检索结果-内蒙古大学图书馆

3rd International Conference on Advancement in electrical and Electronic engineering, ICAEEE 2024

作者： Tasmim Bakchy, Sagor Chandro Peyal, Hasibul Islam Hoshen, Md. Rifat Siddique, Md. Abu Ismail Electrical & Computer Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh Electronics & Communication Engineering Hajee Mohammad Danesh Science & Technology University Dinajpur Bangladesh Electronics & Telecommunication Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh

ISBN: (纸本)9798350388282

Colon cancer is caused by cells that proliferate in the colon, a part of the large intestine. Early detection of cancer may make treatment easier and save many lives each year. The goal of this study is to identify improved approaches to diagnosing colon cancer rapidly and correctly. It intends to accomplish this through the use of a computer program known as a lightweight and efficient Convolutional Neural Network (CNN), which operates quickly and requires little computational power. The method may aid doctors in detecting colon cancer more successfully than earlier. The proposed model outperforms prior efforts with an amazing validation accuracy of 99.48\%. In our study, we employed 10,000 images from two separate classes to distinguish colon cancer cells from normal colon cells. The suggested model performs admirably, as indicated by its remarkable precision, recall, and F1-score, all of which are greater than 99\%, as well as its perfect Area Under Curve (AUC) score of 100\%. The parameters in the suggested model are lower than those in the current transfer learning models. We also compared our novel CNN model to the industry-recognized MobileNetv2 transfer learning standard to demonstrate our method's remarkable effectiveness. To illustrate the model's decision-making process, Gradient-weighted class activation mapping, or Grad Cam++, has been used. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Monocular Quasi-Dense 3D Object Tracking

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2023年第2期45卷 1992-2008页

作者： Hu, Hou-Ning Yang, Yung-Hsu Fischer, Tobias Darrell, Trevor Yu, Fisher Sun, Min National Tsing Hua University Department of Electrical Engineering Hsinchu300 Taiwan Eth Zurich Department of Information Technology and Electrical Engineering Zürich8092 Switzerland Uc Berkeley Department of Electrical Engineering and Computer Science BerkeleyCA94720-1770 United States

A reliable and accurate 3D tracking framework is essential for predicting future locations of surrounding objects and planning the observer's actions in numerous applications such as autonomous driving. We propose a framework that can effectively associate moving objects over time and estimate their full 3D bounding box information from a sequence of 2D images captured on a moving platform. The object association leverages quasi-dense similarity learning to identify objects in various poses and viewpoints with appearance cues only. After initial 2D association, we further utilize 3D bounding boxes depth-ordering heuristics for robust instance association and motion-based 3D trajectory prediction for re-identification of occluded vehicles. In the end, an LSTM-based object velocity learning module aggregates the long-term trajectory information for more accurate motion extrapolation. Experiments on our proposed simulation data and real-world benchmarks, including KITTI, nuScenes, and Waymo datasets, show that our tracking framework offers robust object association and tracking on urban-driving scenarios. On the Waymo Open benchmark, we establish the first camera-only baseline in the 3D tracking and 3D detection challenges. Our quasi-dense 3D tracking pipeline achieves impressive improvements on the nuScenes 3D tracking benchmark with near five times tracking accuracy of the best vision-only submission among all published methods. © 1979-2012 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Optical Flow Estimation in Dense Foggy Scenes with Domain-Adaptive Networks

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第6期4卷 1777-1788页

作者： Yan, Wending Sharma, Aashish Tan, Robby T. National University of Singapore Electrical and Computer Engineering Department Singapore Singapore Agency for Science Technology and Research Singapore Singapore

Estimating optical flow in dense foggy scenes is a challenging task. The basic assumptions for computing flow such as brightness and gradient constancy become invalid. To address the problem, we introduce a semisupervised deep learning method that can learn from real fog images without requiring the corresponding optical flow ground-truths. Our method is a multitask network, integrating the domain transformation and optical flow networks in one framework. The domain transformation is performed between foggy and clean domains. Under our semisupervised training strategy, we train our method in a supervised manner with a pair of synthetic fog images, their corresponding clean images and optical flow ground-truths. Subsequently, given a pair of real fog images and a pair of clean images that are not corresponding to each other (unpaired), in the next training batch, we train our network in an unsupervised manner. The supervised and unsupervised training processes are alternated iteratively. Since our method relies on unsupervised learning for real data, we show that it can be used for test-time training. We show in our experiments that performing test-time training improves the results further on our test data. Extensive experiments show that our method outperforms the state-of-the-art methods in estimating optical flow in dense foggy scenes. © 2020 IEEE.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Efficient IRS-Aided Rate Optimizations for Dual Functional Radar and Communications

引用

IEEE Communications Letters 2024年第1期28卷 39-42页

作者： Sweta, S. Dubey, Ankit Nguyen, Van-Linh Indian Institute of Technology Jammu Department of Electrical Engineering Jammu and Kashmir Jammu181221 India National Chung Cheng University Department of Computer Science and Information Engineering Chiayi62102 Taiwan

This letter presents a novel method to enable beam steering optimization for secure communications and resilience against radio tracking in an intelligent reflecting surfaces-enabled multiple-input multiple-output dual-functional radar and communications system. The approach involves optimizing beam steering by solving two convex sub-problems: i) maximizing secrecy rate and ii) maximizing legitimate receiver rate, solved using Taylor series approximation. Evaluation results demonstrate that optimizing radar and beam steering enhances secure communications while maintaining quality of service. Furthermore, the utilization of IRS effectively prevents passive eavesdropping in both line-of-sight (LOS) and non-LOS scenarios. © 1997-2012 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Smart Monitoring of High-Performance KY Converter in IoT-Enabled Electric Vehicle Systems 14

Smart Monitoring of High-Performance KY Converter in IoT-Ena...

引用

14th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2025

作者： Rathika, N. Ramya, R.R. Ganga, P. Patwa, Sharda Balaji, V. Sivarajan, S. Department of Electrical and Electronics Engineering 6116-Mahendra Institute of Technology Mallasamuthiram Namakkal India Department of Information Technology University College Of Engineering Nagercoil India Department of Electrical and Electronics Engineering Annapoorana Engineering College Tamilnadu India Department of Electrical Engineering Medi-caps University Madhyapradesh Indore India Department of Electrical and Computer Engineering MAI-NEFHI College of Engineering and Technology Eritrea Department of Electrical and Electronics Engineering Vel Tech Multi Tech Dr Rangarajan Dr Sakunthala Engineering College Tamil Nadu Chennai India

ISBN: (纸本)9798331531935

The smart Electric Vehicle (EV)-Improved KY Converter monitoring system, which is Internet of Things (IoT)based, provides an advanced method for improving the dependability and efficiency of EV power systems. By utilizing IoT technology, this system keeps a close eye on the enhanced KY converter's efficiency, which is essential for controlling power conversion in electric vehicles. The Adaptive Neuro-Fuzzy Inference System (ANFIS) based Maximum Power Point Tracking (MPPT) effectively operates the system at maximum power level with fast response and low oscillations. It effectively optimizes energy conversion from Photo Voltaic (PV) by dynamically modifying to the operating point under varying environmental conditions. The deployment of this intelligent monitoring system is expected to yield notable progress in the administration and functioning of electric vehicle power systems, hence augmenting the general sustainability of electric-powered transportation. The proposed system is implemented in MATLAB, employing its sophisticated simulation capabilities to analyse the PV system. This simulation framework enables for the testing and validation of key performance metrics of 98% efficiency exhibiting in boosting power extraction and grid stability. © 2025 IEEE.

关键词： Fuzzy neural networks

来源：评论

学校读者我要写书评

暂无评论

Lithium Battery SOH Estimation: A Novel Octave and LSTM Hybrid Neural Network Approach 12

Lithium Battery SOH Estimation: A Novel Octave and LSTM Hybr...

引用

12th Iranian Conference on Renewable Energies and Distributed Generation, ICREDG 2025

作者： Mousavi, Seyed Mohammadreza Zarif, Amirhossein Rahimian Hamidzadeh, Javad Sadjad University Faculty of Computer Engineering and Information Technology Mashhad Iran Sadjad University Faculty of Electrical and Biomedical Engineering Mashhad Iran

ISBN: (纸本)9798331525132

The lithium battery (LIB) has emerged as a prominent area of research in energy and industrial applications, due to its superior energy density and efficient energy delivery capabilities. This study addresses the critical requirement for accurate State of Health (SOH) estimation as a significant challenge. The primary objective of this study is to utilize key battery health characteristic parameters to improve the accuracy and computational speed of SOH. Significant gaps have been identified in recent methodologies, particularly in terms of SOH estimation accuracy, computational speed, and simulation parameters. To address these limitations, a novel hybrid neural network (NN) approach is proposed, integrating octave convolution (OCT) and long short-term memory (LSTM). To demonstrate the effectiveness of the proposed method in the optimization process, a comparative analysis is conducted against Convolutional Neural Networks (CNN), OCT, LSTM, and CNN-LSTM architectures. The results indicate a significant reduction in the mean squared error (MSE), decreasing from 80.21 percent in CNN to 0.0758 percent in the proposed OCT-LSTM model. Furthermore, the root mean square error (RMSE) exhibits a substantial reduction of 64.91 percent and 58.14 percent compared to the LSTM and CNN-LSTM models, respectively. The simulation parameters used in this study were reduced from 41,228 for the CNN-LSTM model to 38,668 for the OCT-LSTM model. Empirical results show that the proposed method outperforms state-of-the-art methods in the number of parameters, MSE, RMSE, and estimation accuracy. These findings highlight the method's enhanced efficiency, computational speed, and precision, emphasizing its potential as a significant advancement in this domain. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Dual-Channel MEMS Actuated Tunable Optical Filter Based on Polarization Insensitive Compound Ring Resonator for DWDM Networks 11th

Dual-Channel MEMS Actuated Tunable Optical Filter Based on P...

引用

11th EAI International Conference on Advancement of Science and technology, ICAST 2023

作者： Ayalew, Hailu Dessalegn Talabattula, Srinivas Annamalai, Pushparaghavan Electrical and Computer Engineering Faculty Bahir Dar University-Institute of Technology Bahir Dar Ethiopia Department of Electrical Communication Engineering Indian Institute of Science Bangalore India

ISBN: (纸本)9783031641503

One of the key components of wavelength division multiplexing (WDM) networks is tunable optical filters (TOFs). This paper focused on the theoretical analysis and design of a new dual-channel micro-electromechanical system (MEMS) actuated tunable optical filter based on polarization insensitive compound ring resonators (PICRRs) for dense wavelength division multiplexing (DWDM) optical networking applications. It is basically structured on an optimally designed capacitive type microcantilever beam, which is fixed at both ends, with built-in PICRRs, which are placed at both fixed ends of the beam to gain linearly varying longitudinal strain and stress on the resonators. Also, the dimensions of the rings are properly chosen to achieve a full width at half maximum (FWHM) of 0.4078 nm with a flat pass band at 1 dB of 0.3626 nm and a good shape factor for both channels. It also shows a free spectral range of about 20.05 nm for the first channel and 20.046 nm for the second channel, with a high extinction ratio that allows filtering of adjacent channels of 50 GHz DWDM systems. Thus, when the electrostatic attraction force (EAF) is applied, the beam will bend, which induces strain and stress in the rings, which brings a change in effective refractive index of the rings and also affects the perimeter and coupling coefficients of the rings that leads to a change in the output spectrum shift, providing the tunability as high as 4.779 nm/μN, and it is capable of tuning up to 355 GHz with negligible variations of FWHM and channel spacing within the tunability range of the two channels. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Dense wavelength division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Joint Dual Learning With Mutual Information Maximization for Natural Language Understanding and Generation in Dialogues

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2024年 32卷 2445-2452页

作者： Su, Shang-Yu Chung, Yung-Sung Chen, Yun-Nung Rakuten Institute of Technology Rakuten Tokyo158-0094 Japan Massachusetts Institute of Technology Electrical Engineering and Computer Science CambridgeMA02139 United States National Taiwan University Department of Computer Science and Information Engineering Taipei106319 Taiwan

Modular conversational systems heavily rely on the performance of their natural language understanding (NLU) and natural language generation (NLG) components. NLU focuses on extracting core semantic concepts from input texts, while NLG constructs coherent sentences based on these extracted semantics. Inspired by information theory in digital communication, we introduce a one-way communication model that mirrors human conversations, comprising two distinct phases: (1) the conversion of thoughts into messages, similar to NLG, and (2) the comprehension of received messages, similar to NLU. This paper presents a novel algorithm that trains NLU and NLG collaboratively by concatenating their models and maximizing mutual information between inputs and outputs. This approach efficiently facilitates the transmission of semantics, leading to enhanced learning performance for both components. Our experimental results, based on three benchmark datasets, consistently demonstrate significant improvements for both NLU and NLG tasks, highlighting the practical promise of our proposed method. © 2014 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A New ZVS Interleaved Flyback Converter 12

A New ZVS Interleaved Flyback Converter

引用

12th Iranian Conference on Renewable Energies and Distributed Generation, ICREDG 2025

作者： Mojaveri, Shokouh Shabani Delshad, Majid Heydarian-Forushani, Ehsan Branch Islamic Azad University Faculty of Engineering Isfahan Iran Qom University of Technology Department of Electrical and Computer Engineering Qom Iran

ISBN: (纸本)9798331525132

This paper presents a new auxiliary circuit for interleaved flyback converters to create soft switching conditions in the element in addition the semiconductor in the converter structure prevents the voltage spike across the switches. Also, due to the use of the ripple cancellation technique, the input current has decreased. The proposed interleaved flyback converter has been completely analyzed, a 100W laboratory sample has been developed to confirm its performance, and practical results have been provided to verify the proper performance of the circuit. © 2025 IEEE.

关键词： Flyback converter Interleaved Ripple cancellation Zero voltage switching

来源：评论

学校读者我要写书评

暂无评论

Attention U-Net: A Deep Learning Approach for Breast Cancer Segmentation

Attention U-Net: A Deep Learning Approach for Breast Cancer ...

引用

2023 IEEE International Conference on Quantum Technologies, Communications, Computing, Hardware and Embedded Systems Security, iQ-CCHESS 2023

作者： Mridha, Krishna Sarker, Tasnim Bappon, Suborno Deb Sabuj, Shahriar Mahmud Computer Engineering Marwadi University Gujarat Rajkot India Electrical and Electronics Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh Chittagong University of Engineering & Technology Computer Science & Engineering Bangladesh

ISBN: (纸本)9798350314946

One of the main causes of death for women globally is breast cancer. Early discovery can reduce the frequency of early deaths. Breast ultrasound images can help in diagnosis and treatment planning by helping to categories different types of breast cancer. To segment breast cancer pictures in this study, we employed an Attention U-Net. A deep learning model for picture segmentation is called the Attention U-Net. We used a dataset of 780 breast ultrasound pictures divided into three classes-normal, benign, and malignant-to train the Attention U-Net. The mean IoU, precision, recall, and F1 scores for the Attention U-Net were 0.840,0.815,0.848, and 0.831 respectively. These outcomes are comparable to those of other cutting-edge techniques for segmenting breast cancer. The findings of this study indicate that the Attention U-Net is a potential technique for segmenting breast cancer. The great accuracy that the Attention U-Net can attain can assist to increase the precision of diagnosis and treatment planning © 2023 IEEE.

关键词： Deep learning

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：