检索结果-内蒙古大学图书馆

Advances in Data engineering and Intelligent Computing Systems (ADICS), International Conference on

作者： Nijana. V P. Selvi Rajendran Computer Application Department Hindustan Institute of Technology and Science Department of Computer Science and Engineering Hindustan Institute of Technology and Science

ISBN: (数字)9798350364828

ISBN: (纸本)9798350364835

Medical imaging has been used extensively in healthcare in recent years for a variety of purposes, including disease diagnosis, treatment planning, and tracking the course of an illness. These applications entail taking pictures of the afflicted organ using a variety of modalities. Image segmentation and classification is two important process performed in disease diagnostic application. Deep reinforcement learning approach applied in many gaming application. DRL provides the accurate result in many real world applications, so researchers pay attention in DRL in medical data that helps the physicians in treating the patient. This study focus on surveying the various applications such as Image registration, lesion localization, image segmentation, image classification and Landmark detection using deep reinforcement learning in healthcare. In addition, this study investigates on the various DRL algorithms (Qlearning, deep deterministic policy gradient (DDPG), Twin Delayed Deep Deterministic Policy Gradient (TDDDPG), Deep Q Network (DQN) and Soft Actor-Critic (SAC) in Alzheimer's disease prediction. Among the DRL methods the DDPG achieved the highest accuracy in detecting the Alzheimer's disease with 97%.

关键词： Location awareness Surveys Image segmentation Image registration Deep reinforcement learning Prediction algorithms Lesions

来源：评论

学校读者我要写书评

暂无评论

Deep Hypergraph Neural Networks with Tight Framelets 39

Deep Hypergraph Neural Networks with Tight Framelets

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Li, Ming Fang, Yujie Wang, Yi Feng, Han Gu, Yongchun Bai, Lu Lio, Pietro Zhejiang Key Laboratory of Intelligent Education Technology and Application Zhejiang Normal University China Zhejiang Institute of Optoelectronics China School of Computer Science and Technology Zhejiang Normal University China Department of Mathematics City University of Hong Kong Hong Kong School of Artificial Intelligence Engineering Research Center of Intelligent Technology and Educational Application Ministry of Education Beijing Normal University China Department of Computer Science and Technology Cambridge University United Kingdom

ISBN: (纸本)157735897X

Hypergraphs provide a flexible framework for modeling high-order (complex) interactions among multiple entities, extending beyond traditional pairwise correlations in graph structures. However, deep hypergraph neural networks (HGNNs) often face the challenge of oversmoothing with increasing depth, similar to issues in graph neural networks (GNNs). While oversmoothing in GNNs has been extensively studied, its implications in relation to hypergraphs are less explored. This paper addresses this gap by first theoretically exploring the reasons behind oversmoothing in deep HGNNs. Our novel insights suggest that a spectral-based hypergraph convolution, equipped with both low-pass and high-pass filters, can potentially mitigate these effects. Motivated by these findings, we introduce FrameHGNN, a framework that utilizes framelet-based hypergraph convolutions integrating tight framelet transforms with both low-pass and high-pass components, as well as the commonly used strategies in designing deep GNN architecture: initial residual and identity mappings. The experiment results on diverse benchmark datasets demonstrate that FrameHGNN outperforms several state-of-the-art models, effectively reducing oversmoothing while improving predictive accuracy. Our contributions not only advance the theoretical understanding of deep hypergraph learning but also provide a practical spectral-based approach for HGNNs, emphasizing the design of multifrequency channels. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on Virtual Synchronous Generator Control for Parallel Connection of Multiple Grid-Forming Energy Storage Converters 9

Research on Virtual Synchronous Generator Control for Parall...

引用

9th Asia Conference on Power and Electrical engineering, ACPEE 2024

作者： Chen, Guowei Yang, Bo Li, Haoyuan Wang, Hui Wang, Baonan Res. Center for Energy Storage Conversion and Application China Electric Power Research Institute Jiangsu Engineering Technology Nanjing China Shanghai University of Electric Power College of Computer Science and Technology Shanghai China

ISBN: (纸本)9798350309638

The parallel connection of converters facilitates the modularization of the operating system, making the internal structure of the system more flexible and variable. However, due to the low damping and low inertia characteristics of power electronic equipment, which may be certain risks when the energy storage system is connected to the power grid through a power conversion system. To address this issue, the control strategy based on virtual synchronous machine control technology for grid-forming energy storage converters is proposed, which can improve system inertia and damping. Secondly, the conduct research on the off grid control of grid type energy storage converters. Finally, the proposed control strategy was validated through simulation experiments. © 2024 IEEE.

关键词： Synchronous generators

来源：评论

学校读者我要写书评

暂无评论

Graph Regularized Sparse Non-Negative Matrix Factorization for Clustering

引用

IEEE Transactions on Computational Social Systems 2023年第3期10卷 910-921页

作者： Deng, Ping Li, Tianrui Wang, Hongjun Wang, Dexian Horng, Shi-Jinn Liu, Rui Southwest Jiaotong University National Engineering Laboratory of Integrated Transportation Big Data Application Technology School of Computing and Artificial Intelligence Chengdu611756 China National Taiwan University of Science and Technology Department of Computer Science and Information Engineering Taipei106 Taiwan North Sichuan Medical College School of Preclinical Medicine Department of Computer and Mathematics Nanchong637100 China

The graph regularized nonnegative matrix factorization (GNMF) algorithms have received a lot of attention in the field of machine learning and data mining, as well as the square loss method is commonly used to measure the quality of reconstructed data. However, noise is introduced when data reconstruction is performed;and the square loss method is sensitive to noise, which leads to degradation in the performance of data analysis tasks. To solve this problem, a novel graph regularized sparse NMF (GSNMF) is proposed in this article. To obtain a cleaner data matrix to approximate the high-dimensional matrix, the l1-norm to the low-dimensional matrix is added to achieve the adjustment of data eigenvalues in the matrix and sparsity constraint. In addition, the corresponding inference and alternating iterative update algorithm to solve the optimization problem are given. Then, an extension of GSNMF, namely, graph regularized sparse nonnegative matrix trifactorization (GSNMTF), is proposed, and the detailed inference procedure is also shown. Finally, the experimental results on eight different datasets demonstrate that the proposed model has a good performance. © 2014 IEEE.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Exploratory Data Analysis using Autoviz for Machine Learning Classification Problem

Exploratory Data Analysis using Autoviz for Machine Learning...

引用

2024 International Conference on Emerging Innovations and Advanced Computing, INNOCOMP 2024

作者： Guru Prasad, M.S. Praveen Gujjar, J. Kotiyal, Arnav Prasanna Kumar, H.R. Devadas, Raghavendra M Jahan, Afsar Department of Computer Science and Engg. Dehradun India Faculty of Management Studies Bengaluru India Visvesvaraya Technological University PESITM Dept. of Information Science & Engg. Shivamogga India Gitam School of Technology Department of Computer Science and Engineering Gitam University Bengaluru India Department of Computer Application Dehradun India

ISBN: (纸本)9798350376470

As the field of machine learning continues to advance, the importance of effective exploratory data analysis (EDA) cannot be overstated, especially in the context of classification problems. This research paper introduces an innovative and automated approach to exploratory data analysis using Autoviz, a powerful Python library designed to streamline the visualization process for machine learning datasets. The study aims to demonstrate the efficacy of Autoviz in meaningful insights, facilitating feature understanding, and supporting data preprocessing for classification tasks. Furthermore, the paper discusses how Autoviz assists in feature selection by highlighting the relevance and importance of each feature about the target variable. This feature-centric analysis contributes to optimizing machine learning models by guiding the selection of relevant input features, thereby improving model accuracy and interpretability. Autoviz is a Python library designed to automate the exploratory data analysis (EDA) process for machine learning tasks. It is specifically tailored to generate a variety of visualizations that aid in understanding the structure and characteristics of a dataset. The results indicate that Autoviz significantly reduces the time and effort required for exploratory data analysis while maintaining the quality and depth of insights obtained. The differences between Autoviz and Pycaret is discussed in this paper. It has been observed that AutoViz automates the process of exploring and analyzing data, while PyCaret is designed for the comparison, construction, and tuning of machine learning models. © 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 Model for Predicting Chronic Kidney Diseases Based on Medical Data Using Reinforcement Learning

引用

SN computer Science 2024年第4期5卷 353页

作者： Nramban Kannan, Senthil Kumar Aseervatham, Joshi Moholkar, Kavita Palanimuthu, Mithun Marappan, Saranya Narendran, Muthusamy Sathar, Banu Sengan, Sudhakar Department of Computer Science & amp Department of Artificial Intelligence and Data Science Panimalar Engineering College Tamil Nadu Chennai 600123 India Department of Computer Science and Business Systems Engineering JSPM’S Rajarshi Shahu College of Engineering Savitribai Phule Pune University Pune 411033 India Department of Computer Science and Engineering St. Joseph’s Institute of Technology Tamil Nadu Chennai 600119 India Department of Information Technology Paavai Engineering College Tamil Nadu Namakkal 637018 India Department Information Technology KCG College of Technology Tamil Nadu Chennai 600097 India Department of Master of Computer Application T. J. Institute of Technology Chennai 600100 India Department of Computer Science and Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli 627451 India

Kidney diseases (KD) are a global public health concern affecting millions. Early detection and prediction are crucial for effective treatment. Artificial intelligence (AI) techniques have been used in KDP to analyze past medical records, applying patients’ Electronic Medical Record (EHR) data. However, conventional statistical analysis methods conflict with fully comprehending the complexity of EHR data. AI algorithms have helped early KDP learn and identify complex data patterns. However, challenges include training heterogeneous historical data, protecting privacy and security, and developing monitoring system regulations. This study addresses the primary challenge of training heterogeneous datasets for real-world evaluation. Early detection and diagnosis of chronic kidney disease (CKD) is crucial for improved outcomes, reduced healthcare costs, and reliable treatment. Early treatments are crucial for CKD, as it often develops without apparent symptoms. Predictive models, particularly those using reinforcement learning (RL), can identify significant trends in complex healthcare information, which standard techniques may struggle with. The study makes KDP more accurate and reliable using RL methods on clinical data. This lets doctors find diseases earlier and treat them better by looking at static and changing health measurements. Machine learning (ML) algorithms can enhance the accuracy of AI systems over time, enhancing their effectiveness in detecting and diagnosing diseases. In the current investigation, the RL-ANN model is implemented for performing enforceable CKD by assessing the outcomes of multiple neural networks, which include FNN, RNN, and CNN, according to parameters such as accuracy, sensitivity, specificity, prediction error, prediction rate, and kidney failure rate (KFR). The recommended RL-ANN method has a lower failure rate of 70% based on the KFR data. Further, the proposed approach earned 95% in PR and 70% in analysis of errors. However, the RL

关键词： Alerting systems and diagnostic assistance Chronic kidney disease Machine learning Medical history RL-ANN

来源：评论

学校读者我要写书评

暂无评论

Optimizing Network Navigation: A Comparative Analysis of Genetic Algorithm Efficacy Against Traditional Shortest Path Paradigms 3

Optimizing Network Navigation: A Comparative Analysis of Gen...

引用

3rd International Conference on Technological Advancements in Computational Sciences, ICTACS 2023

作者： Kumar, Jeetendra Gupta, Rashmi Kaur, Tejinder Atal Bihari Vaipayyee Vishwavidyalya Department of Computer Science and Application C.G. Bilaspur India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

ISBN: (纸本)9798350342338

it then selects the node with the smallest distance and adds it to the set of visited nodes. The heuristic function estimates the distance between each node and the goal node, allowing the algorithm to explore nodes that are likely to lead to the goal node first.. Once the graph is constructed, you can apply Dijkstra algorithm. Traditional algorithms, such as Dijkstra and Floyd-War shall, have been used to solve this problem efficiently, but their performance can be affected by the complexity and size of the network. © 2023 IEEE.

关键词： genetic algorithm network optimization path finding shortest path problem

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Techniques for Identifying Distressed Individuals on Social Media - A Survey

Machine Learning Techniques for Identifying Distressed Indiv...

引用

Big Data Analytics in Bioinformatics (DABCon), International Conference on

作者： Ankan Sadhukhan Sreejani Samanta Abhijit Pasari Sayantika Samui Dipayan Mandal Sandipta Ghosh Mrinmoy Guria Debrupa Pal Computer Science and Engineering Narula Institute of Technology Kolkata India Computer Application Narula Institute of Technology Kolkata India

ISBN: (数字)9798350378047

ISBN: (纸本)9798350378054

The pervasive presence of social media platforms has turned them into reservoirs of human emotions, providing a distinctive perspective into the intricate tapestry of digital sentiments. This research delves into the realm of emotional upheaval prevalent in online spaces, aiming to uncover signs of distress through the utilization of machine learning algorithms. By scrutinizing extensive volumes of social media data, this survey seeks to establish a pioneering framework for predicting the identification of individuals undergoing emotional distress. Many papers are published on machine learning approaches over the past few decades. In this paper, we provide a comprehensive survey of all best machine learning approaches in the current year to study or identify distress calls on social video through sentiment and media analysis. Furthermore, the challenges and benefits of using Machine Learning, along with its shortcomings, are summarized. Finally, open issues and their consequences for further research in the field of identifying individuals who are mentally depressed on social media are presented.

关键词： Surveys Ethics Machine learning algorithms Social networking (online) Surge protection Machine learning Mental health Predictive models Real-time systems Surges

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Effects of Coding and Compression on Network Performance 5th

Analyzing the Effects of Coding and Compression on Network P...

引用

5th International Conference on Data Science, Machine Learning and applications, ICDSMLA 2023

作者： Agarwal, Ankita Kumar, Deepak Singh, Alka Preethi, D. Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Department of Mathematics Vivekananda Global University Jaipur India Department of Master of Computer Application Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Karnataka Bengaluru India

ISBN: (纸本)9789819780426

This paper objectives to research the consequences of coding and compression on network performance. Network coding is the technique of encoding information before it is despatched over a network and has become an outstanding method to enhance community overall performance. Compression then again is used to reduce the size of the data before transmission, ensuing in quicker transmission time. This observe evaluates the effect those techniques have on network overall performance by measuring the bandwidth utilization, throughput, latency, and packet losses. A test becomes conducted to have a look at how the strategies have an effect on one of kind mixtures of information speeds, packet sizes, and facts loading. Results display that both strategies had a fine impact at the community overall performance, with network coding and compression having an extra effect on networks with higher facts hundreds. Moreover, the effects show that community coding had a greater impact on networks with larger packets, while compression had a more effect on networks with smaller packets. This studies gives insight into how community coding and compression can be used to enhance network overall performance. Coding and compression are important components of network performance that have been studied and tested to have a full-size influence on network pace, scalability, and reliability. Coding is used to reduce the amount of data that is sent over a community, by way of reducing the quantity of records frames that need to be sent and growing the performance of the records transfer technique. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

Stereo Image Dense Matching Based on SGM Constrained by Feature Matching 9

Stereo Image Dense Matching Based on SGM Constrained by Feat...

引用

9th International Conference on computer and Communications, ICCC 2023

作者： Ma, Tao Zhu, Hangbiao Huang, Weijian An, Pei Wang, Chun Yu, Kun Institute of Computer Application China Academy of Engineering Physics Mianyang China School of Electrical and Information Engineering Wuhan Institute of Technology Wuhan China National Key Laboratory of Science and Technology on Electromagnetic Energy Naval University of Engineering Wuhan China

ISBN: (纸本)9798350317251

Dense image matching plays a important role in stereo vision and remote sensing. Semi-global matching (SGM) is a widely used dense image matching framwork, which uses dynamic programming calculation strategy to optimize the global energy function. SGM has the problem of wrong disparity accumulation along the path. To solve the problem, this paper proposes a new dense image matching method based on feature matching and SGM. First, the feature matching is used to extract the reliable reference points. And then, reference points are used as additional constraints in matching cost aggregation to cut off the wrong disparity delivering along the path. In order to evaluate our method, qualitative and quantitative experiments are carried out on three stereo image pairs. The experimental results show that our method can achieve high matching accuracy by effectively reducing the error propagation. © 2023 IEEE.

关键词： Stereo vision

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：