检索结果-内蒙古大学图书馆

Robust Tweets Classification Using Arithmetic Optimization with Deep Learning for Sustainable Urban Living

SN computer Science 2024年第5期5卷 1-11页

作者： Hamza, Manar Ahmed Hashim, Aisha Hassan Abdalla Motwakel, Abdelwahed Elhameed, Elmouez Samir Abd Osman, Mohammed Kumar, Arun Singla, Chinu Munjal, Muskaan Department of Electrical and Computer Engineering International Islamic University Malaysia Kuala Lumpur 53100 Malaysia Department of Computer and Self Development Preparatory Year Deanship Prince Sattam bin Abdulaziz University AlKharj Saudi Arabia Department of Management Information Systems College of Business Administration in Hawtat bani Tamim Prince Sattam bin Abdulaziz University AlKharj Saudi Arabia Department of Computer Science College of Post-Graduated Studies University of Science and Technology Omdurman Sudan Department of Information System Faculty of Computer Science and Information Technology Omdurman Islamic University Omdurman Sudan Department of Electronics and Communication Engineering New Horizon College of engineering Bengaluru India Computer Engineering Thapar Institute of Engineering and Technology Punjab Patiala India

Natural Language Processing (NLP) with Deep Learning (DL) for Tweets Classification includes use of advanced neural network designs to analyse and classify Twitter messages. DL techniques like recurrent neural network (RNN) or transformer-based frameworks like BERT are used to mechanically learn difficult linguistic patterns and contextual info from tweet data. These techniques able to capture subtleties of language with sarcasm, sentiment, and context-specific meanings and making them suitable for tasks like sentiment analysis or topic classification in realm of social media. Leveraging deep symbols learned from great amounts of textual data, these NLP techniques permit precise and nuanced classification of tweets, donating to enhanced information retrieval, sentiment tracking, and trend analysis in dynamic and fast-paced world of social media communication. In this view, this research develops an arithmetic optimization algorithm with deep learning based tweets classification (AOADL-TC) approach for sustainable living. The goal of the AOADL-TC technique is to identify and discriminate different kinds of sentiments that exist in the tweet data. At the initial stage, the AOADL-TC model pre-processes tweet data to convert uniform data into a useful format. For sentiment detection, the AOADL-TC technique applies a parallel bidirectional gated recurrent unit (BiGRU) model. At last, tuning of parameters related to parallel BiGRU model performed by AOA. An wide set of tests carried out to illustrate better performance of AOADL-TC model. The experimental outcomes portrayed that AOADL-TC technique demonstrates the supremacy of the AOADL-TC technique in terms of different evaluation metrics. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep learning Machine learning Natural language processing Sentiment analysis Social media

来源：评论

学校读者我要写书评

暂无评论

Adaptive Control of Euler-Lagrange systems under Time-varying State Constraints without a Priori Bounded Uncertainty

引用

IFAC-PapersOnLine 2023年第2期56卷 3360-3365页

作者： Viswa Narayanan Sankaranarayanan Sumeet Satpute Spandan Roy George Nikolakopoulos Robotics and Artificial Intelligence Group Department of Computer Science Electrical and Space Engineering Luleå University of Technology Sweden Robotics Research Center International Institute of Information Technology Hyderabad India

In this article, a novel adaptive controller is designed for Euler-Lagrangian systems under predefined time-varying state constraints. The proposed controller could achieve this objective without a priori knowledge of system parameters and, crucially, of state-dependent uncertainties. The closed-loop stability is verified using the Lyapunov method, while the overall efficacy of the proposed scheme is verified using a simulated robotic arm compared to the state of the art.

关键词： Adaptive control barrier Lyapunov function Euler-Lagrangian system

来源：评论

学校读者我要写书评

暂无评论

Shape Sensing Stretchable Sensor Grid Towards Camera-Less Motion Capture

Shape Sensing Stretchable Sensor Grid Towards Camera-Less Mo...

引用

IEEE SENSORS

作者： Joseph Karam Aiden Shaevitz Joseph R. Davidson Matthew L. Johnston School of Electrical Engineering and Computer Science Oregon State University Corvallis OR USA Collaborative Robotics and Intelligent Systems Institute Oregon State University Corvallis OR USA

ISBN: (数字)9798350363517

ISBN: (纸本)9798350363524

Stretchable electronics and conformal sensors are valuable for applications in soft robotics and wearable devices. Here, we demonstrate a stretchable sensor sheet with integrated readout for measuring strain and orientation across the sheet. Conductive liquid metal wires encased in silicone measure multi-axis strain. These strain sensors, paired with precision 9-axis IMUs mounted on PCBs embedded in the silicone, enable a shape-sensing, stretchable sensor grid. A prototype is presented first with a single strain sensor and IMU pair, which is charac-terized and calibrated for higher accuracy. Then, a larger scale stretchable grid with 24 strain sensors and 16 IMUs is presented. A four-wire liquid metal bus delivers power to the system and serves as a data communication bus. Long-term, our approach may enable motion capture and shape reconstruction without the need for external cameras or instrumented environments.

关键词： Liquids Shape Metals Soft robotics Strain measurement Capacitive sensors Motion capture Wearable devices Wearable sensors Strain

来源：评论

学校读者我要写书评

暂无评论

Strictly Positive Realness-Based Feedback Gain Design Under Imperfect Input-Output Feedback Linearization in Prioritized Control Problem

Strictly Positive Realness-Based Feedback Gain Design Under ...

引用

IEEE Conference on Decision and Control

作者： Sang-ik An Gyunghoon Park Dongheui Lee School of Electrical and Computer Engineering University of Seoul Faculty of Electrical Engineering and Information Technology Autonomous Systems at Institute of Computer Technology TU Wien Austria German Aerospace Center (DLR) Institute of Robotics and Mechatronics

The prioritized control problem is a process to find a control strategy for a dynamical system with prioritized multiple outputs, so that it can operate outside its nonsingular domain. Singularity typically leads to imperfect inversion in the prioritized control problem, which in turn results in imperfect input-output feedback linearization. In this paper, we propose a method based on the Kalman-Yakubovich-Popov lemma that compensates nonlinear feedback terms caused by the imperfect inversion of the prioritized control problem. In order to realize this idea, we prove existence of a feedback gain matrix that gives a strictly positive real transfer function whose output matrix is identical to the feedback gain matrix. Our proof is constructive so that a set of such matrices can be found. Also, we provide a numerical approach that gives a larger set of feedback gain matrices and validate the result with numerical examples.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Thermal management challenges and approaches for liquid hydrogen-fueled aircraft

Thermal management challenges and approaches for liquid hydr...

引用

AIAA Aviation Forum and ASCEND, 2024

作者： Ordonez, Juan C. Sailabada, Chaianan Guo, Wei Cooley, Lance Cheetham, Peter Kim, Chul Zheng, Jim P. Gladin, Jonathan Cattafesta, Louis FAMU-FSU College of Engineering Department of Mechanical Engineering Center for Advanced Power Systems and Energy and Sustainability Center Florida State University TallahasseeFL32310 United States Electrical and Computer Engineering FAMU-FSU College of Engineering and Center for Advanced Power Systems Florida State University TallahasseeFL32310 United States Center for Advanced Power Systems FAMU-FSU College of Engineering and Center for Advanced Power Systems Florida State University TallahasseeFL32310 United States Department of Electrical Engineering The State University of New York at Buffalo BuffaloNY14260 United States School of Aerospace Engineering Aerospace Systems Design Laboratory Georgia Institute of Technology AtlantaGA30332 United States Department of Mechanical Materials and Aerospace Engineering Illinois Institute of Technology ChicagoIL60616 United States

ISBN: (数字)9781624107160

ISBN: (纸本)9781624107160

This paper presents an overview of thermal management challenges associated with aircraft that rely on liquid hydrogen as the sole fuel source. The paper discusses strategies that can enhance the overall cooling capacity and enable a larger contribution of fuel cells to the overall power. Design considerations for heat exchangers to integrate cryogenic hydrogen with secondary thermal management loops, outer mold line cooling, and additional thermal management strategies are presented. Cooling requirement estimates for a blended-wing aircraft (112 passengers, 2400 nautical miles) are reported. A finite element simulation using RANS suggests a cooling capacity rate of the order of 10 kW/m2 is available through the Outer Mold Line (OML). The paper also reports on the cooling capacity available by using hydrogen as a heat sink to cool the power train. For the IZEA concept, the hydrogen stream to the fuel cell can handle close to 6% of the fuel cell heat generation. © 2024, American institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Hydrogen fuels

来源：评论

学校读者我要写书评

暂无评论

A Distributed Framework for Large-scale Protein-protein Interaction Data Analysis and Prediction Using MapReduce

引用

IEEE/CAA Journal of Automatica Sinica 2022年第1期9卷 160-172页

作者： Lun Hu Shicheng Yang Xin Luo Huaqiang Yuan Khaled Sedraoui MengChu Zhou School of Computer Science and Technology Dongguan University of TechnologyDongguan 523808China School of Computer Science and Technology Wuhan University of TechnologyWuhan 430070China Chongqing Engineering Research Center of Big Data Application for Smart Cities and Chongqing Key Laboratory of Big Data and Intelligent ComputingChongqing Institute of Green and Intelligent TechnologyChinese Academy of SciencesChongqing 400714China Xinjiang Technical Institute of Physics and Chemistry Chinese Academy of SciencesUrumqi 830000China Center of Research Excellence in Renewable Energy and Power Systems and the Department of Electrical and Computer EngineeringFaculty of EngineeringKing Abdulaziz UniversityJeddah 21589Saudi Arabia Department of Electrical and Computer Engineering New Jersey Institute of TechnologyNewarkNJ 07102 USA

Protein-protein interactions are of great significance for human to understand the functional mechanisms of *** the rapid development of high-throughput genomic technologies,massive protein-protein interaction(PPI)data have been generated,making it very difficult to analyze them *** address this problem,this paper presents a distributed framework by reimplementing one of state-of-the-art algorithms,i.e.,CoFex,using *** do so,an in-depth analysis of its limitations is conducted from the perspectives of efficiency and memory consumption when applying it for large-scale PPI data analysis and *** solutions are then devised to overcome these *** particular,we adopt a novel tree-based data structure to reduce the heavy memory consumption caused by the huge sequence information of *** that,its procedure is modified by following the MapReduce framework to take the prediction task distributively.A series of extensive experiments have been conducted to evaluate the performance of our framework in terms of both efficiency and *** results well demonstrate that the proposed framework can considerably improve its computational efficiency by more than two orders of magnitude while retaining the same high accuracy.

关键词： Distributed computing large-scale prediction machine learning MapReduce protein-protein interaction(PPI)

来源：评论

学校读者我要写书评

暂无评论

GRNN-based Real-time Fault Chain Prediction

arXiv

引用

arXiv 2023年

作者： Dwivedi, Anmol Tajer, Ali Electrical Computer and Systems Engineering Department Rensselaer Polytechnic Institute United States

This paper proposes a data-driven graphical framework for the real-time search of risky cascading fault chains (FCs). While identifying risky FCs is pivotal to alleviating cascading failures, the complex spatio-temporal dependencies among the components of the power system render challenges to modeling and analyzing FCs. Furthermore, the real-time search of risky FCs faces an inherent combinatorial complexity that grows exponentially with the size of the system. The proposed framework leverages the recent advances in graph recurrent neural networks to circumvent the computational complexities of the real-time search of FCs. The search process is formalized as a partially observable Markov decision process (POMDP), which is subsequently solved via a time-varying graph recurrent neural network (GRNN) that judiciously accounts for the inherent temporal and spatial structures of the data generated by the system. The key features of this structure include (i) leveraging the spatial structure of the data induced by the system topology, (ii) leveraging the temporal structure of data induced by system dynamics, and (iii) efficiently summarizing the system’s history in the latent space of the GRNN. The proposed framework’s efficiency is compared to the relevant literature on the IEEE 39-bus New England system and the IEEE 118-bus system. © 2023, CC BY.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Experimental demonstration of SnO_(2) nanofiber-based memristors and their data-driven modeling for nanoelectronic applications

引用

Chip 2023年第4期2卷 142-153页

作者： Soumi Saha Madadi Chetan Kodand Reddy Tati Sai Nikhil Kaushik Burugupally Sanghamitra DebRoy Akshay Salimath Venkat Mattela Surya Shankar Dan Parikshit Sahatiya Department of Electrical&Electronics Engineering Birla Institute of Technology and Science PilaniHyderabad CampusHyderabad 500078India Department of Computer Science and Information Systems Birla Institute of Technology and Science PilaniHyderabad CampusHyderabad 500078India Nanomagnetic Division Ceremorphic India Pvt LtdIndia Ceremorphic Inc.San JoseCA 95131USA

This paper demonstrated the fabrication,characterization,datadriven modeling,and practical application of a 1D SnO_(2)nanofiber-based memristor,in which a 1D SnO_(2)active layer wassandwiched between silver(Ag)and aluminum(Al)*** yielded a very high ROFF:RON of~104(ION:IOFF of~105)with an excellent activation slope of 10 mV/dec,low set voltage ofVSET~1.14 V and good *** paper physically explained the conduction mechanism in the layered SnO_(2)*** conductive network was composed of nanofibersthat play a vital role in the memristive action,since more conductive paths could facilitate the hopping of electron *** structures experimentally extracted with the adoption of ultraviolet photoelectron spectroscopy strongly support the claimsreported in this *** machine learning(ML)–assisted,datadriven model of the fabricated memristor was also developedemploying different popular algorithms such as polynomialregression,support vector regression,k nearest neighbors,andartificial neural network(ANN)to model the data of the *** have proposed two types of ANN models(type I andtype II)algorithms,illustrated with a detailed flowchart,to modelthe fabricated *** with standard ML techniques shows that the type II ANN algorithm provides the bestmean absolute percentage error of 0.0175 with a 98%R^(2)*** proposed data-driven model was further validated with the characterization results of similar new memristors fabricated adoptingthe same fabrication recipe,which gave satisfactory ***,the ANN type II model was applied to design and implementsimple AND&OR logic functionalities adopting the fabricatedmemristors with expected,near-ideal characteristics.

关键词： Nanofiber-based memristors Data-driven modeling Artificial neural network(ANN) SnO_(2)

来源：评论

学校读者我要写书评

暂无评论

MCTS-Judge: Test-Time Scaling in LLM-as-a-Judge for Code Correctness Evaluation

arXiv

引用

arXiv 2025年

作者： Wang, Yutong Ji, Pengliang Yang, Chaoqun Li, Kaixin Hu, Ming Li, Jiaoyang Sartoretti, Guillaume Department of Mechanical Engineering National University of Singapore Singapore Robotics Institute Carnegie Mellon University United States School of Computing National University of Singapore Singapore Department of Electrical and Computer Systems Monash University Australia

The LLM-as-a-Judge paradigm shows promise for evaluating generative content but lacks reliability in reasoning-intensive scenarios, such as programming. Inspired by recent advances in reasoning models and shifts in scaling laws, we pioneer bringing test-time computation into LLM-as-a-Judge, proposing MCTS-Judge, a resource-efficient, System-2 thinking framework for code correctness evaluation. MCTS-Judge leverages Monte Carlo Tree Search (MCTS) to decompose problems into simpler, multi-perspective evaluations. Through a node-selection strategy that combines self-assessment based on historical actions in the current trajectory and the Upper Confidence Bound for Trees based on prior rollouts, MCTS-Judge balances global optimization and refinement of the current trajectory. We further designed a high-precision, unit-test-level reward mechanism to encourage the Large Language Model (LLM) to perform line-by-line analysis. Extensive experiments on three benchmarks and five LLMs demonstrate the effectiveness of MCTS-Judge, which improves the base model’s accuracy from 41.0% to 80.0%, surpassing the o1-series models with 3× fewer tokens. Further evaluations validate the superiority of its reasoning trajectory in logic, analytics, thoroughness, and overall quality, while revealing the test-time scaling law of the LLM-as-a-Judge paradigm. Copyright © 2025, The Authors. All rights reserved.

关键词： Scaling laws

来源：评论

学校读者我要写书评

暂无评论

On Penalty-based Bilevel Gradient Descent Method

arXiv

引用

arXiv 2023年

作者： Shen, Han Xiao, Quan Chen, Tianyi Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute United States

Bilevel optimization enjoys a wide range of applications in emerging machine learning and signal processing problems such as hyper-parameter optimization, image reconstruction, meta-learning, adversarial training, and reinforcement learning. However, bilevel optimization problems are traditionally known to be difficult to solve. Recent progress on bilevel algorithms mainly focuses on bilevel optimization problems through the lens of the implicit-gradient method, where the lower-level objective is either strongly convex or unconstrained. In this work, we tackle a challenging class of bilevel problems through the lens of the penalty method. We show that under certain conditions, the penalty reformulation recovers the (local) solutions of the original bilevel problem. Further, we propose the penalty-based bilevel gradient descent (PBGD) algorithm and establish its finite-time convergence for the constrained bilevel problem with lower-level constraints yet without lower-level strong convexity. Experiments on synthetic and real datasets showcase the efficiency of the proposed PBGD algorithm. The code for implementing this algorithm is publicly available on GitHub. Copyright © 2023, The Authors. All rights reserved.

关键词： Adversarial machine learning

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：