检索结果-内蒙古大学图书馆

Deepfake detection using convolutional vision transformers and convolutional neural networks

Neural Computing and Applications 2024年第31期36卷 19759-19775页

作者： Soudy, Ahmed Hatem Sayed, Omnia Tag-Elser, Hala Ragab, Rewaa Mohsen, Sohaila Mostafa, Tarek Abohany, Amr A. Slim, Salwa O. Department of Computer Science Faculty of Computers and Artificial Intelligence Helwan University Cairo Egypt Department of Information Systems Faculty of Computers and Information Kafrelsheikh University Kafrelsheikh Egypt

Deepfake technology has rapidly advanced in recent years, creating highly realistic fake videos that can be difficult to distinguish from real ones. The rise of social media platforms and online forums has exacerbated the challenges of detecting misinformation and malicious content. This study leverages many papers on artificial intelligence techniques to address deepfake detection. This research proposes a deep learning (DL)-based method for detecting deepfakes. The system comprises three components: preprocessing, detection, and prediction. Preprocessing includes frame extraction, face detection, alignment, and feature cropping. Convolutional neural networks (CNNs) are employed in the eye and nose feature detection phase. A CNN combined with a vision transformer is also used for face detection. The prediction component employs a majority voting approach, merging results from the three models applied to different features, leading to three individual predictions. The model is trained on various face images using FaceForensics++ and DFDC datasets. Multiple performance metrics, including accuracy, precision, F1, and recall, are used to assess the proposed model’s performance. The experimental results indicate the potential and strengths of the proposed CNN that achieved enhanced performance with an accuracy of 97%, while the CViT-based model achieved 85% using the FaceForences++ dataset and demonstrated significant improvements in deepfake detection compared to recent studies, affirming the potential of the suggested framework for detecting deepfakes on social media. This study contributes to a broader understanding of CNN-based DL methods for deepfake detection. © The Author(s) 2024.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Explainable energy consumption and speed prediction in sustainable cities using deep learning

引用

Neural Computing and Applications 2025年第8期37卷 6233-6249页

作者： Abd El-Latif, Eman I. El-dosuky, Mohamed Faculty of Science Benha University Benha Egypt Computer Science Department Arab East Colleges Riyadh Saudi Arabia Computer Science Department Faculty of Computers and Information Mansoura University Mansoura Egypt

The idea of sustainable cities has drawn a lot of attention due to the quick expansion of metropolitan areas as well as the growing problems brought on by resource scarcity and climate change. Cities that prioritize sustainable practices are those that minimize their negative effects on the environment, maximize resource efficiency, and improve the standard of living for their citizens. Therefore, for sustainable cities, this paper uses the vehicle energy dataset (VED) to estimate travel times and calculate vehicle energy consumption. The dataset contains 12,609,170 road elevation tracks, 12,203,044 speed limit tracks, and 12,281,719 speed limit records with direction. An open-source routing engine called Valhalla is utilized to do a variety of tasks, including finding paths, matching maps, and creating maneuvers based on paths. The three primary stages of the suggested model are data pre-processing, feature extraction, and result interpretation. In the data pre-processing stage, null values are first eliminated and data normalization is implemented. Then, three techniques known as the gated recurrent unit (GRU), recurrent neural network (RNN), and long short-term memory (LSTM) are used to optimize the model. Finally, the results are interpreted through the use of SHAP (SHapley Additive explanations) in explainable artificial intelligence (XAI) techniques. The LSTM model yields the best prediction results, achieving 15.2662 RMSE, 11.7266 MAE, and 0.6696 R2 at 8 batch size, according to the evaluation results. Additional experiments are carried out in batch sizes of 8, 16, 32, and *** lowest metrics are produced by batch sizes of 64, while the best metrics are produced by batch sizes of 8. © The Author(s) 2025.

关键词： Sustainable city

来源：评论

学校读者我要写书评

暂无评论

Shear Let Transform Residual Learning Approach for Single-Image Super-Resolution

引用

computers, Materials & Continua 2024年第5期79卷 3193-3209页

作者： Israa Ismail Ghada Eltaweel Mohamed Meselhy Eltoukhy Department of Computer Science Faculty of Computers and InformaticsSuez Canal UniversityIsmailia51422Egypt Department of Information Technology College of Computing and Information Technology at KhulaisUniversity of JeddahJeddahSaudi Arabia

Super-resolution techniques are employed to enhance image resolution by reconstructing high-resolution images from one or more low-resolution ***-resolution is of paramount importance in the context of remote sensing,satellite,aerial,security and surveillance ***-resolution remote sensing imagery is essential for surveillance and security purposes,enabling authorities to monitor remote or sensitive areas with greater *** study introduces a single-image super-resolution approach for remote sensing images,utilizing deep shearlet residual learning in the shearlet transform domain,and incorporating the Enhanced Deep Super-Resolution network(EDSR).Unlike conventional approaches that estimate residuals between high and low-resolution images,the proposed approach calculates the shearlet coefficients for the desired high-resolution image using the provided low-resolution image instead of estimating a residual image between the high-and low-resolution *** shearlet transform is chosen for its excellent sparse approximation ***,remote sensing images are transformed into the shearlet domain,which divides the input image into low and high *** shearlet coefficients are fed into the EDSR *** high-resolution image is subsequently reconstructed using the inverse shearlet *** incorporation of the EDSR network enhances training stability,leading to improved generated *** experimental results from the Deep Shearlet Residual Learning approach demonstrate its superior performance in remote sensing image recovery,effectively restoring both global topology and local edge detail information,thereby enhancing image *** to other networks,our proposed approach outperforms the state-of-the-art in terms of image quality,achieving an average peak signal-to-noise ratio of 35 and a structural similarity index measure of approximately 0.9.

关键词： Super-resolution shearlet transform shearlet coefficients enhanced deep super-resolution network

来源：评论

学校读者我要写书评

暂无评论

A new CNN-based watermarking method for color medical images in a fusion domain

引用

Neural Computing and Applications 2025年第18期37卷 12611-12629页

作者： Hosny, Khalid M. Abdel-Aziz, Mostafa M. Lashin, Nabil A. Hamza, Hanaa M. Department of Information Technology Faculty of Computers and Informatics Zagazig University Zagazig44519 Egypt Department of Information Technology Faculty of Information Technology and Computer Science Sinai University Arish Campus Al-Arish45518 Egypt

The transmission of medical images via medical agencies raises security concerns, necessitating increased security measures to ensure integrity and security. However, many watermarking algorithms overlook equipoise;the relation between robustness, invisibility, and payload capacity results in a less satisfactory performance. To bridge this gap, we propose a new blind watermarking method for securing medical images based on a convolutional neural network in a fusion domain. First, we transmute the host color image using a phase-only transform (PHOT) to detect the surface pattern. We feed the detected surface pattern into a pre-trained VGG19 model to impeccably extract the stable feature vector. We encrypt the extracted image features using a hybrid Chirikov map to enhance their robustness and reliability. The synergy between the pre-trained VGG19 model and PHOT in an integrated domain effectively captures additional native and localized image features. A hybrid Fibonacci Q-matrix method scrambles the binary watermark to enhance security. Integrating double encryption into the proposed method markedly enhances its resistance against diverse countermeasures. Experimental outcomes indicate that the proposed scheme performs efficiently in robustness and invisibility. The obtained PSNR value was up to 60.15 dB, which is optimal for human perception. The embedded watermark can be retrieved without any warping. The retrieved watermark seems to be authentic, exhibiting ideal BER and NC values. In almost all attack circumstances, the BER values approached zero while the NC values got closer. The proposed method demonstrates notable enhancements in robustness and invisibility compared to prior methods. © The Author(s) 2025.

关键词： Watermarking

来源：评论

学校读者我要写书评

暂无评论

Multitask multilayer-prediction model for predicting mechanical ventilation and the associated mortality rate

引用

Neural Computing and Applications 2025年第3期37卷 1321-1343页

作者： El-Rashidy, Nora Tarek, Zahraa Elshewey, Ahmed M. Shams, Mahmoud Y. Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33516 Egypt Computer Science Department Faculty of Computers and Information Mansoura University Mansoura35561 Egypt Department of Computer Science Faculty of Computers and Information Suez University P.O.BOX:43221 Suez Egypt

Mechanical ventilation (MV) is a crucial intervention in the intensive care unit (ICU) for severely ill patients. However, it can potentially contribute to lung damage due to the opening and closing of small airways and alveoli. This study aims to enhance the accuracy of mechanical ventilation prediction using a comprehensive dataset from the Medical Information Mart for Intensive Care (MIMIC-III). The data were extracted with three time frames, 6, 12, and 24 h. Then, 6 h left as a time gap and the ventilation as well as the mortality during the next 48 h. The proposed model consists of two layers: Layer 1 predicts ventilation and mortality in the ICU, while Layer 2 predicts the duration of ventilation. Classification techniques are applied to identify patients in need of ventilators, employing multilayer multitask long short-term memory (LSTM) models. Regression tasks use neural networks (multilayer perception). The optimum feature subset was obtained using particle swarm optimization (PSO). Additionally, this study examines the correlation between ventilation and mortality among patients with and without acute respiratory distress syndrome (ARDS). The findings of this research can enhance health-care outcomes and inform policymakers about resource allocation in overwhelmed health services. The best results were obtained when utilizing the first 24 h for prediction. The proposed MTL model achieved promising performance of 0.944, 0.923, 0.951, and 0.921 for the first task and 0.971, 0.961, 0.963, and 0.970 for the second task for accuracy, precision, recall, score, and AUC, respectively. © The Author(s) 2024.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

An Efficient Indoor Localization Based on Deep Attention Learning Model

引用

computer Systems science & Engineering 2023年第8期46卷 2637-2650页

作者： Amr Abozeid Ahmed I.Taloba Rasha M.Abd El-Aziz Alhanoof Faiz Alwaghid Mostafa Salem Ahmed Elhadad Department of Computer Science College of Science and ArtsJouf UniversityQurayyatSaudi Arabia Information System Department Faculty of Computers and InformationAssiut UniversityEgypt Computer Science Department Faculty of Computers and InformationAssiut UniversityAssiutEgypt Department of Computer Science Faculty of Computers and InformationSouth Valley UniversityQenaEgypt

Indoor localization methods can help many sectors,such as healthcare centers,smart homes,museums,warehouses,and retail malls,improve their service *** a result,it is crucial to look for low-cost methods that can provide exact localization in indoor *** this context,imagebased localization methods can play an important role in estimating both the position and the orientation of cameras regarding an ***-based localization faces many issues,such as image scale and rotation ***,image-based localization’s accuracy and speed(latency)are two critical *** paper proposes an efficient 6-DoF deep-learning model for image-based *** model incorporates the channel attention module and the Scale PyramidModule(SPM).It not only enhances accuracy but also ensures the model’s real-time *** complex scenes,a channel attention module is employed to distinguish between the textures of the foregrounds and *** model adapted an SPM,a feature pyramid module for dealing with image scale and rotation variance ***,the proposed model employs two regressions(two fully connected layers),one for position and the other for orientation,which increases outcome *** on standard indoor and outdoor datasets show that the proposed model has a significantly lower Mean Squared Error(MSE)for both position and *** the indoor 7-Scenes dataset,the MSE for the position is reduced to 0.19 m and 6.25°for the ***,on the outdoor Cambridge landmarks dataset,the MSE for the position is reduced to 0.63 m and 2.03°for the *** to the findings,the proposed approach is superior and more successful than the baseline methods.

关键词： Image-based localization computer vision deep learning attention module VGG-16

来源：评论

学校读者我要写书评

暂无评论

A Highly-Parallel and Scalable Hardware Accelerator for the NTest Othello Game Engine

引用

IEEE Transactions on Parallel and Distributed Systems 2025年第08期36卷 1620-1633页

作者： Popa, Stefan Petric, Vlad Ivanovici, Mihai Transilvania University of Brasov Electronics and Computers Department Faculty of Electrical Engineering and Computer Science Romania

Othello is a two-player combinatorial game with 1E+28 legal positions and 1E+58 game tree complexity. We propose a HIghly PArallel, Scalable and configurable hardware accelerator for evaluating the middle and endgame Othello positions. We base HIPAS on NTest - a leading software Othello engine that uses the minimax algorithm with a quality pattern-based evaluation function, alpha-beta pruning, and heuristic mobility sorting. We describe its architecture and Field Programmable Gate Array implementation, measure its performance, and compare it with prior solutions. HIPAS achieves the highest quality evaluation, the highest performance with speed-ups up to several hundreds, and the best energy efficiency. The main novelty is the algorithm implementation as a circular pipeline and a Finite State Machine with pseudo-parallel processing. Although Othello was recently claimed to be weakly solved, the game remains unsolved in a stronger sense. A weak solution only shows how to force a draw. It does not guarantee a win if the opponent makes a mistake. HIPAS can validate the weak solution faster and more efficiently. A multi-threaded NTest software component evaluating the beginning and part of the middle game, combined with one or more instances of HIPAS for handling the remainder can provide a stronger solution. © 1990-2012 IEEE.

关键词： Middleware

来源：评论

学校读者我要写书评

暂无评论

BERT-CNN: A Deep Learning Model for Detecting Emotions from Text

引用

computers, Materials & Continua 2022年第5期71卷 2943-2961页

作者： Ahmed R.Abas Ibrahim Elhenawy Mahinda Zidan Mahmoud Othman Department of Computer Science Faculty of Computer and InformaticsZagazig UniversityZagazig44519Egypt Department of Computer Science Faculty of Computers and Information TechnologyFuture University in Egypt11835Egypt

Due to the widespread usage of social media in our recent daily lifestyles,sentiment analysis becomes an important field in pattern recognition and Natural Language Processing(NLP).In this field,users’feedback data on a specific issue are evaluated and *** emotions within the text is therefore considered one of the important challenges of the current NLP *** have been widely studied in psychology and behavioral science as they are an integral part of the human *** describe a state of mind of distinct behaviors,feelings,thoughts and *** main objective of this paper is to propose a new model named BERT-CNN to detect emotions from *** model is formed by a combination of the Bidirectional Encoder Representations from Transformer(BERT)and the Convolutional Neural networks(CNN)for textual *** model embraces the BERT to train the word semantic representation language *** to the word context,the semantic vector is dynamically generated and then placed into the CNN to predict the *** of a comparative study proved that the BERT-CNN model overcomes the state-of-art baseline performance produced by different models in the literature using the semeval 2019 task3 dataset and ISEAR *** BERTCNN model achieves an accuracy of 94.7%and an F1-score of 94%for semeval2019 task3 dataset and an accuracy of 75.8%and an F1-score of 76%for ISEAR dataset.

关键词： BERT-CNN deep learning emotion detection semeval2019 text classification

来源：评论

学校读者我要写书评

暂无评论

Leveraging EEG Signals and Machine Learning for Schizophrenia Classification 6

Leveraging EEG Signals and Machine Learning for Schizophreni...

引用

6th International Conference on Computing and informatics, ICCI 2024

作者： Elfarsy, Abdelrahman El-Metwally, Sara Medical Informatics Program Faculty of Computers and Information Mansoura University Mansoura Egypt Computer Science Department Faculty of Computers and Information Mansoura University Mansoura Egypt

ISBN: (纸本)9798350373875

Schizophrenia is a neurological disorder known for its potential to disrupt brain function and cause erratic behavior. Timely diagnosis and intervention are crucial for improving patient outcomes. This paper conducts a comprehensive comparative study of three machine learning models: Logistic Regression (LR), Support Vector Machine (SVM), and Random Forest (RF) to classify EEG signals associated with schizophrenia. The dataset utilized in this study comprises EEG data obtained from 28 individuals, data preprocessing techniques, including artifact removal, filtering, and normalization, were applied to enhance data quality. A set of informative statistical features was extracted from the EEG signals to capture relevant information. The three machine learning models are trained and evaluated using various performance metrics, including accuracy, precision, recall, F1-score, and Area Under the Curve (AUC). Random Forest achieved the highest accuracy (96%), while SVM demonstrated strong precision and recall (95%). These findings highlight the potential of machine learning in aiding early schizophrenia diagnosis through EEG signal analysis. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Early Parkinson's Disease Detection and Classification using Machine Learning and Neutrosophic Sets

引用

Neutrosophic Sets and Systems 2025年 82卷 873-886页

作者： Oudah, Hasan H. Metwaly, Ahmed A. Eassa, Mohamed Abdelhafeez, Ahmed Nagm, Ahmad M. Salama, Ahmed S. College of Arts Department of Journalism Ahl Al Bayt University Karbala Iraq Department of Computer Science Faculty of Computers and Informatics Zagazig University Zagazig44519 Egypt Computer Science Department Faculty of Information System and Computer Science October 6 University Giza12585 Egypt Applied Science Research Center Applied Science Private University Amman Jordan Department of Computer Engineering and Electronics Cairo Higher Institute for Engineering Computer Science and Management New Cairo Egypt

Optimizing therapy and rehabilitation for Parkinson's disease (PD) requires early identification and precise evaluation of the illness's course. However, there is disagreement about the best way to use gait analysis to categorize the severity of motor symptoms and identify early-stage Parkinson's disease. The precision of machine learning (ML) models in identifying early and intermediate stages of Parkinson's disease was assessed in this study. Six ML models are used in this study for the prediction of PD. Different metrics are used to evaluate ML models such as accuracy, precision, recall, f1-score, and AUC score. Then we propose a multi-criteria decision-making methodology (MCDM) to evaluate the ML models and select the best one. Two MCDM methods are used such as CRITIC method to compute the criteria weights and the TOPSIS method to rank the alternatives. These methods are used under the bipolar neutrosophic sets (BNSs) to deal with uncertainty information. The results show the support vector machine is the best ML model for the prediction of PD. © 2025, University of New Mexico. All rights reserved.

关键词： Neurodegenerative diseases

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：