检索结果-内蒙古大学图书馆

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Neelamegam, G. Revathy, J. Kannukkiniyal, M. Devendran, M. Akshya, J. Choudhry, Mani Deepak Vsb College of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Christ the King Engineering College Department of Artificial Intelligence and Data Science Coimbatore India Kongu Engineering College Department of Computer Science and Engineering Erode India Hindustan institute of technology Department of Computer Science and Engineering Coimbatore India Srm Institute of Science and Technology Department of Computational Intelligence Chennai India Srm Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798350377972

High reliance on autonomous systems necessitates efficient and reliable data exchange through Vehicle-to-Infrastructure (V2I) communication to have appropriate and stable network performance in dynamic vehicular environments. With heuristic approaches, Dijkstra's algorithm, and Deep Q-Networks (DQN), several methods are proposed for optimizing latency reduction, packet delivery rate improvement, and power efficiency in the direction of V2I communications. However, these approaches suffer from important challenges: low adaptability of the network to real-time dynamics, suboptimal resource usage, and difficulties in scalability towards complex large-scale networks. In this scenario, we propose a framework that incorporates a GNN inside autonomous systems for V2I communication to optimize performance. The GNN will process real-time graph features, including signal strength, packet loss, and mobility speed, as it dynamically changes in adaptation to the evolution of network behaviour and other functions. This work shows the superiority of the proposed GNN model for the efficiency of experimentally conducted simulations compared to the current models;it achieved latency reduced by up to 28%, 5-10% PDR, and 20% energy efficiency across the various scenarios with urban, rural, highway, and suburban networks. The results validate robustness and scalability for practical implementations by the proposed approach in real-world autonomous systems. Further development is possible with this framework: for example, the use of multi-agent reinforcement learning techniques within cooperative decision-making and the enhancement through blockchain-based security mechanisms to ensure the integrity of the data. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

QCNN—A Conceptual Framework for Duplicate Removal in Big data Using Quality Assured Crowd Sourcing Coupled with Neural Networks 1

引用

International Conference on Advances in Communication Technology and Computer Engineering, ICACTCE 2023

作者： Shantha Kumari, K. Ashik, Mohamed Gowrishankar, K. Kanmani, P. Data Science and Business Systems SRM Institute of Science and Technology Chengalpattu India College of Computing and Information University of Technology and Applied Sciences Salalah Oman Electrical and Electronics Engineering AMET University Tamil Nadu Chennai India

ISBN: (数字)9783031371646

ISBN: (纸本)9783031371639

Success of an Enterprise depends on the quality of the data available in its backup. The data need to be consistent, error-free and maintain its integrity irrespective of any threats in any form. Quality data is aka clean data helps in the decision-making process of the Enterprise. However due to multiple entry points available in populating a database, there exists the problem of duplication data, which is one form of dirty data. This duplication data has to be removed without compromising the privacy and integrity of the data. The automated computing algorithms have been limited in its capability for the tasks such as labelling, filtering, translating or transcribing data etc. Hence, crowd sourcing famously referred as human computing are used as supplement to identify and eliminate the duplications available in data. However, it is important to understand that the human crowd is prone in error making and it is essential to choose a qualified crowd that does less error. Because the data labelled by the human crowd is fed to the Neural networks further to identify and eliminate the duplication. This paper provides a conceptual framework that aims to identify the duplicate data through qualified crowds and remove the identified duplication using neural network techniques. The framework explains how to qualify the best crowd to do work, so that clean data is assured with the help of ANNs. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Prediction of AIDS/HIV Infection using Custom Artificial Neural Networks Model 1

Prediction of AIDS/HIV Infection using Custom Artificial Neu...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Sneha, B.J. Shriyashreshta Kodipalli, Ashwini Martis, Roshan Joy Ushasree, A. Devamane, Shridhar B. Global Academy of Technology Department of Ai & Data Science Bangalore India Manipal Institute of Technology Department of Electronics & Communication Engineering Bangalore India Gokaraju Lailavathi Engineering College Department of Computer Science & Engineering Hyderabad India Amrita Vishwavidyapeetam School of Computing Department of Cs Mysuru India

ISBN: (纸本)9798331529246

HIV is a serious disease that impairs immunity. Without treatment, the infection may progress through three stages, which might drastically shorten a person's life. Artificial neural networks (ANNs) are utilized to detect the HIV infection and even to find treatments for it. The AIDS viral infection is predicted in this review. The aim of ANN is to precisely classify patients according to whether or not they have HIV/AIDS. We have formed a custom ANN model and applied it to the Kaggle dataset that is accessible to the public, compared which optimizers offer the best accuracy and whether employing dropouts yields improved accuracy. With Gradient Descent, we achieved the maximum accuracy of 86.92% it is also one of the most commonly used optimizers due to its simplicity and effectiveness, followed by SGD with 86.45% it is a variation of gradient descent in which a random subset of data as opposed to the complete dataset is used to update the parameter and RMSprop with 86.21% uses the average of recent gradient magnitudes to modify the learning rate for each parameter. This aids with training stabilization, particularly when dealing with sparse or noisy data. The accuracy increased to 87.62% after we introduced dropouts to the hidden layer with optimizer as gradient descent, which produced the best results. Loss vs. Accuracy graphs and ROC curve have been plotted. With dropouts, the custom ANN model performed even better on the Gradient Descent optimizer. © 2025 IEEE.

关键词： ANN dropouts HIV/AIDS optimizers

来源：评论

学校读者我要写书评

暂无评论

A Fast Feature Selection for Interpretable Modeling Based on Fuzzy Inference Systems 21

A Fast Feature Selection for Interpretable Modeling Based on...

引用

21st IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2024

作者： Tangherloni, Andrea Cazzaniga, Paolo Stranieri, Nicolò Buffa, Francesca M. Nobile, Marco S. Bocconi Institute for Data Science and Analytics Bocconi University Department of Computing Sciences Milan Italy University of Bergamo Department of Human and Social Sciences Bergamo Italy Bocconi University Department of Computing Sciences Milan Italy Ca' Foscari University of Venice Department of Environmental Sciences Informatics and Statistics Venice Italy

ISBN: (纸本)9798350356632

Large datasets are often beneficial for the generation of predictive models using machine learning approaches. However, it is often the case that not all variables in the dataset contain useful information. In fact, some variables might be useless, redundant, misleading, or even harmful to performance, both in terms of accuracy and computational effort. Because of that, Feature Selection (FS) is one of the most delicate and important steps in machine learning. This is even more relevant in the case of interpretable models based on Fuzzy Inference Systems (FIS). The reasons are two-fold: on the one hand, FIS are generally built on top of a data partitioning based on clustering, which can suffer from high dimensionality;on the other hand, the knowledge base of the FIS, to be concretely understandable, should not contain rules involving too many variables. FS can be performed using multiple approaches, most notably filter and wrapper methods. The latter are often based on evolutionary algorithms, where a population of candidate solutions (each representing a possible set of selected variables) evolves towards the optimal selection. Although wrapper methods can be effective, they are, in general, computationally expensive. In this work, we propose a completely different - and more computationally effective - algorithm based on Random Forest (RF) models. Specifically, we exploit RFs to rank variables according to their importance. Then, we use that information to perform a statistical analysis and determine the minimal set of features necessary to build an accurate FIS. We show the effectiveness of our approach by using two (semi)synthetic datasets built on real-world datasets, and we validate our approach by applying the FS method to a medical dataset. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Incorporating 5G NR Sidelink with MQTT to Maximize Energy Efficiency in IoT-Enabled Microgrids 1

Incorporating 5G NR Sidelink with MQTT to Maximize Energy Ef...

引用

1st IEEE International Conference on Smart Power Control and Renewable Energy, ICSPCRE 2024

作者： Neelamegam, G. Ashforn, Hermina J.M. Raja, Mohamed S. Priyadharshini, J. Akshya, J. Choudhry, Mani Deepak Sundarrajan, M. Vsb College of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Bannari Amman Institute of Technology Department of Artificial Intelligence and Data Science Erode India Kalaignarkarunanidhi Institute of Technology Department of Computer Science and Engineering Coimbatore India K. Ramakrishnan College of Engineering Department of Information Technology Trichy India Srm Institute of Science and Technology Department of Computational Intelligence Chennai India Srm Institute of Science and Technology Department of Computing Technologies Chennai India Srm Institute of Science and Technology Department of Networking and Communications Chennai India

ISBN: (纸本)9798350377002

IoT for smart microgrids is an innovative disruption at the cutting edge of energy management, relying on interconnectedness provided by smart sensors and devices to enhance power generation and distribution precision in metropolitan areas. The problems of the real-time operational capabilities required for efficient energy resource management thus progress, inhibit rapid control and management. The main goal of this research proposal consists of to use of the advanced technology of 5G NR Sidelink combined with MQTT to conduct a revolutionary communication system of Microgrid running through the IoT devices. The 5G NR (New Radio) Sidelink enables direct D2D communication, which leads to a dramatic lowering of the latency in the absence of traditional network infrastructures for communication, while the MQTT protocol improves the communication efficiency among networks of numerous IoT devices. The introduction of this system was followed by a 15% decrease in energy transmission losses and by 20% improvement in response times in comparison to conventional models specified in the quantitative evaluation thus increasing operational efficiency by far. These efficiencies not only reduce operating expenses and power consumption but also increase the solution's scalability, pointing out the possibility of building the solution for bigger urban microgrid implementations. In consideration of that, the suggested mechanism with 5G NR Sidelink along with MQTT overcomes elaborate barriers of IoT-based microgrids and establishes a new potency in advanced energy management in smart cities which could make the distribution network in the urban areas on the edge of the verge of a change. © 2024 IEEE.

关键词： Microgrids

来源：评论

学校读者我要写书评

暂无评论

GIDCL: A Graph-Enhanced Interpretable data Cleaning Framework with Large Language Models

引用

Proceedings of the ACM on Management of data 2024年第6期2卷 1-29页

作者： Mengyi Yan Yaoshu Wang Yue Wang Xiaoye Miao Jianxin Li School of Computer Science and Engineering Beihang University Beijing CN Shenzhen Institute of Computing Sciences Shenzhen University Shenzhen Guangdong CN Shenzhen Institute of Computing Sciences Shenzhen Guangdong CN Center for Data Science Zhejiang University Hangzhou Zhejiang CN

data quality is critical across many applications. The utility of data is undermined by various errors, making rigorous data cleaning a necessity. Traditional data cleaning systems depend heavily on predefined rules and constraints, which necessitate significant domain knowledge and manual effort. Moreover, while configuration-free approaches and deep learning methods have been explored, they struggle with complex error patterns, lacking interpretability, requiring extensive feature engineering or labeled data. This paper introduces GIDCL (Graph-enhanced Interpretable data Cleaning with Large language models), a pioneering framework that harnesses the capabilities of Large Language Models (LLMs) alongside Graph Neural Network (GNN) to address the challenges of traditional and machine learning-based data cleaning methods. By converting relational tables into graph structures, GIDCL utilizes GNN to effectively capture and leverage structural correlations among data, enhancing the model's ability to understand and rectify complex dependencies and errors. The framework's creator-critic workflow innovatively employs LLMs to automatically generate interpretable data cleaning rules and tailor feature engineering with minimal labeled data. This process includes the iterative refinement of error detection and correction models through few-shot learning, significantly reducing the need for extensive manual configuration. GIDCL not only improves the precision and efficiency of data cleaning but also enhances its interpretability, making it accessible and practical for non-expert users. Our extensive experiments demonstrate that GIDCL significantly outperforms existing methods, improving F1-scores by 10% on average while requiring only 20 labeled tuples.

关键词： data quality graph neural network interpretable large language models

来源：评论

学校读者我要写书评

暂无评论

TEXT-TO-IMAGE RECTIFIED FLOW AS PLUG-AND-PLAY PRIORS

arXiv

引用

arXiv 2024年

作者： Yang, Xiaofeng Chen, Cheng Yang, Xulei Liu, Fayao Lin, Guosheng College of Computing and Data Science Nanyang Technological University Singapore Institute for Infocomm Research A*STAR Singapore

Large-scale diffusion models have achieved remarkable performance in generative tasks. Beyond their initial training applications, these models have proven their ability to function as versatile plug-and-play priors. For instance, 2D diffusion models can serve as loss functions to optimize 3D implicit models. Rectified Flow, a novel class of generative models, has demonstrated superior performance across various domains. Compared to diffusion-based methods, rectified flow approaches surpass them in terms of generation quality and efficiency. In this work, we present theoretical and experimental evidence demonstrating that rectified flow based methods offer similar functionalities to diffusion models — they can also serve as effective priors. Besides the generative capabilities of diffusion priors, motivated by the unique time-symmetry properties of rectified flow models, a variant of our method can additionally perform image inversion. Experimentally, our rectified flow based priors outperform their diffusion counterparts — the SDS and VSD losses — in text-to-3D generation. Our method also displays competitive performance in image inversion and editing. Code is available at: https://***/yangxiaofeng/rectified flow prior. © 2024, CC BY.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Feature Augmentation for Domain Generalization

arXiv

引用

arXiv 2024年

作者： Liu, Yingnan Zou, Yingtian Qiao, Rui Liu, Fusheng Lee, Mong Li Hsu, Wynne School of Computing National University of Singapore Singapore Institute of Data Science National University of Singapore Singapore

Domain generalization aims to develop models that are robust to distribution shifts. Existing methods focus on learning invariance across domains to enhance model robustness, and data augmentation has been widely used to learn invariant predictors, with most methods performing augmentation in the input space. However, augmentation in the input space has limited diversity whereas in the feature space is more versatile and has shown promising results. Nonetheless, feature semantics is seldom considered and existing feature augmentation methods suffer from a limited variety of augmented features. We decompose features into class-generic, class-specific, domain-generic, and domain-specific components. We propose a cross-domain feature augmentation method named XDomainMix that enables us to increase sample diversity while emphasizing the learning of invariant representations to achieve domain generalization. Experiments on widely used benchmark datasets demonstrate that our proposed method is able to achieve state-of-the-art performance. Quantitative analysis indicates that our feature augmentation approach facilitates the learning of effective models that are invariant across different domains. Our code is available at https://***/NancyQuris/XDomainMix. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Drawing and Analysis of Bounding Boxes for Object Detection with Anchor-Based Models 23rd

Drawing and Analysis of Bounding Boxes for Object Detecti...

引用

22nd Scandinavian Conference on Image Analysis, SCIA 2023

作者： Madan, Manav Reich, Christoph Hassenpflug, Frank Institute for Data Science Cloud Computing and IT Security Furtwangen University Furtwangen Germany C.R.S. iiMotion GmbH Peterzeller Str. 8 Villingen-Schwenningen78048 Germany

ISBN: (纸本)9783031314346

Supervised object detection models are trained to recognize certain objects. These models are classified into two types: single-stage detectors and two-stage detectors. The single-stage detectors just need one pass through the model to anticipate all the bounding boxes, whereas the two-stage detectors require to first estimate the image portions where the object could be located. Due to their speed and simplicity, single-stage anchor-based models are used in many industrial settings. Training such models require bounding boxes that describe the spatial location of an object, which are usually drawn by an expert. However, the question remains, how much area should be considered when drawing the bounding boxes? In this paper, we demonstrate the effects that the size and placement of a rectangular bounding box can have on the performance of the anchor-based models. For this, we first perform experiments on a synthetically generated binary dataset and then on a real-world object detection dataset. Our results show that fixing the size of the bounding boxes can help in improving the performance of the model in the case of single class object detection (approximately 50% improvement in mAP@[.5:.95] for real world dataset). Furthermore, we also demonstrate how freely available tools can be combined for obtaining the best possible semi automated object labeling pipeline. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Measuring COVID-19 Opinion in the Online Debate using an Unsupervised Model 1

Measuring COVID-19 Opinion in the Online Debate using an Uns...

引用

1st IEEE International Conference on Automation, computing and Renewable Systems, ICACRS 2022

作者： Priyadarsini, K. Jeba Sonia, J. Vijayalakshmi, K. Anbazhagu, U.V. Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai603203 India Department of Computational Intelligence School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai603203 India Department of Computing Technologies School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai603203 India

ISBN: (纸本)9781665460842

A large quantity of potentially threatening COVID-19 false information is available online. In this article, machine learning approach is adopted to assess COVID-19 materials in online health advice adversaries, particularly those who oppose immunizations like (anti-vaccine). Pro-vaccination (pro-vaccine) group is emerging a more attentive conversation regarding COVID-19 above its corresponding portion, the anti-vaccine group. However, the anti-vaccine group presents a wide series of flavors of COVID-19-relatedtopics, andas a result, can demandto a wider cross-section of entities searching for COVID-19 assistance online, such as those who may be wary of receiving a COVID-19 vaccine as a condition of employment or those looking for alternative medications. Later, the anti-vaccine group appears to be better positioned than the pro-vaccine side to obtain complete support moving forward. This is important because if the COVID-19 vaccine is not widely used, the world will not be able to produce herd immunity, parting countries exposed to a COVID-19 comeback in the future. An automatic supervision machine learning model is provided that clarifies these results andcan be used to evaluate the efficacy of intervention efforts. Our method is adaptable and capable of addressing the crucial problem that social media platforms face when analyzing the vast amounts of online health misinformation. © 2022 IEEE

关键词： COVID-19

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：