purpose. However, DNN-based positioning solutions are in general very dependent on the training data. In this paper, an architecture for positioning based on wireless signals is proposed, namely the SAGE-Enhanced CEAP (SE-CEAP). The architecture considers firstly an enhancement of the acquired Channel State Information (CSI) data by means of a high-resolution parameter estimation (HRPE) method, namely the space-alternating generalized-expectation maximization (SAGE) algorithm, and secondly a specifically designed DNN for localization, namely the CNN-Enblock AI Positioning (CEAP). The provided results, considering a realistic 5G New Radio (NR) deployment in an indoor scenario, show that the proposed architecture outperforms other classical DNN-based localization approaches, not only in localization accuracy, but also in generalizability of the results, which is a common drawback of DNN-based solutions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Experiment to Evaluate IoT Application Security Scheme (IoTGazePass)

An Experiment to Evaluate IoT Application Security Scheme (I...

引用

2022 International Conference on engineering and MIS, ICEMIS 2022

作者： Keshlaf, Ayad A. Alfard, Faheemah M. Bouzid, Omar M. Sabratha University Faculty of Engineering Computer Eng. and It Department Sabratha Libya Libyan Center for Electronic Systems Programming and Aviation Research University of Zawia Computer Department Faculty of Engineering Zawia Libya University of Gharyan Faculty of Engineering Elec. and Electronic Eng. Dept Gharyan Libya

ISBN: (数字)9781665454360

ISBN: (纸本)9781665454360

IoTGazePass is a new password scheme that has been designed to tackle the weaknesses of existing types of passwords. It is intended to be suitable for IoT applications. An experiment was conducted to evaluate the strengths and weaknesses of the IoTGazePass scheme (e.g., security, usability and memorability). The evaluation aspects include a comparison with traditional textual and graphical based passwords in terms of memorability and security of the passwords. The results of the evaluation indicate that the IoTGazePass scheme is easy to use, memorable and flexible, as it can generate strong, secure and scalable passwords. The experiment results have also showed that the IoTGazePass scheme have good ability to deal with shoulder surfing attacks. In fact, the experiment results lead to some recommendations and suggestions to improve the planned performance. © 2022 IEEE.

关键词： Authentication

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：