检索结果-内蒙古大学图书馆

2024 International Conference on Thermofluids and Manufacturing science, ICTMS 2024

作者： Krishnendu, S. Nagaraja, K.V. Shali, S. Department of Computer Science Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India Computational Science Lab Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India Department of Mechanical Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India

Efficient heat transfer is very crucial for the various industries in electrical, nuclear power, aerospace and automobile fields. By exhibiting improved thermal conductivity, nanofluids have emerged as an alternative for enhanced thermal and energy efficiency applications. The present study examines the movement of nano fluid across a surface that extend when heat radiation and magnetic fields are present. Using appropriate similarity variables, governing partial differential equations are converted to nonlinear ordinary differential equations. engineering factors which are discussed include Nusselt number and skin friction coefficient. Numerical analysis is optimized using the response surface methodology. The Response Surface Methodology (RSM) with face-centred Central Composite Design is utilized to calculate heat flux transfer at the stretched sheet. The interaction of heat radiation, magnetic field parameter, and solid volume fraction are investigated in the present work. It is worth noting that the local Nusselt number responds positively to the magnetic field parameter and the solid volume fraction, whereas the skin friction coefficient responds negatively. © Published under licence by IOP Publishing Ltd.

关键词： Skin friction

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Feamework for Modeling and Analyzing Complex Networks 15

Probabilistic Feamework for Modeling and Analyzing Complex N...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Nair, Lekshmi S Cheriyan, Jo Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Amritapuri India SAINTGITS College of Engineering Department of Computer Science and Engineering Kottayam India

ISBN: (纸本)9798350370249

Complex networks, characterised by intricate structures arising from the relationships and interactions among their constituent elements, play a pivotal role in various domains such as social networks, biological systems, and technological infrastructures. The evolution and dynamics of complex networks are analysed for various applications such as link prediction, information diffusion, and recommendation systems. Recent research has focused on the study of structural motifs and the probabilistic analysis of motifs to capture the dynamics of the network. The motifs, considered building blocks of the larger network structure, are recurrent patterns in the network. This study focuses on the different probabilistic models built on triads, which are sets of three interconnected nodes. We investigate six different probability distributions, including Poisson, Gamma, Exponential, Power Law, Gaussian, Lorentzian, and Gaussian Mixture Models (GMMs) that can be applied in the complex network to capture the insight of the connectivity pattern. The applications of this research extend to refining network models, improving simulations, and enhancing our understanding of the likelihood of observing distinct patterns within complex social networks. © 2024 IEEE.

关键词： Poisson distribution

来源：评论

学校读者我要写书评

暂无评论

Hop-level Direct Preference Optimization for Knowledge Graph Reasoning with Trees

Hop-level Direct Preference Optimization for Knowledge Graph...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Shen, Tiesunlong Wang, Jin Zhang, Xuejie Cambria, Erik School of Information Science and Engineering Yunnan University China College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)9798350368741

Recent advancements in knowledge graph question answering (KGQA) have shown promise, yet existing methods often fail to align with human reasoning patterns. This study proposes HD-PORT (hop-level direct preference optimization for knowledge graph reasoning with trees), a novel approach that combines Monte Carlo Tree Search (MCTS) with hop-level direct preference optimization (HDPO) for KGQA tasks. MCTS simulates human-like reasoning by exploring multiple inference paths in knowledge graphs, generating interpretable reasoning chains and rich hop-level preferences. HDPO then leverages these preferences for model optimization, addressing the limitations of traditional supervised learning and existing DPO methods that focus on overall solution preferences. By optimizing preferences at each reasoning step, HD-PORT more closely mirrors human problem-solving strategies. Experimental results on benchmark datasets demonstrate that HD-PORT significantly outperforms state-of-the-art methods in both accuracy and interpretability, particularly for complex, multi-hop reasoning tasks. © 2025 IEEE.

关键词： Graph signal processing Knowledge graph Large language model Reasoning

来源：评论

学校读者我要写书评

暂无评论

Three-Stage Transfer Learning with AlexNet50 for MRI Image Multi-Class Classification with Optimal Learning Rate

引用

Computer Modeling in engineering & sciences 2025年第1期142卷 155-183页

作者： Suganya Athisayamani A.Robert Singh Gyanendra Prasad Joshi Woong Cho School of Computing Sastra Deemed to be UniversityThanjavur613401India Department of Computational Intelligence SRM Institute of Science and TechnologyKattankulathur603203India Department of AI and Software Engineering Kangwon National UniversitySamcheok25913Republic of Korea Department of Electronics Information and Communication EngineeringKangwon National UniversitySamcheok25913Republic of Korea

In radiology,magnetic resonance imaging(MRI)is an essential diagnostic tool that provides detailed images of a patient’s anatomical and physiological *** is particularly effective for detecting soft tissue ***,radiologists manually interpret these images,which can be labor-intensive and time-consuming due to the vast amount of *** address this challenge,machine learning,and deep learning approaches can be utilized to improve the accuracy and efficiency of anomaly detection in MRI *** manuscript presents the use of the Deep AlexNet50 model for MRI classification with discriminative learning *** are three stages for learning;in the first stage,the whole dataset is used to learn the *** the second stage,some layers of AlexNet50 are frozen with an augmented dataset,and in the third stage,AlexNet50 with an augmented dataset with the augmented *** method used three publicly available MRI classification datasets:Harvard whole brain atlas(HWBA-dataset),the school of Biomedical engineering of Southern Medical University(SMU-dataset),and The National Institute of Neuroscience and Hospitals brain MRI dataset(NINS-dataset)for *** hyperparameter optimizers like Adam,stochastic gradient descent(SGD),Root mean square propagation(RMS prop),Adamax,and AdamW have been used to compare the performance of the learning ***-dataset registers maximum classification *** evaluated the performance of the proposed classification model using several quantitative metrics,achieving an average accuracy of 98%.

关键词： MRI tumors classification AlexNet50 transfer learning hyperparameter tuning optimizer

来源：评论

学校读者我要写书评

暂无评论

Fruit Tree Disease Recognition Based on Residual Neural Network and Attention Mechanism

引用

Journal of Artificial Intelligence and Technology 2024年第2期4卷 145-152页

作者： Xiedong Song Vladimir Y.Mariano College of Computing and Information Technologies National UniversityManilaPhilippines School of Computer Science and Engineering JiNing UniversityJiNing 273155China

Fruit growing has played a huge role in solving food supply issues in many ***,the yield and quality of fruits can be affected by various diseases,and thus timely and accurate identification of disease conditions is particularly ***,using image recognition and object detection technology to diagnose fruit tree diseases has become a research hotspot in forestry *** neural networks eliminate the preprocessing of manual feature selection and have high recognition ***,it is not easy to train due to the risk of gradient *** order to achieve better recognition effect,this research addresses the problem of applying small-scale data samples through data enhancement and transfer learning,and it optimizes the model by combining the two main attention mechanisms of SE and CBAM with *** experiments,it is found that the CBAM ResNet50 model has the best effect,improving the application performance of the studied model in actual scenarios.

关键词： attention mechanism disease recognition of fruit trees ResNet transfer learning

来源：评论

学校读者我要写书评

暂无评论

Performance comparison of multipath routing protocols for mobile ad hoc network

引用

International Journal of Systems, Control and Communications 2022年第1期13卷 82-98页

作者： Prasad, Sanjeev Kumar Sharma, Tripti Department School of Computing Science and Engineering Galgotias University NCR India Department Computer Science and Engineering Inderprastha Engineering College NCR India

In mobile ad hoc networks (MANETs), nodes are connected by multihop wireless connections and topology is changing very frequently due to movement of nodes. Therefore, it leads to the need of efficient dynamic routing protocols. Many routing protocols have been proposed for communication in dynamic environments and it is observed that multipath routing protocols are more preferred over the single path routing protocols in terms of many network parameters such as delay, energy consumption etc. These protocols are designed to fulfil the requirements of communication in the network. Therefore, the aim of this paper is to determine the difference between multipath routing protocols when operating in large-area MANETs with the help of constant bit rate, and variable bit rate data-traffic patterns;and these traffic patterns applied on the network with the different speeds and varying simulation pause time. This paper tests the performance of the following multipath protocols AOMDV, BAOMDV, BAMR, and LLECP-AOMDV on the NS-2 network platform. Copyright © 2022 Inderscience Enterprises Ltd.

关键词： Mobile ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Application of Genetically Optimized LVQ Neural Network in Trade Economic Forecasting

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第2期9卷 945-958页

作者： Zhang, Xin Wei, Yan-Qiu Ni, Lin Hashim, Zrdplwa School of Business Applied Technology College of Soochow University Suzhou215325 China Fan Li Business School Shaoxing Vocational & Technical College Shaoxing312000 China Faculty of Engineering Computing and Science Swinburne University of Technology Kuching93350 Malaysia

For the purpose of enhancing the prediction accuracy of trade economic cost under increasingly complex environment, genetic optimization LVQ neural network (AGLVQ) algorithm is intended for trade economic forecast. First, this paper optimizes LVQ neural network algorithm by updating the weight vector. Then, on the ground of this, this paper further enhances the individual selection strategy in genetic algorithm to select the optimal individual and the individual with poor fitness value with a large probability and the individual with medium fitness value with a small probability, actually eluding the overfitting phenomenon of training data. The characteristic data affecting import and export costs should be fully considered in the forecasting model of trade economy to guarantee the forecasting accuracy. Finally, MATLAB R2017a is used to forecast and simulate trade economic costs. The simulation outcome signifies that when the genetic variation probability is 0.1, the optimization iteration time of test sample prediction is short and the root mean square error (RMSE) is small. The predicted cost is almost the same as the actual cost, and AGLVQ algorithm has high prediction accuracy. © 2024, J. Network Intell. All rights reserved.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Pandemic state’s impact on agriculture

Pandemic state’s impact on agriculture

引用

International Conference on Artificial Intelligence, Blockchain, computing and Security, ICABCS 2023

作者： Sheeja Kumari, V. Wilfred Blessing, N.R. Rohith Bhat, C. Sudha, I. Michael, G. Manikandan, T. Department of Computational Intelligence – Institute of AI & ML SIMATS School of Engineering SIMATS University Chennai India IT Department College of Computing and Information Sciences University of Technology and Applied Sciences-Ibri Oman Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Chennai India

ISBN: (纸本)9781032669663

The COVID-19 outbreak has significantly disrupted the agricultural system in India. In spite of this, the most recent quarterly GDP forecasts post-COVID scenario demonstrate the tenacity and durability of the Indian agricultural sector, which is anticipated to be the only sector to record a positive growth rate of 4% for fiscal years (FY) 2020 and 2021. Similarly, growth for the most recent quarter is projected to have been 5.89%, representing a reduction of 2.4% point. In this context, our goal is to compile a summary of the early evidence on the impact of COVID-19 on the agricultural sector in India, including production, marketing, and consumption, and then to design a set of pragmatic strategies to recover and thrive after the pandemic. According to the survey’s findings, the pandemic has disrupted production and marketing through labour and logistical restrictions, while the negative income shock has restricted access to markets and increased food commodity prices, altering consumption patterns. The pandemic caused great emotional, social, economic, and bodily harm to everyone involved in India’s agriculture industry. The state has responded to the crisis by seizing the opportunity it presents and launching a variety of programmes and necessary changes. We suggest a ten-point plan that includes social safety nets, family farming, the trading of buffer stock, staggered procurement, and secondary agriculture in order to revitalise and prosper after the epidemic. © 2024, CRC Press/Balkema. All rights reserved.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

A Systematic Literature Review of Machine Learning and Deep Learning Approaches for Spectral Image Classification in Agricultural Applications Using Aerial Photography

引用

Computers, Materials & Continua 2024年第3期78卷 2967-3000页

作者： Usman Khan Muhammad Khalid Khan Muhammad Ayub Latif Muhammad Naveed Muhammad Mansoor Alam Salman A.Khan Mazliham Mohd Su’ud College of Computing and Information Sciences Karachi Institute of Economics and TechnologyKarachi75190Pakistan Faculty of Computing and Informatics(FCI) Multimedia UniversityCyberjaya63100Malaysia Faculty of Computing Riphah International UniversityIslamabad46000Pakistan Faculty of Engineering and Information Technology School of Computer ScienceUniversity of Technology SydneySydneyAustralia

Recently,there has been a notable surge of interest in scientific research regarding spectral *** potential of these images to revolutionize the digital photography industry,like aerial photography through Unmanned Aerial Vehicles(UAVs),has captured considerable *** encouraging aspect is their combination with machine learning and deep learning algorithms,which have demonstrated remarkable outcomes in image *** a result of this powerful amalgamation,the adoption of spectral images has experienced exponential growth across various domains,with agriculture being one of the prominent *** paper presents an extensive survey encompassing multispectral and hyperspectral images,focusing on their applications for classification challenges in diverse agricultural areas,including plants,grains,fruits,and *** meticulously examining primary studies,we delve into the specific agricultural domains where multispectral and hyperspectral images have found practical ***,our attention is directed towards utilizing machine learning techniques for effectively classifying hyperspectral images within the agricultural *** findings of our investigation reveal that deep learning and support vector machines have emerged as widely employed methods for hyperspectral image classification in ***,we also shed light on the various issues and limitations of working with spectral *** comprehensive analysis aims to provide valuable insights into the current state of spectral imaging in agriculture and its potential for future advancements.

关键词： Machine learning deep learning unmanned aerial vehicles multi-spectral images image recognition object detection hyperspectral images aerial photography

来源：评论

学校读者我要写书评

暂无评论

MUTS-Based Cooperative Target Stalking for A Multi-USV System

引用

IEEE/CAA Journal of Automatica Sinica 2023年第7期10卷 1582-1592页

作者： Chengcheng Wang Yulong Wang Qing-Long Han Yunkai Wu Shanghai Key Laboratory of Power Station Automation Technology and the School of Mechatronic Engineering and AutomationShanghai UniversityShanghai 200444China School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyMelbourne VIC 3122Australia College of Automation Jiangsu University of Science and TechnologyZhenjiang 212100China

This paper is concerned with the cooperative target stalking for a multi-unmanned surface vehicle(multi-USV)*** on the multi-agent deep deterministic policy gradient(MADDPG)algorithm,a multi-USV target stalking(MUTS)algorithm is ***,a V-type probabilistic data extraction method is proposed for the first time to overcome shortcomings of the MADDPG *** advantages of the proposed method are twofold:1)it can reduce the amount of data and shorten training time;2)it can filter out more important data in the experience buffer for ***,in order to avoid the collisions of USVs during the stalking process,an action constraint method called Safe DDPG is ***,the MUTS algorithm and some existing algorithms are compared in cooperative target stalking *** order to demonstrate the effectiveness of the proposed MUTS algorithm in stalking tasks,mission operating scenarios and reward functions are well designed in this *** proposed MUTS algorithm can help the multi-USV system avoid internal collisions during the mission ***,compared with some existing algorithms,the newly proposed one can provide a higher convergence speed and a narrower convergence domain.

关键词： Cooperative target stalking improved deep reinforcement learning multi-unmanned surface vehicle(multi-USV)systems V-type probabilistic data extraction

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：