检索结果-内蒙古大学图书馆

Minimizing Number of Nodes in Decision Trees with Hypotheses

Procedia computer science 2021年 192卷 232-240页

作者： Mohammad Azad Igor Chikalov Shahid Hussain Mikhail Moshkov Jouf University College of Computer and Information Sciences Department of Computer Science Sakaka 72441 Saudi Arabia Intel Corporation 5000 W Chandler Blvd Chandler AZ 85226 USA Habib University Dhanani School of Science and Engineering Computer Science Program Karachi 75290 Pakistan King Abdullah University of Science and Technology (KAUST) Computer Electrical and Mathematical Sciences & Engineering Division Thuwal 23955-6900 Saudi Arabia

In this paper, we consider decision trees that use both conventional queries based on one attribute each and queries based on hypotheses about values of all attributes. This approach is similar to one studied in exact learning, where membership and equivalence queries are considered. We propose dynamic programming algorithms for the minimization of the number of nodes in such decision trees and discuss results of computer experiments.

关键词： Decision tree Hypothesis Number of nodes

来源：评论

学校读者我要写书评

暂无评论

S3Attention: Improving Long Sequence Attention with Smoothed Skeleton Sketching

arXiv

引用

arXiv 2024年

作者： Wang, Xue Zhou, Tian Zhu, Jianqing Liu, Jialin Yuan, Kun Yao, Tao Yin, Wotao Jin, Rong Cai, Han Qin Alibaba Group BellevueWA98004 United States Computer Electrical and Mathematical Science and Engineering Division King Abdullah University of Science and Technology Thuwal23955 Saudi Arabia Department of Statistics and Data Science University of Central Florida OrlandoFL32816 United States Center for Machine Learning Research Peking University Beijing100871 China Antai College of Economics and Management Shanghai Jiao Tong University Shanghai200030 China Meta Menlo ParkCA94025 United States Department of Statistics and Data Science Department of Computer Science University of Central Florida OrlandoFL32816 United States

Attention based models have achieved many remarkable breakthroughs in numerous applications. However, the quadratic complexity of Attention makes the vanilla Attention based models hard to apply to long sequence tasks. Various improved Attention structures are proposed to reduce the computation cost by inducing low rankness and approximating the whole sequence by sub-sequences. The most challenging part of those approaches is maintaining the proper balance between information preservation and computation reduction: the longer sub-sequences used, the better information is preserved, but at the price of introducing more noise and computational costs. In this paper, we propose a smoothed skeleton sketching based Attention structure, coined S3Attention, which significantly improves upon the previous attempts to negotiate this trade-off. S3Attention has two mechanisms to effectively minimize the impact of noise while keeping the linear complexity to the sequence length: a smoothing block to mix information over long sequences and a matrix sketching method that simultaneously selects columns and rows from the input matrix. We verify the effectiveness of S3Attention both theoretically and empirically. Extensive studies over Long Range Arena (LRA) datasets and six time-series forecasting show that S3Attention significantly outperforms both vanilla Attention and other state-of-the-art variants of Attention structures. Copyright © 2024, The Authors. All rights reserved.

关键词： Musculoskeletal system

来源：评论

学校读者我要写书评

暂无评论

A Transfer Learning-Based Intelligent Judiciary System for Public Safety

A Transfer Learning-Based Intelligent Judiciary System for P...

引用

Communications, Computing, Cybersecurity, and Informatics (CCCI), International Conference on

作者： Lakshin Pathak Mili Virani Mohammad S. Obaidat Prachita Patel Jigna J. Hathaliya Nilesh Kumar Jadav Sudeep Tanwar Nagendar Yamsani Dept.of CSE Nirma University Ahmedabad India King Abdullah II School of Information Technology The University of Jordan Amman Jordan School of Computer & Communication Engineering University of Science and Technology Beijing Beijing China Department of Computational Intelligence School of Computing SRM University TN India School of Engineering The Amity University Noida UP India Dept. of CE-AI Marwadi University Rajkot India Department of CS & AI SR University Telangana India

ISBN: (数字)9798350349832

ISBN: (纸本)9798350349849

With the increasing prevalence of criminal activities, there is a growing need for effective crime detection methods leveraging modern technologies, such as artificial intelligence (AI), the Internet of Things (IoT), and cloud computing. In this paper, we propose a transfer learning (TL)-based solution for criminal face detection using convolutional neural networks (CNNs) to improve public safety. Leveraging pre-trained CNN models, we fine-tune them on a dataset comprising images of known criminals and non-criminals. The proposed framework aims to mitigate the challenges associated with training CNNs from scratch, such as data scarcity and computational inefficien-cies. Experimental results demonstrate the effectiveness of the proposed framework in accurately identifying criminal faces, showcasing its potential for enhancing law enforcement efforts. We achieved the highest accuracy of 97% with the TL scheme.

关键词： Training Analytical models Accuracy Law enforcement Computational modeling Public security Convolutional neural networks Internet of Things Artificial intelligence Faces

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Assisted Secure and Trusted Ticketing System for Outsourced Premier League

Blockchain-Assisted Secure and Trusted Ticketing System for ...

引用

Communications, Computing, Cybersecurity, and Informatics (CCCI), International Conference on

作者： Sapan Anupkumar Shah Shanika Soni Mohammad S. Obaidat Nilesh Kumar J Adav Jigna J. Hathaliya Sudeep Tanwar Nagendar Yamsani Dept. of CSE Nirma University Ahmedabad India King Abdullah II School of Information Technology The University of Jordan Amman Jordan School of Computer & Communication Engineering University of Science and Technology Beijing Beijing China Department of Computational Intelligence School of Computing SRM University TN India School of Engineering The Amity University Noida UP India Dept. of CE-AI Marwadi University Rajkot India Department of CS & AI SR University Telangana India

ISBN: (数字)9798350349832

ISBN: (纸本)9798350349849

The integration of advanced analytics and real-time data has significantly enhanced the performance and strategic decision-making in the outsource premier league. But the major challenge is to get the ticket and to see the match in the stadium. Buying the ticket at the normal price or at the regular price is now another challenge for entering the Stadium. The inflated price of tickets and corruption are increasing day by day. Due to this, most people either do not buy the ticket and watch the match or need to pay more than the desired price. To address the aforementioned issue, we have implemented a blockchain-based Indian Premier League (IPL) ticket management system to mitigate the price manipulation of IPL tickets. Moreover, the proposed approach ensures the privacy and security of transactions and wallets and prevents price manipulation fraud by leveraging blockchain. The open and transparent nature of blockchain helps IPL fans securely get tickets at regular prices. We implemented and tested smart contract functions using the Sepolia test network. Additionally, we integrated the MetaMask wallet to realize the virtual money flow of different smart contract functions. Next, we analyzed transactions using EtherScan, which helps visualize transaction history. Moreover, the performance of the proposed approach is calculated using the transaction and execution cost of each smart contract function.

关键词： Privacy Costs Smart contracts Real-time systems Mathematical models Blockchains Telecommunication computing Fraud History Informatics

来源：评论

学校读者我要写书评

暂无评论

DESTRESS: Computation-Optimal and Communication-Efficient Decentralized Nonconvex Finite-Sum Optimization

arXiv

引用

arXiv 2021年

作者： Li, Boyue Li, Zhize Chi, Yuejie Department of Electrical and Computer Engineering Carnegie Mellon University PittsburghPA15213 United States Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal 23955-6900 Saudi Arabia

Emerging applications in multi-agent environments such as internet-of-things, networked sensing, autonomous systems and federated learning, call for decentralized algorithms for finite-sum optimizations that are resource-efficient in terms of both computation and communication. In this paper, we consider the prototypical setting where the agents work collaboratively to minimize the sum of local loss functions by only communicating with their neighbors over a predetermined network topology. We develop a new algorithm, called DEcentralized STochastic REcurSive gradient methodS (DESTRESS) for nonconvex finite-sum optimization, which matches the optimal incremental first-order oracle (IFO) complexity of centralized algorithms for finding first-order stationary points, while maintaining communication efficiency. Detailed theoretical and numerical comparisons corroborate that the resource efficiencies of DESTRESS improve upon prior decentralized algorithms over a wide range of parameter regimes. DESTRESS leverages several key algorithm design ideas including randomly activated stochastic recursive gradient updates with mini-batches for local computation, gradient tracking with extra mixing (i.e., multiple gossiping rounds) for per-iteration communication, together with careful choices of hyper-parameters and new analysis frameworks to provably achieve a desirable computation-communication trade-off. © 2021, CC BY.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Human body communication transceivers

Nature Reviews Electrical Engineering

引用

Nature Reviews electrical engineering 2025年 1-16页

作者： Qi Huang Shreyas Sen Abdelhay Ali Abdulkadir Celik Gianluca Setti Khaled N. Salama Ahmed M. Eltawil Jaafar Elmirghani Noha Al-Harthi Mohammed E. Fouda Department of Electrical and Computer Engineering Purdue University West Lafayette IN USA Electrical and Computer Engineering at King Abdullah University of Science and Technology Thuwal Saudi Arabia Neom Saudi Arabia Compumacy for Artificial Intelligence Solutions Cairo Egypt

Although advances in medical technology have facilitated access to treatments and preventative protocols, health care remains constrained by frequent, multiple doctor visits, disrupting daily routines and burdening medical infrastructure. The Internet of Bodies offers a transformative solution by integrating wearable, implantable, ingestible and injectable devices in, on and around the body and thus enabling seamless connectivity in biomedical applications. Since the term was first introduced in the mid-1990s, the Internet of Bodies has made notable progress owing to advances in miniaturized electronics, flexible substrates and low-power design. A critical component of this development is the introduction of human body communication (HBC), which uses the human body as a transmission medium. By replacing the radio front-end with simple direct skin interfaces, sensing and communication modules become smaller, lighter, more energy-efficient and accessible. In this Review, we focus on the role of HBC transceivers for next-generation health-care and body-area networks. We discuss the fundamental principles of HBC, including signal propagation, channel modelling and performance trade-offs. Key design challenges such as dynamic channel variations, skin–electrode interfaces, interference, safety regulations and energy efficiency are analysed. Additionally, we explore the circuit design techniques that affect HBC performance and adaptability. Advancements in miniaturized electronics, low-power design and deep-learning-driven transceiver architectures are needed to further unlock the potential of HBC systems, paving the way for their widespread adoption in personalized health-care and secure body-centric communication systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RAKI:A Robust ECC Based Three-party Authentication and Key Agreement Scheme for Medical IoT

RAKI:A Robust ECC Based Three-party Authentication and Key A...

引用

GLOBECOM 2022 - 2022 IEEE Global Communications Conference

作者： Yousheng Zhou Lunhao Li Mohammad S. Obaidat Yuanni Liu P. Vijayakumar Kuei-Fang Hsiao School of Cyber Security and Information Law Chongqing University of Posts and Telecommunications Chongqing China Department of Computer Science and Engineering Indian Institute of Technology Dhanbad India King Abdullah II School of Information Technology University of Jordan Amman Jordan School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China Department of Computer Science & Engineering University College of Engineering Tindivanam Tindivanam India Information Systems Department University of Sharjah Shrajah UAE

ISBN: (纸本)9781665435413

With its advantages are gradually emerging, the Internet of Things (IoT) is profoundly changing the way people work and live. Among all IoT applications, medical IoT is partic-ularly important, in which the user can communicate with smart medical device through the hospital gateway node. However, due to the inherent defects of these smart devices and the openness of wireless networks, medical IoT is vulnerable to kinds of attacks, such as impersonation attack and password guessing attack. Unfortunately, there are few authentication schemes for medical IoT at present, while existing three-party schemes have various weakness and are not suitable for medical IoT. Given the sensitivity of patient data and the deadly consequences of attacks on medical devices, there is an urgent need to develop a suitable authentication scheme in Medical IoT Network with high security. To alleviate the above problems, a robust ECC based three-party authentication and key agreement scheme for medical IoT(RAKI) has been proposed, which is secure with random oracle model and the informal security analysis. Besides, the performance comparisons against existing competing three-party schemes indicate that our scheme is efficient for medical IoT.

关键词： Medical devices Sensitivity Protocols Wireless networks Authentication Resists Passwords

来源：评论

学校读者我要写书评

暂无评论

Retraction Note: Unlocking the power of recalling enhanced recurrent neural network: channel estimation and data analysis for 5G MIMO communication system

引用

Optical and Quantum Electronics 2024年第11期56卷 1-2页

作者： Alqahtani, abdullah Saleh Pathak, Pankaj Pandiaraj, Saravanan Indrapriyadarsini, H. Arun Kumar, U. Nataraju, Susheela Department of Self-Development Skills-IT CFY Deanship King Saud University Riyadh Saudi Arabia Symbiosis Institute of Digital and Telecom Management (SIDTM) Symbiosis International (Deemed University) Lavale Pune India Department of Electronics and Communication Engineering Karpagam Institute of Technology Coimbatore India Department of Electrical and Electronics Engineering Faculty of Engineering Karpagam Academy of Higher Education (Deemed to Be University) Coimbatore India Department of Computer Science Engineering G Madegowda Institute of Technology Bharathinagara (K M Doddi) India

来源：评论

学校读者我要写书评

暂无评论

Hardware implementation of memristor-based artificial neural networks

引用

Nature Communications 2024年第1期15卷 1974页

作者： Aguirre, Fernando Sebastian, Abu Le Gallo, Manuel Song, Wenhao Wang, Tong Yang, J. Joshua Lu, Wei Chang, Meng-Fan Ielmini, Daniele Yang, Yuchao Mehonic, Adnan Kenyon, Anthony Villena, Marco A. Roldán, Juan B. Wu, Yuting Hsu, Hung-Hsi Raghavan, Nagarajan Suñé, Jordi Miranda, Enrique Eltawil, Ahmed Setti, Gianluca Smagulova, Kamilya Salama, Khaled N. Krestinskaya, Olga Yan, Xiaobing Ang, Kah-Wee Jain, Samarth Li, Sifan Alharbi, Osamah Pazos, Sebastian Lanza, Mario Physical Science and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955-6900 Saudi Arabia Departament d’Enginyeria Electrònica Universitat Autònoma de Barcelona (UAB) Barcelona 08193 Spain IBM Research – Zurich Rüschlikon Switzerland Department of Electrical and Computer Engineering University of Southern California (USC) Los Angeles 90089 CA United States Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor 48109 MI United States Department of Electrical Engineering National Tsing Hua University Hsinchu 30013 Taiwan Dipartimento di Elettronica Informazione e Bioingegneria Politecnico di Milano and IUNET Piazza L. da Vinci 32 Milano 20133 Italy School of Electronic and Computer Engineering Peking University Shenzhen China Department of Electronic and Electrical Engineering University College London (UCL) Torrington Place WC1E 7JE London United Kingdom Departamento de Electrónica y Tecnología de Computadores Facultad de Ciencias Universidad de Granada Avenida Fuentenueva s/n Granada 18071 Spain Engineering Product Development (EPD) Pillar Singapore University of Technology & amp Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955-6900 Saudi Arabia Key Laboratory of Brain-Like Neuromorphic Devices and Systems of Hebei Province Hebei University Baoding 071002 China Department of Electrical and Computer Engineering College of Design and Engineering National University of Singapore (NUS) Singapore Singapore

Artificial Intelligence (AI) is currently experiencing a bloom driven by deep learning (DL) techniques, which rely on networks of connected simple computing units operating in parallel. The low communication bandwidth between memory and processing units in conventional von Neumann machines does not support the requirements of emerging applications that rely extensively on large sets of data. More recent computing paradigms, such as high parallelization and near-memory computing, help alleviate the data communication bottleneck to some extent, but paradigm- shifting concepts are required. Memristors, a novel beyond-complementary metal-oxide-semiconductor (CMOS) technology, are a promising choice for memory devices due to their unique intrinsic device-level properties, enabling both storing and computing with a small, massively-parallel footprint at low power. Theoretically, this directly translates to a major boost in energy efficiency and computational throughput, but various practical challenges remain. In this work we review the latest efforts for achieving hardware-based memristive artificial neural networks (ANNs), describing with detail the working principia of each block and the different design alternatives with their own advantages and disadvantages, as well as the tools required for accurate estimation of performance metrics. Ultimately, we aim to provide a comprehensive protocol of the materials and methods involved in memristive neural networks to those aiming to start working in this field and the experts looking for a holistic approach. © The Author(s) 2024.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EMERGENCE OF BIOLOGICAL TRANSPORTATION NETWORKS AS A SELF-REGULATED PROCESS

arXiv

引用

arXiv 2022年

作者： Haskovec, Jan Markowich, Peter Portaro, Simone Mathematical and Computer Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia Faculty of Mathematics University of Vienna Oskar-Morgenstern-Platz 1 Vienna1090 Austria

We study self-regulating processes modeling biological transportation networks. Firstly, we write the formal L2-gradient flow for the symmetric tensor valued diffusivity D of a broad class of entropy dissipations associated with a purely diffusive model. The introduction of a prescribed electric potential leads to the Fokker-Planck equation, for whose entropy dissipations we also investigate the formal L2-gradient flow. We derive an integral formula for the second variation of the dissipation functional, proving convexity (in dependence of diffusivity tensor) for a quadratic entropy density modeling Joule heating. Finally, we couple in the Poisson equation for the electric potential obtaining the Poisson-Nernst-Planck system. The formal gradient flow of the associated entropy loss functional is derived, giving an evolution equation for D coupled with two auxiliary elliptic *** Codes 35K57, 35G61, 92C42 © 2022, CC BY-NC-ND.

关键词： Poisson equation

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：