检索结果-内蒙古大学图书馆

11th IEEE International Conference on Intelligent computing and Information Systems, ICICIS 2023

作者： Ismail, Mennat-Allah Mohammed, Yasmine Gamal, Nadine Hatem, Maram Ibrahim, Sara Abbas, Esraa Hamdi Mohsen, Mayar Nasser, Maram Ebied, Hala M. Ain Shams University Faculty of Computer and Information Sciences Dept. of Bioinformatics Cairo Egypt Ain Shams University Faculty of Computer and Information Sciences Dept. Bioinformatics Cairo Egypt Ain Shams University Faculty of Computer and Information Sciences Information System Department Cairo Egypt Ain Shams University Faculty of Computer and Information Sciences Scientific Computing Department Cairo Egypt

ISBN: (纸本)9798350322101

Numerous musculoskeletal disorders can be caused by bone diseases, which are widespread. Musculoskeletal conditions are estimated to affect 1.71 billion people worldwide. In addition to musculoskeletal fractures, knee osteoarthritis, fractures, and femoral neck injuries are all relatively prevalent bone illnesses. Missed fractures, on the other hand, are a frequent prognostic failure in accidents and emergencies. As a result, patients' treatment and care are complicated and delayed. Deep Learning (DL) and Artificial Intelligence (AI) are currently garnering a lot of interest for their potential to help physicians identify bone fractures. Studies in traumatology and orthopedics have demonstrated the utility and potential of DL in the radiograph-based diagnosis of fractures and illnesses. In this paper, different classification techniques have been compared to classify the bone. The methods used for detection and segmentation of wrist bones are Inception-v3, VGG16, Densenet-121, and Resnet-50while for elbow bones, Resnet-50, Inception-v3, Densenet-121, and Densenet-169 are used. Two datasets are used in the experiments.: Kaggle dataset and MURA dataset. The experimental results show that the Densenet-169 and Inception-v3 performed better than the other models using MURA dataset and Kaggle dataset respectively. © 2023 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

High-capacity DNA-based steganography

High-capacity DNA-based steganography

引用

2012 8th International Conference on Informatics and Systems, INFOS 2012

作者： Khalifa, Amal Atito, Ahmed Dep. of Scientific Computing Faculty of Computers and Information Sciences Ain Shams University Cairo Egypt Dep. of Mathematics and Computer Science Faculty of Science South Valley University Qena Egypt

ISBN: (纸本)9789774035067

In this paper, a Steganography algorithm is proposed to communicate data securely using basic concepts and properties of the Deoxyribonucleic Acid (DNA). The proposed method is implemented in two main levels: In level one, a DNA-based Playfair cipher is initially applied to encrypt the secret message. In level two;a substitution method is used to hide the encrypted secret message into some reference DNA. That is, the bases of the reference DNA are replaced with the encrypted DNA depending on a generic two-by-two complementary rule. The performance of the presented algorithm is inspected with respect to the Hiding capacity as well as robustness against attacks. © 2012 Cairo University.

关键词： DNA

来源：评论

学校读者我要写书评

暂无评论

Acoustic scattering on arbitrary manifold surfaces

Acoustic scattering on arbitrary manifold surfaces

引用

Geometric Modeling and Processing, GMP 2002

作者： Bajaj, C. Xu, Guoliang Warren, J. Department of Computer Sciences Texas Institute of Computational and Applied Mathematics University of Texas AustinTX78712 United States Institute of Computational Mathematics and Scientific/Engineering Computing Chinese Academy of Sciences Beijing China Department of Computer Science Rice University HoustonTX United States

ISBN: (纸本)0769516742

We propose the use of surface subdivision as adaptive and higher-order boundary elements for solving a Helmholtz partial differential equation to calculate accurate acoustic scattering on arbitrary manifolds. Such acoustic transfer functions prove useful for designing and tuning hearing aid devices for hearing impaired individuals. The number of unknowns of the discretized linear system is the same as that in a linear element approach. Our results show that the accuracy of the subdivision approach is much better than that of the linear element approach. © 2002 IEEE.

关键词： Hearing aids

来源：评论

学校读者我要写书评

暂无评论

A real time dynamic model for optimizing hydrocarbons' production based on deep recurrent network 11

A real time dynamic model for optimizing hydrocarbons' produ...

引用

11th International Conference on computer Engineering and Systems, ICCES 2016

作者： Elons, A.S. Elgendy, M.Y. Magdy, Dalia Ahmed Scientific Computing Department Ain-Shams University Cairo Egypt Research and Development Department Apex Company Cairo Egypt Computer and Information System Department Sadat Academy for Management Sciences Cairo Egypt

ISBN: (纸本)9781509032679

Contrary to common sense that oil and gas products do exist on a constant vertical depth in a specific region, they exist on varying depths in the same region. This fact forces the drilling directions to change deviations to keep track in the production zone 'Pay-Zone'. Drilling a new borehole can be directed by the knowledge of the surrounding already drilled boreholes. Geo-steering process is a real-Time determining for drilling directions based on drilling sensors readings and surrounding boreholes data to maximize oil and gas production inside a new borehole. A previous work was done by us that proposes an initial pre-drilling plan based on sensors measurements of the drilled surrounding boreholes. This work extends it by adding a dynamic adaptation feature for this plan based on the current borehole sensors measurements. This adaptation considers the current borehole previous measurements to re-direct the drilling path to keep track the Pay-Zone. This paper presents Long Short-Term Memory (LSTM) Recurrent Neural Network for modeling the previous sensors measurements sequence to adapt the drilling directions. The dataset consists of 3 groups of boreholes in 3 different Areas, each group consists of 5 boreholes, 4 of them considered as surrounding boreholes for the 5th. Two groups is exploited as training set while the 3rd is used for testing issue. The results shows that LSTM Recurrent network outperforms both the conventional Recurrent Network and Deep Forward Network. The prediction results reached 98% accuracy for the testing data. © 2016 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Using unified parallel C to parallelize the FDTD method of computational electrodynamics

Using unified parallel C to parallelize the FDTD method of c...

引用

IEEE International Conference on Multi Topic

作者： A. Hussain A. Shafi J. Raza The Center for High Performance Scientific Computing Department of Computing NUST School of Electrical Engineering and Computer Sciences Pakistan

This paper discusses a parallel implementation of the finite-difference time-domain (FDTD) method using unified parallel C (UPC). UPC is an extension of ANSI C-primarily designed for programming distributed memory parallel hardware. The FDTD method is a powerful and widely used numerical technique in computational electromagnetics community. It is a resource - CPU cycles and memory-hungry technique. Consequently, a parallel implementation is highly desirable to decrease time-to-solution and be able to study larger problems with limited resources. To the best of our knowledge, this is the first attempt to exploit UPC to parallelize the FDTD method. We evaluate the performance of our implementation on a cluster of four SunFire v890 compute nodes - each equipped with 16 processing cores - and report impressive speedups.

关键词： Finite difference methods Computational electromagnetics Time domain analysis Concurrent computing Message passing Parallel processing High performance computing Parallel programming Hardware Electromagnetic propagation

来源：评论

学校读者我要写书评

暂无评论

Amazigh speech recognition based on the Kaldi ASR toolkit

引用

International Journal of Information Technology (Singapore) 2023年第7期15卷 3533-3540页

作者： Barkani, Fatima Hamidi, Mohamed Laaidi, Naouar Zealouk, Ouissam Satori, Hassan Satori, Khalid Laboratory of Computer Science Signals Automation and Cognitivism Faculty of Sciences Dhar Mahraz University Sidi Mohamed Ben Abdellah Fez Morocco Team of modeling and scientific computing Pluridisciplinary Faculty of Nador Mohammed First University Oujda Morocco

In this work, we offer a new approach to integrating the Amazigh language, which is a less-resourced language, into an isolated speech recognition system by exploiting the Kaldi open-source platform. Our designed system is able to recognize the ten first Amazigh digits and ten daily must-used Amazigh isolated words, which present typical syllabic structure and which are considered a good representative sample of the Amazigh language. The designed speech system was implemented using Hidden Markov Models (HMMs) with different number of Gaussian distributions. In addition, we evaluated our created system performance by varying the feature extraction methods in order to determine the optimal method for maximum performance. The best-obtained result is 93.96% was obtained with Mel Frequency Cepstral Coefficients (MFCCs) technique. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Amazigh language CMU Sphinx4 FBANK GMM HMM Kaldi MFCC PLP Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Text-to-Image Synthesis using Generative Adversarial Networks

Text-to-Image Synthesis using Generative Adversarial Network...

引用

IEEE International Conference on Intelligent computing and Information Systems (ICICIS)

作者： Mostafa Samy Ibrahim Mariam Nabil El-Berry Mohamed Fahmy Tolba Sayed Fadel Bahgat Bachelor of Computer and Information Science Faculty of Computer and Information Sciences-Ain Shams University Lecturer in Scientific Computing Department Faculty of Computer and Information Sciences-Ain Shams University Maryam Scientific Computing Department Faculty of Computer and Information Sciences-Ain Shams University

Text-to-image synthesis is considered a unique problem in image synthesis, which is the task of generating image from input text. Previously, the purpose of text-to-image synthesiswas to match words and images using retrieval methods basedon a phrase or collection of keywords. With the evolution ofdeep learning, particularly the usage of generative models, image synthesis has made potentially significant advancements. One of the most significant generative models are Generative Adversarial Networks (GANs), and they have been widely successfully utilized in various domains. In this study proposes our model, examines and summarizes recent work on GAN-based text-to-image synthesis, as well as providing an overview of the evolution of both classic and cutting-edge models. The usual structure of each category is described in depth. The survey presents a thorough review of the development of GAN-based text to image synthesis. Finally, Dynamic Memory GAN with Contrastive Learning (DMGAN+CL) with prompt engineering, which optimizes and acquires consistent textual representations for captions using the contrastive learning technique. We tested our technique on the CUB-200 dataset, and the findings demonstrate that our framework achieved comparable results with other typical GANs architectures in text-to-image synthesis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MULTILEVEL AUGMENTATION METHODS FOR SOLVING OPERATOR EQUATIONS

引用

Numerical Mathematics(Theory,Methods and Applications) 2005年第1期 31-55页

作者：陈仲英巫斌许跃生 Academy of Mathematics and System Sciences Beijing 100080 Chinese Academy of Sciences Department of Mathematics Department of Scientific Computing and Computer Applications Department of Scientific Computing and computer Applications Guangzhou 510275 NY 13244-1150 PRC. Syracuse University USA/ Institute of Mathematics Zhongshan University

We introduce multilevel augmentation methods for solving operator equations based on direct sum decompositions of the range space of the operator and the solution space of the operator equation and a matrix splitting scheme. We establish a general setting for the analysis of these methods, showing that the methods yield approximate solutions of the same convergence order as the best approximation from the subspace. These augmentation methods allow us to develop fast, accurate and stable nonconventional numerical algorithms for solving operator equations. In particular, for second kind equations, special splitting techniques are proposed to develop such algorithms. These algorithms are then applied to solve the linear systems resulting from matrix compression schemes using wavelet-like functions for solving Fredholm integral equations of the second kind. For this special case, a complete analysis for computational complexity and convergence order is presented. Numerical examples are included to demonstra

关键词： Multilevel augmentation methods operator equations Predholm integral equations of the second kind.

来源：评论

学校读者我要写书评

暂无评论

Two integrable differential-difference equations exhibiting soliton solutions of the Kaup-Kupershmidt equation type

Two integrable differential-difference equations exhibiting ...

引用

作者： Tam, Hon-Wah Hu, Xing-Biao Department of Computer Science Hong Kong Baptist University Kowloon Tong Hong Kong P.O. Box 8730 Beijing 100080 China State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics and Scientific Engineering Computing Academy of Mathematics and Systems Sciences P.O. Box 2719 Beijing 100080 China

Two new integrable differential-difference equations are proposed. By using Hirota's method, 3-soliton solutions of the Kaup-Kupershmidt equation type are obtained with the assistance of Mathematica. Besides, Lax ... 详细信息

关键词： Difference equations

来源：评论

学校读者我要写书评

暂无评论

A hybrid system for three-dimensional objects reconstruction from point-clouds based on ball pivoting algorithm and radial basis functions

引用

WSEAS Transactions on computers 2005年第7期4卷 796-804页

作者： Hussein, Ashraf Scientific Computing Department Faculty of Computer and Information Sciences Ain Shams University Abbassia 11566 Cairo Egypt

In this paper, a new hybrid system for 3D objects reconstruction is presented. This system is based on the well-known Ball Pivoting Algorithm (BPA) of Bernardini et al. combined with the Radial Basis Function (RBF) model. The BPA can reconstruct surfaces from very large data sets in a little execution time, using small amount of memory, and exhibits linear complexity but it produces holes in case of low sampling density besides it is not capable to fill mis-registration domains. So, the BPA is coupled with the RBF in an integrated system to gain the edge of the RBF as a powerful interpolator for generating surface vertices within severe holes and/or mis-registration domains. Performance and accuracy of the system components are investigated through reconstructing benchmark objects. The results obtained compare favorably with other eminent algorithms. Finally, the proposed system exhibited high robustness in reconstructing objects from real large clouds with non-uniform sampling and mis-registrations.

关键词： Image reconstruction

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：