检索结果-内蒙古大学图书馆

Electronics, Communications, and Computations (JAC-ECC), International Japan-Africa Conference on

作者： Nada Mossad Youssef Mohamed A Fares Ahmed B. Zaky Egypt-Japan University of Science and Technology (E-JUST) Alexandria Egypt The Department of Electrical Engineering The Computer Systems Engineering Program Faculty of Engineering at Shoubra Benha University

Sentiment analysis and emotion classification are two crucial components of natural language processing (NLP), which have been widely explored in recent years due to their broad applications. Sentiment analysis aims to identify the polarity of written texts, ranging from positive to negative. Meanwhile, emotion classification is focused on recognizing and categorizing the emotional states expressed in the text. To achieve a deeper understanding of sentiments and emotions, it's essential to utilize models like BERT transformers that can effectively interpret the context. The process begins with data preprocessing, including tokenization and noise removal, followed by fine-tuning techniques to adapt the BERT model to the proposed tasks. We employed the BERT model on four datasets obtained from various sources, including Twitter, news websites, and restaurant reviews, where each dataset represents a distinct Arabic dialect. Our proposed model outperforms commonly used techniques like LSTM and CNN, yielding superior results. Despite the progress made, there are still challenges to overcome, such as dealing with Arabic diacritics, the new Arabic Arabizi, which uses Latin characters, and handling Arabic idioms. Further research is required to address these challenges adequately.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Fingerprint Based Indoor Visible Light Positioning System for Tilted Receivers Equipped with a Single Photo Detector

A Fingerprint Based Indoor Visible Light Positioning System ...

引用

IEEE Conference on Wireless Communications and Networking

作者： Ibrahim M. Abou-Shehada Ali H. Muqaibel Wessam Mesbah Ki-Hong Park Mohamed-Slim Alouini Electrical Engineering Department King Fahd University of Petroleum and Minerals Dhahran Saudi Arabia Electrical Engineering Department Center for Communication Systems and Sensing King Fahd University of Petroleum and Minerals Dhahran Saudi Arabia Electrical and Computer Engineering Program King Abdullah University of Science and Technology Thuwal Saudi Arabia

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

Indoor positioning systems (IPS) are gaining higher attention recently due to the increased demand for indoor location aware services. Visible light communication (VLC) is a promising technology to use for IPS. In particular, received signal strength (RSS) based visible light positioning (VLP) systems are gaining high attention due to their low complexity and cost, in addition to higher positioning accuracy compared to their radio frequency (RF) counterparts. One of the main challenges in RSS based VLP systems is encountered when the receiver (the target) is tilted and not placed in parallel with the transmitters (the anchors). RSS based trilateration techniques require a computationally expensive and time-consuming process to solve the nonlinear problem of tilted receivers. Fingerprint based systems generally provide high positioning accuracy with short positioning time, and maybe used to circumvent the need to deal with the high complexity associated with tilted receivers. However, the design of a fingerprinting VLP system for tilted receiver has not been explored yet as far as receivers with a single photodetector (PD) are concerned. In this work, a fingerprint based VLP system for tilted receivers using artificial neural networks (ANN) is proposed, where different types of input features for training the positioning algorithm are studied. We show that using the components of the normal vector to the PD's surface in addition to RSS values provides an excellent positioning accuracy with an average positioning error of 25.41 cm and a remarkably low average positioning time less than $\mathbf{5} \boldsymbol{\mu} \boldsymbol{s}$ . In addition, important research directions for future work are discussed.

关键词： Training Accuracy Receivers Artificial neural networks Fingerprint recognition Vectors Real-time systems

来源：评论

学校读者我要写书评

暂无评论

RN-SDEs: Limited-Angle CT Reconstruction with Residual Null-Space Diffusion Stochastic Differential Equations

arXiv

引用

arXiv 2024年

作者： Guo, Jiaqi Lopez-Tapia, Santiago Li, Wing Shun Wu, Yunnan Carignano, Marcelo Backman, Vadim Dravid, Vinayak P. Katsaggelos, Aggelos K. The Department of Electrical and Computer Engineering Northwestern University IL60201 United States The Applied Physics Program Northwestern University EvanstonIL60201 United States

Computed tomography is a widely used imaging modality with applications ranging from medical imaging to material analysis. One major challenge arises from the lack of scanning information at certain angles, leading to distorted CT images with artifacts. This results in an ill-posed problem known as the Limited Angle Computed Tomography (LACT) reconstruction problem. To address this problem, we propose Residual Null-Space Diffusion Stochastic Differential Equations (RN-SDEs), which are a variant of diffusion models that characterize the diffusion process with mean-reverting (MR) stochastic differential equations. To demonstrate the generalizability of RN-SDEs, our experiments are conducted on two different LACT datasets, i.e., ChromSTEM and C4KC-KiTS. Through extensive experiments, we show that by leveraging learned Mean-Reverting SDEs as a prior and emphasizing data consistency using Range-Null Space Decomposition (RNSD) based rectification, RN-SDEs can restore high-quality images from severe degradation and achieve state-of-the-art performance in most LACT tasks. Additionally, we present a quantitative comparison of computational complexity and runtime efficiency, highlighting the superior effectiveness of our proposed approach. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

ConvNeXt Model for Breast Cancer Image Classification

ConvNeXt Model for Breast Cancer Image Classification

引用

International Conference on Cybernetics and Intelligent System (ICORIS)

作者： Devin Setiawan Andrea Stevens Karnyoto Indo Intan Bens Pardamean Department of Electrical Engineering and Computer Science University of Kansas Lawrence United States Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Department of Informatics Engineering Universitas Dipa Makassar Makassar Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331539603

ISBN: (纸本)9798331539610

Breast cancer is an occurrence of cancer that attacks breast tissue and is the most common cancer among women worldwide, affecting one in eight women. In this modern world, breast cancer image classification simplifies the process of analyzing, providing objective and accurate results. By leveraging machine learning algorithms and computer vision techniques, we developed breast cancer detection. The dataset is histopathology dataset from BreakHis and UNHAS Hospital. We chose the ConvNeXt-Tiny model then modified the classifier head as the proposed method. Before the dataset is processed by the model, we augment the images by applying random horizontal and vertical flips, adjustments to brightness, contrast, saturation, and hue using color jitter. The augmentation process simulates real-world variance and enhances the model's ability to generalize to unseen data. Our proposed model gained better performance (accuracy, F1-Score) results compared two other techniques to VGG16 and SVM. According to our experiments, the F1-Score for the ConvNeXt-Tiny model with classifier head modification is higher at 0.9516, than the gain for VGG16 at 0.9292, and the gain for the SVM at 0.83.

关键词： Support vector machines Accuracy Head Computational modeling Transfer learning Breast cancer Magnetic heads Data models Reliability Image classification

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Real-Time Multi-Person Pose Detection in electrical Industrial Safety Scenarios Using YOLOv8-Pose and OpenPose 4

Comparative Analysis of Real-Time Multi-Person Pose Detectio...

引用

4th IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2024

作者： Tsai, Shang-Te Wu, Zong-Rong Lin, Pin-Hsuan Chen, Chin-Hsiung Chien, Wei Chang, Yu-Cheng School of Art and Design Sanming University Fujian365004 China National Yunlin University of Science and Technology Department of Technical and Vocational Program in Artificial Intelligence Yunlin Taiwan National Central University Department of Business Administration Taoyuan Taiwan Commercial Industrial Vocational Senior High School Department of Electrical Engineering New Taipei Municipal Tamsui New Taipei Taiwan Lunghwa University of Science and Technology Department of Computer Information and Network Engineering Taoyuan Taiwan National Taipei University of Technology Department of Computer Science and Information Engineering Taipei Taiwan

ISBN: (纸本)9798350360721

We reviewed the application of modern technology for rapid and accurate multi-person real-time pose detection in the hazardous field of electrical engineering. We focused on two leading pose detection technologies: YOLOv8 and OpenPose. To optimize performance, we integrated these two techniques into the LSTM model for training and investigated frame rates and accuracy. © 2024 IEEE.

关键词： Accident prevention

来源：评论

学校读者我要写书评

暂无评论

Dynamic Mesh Recovery from Partial Point Cloud Sequence

Dynamic Mesh Recovery from Partial Point Cloud Sequence

引用

International Conference on computer Vision (ICCV)

作者： Hojun Jang Minkwan Kim Jinseok Bae Young Min Kim Dept. of Electrical and Computer Engineering Seoul National University Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University

The exact 3D dynamics of the human body provides crucial evidence to analyze the consequences of the physical interaction between the body and the environment, which can eventually assist everyday activities in a wide range of applications. However, optimizing for 3D configurations from image observation requires a significant amount of computation, whereas real-world 3D measurements often suffer from noisy observation or complex occlusion. We resolve the challenge by learning a latent distribution representing strong temporal priors. We use a conditional variational autoencoder (CVAE) architecture with a transformer to train the motion priors with a large-scale motion dataset. Then our feature follower effectively aligns the feature spaces of noisy, partial observation with the necessary input for pre-trained motion priors, and quickly recovers a complete mesh sequence of motion. We demonstrate that the transformer-based autoencoder can collect necessary spatio-temporal correlations robust to various adversaries, such as missing temporal frames, or noisy observation under severe occlusion. Our framework is general and can be applied to recover the full 3D dynamics of other subjects with parametric representations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Review of Deep Learning for Biomedical Signals: Current Applications, Advancements, Future Prospects, Interpretation, and Challenges

引用

computers, Materials and Continua 2025年第3期83卷 3753-3841页

作者： Ali Mohammad Alqudah Zahra Moussavi Biomedical Engineering Program University of Manitoba Winnipeg MB R3T 2N2 Canada Department of Electrical and Computer Engineering University of Manitoba Winnipeg MB R3T 2N2 Canada

This review presents a comprehensive technical analysis of deep learning (DL) methodologies in biomedical signal processing, focusing on architectural innovations, experimental validation, and evaluation frameworks. We systematically evaluate key deep learning architectures including convolutional neural networks (CNNs), recurrent neural networks (RNNs), transformer-based models, and hybrid systems across critical tasks such as arrhythmia classification, seizure detection, and anomaly segmentation. The study dissects preprocessing techniques (e.g., wavelet denoising, spectral normalization) and feature extraction strategies (time-frequency analysis, attention mechanisms), demonstrating their impact on model accuracy, noise robustness, and computational efficiency. Experimental results underscore the superiority of deep learning over traditional methods, particularly in automated feature extraction, real-time processing, cross-modal generalization, and achieving up to a 15% increase in classification accuracy and enhanced noise resilience across electrocardiogram (ECG), electroencephalogram (EEG), and electromyogram (EMG) signals. Performance is rigorously benchmarked using precision, recall, F1-scores, area under the receiver operating characteristic curve (AUC-ROC), and computational complexity metrics, providing a unified framework for comparing model efficacy. The survey addresses persistent challenges: synthetic data generation mitigates limited training samples, interpretability tools (e.g., Gradient-weighted Class Activation Mapping (Grad-CAM), Shapley values) resolve model opacity, and federated learning ensures privacy-compliant deployments. Distinguished from prior reviews, this work offers a structured taxonomy of deep learning architectures, integrates emerging paradigms like transformers and domain-specific attention mechanisms, and evaluates preprocessing pipelines for spectral-temporal trade-offs. It advances the field by bridging technical advancement

关键词： Deep learning deep models biomedical signals physiological signals biosignals

来源：评论

学校读者我要写书评

暂无评论

A Low Complexity ML-Based Methods for Malware Classification

引用

computers, Materials & Continua 2024年第9期80卷 4833-4857页

作者： Mahmoud E.Farfoura Ahmad Alkhatib Deema Mohammed Alsekait Mohammad Alshinwan Sahar A.El-Rahman Didi Rosiyadi Diaa Salama Abd Elminaam Cybersecurity Department Al-Zaytoonah University of JordanAmman11733Jordan Department of Computer Science and Information Technology Applied CollegePrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Faculty of Information Technology Applied Science Private UniversityAmman11931Jordan Computer Systems Program-Electrical Engineering Department Faculty of Engineering-ShoubraBenha UniversityCairo11629Egypt Research Center for Artificial Intelligence and Cybersecurity Electronics and Informatics OrganizationNational Research and Innovation Agency(BRIN)KST Samaun SamadikunBandung40135Republic of Indonesia Jadara Research Center Jadara UniversityIrbid21110Jordan MEU Research Unit Middle East UniversityAmman11831Jordan

The article describes a new method for malware classification,based on a Machine Learning(ML)model architecture specifically designed for malware detection,enabling real-time and accurate malware *** an innovative feature dimensionality reduction technique called the Interpolation-based Feature Dimensionality Reduction Technique(IFDRT),the authors have significantly reduced the feature space while retaining critical information necessary for malware *** technique optimizes the model’s performance and reduces computational *** proposed method is demonstrated by applying it to the BODMAS malware dataset,which contains 57,293 malware samples and 77,142 benign samples,each with a 2381-feature *** the IFDRT method,the dataset is transformed,reducing the number of features while maintaining essential data for accurate *** evaluation results show outstanding performance,with an F1 score of 0.984 and a high accuracy of 98.5%using only two reduced *** demonstrates the method’s ability to classify malware samples accurately while minimizing processing *** method allows for improving computational efficiency by reducing the feature space,which decreases the memory and time requirements for training and *** new method’s effectiveness is confirmed by the calculations,which indicate significant improvements in malware classification accuracy and *** research results enhance existing malware detection techniques and can be applied in various cybersecurity applications,including real-timemalware detection on resource-constrained *** and scientific contribution lie in the development of the IFDRT method,which provides a robust and efficient solution for feature reduction in ML-based malware classification,paving the way for more effective and scalable cybersecurity measures.

关键词： Malware detection ML-based models dimensionality reduction feature engineering

来源：评论

学校读者我要写书评

暂无评论

Simulation of Photonic Metasurfaces using a Surface Integral Equation Solver with Generalized Sheet Transition Conditions

Simulation of Photonic Metasurfaces using a Surface Integral...

引用

Antennas and Propagation (LACAP), IEEE Latin American Conference on

作者： Sebastian Celis Sierra Partha Mondal Ran Zhao Hakan Bagci Electrical and Computer Engineering (ECE) Program King Abdullah University of Science and Technology Thuwal Saudi Arabia School of Electronic Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798331527587

ISBN: (纸本)9798331527594

Photonic metasurfaces are efficiently and accurately simulated using a surface integral equation (SIE) solver. This solver models the metasurface as an infinitesimally thin sheet on which generalized sheet transition conditions (GSTCs) are enforced. GSTCs connect the electromagnetic fields on both sides of the metasurface using equivalent susceptibility tensors and avoid modelling of geometrically intricate metasurface unit cells by the SIE solver. Susceptibility tensors are obtained from the transmission and the reflection coefficients associated with a unit cell. A numerical example, involving a metasurface that supports high-quality factor resonances and excited by a Gaussian beam, is presented to demonstrate the accuracy of the proposed approach.

关键词： Tensors Accuracy Integral equations Metasurfaces Mathematical models Numerical models Reflection coefficient Electromagnetic fields Dispersion Photonics

来源：评论

学校读者我要写书评

暂无评论

Designing Classical Header Bits for Quantum Wrapper Networking with O-band Quantum Signal

Designing Classical Header Bits for Quantum Wrapper Networki...

引用

Frontiers in Optics + Laser Science 2023, FiO, LS 203: Part of Frontiers in Optics + Laser Science 2023

作者： Gül, G. Berkay On, M. Singh, S.K. Proietti, R. Kanter, G.S. Yoo, S.J.B. Kumar, P. Graduate Program in Applied Physics Northwestern University 2145 Sheridan Road EvanstonIL60208 United States Department of Electrical and Computer Engineering University of California Davis DavisCA95616 United States Department of Electronics and Communication Eng. Indian Institute of Technology Roorkee247667 India Department of Electronics and Telecommunications Engineering Politecnico di Torino Italy Center for Photonic Communication and Computing Dept. of Electrical and Computer Eng. Northwestern University EvanstonIL60208 United States

We investigate the impact of wavelength choice for the classical headers in quantum wrapper networking with O-band quantum payload. We show that a C-band header performs substantially better than an O-band header. ... 详细信息

ISBN: (纸本)9781957171296

关键词： Bandpass filters Beam splitters Bit error rate Entanglement distribution Quantum teleportation Raman scattering

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：