检索结果-内蒙古大学图书馆

International Conference on Computing for Sustainable Global Development (INDIACom)

作者： N. Murali R. Rajesh S. Sridharan A. Emmanuel Peo Mariadas S. Palani Murugan S. Manikandan Department of Department of Computer Science and Engineering E.G.S. Pillay Engineering College Nagapattinam Tamil Nadu India Department of Computer Science and Engineering E.G.S. Pillay Engineering College Nagapattinam Tamil Nadu India Department of Computer Science and Engineering University College of Engineering Thirukkuvalai Tamil Nadu India Department of Artificial Intelligence and Data Science E.G.S. Pillay Engineering College Nagapattinam Tamil Nadu India Department of Information Technology E.G.S. Pillay Engineering College Nagapattinam Tamil Nadu India

The system is a face-based attendance system for students that make use of multi-CNN (Convolutional Neural Network) technology with GPS tracking. The device simplifies the process of taking attendance for both teachers and students while offering precise and effective attendance monitoring. The method makes use of GPS tracking to pinpoint the location of student and get confirmation of their attendance. The multi CNN technology is utilized to improve the attendance’s accuracy. Tracking multiple CNN models are combined in the multi-CNN system to increase the process’s accuracy for tracking attendance. Additionally, the system makes use of facial recognition technologies to make sure. The appropriate pupil is noted as present. When a student leaves a class, the department head and parents are both notified at the same time. A web-based dashboard and a mobile app for students and teachers make up the system. Every database is kept in cloud storage.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Evaluation of AI-Driven data Mining Techniques for Large-Scale data Processing

An Evaluation of AI-Driven Data Mining Techniques for Large-...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Sheetal Choudhary Naghma Khatoon K. Ranjith Singh Divya K Santosh D. Kumar Abhishek Kumar Gupta Department of Computer Science Himalayan University Itanagar India Department of Coputing & Information Technology Usha Martin University Ranchi India Department of Computer Science Karpagam Academy of Higher Education Coimbatore Department of Electronics and Communication Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Artificial Intelligence & Data Science Vishwakarma Institute of Information Technology Pune India Department of Computer Science Mangalayatan University Aligarh India

Information mining and synthetic intelligence (AI) have gained a lot interest in recent years in the discipline of large-scale statistics processing. AI-driven statistics mining strategies are especially effective for identifying beneficial styles and functions in huge datasets. This paper presents an assessment of several typically used AI-pushed information mining techniques for processing big datasets and compares their performance in phrases of pace, accuracy, and scalability. Not unusual algorithms including precept component evaluation and clustering analysis are evaluated and in comparison to recent advances in AI-driven records mining which includes deep mastering and associative statistics mining. The overall performance of every technique is measured throughout 3 categories: speed, accuracy, and scalability. The effects of the evaluation show that deep learning and associative information mining outperform the conventional strategies in terms of accuracy and scalability whilst they're fairly slower than the other techniques. Therefore, these algorithms can be more suitable for positive types of massive-scale statistics processing tasks that require excessive accuracy and scalability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

data-Driven LQR Design for LTI systems with Exogenous Inputs

Data-Driven LQR Design for LTI systems with Exogenous Inputs

引用

Mediterranean Conference on Control and Automation (MED)

作者： Vijayanand Digge Ramkrishna Pasumarthy Department of Electrical Engineering Indian Institute of Technology Madras Chennai India Department of Electrical Engineering Robert Bosch Center of Data Science and Artificial Intelligence Network Systems Learning Control and Evolution Group Indian Institute of Technology Madras Chennai India

ISBN: (数字)9781665406734

ISBN: (纸本)9781665406741

This paper presents a data-driven state feedback control law, based on a linear quadratic regulator (LQR) design, for systems with exogenous inputs. In general, this framework is referred to as a data-driven min-max controller, and is more robust to disturbances than the standard LQR controllers. Instead of relying on system models, in this work, the state feedback control law is computed directly from the knowledge of the inputs and the states. The LQR gain is parametrized with matrices that are directly estimated using open-loop experiment data of the system. We experimentally validate our results by implementing the data driven controller for performance management of a web-server hosted on a private cloud.

关键词： Linear systems State feedback Regulators Riccati equations Markov processes Mathematical models Parametric statistics

来源：评论

学校读者我要写书评

暂无评论

Learning Counterfactual Outcomes Under Rank Preservation

arXiv

引用

arXiv 2025年

作者： Wu, Peng Li, Haoxuan Zheng, Chunyuan Zeng, Yan Chen, Jiawei Liu, Yang Guo, Ruocheng Zhang, Kun School of Mathematics and Statistics Beijing Technology and Business University China Center for Data Science Peking University China School of Mathematical Sciences Peking University China College of Computer Science and Technology Zhejiang University China Computer Science and Engineering University of California Santa Cruz Bolivia ByteDance Research China Department of Philosophy Carnegie Mellon University United States Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates

Counterfactual inference aims to estimate the counterfactual outcome at the individual level given knowledge of an observed treatment and the factual outcome, with broad applications in fields such as epidemiology, econometrics, and management science. Previous methods rely on a known structural causal model (SCM) or assume the homogeneity of the exogenous variable and strict monotonicity between the outcome and exogenous variable. In this paper, we propose a principled approach for identifying and estimating the counterfactual outcome. We first introduce a simple and intuitive rank preservation assumption to identify the counterfactual outcome without relying on a known structural causal model. Building on this, we propose a novel ideal loss for theoretically unbiased learning of the counterfactual outcome and further develop a kernel-based estimator for its empirical estimation. Our theoretical analysis shows that the rank preservation assumption is not stronger than the homogeneity and strict monotonicity assumptions, and shows that the proposed ideal loss is convex, and the proposed estimator is unbiased. Extensive semi-synthetic and real-world experiments are conducted to demonstrate the effectiveness of the proposed method. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Forward Kinematics Analysis of 6-PUS Parallel Mechanism based on Optimized BP-NR Algorithm

Forward Kinematics Analysis of 6-PUS Parallel Mechanism base...

引用

IEEE International Conference on Mechatronics and Automation

作者： Wenjing Niu Xin Guo Wenyuan Liang Peng Fang School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin China Ministry of Education Engineering Research Center for Intelligent Rehabilitation Device and Detection Technology Tianjin China Qinhuangdao Research Institute of National Rehabilitation Aids Research Center Qinhuangdao China National Research Center for Rehabilitation Aids Beijing China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

This paper analyzes in detail the forward kinematics of 6-PUS parallel mechanism using MATLAB , SolidWorks and Adams software. The proposed algorithm combines the BP Neural Network with the Newton-Raphson method to form BP-NR algorithm. The BP neural network computes an approximation of the kinematic forward solution of the mechanism, which is used as the initial value of Newton-Raphson method for iterative computation to obtain the exact solution. Simulation verification shows that the BP-NR algorithm can simultaneously achieve high accuracy and real-time performance.

关键词： Accuracy Neural networks Software algorithms Kinematics Approximation algorithms Prediction algorithms Software

来源：评论

学校读者我要写书评

暂无评论

A Motion Flow Guided MicroNet Framework for Micro Expression Recognition

TechRxiv

引用

TechRxiv 2022年

作者： Verma, Monu Vipparthi, Santosh Kumar Singh, Girdhari The Electrical and Computer Engineering University of Miami FL33155 United States The Mehta Family School of Data Science and Artificial Intelligence IIT Guwahati 781039 India The Department of Computer Science and Engineering Malaviya National Institute of Technology Jaipur302017 India

The micro-expression recognition (MER) has gained high attention in real-world applications: human-computer interaction, depression estimation, virtual reality, etc. However, MER systems still face difficulty in capturing the subtle information with spatial appearance of micro expressions. In this paper, an efficient and robust motion flow guided MicroNet framework is proposed for MER. The proposed MicroNet consists: motion flow generator (MFGen) and avalanche feature (AFeat) block. The MFGen is introduced to extract the temporal changes at expressive regions by analyzing the motion intensity of pixels among the frames. Further, the AFeat block is designed to capture the spatiotemporal feature using a multi-lateral complementary feature (MCFeat) block. The MCFeat block is proposed to elicit the coarse and deep edge responses from multi-scale receptive fields. Thus, the proposed MicroNet estimates not only momentary variations but also learns affective appearance features of micro expressions. Furthermore, the efficacy of the proposed MicroNet is examined by conducting experiments on two experimental setups using six comprehensive datasets: CASME-I, CASME-II, CAS(ME)2, SAMM, SMIC and COMPOSITE, with two validation schemes: leave-one-subject-out and cross-domain to demonstrate the generalization capacity and robustness of the proposed framework. Also, eight ablation experiments have been executed to validate each module’s role in the MicroNet framework. © 2022, CC BY.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

AN EXPLAINABLE ATTENTION MODEL FOR CERVICAL PRECANCER RISK CLASSIFICATION USING COLPOSCOPIC IMAGES

arXiv

引用

arXiv 2024年

作者： Khare, Smith K. Booth, Berit Bargum Blanes-Vidal, Victoria Petersen, Lone Kjeld Nadimi, Esmaeil S. Applied AI and Data Science Unit Mærsk Mc-Kinney Møller Institute Faculty of Engineering University of Southern Denmark Odense Denmark Centre for Clinical Artificial Intelligence Odense University Hospital Odense Denmark Centre for Department of Gynecology and Obstetrics Odense University Hospital Odense Denmark Odense University Hospital Odense Denmark

Cervical cancer remains a major worldwide health issue, with early identification and risk assessment playing critical roles in effective preventive interventions. This paper presents the Cervix-AID-Net model for cervical precancer risk classification. The study designs and evaluates the proposed Cervix-AID-Net model based on patients colposcopy images. The model comprises a Convolutional Block Attention Module (CBAM) and convolutional layers that extract interpretable and representative features of colposcopic images to distinguish high-risk and low-risk cervical precancer. In addition, the proposed Cervix-AID-Net model integrates four explainable techniques, namely gradient class activation maps, Local Interpretable Model-agnostic Explanations, CartoonX, and pixel rate distortion explanation based on output feature maps and input features. The evaluation using holdout and tenfold cross-validation techniques yielded a classification accuracy of 99.33% and 99.81%. The analysis revealed that CartoonX provides meticulous explanations for the decision of the Cervix-AID-Net model due to its ability to provide the relevant piece-wise smooth part of the image. The effect of Gaussian noise and blur on the input shows that the performance remains unchanged up to Gaussian noise of 3% and blur of 10%, while the performance reduces thereafter. A comparison study of the proposed model’s performance compared to other deep learning approaches highlights the Cervix-AID-Net model’s potential as a supplemental tool for increasing the effectiveness of cervical precancer risk assessment. The proposed method, which incorporates the CBAM and explainable artificial integration, has the potential to influence cervical cancer prevention and early detection, improving patient outcomes and lowering the worldwide burden of this preventable disease. © 2024, CC BY.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Solving the Traveling Salesperson Problem using Frequency Fitness Assignment

Solving the Traveling Salesperson Problem using Frequency Fi...

引用

IEEE Symposium Series on Computational intelligence (SSCI)

作者： Tianyu Liang Zhize Wu Jörg Lässig Daan van den Berg Thomas Weise Institute of Applied Optimization School of Artificial Intelligence and Big Data Hefei University Hefei Anhui China Enterprise Application Development Group Faculty of Electrical Engineering and Computer Science Höchschule Zittau/Gorlitz Görlitz Germany Department of Computer Science Vrije Universiteit Amsterdam Amsterdam The Netherlands Institute of Applied Optimization School of Artificial Intelligence and Big Data Hefei Anhui China

ISBN: (纸本)9781665487696

Metaheuristic optimization is based on the idea that better solutions are preferable to worse ones. Frequency Fitness Assignment (FFA) is a module that can be plugged into most optimization algorithms. It replaces the objective values in the selection step with their encounter frequency during the search so far. The search effort is therefore distributed evenly over the whole range of the objective values. Recently, it was shown that using FFA can significantly improve the performance of algorithms on hard problems such as Trap and Jump functions and the NP-hard MaxSat problem. However, the objective functions of all of these problems have relatively small ranges. This work is the first to explore the impact of FFA on metaheuristics for solving Traveling Salesperson Problem (TSP) instances, whose objective values tend to cover a wider range. We plug FFA into the (1+1) EA to obtain the (1+1) FEA. We perform extensive experiments on 18 instances from TSPLIB using two different unary search operators. We find that the (1+1) FEA does not get stuck in local optima and can solve many more instances to optimality than the (1+1) EA. However, it tends to be slower in reaching good intermediate solutions. Its performance decreases with the problem scale and the number of different possible tour lengths.

关键词： Metaheuristics Search problems Linear programming Computational intelligence Plugs

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Prediction Using a Deep Learning Algorithm on the Cloud Medical data

Breast Cancer Prediction Using a Deep Learning Algorithm on ...

引用

Self Sustainable artificial intelligence Systems (ICSSAS), International Conference on

作者： C. Tamilselvi M. Sindhuja S. Hemamalini S. Lincy Jemina Batini Dhanwanth Mohanaprakash T A Department of IT Dr. MGR Educational and Research Institute Chennai India Department of CSE Sree Sastha Institute of Engineering and Technology Chennai India Department of Artificial Intelligence and Data Science Panimalar Engineering college Chennai India Department of CSE Panimalar Engineeering College Chennai India Department of CSE Panimalar Institute of Technology Chennai India

Recent strides in data generation have given rise to an unprecedented surge in information accumulation, marking the advent of the big data era. Unfortunately, conventional machine learning algorithms find it challenging to adeptly manage the distinctive characteristics presented by big data. This study is centered on the task of breast cancer prediction in the midst of this data-rich landscape. Specifically, we delve into two pivotal data types: gene expression (GE) and DNA methylation (DM).Our objective revolves around unlocking the potential of Deep Learning algorithms, both when applied individually to each dataset and when they come together in synergy. For this purpose, we've elected MATLAB as our primary platform. At the heart of breast cancer prediction, we employ the Convolutional Neural Network (CNN) algorithm, renowned for its proficiency in pattern recognition and feature extraction. Our study is underpinned by a comprehensive analysis that encompasses GE, DM, and the amalgamated GE and DM ***, we gauge the performance of the CNN algorithm by placing it head-to-head with the Random Forest (RF) algorithm, a widely adopted choice in machine learning for classification tasks. The outcomes of our experiments vividly underscore the superiority of our approach, especially when we harness the potential of the GE dataset. This particular configuration yielded the highest accuracy and the most cost-effective results among all the classifiers considered. These findings serve as a beacon, illuminating the remarkable efficacy of Deep Learning techniques in the domain of breast cancer prediction, particularly when set against the backdrop of big data. This study underscores the remarkable potential of Deep Learning algorithms as they navigate the complex healthcare landscape and promises more accurate, cost-efficient diagnostic tools on the horizon.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Understanding the Limitations of Secure Shell (SSH) in Wireless Network Security

Understanding the Limitations of Secure Shell (SSH) in Wirel...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Amit Upadhyay Sandip Kulkarni Sharmistha Roy K. Yuvaraj V. Ashok Sunil D. Kale Department of Computer Science Mangalayatan University Aligarh India Department of Computer Science Himalayan University Itanagar India Department of Coputing & Information Technology Usha Martin University Ranchi India Department of Computer Science Karpagam Academy of Higher Education Coimbatore Department of Mechanical Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Artificial Intelligence & Data Science Vishwakarma Institute of Information Technology Pune INDIA

comfy Shell (SSH) is an effective community protocol used to securely connect devices over a computer community. It gives information encryption for relaxed conversation among clients and servers, and can be used to guard information at the same time as being transmitted over a wi-fi community. But, as with every protocol, there are positive obstacles that should be considered when the usage of SSH to relaxed wi-fi networks. Because of the character of wireless networks, in which records is transmitted through the air, SSH is at risk of numerous vulnerabilities. First, SSH is susceptible to man-in-the- center attacks, which can permit an attacker to intercept the network traffic and examine, alter, or block positive packets. Specially, using SSH makes it viable for an attacker to perform password sniffing, for the reason that protocol does not encrypt the user's login credentials. Additionally, the usage of SSH protocols does now not shield against malware or different malicious software, making it feasible for an attacker to monitor or manipulate an affected system.

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：