检索结果-内蒙古大学图书馆

IEEE International Conference on High Performance Computing Workshops (HiPCW)

作者： Mayank Arya Yogesh Simmhan Department of Computational and Data Sciences Indian Institute of Science Bangalore India

ISBN: (数字)9798331509118

ISBN: (纸本)9798331509125

Large Language Models (LLMs) have revolutionized machine learning by efficiently handling tasks like translation, text generation, summarization, and classification, making them ideal for applications such as virtual assistants and agentic workflows. However, their substantial computational requirements limit their wide adoption, particularly for smaller organizations lacking the computing infrastructure. Current LLM serving is done on the cloud, which imposes cost, latency and privacy concerns. Cloud–edge collaboration also struggles with network bottlenecks and model partitioning complexities. This work explores the potential for using edge accelerators, like Nvidia’s Jetson, for LLM inference. These compact devices have 100–1000s of GPU cores and 10+GB of shared GPU memory, allowing real-time edge inference close to the data source. We analyze and evaluate the efficiency of edge devices for LLM inference for different models and power modes, and make a case for tuning power modes to reduce power usage by ≈4–6% while matching the throughput of the highest performance mode.

关键词： Cloud computing Privacy Translation computational modeling Virtual assistants Soft sensors Graphics processing units Throughput Real-time systems Tuning

来源：评论

学校读者我要写书评

暂无评论

Real-World Wireless Network Modeling and Optimization:From Model/data-Driven Perspective

引用

Chinese Journal of Electronics 2022年第6期31卷 991-1012页

作者： LI Yang ZHANG Shutao REN Xiaohui ZHU Jianhang HUANG Jiajie HE Pengcheng SHEN Kaiming YAO Zhiqiang GONG Jie CHANG Tsunghui SHI Qingjiang LUO Zhiquan Shenzhen Research Institute of Big Data Pengcheng Lab School of Science and Engineering The Chinese University of Hong Kong (Shenzhen) College of Mathematics and Computational Sciences Xiangtan University School of Computer Science and Engineering Sun Yat-Sen University School of Software Engineering Tongji University

With the rapid development of the fifth-generation wireless communication systems, a profound revolution in terms of transmission capacity, energy efficiency, reliability, latency, and connectivity is highly expected to support a new batch of industries and applications. To achieve this goal, wireless networks are becoming extremely dynamic, heterogeneous, and complex. The modeling and optimization for the performance of realworld wireless networks are extremely challenging due to the difficulty to predict the network performance as a function of network parameters, and the prohibitively huge number of parameters to optimize. The conventional network modeling and optimization approaches rely on drive test, trial-and-error, and engineering experience,which are labor intensive, error-prone, and far from optimal. On the other hand, while the research community has spent significant efforts in understanding the fundamental limits of radio channels and developing physical layer techniques to operate close to it, very little is known about the performance limits of wireless networks, where millions of radio channels interact with one another in complex manners. This paper reviews the very recent mathematical and learning based techniques for modeling and optimizing the performance of real-world wireless networks in five aspects, including channel modeling, user demand and traffic modeling, throughput modeling and prediction, network parameter optimization, and IRS empowered performance optimization, and also presents the corresponding notable performance gains.

关键词： network parameter optimization telecommunication computing optimisation mathematical techniques wireless channels performance optimization learning based techniques telecommunication traffic mathematical analysis physical layer techniques channel modeling wireless network modeling fifth generation wireless communication systems learning (artificial intelligence) model-data-driven perspective IRS empowered performance optimization radio channels traffic modeling radio networks

来源：评论

学校读者我要写书评

暂无评论

An efficient wavelet-based physics-informed neural networks for singularly perturbed problems

arXiv

引用

arXiv 2024年

作者： Pandey, Himanshu Singh, Anshima Behera, Ratikanta Department of Computational and Data Sciences Indian Institute of Science Bangalore India

Physics-informed neural networks (PINNs) are a class of deep learning models that utilize physics in the form of differential equations to address complex problems, including ones that may involve limited data availability. However, tackling solutions of differential equations with rapid oscillations, steep gradients, or singular behavior becomes challenging for PINNs. Considering these challenges, we designed an efficient wavelet-based PINNs (W-PINNs) model to address this class of differential equations. Here, we represent the solution in wavelet space using a family of smooth-compactly supported wavelets. This framework represents the solution of a differential equation with significantly fewer degrees of freedom while still retaining the dynamics of complex physical phenomena. The architecture allows the training process to search for a solution within the wavelet space, making the process faster and more accurate. Further, the proposed model does not rely on automatic differentiations for derivatives involved in differential equations and does not require any prior information regarding the behavior of the solution, such as the location of abrupt features. Thus, through a strategic fusion of wavelets with PINNs, W-PINNs excel at capturing localized nonlinear information, making them well-suited for problems showing abrupt behavior in certain regions, such as singularly perturbed and multiscale problems. The efficiency and accuracy of the proposed neural network model are demonstrated in various 1D and 2D test problems, i.e., the FitzHugh-Nagumo (FHN) model, the Helmholtz equation, the Maxwell equation, and the Allen-Cahn equation, along with other highly singularly perturbed nonlinear differential equations. The proposed model significantly improves with traditional PINNs, recently developed wavelet-based PINNs, and other state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Maxwell equations

来源：评论

学校读者我要写书评

暂无评论

Facial Image-Based Autism Detection:A Comparative Study of Deep Neural Network Classifiers

引用

computers, Materials & Continua 2024年第1期78卷 105-126页

作者： Tayyaba Farhat Sheeraz Akram Hatoon SAlSagri Zulfiqar Ali Awais Ahmad Arfan Jaffar Faculty of Computer Science and Information Technology The Superior UniversityLahore54600Pakistan Intelligent Data Visual Computing Research(IDVCR) Faculty of Computer Science and Information TechnologyThe Superior UniversityLahore54600Pakistan Information Systems Department College of Computer and Information SciencesImam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh12571Saudi Arabia School of Computer Science and Electronic Engineering(CSEE) University of EssexWivenhoe ParkColchesterCO43SQUK

Autism Spectrum Disorder(ASD)is a neurodevelopmental condition characterized by significant challenges in social interaction,communication,and repetitive *** and precise ASD detection is crucial,particularly in regions with limited diagnostic resources like *** study aims to conduct an extensive comparative analysis of various machine learning classifiers for ASD detection using facial images to identify an accurate and cost-effective solution tailored to the local *** research involves experimentation with VGG16 and MobileNet models,exploring different batch sizes,optimizers,and learning rate *** addition,the“Orange”machine learning tool is employed to evaluate classifier performance and automated image processing capabilities are utilized within the *** findings unequivocally establish VGG16 as the most effective classifier with a 5-fold cross-validation ***,VGG16,with a batch size of 2 and the Adam optimizer,trained for 100 epochs,achieves a remarkable validation accuracy of 99% and a testing accuracy of 87%.Furthermore,the model achieves an F1 score of 88%,precision of 85%,and recall of 90% on test *** validate the practical applicability of the VGG16 model with 5-fold cross-validation,the study conducts further testing on a dataset sourced fromautism centers in Pakistan,resulting in an accuracy rate of 85%.This reaffirms the model’s suitability for real-world ASD *** research offers valuable insights into classifier performance,emphasizing the potential of machine learning to deliver precise and accessible ASD diagnoses via facial image analysis.

关键词： Autism Autism Spectrum Disorder(ASD) disease segmentation features optimization deep learning models facial images classification

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Automatic Translation of Text to Sign Language

引用

computers, Materials & Continua 2022年第2期70卷 2471-2488页

作者： Muhammad Sanaullah Babar Ahmad Muhammad Kashif Tauqeer Safdar Mehdi Hassan Mohd Hilmi Hasan Norshakirah Aziz Department of Computer Science Bahauddin Zakariya UniversityMultan60000Pakistan Department of Computer Science Air UniversityMultan60000Pakistan Department of Computer Science Air UniversityIslamabad44000Pakistan Centre for Research in Data Science Department of Computer and Information SciencesUniversitiTeknologi PETRONASSeri Iskandar32610PerakMalaysia

Communication is a basic need of every human being;by this,they can learn,express their feelings and exchange their ideas,but deaf people cannot listen and *** communication,they use various hands gestures,also known as Sign Language(SL),which they learn from special *** normal people have not taken SL classes;therefore,they are unable to perform signs of daily routine sentences(e.g.,what are the specifications of this mobile phone?).A technological solution can facilitate in overcoming this communication gap by which normal people can communicate with deaf *** paper presents an architecture for an application named Sign4PSL that translates the sentences to Pakistan Sign Language(PSL)for deaf people with visual representation using virtual signing *** research aims to develop a generic independent application that is lightweight and reusable on any platform,including web and mobile,with an ability to perform offline text *** Sign4PSL relies on a knowledge base that stores both corpus of PSL Words and their coded form in the notation ***4PSL takes English language text as an input,performs the translation to PSL through sign language notation and displays gestures to the user using virtual *** system is tested on deaf students at a special *** results have shown that the students were able to understand the story presented to them appropriately.

关键词： Sign language sign markup language deaf communication hamburg notations machine translation

来源：评论

学校读者我要写书评

暂无评论

Image Fusion Using Wavelet Transformation and XGboost Algorithm

引用

computers, Materials & Continua 2024年第4期79卷 801-817页

作者： Shahid Naseem Tariq Mahmood Amjad Rehman Khan Umer Farooq Samra Nawazish Faten S.Alamri Tanzila Saba Department of Information Sciences Division of S&TUniversity of EducationLahore54770Pakistan Artificial Intelligence and Data Analytics(AIDA)Lab CCIS Prince Sultan UniversityRiyadh11586Saudi Arabia Faculty of Information Sciences University of EducationVehari CampusVehari61100Pakistan Department of Computer Science University of Engineering and TechnologyTaxila47050Pakistan Department of Mathematical Sciences College of SciencePrincess Nourah Bint Abdulrahman UniversityRiyadh84428Saudi Arabia

Recently,there have been several uses for digital image *** fusion has become a prominent application in the domain of imaging *** create one final image that provesmore informative and helpful compared to the original input images,image fusion merges two or more initial images of the same *** fusion aims to produce,enhance,and transform significant elements of the source images into combined images for the sake of human visual *** fusion is commonly employed for feature extraction in smart robots,clinical imaging,audiovisual camera integration,manufacturing process monitoring,electronic circuit design,advanced device diagnostics,and intelligent assembly line robots,with image quality varying depending on *** research paper presents various methods for merging images in spatial and frequency domains,including a blend of stable and curvelet transformations,everageMax-Min,weighted principal component analysis(PCA),HIS(Hue,Intensity,Saturation),wavelet transform,discrete cosine transform(DCT),dual-tree Complex Wavelet Transform(CWT),and multiple wavelet *** fusion methods integrate data from several source images of an identical target,thereby enhancing information in an extremely efficient *** precisely,in imaging techniques,the depth of field constraint precludes images from focusing on every object,leading to the exclusion of certain *** tackle thess challanges,a very efficient multi-focus wavelet decomposition and recompositionmethod is *** use of these wavelet decomposition and recomposition techniques enables this method to make use of existing optimized wavelet code and filter *** simulated outcomes provide evidence that the suggested approach initially extracts particular characteristics from images in order to accurately reflect the level of clarity portrayed in the original *** study enhances the performance of the eXtreme Gradient Boosting(XGBoos

关键词： Image fusion max-min average CWT XGBoost DCT inclusive innovations spatial and frequency domain

来源：评论

学校读者我要写书评

暂无评论

CapsNet-FR: Capsule Networks for Improved Recognition of Facial Features

引用

computers, Materials & Continua 2024年第5期79卷 2169-2186页

作者： Mahmood Ul Haq Muhammad Athar Javed Sethi Najib Ben Aoun Ala Saleh Alluhaidan Sadique Ahmad Zahid farid Department of Computer System Engineering University of Engineering&TechnologyPeshawar25000Pakistan College of Computer Science and Information Technology Al-Baha UniversityAlaqiq65779-7738Saudi Arabia REGIM-Lab:Research Groups in Intelligent Machines National School of Engineers of Sfax(ENIS)University of SfaxSfax3038Tunisia Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh84428Saudi Arabia EIAS:Data Science and Blockchain Laboratory College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia Department of Computer Sciences Bahria University Karachi CampusKarachi541004Pakistan Department of Electrical Engineering Abasyn UniversityPeshawar25000Pakistan

Face recognition (FR) technology has numerous applications in artificial intelligence including biometrics, security,authentication, law enforcement, and surveillance. Deep learning (DL) models, notably convolutional neuralnetworks (CNNs), have shown promising results in the field of FR. However CNNs are easily fooled since theydo not encode position and orientation correlations between features. Hinton et al. envisioned Capsule Networksas a more robust design capable of retaining pose information and spatial correlations to recognize objects morelike the brain does. Lower-level capsules hold 8-dimensional vectors of attributes like position, hue, texture, andso on, which are routed to higher-level capsules via a new routing by agreement algorithm. This provides capsulenetworks with viewpoint invariance, which has previously evaded CNNs. This research presents a FR model basedon capsule networks that was tested using the LFW dataset, COMSATS face dataset, and own acquired photos usingcameras measuring 128 × 128 pixels, 40 × 40 pixels, and 30 × 30 pixels. The trained model outperforms state-ofthe-art algorithms, achieving 95.82% test accuracy and performing well on unseen faces that have been blurred orrotated. Additionally, the suggested model outperformed the recently released approaches on the COMSATS facedataset, achieving a high accuracy of 92.47%. Based on the results of this research as well as previous results, capsulenetworks perform better than deeper CNNs on unobserved altered data because of their special equivarianceproperties.

关键词： CapsNet face recognition artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

An asynchronous discontinuous Galerkin method for massively parallel PDE solvers

arXiv

引用

arXiv 2024年

作者： Goswami, Shubham K. Aditya, Konduri Department of Computational and Data Sciences Indian Institute of Science Bengaluru India

The discontinuous Galerkin (DG) method is widely being used to solve hyperbolic partial differential equations (PDEs) due to its ability to provide high-order accurate solutions in complex geometries, capture discontinuities, and exhibit high arithmetic intensity. However, the scalability of DG-based solvers is impeded by communication bottlenecks arising from the data movement and synchronization requirements at extreme scales. To address these challenges, recent studies have focused on the development of asynchronous computing approaches for PDE solvers. Herein, we introduce the asynchronous DG (ADG) method, which combines the benefits of the DG method with asynchronous computing to overcome communication bottlenecks. The ADG method relaxes the need for data communication and synchronization at a mathematical level, allowing processing elements to operate independently regardless of the communication status, thus potentially improving the scalability of solvers. The proposed ADG method ensures flux conservation and effectively addresses challenges arising from asynchrony. To assess its stability, Fourier-mode analysis is employed to examine the dissipation and dispersion behavior of fully-discrete equations that use the DG and ADG schemes along with the Runge-Kutta (RK) time integration scheme. Furthermore, an error analysis within a statistical framework is presented, which demonstrates that the ADG method with standard numerical fluxes achieves at most first-order accuracy. To recover accuracy, we introduce asynchrony-tolerant (AT) fluxes that utilize data from multiple time levels. Extensive numerical experiments were conducted to validate the performance of the ADG-AT scheme for both linear and nonlinear problems. Overall, the proposed ADG-AT method demonstrates the potential to achieve accurate and scalable DG-based PDE solvers, paving the way for simulations of complex physical systems on massively parallel supercomputers. © 2024, CC BY-NC-ND.

关键词： Runge Kutta methods

来源：评论

学校读者我要写书评

暂无评论

Co-linear Chaining with Overlaps and Gap Costs 26th

Co-linear Chaining with Overlaps and Gap Costs

引用

26th International Conference on Research in computational Molecular Biology, RECOMB 2022

作者： Jain, Chirag Gibney, Daniel Thankachan, Sharma V. Department of Computational and Data Sciences Indian Institute of Science Bangalore India School of Computer Science and Engineering Georgia Institute of Technology Atlanta United States Department of Computer Science University of Central Florida Orlando United States

ISBN: (纸本)9783031047480

Co-linear chaining has proven to be a powerful heuristic for finding near-optimal alignments of long DNA sequences (e.g., long reads or a genome assembly) to a reference. It is used as an intermediate step in several alignment tools that employ a seed-chain-extend strategy. Despite this popularity, efficient subquadratic-time algorithms for the general case where chains support anchor overlaps and gap costs are not currently known. We present algorithms to solve the co-linear chaining problem with anchor overlaps and gap costs in O~ (n) time, where n denotes the count of anchors. We also establish the first theoretical connection between co-linear chaining cost and edit distance. Specifically, we prove that for a fixed set of anchors under a carefully designed chaining cost function, the optimal ‘anchored’ edit distance equals the optimal co-linear chaining cost. Finally, we demonstrate experimentally that optimal co-linear chaining cost under the proposed cost function can be computed orders of magnitude faster than edit distance, and achieves correlation coefficient above 0.9 with edit distance for closely as well as distantly related sequences. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Anchors

来源：评论

学校读者我要写书评

暂无评论

PAD: A Robustness Enhancement Ensemble Method via Promoting Attention Diversity 30

PAD: A Robustness Enhancement Ensemble Method via Promoting ...

引用

Joint 30th International Conference on computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Yang, Yuting Huang, Pei Ma, Feifei Cao, Juan Li, Jintao China University of Chinese Academy of Sciences China Department of Computer Science Stanford University United States State Key Laboratory of Computer Science Institute of Software CAS China Laboratory of Parallel Software and Computational Science Institute of Software CAS China

ISBN: (纸本)9782493814104

Deep neural networks can be vulnerable to adversarial attacks, even for the mainstream Transformer-based models. Although several robustness enhancement approaches have been proposed, they usually focus on some certain type of perturbation. As the types of attack can be various and unpredictable in practical scenarios, a general and strong defense method is urgently in require. We notice that most well-trained models can be weakly robust in the perturbation space, i.e., only a small ratio of adversarial examples exist. Inspired by the weak robust property, this paper presents a novel ensemble method for enhancing robustness. We propose a lightweight framework PAD to save computational resources in realizing an ensemble. Instead of training multiple models, a plugin module is designed to perturb the parameters of a base model which can achieve the effect of multiple models. Then, to diversify adversarial example distributions among different models, we promote each model to have different attention patterns via optimizing a diversity measure we defined. Experiments on various widely-used datasets and target models show that PAD can consistently improve the defense ability against many types of adversarial attacks while maintaining accuracy on clean data. Besides, PAD also presents good interpretability via visualizing diverse attention patterns. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Deep neural networks

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：