检索结果-内蒙古大学图书馆

A lightweight human pose estimation model based on nonlinear spiking neural convolution model

NEUROCOMPUTING 2025年 622卷

作者： Zhang, Yuxuan Xia, Meichen Peng, Hong Liu, Zhicai Guo, Jun XiHua Univ Sch Comp & Software Engn Chengdu 610039 Peoples R China Xihua Univ West China Hosp Dept Intens Care Unit Chengdu 610064 Peoples R China Xihua Univ West China Hosp Natl Clin Res Ctr Geriatr Chengdu 610064 Peoples R China Peoples Hosp Dafang Bijie 551600 Guizhou Peoples R China

Human pose estimation is an important task in the field of computer vision. Existing high-precision models need more parameters and computational complexity, making them unsuitable for resource-constrained devices. On the other hand, current lightweight models often have limited accuracy for reduced parameters and computations. To address the challenge, this paper proposes a novel lightweight human pose estimation model based on nonlinear spiking neural P system (NSNP). It adopts a lightweight backbone network similar to the HRNet framework. Moreover, the nonlinear spiking neural convolutional model introduces a novel Dual- channel Atrous Spatial Pooling (DCASP) module. This module facilitates the interaction of information from different scales of receptive fields to capture details in the image. Experimental results demonstrate that the proposed model achieves 89.0% accuracy on the MPII dataset with only 4.5 million parameters and 71.5% average accuracy on the COCO2017 validation set with a mere 4.2 Gflops computational complexity. The experimental results of this paper's model surpass those of the latest lightweight models, indicating that this approach effectively balances accuracy and complexity. The code is available at https://***/ YuxuanZhang-web/Lite-NSNP-Pose.

关键词： Human pose estimation Nonlinear spiking neural P system Lightweight model convolution model

来源：评论

学校读者我要写书评

暂无评论

Assessing shipping water vertical loads on a fixed structure by convolution model and wet dam-break tests

引用

APPLIED OCEAN RESEARCH 2019年 82卷 63-73页

作者： Hernandez-Fontes, Jassiel V. Vitola, Marcelo A. Esperanca, Paulo de Tarso T. Sphaier, Sergio H. Univ Fed Rio de Janeiro LabOceano Ocean Technol Lab Ocean Engn Program COPPE Parque Tecnol Rio BR-21941907 Rio De Janeiro RJ Brazil Univ Nacl Autonoma Mexico Dept Hydraul Engn Inst II UNAM Mexico City DF Mexico

Estimation of loads derived from shipping water events in naval and offshore structures is of importance to improve their structural design or to predict changes in their dynamics. For the case of vertical loads on deck of a fixed structure, it is possible to estimate analytically their evolution in time by considering the distribution of shipping water elevations. However, the classical approach to estimate this distribution (i.e., dam-break method) tends to overestimate the amount of water on deck and does not follow the generated decay trends observed experimentally. In the present work, the time evolution of the vertical loads due to shipping water events was studied analytically and experimentally. The validation of the use of a convolution model to estimate the time evolution of vertical loads is presented, aiming to improve the results obtained with classical approaches. A systematic experimental study has been conducted using the wet dam-break method to generate isolated shipping water events, measuring the slow-varying vertical loads on a rectangular fixed structure. A force balance and a high-speed camera have been used at the same sampling rate to monitor the vertical loads and the shipping water evolution on the deck. Results demonstrated that the use of the convolution model improved the representation of the time series of loads compared with the traditional dam-break approach. With this new method, it was possible to capture the peaks and the decay tendencies observed in the experimental data in an approximated way.

关键词： convolution model Force balance Shipping water Systematic experiments Vertical loads Wet dam-break

来源：评论

学校读者我要写书评

暂无评论

An Exponential-Gamma convolution model for Background Correction of Illumina BeadArray Data

引用

COMMUNICATIONS IN STATISTICS-THEORY AND METHODS 2011年第17期40卷 3055-3069页

作者： Chen, Min Xie, Yang Story, Michael Univ Texas SW Med Ctr Dallas Div Biostat Dept Clin Sci Simmons Canc Ctr Dallas TX 75390 USA Univ Texas SW Med Ctr Dallas Dept Radiat Oncol Dallas TX 75390 USA

Illumina BeadArrays are becoming an increasingly popular Microarray platform due to its high data quality and relatively low cost. One distinct feature of Illumina BeadArrays is that each array has thousands of negative control bead types containing oligonucleotide sequences that are not specific to any target genes in the genome. This design provides a way of directly estimating the distribution of the background noise. In the literature of background correction for BeadArray data, the information from negative control beads is either ignored, used in a naive way that can lead to a loss in efficiency, or the noise is assumed to be normally distributed. However, we show with real data that the noise can be skewed. In this study, we propose an exponential-gamma convolution model for background correction of Illumina BeadArray data. Using both simulated and real data examples, we show that the proposed method can improve the signal estimation and detection of differentially expressed genes when the signal to noise ratio is large and the noise has a skewed distribution.

关键词： Background correction convolution model Gamma distribution Illumina BeadArray

来源：评论

学校读者我要写书评

暂无评论

A RECURSIVE ALGORITHM AND ITS CONVERGENCE FOR PARAMETER ESTIMATION OF convolution model

引用

Acta Mathematica Scientia 2008年第1期28卷 93-100页

作者：胡必锦汪达成雷鸣 Institute of Information and Calculation Science Chongqing Jiaotong University

In this article, the problem on the estimation of the convolution model parameters is considered. The recursive algorithm for estimating model parameters is introduced from the orthogonal procedure of the data, the convergence of this algorithm is theoretically discussed, and a sufficient condition for the convergence criterion of the orthogonal procedure is given. According to this condition, the recursive algorithm is convergent to model wavelet A- = （1, α1,..., αq）.

关键词： convolution model parameter estimation recursive algorithm norm of operators convergence

来源：评论

学校读者我要写书评

暂无评论

A convolution model to convert transmission dose images to exit dose distributions

引用

MEDICAL PHYSICS 1997年第2期24卷 189-199页

作者： Boellaard, R vanHerk, M Mijnheer, BJ The Netherlands Cancer Institute/Antoni van Leeuwenhoek Huis Radiotherapy Department Plesmanlaan 121 1066 CX Amsterdam The Netherlands

The aim of this study is to develop a model which computes exit dose values from transmission dose data obtained during patient treatment with an electronic portal imaging device (EPID). The proposed model convolves the primary dose distribution, derived from transmission dose distributions at large air gaps, with a scatter kernel to obtain the exit dose. The influence of inhomogeneities on the scatter contribution is taken into account by using a radiological path length model. To determine the parameters of the model, an extensive set of transmission dose measurements was performed behind various phantoms in an 8 MV beam using a liquid-filled EPID. The influence on the transmission dose of field size, phantom thickness, air gap between phantom and detector, and source-phantom distance was investigated. At air gaps larger than 50 cm the distribution of scattered dose is almost flat and its contribution to the total dose is relatively small, thus allowing an accurate separation of the primary and scattered dose by subtraction. Scattered dose distributions for air gaps smaller than 50 cm were obtained by subtracting the primary dose (corrected for divergence) from the measured total transmission dose. The resulting scattered dose distribution behind homogeneous phantoms has a Gaussian shaped profile, which becomes wider with increasing air gap. The relative contribution of scattered dose depends on the phantom thickness and is maximal for a thickness of about 10 cm. Using these results, the parameters of the convolution model (i.e., the shape of the scatter kernel) were determined. With the model the absolute exit dose is predicted with an accuracy of about 2% (1 s.d.) within the entire radiation field for homogeneous phantoms. Inhomogeneities are taken into account by calculating the radiological path length from the measured primary dose, i.e., without using CT data. By using the measured radiological path length the exit dose can be determined for inhomogeneous ph

关键词： in vivo dosimetry portal imaging exit dose transmission dose convolution model

来源：评论

学校读者我要写书评

暂无评论

Two-dimensional exit dosimetry using a liquid-filled electronic portal imaging device and a convolution model

引用

RADIOTHERAPY AND ONCOLOGY 1997年第2期44卷 149-157页

作者： Boellaard, R vanHerk, M Uiterwaal, H Mijnheer, B Radiotherapy Department The Netherlands Cancer Institute/Antoni van Leeuwenhoek Huis Plesmanlaan 121 1066 CX Amsterdam The Netherlands

Background and purpose: To determine the accuracy of two-dimensional exit dose measurements with an electronic portal imaging device, EPID, using a convolution model for a variety of clinically relevant situations. Materials and methods: Exit doses were derived from portal dose images, obtained with a liquid-filled EPID at distances of 50 cm or more behind the patient, by using a convolution model. The resulting on-and off-axis exit dose values were first compared with ionization chamber exit dose measurements for homogeneous and inhomogeneous phantoms in open and wedged 4,8 and 18 MV photon beams. The accuracy of the EPID exit dose measurements was then determined for a number of anthropomorphic phantoms (lung and larynx) irradiated under clinical conditions and for a few patients treated in an 8 MV beam. The latter results were compared with in vivo exit dose measurements using diodes. Results: The exit dose can be determined from portal images with an accuracy of 1.2% (1 SD) compared with ionization chamber measurements for open beams and homogeneous phantoms at all tested beam qualities. In the presence of wedges and for inhomogeneous phantoms the average relative accuracy slightly deteriorated to 1.7% (1 SD). For lung phantoms in a 4 MV beam a similar accuracy was obtained after refinement of our convolution model, which requires knowledge of the patient contour. Differences between diode and EPID exit dose measurements for an anthropomorphic lung phantom in an 8 MV beam were 2.5% at most, with an average agreement within 1% (1 SD). For larynx phantoms in a 4 MV beam exit doses obtained with an ionization chamber and EPID agreed within 1.5% (1 SD). Finally, exit doses in a few patients irradiated in an 8 MV beam could be determined with the EPID with an accuracy of 1.1% (1 SD) relative to exit dose measurements using diodes. Conclusions: Portal images, obtained with our EPID and analyzed with our convolution model, can be used to determine the exit dose distrib

关键词： portal imaging exit dosimetry in vivo dosimetry electronic portal imaging device convolution model

来源：评论

学校读者我要写书评

暂无评论

Calibration of VFTO Bushing Sensor Based on convolution model

Calibration of VFTO Bushing Sensor Based on Convolution Mode...

引用

26th IEEE International Instrumentation and Measurement Technology Conference

作者： Ma Guo-ming Li Cheng-rong Quan Jiang-tao Jiang Jian N China Elect Power Univ Beijing Key Lab High Voltage Beijing Peoples R China N China Elect Power Univ EMC Beijing Peoples R China

ISBN: (纸本)9781424433520

Disconnector switching operations in large gas insulated switchgear (GIS) systems may cause very fast transients overvoltages (VFTO), which produce dielectric stress to transformer connecting with the disconnector. A VFTO bushing sensor is developed to measure the VFTO at the transformer entrance. Since the high frequency ratio of the bushing sensor is not constant, calibration before the field measurement is needed. Based on the convolution model and step response, a new calibration method is used to identify the frequency response of the bushing sensor. Calibration of an 110kV rated bushing sensor is carried on in our laboratory to investigate the effectiveness of this method, and the calibrated results agree well with the amplitude-response gained by frequency sweep test, which demonstrates the calibrating method can be applied in VFTO bushing sensor calibration. Calibration of an UHV rated bushing sensor is processed in a factory and the frequency response of the sensor is given at the end of the paper.

关键词： VFTO Step Response convolution model UHV Rated Bushing Sensor

来源：评论

学校读者我要写书评

暂无评论

Hermite regression estimation in noisy convolution model

引用

JOURNAL OF STATISTICAL PLANNING AND INFERENCE 2024年 233卷

作者： Sacko, Ousmane Univ Paris Nanterre MODALX UMR 9023 Paris France

In this paper, we consider the following regression model: y(kT/n) = f star g (kT/n) + epsilon(k), k = -n, ..., n - 1 T fixed, where g is known and f is the unknown function to be estimated. The errors (epsilon(k))(-n <= k <= n-1) are independent and identically distributed centered with finite known variance. Two adaptive estimation methods for f are considered by exploiting the properties of the Hermite basis. We study the quadratic risk of each estimator. If f belongs to Sobolev regularity spaces, we derive rates of convergence. Adaptive procedures to select the relevant parameter inspired by the Goldenshluger and Lepski method are proposed and we prove that the resulting estimators satisfy oracle inequalities for sub-Gaussian epsilon's. Finally, we illustrate numerically these approaches.

关键词： convolution model Hermite basis model selection Nonparametric regression Projection estimator

来源：评论

学校读者我要写书评

暂无评论

convolution models for the dielectric function of glass

Convolution models for the dielectric function of glass

引用

9th Conference of the European-Society-of-Glass-Science-and-Technology/Annual Meeting of the International-Commission-on-Glass

作者： van Nijnatten, P. A. POB 6235 NL-5600 HE Eindhoven Netherlands

ISBN: (纸本)9780878493876

Spectral behaviour of the real and imaginary parts of the optical constants of glass has been widely investigated to obtain band structural parameters of optically induced transitions. Curve fitting procedures for obtaining a classical oscillator fit to reflectance and/or transmittance data play an important role in this application. The present form of the dispersion model that is widely used to describe disordered media like glass uses a convolution of the Lorentzian oscillator function and the Gaussian Probability Density Function. This model is capable of describing symmetrical band shapes only. In this paper a convolution model is proposed based on using the Beta function as PDF. The maximum of the PDF, which corresponds to the frequency with the highest probability, corresponds to the central frequency of the particular oscillator species in the convolution model. For a certain value of the parameter that describes the degree of asymmetry, the new model is equivalent with the present convolution model and the remaining parameters have an identical meaning yielding practically identical values. The new model also solves a problem related to the infinite integration intervals of the Gaussian PDF based convolution model.

关键词： dispersion convolution model dielectric function permittivity optical constants refractive index absorption silica glass

来源：评论

学校读者我要写书评

暂无评论

Comparing multilevel and multiscale convolution models for small area aggregated health data

引用

SPATIAL AND SPATIO-TEMPORAL EPIDEMIOLOGY 2017年 22卷 39-49页

作者： Aregay, Mehreteab Lawson, Andrew B. Faes, Christel Kirby, Russell S. Carroll, Rachel Watjou, Kevin Med Univ South Carolina Dept Publ Hlth Charleston SC 29425 USA Hasselt Univ Interuniv Inst Biostat & Stat Bioinformat Diepenbeek Belgium Univ S Florida Dept Community & Family Hlth Tampa FL USA

In spatial epidemiology, data are often arrayed hierarchically. The classification of individuals into smaller units, which in turn are grouped into larger units, can induce contextual effects. On the other hand, a scaling effect can occur due to the aggregation of data from smaller units into larger units. In this paper, we propose a shared multilevel model to address the contextual effects. In addition, we consider a shared multiscale model to adjust for both scale and contextual effects simultaneously. We also study convolution and independent multiscale models, which are special cases of shared multilevel and shared multiscale models, respectively. We compare the performance of the models by applying them to real and simulated data sets. We found that the shared multiscale model was the best model across a range of simulated and real scenarios as measured by the deviance information criterion (DIC) and the Watanabe Akaike information criterion (WAIC). (C) 2017 Elsevier Ltd. All rights reserved.

关键词： Multilevel model Multiscale model convolution model Shared random effects Scaling effects Contextual effects

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：