检索结果-内蒙古大学图书馆

2023 International conference on Circuit Power and Computing Technologies, ICCPCT 2023

作者： Sangeetha, B. Parvathi Pradhap, J. Ganesh, Sham Revanth, Amruth Aarupadai Veedu Institute of Technology Department of Electrical and Electronics Engineering Tamil Nadu Paiyanur603104 India

ISBN: (纸本)9798350333244

A Hybrid Electric Vehicle (HEV) and an evolution of Electric Vehicles (EV) have achieved engrossment in day to day life because of its advantage like structural flexibility, improvement towards air quality, noise free and comfort. The performance of Energy Management System (EMS) is hampered by complex configuration and behaviour of multi-source hybrid energy systems. The goal of EMS is to instantly regulate energy flows from converters to meet control objectives, regardless of architecture of powertrain. In this paper, a novel bidirectional isolated DC-DC converter together with cascaded Artificial Neural network (ANN) controller is used to enhance system input voltage from the Diode Bridge Rectifier (DBR) with medium power applications. Furthermore, the adoption of cascaded ANN controller supports in regulating current and voltage individually. A MATLAB simulation followed by hardware analysis is performed to determine the steady state operation of converter. According to the simulation results, EMS with vehicle system designation greatly increase fuel economy. © 2023 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Two-dimensional Dataset Reduction in Data-Driven Fault Detection for IoT-based Cyber Physical systems

Two-dimensional Dataset Reduction in Data-Driven Fault Detec...

引用

IEEE International conference on Omni-Layer Intelligent systems (IEEE COINS)

作者： Tertytchny, Georgios Michael, Maria K. Univ Cyprus KIOS Res & Innovat Ctr Excellence Dept Elect & Comp Engn Nicosia Cyprus

ISBN: (数字)9781665483568

ISBN: (纸本)9781665483568

internet of Things (IoT)-based Cyber-Physical systems (CPS) are the integration of computational, networking and physical processes. IoT devices are used to enhance monitoring and control of such systems. CPS normal operation might be altered by physical component faults, which can be exploited to generate abnormal behaviour. Data-driven fault detection can be used in CPS to take advantage of the large amount of data being generated by IoT devices. However, the data can be noisy, corrupted or redundant, which can lead to misclassification and/or degradation in the performance of the detectors. A proper selection of data in terms of features and instances can improve the quality of the data and enhance the performance of such detectors. Moreover, it can allow for the implementation of lightweight but still accurate fault detectors, which are required in resource constrained edge-based IoT environments. This work studies the unified problem of instance and feature selection, for the purpose of two-dimensional reduction, in class-based fault detection datasets used in IoT-based CPS. To avoid the high complexity required by an optimal two-dimensional reduction approach, we examine order-based feature and instance dataset reduction and evaluate the new fault detectors which are trained based on the reduced datasets, in terms of accuracy gain/loss. A new weighted metric which combines accuracy and dataset reduction rates is introduced that enables the selection of an appropriate reduction scheme per application. Experimental results suggest that a proper selection of instance and feature selection algorithms can significantly reduce dataset size by up to 90 %.

关键词： Instance Selection Feature Selection Dataset Reduction Fault Detection Machine Learning Cyber Physical systems (CPS) internet of Things (IoT)

来源：评论

学校读者我要写书评

暂无评论

Democratizing access to collaborative music making over the network using air instruments 22

Democratizing access to collaborative music making over the ...

引用

17th International Audio Mostly conference (AM)

作者： Cocchiara, Davide Turchet, Luca Univ Trento Dept Informat Engn & Comp Sci Trento Italy

ISBN: (纸本)9781450397018

To date, scarce research has been conducted on the development of tools capable of fostering the democratization of the access to collaborative music making over the network. This paper describes a system based on interconnected air instruments conceived for introducing musically untrained people to collaborative music playing. The system consists of an application controlling synthesizers via real-time finger tracking on input from a consumer-grade camera, which is used in conjunction with a basic networking music performance system communicating control messages. Moving fingers in the air is one of the simplest movements that everybody can afford, thus it was selected as an optimal candidate to build a musical instrument accessible to everybody. A user study was conducted to assess the experience in interacting with the system, involving ten pairs of participants with no musical expertise. Overall, results showed that participants deemed that the system was effective in providing a high user experience, adequate to enable non-musicians to play together at a distance. Moreover, the system was judged as capable of promoting music playing for non-musicians thus fostering easiness of access to music making in a collaborative fashion. A critical reflection on the results is provided, along with a discussion of the study limitations and possible future works.

关键词： networked music performance systems digital musical instruments computer vision internet of Musical Things

来源：评论

学校读者我要写书评

暂无评论

Industrial internet of Things Intrusion Detection Model Integrating Graph Attention network and Gated Temporal Convolutional network

Industrial Internet of Things Intrusion Detection Model Inte...

引用

Advanced Algorithms and control Engineering (ICAACE), International conference on

作者： Chenghe Peng Ying Zhang College of Information Engineering Shanghai Maritime University Shanghai China

ISBN: (数字)9798350361445

ISBN: (纸本)9798350361452

In recent years, the application of the Industrial internet of Things (IIoT) in industry has become increasingly important. However, because IIoT devices and systems are connected to the internet, they may face the risk of malicious intrusions that can cause serious damage to production processes and data security. Intrusion detection systems (IDS) can be used to monitor IIoT for malicious activities and develop response strategies. Therefore, this article proposes an intrusion detection model called GTRGAT to ensure the network security of IIoT. In particular, the GTRGAT model uses GTCN to quickly pull out sequence features from IIoT traffic. GTCN combines convolutional operations and gating mechanisms, aiming to process time series data more efficiently and capture its intrinsic patterns. By using the TON_IoT dataset, the performance of the GTRGAT model is verified, showing that it can accurately detect intrusions. The experiment also showed that the GTRGAT model works better than other advanced methods, so it can be used as a workable way to find intrusions in industrial IoT networks.

关键词： Machine learning algorithms Time series analysis Intrusion detection Production Machine learning network security Logic gates

来源：评论

学校读者我要写书评

暂无评论

Dynamic Composite S-Boxes for High-Speed IoT Encryption with Enhanced Security

Dynamic Composite S-Boxes for High-Speed IoT Encryption with...

引用

International conference on Communication systems and network Technologies (CSNT)

作者： D Sony D. Krishna Reddy Electronics and Communication Engineering Chaitanya Bharathi Insitute of Technology Hyderabad India

ISBN: (数字)9798331531935

ISBN: (纸本)9798331531942

For resource-constrained systems and IoT applications, the proposed DS2B is an efficient encryption scheme. Further, the issues of the DS2B are that it has a very simple form and offers strong encryption. Therefore, to support strong nonlinearity, the results of some of the performance analyses of the DS2B presented have been able to support strong nonlinear analysis. For achieving throughput enhancement, dynamic composite S boxes and associated pipelining methods replace LUT-based S boxes. The flip-flop-based masking technique, applied for the highest level of transformation of the encryption key and for enhancing resistance against any scan-based attacks, is utilized in the S box module in this work. Without compromising the quality of the proposed core, this research presents alternatives that are faster as well as more secure. The performance of the proposed method is analyzed, and simulation results have clearly depicted its effectiveness.

关键词： Resistance Simulation Speech enhancement Throughput Hardware Encryption performance analysis internet of Things Hardware design languages S Box

来源：评论

学校读者我要写书评

暂无评论

Infrared and visible image fusion based on Laplacian pyramid and generative adversarial network

引用

KSII TRANSACTIONS ON internet AND INFORMATION systems 2021年第5期15卷 1761-1777页

作者： Wang, Juan Ke, Cong Wu, Minghu Liu, Min Zeng, Chunyan Hubei Univ Technol Hubei Key Lab High Efficiency Utilizat Solar Ener Wuhan 430068 Peoples R China Hubei Power Grid Intelligent Control & Equipment Wuhan 430068 Peoples R China

An image with infrared features and visible details is obtained by processing infrared and visible images. In this paper, a fusion method based on Laplacian pyramid and generative adversarial network is proposed to obtain high quality fusion images, termed as Laplacian-GAN. Firstly, the base and detail layers are obtained by decomposing the source images. Secondly, we utilize the Laplacian pyramid-based method to fuse these base layers to obtain more information of the base layer. Thirdly, the detail part is fused by a generative adversarial network. In addition, generative adversarial network avoids the manual design complicated fusion rules. Finally, the fused base layer and fused detail layer are reconstructed to obtain the fused image. Experimental results demonstrate that the proposed method can obtain state-of-the-art fusion performance in both visual quality and objective assessment. In terms of visual observation, the fusion image obtained by Laplacian-GAN algorithm in this paper is clearer in detail. At the same time, in the six metrics of MI, AG, EI, MS_SSIM, Q(abf) and SCD, the algorithm presented in this paper has improved by 0.62%, 7.10%, 14.53%, 12.18%, 34.33% and 12.23%, respectively, compared with the best of the other three algorithms.

关键词： Laplacian pyramid generative adversarial network base layer detail layer fusion

来源：评论

学校读者我要写书评

暂无评论

Proceedings of the 2023 International conference on Emerging Techniques in Computational Intelligence, ICETCI 2023

Proceedings of the 2023 International Conference on Emerging...

引用

3rd International conference on Emerging Techniques in Computational Intelligence, ICETCI 2023

ISBN: (纸本)9798350300604

The proceedings contain 52 papers. The topics discussed include: analysis of wireless sensor network security models: a salient approach for deeper inspection using deep neural networks;an improved hybrid model for target detection;gesture controlled virtual mouse and keyboard using OpenCV;NLP based topic modeling for healthcare: analyzing patient reviews to improve quality of care and access to services;performance optimization for transformer models on text classification tasks;a GIS-based framework applied to assess vulnerability and impact heatwave scenarios in urban systems;adaptive neural dynamic surface control for course tracking of ships with full state constraints;design of slotted triangular microstrip patch antenna with different feeding techniques;and support vector machines: spherical separability: limitations of learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Method of Speech Denoising by Long Short-Term Memory Neural network 11th

Two-Stage Method of Speech Denoising by Long Short-Term Memo...

引用

11th International conference on High-performance Computing systems and Technologies in Scientific Research, Automation of control and Production (HPCST)

作者： Nasretdinov, Rauf Ilyashenko, Ilya Lependin, Andrey AltSU Altai State Univ Lenin Ave 61 Barnaul 656049 Russia

ISBN: (纸本)9783030941413;9783030941406

This work is devoted to the development of a method for cleaning single-channel speech audio signals from additive noise. The main feature of the method is the application of a two-stage neural network. At the first stage, wideband processing of the input noisy signal is carried out, which allows the effective estimation of noise with a sophisticated spectral structure. The second stage of signal processing is a two-component neural network over the result of matrix representations that reveals the quasi-stationary characteristics of the clean and noise signal components in separate overlapping narrow frequency bands. The use of two components of noisy signals, which estimate complex masks of the clean and noise parts, makes it possible to improve useful information extraction about the formant structure of speech and effectively clean the input signal from noises of various nature. All of this together made it possible to develop a new method of speech enhancement, surpassing the best existing solutions in most quality metrics.

关键词： Signal processing Speech enhancement Noise masking Recurrent neural networks Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

OpenRAN Gym: An Open Toolbox for Data Collection and Experimentation with AI in O-RAN

OpenRAN Gym: An Open Toolbox for Data Collection and Experim...

引用

IEEE Wireless Communications and networking conference (IEEE WCNC)

作者： Bonati, Leonardo Polese, Michele D'Oro, Salvatore Basagni, Stefano Melodia, Tommaso Northeastern Univ Inst Wireless Internet Things Boston MA 02115 USA

ISBN: (纸本)9781665442664

Open Radio Access network (RAN) architectures will enable interoperability, openness, and programmatic data-driven control in next generation cellular networks. However, developing scalable and efficient data-driven algorithms that can generalize across diverse deployments and optimize RAN performance is a complex feat, largely unaddressed as of today. Specifically, the ability to design efficient data-driven algorithms for network control and inference requires at a minimum (i) access to large, rich, and heterogeneous datasets;(ii) testing at scale in controlled but realistic environments, and (iii) software pipelines to automate data collection and experimentation. To facilitate these tasks, in this paper we propose OpenRAN Gym, a practical, open, experimental toolbox that provides end-to-end design, data collection, and testing workflows for intelligent control in next generation Open RAN systems. OpenRAN Gym builds on software frameworks for the collection of large datasets and RAN control, and on a lightweight O-RAN environment for experimental wireless platforms. We first provide an overview of OpenRAN Gym and then describe how it can be used to collect data, to design and train artificial intelligence and machine learning-based O-RAN applications (xApps), and to test xApps on a softwarized RAN. Then, we provide an example of two xApps designed with OpenRAN Gym and used to control a large-scale network with 7 base stations and 42 users deployed on the Colosseum testbed. OpenRAN Gym and its software components are open source and publicly-available to the research community.

关键词： Wireless communication Base stations Data collection Software Inference algorithms Artificial intelligence Task analysis

来源：评论

学校读者我要写书评

暂无评论

Construction of Beidou Space Time Technology Application Micromajor and Practice of Characteristic New Engineering Education 14th

Construction of Beidou Space Time Technology Application Mic...

引用

14th China Satellite Navigation conference, CSNC 2024

作者： Xing, Jianping Yang, Xingmei Cao, Chong Meng, Lingguo Ning, Yafei Liu, Hairui Wang, Shengli School of Microelectronics Shandong University Jinan250101 China Global New Space Time Information Technology Research Institute Beijing100084 China Shandong Muke Space Information Technology Co. Ltd. Jinan250101 China School of Oceanography Shandong University of Science and Technology Qingdao266071 China

ISBN: (纸本)9789819969272

Beidou is widely used in various industries and fields of economic and social development. It is deeply integrated with big data, the internet of Things, artificial intelligence and other emerging technologies, promoting the birth of a new business form of "Beidou + micro specialty", and supporting the economic and social digital transformation and improving quality and efficiency. Beidou + micro specialty enables learners to have certain academic and professional qualities and industry employability in this field through flexible and systematic training. The micro specialty has built universal technologies, protocols, standards and systems such as integrated Beidou high-performance antenna, PPP precise single-point positioning, chip and terminal embedded development, integrated navigation, Beidou high-precision satellite-based enhancement [1], Beidou + SoC implementation, Beidou precise time service, Beidou + 5G, Beidou + AI, communication gateway cluster, UAV + digital twin processing, space-time security + data encryption, massive space-time data platform + APP processing, and pseudosatellite development frontier, As well as the system of typical cases of Beidou major demonstration projects (Beidou Kinetic Energy Project, Beidou Precision Transportation and Logistics (including high-speed field application), Beidou Precision Scene Monitoring, Beidou Smart Ship, Beidou Precision Agricultural Machinery and Agricultural internet of Things Project, Beidou Smart Environmental Protection, Beidou Precision Time Service network, Beidou + Quantum Security Integration, Beidou Police/Civil (such as school bus, tourism guide) Project, Beidou UAV + emergency rescue, etc.). The use of micro specialty mode to achieve more in-depth and efficient interdisciplinary integration can also better enhance the depth and width of talent training, and provide useful reference for the training of compound talents. © 2024, Aerospace Information Research Institute.

关键词： internet of things

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：