检索结果-内蒙古大学图书馆

Improved channel estimation for underwater wireless optical communication OFDM systems by combining deep learning and machine learning models

引用

Optical and Quantum Electronics 2025年第3期57卷 1-21页

作者： Salama, Wessam M. Aly, Moustafa H. Department of Computer Engineering Faculty of Engineering Pharos University Canal El Mahmoudia Street Beside Green Plaza Complex 21648 Alexandria Egypt OSA Member Department of Electronics and Communications Engineering College of Engineering and Technology Arab Academy for Science Technology and Marine Transport Alexandria1029 Egypt

Recent studies on channel estimation in wireless communication systems have focused on deep learning methods. Our primary contribution is based on the use of DenseNet121 hybrid with Random Forest (RF), Gated Recurrent Units (GRU), Long Short-Term Memory Networks (LSTM), and Recurrent Neural Networks (RNN) to improve the channel estimation and lower the error rate. In order to mitigate inter-symbol interference and map the datasets, this paper introduces M-quadrature amplitude modulation (16-QAM) and orthogonal frequency division multiplexing (OFDM), which is based on quadrature phase shift keying (QPSK). Additionally, the existence or lack of cyclic prefixes forms the basis of our simulation. Additionally, the suggested models are investigated using pilot samples 2, 4, 8, and 64. Labeled OFDM signal samples, where the labels match the signal received after applying OFDM and passing through the medium, are used to train the proposed models. The DenseNet121 functions as a powerful feature extractor to extract intricate spatial information from received signal data. Sequential models like as RNN, LSTM, and GRU are used to model temporal dependencies in the retrieved features. RF is also utilized to exploit non-linear relationships and interactions between features to further increase prediction accuracy and reduce bit error rate (BER). By comparing the models using key metrics like accuracy, bit error rate (BER), and mean squared error (MSE), superior performance is attained based on the DenseNet121_RNN_GRU_RF model. Additionally, the DLMs are assessed against traditional methods like minimal mean square error (MMSE) and least squares (LS). Using the DenseNet121_RNN_GRU_RF model indicates a considerable gain over alternative architectures, with an improvement of 36.3% over DensNet121-RNN-LSTM-RF, according to a comparison of the suggested models without cyclic prefix for OFDM_QPSK. The improvement in percentages of roughly 63.3% over DensNet121-RNN-LSTM, 68.18% over De

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

On Robots with Reasoning Capabilities and Human-Like Appearance and Behaviour: Implications for Accident Investigations 6

On Robots with Reasoning Capabilities and Human-Like Appeara...

引用

6th Social Robots with AI: Prospects, Risks, and Responsible Methods Robophilosophy, RP 2024

作者： Salvini, Pericle Pattinson, Jo-Ann Kunze, Lars Winfield, Alan Jirotka, Marina Department of Computer Science University of Oxford United Kingdom Faculty of Environment University of Leeds United Kingdom School of Engineering University of the West of England United Kingdom

ISBN: (纸本)9781643685670

AI-enhanced reasoning enables robots to create detailed accounts of their own situated behaviour as well as the behaviour of other people. This capability is currently employed by robot designers to achieve transparency, trust, and enhance robot social and communicative capabilities. Furthermore, robots may be designed to resemble humans both in their physical appearance and their behaviour. This approach is intended to facilitate more effective interactions with people. In this article we identify and examine some of the ethical, social and legal implications of these capabilities for the investigation of robot accidents. We consider two aspects in particular. The first of these is the role of robots as subjects in a testimony regarding an incident in which they are directly or indirectly involved. This can be described as a case of robots acting as witnesses. The second aspect is the role of robots as objects in a human testimony. This can be described as a case of robots being witnessed. © 2025 IOS Press. All rights reserved.

关键词： Social robots

来源：评论

学校读者我要写书评

暂无评论

Automatic speaker identification system based on MLP network and deep learning in the presence of severe interference

引用

Multimedia Tools and Applications 2025年 1-42页

作者： Shafik, Amira Sedik, Ahmed El-Shafai, Walid Khalaf, Ashraf A. M. El-Rabaie, El-Sayed M. El-Samie, Fathi E. Abd Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Electrical Engineering Faculty of Engineering Minia University Minia61519 Egypt Smart Systems Engineering Laboratory College of Engineering Prince Sultan University Riyadh11586 Saudi Arabia Department of the Robotics and Intelligent Machines Faculty of Artificial Intelligence Kafr Elsheikh University Kafr El‑Shaikh Egypt Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Automatic Speaker Identification (ASI) is so crucial for security. Current ASI systems perform well in quiet and clean surroundings. However, in noisy situations, the robustness of an ASI system against additive noise and interference is a crucial factor. An investigation of the impact of interference on ASI system performance is presented in this paper, which introduces algorithms for achieving high ASI system performance. The objective is to resist the interference of various forms. This paper presents two models for the ASI task in the presence of interference. The first one depends on Normalized Pitch Frequency (NPF) and Mel-Frequency Cepstral Coefficients (MFCCs) as extracted features and Multi-Layer Perceptron (MLP) as a classifier. In this model, we investigate the utilization of a Discrete Transform (DT), such as Discrete Wavelet Transform (DWT), Discrete Cosine Transform (DCT) and Discrete Sine Transform (DST), to increase the robustness of extracted features against different types of degradation through exploiting the sub-band decomposition characteristics of DWT and the energy compaction property of DCT and DST. This is achieved by extracting features directly from contaminated speech signals in addition to features extracted from discrete transformed signals to create hybrid feature vectors. The enhancement techniques, such as Spectral Subtraction (SS), Winer Filter, and adaptive Wiener filter, are used in a preprocessing stage to eliminate the effect of the interference on the ASI system. In the second model, we investigate the utilization of Deep Learning (DL) based on a Convolutional Neural Network (CNN) with speech signal spectrograms and their Radon transforms to increase the robustness of the ASI system against interference effects. One of this paper goals is to introduce a comparison between the two models and build a more robust ASI system against severe interference. The experimental results indicate that the two proposed models lead to satisfa

关键词： Additive noise

来源：评论

学校读者我要写书评

暂无评论

Superpixel-Based Sparse Labeling for Efficient and Certain Medical Image Annotation 27th

Superpixel-Based Sparse Labeling for Efficient and Certain M...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Rezaei, Somayeh Jiang, Xiaoyi Department of Information Engineering University of Padova Padua Italy Faculty of Mathematics and Computer Science University of Münster Einsteinstrasse 62 Münster48149 Germany

ISBN: (纸本)9783031781971

Supervised deep learning crucially depends on large amount of high-quality annotation data. While labeling for classification and grading tasks is rather efficient to achieve, labeling for segmentation is much more difficult and time-consuming, characterized by pixel-based dense annotation in practice. This approach suffers from two fundamental disadvantages: 1) Lack of efficiency because of the large number of pixels on region boundaries (other parts of an image can be easily labeled) and more importantly the need of precise positioning of boundary pixels. 2) Lack of certainty. The area around the boundaries is in fact the part of an image, where even medical experts are often uncertain and may make non-precise annotations, resulting in varying annotations by different experts (the serious problem of inter-observer variability). To overcome these disadvantages, we propose superpixel-based annotation instead of pixels. Importantly, we do not require to label in the area of boundaries with high uncertainty for medical experts. We automatically fill the unlabeled area (boundary gap). In addition to heuristic rules we also study the random walker. Experiments were conducted with three different medical segmentation tasks and two network models. Despite the easy-to-make sparse annotation we are able to achieve segmentation results that are comparable or even superior to those obtained by using pixel-based dense annotation. In addition to the high efficiency, our approach substantially reduces the inter-observer variability as a positive side effect. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Superpixels

来源：评论

学校读者我要写书评

暂无评论

Whale Optimization Algorithm-Based Feature Selection Combined with the XGBoost Model for Breast Cancer Detection: A Comparative Study 9th

Whale Optimization Algorithm-Based Feature Selection Combine...

引用

9th International Conference on Smart City Applications, SCA 2024

作者： Benghazouani, Salsabila Nouh, Said Zakrani, Abdelali Department of Mathematics and Computer Science Faculty of Sciences Ben M’Sik Hassan II University Casablanca Morocco Department of Computer Science Engineering ENSAM Hassan II University Casablanca Morocco

ISBN: (纸本)9783031886522

Breast cancer has emerged as a significant cause of female mortality globally, underscoring the critical need for early detection and diagnosis. Machine Learning, as a cutting-edge technology, holds immense promise in addressing healthcare challenges, including breast cancer detection. Despite advancements in technology, accurately discerning malignant breast masses from benign ones remains a complex and challenging task in medical research. Feature selection techniques play a vital role in this endeavor, as they aim to identify the most pertinent and informative features from complex datasets, thus improving the accuracy and reliability of models for detecting breast cancer. Numerous recent studies have emphasized the efficacy of metaheuristic algorithms in optimizing various problems across different domains, with particular focus on the Whale Optimization Algorithm (WOA). This paper focuses on evaluating the effectiveness of different feature selection (FS) approaches, such as WOA-based Feature selection, Recursive Feature Elimination, and SelectFromModel, in conjunction with diverse machine learning approaches for detecting breast cancer. The study assesses methods, including Support Vector Machine, XGBoost, Decision Tree, and Logistic regression using performance evaluation measures including, recall, F1-score, accuracy, area under the curve (AUC), precision, and feature removal percentage. Notably, FS based WOA combined with XGBoost model demonstrated outstanding performance measures, with an accuracy rate of 99.4%, an F1-score of 99.4%, 100.0% precision, 98.8% recall, and a 99.4% AUC. These findings contribute valuable insights into enhancing breast cancer detection accuracy and facilitating early intervention strategies, thereby potentially improving patient outcomes. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Breast Cancer Classification Feature Selection Machine Learning Whale Optimization Algorithm

来源：评论

学校读者我要写书评

暂无评论

Impact of defects on the spectral characteristics of PureB avalanche-mode light emitting diodes 29

Impact of defects on the spectral characteristics of PureB a...

引用

Light-Emitting Devices, Materials, and Applications XXIX 2025

作者： Jelavić, Eva Nanver, Lis K. Knežević, Tihomir Ruder Boskovic Institute Division of Materials Physics Laboratory for Semiconductors Zagreb Croatia University of Twente Faculty of Electrical Engineering Mathematics & Computer Science Enschede Netherlands

ISBN: (纸本)9781510685208

Single photon avalanche diodes (SPADs) fabricated in PureB silicon technology offer exceptional versatility, functioning both as light emitting diodes and detectors sensitive down to a single photon. In PureB technology, nanometer-thin layers of boron are deposited on the silicon surface, creating defect-free ultra-shallow junctions. In this paper, PureB diodes with a junction depth of a few tens of nanometers are studied as avalanche-mode light-emitting diodes (AMLEDs) with the advantage that optical absorption was minimal. They were systematically analyzed to investigate the impact of defects on their optical and electrical characteristics. Bulk defects were unintentionally introduced by contamination during the processing of the n+ buried layer. These defects cause the increase in dark currents and the formation of light-emitting spots, observable in light emission spectra taken at reverse biases below the breakdown voltage. An increase in relative intensity for wavelengths from 450 nm to 550 nm was observed in spectral characteristics of light emitting spots compared to the light emission of the active-region breakdown. Optical and electrical characterization was conducted on diodes with different geometry, implantation doses in the multiplication region, and distance to an implicit guard ring to examine the impact of these parameters on the light emission spectrum. Low-temperature electrical characteristics and light emission patterns of the devices were obtained by measurements at cryogenic temperatures. © 2025 SPIE.

关键词： Particle beams

来源：评论

学校读者我要写书评

暂无评论

Neural-XGBoost: A Hybrid Approach for Disaster Prediction and Management Using Machine Learning

引用

IEEE Access 2025年 13卷 86768-86780页

作者： Saleem, Muhammad Asim Javeed, Ashir Benjapolakul, Watit Srisiri, Wattanasak Chaitusaney, Surachai Kaewplung, Pasu Chulalongkorn University Center of Excellence in Artificial Intelligence Machine Learning and Smart Grid Technology Department of Electrical Engineering Faculty of Engineering Bangkok 10330 Thailand Blekinge Institute of Technology Department of Computer Science Karlskrona Sweden

Effective disaster prediction is essential for disaster management and mitigation. This study addresses a multi-classification problem and proposes the Neural-XGBoost disaster prediction model (N-XGB), a hybrid model that combines neural networks (NN) for feature extraction with XGBoost for classification. The NN component extracts high-level features, while XGBoost uses gradient-boosted decision trees for accurate predictions, combining the strengths of deep learning and boosting techniques for improved accuracy. The N-XGB model achieves an accuracy of 94.8% and an average F1 score of 0.95 on a real-world dataset that includes wildfires, floods and earthquakes, significantly outperforming baseline models such as random forest, Support vector machine and logistic regression 85% accuracy. The balanced F1 scores for wildfires 0.96, floods 0.93, and earthquakes 0.96 demonstrate the model's robustness in multi-class classification. The Synthetic Minority Oversampling Technique (SMOTE) balances datasets and improves model efficiency and capability. The proposed N-XGB model provides a reliable and accurate solution for predicting disasters and contributes to improving preparedness, resource allocation and risk management strategies. © 2013 IEEE.

关键词： Disaster Prediction Feature Extraction Machine Learning SMOTE XGBoost

来源：评论

学校读者我要写书评

暂无评论

Advanced Power and Voltage Regulation in a DC Microgrid with Solar Energy and Battery Storage 15

Advanced Power and Voltage Regulation in a DC Microgrid with...

引用

15th International Renewable Energy Congress, IREC 2025

作者： Elrashid, M. Rajab, Z. Elhashane, M. Younis, A. Gomez-Romero, J. Tnatin, Salah I.S Mohamed, F. Benghazi University Faculty if Engineering Electrical and Electronic Department Libya University of Granada Department of Computer Science and Artificial Intelligence Spain Omar Al-Mukhtar University Faculty of Engineering Electrical Department Libya Authority of Natural Science Research and Technology Tripoli Libya

ISBN: (纸本)9798331516772

This research investigates the modeling, design, and simulation of a microgrid with advanced energy management controller, developed using MATLAB/Simulink. This paper presents a comprehensive analysis, modeling, and simulation of a smart controller for a boost converter, using an artificial neural network (ANN) for maximum power point tracking (MPPT) to enhance power output. The study begins with a comparison between traditional MPPT techniques and the ANN-based approach. These MPPT strategies are compared in terms of their response to dynamic weather conditions (such as temperature and irradiance variations) and their ability to minimize oscillations around the maximum power point. The simulation results demonstrate that the ANN-based MPPT method outperforms the conventional P&O and IC methods, providing faster response times and higher output power. Additionally, the system's performance was evaluated under conditions of power shortage and during battery charging and discharging cycles, showing the effectiveness of the smart controller in maintaining system stability and optimizing energy management. © 2025 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation Based Real-Time Traffic Monitoring via Res-UNet Classifier and Kalman Filter

引用

SN computer science 2025年第1期6卷 1-17页

作者： Qureshi, Asifa Mehmood Algarni, Asaad Aljuaid, Hanan Alatiyyah, Mohammed Hamad Alnowaiser, Khaled Jalal, Ahmad Department of Creative Technologies Air University E-9 Islamabad 44000 Pakistan Department of Computer Sciences Faculty of Computing and Information Technology Northern Border University Rafha 91911 Saudi Arabia Department of Computer Sciences College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh 11671 Saudi Arabia Department of Computer Science College of Sciences and Humanities in Aflaj Prince Sattam Bin Abdulaziz University Al-Kharj Saudi Arabia Department of Computer Engineering College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University Al-Kharj 11942 Saudi Arabia Department of Computer Science Air University E-9 Islamabad 44000 Pakistan

In computer vision, accurate vehicle recognition and tracking is a challenging research topic. Manual surveillance systems are cumbersome, labor-intensive, and inefficient in today's congested traffic environment. Automated traffic monitoring systems are needed in today's world because they provide potential solutions to these issues. However, there are still some challenges in automating these systems which need to be addressed. One of the challenges is the extraction of foreground from a complex environment that only contains vehicles along with spatial and temporal information. In this paper, a semantic segmentation-based foreground extraction model is proposed to overcome these challenges. After segmentation, a blob detection technique is applied to detect each vehicle. To overcome the issue of vehicle-to-vehicle occlusion we extracted Harris corner points and computed the separation line based on the vehicle geometry coordinates. Furthermore, we introduce an ID assignment mechanism based on VGG-16 extracted features. Based on the detections, the number of cars is also counted for each frame. For tracking, we first applied Farneback optical flow algorithm to detect motion in vehicles. Only those vehicles were passed to the tracking algorithm in which motion was detected. To estimate each vehicle's location in succeeding image frames Kalman filter was implemented. A vehicle reidentification and ID recovery module are also proposed to enhance the tracking outcome. Vehicle trajectories based on vehicle location midpoint were also estimated. Extensive experiments are used to validate the proposed system and achieved a precision score of 0.965 and 0.931 over Roundabout and AU-AIR datasets for vehicle detection. However, for vehicle tracking the precision is 0.948 over the Roundabout dataset and 0.839 for the AU-AIR dataset. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Blob detection Detection and tracking Kalman filter Occlusion handling Res-Unet Semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Reinforcement Learning Framework for Optimizing Node Deployment in WSNs 14

A Hybrid Reinforcement Learning Framework for Optimizing Nod...

引用

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

作者： Priyadarshi, Rahul Rout, Jayant Kumar Gupta, Akash Kumar Ranjan, Rakesh Verma, Amit Teja, Panduranga Ravi Faculty of Engineering and Technology ITER SOA Bhubaneswar India School of Computer Application KIIT Bhubaneswar India Dept of ECE BIT Mesra Deoghar India School of Computer Science UPES Dehradun India

ISBN: (纸本)9798331531935

Efficient node deployment in Wireless Sensor Networks (WSNs) is critical for maximizing network coverage, enhancing energy efficiency, and prolonging network lifetime. However, achieving optimal node placement is challenging due to the limited energy resources and dynamic environmental conditions in WSNs. This paper presents a novel hybrid approach that combines Reinforcement Learning (RL) with the Differential Evolution (DE) algorithm to optimize node deployment in WSNs. In this method, RL dynamically adapts node positions based on local network states, while DE performs global optimization to refine these placements and improve coverage. Simulation results demonstrate that the proposed RL-DE hybrid approach significantly outperforms traditional deployment methods, standalone RL, and DE in terms of coverage, energy conservation, and network longevity. The results suggest that the RL-DE approach provides an adaptive and robust solution for node deployment in WSNs, with potential applications in real-world sensor network deployments. © 2025 IEEE.

关键词： Energy efficiency

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：