检索结果-内蒙古大学图书馆

Information collection system for fall detection of stroke patients under cascade algorithm in the context of multi-modal information fusion and e-health

引用

EXPERT SYSTEMS 2023年第4期40卷 e12809-e12809页

作者： Lv, Xiao Ma, Dingying Zhou, Jinsheng Zhang, Lili Li, Xinke Ningbo Ninth Hosp Dept Phys Med & Rehabil 68 Xiangbei Rd Ningbo 315020 Zhejiang Peoples R China Ningbo First Hosp Dept Phys Med & Rehabil Ningbo Peoples R China

To effectively detect stroke patients after falling under e-health, the fall situation of patients is graded, and warnings are given to improve the survival probability of stroke patients after falling. First, the fall model of stroke patients is analysed. According to the model, multi-modal information fusion fall detection technology is proposed, including data fusion algorithm and feature recognition technology. Also, various sensor data are adjusted. The fall detection cascade algorithm is proposed to classify data with different features in order, thereby completing target detection. Finally, combined with heart rate sensor, height sensor and microcontroller unit software and patients' e-health information, the research and development of an information collection system for fall detection are realized. Six young volunteers are selected to test the system performance. The results show that for the six testers, the heart rate detected by the ordinary device and the device of this investigation is the same when it is resting in different states of resting, walking, as well as walking and falling. The heart rate difference between walking and falling detection is not large (within the allowable error range of the device). But the best detection effect is to measure after the patient falls, which not only reduces power consumption but also keeps the detection error to a minimum. The height sensor is in the static state, increased by 75 m in the vertical direction and decreased by 75 cm from the static position in the vertical direction. The height difference of the data information exported from these three cases has some errors compared with the actual 75 cm. The tester's three situations of resting, walking and falling, standing up after sitting still and falling are observed. The waveform when resting is stable, and the acceleration information also fluctuates significantly when walking and after standing up. The accuracy of the developed system is above 80%, wh

关键词： cascade algorithm information collection system for fall detection multi-modal information fusion stroke patients

来源：评论

学校读者我要写书评

暂无评论

Longitudinal tear detection of conveyor belt under uneven light based on Haar-AdaBoost and cascade algorithm

引用

MEASUREMENT 2021年 168卷 108341-108341页

作者： Wang, Gongxian Zhang, Libin Sun, Hui Zhu, Chao Wuhan Univ Technol Sch Logist Engn Wuhan 430063 Hubei Peoples R China

As the light of the belt conveyor changes drastically and unevenly, it will cause the longitudinal tear detection rate of the traditional methods drop sharply. To improve the situation, a novel method, which replaces the traditional geometric features with the Haar features, is proposed. First, the Haar feature was employed to train weak classifiers. Then, the AdaBoost algorithm is utilized to upgrade the weak classifiers to strong classifiers. Finally, the cascade algorithm is introduced to combine strong classifiers in series into a cascade classifier that can reduce the training and processing time. The experiment following the above proposed method has shown that the recall, accuracy, and precision of tear detection under uneven light almost approaches the level under the uniform light (less than 3% difference), which indicates that our method is more accurate and robust than the existing methods in real-time belt tear detection.

关键词： cascade algorithm Conveyor belt Haar-AdaBoost algorithm Longitudinal tear detection Real time

来源：评论

学校读者我要写书评

暂无评论

Neural Network Approximation of Refinable Functions

引用

IEEE TRANSACTIONS ON INFORMATION THEORY 2023年第1期69卷 482-495页

作者： Daubechies, Ingrid De Vore, Ronald Dym, Nadav Faigenbaum-Golovin, Shira Kovalsky, Shahar Z. Lin, Kung-Chin Park, Josiah Petrova, Guergana Sober, Barak Duke Univ Dept Math Durham NC 27708 USA Texas A&M Univ Dept Math College Stn TX 77843 USA Technion Israel Inst Technol Fac Math IL-3200003 Haifa Israel Duke Univ Rhodes Informat Initiat Durham NC 27708 USA Univ North Carolina Chapel Hill Dept Math Chapel Hill NC 27599 USA Hebrew Univ Jerusalem Dept Stat & Data Sci & Digital Humanities IL-9190501 Jerusalem Israel

In the desire to quantify the success of neural networks in deep learning and other applications, there is a great interest in understanding which functions are efficiently approximated by the outputs of neural networks. By now, there exists a variety of results which show that a wide range of functions can be approximated with sometimes surprising accuracy by these outputs. For example, it is known that the set of functions that can be approximated with exponential accuracy (in terms of the number of parameters used) includes, on one hand, very smooth functions such as polynomials and analytic functions and, on the other hand, very rough functions such as the Weierstrass function, which is nowhere differentiable. In this paper, we add to the latter class of rough functions by showing that it also includes refinable functions. Namely, we show that refinable functions are approximated by the outputs of deep ReLU neural networks with a fixed width and increasing depth with accuracy exponential in terms of their number of parameters. Our results apply to functions used in the standard construction of wavelets as well as to functions constructed via subdivision algorithms in Computer Aided Geometric Design.

关键词： Artificial neural networks Standards Deep learning Approximation algorithms Upper bound Stress Terminology Neural networks neural network approximation refinable functions exponential accuracy cascade algorithm

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition Method Based on cascade Convolution Neural Network 17

Facial Expression Recognition Method Based on Cascade Convol...

引用

17th IEEE International Wireless Communications and Mobile Computing Conference (IEEE IWCMC)

作者： Liu, Weida Fang, Jian Jilin Engn Normal Univ Dept Elect Engn Jilin Jilin Peoples R China

ISBN: (纸本)9781728186160

In view of the problem that the convolution neural network research of facial expression recognition ignores the internal relevance of the key links, which leads to the low accuracy and speed of facial expression recognition, and can't meet the recognition requirements, a series cascade algorithm model for expression recognition of educational robot is constructed and enables the educational robot to recognize multiple students' facial expressions simultaneously, quickly and accurately in the process of movement, in the balance of the accuracy, rapidity and stability of the algorithm, based on the cascade convolution neural network model. Through the CK+ and Oulu-CASIA expression recognition database, the expression recognition experiments of this algorithm are compared with the commonly used STM-ExpLet and FN2EN cascade network algorithms. The results show that the accuracy of the expression recognition method is more than 90%. Compared with the other two commonly used cascade convolution neural network methods, the accuracy of expression recognition is significantly improved.

关键词： Convolution Neural Network Facial Expression Recognition cascade algorithm

来源：评论

学校读者我要写书评

暂无评论

LabVIEW based robust cascade predictive model for evaluating cancer prognosis

引用

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS 2020年 549卷 123978-123978页

作者： Kaya, Duygu Turk, Mustafa Firat Univ Fac Engn Dept Elect & Elect Engn Elazig Turkey

Cancer is a disease that is found in many forms. Early diagnosis process significantly affects follow-up of the disease. As in other diseases, it is important to classify the data in cancer cases to determine whether the person belongs to healthy-patient or high-low risk groups. For this purpose, machine learning based on artificial intelligence can be used as a very effective method to follow both the progress and the treatment response process of such diseases and to reveal important features of data sets. In this publication, breast cancer diagnosis was carried out using Principal Component Analysis-Support Vector Machine (PCA-SVM) and proposed parallel Principal Component Analysis-Linear Discriminant Analysis-Support Vector Machine (PCA-LDA-SVM) model classifier algorithms, by LabVIEW. LabVIEW, known as Virtual Instrument (VI), is a graphical programming language. The durableness of the used algorithms is analyzed using accuracy, sensitivity, specificity, rand index, False Positive Rate (FPR), False Discovery Rate (FDR), False Negative Rate (FNR), Negative Predictive Value (NPV), Matthews Correlation Coefficient (MCC) parameters and status detection. The obtained results are compared with each other. After training, of the 140 data used in the test set, 130 were used for the test performance analysis and 10 data were used for the status determination of the newly entered data. Performance analysis has been examined for Polynomial and Gaussian kernel functions. The proposed parallel model provides improvement especially for the Polynomial kernel function. With the proposed model, an increase in classification accuracy was observed in the test phase compared to PCA-SVM, and it was observed that 10 data used for status determination were correctly classified. (C) 2020 Elsevier B.V. All rights reserved.

关键词： LabVIEW Prognosis of disease cascade algorithm Machine learning Support vector machine

来源：评论

学校读者我要写书评

暂无评论

Some new discrete biorthogonal wavelets constructed with Laguerre polynomials

引用

SN APPLIED SCIENCES 2020年第9期2卷 1470页

作者： Peachap, Atemangoh Bruno Tchiotsop, Daniel Louis-Dorr, Valerie Wolf, Didier Univ Dschang Unite Rech Mat Condensee Elect & Traitement Signa Fac Sci POB 69 Dschang Cameroon Univ Dschang Unite Rech Automat & Informat Appl LAIA IUT FV Bandjoun POB 134 Bandjoun Cameroon Univ Lorraine Ctr Rech Automat Nancy CRAN UMR CNRS 7039 ENSEM Nancy France

In this study, we present a new family of discrete wavelets which are constructed with the help of Laguerre polynomials and the Daubechies biorthogonal wavelets construction method. Our aim is to propose the discrete version of some previously constructed continuous Laguerre wavelets and also to present a method of discrete wavelets construction by several iterations. With this scheme, we use two different sets of finite impulse response filters for the signal decomposition and their duals for reconstruction. The quadruplet finite impulse response filters respect the a nti-aliasing and the perfect reconstruction conditions, and at the same time, they resemble as much as possible the continuous Laguerre wavelets when using the cascade algorithm. We use the mean squared error, the maximum deviation, and the standard deviation to quantify the similarity between the continuous Laguerre wavelets and the constructed discrete Laguerre *** results show that, they are both the same wavelets due to the small nature of these parameters. Our method is important because, it can permit the determination of the finite impulse response filter coefficients corresponding to many other continuous wavelets.

关键词： Laguerre wavelets Biorthogonal wavelets cascade algorithm FIR filters

来源：评论

学校读者我要写书评

暂无评论

ENHANCEMENT OF FAST FACE DETECTION algorithm BASED ON A cascade OF DECISION TREES 2

ENHANCEMENT OF FAST FACE DETECTION ALGORITHM BASED ON A CASC...

引用

International Workshop on Photogrammetric and Computer Vision Techniques for Video Surveillance, Biometrics and Biomedicine

作者： Khryashchev, V. V. Lebedev, A. A. Priorov, A. L. YSU Yaroslavl Russia

Face detection algorithm based on a cascade of ensembles of decision trees (CEDT) is presented. The new approach allows detecting faces other than the front position through the use of multiple classifiers. Each classifier is trained for a specific range of angles of the rotation head. The results showed a high rate of productivity for CEDT on images with standard size. The algorithm increases the area under the ROC-curve of 13% compared to a standard Viola-Jones face detection algorithm. Final realization of given algorithm consist of 5 different cascades for frontal/non-frontal faces. One more thing which we take from the simulation results is a low computational complexity of CEDT algorithm in comparison with standard Viola-Jones approach. This could prove important in the embedded system and mobile device industries because it can reduce the cost of hardware and make battery life longer.

关键词： Face Detection cascade algorithm Decision Trees

来源：评论

学校读者我要写书评

暂无评论

Evenly cascaded Convolutional Networks

Evenly Cascaded Convolutional Networks

引用

IEEE International Conference on Big Data (Big Data)

作者： Ye, Chengxi Devaraj, Chinmaya Maynord, Michael Fermueller, Cornelia Aloimonos, Yiannis Univ Maryland Inst Adv Comp Studies College Pk MD 20740 USA

ISBN: (纸本)9781538650356

We introduce Evenly cascaded convolutional Network (ECN), a neural network taking inspiration from the cascade algorithm of wavelet analysis. ECN employs two feature streams - a low-level and high-level steam. At each layer these streams interact, such that low-level features are modulated using advanced perspectives from the high-level stream. ECN is evenly structured through resizing feature map dimensions by a consistent ratio, which removes the burden of ad-hoc specification of feature map dimensions. ECN produces easily interpretable features maps, a result whose intuition can be understood in the context of scale-space theory. We demonstrate that ECN's design facilitates the training process through providing easily trainable shortcuts. We report new state-of-the-art results for small networks, without the need for additional treatment such as pruning or compression - a consequence of ECN's simple structure and direct training. A 6-layered ECN design with under 500k parameters achieves 95.24% and 78.99% accuracy on CIFAR-10 and CIFAR-100 datasets, respectively, outperforming the current state-of-the-art on small parameter networks, and a 3 million parameter ECN produces results competitive to the state-of-the-art.

关键词： cascade algorithm multi-level feature representation network efficiency recurrent convolution recursive convolution

来源：评论

学校读者我要写书评

暂无评论

A cascade Method for TFT-LCD Defect Detection 9

A Cascade Method for TFT-LCD Defect Detection

引用

9th International Conference on Digital Image Processing (ICDIP)

作者： Yi, Songsong Wu, Xiaojun Yu, Zhiyang Mo, Zhuoya Harbin Inst Technol Sch Mech Engn & Automat Shenzhen 518055 Guangdong Peoples R China Shenzhen Key Lab Adv Mot Control & Modern Automat Shenzhen 518055 Guangdong Peoples R China Guangdong Tianji Ind Intelligent Syst Co Ltd Dongguan 523808 Peoples R China

ISBN: (纸本)9781510613058;9781510613041

In this paper, we propose a novel cascade detection algorithm which focuses on point and line defects on TFT-LCD. At the first step of the algorithm, we use the gray level difference of su-bimage to segment the abnormal area. The second step is based on phase only transform (POT) which corresponds to the Discrete Fourier Transform (DFT), normalized by the magnitude. It can remove regularities like texture and noise. After that, we improve the method of setting regions of interest (ROI) with the method of edge segmentation and polar transformation. The algorithm has outstanding performance in both computation speed and accuracy. It can solve most of the defect detections including dark point, light point, dark line, etc.

关键词： TFT-LCD defect detection cascade algorithm

来源：评论

学校读者我要写书评

暂无评论

Smoothness of refinable function vectors on Rⁿ

引用

INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING 2017年第5期15卷 1750051-1750051页

作者： Tinaztepe, Ramazan Jacobs, Denise Heil, Christopher Univ Dammam Imam Abdulrahman Bin Faisal Univ Sch Supporting Studies Dammam 34212 Saudi Arabia Georgia Inst Technol Sch Math Atlanta GA 30332 USA

Let A be a dilation matrix, an n x n expansive matrix that maps Z(n) into itself. Let. be a finite subset of Z(n), and for kappa is an element of Lambda let c kappa be r x r complex matrices. The refinement equation corresponding to A, Z(n),Lambda and c = {c(kappa)}(kappa is an element of Lambda) is f(x) = Sigma(kappa is an element of Lambda)c(kappa) f(Ax - kappa). A solution f : R-n -> C-r, if one exists, is called a refinable vector function or a vector scaling function of multiplicity r. This paper characterizes the higher-order smoothness of compactly supported solutions of the refinement equation, in terms of the p-norm joint spectral radius of a finite set of finite matrices determined by the coefficients c(kappa).

关键词： cascade algorithm dilation matrix joint spectral radius multiresolution analysis multiwavelets nonseparable wavelets refinement equations refinable functions scaling functions self-similarity wavelets

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：