Shaohua Li, Haixiang Zhang^*, Hanjie Ma, Jie Feng, Mingfeng Jiang

CMC-Computers, Materials & Continua, Vol.76, No.3, pp. 3379-3392, 2023, DOI:10.32604/cmc.2023.041538

Abstract Scale variation is a major challenge in multi-person pose estimation. In scenes where persons are present at various distances, models tend to perform better on larger-scale persons, while the performance for smaller-scale persons often falls short of expectations. Therefore, effectively balancing the persons of different scales poses a significant challenge. So this paper proposes a new multi-person pose estimation model called FSA Net to improve the model’s performance in complex scenes. Our model utilizes High-Resolution Network (HRNet) as the backbone and feeds the outputs of the last stage’s four branches into the DCB module. The dilated convolution-based (DCB) module employs… More >

Bilal Hassan^1,*, Hafiz Husnain Raza Sherazi², Mubashir Ali³, Yusra Siddiqi²

Intelligent Automation & Soft Computing, Vol.37, No.3, pp. 2727-2743, 2023, DOI:10.32604/iasc.2023.039275

Abstract Following the success of soft biometrics over traditional biometrics, anthropometric soft biometrics are emerging as candidate features for recognition or retrieval using an image/video. Anthropometric soft biometrics uses a quantitative mode of annotation which is a relatively better method for annotation than qualitative annotations adopted by traditional biometrics. However, one of the most challenging tasks is to achieve a higher level of accuracy while estimating anthropometric soft biometrics using an image or video. The level of accuracy is usually affected by several contextual factors such as overlapping body components, an angle from the camera, and ambient conditions. Exploring and developing… More >

Sani Salisu^1,2, A. S. A. Mohamed^1,*, M. H. Jaafar³, Ainun S. B. Pauzi¹, Hussain A. Younis^1,4

CMC-Computers, Materials & Continua, Vol.76, No.2, pp. 2385-2400, 2023, DOI:10.32604/cmc.2023.035904

Abstract In this article, a comprehensive survey of deep learning-based (DL-based) human pose estimation (HPE) that can help researchers in the domain of computer vision is presented. HPE is among the fastest-growing research domains of computer vision and is used in solving several problems for human endeavours. After the detailed introduction, three different human body modes followed by the main stages of HPE and two pipelines of two-dimensional (2D) HPE are presented. The details of the four components of HPE are also presented. The keypoints output format of two popular 2D HPE datasets and the most cited DL-based HPE articles from… More >

Jinhe Zhang², Jie Liu^1,2,*

The International Conference on Computational & Experimental Engineering and Sciences, Vol.25, No.4, pp. 1-2, 2023, DOI:10.32604/icces.2023.09279

Abstract The small uncertainties of geometric parameters of industrial robot, which are caused by links manufacturing and service wear errors, can deteriorate the positioning accuracy of end-effector through multi-level propagation and is difficult to be measured and compensated by high-precision instruments. Hence, an efficient inverse identification method of parameter uncertainty based on global sensitivity analysis and optimal measurement point selection is proposed. In order to ensure the universality of identification results in calibration and control works, the standard Denavit-Hartenberg (D-H) method is employed to establish the kinematic model of series 6 degrees of freedom (DOF) robots. Considering the stochastic error between… More >

Jiepeng Yao^1,2, Zhanjia Peng^1,2, Jingjing Liu^1,2, Chengxiao Fan^1,2, Zhongyi Wang^1,2,3, Lan Huang^1,2,*

CMES-Computer Modeling in Engineering & Sciences, Vol.137, No.3, pp. 2243-2265, 2023, DOI:10.32604/cmes.2023.028101

Abstract In the establishment of differential equations, the determination of time-varying parameters is a difficult problem, especially for equations related to life activities. Thus, we propose a new framework named BioE-PINN based on a physical information neural network that successfully obtains the time-varying parameters of differential equations. In the proposed framework, the learnable factors and scale parameters are used to implement adaptive activation functions, and hard constraints and loss function weights are skillfully added to the neural network output to speed up the training convergence and improve the accuracy of physical information neural networks. In this paper, taking the electrophysiological differential… More >

Hassan Okasha^1,2, Mazen Nassar^1,3,*

CMES-Computer Modeling in Engineering & Sciences, Vol.137, No.3, pp. 2219-2241, 2023, DOI:10.32604/cmes.2023.028783

Abstract In this paper, we introduce a new four-parameter version of the traditional Weibull distribution. It is able to provide seven shapes of hazard rate, including constant, decreasing, increasing, unimodal, bathtub, unimodal then bathtub, and bathtub then unimodal shapes. Some basic characteristics of the proposed model are studied, including moments, entropies, mean deviations and order statistics, and its parameters are estimated using the maximum likelihood approach. Based on the asymptotic properties of the estimators, the approximate confidence intervals are also taken into consideration in addition to the point estimators. We examine the effectiveness of the maximum likelihood estimators of the model’s… More >

R. Rajaraman^a , L. Anna Gowsalya^b,*, R. Velraj^c

Frontiers in Heat and Mass Transfer, Vol.11, pp. 1-8, 2018, DOI:10.5098/hmt.11.23

Abstract To get accurate results in casting simulations, prediction of interfacial heat transfer coefficient (IHTC) is imperative. In this paper an attempt has been made for estimating IHTC during solidification process of a rectangular aluminium alloy casting in a sand mould. The cast temperature and mould temperature are measured during the experimental process at different time intervals during the process of solidification. Two different inverse methods, namely control volume and Beck’s approach are used to estimate the heat flux and temperature at the mould surface by using the experimentally measured temperatures. In the case of control volume technique, the partial derivative… More >

Xiaoli Jing, Xianpeng Wang^*, Xiang Lan, Ting Su

CMES-Computer Modeling in Engineering & Sciences, Vol.137, No.2, pp. 1789-1804, 2023, DOI:10.32604/cmes.2023.028477

Abstract At present, the traditional channel estimation algorithms have the disadvantages of over-reliance on initial conditions and high complexity. The bacterial foraging optimization (BFO)-based algorithm has been applied in wireless communication and signal processing because of its simple operation and strong self-organization ability. But the BFO-based algorithm is easy to fall into local optimum. Therefore, this paper proposes the quantum bacterial foraging optimization (QBFO)-binary orthogonal matching pursuit (BOMP) channel estimation algorithm to the problem of local optimization. Firstly, the binary matrix is constructed according to whether atoms are selected or not. And the support set of the sparse signal is recovered… More >

L. Anna Gowsalya^a , P.D. Jeyakumar^b,*, R. Rajaraman^c,†, R. Velraj^d

Frontiers in Heat and Mass Transfer, Vol.12, pp. 1-7, 2019, DOI:10.5098/hmt.12.21

Abstract Solidification of casting is a complex phenomenon which requires accurate input to simulate for real time applications. Interfacial heat transfer coefficient (IHTC) is an important input parameter for the simulation process. The IHTC is varying with respect to time during solidification and the exact value is to be given as input for the accurate simulation of the casting process. In this work an attempt is made to estimate the IHTC during solidification of spherical shaped aluminum alloy component with sand mould. The mould surface heat flux and mould surface temperatures are estimated by inverse control volume technique using the temperature… More >

S. Ravi Teja^a , Chellapilla V. K. N. S. N. Moorthy^b,*, S. Jayakumar^c , Ayyagari Kiran Kumar^d , V. Srinivas^c,*

Frontiers in Heat and Mass Transfer, Vol.15, pp. 1-9, 2020, DOI:10.5098/hmt.15.7

Abstract This article is a summary of research involving the evaluation of the thermo-physical properties of Mono-ethylene - glycol-based solar thermic fluids oxidized multiwalled carbon nanotubes. Nanofluids were prepared with Mono-ethylene glycol and water as base fluids in 100:0, 90:10 and 80:20 ratios. These base fluids of three categories were dispersed with purified and oxidized multiwalled carbon nanotubes (MWCNTs) in the weight fractions of 0.125, 0.25 and 0.5 percentages. The variation in zeta potential is studied to examine the dispersion stability during 2 months. Thermal conductivity and dynamic viscosity were measured by hot disk method and Anton paar viscometer respectively. Significant… More >