检索结果-内蒙古大学图书馆

Least-squares support vector machine-based kalman filtering for GNSS navigation with dynamic model real-time correction

引用

IET RADAR SONAR AND NAVIGATION 2017年第3期11卷 528-538页

作者： Zhou, Zebo Li, Yong Fu, Chen Rizos, Chris Univ Elect Sci & Technol China Sch Aeronaut & Astronaut Chengdu Peoples R China Univ New South Wales Sch Surveying & Spatial Informat Syst Sydney NSW Australia

The accuracy of kalman filtering (kF) relies on the quality of the observations as well as the dynamic model. However, the dynamic model is usually assumed to be invariant, which is not realistic in real global navigation satellite system (GNSS) navigation applications due to unexpected vehicular motion. A new algorithm is proposed to enhance the kF by using the least-squares support vector machine (LSSVM) technique. The LSSVM-enhanced kF (LSSVM-kF) adaptively estimates the dynamic modelling bias from historical information, and then uses the bias estimate to compensate the dynamic model. The algorithm treats the dynamic model bias as a time-variant ambiguous function which is trained with the LSSVM. A k-fold crossvalidation method is developed to tune the training parameters of the LSSVM. With the corrected dynamic model, the kF is implemented to estimate the navigation parameters. To integrate LSSVM with kF, the unscented transformation is introduced to numerically compute the covariance of the LSSVM training. To verify the algorithm, simulation, semi-simulation and real GNSS vehicular experiments were carried out. The results show that the LSSVM-kF can adequately adapt to time-variant dynamics and achieve a reliable and accurate GNSS navigation solution.

关键词： least squares approximations GNSS navigation LSSVM training covariance knowledge engineering techniques conventional kalman filtering GNSS vehicular experiments unexpected vehicular motion unscented transformation adaptive estimation LSSVM technique satellite navigation Radionavigation and direction finding least-squares support vector machine telecommunication computing dynamic modelling bias LSSVM-enhanced kF Filtering methods in signal processing k-fold cross-validation method neural network-based kF CkF kalman filters Sage-Husa adaptive kF Interpolation and function approximation (numerical analysis) support vector machines time-variant dynamics dynamic model real-time correction LSSVM-kF Communications computing

来源：评论

学校读者我要写书评

暂无评论

Wavelet statistical texture features-based segmentation and classification of brain computed tomography images

引用

IET IMAGE PROCESSING 2013年第1期7卷 25-32页

作者： Nanthagopal, A. Padma Sukanesh, R. Tiruchy Anna Univ Tiruchy 625023 India Thiagarajar Coll Engn Dept Elect & Commun Engn Madurai 625015 Tamil Nadu India

A computer software system is designed for segmentation and classification of benign and malignant tumour slices in brain computed tomography images. In this study, the authors present a method to select both dominant run length and co-occurrence texture features of wavelet approximation tumour region of each slice to be segmented by a support vector machine (SVM). Two-dimensional discrete wavelet decomposition is performed on the tumour image to remove the noise. The images considered for this study belong to 208 tumour slices. Seventeen features are extracted and six features are selected using Student's t-test. This study constructed the SVM and probabilistic neural network (PNN) classifiers with the selected features. The classification accuracy of both classifiers are evaluated using the k fold cross validation method. The segmentation results are also compared with the experienced radiologist ground truth. Quantitative analysis between ground truth and the segmented tumour is presented in terms of segmentation accuracy and segmentation error. The proposed system provides some newly found texture features have an important contribution in classifying tumour slices efficiently and accurately. The experimental results show that the proposed SVM classifier is able to achieve high segmentation and classification accuracy effectiveness as measured by sensitivity and specificity.

关键词： support vector machine Neural computing techniques probability segmentation accuracy malignant tumour slice classification PNN classifier statistical analysis computerised tomography Patient diagnostic methods and instrumentation Function theory, analysis neural nets brain two-dimensional discrete wavelet decomposition segmentation error classification accuracy Biology and medical computing benign tumour slices classification Computer vision and image processing techniques knowledge engineering techniques benign tumour slices segmentation wavelet statistical texture features-based classification sensitivity noise removal Optical, image and video signal processing Integral transforms image segmentation cancer discrete wavelet transforms image classification malignant tumour slice segmentation wavelet statistical texture features-based segmentation feature extraction tumours brain computed tomography image image texture student t-test SVM classifier X-ray techniques: radiography and computed tomography (biomedical imaging/measurement) statistical testing medical image processing image denoising support vector machines wavelet approximation tumour region computer software system tumour image Probability theory, stochastic processes, and statistics X-rays and particle beams (medical uses) k-fold cross-validation method Other topics in statistics probabilistic neural network

来源：评论

学校读者我要写书评

暂无评论

Classification of drug molecules for oxidative stress signalling pathway

引用

IET SYSTEMS BIOLOGY 2019年第5期13卷 243-250页

作者： Verma, Nikhil Singh, Harpreet khanna, Divya Rana, Prashant Singh Bhadada, Sanjay kumar Thapar Inst Engn & Technol Comp Sci & Engn Dept Patiala 147004 Punjab India Postgrad Inst Med Educ & Res Dept Endocrinol Chandigarh 160012 India

In humans, oxidative stress is involved in the development of diabetes, cancer, hypertension, Alzheimers' disease, and heart failure. One of the mechanisms in the cellular defence against oxidative stress is the activation of the Nrf2-antioxidant response element (ARE) signalling pathway. Computation of activity, efficacy, and potency score of ARE signalling pathway and to propose a multi-level prediction scheme for the same is the main aim of the study as it contributes in a big amount to the improvement of oxidative stress in humans. Applying the process of knowledge discovery from data, required knowledge is gathered and then machine learning techniques are applied to propose a multi-level scheme. The validation of the proposed scheme is done using the k-fold cross-validation method and an accuracy of 90% is achieved for prediction of activity score for ARE molecules which determine their power to refine oxidative stress.

关键词： cancer cellular biophysics biochemistry drugs molecular biophysics proteins learning (artificial intelligence) medical computing oxidative stress Nrf2-antioxidant response element signalling pathway ARE signalling pathway diabetes cancer hypertension Alzheimers' disease heart failure machine learning techniques k-fold cross-validation method ARE molecules

来源：评论

学校读者我要写书评

暂无评论

Magnetic Resonance Estimation of Longitudinal Relaxation Time (T₁) in Spoiled Gradient Echo Using an Adaptive Neural Network

Magnetic Resonance Estimation of Longitudinal Relaxation Tim...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Bagher-Ebadian, H. Jain, R. Paudyal, R. Nejad-Davarani, S. P. Narang, J. Jiang, Q. Mikkelsen, T. Ewing, J. R. Henry Ford Hosp Dept Neurol Detroit MI 48202 USA Henry Ford Hosp Dept Neurosurg Detroit MI 48202 USA Henry Ford Hosp Dept Radiol Detroit MI 48202 USA

ISBN: (纸本)9781424496365

Recently, the acquisition of high-resolution T-1 maps in a clinically feasible time frame has been demonstrated with Driven Equilibrium Single Pulse Observation of T-1 (DESPOT1). DESPOT1 derives the longitudinal relaxation time, T-1, from two or more spoiled gradient recalled echo (SPGR) images acquired with a constant T-R and different flip angles. In general, T-1 can be estimated from two or more SPGR images. Estimation of MR parameters (T-1, M-0, etc.) from these sequences is challenging and susceptible to the level of noise in signal acquisition. methods such as Simplex Optimization, Weighted Non-Linear Least Squares (WNLS), Linear Least Square (LLS or Gupta's LLS), and Intensity based Linear Least Square (ILLS) method have been employed to estimate T-1. In both linear and non-linear methods, the estimated T-1 values are highly dependent on defining the weighting factors;errors in these weighting factors can result in a biased estimate of T-1. In this study, an adaptive neural network (ANN) is introduced, trained and evaluated. The ANN was trained using an analytical model of the SPGR signal in the presence of different levels of signal to noise ratio (2 to 30). Receiver Operator Characteristic (ROC) analysis and the k-fold cross-validation (kFCV) method were employed to train, test, and optimize the network. The result (Az=0.81) shows that, compared to the other techniques, ANNs can provide a faster and unbiased estimate of T-1 from SPGR signals.

关键词： Artificial neural networks Estimation Gupta linear least square method Hospitals Imaging k-fold cross-validation method Mathematical model Signal to noise ratio Training adaptive neural network biomedical MRI driven equilibrium single pulse observation high-resolution T1 map acquisition image sequences image sequences intensity based linear least square method least squares approximations longitudinal relaxation time magnetic resonance estimation medical image processing neural nets receiver operator characteristic analysis signal acquisition signal to noise ratio simplex optimization spoiled gradient echo spoiled gradient recalled echo image weighted nonlinear least squares weighting factor

来源：评论

学校读者我要写书评

暂无评论

Magnetic Resonance Imaging Estimation of Longitudinal Relaxation Rate Change (ΔR₁) in Dual Gradient Echo Sequences Using an Adaptive Model

Magnetic Resonance Imaging Estimation of Longitudinal Relaxa...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Bagher-Ebadian, H. Nejad-Davarani, S. P. Ali, M. M. Brown, S. Makki, M. Jiang, Q. Noll, D. C. Ewing, J. R. Henry Ford Hosp Dept Neurol Detroit MI 48202 USA Univ Michigan Dept Biomed Engn Ann Arbor MI 48109 USA Henry Ford Hosp Dept Radiol Detroit MI 48202 USA Henry Ford Hosp Dept Radiat Oncol Detroit MI 48202 USA Univ Hosp Children Zurich Dept Diagnost Imaging Zurich Switzerland Wayne State Univ Dept Neurol Detroit MI 48202 USA

ISBN: (纸本)9781424496365

Magnetic Resonance Imaging (MRI) estimation of contrast agent concentration in fast pulse sequences such as Dual Gradient Echo (DGE) imaging is challenging. An Adaptive Neural Network (ANN) was trained with a map of contrast agent concentration estimated by Look-Locker (LL) technique (modified version of inversion recovery imaging) as a gold standard. Using a set of features extracted from DGE MRI data, an ANN was trained to create a voxel based estimator of the time trace of CA concentration. The ANN was trained and tested with the DGE and LL information of six Fisher rats using a k-fold cross-validation (kFCV) method with 60 folds and 10500 samples. The Area Under the Receiver Operator Characteristic Curve (AUROC) for 60 folds was used for training, testing and optimization of the ANN. After training and optimization, the optimal ANN (4: 7: 5: 1) produced maps of CA concentration which were highly correlated (r = 0.89, P < 0.0001) with the CA concentration estimated by the LL technique. The estimation made by the ANN had an excellent overall performance (AUROC = 0.870).

关键词： AUROC Animals Area Under the Receiver Operator Characteristic Curve Artificial neural networks DGE MRI data Feature extraction Fisher rat Hospitals Imaging k-fold cross-validation method Training Tumors adaptive model adaptive neural network biomedical MRI contrast agent concentration dual gradient echo imaging dual gradient echo sequence fast pulse sequence feature extraction feature extraction image sequences inversion recovery imaging longitudinal relaxation rate change look-locker technique magnetic resonance imaging estimation medical image processing neural nets voxel based estimator

来源：评论

学校读者我要写书评

暂无评论

Classification and Recognition of Building Appearance Based on Optimized Gradient-Boosted Decision Tree Algorithm

引用

SENSORS 2023年第11期23卷

作者： Hu, Mengting Guo, Lingxiang Liu, Jing Song, Yuxuan Xiamen Univ Technol Sch Civil Engn & Architecture Xiamen 361024 Peoples R China Fuzhou Univ Arts & Design Coll Xiamen Xiamen 361000 Peoples R China Jilin Agr Univ Coll Forestry & Grassland Changchun 130118 Peoples R China

There are high concentrations of urban spaces and increasingly complex land use types. Providing an efficient and scientific identification of building types has become a major challenge in urban architectural planning. This study used an optimized gradient-boosted decision tree algorithm to enhance a decision tree model for building classification. Through supervised classification learning, machine learning training was conducted using a business-type weighted database. We innovatively established a form database to store input items. During parameter optimization, parameters such as the number of nodes, maximum depth, and learning rate were gradually adjusted based on the performance of the verification set to achieve optimal performance on the verification set under the same conditions. Simultaneously, a k-fold cross-validation method was used to avoid overfitting. The model clusters trained in the machine learning training corresponded to various city sizes. By setting the parameters to determine the size of the area of land for a target city, the corresponding classification model could be invoked. The experimental results show that this algorithm has high accuracy in building recognition. Especially in R, S, and U-class buildings, the overall accuracy rate of recognition reaches over 94%.

关键词： decision tree algorithm building classification k-fold cross-validation method model cluster

来源：评论

学校读者我要写书评

暂无评论

Static Voltage Stability Analysis Using Generalized Regression Neural Network

Static Voltage Stability Analysis Using Generalized Regressi...

引用

IEEE International Power Engineering and Optimization Conference

作者： Maryam Mirzaei Jasronita Jasni Hashim Hizam Noor Izzri Abdul Wahab Ehsan Moazami Department of Electrical and Electronic Faculty of Engineering University Putra Malaysia

ISBN: (纸本)9781467350723

The ability of power system to maintain steady voltage at all the buses after happening a disturbance from a given initial operation condition is defined the voltage stability in the system. The focus of this paper is on voltage stability monitoring using the generalized regression neural network by improving algorithm. In this paper, to identify load buses and certain operation condition, the static voltage stability method in power systems is presented. Based on load buses, the index of voltage stability is obtained from the voltage equation derived from a two bus network. The proposed methods are tested on the IEEE-14 bus test system.

关键词： Voltage stability Generalized regression neural network Thevenin equivalent circuit k-fold cross-validation method

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：