检索结果-内蒙古大学图书馆

Secure speaker identification in open and closed environments modeled with symmetric comb filters

Multimedia Tools and Applications 2025年第18期84卷 19147-19189页

作者： Shafik, Amira Monir, Mohamad El-Shafai, Walid Khalaf, Ashraf A. M. Nassar, M.M. El-Fishawy, Adel S. El-Din, M. A. Zein Dessouky, Moawad I. El-Rabaie, El-Sayed M. Abd El-Samie, Fathi E. Department Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Security Engineering Laboratory Department of Computer Science Prince Sultan University Riyadh11586 Saudi Arabia Electrical Engineering Department Faculty of Engineering Minia University Minia61519 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Speech is a fundamental means of human interaction. Speaker Identification (SI) plays a crucial role in various applications, such as authentication systems, forensic investigation, and personal voice assistance. However, achieving robust and secure SI in both open and closed environments remains challenging. To address this issue, researchers have explored new techniques that enable computers to better understand and interact with humans. Smart systems leverage Artificial Neural Networks (ANNs) to mimic the human brain in identifying speakers. However, speech signals often suffer from interference, leading to signal degradation. The performance of a Speaker Identification System (SIS) is influenced by various environmental factors, such as noise and reverberation in open and closed environments, respectively. This research paper is concerned with the investigation of SI using Mel-Frequency Cepstral Coefficients (MFCCs) and polynomial coefficients, with an ANN serving as the classifier. To tackle the challenges posed by environmental interference, we propose a novel approach that depends on symmetric comb filters for modeling. In closed environments, we study the effect of reverberation on speech signals, as it occurs due to multiple reflections. To address this issue, we model the reverberation effect with comb filters. We explore different domains, including time, Discrete Wavelet Transform (DWT), Discrete Cosine Transform (DCT), and Discrete Sine Transform (DST) domains for feature extraction to determine the best combination for SI in case of reverberation environments. Simulation results reveal that DWT outperforms other transforms, leading to a recognition rate of 93.75% at a Signal-to-Noise Ratio (SNR) of 15 dB. Additionally, we investigate the concept of cancelable SI to ensure user privacy, while maintaining high recognition rates. Our simulation results show a recognition rate of 97.5% at 0 dB using features extracted from speech signals and their DCTs. Fo

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Service Recovery in NFV-Enabled Networks: Algorithm Design and Analysis

引用

IEEE Transactions on Cloud Computing 2024年第2期12卷 800-813页

作者： Nguyen, Dung H. P. Lin, Chih-Chieh Nguyen, Tu N. Chu, Shao-I Liu, Bing-Hong Pham Van Dong University Faculty of Engineering and Technology Quang Ngai570000 Viet Nam National Kaohsiung University of Science and Technology Department of Electronic Engineering Kaohsiung80778 Taiwan Kennesaw State University Department of Computer Science MariettaGA30060 United States

Network function virtualization (NFV), a novel network architecture, promises to offer a lot of convenience in network design, deployment, and management. This paradigm, although flexible, suffers from many risks engendering interruption of services, such as node and link failures. Thus, resiliency is one of the requirements in NFV-enabled network design for recovering network services once occurring failures. Therefore, in addition to a primary chain of virtual network functions (VNFs) for a service, one typically allocates the corresponding backup VNFs to satisfy the resiliency requirement. Nevertheless, this approach consumes network resources that can be inherently employed to deploy more services. Moreover, one can hardly recover all interrupted services due to the limitation of network backup resources. In this context, the importance of the services is one of the factors employed to judge the recovery priority. In this article, we first assign each service a weight expressing its importance, then seek to retrieve interrupted services such that the total weight of the recovered services is maximum. Hence, we also call this issue the VNF restoration for recovering weighted services (VRRWS) problem. We next demonstrate the difficulty of the VRRWS problem is NP-hard and propose an effective technique, termed online recovery algorithm (ORA), to address the problem without necessitating the backup resources. Eventually, we conduct extensive simulations to evaluate the performance of the proposed algorithm as well as the factors affecting the recovery. The experiment shows that the available VNFs should be migrated to appropriate nodes during the recovery process to achieve better results. © 2013 IEEE.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

A Robust Framework for Epileptic Seizure Diagnosis: Utilizing GRU-CNN Architectures in EEG Signal Analysis 20

A Robust Framework for Epileptic Seizure Diagnosis: Utilizin...

引用

20th CSI International Symposium on Artificial Intelligence and Signal Processing, AISP 2024

作者： Nikoupour, Maryam Keyvanpour, Mohammad Reza Shojaedini, Seyed Vahab Alzahra University Data Mining Laboratory Department of Computer Engineering Faculty of Engineering Tehran Iran Alzahra University Faculty of Engineering Department of Computer Engineering Tehran Iran Iranian Research Organization for Science and Technology Department of Electrical Engineering Tehran Iran

ISBN: (纸本)9798350383942

Seizures that take place repeatedly and without provocation are referred to as epilepsy. Epilepsy can be diagnosed with electroencephalography (EEG). One of the most influential challenges of the past few years has been the use of deep learning algorithms to replace manual inspection of medical signals by specialists, such as epilepsy signal classification. This paper presents a multi-label classification approach for epileptic seizures using deep learning. UCI machine learning repository's epileptic seizure dataset has been used to classify epileptic seizure patients. 178 features are present in each of the 11500 samples in the dataset. Based on a variety of criteria, the proposed method may have a positive impact on epilepsy diagnosis, in most cases by approximately 6% compared with existing methods utilizing long short-term memory (LSTM) and autoencoder. It is possible thus to develop and apply gated recurrent unit-based methods with good potential for categorizing EEG signals for epilepsy diagnosis based on gated recurrent unit (GRU)-CNN based methods. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Monitoring energy losses of a residential building through thermographic assessments 17

Monitoring energy losses of a residential building through t...

引用

17th International Conference on Development and Application systems, DAS 2024

作者： Eugen, Iavorschi Laurențiu, Milici Dan Faculty of Electrical Engineering and Computer Science Department of Electrical Engineering "Stefan cel Mare" University of Suceava Suceava Romania

ISBN: (纸本)9798350349290

One of the significant opportunities for reducing energy waste and carbon emissions is the renovation, modernization, and rehabilitation of existing buildings. Replacing the windows of existing residential buildings with new energy-efficient ones is an easy way to upgrade an existing home into a nearly zero-energy building, NZEB (nearly zero-energy building). There is a wide variety of methods to discover the thermal weak points of a building, and the continuous innovation of construction materials provides solutions to maximize energy savings and minimize heat transfer to the exterior. This document presents a methodology for visualizing and recording the temperature distribution on the investigated surface of the building envelope to identify and locate vulnerable points where heat losses to the exterior are substantial. The objective was to highlight the need for upgrading the insulation system and replacing the existing windows of the analyzed building based on a multi-objective approach to maximize the building's energy performance and increase thermal comfort indoors. Using a Fluke Ti300+ Thermal Camera, energy losses were visualized through thermographic assessments, which could provide an adequate picture for accurately assessing the building's condition before renovation, to evaluate the need for partial renovation. For the case study, a residential building with one floor and mansard roof located in a region with hot summers and cold winters in Romania was chosen. The results showed that there are several options for significantly reducing the building's energy consumption. Thus, multiple energy efficiency solutions were proposed for the building to reduce heat losses. ©2024 IEEE.

关键词： Heat transfer

来源：评论

学校读者我要写书评

暂无评论

A Nobel Approach to Identify the Rainfall Prediction Using Deep Convolutional Neural Networks Algorithm 6th

A Nobel Approach to Identify the Rainfall Prediction Using D...

引用

6th International Conference on Information and Communication Technology for Intelligent systems, ICTIS 2021

作者： Desai, Prachi Gandhi, Ankita Acharya, Mitali Department of Computer Science Engineering Faculty of Engineering and Technology Parul University Vadodara India

ISBN: (纸本)9789811935749

It is unlikely to have a big impact on a country's economic *** also helps to reduce the loss of life and property caused by natural *** study of rainfall prediction using machine learning techniques, with a special emphasis on *** India, about 70% of the population is dependent on agriculture and related *** forecasting has been an issue of major technical and economic importance in the agricultural *** rain prediction model is still mostly based on artificial neural networks, and it has only been used in India so *** the present study, a comparative analysis of the two rainfall forecasting techniques, and is more *** today’s technology, the ability to predict the rainfall is not very well-informed about the complexity of the *** methods used are the methods of statistical and mathematical methods that don’t work if there is a situation of a nonlinear *** existing installation may fail when the level of complexity of the information contained in it, increase it in the ***, this is the best way to get to the waiting;in the rain, it is a study of deep learning and neural networks, and genetic algorithms, is that it gives you more precise, it is used to predict the *** order to come up with a good rain is a joint, an appraisal is not *** simplest and easiest approach to get on a larger scale is to use weather *** the present study, it can be used in all types of weather stations, and the forecast will give access to some parts of the country.A technique for predicting month-to-month rain for a specific area in India using a deep CNN learning method as a replacement fortuning *** CNN was compared against an ANN. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

Machine learning and deep learning algorithms in detecting COVID-19 utilizing medical images: a comprehensive review

引用

Iran Journal of computer science 2024年第3期7卷 699-721页

作者： Nurjahan Mahbub-Or-Rashid, Md. Satu, Md. Shahriare Tammim, Sanjana Ruhani Sunny, Farhana Akter Moni, Mohammad Ali Department of IoT and Robotics Engineering Bangabandhu Sheikh Mujibur Rahman Digital University Kaliakair Bangladesh Department of Computer Science and Engineering Bangladesh University of Business and Technology Mirpur Bangladesh Department of Management Information Systems Noakhali Science and Technology University Noakhali Bangladesh Department of Computer Science and Software Engineering Auburn University Auburn AL United States Department of Computer Science and Engineering Green University of Bangladesh Dhaka Bangladesh Faculty of Health and Behavioural Sciences School of Health and Rehabilitation Sciences The University of Queensland St Lucia Australia

The public’s health is seriously at risk from the coronavirus pandemic. Millions of people have already died as a result of this devastating illness, which affects countless people daily worldwide. Unfortunately, no specific therapeutic drugs or vaccines are available to cure patients completely. Therefore, early identification of infected individuals and their isolation can help reduce community transmission of COVID-19. Despite being commonly used, the reverse transcription polymerase chain reaction (RT-PCR) test is costly, time-consuming, and requires suitable kits, which are not always readily available. An alternative solution for the traditional RT-PCR test is machine learning and deep learning-based COVID-19 detection that utilizes clinical features of chest X-rays and computed tomography (CT) images. In this study, we conducted a detailed review of more than 100 recently published works to detect COVID-19-infected patients. Thus, different data preprocessing, data augmentation, image enhancement, feature extraction, machine learning, deep learning, Explainable Artificial Intelligence (AI) methods, etc. were explored to understand how these techniques were used to process images for identifying COVID-19. Additionally, we identified the current challenges in this field and suggested further research directions. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Chest X-ray Computed tomography COVID-19 Deep learning Machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing visual clarity in hazy media: a comprehensive approach through preprocessing and feature fusion attention-based dehazing

引用

Multimedia Tools and Applications 2025年第17期84卷 18071-18093页

作者： Ayoub, Abeer El-Shafai, Walid El-Samie, Fathi E. Abd Hamad, Ehab K. I. Rabaie, El-Sayed M. Department of Electronics and Electrical Communication Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Security Engineering Lab 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 Electrical Engineering Department Faculty of Engineering Aswan University Aswan81542 Egypt

Particles in the atmosphere, such as dust and smoke, can cause visual clarity problems in both images and videos. Haze is the result of the interaction between airborne particles and light, which is scattered and attenuated. Hazy media present difficulties in a variety of applications due to the reduced contrast and loss of essential information. In response, dehazing techniques have been introduced to bring hazy videos and images back to clarity. Here, we provide a novel technique for eliminating haze. It comprises preprocessing steps before dehazing. Preprocessing is applied to hazy images through homomorphic processing and Contrast Limited Adaptive Histogram Equalization (CLAHE). We present a dehazing technique referred to as the pre-trained Feature Fusion Attention Network (FFA-Net) that directly lets dehazed images be restored from hazy or preprocessed hazy inputs without requiring the determination of atmospheric factors, such as air light and transmission maps. The FFA-Net architecture incorporates a Feature Attention (FA) method to do this task. We assess the proposed technique in a variety of circumstances, including visible frames, Near-Infrared (NIR) frames, and real-world hazy images. Evaluation criteria like entropy, correlation, and Peak Signal-to-Noise Ratio (PSNR) are used to compare the quality of dehazed frames or images to their hazy counterparts. Furthermore, histogram analysis and spectral entropy are adopted to determine the effectiveness of the proposed technique in comparison to existing dehazing techniques. Comparative results are presented for both real-world and simulated environments. The benefits of the proposed technique are demonstrated by a comparison of the results obtained from the standalone pre-trained FFA-Net and the proposed comprehensive methodology. Moreover, a thorough assessment is carried out for comparing the effectiveness of the proposed FFA-Net technique to those of some current dehazing techniques on real hazy images. T

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Retinal disorder diagnosis based on hybrid deep learning models

引用

Multimedia Tools and Applications 2025年 1-25页

作者： Sedik, Ahmed El-Shafai, Walid El-Hag, Noha A. El-Banby, Ghada M. Abd El-Samie, Fathi E. Smart Systems Engineering Laboratory College of Engineering Prince Sultan University Riyadh11586 Saudi Arabia Department of the Robotics and Intelligent Machines Faculty of Artificial Intelligence Kafrelsheikh University Kafr el-Sheikh Egypt Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt The Higher Institute of Commercial Sciences Algarbia Al Mahalla Al Kubra31951 Egypt Department of Industrial Electronics and Control Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Anomaly detection from medical images is badly needed for automated diagnosis. For example, medical images obtained with several modalities, such as magnetic resonance (MR) and confocal microscopy, need to be classified for anomaly detection. The MR images may contain tumors that need to be detected with anomaly detection techniques. In MR imaging, brain tumors are represented as areas composed of abnormal cells that need to be detected. On the other hand, confocal microscopy can be used for retinal imaging. Hence, there is a need to apply classification techniques for diagnosing diseases of the eye, such as Diabetic Retinopathy (DR), which leads to exudates in different regions of the retina. The detection of exudates is necessary for the diagnosis of DR. In this paper, two models are presented for the classification of MR and retinal images. Much research has been done in this area, but it did not achieve high accuracy of classification in an acceptable time. In addition, the previous models did not consider both types of image modalities considered in this paper. The suggested models are Convolutional Neural Network (CNN) and Convolutional Long Short-Term Memory (Conv-LSTM). They are used to classify normal and abnormal cases of both brain tumor and DR diseases. The CNN model is composed of six convolutional layers and six max-pooling layers. A soft-max activation function takes the classification decision. The proposed Conv-LSTM model is composed of three stages: pre-processing, feature extraction, and classification. The deep learning model performance is better than those of traditional networks. The CNN gives an accuracy of 94.26% for DR classification and 95.8% for brain tumor classification, while the Conv-LSTM gives the maximum accuracy of 96.41% for DR classification and 97.4% for brain tumor classification. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Confocal microscopy

来源：评论

学校读者我要写书评

暂无评论

Development of a Nail-based Application for the Detection of Disease using Image Processing 2

Development of a Nail-based Application for the Detection of...

引用

2nd DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry, IDICAIEI 2024

作者： Gote, Pradnyawant M. Kumar, Praveen Dhale, Trishul Mishra, Gaurav Vedprakash Faculty of Engineering and Technology Department of Computer Science & Design Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Computer Science & Medical Engineering Maharashtra Wardha442001 India Jawaharlal Nehru Medical College Department of Radiodiagnosis Maharashtra Wardha442001 India

ISBN: (纸本)9798331528713

Disease diagnosis using non-invasive techniques is a key determinant in the improvement of outcomes in patients and the enhancement of precautionary health measures. The study focuses on the design and development of a nail-based detection application employing image processing techniques to detect diseases such as systemic disease, fungal disease, Leukonychia (White spots on nails) and Paronychia (Nail bed infection) through analysis of the patterns of the fingernails and other related symptoms. The developed system integrates several techniques, comprising a customized imaging application, a user-friendly interface, and software for real-time image processing and disease classification. A variety of algorithms proposed for image processing, such as Median filtering, Sobel Mask and HOG features, are designed to extract important features from nail images and then use machine learning models that match these features against a database of established markers of various diseases. Comprehensive testing utilizing an annotated dataset of nail images demonstrated the system's accuracy in classifying certain diseases, further showcasing its potential for possible usage as a proficient tool for early disease diagnosis. Thus, this application is easy to use, user-friendly interface, and provides advancements in diagnosing diseases both in clinical settings and in the comfort of one's home. The incorporation of this technology into routine clinical practice might facilitate the possibility of early diagnosis and early intervention, which could improve patient outcomes and reduce healthcare system burdens. © 2024 IEEE.

关键词： Median filters

来源：评论

学校读者我要写书评

暂无评论

Automated Classification and Segmentation of Brain Tumor Images using Backboned ResUNet Framework 6

Automated Classification and Segmentation of Brain Tumor Ima...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Prasanalakshmi, B. Anitha, Cuddapah Balamanigandan, R. Mahaveerakannan, R. Gade, N.V. Ratnakishor Adjunct Faculty Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India Department of Computer Science and Engineering School of Computing Mohan Babu University Andhra Pradesh Tirupati India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India

ISBN: (纸本)9798331522667

One of the most challenging issues in computer imaging is the automated segmentation of brain tumors using Magnetic Resonance Images (MRI). Several approaches are explored using Deep Neural Networks in image segmentation since they perform well in automated tumor segmentation using tumor scans. Due to the complexity, training deeper neural networks usually takes a long time and many processing resources. An automated approach for classifying and segmenting images of Brain tumor MRI is proposed. As a hybrid transfer learning approach, modified ResNet50 identifies the class of MRI images as Benign or malignant. After identifying the Benign images, the tumor’s location is segmented using a hybrid network involving ResUNet with the Xception network as Backbone. This combination approach is chosen after its comparative analysis with other backbones. Various combination approaches are carried out, and performance metrics like Jaccard, Dice, and Tversky coefficient are done to prove the ResUNet backboned with Xception plays a better role concerning accuracy and speed. The proposed approach was tested on the dataset Cancer Imaging Archive to validate its efficiency. The proposed model has an average dice similarity coefficient score of 0.94, outperforming the conventional transfer learning training method with all the layers. © 2025 IEEE.

关键词： Magnetic resonance imaging

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：