检索结果-内蒙古大学图书馆

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Guru Prasad M S Ravatappa A Bhosagi Madhusudhana K Prithviraj Chandrappa S Vikash Kumar Department of Computer Science and Engineering Graphic Era (Deemed to be University) Dehradun India School of Computing and Information Technology Reva University Bengaluru India Dept. of Electronics & Communication Engineering SDM Institute of Technology Ujire India Department of Computer Science and Engineering Nitte (Deemed to be University) NMAMIT Mangalore India Department of Computer Science and Engineering Jain (Deemed-to-be University) Bengaluru India Department of Computer Application Graphic Era Deemed University Dehradun India

ISBN: (数字)9798331530389

ISBN: (纸本)9798331530396

In the field of the fashion industry, the introduction of deep learning technology has taken an innovative revolution by providing assistance in the construction of intellectual systems that are intelligent to deliver personalized ensemble recommendations. In this research work, an innovative ensemble recommendation structure called Deep Learning VGG16 (Visual Geometry Group 16) recommender is presented. The proposed method allows a deep learning model VGG16 to understand complex patterns and developments resulting from a vast group of fashion images. In order to increase the user experience and greater participation in the well-established fashion industry, the system offers personalized ensemble ideas. The important, core and fundamental component of the system is VGG16, consisting of 13 convolutional layers and 3 fully connected layers, which is used to support the analysis of fashion images. A cutting-edge convolutional neural network (CNN) model is improved over a large and diverse collection of fashion images. Model will extract advanced high-level information and statistics with the capability to distinguish particulars in colour patterns, clothing combinations, and stylistic elements. Using this process of development, the system becomes better at identifying user preferences and fashion trends.

关键词： Deep learning Adaptation models Visualization Virtual assistants Clothing Market research Clothing industry User experience Convolutional neural networks Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Framework for Unmanned Aerial Vehicle (UAV)-Enabled Real-Time Human Detection System for Disaster Management

A Comprehensive Framework for Unmanned Aerial Vehicle (UAV)-...

引用

Electrical Electronics and computing Technologies (ICEECT), International Conference on

作者： Govind Murari Upadhyay Mukesh Joshi Preeti Rathi Prashant Vats Meenakshi Narula Shashi Kant Gupta Dept. of Computer Application Manipal University Jaipur Jaipur Rajasthan India School of Computing Graphic Era Hill University Uttarakhand India Dept. of CSE School of Engg. & Techn. K.R. Mangalam University Gurugram Haryana India Dept. of CSE School of CSE Manipal University Jaipur Jaipur Rajasthan India Department of Information Technology Jagannath International Management School New Delhi India Department of CSE ITM University Gwalior Madhya Pradesh India

ISBN: (数字)9798350378092

ISBN: (纸本)9798350378108

Disasters pose significant challenges to emergency response efforts, often hindering timely and effective interventions. In recent years, integrating Unmanned Aerial Vehicles (UAVs) has emerged as a promising approach to enhance disaster management capabilities. This paper presents a novel real-time framework leveraging UAV technology for disaster response. The framework encompasses UAV deployment strategies, real-time data acquisition through aerial imaging and remote sensing, robust data transmission using advanced communication infrastructure, automated AI and machine learning analysis, and dynamic resource coordination based on actionable insights. By integrating these elements, the proposed framework aims to improve situational awareness, optimize response efforts, and facilitate informed decision-making during disaster scenarios. This paper discusses the key components of the framework, highlighting its potential impact on enhancing disaster response capabilities in real-time scenarios.

关键词： Disasters Imaging Disaster management Machine learning Autonomous aerial vehicles Emergency services Real-time systems Sensors Vehicle dynamics Remote sensing

来源：评论

学校读者我要写书评

暂无评论

A novel machine learning hybrid model for heart disease risk assessment

引用

AIP Conference Proceedings 2025年第1期3224卷

作者： Saurabh Srivastava Tasneem Ahmed Amit Saxena Rajeev Kumar Department of Computer Science & Engineering Moradabad Institute of Technology Moradabad India Advanced Computing and Research Laboratory Dept. of Computer Application Integral University Lucknow India

Heart disease claims millions of lives annually in more than a hundred countries. Heart disease has become one of the world’s leading causes of mortality, according to a World Health Organization (WHO) report. Among the conditions that can cause heart attacks include angina pectoris, congestive heart failure, cardiomyopathy, congenital heart disease, arrhythmias, myocarditis, heart attacks, and heart cancer. Heart disease presents a significant global health challenge, prompting extensive research into early detection and preventive measures. This study introduces a predictive model leveraging advanced machine learning (ML) techniques to assess heart disease risk. The model development process encompasses several phases, including data preprocessing, feature selection, and model training employing state-of-the-art algorithms like logistic regression (LR), decision tree (DT), random forests (RF), artificial neural network (ANN), naïve Bayes (NB), K-Nearest Neighbor (KNN), and support vector machine (SVM). Additionally, feature importance analysis and model evaluation techniques are utilized to refine interpretability and performance. The results exhibit the model’s efficacy in accurately predicting heart disease risk, offering valuable insights for early detection and personalized healthcare strategies. Overall, this research emphasizes the potential of data-driven methodologies in constructing predictive models for heart disease, presenting a promising avenue for enhancing patient outcomes and alleviating the burden on global healthcare systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A transfer learning based model for brain tumor detection using magnetic resonance imaging

引用

AIP Conference Proceedings 2025年第1期3224卷

作者： Saurabh Srivastava Tasneem Ahmed Rajeev Kumar Amit Saxena Department of Computer Science & Engineering Moradabad Institute of Technology Moradabad India Advanced Computing and Research Laboratory Dept. of Computer Application Integral University Lucknow India

Rapid and uncontrolled proliferation of cells is the cause of brain tumors. If treatment is not carried out early, death can occur. A major challenge in detecting a brain tumor is that it originates from variations in size, shape, and location. Since tumor cells are diverse, it might be difficult for radiologists to classify brain tumors, which are malignant diseases. The overall survival of patients, treatment planning, and risk factor identification depend on robust and accurate tumor classification and prediction. In the medical field, deep learning (DL) and machine learning (ML) are often employed to diagnose illnesses. Various tools have been developed that are used to diagnose different diseases such as heart disease, lung cancer, and many more. In this study, a DL-based transfer learning technique has been used to build a model that can easily identify whether a patient is suffering from a brain tumor or not. Brain tumors have been categorized into four types of categories based on the characteristics of the tumor. Patients who are suffering from the first and second categories of tumors can be saved by treatments that include surgery, radiation therapy, and chemotherapy. The third and fourth categories of tumors are more dangerous because these categories of tumors spread very fast, so if it is diagnosed early stage then the patient can be saved or increase the patient’s life span. Glioma, Meningioma, and Pituitary are a dangerous form of tumors, and the survival rate of patients who are suffering from these is very low. The developed system can predict that a patient is suffering from a brain tumor or not using MRI, and also predict the type of tumor such as Glioma, Meningioma, and Pituitary.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DUNE Software and High Performance computing

arXiv

引用

arXiv 2022年

作者： Fleming, Bonnie Knoepfel, Kyle Lin, Meifeng Qian, Xin Ren, Yihui Viren, Brett Wei, Hanyu Yoo, Shinjae Yu, Haiwang Dept. of Physics Brookhaven National Laboratory United States Computer Science Brookhaven National Laboratory United States Dept. of Physics Yale University United States Dept. of Physics and Astronomy Louisiana State University United States Scientific Computing Division Fermi National Accelerator Laboratory United States

DUNE, like other HEP experiments, faces a challenge related to matching execution patterns of our production simulation and data processing software to the limitations imposed by modern high-performance computing facilities. In order to efficiently exploit these new architectures, particularly those with high CPU core counts and GPU accelerators, our existing software execution models require adaptation. In addition, the large size of individual units of raw data from the far detector modules pose an additional challenge somewhat unique to DUNE. Here we describe some of these problems and how we begin to solve them today with existing software frameworks and toolkits. We also describe ways we may leverage these existing software architectures to attack remaining problems going forward. This whitepaper is a contribution to the Computational Frontier of Snowmass21. © 2022, CC BY.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

A scalable generative model for dynamical system reconstruction from neuroimaging data 24

A scalable generative model for dynamical system reconstruct...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Eric Volkmann Alena Brändle Daniel Durstewitz Georgia Koppe Department of Theoretical Neuroscience Central Institute of Mental Health (CIMH) Medical Faculty Mannheim Heidelberg University Mannheim Germany and Institute for Machine Learning Johannes Kepler University Linz Austria Department of Theoretical Neuroscience Central Institute of Mental Health (CIMH) Medical Faculty Mannheim Heidelberg University Mannheim Germany and Interdisciplinary Center for Scientific Computing Heidelberg University Heidelberg Germany and Faculty of Physics and Astronomy Heidelberg University Heidelberg Germany Interdisciplinary Center for Scientific Computing Heidelberg University Heidelberg Germany and Hector Institute for AI in Psychiatry & Dept. for Psychiatry and Psychotherapy CIMH and Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany

ISBN: (纸本)9798331314385

Data-driven inference of the generative dynamics underlying a set of observed time series is of growing interest in machine learning and the natural sciences. In neuroscience, such methods promise to alleviate the need to handcraft models based on biophysical principles and allow to automatize the inference of inter-individual differences in brain dynamics. Recent breakthroughs in training techniques for state space models (SSMs) specifically geared toward dynamical systems (DS) reconstruction (DSR) enable to recover the underlying system including its geometrical (attractor) and long-term statistical invariants from even short time series. These techniques are based on control-theoretic ideas, like modern variants of teacher forcing (TF), to ensure stable loss gradient propagation while training. However, as it currently stands, these techniques are not directly applicable to data modalities where current observations depend on an entire history of previous states due to a signal's filtering properties, as common in neuroscience (and physiology more generally). Prominent examples are the blood oxygenation level dependent (BOLD) signal in functional magnetic resonance imaging (fMRI) or Ca2+ imaging data. Such types of signals render the SSM's decoder model non-invertible, a requirement for previous TF-based methods. Here, exploiting the recent success of control techniques for training SSMs, we propose a novel algorithm that solves this problem and scales exceptionally well with model dimensionality and filter length. We demonstrate its efficiency in reconstructing dynamical systems, including their state space geometry and long-term temporal properties, from just short BOLD time series.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A scalable generative model for dynamical system reconstruction from neuroimaging data

arXiv

引用

arXiv 2024年

作者： Volkmann, Eric Brändle, Alena Durstewitz, Daniel Koppe, Georgia Medical Faculty Mannheim Heidelberg University Mannheim Germany Institute for Machine Learning Johannes Kepler University Linz Austria Interdisciplinary Center for Scientific Computing Heidelberg University Heidelberg Germany Faculty of Physics and Astronomy Heidelberg University Heidelberg Germany Hector Institute for AI in Psychiatry Dept. for Psychiatry and Psychotherapy CIMH Germany Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Complex Semantic Tabular Interpretation using SDD-Gen

Complex Semantic Tabular Interpretation using SDD-Gen

引用

International Conference on Semantic computing

作者： Matthew Johnson Jeanette A. Stingone Sofia Bengoa James Masters Deborah L. McGuinness Tetherless World Constellation Rensselaer Polytechnic Institute Troy USA Department of Epidemiology Columbia University New York USA Department of Environmental Medicine and Public Health Icahn School of Medicine at Mount Sinai New York USA Scientific Computing and Data Icahn School of Medicine at Mount Sinai New York USA Dept. of Computer Science Tetherless World Constellation Rensselaer Polytechnic Institute Troy USA

Knowledge graphs have become an essential technology for both businesses and governments. They enable a wide variety of critical tasks, such as aligning diverse datasets, improving the capabilities of search engines, supporting error checking, and generating explanations using inference engines. However, populating, augmenting, and/or validating a knowledge graph can be challenging because developers need domain knowledge to understand their data and experience in ontology modeling to align concepts properly as well as experience with conflict detection and truth maintenance tools. Previous efforts have explored automatically integrating simple tabular data into knowledge graphs to lower the barrier to entry. These methods heavily rely on named entity overlap and require that tables are similar to relational tables in third normal form. While these methods have been successful under competition, these limitations make them impractical for general usage. In this paper, we introduce the semantic data dictionary generator (SDD-Gen), an algorithm that aligns complex tabular data to ontological terms for knowledge graph generation. Our methodology leverages context information from data dictionaries to make alignments, enabling us to align complex tables with few named entities and multiple subject columns.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ETHER: A 6G Architectural Framework for 3D Multi-Layered Networks

ETHER: A 6G Architectural Framework for 3D Multi-Layered Net...

引用

IEEE Conference on Wireless Communications and Networking

作者： K. Ntontin L. Tomaszewski J. A. Ruiz-de-Azua A. Cárdenas R. Pueyo Centelles C.-K. Lin A. Mesodiakaki A. Antonopoulos N. Pappas M. Fiore S. Aguilar S. Watts P. Harris A. R. Santiago F. Lazarakis M. Calisti S. Chatzinotas SnT University of Luxembourg Luxembourg Orange Polska S.A. Warszawa Poland i2CAT Foundation Barcelona Spain Collins Aerospace Penrose Wharf Business Centre Cork Ireland Department of Informatics Aristotle University of Thessaloniki Thessaloniki Greece Nearby Computing Barcelona Spain Dept. of Computer and Information Science Linköping University Sweden Net AI Scotland UK Sateliot Barcelona Spain Avanti Communications London UK Ubiwhere Aveiro Portugal National Centre for Scientific Research “Demokritos” Agia Paraskevi Greece Martel Innovate Dübendorf Switzerland

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

Due to the fact that large swathes on Earth still lack broadband communication coverage, especially in remote/rural areas and developing countries, there have been several attempts, starting from 3GPP Release 17, to lay out the architectural amendments needed for the integration of terrestrial networks with their non-terrestrial counterparts. Such attempts have led to recent projects regarding such integration that consider either 5G/5G-Advanced networks or more revolutionary approaches for the forthcoming 6G networks. In this manuscript, we give an overview of the architectural framework, technical innovations, and considered use cases of the Horizon Europe ETHER project.

关键词： 6G mobile communication Earth Technological innovation Three-dimensional displays Europe Developing countries Broadband communication

来源：评论

学校读者我要写书评

暂无评论

Enhance the Mammogram Images for Both Segmentation and Feature Extraction Using Wavelet Transform

Enhance the Mammogram Images for Both Segmentation and Featu...

引用

2019 International Conference on Advanced Science and Engineering, ICOASE 2019

作者： Zebari, Dilovan Asaad Haron, Habibollah Zeebaree, Subhi R.M. Zeebaree, Diyar Qader Faculty of Engineering School of Computing University Teknologi Malaysia Johor Malaysia University Teknologi Malaysia Faculty of Computing Department of Computer Science Johor Malaysia IT Dept. Technical College of Informatics Akre Duhok Scientific Research and Development Center Nawroz University Duhok Iraq

ISBN: (纸本)9781538693438

Breast cancer (BC) is a main killer disease for women and men. It can be cured and controlled only if it is detected at its early detection. BC initial identification can be realized by the help of computer support identification approaches. From the detailed study on previous researches, it is found that, there is no system producing high accuracy because of one or more reasons. Absence of effective preprocessing is the discussed reason that obstructs the detection accuracy of computer-Aided diagnosis (CAD) method. Noise removal and contrast enhancement are the two types of preprocessing. There is no system performs the preprocessing on mammogram image. This work is an attempt to develop an enhanced preprocessing method for CAD of breast cancer by incorporating suitable noise reduction and contrast enhancement methods in the conventional CAD system. Contrast enhancement after noise reduction double enhances the mammogram image and the proposed methods MSE value for the mammogram image mdb072 has been 1.44% reduced. Reduction in MSE increases the PSNR to 0.16%. Many mammogram images have been tested and the result shows that, increase in contrast, decrease in mean square error and increase in peak signal to noise ratio when comparing to existing methods. © 2019 IEEE.

关键词： Wavelet transforms

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：