检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhou, Ziqi Zhang, Jingyue Zhang, Jingyuan He, Yangfan Wang, Boyue Shi, Tianyu Khamis, Alaa Faculty of Applied Science & Engineering University of Toronto Toronto Canada Department of Computer Science University of Minnesota Twin CitiesMN United States Department of Mechanical Engineering University of Wisconsin MadisonWI United States Transportation Research Institute University of Toronto Toronto Canada IRC for Smart Mobility & Logistics King Fahd University of Petroleum and Minerals Dhahran Saudi Arabia

One of the key challenges in current Reinforcement Learning (RL)-based Automated Driving (AD) agents is achieving flexible, precise, and human-like behavior cost-effectively. This paper introduces an innovative approach that uses large language models (LLMs) to intuitively and effectively optimize RL reward functions in a human-centric way. We developed a framework where instructions and dynamic environment descriptions are input into the LLM. The LLM then utilizes this information to assist in generating rewards, thereby steering the behavior of RL agents towards patterns that more closely resemble human driving. The experimental results demonstrate that this approach not only makes RL agents more anthropomorphic but also achieves better performance. Additionally, various strategies for reward-proxy and reward-shaping are investigated, revealing the significant impact of prompt design on shaping an AD vehicle’s behavior. These findings offer a promising direction for the development of more advanced, human-like automated driving systems. Our experimental data and source code can be found here. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Offline Writer Identification Based on CLBP and VLBP 1

引用

4th Mediterranean Conference on Pattern Recognition and Artificial Intelligence, MedPRAI 2020

作者： Abbas, Faycel Gattal, Abdeljalil Djeddi, Chawki Bensefia, Ameur Jamil, Akhtar Saoudi, Kamel Department of Mathematics and Computer Science Larbi Tebessi University Tebessa Algeria LIMPAF Laboratory Computer Sciences Department Faculty of Sciences and Applied Sciences Mohand Akli University Bouira Algeria Higher Colleges of Technology CIS Division Abu Dhabi United Arab Emirates Department of Computer Engineering Istanbul Sabahattin Zaim University Istanbul Turkey Department of Electrical Engineering Mohand Akli University Bouira Algeria

ISBN: (数字)9783030718046

ISBN: (纸本)9783030718039

Writer identification from handwriting is still considered to be challenging task due to homogeneous vision comparing writer of handwritten documents. This paper presents a new method based on two LBPs kinds: Complete Local Binary Patterns (CLBP) and Local Binary Pattern Variance (LBPV) for extracting the features from handwriting documents. The feature vector is then normalized using Probability Density Function (PDF). Classifications are based on the minimization of a similarity criteria based on a distance between two features vectors. A series of evaluations using different combinations of distances metrics are realized high identification rates which are compared with the methods that are participated in the ICDAR 2013 competition. © 2021, Springer Nature Switzerland AG.

关键词： Probability density function

来源：评论

学校读者我要写书评

暂无评论

Integration of DL on Multi-Carrier Non-Orthogonal Multiple Access System with Simultaneous Wireless Information and Power Transfer

Integration of DL on Multi-Carrier Non-Orthogonal Multiple A...

引用

International Conference on System Modeling & Advancement in Research Trends (SMART)

作者： Abhay Chaturvedi Ankit Bhardwaj Digvijay Singh Bhasker Pant José Luis Arias Gonzáles Firos A. Department of Electronics and Communication Engineering GLA University Mathura Uttar Pradesh The Math Company University of Connecticut Department of Computer Science and Engineering University of Connecticut Storrs Connecticut Uttaranchal Institute of Technology Uttaranchal University Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Computer Science & Engineering Graphic Era Hill University Dehradun Uttarakhand India Business Department Pontifical Catholic University of Peru Department of Computer Science and Engineering Rajiv Gandhi University (A central university) Rono-Hills Doimukh Arunachal Pradesh India

ISBN: (纸本)9781665487351

Simultaneous Multi-Carrier (MC) NOMA&Wireless Information (SWIPT) are exciting ideas for coming net within the 5th generation and beyond because of their capability for allowing bandwidth and power effective system designs. Using the pattern-division-multiple-access (PDMA) approach, this study investigates the concurrent downlink scalability issue for a SWIPT-enabled MCNOMA system incorporating time swapping receivers. We put a lot of effort into reducing the systems overall transmit power while still providing each user with the level of service they expect in terms of gathered power and data rate. The corresponding optimization problem is a challenging quasi mixed integer computing problem. We present an effective deep learning (DL) based method as opposed to the traditional repetitive searching-based techniques for finding an approximation of the ideal answer. We particularly use a deep belief network (DBN), a common kind of DL model. The created technique's thorough technique is divided into three parts: data generation, testing, and execution. The simulated Results show that the suggested DBN-based strategy works. might produce results in terms of power usage that are similar to those of the thorough search technique. The findings also show that MCNOMA with PDMA outperforms MCNOMA with the other methods in terms of power consumption in systems that support SWIPT.

关键词： Wireless communication NOMA Computational modeling Search methods Scalability Receivers Resource management

来源：评论

学校读者我要写书评

暂无评论

A protection and assurance version for E-authorities Web Services based totally on Cloudlet computing

A protection and assurance version for E-authorities Web Ser...

引用

2021 International Conference on Technological Advancements and Innovations, ICTAI 2021

作者： Singh, Devang Pratap Rajpoot, Subhadra Singh, Puneet Computer Science and Engineering Amity School of Engineering and Technology Greater Noida India Amity School of Engineering and Technology Department of Applied Sciences Greater Noida India Faculty of Communications Engineering Military College of Telecommunication Engineering Madhya Pradesh Mhow India

ISBN: (纸本)9781665420877

In the present scenario, Web Administration and cloud computing are the spine architecture of any e-authorities application due to its interoperable and robust nature. Web benefits that are kept up in Cloud computing bring in easy consideration in examination and industry as far as getting the conveyed Web administrations. Consequently, gaining more trust between the imparted Web administrations which has been continuously getting more accessible for Web administrations shoppers, executives, and Web specialist organizations particularly the e-government administrations. Likewise, the proposed architecture is handling the issues that emerge when Web administration purchasers are speaking with most of the e-legislative Web administrations are furnished through a depended on Cloud-based system that is not bound via any administrative authority. Furthermore, Cloudlet computing is used to quantify the supplier of Web benefits' reliability and compliance to the distributed strategy using input from the Web administration customer. © 2021 IEEE.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

Expectation-Maximization clustering of states based on crime cases against children

Expectation-Maximization clustering of states based on crime...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Lalitha Saroja Thota Isharath Sultana Yerraginnela Shravani Suresh Babu Changalasetty Syed Asif Basha Sreelasya Changalasetty Pulime Satyanarayana Firdouse Banu Department of CSE Shadan Womens College of Engineering and Technology Hyderabad India Department of CSE Sri Indu College of Engineering Hyderabad India College of Computer Science King Khalid University Abha Saudi Arabia Department of CSE Vellore Institute of Technology Vellore India Department of CSE Samskruthi College of Engineering and Technology Hyderabad India Dept of Applied Information System Applied College Khamis Mushaiyt King Khalid University Saudi Arabia

A child is the utmost innocent and vulnerable human being. Yet, children fall easy target to many types of violence, all over the place and each single day. Globally, one billion children face certain form of emotional, physical or sexual crimes each single year. To prevent and address crimes against children, a multifaceted approach combining law enforcement, healthcare workers, educators, researchers and social service providers is necessary. Modern technology and advanced tools are widely in use for criminal investigations from crime data. Although crime data set solely comprises the number of crimes reported in each state for various years, clustering can still be used to group states in India according to the crime cases against children. In this paper, we apply Expectation-Maximization (EM) cluster methodology in WEKA platform to find patterns and trends in child crime rate data and cluster states in India based on crime cases against children which may help to create efficient interventions to stop and deal with crimes against children.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a QoL Improvement System for Visually Impaired Patients

Design and Implementation of a QoL Improvement System for Vi...

引用

International Conference on Advances in Computational Tools for engineering Applications, ACTEA

作者： Roy Abi Zeid Daou Jad Beaino Johnny Hawat Ramy Ibrahim Ali Hayek Josef Boercsoek Jose Javier Serrano Olmedo Mechatronics department Faculty of Engineering Université La Sagesse Beirut Lebanon MART Learning Education and Research Center Chananir Lebanon Department Lippstadt 2 Hardware Engineering University of Applied Science Hamm-Lippstadt Hamm Department of Computer Architecture and System Programming Faculty of Electrical Engineering/Computer Science University of Kassel Germany Lab of Bioinstrumentation and Nanomedicine Centro de Tecnología Biomédica Universidad Politécnica de Madrid Spain

Visually impaired people encounter several challenges in their mobility and navigation. Their daily activities are obstructed due to their inability to adapt or recognize accurately their surroundings, especially outside their house which they are more familiar with. Thus, it becomes the main reason of accidents, falling off, getting lost in unknown areas, etc. Furthermore, one of the sensory systems that helps the body to process data about the external environment is the visual system. Blind people also lose touch with the outside world, develops poor motor habits, which results in postural problems as a result. This project will assist visually impaired people in their daily life and simplify normal tasks through a system combining two previously designed projects, “Smart Shoes for Blind and Visually Impaired People”, and “Human posture monitoring device”. The multifunctional system is developed with the goal of securing safe movements for visually impaired people as well as maintaining a good back posture by detecting leaning postures (LP). The purpose of the smart shoe is to identify obstacles and protect the user from unintended accidents. A compatible Android application has been developed to alert the user when there is an obstruction or when he is walking on a wet surface. Voice alarms will be used to acoustically alert the user. If the user collapses, a message with their position will be sent right away to a relative. On the other hand, the smart vest will identify the position of the user's back and alert him to maintain a straight posture through the same application as well. As the system is dealing with human health, some safety measurements would be taken into consideration to implement a safe electrical system in order to reduce error and to increase accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modeling of Memory Dependent Derivative Under Three-Phase Lag in Generalized Thermo-Viscoelasticity

引用

International Journal of applied and Computational mathematics 2021年第6期7卷 1-20页

作者： Singh, Biswajit Sarkar, Smita Pal Barman, Krishnendu Department of Mathematics Indian Institute of Engineering Science and Technology Shibpur Howrah 711103 West Bengal India Applied Mathematics with Oceanology and Computer Programming Vidyasagar University Paschim Medinipur 721102 West Bengal India

In this study, a new generalized model of thermo-viscoelasticity with three phase-lag (TPL) theory concerning memory-dependent derivative (MDD) theory is emphasized. The governing combined equations of the novel model associated with kernel function and time delay are considered in a two-dimensional semi-infinite space. The bounding surface of the medium is assumed to be free of traction and subjected to time-dependent thermal loading. Using Laplace and Fourier Transform techniques, the problem is transformed from the space–time domain and then solved numerically. Suitable numerical technique is used to find the inversion of Fourier and Laplace transforms. In the simulation, the effects of the time-delay parameter and kernel function on the distributions of the displacement components, stresses and temperature field are studied and represented graphically. The results shows that the presence of TPL, the time-delay and kernel function extensively affect all the distributions. © 2021, The Author(s), under exclusive licence to Springer Nature India Private Limited.

关键词： Laplace and Fourier transform Memory dependent derivative Thermo-viscoelasticity Three phase-lag Vector matrix differential equation

来源：评论

学校读者我要写书评

暂无评论

Heatline visualization in hydromagnetic natural convection flow inside a prismatic heat exchanger using nanofluid

引用

International Journal of Thermofluids 2022年 16卷

作者： Islam, Saiful Bairagi, Tanmoy Islam, Tarikul Rana, B.M.J. Reza-E-Rabbi, S.K. Rahman, M.M. Department of Mathematics Bangladesh University of Engineering and Technology Dhaka Bangladesh Department of Computer Science and Engineering Stamford University Bangladesh Dhaka Bangladesh Department of Mathematics Bangabandhu Sheikh Mujibur Rahman Science and Technology University Gopalganj Bangladesh Department of Applied Mathematics Gono Bishwabidyalay Dhaka Bangladesh Mathematics Discipline Khulna University Khulna Bangladesh

This article deals with a numerical analysis of magneto hydrodynamic natural convection phenomena in a prismatic heat exchanger containing Cu-nanoparticles with water as a base fluid. The nature of this fluid flow is steady, and a heat exchanger is created by involving two uniform cylinders with the same shape in a prismatic cavity. To create the heat exchanger and the buoyancy force, a hot cylinder and another cool cylinder are taken a left and right sides respectively. All other walls of this prismatic cavity are kept as heat insulation. For solving governing equations, the finite element technique is applied by involving Galerkin weighted residual method. The impact of the magnetic field, the buoyancy force, and the size of nanoparticles are explained with the help of involving parameters Rayleigh number (Ra), Hartmann number (Ha), and the nanoparticles volume fraction (). These parameters are graphically and physically explained by using streamline, isotherm, and heatline contours. The Nusselt number is also calculated and explained in detail to show the validation of this investigation. The outcomes indicate that the natural convective heat and energy transfer are improved by increasing the Rayleigh number, and the nanoparticle volume fraction. Reverse behavior is noticed for the upsurge of Hartmann number. The findings of this heat exchanger model can be pragmatic to construct an operative cooling system for numerous shape mechanical chambers. © 2022 The Author(s)

关键词： Magnetohydrodynamics

来源：评论

学校读者我要写书评

暂无评论

Empowering Marketing Management and Gaming Consumer Interaction Through AI and Citizen science

Empowering Marketing Management and Gaming Consumer Interact...

引用

IEEE Games Media Entertainment (GEM)

作者： Celestine Iwendi Chatti Subba Lakshmi Bala Dhandayuthapani Veerasamy Paul Hollins Damilare Adeola Pradeep Hewage Adedapo Paul Aderemi Piyush Kumar Shukla School of Creative Technologies University of Bolton Bolton United Kingdom Department of Computer Science & Engineering Guru Nanak Institutions Technical Campus Hyderabad Telangana India Department of Information Technology College of Computing and Information Sciences University of Technology and Applied Sciences Oman Cultural Research Development School of Arts. University of Bolton Bolton United Kingdom Department of Computer Science & Engineering University Institute of Technology Rajiv Gandhi Proudyogiki Vishwavidyalaya (Technological University of Madhya Pradesh) Bhopal Madhya Pradesh India

ISBN: (数字)9798350374537

ISBN: (纸本)9798350374544

There has been a significant revolution seen by AI getting incorporated into the management and customer relations of companies. The research of the present Artificial Intelligence (AI) revolution that influences a variety of fields i.e. video games are the topic of the article. AI systems such as machine learning and data analytics can help brands understand consumer behaviour in much greater detail; hence, companies can better reach and interest potential consumers through personalized marketing plans and campaigns. This is another case of citizen science that can host a large number of artisanal anglers who can together provide data that can make the research wider-reaching. The proposed scheme improves the level of customer accuracy and tackles trends timely as well as creates slight space for real-time communication by applying neighbour-based recommendation techniques, neural networks, and sentiment analysis. Its supremacy over the conventional methods of statistical significance is highlighted through the advent of predictive analytics and dynamic pricing approaches. The advantage of deploying natural language processing (NLP) is that it helps to understand what the customers mean with how they write. Measuring the key performance indicators at the end of this approach can be called the method of adaptation and flexibility which makes digital marketing not just refer only the success but also turn to the happiness of customers.

关键词： Video games Technological innovation Sentiment analysis Neural networks Companies Pricing Market research

来源：评论

学校读者我要写书评

暂无评论

Some fractional-order modeling and analysis of the transmission dynamics together with prevention controls

引用

The European Physical Journal Special Topics 2024年 1-25页

作者： Guirao, Juan L. G. Jan, Rashid Baleanu, Dumitru Mohammed, Pshtiwan Othman Abdullah, Farah Aini Chorfi, Nejmeddine Department of Applied Mathematics and Statistics Technical University of Cartagena Hospital de Marina Cartagena Spain Department of Civil Engineering Institute of Energy Infrastructure (IEI) College of Engineering Universiti Tenaga Nasional (UNITEN) Kajang Malaysia Mathematics Research Center Near East University TRNC Nicosia Turkey Department of Computer Science and Mathematics Lebanese American University Beirut Lebanon Institute of Space Science-Subsidiary of INFLPR Magurele-Bucharest Romania Department of Mathematics College of Education University of Sulaimani Sulaimani Iraq Research and Development Center University of Sulaimani Sulaymaniyah Iraq School of Mathematical Sciences Universiti Sains Malaysia USM Penang Malaysia Department of Mathematics College of Science King Saud University Riyadh Saudi Arabia

The purpose of the present research is to improve our understanding of how coronavirus infection spreads by creating an epidemic model that incorporates isolation and quarantine measures. The dynamics of this viral spread are represented using the Caputo–Fabrizio operator. By analyzing the equilibria of the model and utilizing the next-generation matrix method, we determine the endemic indicator, $${\mathcal {R}}_0$$ . The main findings demonstrate that the equilibrium without infection is locally stable when $${\mathcal {R}}_0$$ is less than one and unstable otherwise. Also, we demonstrate the existence and uniqueness of the solution of our recommended model. In addition to this, we interrogate the solution pathways of the system by varying different factors, aiming to comprehend the intricate transmission of COVID-19 and visualize the crucial factors of the system that can aid public health officials in the control of the spread of infection.

关键词：

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：