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： Ahmed, Omar Fekry, Sameh Metwally, Abdullah Abdelwahid, Abdelrahman Khattab, Dina Abdulelmagid, Amer Hossieny, Radwa Ain Shams University Faculty of Computer and Information Science Scientific Computing Department Cairo Egypt

ISBN: (纸本)9798350322101

Due to the growing usage of DeepFake technology to produce fake photos and videos, the problem of DeepFake identification has become a serious concern in recent years. With the use of this technology, fake material that is difficult to tell apart from real content may be produced. Therefore, the development of accurate DeepFake detection algorithms is essential to identify and prevent the spread of manipulated content. However, current publicly available DeepFake detection datasets suffer from a lack of diversity, with only a few actors appearing in multiple videos. This results in an oversampled training dataset, leading to model overfitting and inadequate performance when tested on new data. The overfitting problem can cause deep neural networks to focus more on facial features than on specific traits of DeepFake content, thereby reducing the model's ability to generalize. To address this issue and broaden the training dataset's variety, we suggest applying data augmentation methods like Face Cutout and Random Erase. The Face Cutout technique randomly removes a rectangular area of an image containing the face, while the Random Erase technique randomly removes a rectangular area of the image. These techniques introduce variations in the images, making it more challenging for the model to overfit and focus on specific traits of DeepFake content. We evaluated our approach using several models and achieved significant accuracy improvements using the EfficientnetV2B0 model and Random Erase augmentation. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Compiler-Assisted Instrumentation Selection for Large-Scale C++ Codes 37th

Compiler-Assisted Instrumentation Selection for Large-Scale...

引用

37th International Conference on High Performance computing , ISC High Performance 2022

作者： Kreutzer, Sebastian Iwainsky, Christian Lehr, Jan-Patrick Bischof, Christian Scientific Computing Department of Computer Science Technical University of Darmstadt Darmstadt Germany Darmstadt Germany

ISBN: (纸本)9783031232190

Code instrumentation is the primary method for collecting fine-grained performance data. As instrumentation introduces an inherent runtime overhead, it is essential to measure only those regions of the code which are most relevant to the analysis. In practice, the typical approach is to define filter lists manually. Prior projects aim to automate this process using static analysis. Specifically, InstRO enables tailored instrumentation via sophisticated user-defined selection of code regions. However, due to the need for whole-program call-graph analysis, its application on large-scale scientific codes is currently impractical. In this work, we present the new instrumentation tool CaPI (short for "Compiler-assisted Performance Instrumentation"), which is targeted towards such large-scale applications. We demonstrate its application on the CFD framework OpenFOAM. Our evaluation shows that a hybrid approach of CaPI and existing profile-guided filtering outperforms profile-guided filtering alone. Furthermore, we identify correctness and usability issues and propose possible avenues to improve CaPI, as well as compiler-assisted instrumentation tools in general. © 2022, Springer Nature Switzerland AG.

关键词： Static analysis

来源：评论

学校读者我要写书评

暂无评论

A comparative study on dynamic and static sparsity patterns in parallel sparse approximate inverse preconditioning

引用

Journal of Mathematical Modelling and Algorithms 2003年第3期2卷 203-215页

作者： Wang, Kai Kim, Sangbae Zhang, Jun Laboratory for High Performance Scientific Computing and Computer Simulation Department of Computer Science University of Kentucky Lexington KY 40506-0046 United States

Sparse approximate inverse (SAI) techniques have recently emerged as a new class of parallel preconditioning techniques for solving large sparse linear systems on high performance computers. The choice of the sparsity pattern of the SAI matrix is probably the most important step in constructing an SAI preconditioner. Both dynamic and static sparsity pattern selection approaches have been proposed by researchers. Through a few numerical experiments, we conduct a comparable study on the properties and performance of the SAI preconditioners using the different sparsity patterns for solving some sparse linear systems. © 2004 Kluwer Academic Publishers. Printed in the Netherlands.

关键词： Dynamic and static sparsity pattern Parallel preconditioning Sparse approximate inverse Sparse matrices

来源：评论

学校读者我要写书评

暂无评论

Foundation Models for Atomistic Simulation of Chemistry and Materials

arXiv

引用

arXiv 2025年

作者： Yuan, Eric C.-Y. Liu, Yunsheng Chen, Junmin Zhong, Peichen Raja, Sanjeev Kreiman, Tobias Vargas, Santiago Xu, Wenbin Head-Gordon, Martin Yang, Chao Blau, Samuel M. Cheng, Bingqing Krishnapriyan, Aditi Head-Gordon, Teresa Kenneth S. Pitzer Theory Center Department of Chemistry United States Department of Chemical and Biomolecular Engineering United States Electrical Engineering and Computer Science United States Bakar Institute of Digital Materials for the Planet University of California BerkeleyCA94720 United States Chemical Sciences Division United States Applied Mathematics and Computational Research Division United States Energy Technologies Area United States National Energy Research Scientific Computing Center Lawrence Berkeley National Laboratory BerkeleyCA94720 United States

Given the power of large language and large vision models, it is of profound and fundamental interest to ask if a foundational model based on data and parameter scaling laws and pre-training strategies is possible for learned simulations of chemistry and materials. The scaling of large and diverse datasets and highly expressive architectures for chemical and materials sciences should result in a foundation model that is more efficient and broadly transferable, robust to out-of-distribution challenges, and easily fine-tuned to a variety of downstream observables, when compared to specific training from scratch on targeted applications in atomistic simulation. In this Perspective we aim to cover the rapidly advancing field of machine learned interatomic potentials (MLIP), and to illustrate a path to create chemistry and materials MLIP foundation models at larger scale. © 2025, CC BY-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A MOLECULAR WATER PUMP IN QUARTZ DISLOCATIONS

引用

NATURE 1992年第6358期355卷 337-339页

作者： HEGGIE, MI Scientific Computing Group Department of Computer Science University of Exeter Prince of Wales Road Exeter EX4 4PT UK

RECENTLY Bakker and Janssen 1 have reported experiments suggesting that water leaks out of bubbles in quartz preferentially along dislocations against thermodynamic gradients in fugacity, chemical potential and pressure. This effect indicates that the density of gas-rich fluid inclusions cannot be calculated from metamorphic pressure-temperature conditions and, conversely, that the density of the fluid cannot be used to infer metamorphic pressure-temperature conditions. Using computer modelling techniques, I show here that water not only diffuses easily along dislocations in quartz, but can also be 'pumped' along them. The simulations indicate that in dislocation cores, water molecules dissociate and the protons and hydroxyl groups become strongly bound to kinks. A shear stress can do work on kinks to move them along a dislocation, dragging with them these water-bearing species and sweeping other, undissociated water molecules before them.

关键词： science Humanities and Social sciences multidisciplinary

来源：评论

学校读者我要写书评

暂无评论

EEG based epilepsy detection using approximation entropy and different classification strategies 8

EEG based epilepsy detection using approximation entropy and...

引用

8th International Conference on Intelligent computing and Information Systems, ICICIS 2017

作者： Naser, Aya Tantawi, Manal Shedeed, Howida A. Tolba, Mohamed F. Scientific Computing Dept. Faculty of Computer and Information Science Ain Shames University Cairo Egypt

ISBN: (纸本)9772371723

Epilepsy is the 4th prevalent neurological disorder, which distinguishes itself by frequent seizures. These seizures are unprovoked and can be detected by investigating the electroencephalogram (EEG) of the subject. In this paper, an automatic method is proposed to discriminate between normal and epileptic (interictal& ictal) classes. Approximation entropy (APEN) has been utilized as a single informative feature. Multiple classifiers such as: support vector machine (SVM), Probabilistic Neural Network (PNN) and Soft-max regression along with different strategies for classification have been examined. Experiments were carried out by the most popular dataset used in this domain. 96.875%, 53.75% and 65% are the best results achieved by soft-max regression classifier using multi-class strategy for normal, interictal and ictal classes respectively. © 2017 IEEE.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Analyzing Electrooculography (EOG) for Eye Movement Detection 4th

引用

4th International Conference on Advanced Machine Learning Technologies and Applications, AMLTA 2019

作者： Reda, Radwa Tantawi, Manal shedeed, Howida Tolba, Mohamed F. Scientific Computing Department Faculty of Computer and Information Science FCIS-Ain Shams University Cairo Egypt

ISBN: (纸本)9783030141172

Although the cognitive parts of their brains are intact, some individual scan only interact with the outside environment through eye movements. Those people suffer from severe motor disabilities preventing them from moving all their limbs. Recently, Human computer Interfaces (HCI) has emerged to help these people by providing them a new way for communication. These interfaces are based on detecting eye movements. Electro-oculogram (EOG) records eye movements through few electrodes placed around the eyes vertically and horizontally. In this paper, EOG vertical and horizontal signals are analyzed to detect four eye movements (left, right, up and down) along with blinking. Three statistical features are extracted from filtered EOG signals. Extracted features from horizontal and vertical EOG signals are concatenated to form final feature vector. K Nearest Neighbor (KNN), Linear Discriminant Analysis (LDA), Multinomial Logistic Regression (MLR), Naïve Bayes (NB), Decision Trees and Support Vector Machines (SVM) are six classifiers that are evaluated in this study. The results reveal the superiority of SVM Classifier in providing the best average accuracy. © 2020, Springer Nature Switzerland AG.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Composition and Perception beyond Photorealism 5

Composition and Perception beyond Photorealism

引用

5th Joint Symposium on Computational Aesthetics, Sketch-Based Interfaces and Modeling, and Non-Photorealistic Animation and Rendering, Expressive 2016

作者： Ji, Li Wyvill, Brian Gammon, Lynda Gooch, Amy Department of Computer Science Department of Visual Arts University of Victoria Scientific Computing and Imaging University of Utah

ISBN: (纸本)9783038680215

Composition is an important aestheic aspect of celebrated works of art, and we examine a few common compositional techniques in the context of computer graphics rendering and perception. In computer graphics, photorealistic rendering simulates a camera, which defines an image of a scene in a single instant after the shutter is released. In contrast, a human observer looks at one part of a scene at a time and stitches a series of visual memories together to form a complete impression of the scene. This perception process is related to visual composition, in which an artist selectively articulates and suppresses details to direct the viewers' eyes. In non-photorealistic rendering research, painting is an important source of examples for stylized rendering. We discuss the importance of painting's specific presentation conditions, and how painting composition takes effect through a viewer's attentive looking. Based on these analysis, we demonstrate how to apply knowledge of composition to digital image synthesis with an interpolative material model and a staged photography art project. © 2016 The Author(s) Eurographics Proceedings © 2016 The Eurographics Association.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Ensuring numerical quality in grid computing

Ensuring numerical quality in grid computing

引用

12th GAMM-IMACS International Symposium on scientific computing, computer Arithmetic and Validated Numerics, SCAN 2006

作者： Frommer, Andreas Hüsken, Matthias Bergische Universität Wuppertal Applied Computer Science and Scientific Computing D-42097 Wuppertal Germany

ISBN: (纸本)076952821X

Certain numerically intensive applications executed within a grid computing environment crucially depend on the properties of floating-point arithmetic implemented on the respective platform. Differences in these properties may have drastic effects. This paper identifies the central problems related to this situation. We propose an approach which gives the user valuable information on the various platforms available in a grid computing environment in order to assess the numerical quality of an algorithm run on each of these platforms. In this manner, the user will at least have very strong hints whether a program will perform reliably in a grid before actually executing it. Our approach extends the existing IeeeCC754 test suite by two "grid-enabled" modes: The first mode calculates a "numerical checksum" on a specific grid host and executes the job only if the checksum is identical to a locally generated one. The second mode provides the user with information on the reliability and IEEE 754-conformity of the underlying floating-point implementation of various platforms. Furthermore, it can help to find a set of compiler options to optimize the application's performance while retaining numerical stability.

关键词： Digital arithmetic

来源：评论

学校读者我要写书评

暂无评论

Eye Movements Recognition Using Electrooculography Signals 1st

Eye Movements Recognition Using Electrooculography Signals

引用

1st International Conference on Artificial Intelligence and computer Visions, AICV 2020

作者： Reda, Radwa Tantawi, Manal Shedeed, Howida Tolba, Mohamed F. Scientific Computing Department Faculty of Computer and Information Science FCIS Ain Shams University Cairo Egypt

ISBN: (纸本)9783030442880

Nowadays, the number of people who suffer from severe motor disabilities is increasing remarkably. This disability gradually prevents them from moving all their limbs and they can communicate with their external environment only through the movement of their eyes. Hence, Human computer Interfaces (HCI) have come out to provide those people with new communication way based on detecting eye movements. Eye movements are recorded by Electrooculogram (EOG). These signals are captured by placing electrodes horizontally and vertically around the eyes. In this work, the five eye movements left, right, up, down and blinking are classified by investigating both horizontal and vertical EOG signals. Statistical and geometrical features are extracted from EOG signals after applying Discrete Wavelet Transform (DWT). Six classifiers are examined in this study using both horizontal and vertical EOG features. The experimental results show the superiority of Naïve Bayes classifier. © 2020, Springer Nature Switzerland AG.

关键词： Discrete wavelet transforms

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：