检索结果-内蒙古大学图书馆

4th ISPRS Geospatial Week 2019

作者： Weinmann, M. Weinmann, M. Institute of Photogrammetry and Remote Sensing Karlsruhe Institute of Technology Germany Institute of Computer Science II-Computer Graphics University of Bonn Germany

In this paper, we address the semantic interpretation of urban environments on the basis of multi-modal data in the form of RGB color imagery, hyperspectral data and LiDAR data acquired from aerial sensor platforms. We extract radiometric features based on the given RGB color imagery and the given hyperspectral data, and we also consider different transformations to potentially better data representations. For the RGB color imagery, these are achieved via color invariants, normalization procedures or specific assumptions about the scene. For the hyperspectral data, we involve techniques for dimensionality reduction and feature selection as well as a transformation to multispectral Sentinel-2-like data of the same spatial resolution. Furthermore, we extract geometric features describing the local 3D structure from the given LiDAR data. The defined feature sets are provided separately and in different combinations as input to a Random Forest classifier. To assess the potential of the different feature sets and their combination, we present results achieved for the MUUFL Gulfport Hyperspectral and LiDAR Airborne Data Set. © Authors 2019.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Scalable method for Bayesian experimental design without integrating over posterior distribution

arXiv

引用

arXiv 2023年

作者： Hoang, Vinh Espath, Luis Krumscheid, Sebastian Tempone, Raúl Mathematics for Uncertainty Quantification RWTH Aachen University Germany Faculty of Science University of Nottingham United Kingdom Steinbuch Center for Computing Institute for Applied and Numerical Mathematics Karlsruhe Institute of Technology Karlsruhe76131 Germany Computer Electrical and Mathematical Sciences and Engineering KAUST Alexander von Humboldt professor in Mathematics of Uncertainty Quantification RWTH Aachen University Germany

We address the computational efficiency in solving the A-optimal Bayesian design of experiments problems for which the observational map is based on partial differential equations and, consequently, is computationally expensive to evaluate. A-optimality is a widely used and easy-to-interpret criterion for Bayesian experimental design. This criterion seeks the optimal experimental design by minimizing the expected conditional variance, which is also known as the expected posterior variance. This study presents a novel likelihood-free approach to the A-optimal experimental design that does not require sampling or integrating the Bayesian posterior distribution. Our proposed approach is developed based on two properties of the conditional expectation: the law of total variance and the property of orthogonal projection. The expected conditional variance is obtained via the variance of the conditional expectation using the law of total variance, and we take advantage of the orthogonal projection property to approximate the conditional expectation. We derive an asymptotic error estimation for the proposed estimator of the expected conditional variance and show that the intractability of the posterior distribution does not affect the performance of our approach. We use an artificial neural network (ANN) to approximate the nonlinear conditional expectation in the implementation of our method. We then extend our approach for dealing with the case that the domain of experimental design parameters is continuous by integrating the training process of the ANN into minimizing the expected conditional variance. Specifically, we propose a nonlocal approximation of the conditional expectation and apply transfer learning to reduce the number of evaluations of the observation model. Through numerical experiments, we demonstrate that our method greatly reduces the number of observation model evaluations compared with widely used importance sampling-based approaches. This reduction is c

关键词： Design of experiments

来源：评论

学校读者我要写书评

暂无评论

Segmentation and Feature Extraction in Medical Imaging: A Systematic Review

引用

Procedia computer science 2020年 167卷 26-36页

作者： Chiranji Lal Chowdhary D.P. Acharjya Associate Professor School of Information Technology & Engg Vellore Institute of Technology Vellore India Professor School of Computer Science & Engg Vellore Institute of Technology Vellore India

Image processing techniques being crucial towards analyzing and resolving issues in medical imaging since last two decades. Medical imaging is a process or technique to find the inner or outer construction of mortal body. The process observes medicinal diagnosis, analyze illnesses and develop data-sets of normal and abnormal imageries. Medical imaging is divided in two folds such as invisible-light medical imaging and visible-light medical imaging. The second type of medical imaging were can be understood by a common person whereas the first type can be interpreted by a radiologist. Analysis of all these require segmentation and feature extraction. In fact a lot of medical imaging techniques are available but authors restrict survey to tumor detection through mammograms or magnetic resonance imaging. In this paper, authors survey on various segmentation and feature extraction methods in medicinal images used for preprocessing.

关键词： Medical Imaging Fuzzy Segmentation Feature Extraction Imaging Modality Segmentation

来源：评论

学校读者我要写书评

暂无评论

Real-time multi-factor adaptive task scheduling model for improved QoS in cloud environment

引用

AIP Conference Proceedings 2024年第1期3075卷

作者： M. Baskar G. John Samuel Babu Associate Professor Department of Computing Technologies School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chengalpattu Tamilnadu 603 203 India. Associate Professor Department of Computer Science and Engineering MLR Institute of Technology Hyderabad Telangana 500043 India.

The task scheduling and data security issue in the cloud is well-studied, and different approaches exist around the problem. Most approaches consider makespan, throughput, delay, and others in task scheduling. The existing methods need better performance in various quality of service metrics as they consider only limited features of task scheduling. To overcome these issues, an efficient multi-factor adaptive task scheduling (MATS) is presented in this article. The method considers the cost, delay, and utilization of various services in selecting a service for task scheduling. According to the factors mentioned above, the method applies MFTS scheduling which approximates the factors toward maximizing the QoS performance. The MFTS algorithm computes Cost Support Measure (CSM), Delay Centric QoS Support Measure (DCQSM), and Utilization Support Measure (USM). Using all these measures, the value of Selection Weight (SW) is measured to support scheduling. Further to maximize data security, the proposed MATS model discovers the routes and estimates Quality Centric Transmission Support (QCTS) to identify an optimal route to support QoS maximization. The MATS scheduling approach achieves higher QoS performance with data security.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hybrid CNN-SVM Classifier for Handwritten Digit Recognition

引用

Procedia computer science 2020年 167卷 2554-2560页

作者： Savita Ahlawat Amit Choudhary Reader Deptt. of Computer Science and Engineering Maharaja Surajmal Institute of Technology New Delhi Associate Professor Deptt. of Computer Science Maharaja Surajmal Institute New Delhi

The aim of this paper is to develop a hybrid model of a powerful Convolutional Neural Networks (CNN) and Support Vector Machine (SVM) for recognition of handwritten digit from MNIST dataset. The proposed hybrid model combines the key properties of both the classifiers. In the proposed hybrid model, CNN works as an automatic feature extractor and SVM works as a binary classifier. The MNIST dataset of handwritten digits is used for training and testing the algorithm adopted in the proposed model. The MNIST dataset consists of handwritten digits images which are diverse and highly distorted. The receptive field of CNN helps in automatically extracting the most distinguishable features from these handwritten digits. The experimental results demonstrate the effectiveness of the proposed framework by achieving a recognition accuracy of 99.28% over MNIST handwritten digits dataset.

关键词： Handwritten digit recognition Hybrid model Convolutional Neural Network Support Vector Machine

来源：评论

学校读者我要写书评

暂无评论

Improved diabetes disease prediction IWFO model using machine learning algorithms

引用

AIP Conference Proceedings 2024年第1期3161卷

作者： R. Gunavathi V. Sivakumar B. Senthil Kumar S. Vijayalakshmi Associate professor School of Science Department of Data Science Christ University Pune India Associate Professor & Program Leader School of Computing Asia Pacific University of Technology and Innovation Kuala Lumpur Malaysia Assistant Professor Department of Computer Science Sree Narayana Guru College Coimbatore India

Diabetic disease is the mostly affected and massive disease on a global level. Diagnosing the diabetic earlier will help the medicalist to give the improved and latest clinical treatment. The healthcare specialist unit uses many machine learning techniques, methodologies and tools for decision making in diabetic field. The machine learning techniques are utilized for the prediction of the diabetic diseases in the initial level. To eliminate such issues, optimized detection techniques are proposed. First of all, the training samples are increased using the sliding window protocol. Further, class imbalanced training data classes are balanced and resolved using the adaptive and gradient booster technique. Further, the diabetic feature selection process is improved by the Intensity Weighted Firefly Optimization firefly techniques (IWFO), in which irrelevant features are reduced based on the correlation between the features that deducts the unwanted features involved in the diabetic disease process. Then the feature transformation problem is faced by the PCA technique, which manages the several types of features. Finally, the improved and optimal hybrid random forest is applied into the normal and diabetes classes respectively. The proposed system predicts the diabetic disease efficiently and maximizes its precision of the prediction system. The present paper is compared with different classifiers to determine the efficiency of the work. Overall, the initiated system improved the present studies accuracy level.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Mammogram Enhancement using Nonlinear Unsharp Masking and L 0 Gradient Minimization

引用

Procedia computer science 2020年 171卷 1848-1857页

作者： Divya Christopher Philomina Simon Assistant Professor in Computer Science and Engineering Lourdes Matha College of Science and Technology Kerala - 695574 Affiliated to APJ Abdul Kalam Technological University Thiruvananthapuram India Assistant Professor in Computer Science University of Kerala Kariavattom Thiruvananthapuram Kerala – 695581 India

Mammography is an effective modality for detecting and diagnosing breast cancer. Mammogram enhancement is used to improve the local contrast of mammograms, such that lesions appear more visible in the enhanced image. This paper introduces two novel approaches for mammogram enhancement based on a new unsharp masking scheme, called nonlinear UM and L 0 Gradient Minimization, NLUM L 0 GMIN for detecting breast cancer at an early stage. Three different techniques are unified in the proposed method; i) a Nonlinear filtering process to enhance the fine details within a 3x3 local neighborhood, ii) an L 0 Gradient Minimization step globally preserving the high-contrast edges while suppressing low-contrast details seen as opaque fibrous tissues; and to obtain a detail mammogram after subtracting smoothed mammogram from the original mammogram, iii) Finally, an Unsharp masking technique combining detail mammogram with filtered mammogram passed through Non-linear filter, using PLIP operators which satisfy both Weber’s law and saturation characteristics of the human visual system.. An HVS-based decomposition scheme is used to analyse and visualize the malignant areas in the enhanced mammogram. The distinct arrangement of PLIP operators in the proposed framework has given rise to two methods NLUM L 0 GMINAUTO and NLUM L 0 GMIN, which outperforms NLUM method and other existing techniques for mammogram enhancement. The former is good at enhancing less-dense and medium-dense mammograms whereas the later enhances unseen masses within high-dense mammograms. Experimental results have stated the significance of the proposed method in effectively diagnosing breast cancer in comparison with the previous methods for mammogram enhancement. The mini-MIAS database has categorized mammograms as fatty, fatty-glandular and dense-glandular, which has helped us in focusing on enhancing images uniquely for each category. The proposed NLUM L 0 GMIN scheme is robust and effective in identifying cance

关键词： L 0 Gradient Minimization ( L 0 GMIN) Nonlinear Unsharp Masking (NLUM) Parameterized Logarithmic Image Processing (PLIP) Human-Visual-System (HVS)-based image decomposition Unsharp Masking (UM) Mammogram enhancement

来源：评论

学校读者我要写书评

暂无评论

IoT Research on Healthcare Data to Control Illness of Oncology

IoT Research on Healthcare Data to Control Illness of Oncolo...

引用

Advance Computing and Innovative Technologies in Engineering (ICACITE), International Conference on

作者： Dhiraj Kapila Prince Tehseen Ganai G.Sreenivasa Raju Lims Thomas Manisha Girase José Luis Arias Gonzales Assistant Professor Department of Computer Science &#x0026 Engineering Lovely Professional University Phagwara India Research Scholar Department of Information Technology Shri Jagdishprasad Jhabarmal Tibrewala University Rajasthan India Assistant Professor Department of Electronics and Communication Engineering Anurag University Assistant Professor Department of Social Work Vimala College (Autonomous) Thrissur Professor &#x0026 Head Dept. Of Microbiology K SK W Arts Science &#x0026 Commerce College CIDCO Nashik Maharashtra Departrnent of business University of British Columbia

Let us begin with the internet of things that empowers software programmers to start increasing prediction without being done with full to do so. With today's data availability, machine learning techniques are being developed to improve performance and maintenance prediction. Cancer, according the Health Organisation, is a global disease and the second leading cause of death worldwide. People with cancer have been identified as having an increased risk of dying in the current worldwide epidemic. With the disease's incidence growing decade after decade, the need for a continuously and then round surveillance apparatus has become crucial. A cancer monitoring system known as the internet of Things (IoT) has the potential to identify cancer-related indications in their initial phases, continue to monitor disease individuals, and screen someone who has been cured through post-treatment operations. This research presents a multi-layered architectural for an IoT-based disease monitoring and control system that might be utilised as a foundation for remotely cancer diagnosis and management.

关键词： Wireless communication Hospitals Surveillance Machine learning Maintenance engineering Oncology Software

来源：评论

学校读者我要写书评

暂无评论

An effective coaxiality measurement for twist drill based on line structured light sensor

arXiv

引用

arXiv 2021年

作者： Cheng, Ailing Ye, Jiaojiao Yang, Fei Lu, Shufang Gao, Fei The Laboratory of Graphics & Image Processing College of Computer Science and Technology Zhejiang University of Technology Zhejiang Province Hangzhou310023 China The Research Center of Intelligent Computing Software Zhejiang Lab. Zhejiang Province Hangzhou311121 China

Aiming at the accurate and effective coaxiality measurement for twist drill with irregular surface, an optical measurement mechanism is proposed in this paper. First, A high-precision rotation instrument based on four core units is designed, which can obtain the 3-D point cloud data of full angle for the twist drill. Second, in the data processing stage, an improved robust Gaussian mixture model is established for accurate and rapid blade back segmentation. To improve measurement efficiency, a rapid reconstruction method of the twist drill axis based on orthogonal synthesis is provided to locate the axial position of the maximum deviation from the benchmark by utilizing the extracted blade back data. Finally, by calculating the maximum radial Euclidean distance from the benchmark, the coaxiality error of the twist drill is obtained. Comparing with other measurement methods, experimental results show that our proposed method is effective with high precision of 3 um and high efficiency of less than 3 s/pc. The result demonstrate that the proposed method is effective, robust and automatic, it can be applied in many actual industrial scene. © 2021, CC BY.

关键词： Drills

来源：评论

学校读者我要写书评

暂无评论

An enhanced hybrid approach for building of Question Answering Prototype

An enhanced hybrid approach for building of Question Answeri...

引用

Advances in Computing and Future Communication Technologies (ICACFCT), International Conference on

作者： Vikas Bali Amandeep Verma Research Scholar Dept. of Computer Science Punjabi University Patiala India Assistant Professor Punjabi University Regional Centre for Information Technology and Management Mohali India

ISBN: (数字)9781665420761

ISBN: (纸本)9781665420778

The technical advancement and massive shift in technology with the introduction of Artificial Intelligence (AI) and Computational Linguistics has appeared Question Answering as one of the prime extents for the computer scientists. Question answering is more focused on Answer Driven Search where, instead of big pack of words, the exact answer is provided to the user’s query in minimal amount of time. Changing era has evolved numerous approaches enhanced QA system implementation by exploiting natural language processing (NLP) and computational theory. [1] Three mandatory modules in the architecture of QAS includes question processing module, information retrieval (IR) module and answer processing module. In this paper, we purpose an enhanced hybrid approach for the building of QA prototype for factoid type questions by adopting best mathematical methods for QA implementation.

关键词： Architecture Buildings Prototypes computer architecture Information retrieval Question answering (information retrieval) Communications technology

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：