检索结果-内蒙古大学图书馆

Communication, Control and Intelligent Systems (CCIS)

作者： Prasanna V Suresh Kumar N Divyaprabha P R Sundaram Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Chennai India Department of Information Technology Sri Ramakrishna Engineering College Coimbatore India Department of Computer Science and Engineering Sri Ramakrishna Engineering College Coimbatore India Department of Computer Science and Engineering Ganesh College of Engineering Salem India

ISBN: (数字)9798331528201

ISBN: (纸本)9798331528218

As the primary cause of death globally, cardiovascular diseases (CVDs) demand precise and timely prediction to enhance patient outcomes. Other examples of conventional approaches for CVD prediction include statistical models as well as machine learning models such as a single model that often struggle to address complex and comprehensive data from clinical records and Medical Imaging. To address these issues, the concept proposed here is to integrate the medical imaging data with clinical data as new apart from utilizing the hybrid CNN–GRU model to predict cardiovascular diseases with higher accuracy and interpretability. While the GRU module deals with the time sequences of clinical data including past history and other test results, the CNN module is to extract the spatial features from the medical images. Thus, by integrating these modules, it is more accurate to predict the data of the patient as a synergy of spatial and temporal arrangements. Cross-validation techniques and performance indices are used for model training and testing on a diverse data set containing imaging and other clinical-related data. Experimental results depict that the suggested hybrid CNN-GRU model performs much better than the traditional approaches and has higher levels of predicted accuracy and robustness. It is also feasible to generalize this integrated strategy to other medical disorder where multi-modal data analysis is crucial, besides enhancing the capacity to estimate CVDs. The findings underline the importance of integrating doctors’ information with radiological images and applying new patterns of neural networks to augmenting clinical judgment. The suggested work is implemented using python.

关键词： Analytical models Accuracy data analysis Computational modeling Predictive models Feature extraction data models Convolutional neural networks Cardiovascular diseases Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

A LEGAL PREDICTION MODEL USING SUPPORT VECTOR MACHINE AND K-MEANS CLUSTERING ALGORITHM FOR PREDICTING JUDGEMENTS AND MAKING DECISIONS

A LEGAL PREDICTION MODEL USING SUPPORT VECTOR MACHINE AND K-...

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering, RMKMATE 2023

作者： Rani, A. Jaya Mabel Bharathwaj, K.S. Swaroopan, N.M. Jothi Kumar, K. Hari Geetha, R. Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India Department of Artificial Intelligence and Data Science Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India Department of EEE R.M.K. Engineering College Chennai India Department of Computer Science St Jude's College KanyaKumari District Tamil Nadu Thoothoor India Department of EEE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences ThandalamTamil Nadu Chennai India

ISBN: (纸本)9798350305708

The legal community has displayed significant interest in harnessing predictive models to anticipate case outcomes, providing judges and attorneys with valuable tools to enhance their decision-making processes. These models offer the potential to expedite choices, offer support for arguments, and strengthen defence strategies. However, accurately predicting legal rulings and case results is a complex endeavour, involving multifaceted stages such as sourcing appropriate bulk case documents, extracting and refining data, and navigating the intricate nature of legal paper complexities. In this innovative machine learning-powered legal prediction model is introduced, named "Legal Acumen." Beyond predictions, this model also offers informed decisions based on the appropriate laws, providing an added layer of insight and value. "Legal Acumen" not only generates predictions about judgments from the Supreme Court but also incorporates a feature that aids end users: upon uploading a new case description document to a designated folder, the system rapidly comprehends its contents and generates both a prediction and a legally informed decision. The understanding indicates that "Legal Acumen" stands among the pioneering legal prediction models striving to anticipate decisions from the Indian Supreme Court. For automatic prediction of Legal Acumen used different types of machine learning algorithms such as Support vector machine, Decision Tree algorithm, Etc., But this paper proposed two-step process. First step used Support vector machine for the prediction of judgement. Then the second step explained about the punishment of the criminal based on K-Means Clustering algorithm. © 2023 IEEE.

关键词： Acumen appeals court decisions Indian judgments prediction supreme

来源：评论

学校读者我要写书评

暂无评论

Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models

arXiv

引用

arXiv 2024年

作者： Wu, Yuchen Chen, Minshuo Li, Zihao Wang, Mengdi Wei, Yuting Department of Statistics and Data Science The Wharton School University of Pennsylvania United States Department of Electrical and Computer Engineering Princeton University United States

Diffusion models benefit from instillation of task-specific information into the score function to steer the sample generation towards desired properties. Such information is coined as guidance. For example, in text-to-image synthesis, text input is encoded as guidance to generate semantically aligned images. Proper guidance inputs are closely tied to the performance of diffusion models. A common observation is that strong guidance promotes a tight alignment to the task-specific information, while reducing the diversity of the generated samples. In this paper, we provide the first theoretical study towards understanding the influence of guidance on diffusion models in the context of Gaussian mixture models. Under mild conditions, we prove that incorporating diffusion guidance not only boosts classification confidence but also diminishes distribution diversity, leading to a reduction in the differential entropy of the output distribution. Our analysis covers the widely adopted sampling schemes including DDPM and DDIM, and leverages comparison inequalities for differential equations as well as the Fokker-Planck equation that characterizes the evolution of probability density function, which may be of independent theoretical interest. Copyright © 2024, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

IoT-Enabled Dust Cleaning Mechanism for Enhanced Performance of Solar Panel Arrays 23

IoT-Enabled Dust Cleaning Mechanism for Enhanced Performance...

引用

Proceedings of the 5th International Conference on Information Management & Machine Intelligence

作者： Udit Mamodiya Budesh Kanwer Indra Kishor Poornima University India Department of Artificial Intelligence & Data Science Poornima Institute of Engineering and Technology India Dept. of Computer Science Poornima Institute of Engineering and Technology India

ISBN: (纸本)9798400709418

Over the past two decades, solar energy sources have secured a remarkable position among alternative energy options, demonstrating the feasibility of harnessing green energy to meet a significant portion of the world's electrical power needs. The development of technology to control solar energy generation has proven essential for lowering costs and increasing reliability. As a renewable energy source, solar panels provide power without releasing any pollutants. However, dirt has a negative impact on solar panels and is a significant environmental issue that affects energy generation. When dirt builds up on the surface of the solar panel, the intensity of the light falling on it decreases. As a result, the solar panel produces less electrical energy overall. As cleaning the solar panel is essential, these procedures must be continuously observed and assessed in order to be optimized. This indicates the importance of using intelligent systems to keep an eye out for dirt and clean solar panels in order to maximize their efficiency. We have developed a 1 kW solar tracking system. This research paper aims to illustrate the idea of an innovative, intelligent IoT-based dust cleaning mechanism for overall performance improvement for the solar tracker system. In a month, if the modules are not cleaned, efficiency could drop by 20% to 30%. The tracking efficiency of a dirty solar panel is measured at 41.27%, and this efficiency significantly improves to 59.89% when the panel is cleaned and combined with a tracking system

关键词： Dust cleaning system

来源：评论

学校读者我要写书评

暂无评论

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Kaijun Deng Dezhi Zheng Jindong Xie Jinbao Wang Weicheng Xie Linlin Shen Siyang Song Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Department of Computer Science University of Exeter

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code is available at https://***/CVI-SZU/DEGSTalk.

关键词： Hair Training Three-dimensional displays Dynamics Signal processing Rendering (computer graphics) Noise measurement Speech processing Faces Videos

来源：评论

学校读者我要写书评

暂无评论

Early Childhood Action Monitoring and Analytics System (ECAMS) 28

Early Childhood Action Monitoring and Analytics System (ECAM...

引用

28th IEEE Pacific Rim International Symposium on Dependable Computing, PRDC 2023

作者： Andarage, Isuru Supasan Naotunna Fernando, Dileepa Lokuarachchi, Buddhi Avishka Athuluwage, Malithi Gimhani Wijewickrama, Pavithra Sri Lanka Technological Campus Department of Data Science Padukka10500 Sri Lanka Nanyang Technological University School of Computer Science and Engineering Singapore Singapore Sri Lanka Technological Campus Faculty of Engineering Padukka10500 Sri Lanka Sabaragamuwa University of Sri Lanka Department of Sport Sciences and Physical Education Belihuloya Sri Lanka

ISBN: (纸本)9798350358766

The cultivation of fundamental movement skills (FMS) during the early stages of childhood bears immense importance in shaping an individual's involvement and achievements in sports throughout their entire life. Therefore, the assessment of motor skills in early childhood (age 3-5 years) significantly influences the advancement of sports within a nation. To this end, early childhood motor skill assessment has been performed manually posing efficiency challenges. The current automation approaches either involve invasiveness or depend on a substantial volume of annotated video training data. In this research, we introduce the Early Childhood Actions Monitoring and Analytics System (ECAMS) toolkit designed to evaluate early childhood motor skills, including activities like sitting up, running, walking, and jumping. This research employs computer vision and machine learning techniques integrated with the TGM2D (Test of Gross Motor Development-2nd Edition) toolkit to accurately detect motor skills from a given video input. This real-time analysis will offer accurate guidance to individuals involved in early childhood development, including educators, trainers, parents, and sports analysts. © 2023 IEEE.

关键词： Sports

来源：评论

学校读者我要写书评

暂无评论

Overview of Shared-task on Abusive Comment Detection in Tamil and Telugu 3

Overview of Shared-task on Abusive Comment Detection in Tami...

引用

3rd Workshop on Speech and Language Technologies for Dravidian Languages, DravidianLangTech 2023

作者： Priyadharshini, Ruba Chakravarthi, Bharathi Raja Subramanian, Malliga Navaneethakrishnan, Subalalitha Chinnaudayar Shanmugavadivel, Kogilavani Premjith, B. Murugappan, Abirami Kumaresan, Prasanna Kumar Prashanth, Karnati Sai Reddy, Mangamuru Sai Rishith Chandu, Janakiram Gandhigram Rural Institute-Deemed to be University India Insight SFI Research Centre for Data Analytics School of Computer Science University of Galway Ireland Kongu Engineering College Tamil Nadu India SRM Institute of Science and Technology Kattankulathur Chennai India Amrita School of Artificial Intelligence Amrita Vishwa Vidyapeetham India Department of Information Science and Technology Anna University India

ISBN: (纸本)9789544520854

This paper discusses the submissions to the shared task on abusive comment detection in Tamil and Telugu codemixed social media text conducted as part of the third Workshop on Speech and Language Technologies for Dravidian Languages at RANLP 2023. The task encourages researchers to develop models to detect the contents containing abusive information in Tamil and Telugu codemixed social media text. The task has three subtasks - abusive comment detection in Tamil, Tamil-English and Telugu-English. The dataset for all the tasks was developed by collecting comments from YouTube. The submitted models were evaluated using macro F1-score, and prepared the rank list accordingly. © DravidianLangTech 2023 - 3rd Workshop on Speech and Language Technologies for Dravidian Languages, associated with 14th International Conference on Recent Advances in Natural Language Processing, RANLP 2023 - Proceedings.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Coalition Formation Game Approach for Task Allocation in Heterogeneous Multi-Robot Systems under Resource Constraints

Coalition Formation Game Approach for Task Allocation in Het...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Liwang Zhang Dong Liang Minglong Li Wenjing Yang Shaowu Yang Department of Intelligent Data Science College of Computer Science and Technology National University of Defense Technology Changsha China College of Sciences National University of Defense Technology Changsha China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

This paper studies a case of the multi-robot task allocation (MRTA) problem, where each unmanned aerial vehicle (UAV) is endowed with multiple but limited resources. Completing each task necessitates UAVs to combine different resources through coalition formation, which will incur various costs including flight cost, execution cost, and cooperation cost. To minimize the total cost while maximizing both task completion rate and resource utilization rate, we model the MRTA problem of the UAVs as a leader-follower coalition formation game. In this game, leader UAVs coordinate follower UAVs to fulfill task resource requisites. Meanwhile, follower UAVs select suitable coalitions to join based on the altruistic preference. Theoretical analysis confirms the existence of a Nash stable partition in the coalition formation game. To achieve this stable partition, we propose a coalition formation algorithm. Simulation experiments validate that the proposed algorithm outperforms existing methods for the MRTA problem under resource constraints in terms of both task completion rate and resource utilization rate.

关键词： Costs Games Autonomous aerial vehicles Partitioning algorithms Resource management Multi-robot systems Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Joint Covert and Secure Communication for SWIPT-Assisted CNOMA Systems

引用

IEEE Internet of Things Journal 2025年第12期12卷 20406-20419页

作者： Huang, Gaojian Lei, Yuxin Li, Xingwang Khan, Wali Ullah Wang, Gongpu Nallanathan, Arumugam Henan Polytechnic University School of Physics and Electronic Information Engineering School of Surveying and Land Information Engineering Photoelectric Detection and Sensing Integrated Engineering Technology Research Center of Henan Province Jiaozuo454003 China City University of Macau Faculty of Data Science China Henan Polytechnic University School of Physics and Electronic Information Engineering Jiaozuo454003 China Southeast University National Mobile Communications Research Laboratory Nanjing210096 China University of Luxembourg Interdisciplinary Center for Security Reliability and Trust Luxembourg City1855 Luxembourg Beijing Jiaotong University School of Computer Science and Technology Beijing100044 China Queen Mary University of London School of Electronic Engineering and Computer Science LondonE1 4NS United Kingdom Kyung Hee University Department of Electronic Engineering Yongin17104 Korea Republic of

With the rapid advancement of physical-layer security technology, the covert and secure communication has become crucial in safeguarding wireless communication systems. In this article, we propose a joint covert and secure transmission scheme for simultaneous wireless information and power transfer (SWIPT) assisted cooperative nonorthogonal multiple access (CNOMA) systems. In the CNOMA system, a greedy relay transmits the confidential information to the far user (Carol), with the assistance of the near user (Bob). Meanwhile, as a SWIPT node, Bob is self-sustained by harvesting energy from relay. What is more, a warden (Alice) and noncolluding eavesdroppers (Eves) always attempt to detect and capture the confidential information, respectively. To counteract the attacks from Alice and Eves, a jamming-assisted scheme is employed. For the proposed system model, we derive closed-form expressions for the detection error probability (DEP) and the average minimum detection error probability (AMDEP) of Alice. Additionally, closed-form expressions for the outage probability (OP) of users and the intercept probability (IP) of Eves are obtained. Furthermore, to maximize the effective covert rate (ECR) of Carol, an optimization problem is formulated, subject to covertness and security constraints. Numerical results are provided to demonstrate the impact of the system parameters on covert and secure performance, with the results showing perfect agreement with the theoretical analysis. © 2014 IEEE.

关键词： Inductive power transmission

来源：评论

学校读者我要写书评

暂无评论

Towards Federated Learning on Fresh datasets

Towards Federated Learning on Fresh Datasets

引用

IEEE Internatonal Conference on Mobile Adhoc and Sensor Systems (MASS)

作者： Chen Wu Mingjun Xiao Jie Wu Yin Xu Jinrui Zhou He Sun School of Data Science University of Science and Technology of China China School of Computer Science and Technology & Suzhou Institute for Advanced Research University of Science and Technology of China China Department of Computer and Information Sciences Temple University USA

Federated Learning (FL) is an emerging privacy-preserving distributed computing paradigm that enables numerous clients to collaboratively train machine learning models without the need for transmitting the private datasets of clients to the FL server. Unlike most existing research where the local datasets of clients are considered to be unchanging over time during the whole FL process, we consider such scenarios in this paper where the local datasets of clients need to be updated periodically, and the server can stimulate clients to use as fresh as possible datasets to train their local models. Our objective is to determine a client selection strategy to minimize the loss of global model for FL with a limited budget. To this end, we leverage the concept of Age of Information (AoI) to quantify the freshness of local datasets and theoretically analyze the convergence bound of our AoI-aware FL system. Based on the convergence bound, we formalize our problem as a restless multi-armed bandit problem. Then, we devise a Whittle’s-Index-based Client Selection algorithm, called WICS, to tackle the client selection problem. Extensive simulations show that the proposed algorithm can reduce the training loss and improve learning accuracy compared to state-of-the-art algorithms.

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：