检索结果-内蒙古大学图书馆

2024 International Conference on Distributed Systems, computer Networks and Cybersecurity, ICDSCNC 2024

作者： Gowri, A.S. Jose, P. Karthik, S.M. Shaheema, S Berlin Karuppasway, K.M. Balamurugan, R. School of Computing Srm Institute of Science and Technology Department of Networking and Communications Kattankulathur India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India Department for Applied Research Gandhigram India Stella Mary's College of Engineering Department of Artificial Intelligence and Data Science Azhikal India Bharath Institute of Higher Education and Research Department of Mathematics and Statistics Chennai India Dmi College of Engineering Department of Information Technology Chennai India

ISBN: (纸本)9798350375442

Diabetes is a metabolic disease that affects a large number of the global population and is incurable. The primary causes of death symptoms are kidney failure, heart attacks, strokes, and blindness. In this paper Principal component analysis used for pre-processing the data to extract features and The Efficient Hybrid Machine Learning Model Convolution Neural Network-Support Vector Machine is used to categorize the Pima Indian dataset. CNN and non-linear SVM used in a hybrid model to classify the diabetes data from the Pima Indians. To identify positive classes of pima Indians diabetes, the HCNN-SVM extract the features from the original data expression and learns diabetes data through a novel convolution network environment to the SVM classifier with RBF function and achieve the accuracy as 98,04%. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Framework for Controllable Pareto Front Learning with Completed Scalarization Functions and its Applications

arXiv

引用

arXiv 2023年

作者： Tuan, Tran Anh Hoang, Long P. Le, Dung D. Thang, Tran Ngoc School of Applied Mathematics and Informatics Hanoi University of Science and Technology Hanoi Viet Nam College of Engineering and Computer Science VinUniversity Hanoi Viet Nam

Pareto Front Learning (PFL) was recently introduced as an efficient method for approximating the entire Pareto front, the set of all optimal solutions to a Multi-Objective Optimization (MOO) problem. In the previous work, the mapping between a preference vector and a Pareto optimal solution is still ambiguous, rendering its results. This study demonstrates the convergence and completion aspects of solving MOO with pseudoconvex scalarization functions and combines them into Hypernetwork in order to offer a comprehensive framework for PFL, called Controllable Pareto Front Learning. Extensive experiments demonstrate that our approach is highly accurate and significantly less computationally expensive than prior methods in term of inference time. Copyright © 2023, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

A Noise-Model-Free Hyperspectral Image Denoising Method Based on Diffusion Model

A Noise-Model-Free Hyperspectral Image Denoising Method Base...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Keli Deng Zhongshun Jiang Qipeng Qian Yi Qiu Yuntao Qian College of Computer 0Science Zhejiang University Hangzhou China Department of Applied Mathematics University of Arizona Tucson AZ College of Engineering Huzhou University Huzhou China

Hyperspectral Image (HSI) denoising is a crucial preprocessing step to ensure the accuracy of the subsequent HSI analysis and interpretation. Neural network methods recently achieve state-of-the-art performance in HSI denoising. Nevertheless, these methods are typically trained on specific noise models, which could limit their performance as noise models in HSI may vary across different spectral bands. To mitigate this problem, we introduce an HSI denoising method based on the Diffusion Model (DM) whose training process is independent of the noise model, noted as a noise-model-free method. In this method, we first introduce a DM for HSI by increasing the input and output dimensions to incorporate spectral and spatial information. We then derive a DM-based HSI denoising process for a common noise model. Moreover, to address the issue of overfitting during training, we have introduced a stochastic sampling method to more effectively balance the significance of both spatial and spectral information. Experimental results on in-distribution and out-of-distribution samples demonstrate the efficacy of our approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Partitions into an exact number of parts

引用

The Ramanujan Journal 2025年第3期67卷 1-19页

作者： Ballantine, Cristina Merca, Mircea Department of Mathematics and Computer Science College of The Holy Cross Worcester USA Department of Mathematical Methods and Models Fundamental Sciences Applied in Engineering Research Center National University of Science and Technology Politehnica Bucharest Bucharest Romania Academy of Romanian Scientists Bucharest Romania

In this paper, we examine the functions $$P_k(n)$$ , which counts the partitions of n into exactly k parts, and $$Q_k(n)$$ , which counts the partitions of n into exactly k distinct parts. These partition functions are closely linked to two classical identities of Euler. We explore this connection and establish several new relationships between $$P_k(n)$$ and $$Q_k(n)$$ . We give both analytic and combinatorial proofs of the theorems.

关键词： Convolution identities Distinct partitions Partitions

来源：评论

学校读者我要写书评

暂无评论

Price Prediction of Seasonal Items Using Time Series Analysis

引用

computer Systems Science & engineering 2023年第7期46卷 445-460页

作者： Ahmed Salah Mahmoud Bekhit Esraa Eldesouky Ahmed Ali Ahmed Fathalla Faculty of Computers and Informatics Zagazig UniversitySharkeya44523Egypt Information Technology Department the University of Technology and Applied SciencesIbriOman School of Electrical and Data Engineering University of Technology SydneySydney2007Australia College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Computer Science Department Faculty of Computers and InformaticsSuez Canal UniversityIsmailia41522Egypt Higher Future Institute for Specialized Technological Studies Cairo3044Egypt Department of Mathematics Faculty of ScienceSuez Canal UniversityIsmailia41522Egypt

The price prediction task is a well-studied problem due to its impact on the business *** are several research studies that have been conducted to predict the future price of items by capturing the patterns of price change,but there is very limited work to study the price prediction of seasonal goods(e.g.,Christmas gifts).Seasonal items’prices have different patterns than normal items;this can be linked to the offers and discounted prices of seasonal *** lack of research studies motivates the current work to investigate the problem of seasonal items’prices as a time series *** proposed utilizing two different approaches to address this problem,namely,1)machine learning(ML)-based models and 2)deep learning(DL)-based ***,this research tuned a set of well-known predictive models on a real-life *** models are ensemble learning-based models,random forest,Ridge,Lasso,and Linear ***,two new DL architectures based on gated recurrent unit(GRU)and long short-term memory(LSTM)models are ***,the performance of the utilized ensemble learning and classic ML models are compared against the proposed two DL architectures on different accuracy metrics,where the evaluation includes both numerical and visual comparisons of the examined *** obtained results show that the ensemble learning models outperformed the classic machine learning-based models(e.g.,linear regression and random forest)and the DL-based models.

关键词： Deep learning price prediction seasonal goods time series analysis

来源：评论

学校读者我要写书评

暂无评论

Design Considerations for Hybrid Underwater Target Tracking: Integrating Particle Filters and Deep Learning for Enhanced Decision

Design Considerations for Hybrid Underwater Target Tracking:...

引用

Decision Aid Sciences and Application (DASA), International Conference on

作者： Abdullatif Baba Basil Alothman Maha Shabon Ziad Salem Computer Science and Engineering Department Kuwait College of Science and Technology (KCST) Kuwait Computer Engineering Department University of Turkish Aeronautical Association (UTAA) Ankara Türkiye Computer Science Department Center for Applied Mathematics and Bioinformatics (CAMB) Gulf University for Science and Technology (GUST) Hawally Kuwait

ISBN: (数字)9798350369106

ISBN: (纸本)9798350369113

This paper delves into the key characteristics of Autonomous underwater vehicle (AUV) design, highlighting considerations such as hull structure, hydrodynamics, propulsion systems, and sensor integration. The main contribution of this paper is the tracking of underwater dynamic targets, distinguishing between reactive and deliberative tracking levels by proposing a novel hybrid tracking approach, the Multiple Model Particle Filter (MMPF), that integrates deep learning to predict dynamic target trajectory. Finally, a few simulations are delivered to demonstrate the efficiency of the proposed approach in tracking underwater maneuvering targets under different trajectory scenarios.

关键词： Deep learning Autonomous underwater vehicles Target tracking Simultaneous localization and mapping Navigation Particle filters Trajectory Safety Security Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Data Analytics on Eco-Conditional Factors Affecting Speech Recognition Rate of Modern Interaction Systems

引用

Journal of Mobile Multimedia 2022年第4期18卷 1153-1176页

作者： Kaladevi, A.C. Saravanakumar, R. Veena, K. Muthukumaran, V. Thillaiarasu, N. Kumar, S. Satheesh Department of Computer Science and Engineering Sona College of Technology Salem India Department of CSE Dayananda Sagar Academy of Technology and Management Bangalore 560082 India Department of Computer Science J.K.K.Nataraja College of Arts & Science Namakkal Dt. Komarapalayam India Department of Mathematics School of Applied Sciences REVA University Karnataka Bengaluru India School of Computing and Information Technology REVA University Bengaluru India Department of Computer Science School of Applied Sciences REVA University Bengaluru India

Speech-based Interaction systems contribute to the growing class of contemporary interactive techniques (Human-computer Interactive system), which have emerged quickly in the last few years. Versatility, multi-channel synchronization, sensitivity, and timing are all notable characteristics of speech recognition. In addition, several variables influence the precision of voice interaction recognition. However, few researchers have done a significant study on the five eco-condition variables that tend to affect speech recognition rate (SRR): ambient noise, human noise, utterance speed, and frequency. The principal strategic goal of this research is to analyze the influence of the four variables mentioned earlier on SRR, and it includes many stages of experimentation on mixed noise speech data. The sparse representation-based analyzing technique is utilized to analyze the effects. Speech recognition is not noticeably affected by a person's usual speaking pace. As a result, high-frequency voice signals are more easily recognized (∼98.12%) than low-frequency speech signals in noisy environments. By performing the experiments, the test results may help design the distributive controlling and commanding systems. © 2022 River Publishers.

关键词： ambient noise eco-conditional factors frequency human noise Interaction system recognition rate utterance speed

来源：评论

学校读者我要写书评

暂无评论

Study of fuzzy expert system for the diagnosis of various types of cancer

引用

Materials Today: Proceedings 2022年 56卷 298-307页

作者： Boadh, Rahul Grover, Reena Dahiya, Mamta Kumar, Ajay Rathee, Rakesh Rajoria, Yogendra Kumar Rawat, Meena Rani, Sangeeta Department of the Mathematics School of Basic and Applied Science K.R. Mangalam University Sohna Road Gurugram Haryana 122103 India Department of Mathematics Faculty of Engineering and Technology SRM Institute of Science and Technology Delhi-NCR Campus U.P. Ghaziabad India Department of Computer Science and Engineering Faculty of Engineering and Technology Shree Guru Govind Singh Tricentenary University Haryana Gurugram122505 India Department of Mechanical Engineering Faculty of Engineering and Technology Shree Guru Govind Singh Tricentenary University Haryana Gurugram122505 India University Institute of Engineering and Technology Maharshi Dayanand University Haryana Rohtak124001 India Department of Computer Science and Engineering World College of Technology and Management Gurgaon122506 India

Early exposure of critical diseases is the main necessity for the patients and a difficult errand for the oncologist. In the event that it is distinguished early, it makes the patient bound to live. Lately, the fuzzy rationale has shown up as a dynamical strategy in the acknowledgment of illnesses like various sorts of malignant growths. For the most part, the identification of malignant growths illnesses is taken care of with vagary, mistake, and unclearness yet very much worked by utilizing fuzzy rationale-based models. This paper surveys a few techniques for the early identification of diseases to sum things up. By using fuzzy artificial intelligent Programme, created calculation;patient information alongside master specialist's recommendation, any quiet's infections can be analyzed early which lessen mortality and grimness. This review gives a proposal that a fuzzy approach running smoothly in multiple regions to the diagnosis of cancers. © 2022

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Logic-Based Deep Learning for Human-Machine Interaction and Gesture Recognition in Uncertain and Noisy Environments

Fuzzy Logic-Based Deep Learning for Human-Machine Interactio...

引用

Advances in computer Science, Electrical, Electronics, and Communication Technologies (CE2CT), International Conference on

作者： John Anand V. Thamilarasi Ashish Rayal Himanshu Kumar Gupta Kamboji Jyothi Pramatma Vishwakarma Department of Computer Science & Engineering (AI) IIMT College of Engineering Greater Noida India Department of Computer Science & Engineering Sri Sarada College for Women(Autonomous) Salem-16 Tamilnadu India Department of Mathematics School of Applied and Life Sciences Uttaranchal University Dehradun India Department of Electrical Engineering Bipin Tripathi Kumaon Institute of Technology Dwarahat Almora India Department of Mathematics Chaitanya Bharathi Institute of Technology Proddatur AP India Department of Computer Aplication Lovely Professional University Punjab India

ISBN: (数字)9798331518578

ISBN: (纸本)9798331518585

Conventional deep learning methods have considerable hurdles when it comes to Human-Machine Interaction (HMI) and gesture identification in noisy and uncertain situations. A Fuzzy Logic-Based Deep Learning (Fuzzy DL) method is presented in this work to improve the resilience, accuracy, and adaptability of human gesture recognition in a variety of scenarios. We test several algorithms on various datasets, lighting situations, and noise levels, such as CNN, LSTM, Transformer, and Fuzzy DL. The outcomes show that Fuzzy DL functions better than other systems, retaining 91.0% accuracy at high noise levels and reaching 97.5% accuracy under typical circumstances. In comparison to traditional structures, it also shows faster inference times and a lower mean squared error. Its superiority is further demonstrated by comparative analysis on precision, recall, and F1-score. This study presents a robust and noise-resilient solution for real-world HMI applications, including as assistive systems and virtual interfaces. The outcomes indicate that incorporating fuzzy logic with DL substantially enhances gesture recognition in difficult environments.

关键词： Deep learning Human computer interaction Fuzzy logic Accuracy Gesture recognition Transformers Noise measurement Long short term memory Noise level Resilience

来源：评论

学校读者我要写书评

暂无评论

Open set label noise learning with robust sample selection and margin-guided module

引用

Knowledge-Based Systems 2025年 321卷

作者： Zhao, Yuandi Xia, Qianxi Sun, Yang Wen, Zhijie Ma, Liyan Ying, Shihui College of Air Traffic Management Civil Aviation University of China Tianjin300300 China Department of Mathematics College of Sciences Shanghai University Shanghai200444 China School of Computer Engineering and Science Shanghai University Shanghai200444 China Shanghai Institute of Applied Mathematics and Mechanics Shanghai University Shanghai200072 China School of Mechanics and Engineering Science Shanghai University Shanghai200072 China

In recent years, the remarkable success of deep neural networks (DNNs) in computer vision is largely due to large-scale, high-quality labeled datasets. Training directly on real-world datasets with label noise may result in overfitting. The traditional method is limited to deal with in-distribution (ID) label noise, where noisy training data has true class labels within the known label space. However, there are some real-world datasets containing out-of-distribution (OOD) label noise, meaning that some samples belong to an unknown class outside the known label space. To address the OOD label noise problem, we introduce a method based on Robust Sample Selection and Margin-Guided Module (RSS-MGM). Firstly, unlike the prior clean sample selection approach, which only selects a limited number of clean samples, a robust sample selection module combines small loss selection and high-confidence sample selection to obtain more clean samples. Secondly, to efficiently distinguish OOD label noise and ID ones, margin functions are designed to filter OOD data and ID data. Thirdly, different processing methods are selected for different types of samples in order to fully utilize the data's prior information and optimize the whole model. Furthermore, extensive experimental results with noisy labeled data from benchmark datasets and real-world datasets, such as CIFAR-100N-C, CIFAR80N-O, WebFG-469, and Food101N, indicate that our approach outperforms many state-of-the-art label noise learning methods. Especially, it can more accurately divide OOD label noise and ID ones. © 2025 Elsevier B.V.

关键词： Deep neural networks

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：