检索结果-内蒙古大学图书馆

Annual IEEE Conference on Applied Power Electronics Conference and Exposition (APEC)

作者： Ayodhya Somiruwan Gamwari Ayooluwa Ajiboye Rakesh Resalayyan Alireza Khaligh Department of Electrical and Computer Engineering The Institute for Systems Research University of Maryland College Park USA

A novel frequency-domain approach to quantify the effect of the gate-drain parasitic capacitance of a SiC MOSFET is presented in this paper. The effect of this parasitic capacitance during the soft turn-off and hard turn-on transition of a MOSFET half bridge can cause an undesired spurious turn-on in the soft turned-off switch. The proposed model based on Miller’s theorem accurately quantifies the effect and the behavior of the gate loop irrespective of the usage of spurious turn-on mitigating active Miller clamp. The insights drawn in this paper can be used in designing the gate loop of the power MOSFET to avoid undesired spurious turn-on of the MOSFET due to crosstalk. Moreover, the analytical model is validated with hardware experimental results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Deep Transfer Learning Based Object Detection and Tracking Approach

引用

Intelligent Automation & Soft Computing 2023年第3期35卷 3613-3626页

作者： C.Narmadha T.Kavitha R.Poonguzhali V.Hamsadhwani Ranjan walia Monia B.Jegajothi Electronics and Communication Engineering Periyar Maniammai Institute of Science&Technology(PMIST)Thanjavur613403India Department of Computer Science and Engineering Periyar Maniammai Institute of Science&TechnologyThanjavur613403India Department of Electrical and Electronics Engineering Periyar Maniammai Institute of Science and TechnologyThanjavur613403India Electrical Engineering Department Model Institute of Engineering&Technology(Autonomous)Jammu181122India Department of Computer Science and Engineering Shri Mata Vaishno Devi UniversityKatra182320India Center for Energy Research Chennai Institute of TechnologyChennai600069India

At present days,object detection and tracking concepts have gained more importance among researchers and business ***,deep learning(DL)approaches have been used for object tracking as it increases the perfor-mance and speed of the tracking *** paper presents a novel robust DL based object detection and tracking algorithm using Automated Image Anno-tation with ResNet based Faster regional convolutional neural network(R-CNN)named(AIA-FRCNN)*** AIA-RFRCNN method performs image anno-tation using a Discriminative Correlation Filter(DCF)with Channel and Spatial Reliability tracker(CSR)called DCF-CSRT *** AIA-RFRCNN model makes use of Faster RCNN as an object detector and tracker,which involves region proposal network(RPN)and Fast *** RPN is a full convolution network that concurrently predicts the bounding box and score of different *** RPN is a trained model used for the generation of the high-quality region proposals,which are utilized by Fast R-CNN for detection ***,Residual Network(ResNet 101)model is used as a shared convolutional neural network(CNN)for the generation of feature *** performance of the ResNet 101 model is further improved by the use of Adam optimizer,which tunes the hyperparameters namely learning rate,batch size,momentum,and weight ***,softmax layer is applied to classify the *** performance of the AIA-RFRCNN method has been assessed using a benchmark dataset and a detailed comparative analysis of the results takes *** outcome of the experiments indicated the superior characteristics of the AIA-RFRCNN model under diverse aspects.

关键词： Object detection tracking deep learning deep transfer learning image annotation

来源：评论

学校读者我要写书评

暂无评论

Key-Independent Image Encryption using DNA Encoding and Chaotic Dynamics 10

Key-Independent Image Encryption using DNA Encoding and Chao...

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Maharaja Vannia Moorthi, V. Krishna, Megha R. Kumar, Gopika Anil Thanikaiselvan, V. Subashanthini, S. Amirtharajan, Rengarajan Vellore Institute of Technology School of Electronics Engineering Vellore India Vellore Institute of Technology School of Computer Science Engineering and Information Systems Vellore India Sastra Deemed University School of Electrical & Electronics Engineering Thanjavur613 401 India

ISBN: (纸本)9798350353068

Privacy violations are common in our technology-driven world, where almost everyone interacts with internet-connected electronic devices. To address this, cryptography has emerged, concealing data during transmission to deter hackers. Cryptography involves basic mathematical operations, exchanging data based on a shared key known only to the sender and receiver. However, this method suffers from key dependency at the receiver's end, requiring constant key knowledge. To overcome this issue, a novel image encryption method has been introduced in this paper that is independent of the key on the receiver side. This method leverages techniques such as DNA Encoding, Chaotic Dynamics, and Key Hiding Mechanisms to increase the security of the sent image. The proposed method has been tested experimentally, and the results demonstrate its effectiveness with entropy values exceeding 7.995 and correlation coefficient values below 1% for the vertical, horizontal, and diagonal directions. Overall, the proposed image encryption scheme offers a promising solution for protecting sensitive image data in various applications, combining advanced encryption techniques with key management enhancements to ensure confidentiality and integrity. © 2024 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Droop Control for Microgrids with Variable Inverter Outputs: A Virtual Impedance-Based Adaptive Strategy

Droop Control for Microgrids with Variable Inverter Outputs:...

引用

2024 IEEE International Conference on Unmanned systems, ICUS 2024

作者： Zhang, Hualin Wang, Shuwang Zhang, Baicheng Kong, Guanqiao School of Electrical and Control Engineering Liaoning Technical University Huludao China School of Cyber Science and Engineering Southeast University Nanjing China CSSC Systems Engineering Research Institute Beijing China

ISBN: (纸本)9798350384185

With the widespread application of renewable energy sources (RES) in islanded microgrids, the system instability caused by the intermittency of RES generation has also increased. To maintain stability during RES fluctuations, a n ovel adaptive droop control strategy utilizing adaptive virtual impedance is proposed in this study. This strategy allows the droop coefficients and virtual impedance to adaptively change based on the actual capacity of the inverters, thereby automatically adjusting the inverter output voltage and ensuring proper power sharing even as inverter capacity changes. Moreover, this strategy ensures appropriate power sharing under different load conditions and microgrid configurations. F inally, t he p roposed s trategy i s validated through MATLAB/Simulink simulations, showcasing its advantages over traditional droop control. © 2024 IEEE.

关键词： Microgrids

来源：评论

学校读者我要写书评

暂无评论

Multi-channel CNN to classify Nepali COVID-19 related tweets using hybrid features

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第3期15卷 2047-2056页

作者： Sitaula, Chiranjibi Shahi, Tej Bahadur Department of Electrical and Computer Systems Engineering Monash University Wellington Rd ClaytonVIC3800 Australia Earth Observation and AI Research Group Department of Infrastructure Engineering The University of Melbourne ParkvilleVIC3010 Australia School of Engineering and Technology Central Queensland University Rockhampton Australia Central Department of Computer Science and Information Technology Tribhuvan University TU Rd Kathmandu Kirtipur44618 Nepal

Because of the current COVID-19 pandemic’s increasing fears among people, it has triggered several health complications such as depression and anxiety. Such complications have not only affected developed countries but also developing countries such as Nepal. These complications can be understood from peoples’ tweets and comments posted online after their felicitous analysis and sentiment classification. Nevertheless, owing to the limited number of tokens and words in each tweet, it is crucial to capture multiple pieces of information associated with them for better understanding. In this study, we, first, represent each tweet by combining both syntactic and semantic information, called hybrid features. The syntactic information is generated from the bag-of-words method, whereas the semantic information is generated from the combination of the fastText-based (ft) and domain-specific (ds) methods. Second, we design a novel multi-channel CNN (MCNN) model, which ensembles the multiple CNNs, to capture multi-scale information for better classification. Last, we evaluate the efficacy of both the proposed feature extraction method and the MCNN model classifying tweets into three sentiment classes (positive, neutral, and negative) on the NepCOV19Tweets dataset, which is the only public COVID-19 tweets dataset in the Nepali language. The evaluation results show that the proposed hybrid features outperform individual feature extraction methods with the highest classification accuracy of 69.7% and the MCNN model outperforms the existing methods with the highest classification accuracy of 71.3% during classification. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

A Tensor Low-Rank Approximation for Value Functions in Multi-Task Reinforcement Learning 58

A Tensor Low-Rank Approximation for Value Functions in Multi...

引用

58th Asilomar Conference on Signals, systems and computers, ACSSC 2024

作者： Rozada, Sergio Paternain, Santiago Bazerque, Juan Andrés Marques, Antonio G. King Juan Carlos University Dept. of Signal Theory and Communications Madrid Spain Rensselaer Polytechnic Institute Dept. of Electrical Computer and Systems Engineering TroyNY United States University of Pittsburgh Dept. of Electrical and Computer Engineering PittsburghPA United States

ISBN: (纸本)9798350354058

In pursuit of reinforcement learning systems that could train in physical environments, we investigate multi-task approaches as a means to alleviate the need for massive data acquisition. In a tabular scenario where the Q-functions are collected across tasks, we model our learning problem as optimizing a higher order tensor structure. Recognizing that close-related tasks may require similar actions, our proposed method imposes a low-rank condition on this aggregated Q-tensor. The rationale behind this approach to multi-task learning is that the low-rank structure enforces the notion of similarity, without the need to explicitly prescribe which tasks are similar, but inferring this information from a reduced amount of data simultaneously with the stochastic optimization of the Q-tensor. The efficiency of our low-rank tensor approach to multi-task learning is demonstrated in two numerical experiments, first in a benchmark environment formed by a collection of inverted pendulums, and then into a practical scenario involving multiple wireless communication devices. © 2024 IEEE.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

A Sparsity-driven tinyML Accelerator for Decoding Hand Kinematics in Brain-computer Interfaces

A Sparsity-driven tinyML Accelerator for Decoding Hand Kinem...

引用

2023 IEEE Biomedical Circuits and systems Conference, BioCAS 2023

作者： Krishna, Adithya Ramanathan, Vignesh Yadav, Satyapreet Singh Shah, Sahil Van Schaik, Andre Mehendale, Mahesh Thakur, Chetan Singh Indian Institute of Science Department of Electronic Systems Engineering Bangalore India The Marcs Institute Western Sydney University International Centre for Neuromorphic Systems Australia University of Maryland Department of Electrical and Computer Engineering United States

ISBN: (纸本)9798350300260

Despite advances in understanding the mechanisms of movement disorders, controlling voluntary movements remains challenging, with limited treatment options. However, the integration of machine learning (ML) accelerators into the braincomputer interface (BCI) pipeline offers promising solutions by harnessing the capabilities of ML algorithms to decode intended motor actions accurately. While there have been numerous efforts to classify intended hand movements into discrete classes, the challenging problem of decoding continuous hand kinematics has seen limited research efforts. Our work focuses on tackling this challenge using RAMAN, an energy-efficient tinyML accelerator. We demonstrate the successful decoding of macaque hand kinematics from the MC_Maze dataset on the Efinix Ti60 FPGA with RAMAN architecture. Our approach achieves an R2-score of 0.91 across 108 different maze configurations with a significantly low memory footprint of 230 KB, a latency of 86.7 ms while consuming 52.23 mW of power at a 5 MHz clock rate and 5.78 ms latency with the peak power efficiency of 102.34 GOp/s/W at 75 MHz and 75% pruning. © 2023 IEEE.

关键词： BCI Energy-efficient FPGA Hand kinematics RAMAN Regression Sparsity tinyML accelerator

来源：评论

学校读者我要写书评

暂无评论

A Novel Trajectory Planning Method Based on Trust Region Policy Optimization

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-15页

作者： Ye, Bao-Lin Zhang, Jiajie Li, Lingxi Wu, Weimin Jiaxing Key Laboratory of Smart Transportations the School of Information Science and Engineering Jiaxing University China Elmore Family School of Electrical and Computer Engineering Purdue University Indianapolis USA State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China

Trajectory planning method is a research hotspot in autonomous driving. Existing reinforcement learning-based trajectory planning methods suffer from unstable performance due to the strong randomness of network weight parameter updates during the training process. Therefore, this paper proposes a novel trajectory planning method based on deep reinforcement learning trust region policy optimization (TRPO). Firstly, in order to enhance the robustness of the trajectory planning method based on deep reinforcement learning TRPO, a TRPO-LSTM based decision model was proposed. More specifically, a long short term memory (LSTM) based state feature extraction network was designed and embeded into a TRPO-based decision model to enhance the ability of TRPO to extract information from the environmental state space. Secondly, in order to make the planned trajectory adaptive to the dynamic changes of traffic environment, we presented a novel TRPO-LSTM trajectory fitting algorithm. To the best of our knowledge, this is the first work aiming at applying the TRPO-LSTM based decision model in the trajectory fitting process to search the optimal longitudinal trajectory speed. Finally, the proposed trajectory planning method was implemented and simulated on the CARLA simulator. The experimental results show that, compared with existing trajectory planning methods based on deep reinforcement learning algorithms, our proposed method achieves a cumulative reward improvement of over 28.9% in the scenario of four lane highway, and has better robustness. Meanwhile, the proposed method can achieve a lower collision rate of 0.93% while improving the average speed and comfort of vehicle driving. IEEE

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Synergistic frameworks for sensor fault isolation and accommodation in grid-side converters

引用

Journal of Automation and Intelligence 2024年第4期3卷 202-218页

作者： Faizan Mehmood Lenos Hadjidemetriou Panayiotis M.Papadopoulos Marios M.Polycarpou KIOS Research and Innovation Center of Excellence and the Department of Electrical and Computer EngineeringUniversity of CyprusNicosia2109Cyprus Energy EnvironmentWater Research CenterThe Cyprus InstituteAglantziaNicosia2121Cyprus

The stable and reliable operation of grid-integrated renewable energy systems requires advanced control and coordination of grid-side converters(GSCs),utilizing the feedback measurements of voltage and current sensors from both the direct current(DC)and alternating current(AC)sides of the ***,the effective operation of the converter is susceptible to sensor failures or divergence from their proper *** sensor fault detection algorithms are usually effective under abrupt faults,the fault propagation effect caused by the physical interconnection between the DC and AC sides of the converter may limit the performance of the sensor fault isolation process in revealing the exact location of a potential faulty ***,this work proposes a robust,model-based fault isolation and accommodation ***,a synergistic sensor fault isolation framework based on adaptive estimation schemes is proposed for both single and multiple faults in the DC voltage and AC current sensors,considering modeling uncertainty and measurement *** performance analysis in terms of stability,learning capability,and fault isolability is rigorously *** accommodation scheme based on a virtual sensor utilizing dynamic sensor fault estimation with realtime learning capabilities is applied to a ***,the performance of the proposed fault isolation and accommodation scheme is evaluated through simulation analysis under several scenarios involving single and multiple sensor faults.

关键词： Fault accommodation Fault detection Fault isolation Grid-side converter Nonlinear system Sensor faults

来源：评论

学校读者我要写书评

暂无评论

Investigation on three-inverter fed two OEWIM drives

Investigation on three-inverter fed two OEWIM drives

引用

2023 IEEE PES Innovative Smart Grid Technologies Europe, ISGT EUROPE 2023

作者： Pradabane, Srinivasan Yammani, Chandrasekhar D’Arco, Salvatore Ljøkelsøy, Kjell Department of Electrical Engineering National Institute of Technology Warangal India Energy Systems SINTEF Energy Research Trondheim Norway

ISBN: (纸本)9798350396782

The AC drive configuration presented in this article consists of two open-end winding induction motors (OWEIM) fed by three two-level inverters for EVs. One end of both the OEWIMs are connected to the output terminals of an inverter whereas the other three-phase terminals of both the OEWIMs are connected to two other inverter outputs. This proposed configuration is capable of parallel operation where they are connected to a common shaft. This topology has several advantages such as redundant switching states, half-rated DC link capacitors and power semiconductor devices. Further this results in reduction in size of the overall size of the entire configuration. The common inverter is rated for Vdc whereas the other two inverters are rated for Vdc/2, resulting in only three inverters for the entire drive system, while the conventional OEWIM require four inverters for the same operation. A fuzzy logic based (field-oriented control) FOC is used for the implementation of the proposed drive system. First the simulation studies were carried out using MATLAB/Simulink and the same has been verified using OP5600 (Hardware-in-Loop) HIL system. © 2023 IEEE.

关键词： ac drive drive EV fuzzy oewim opal-rt

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：