Amin Bemani¹, Alireza Baghban², Shahaboddin Shamshirband^{3, 4, *}, Amir Mosavi^{5, 6, 7}, Peter Csiba⁷, Annamaria R. Varkonyi-Koczy^{5, 7}

CMC-Computers, Materials & Continua, Vol.63, No.3, pp. 1175-1204, 2020, DOI:10.32604/cmc.2020.07723 - 30 April 2020

Abstract In the present work, a novel machine learning computational investigation is carried out to accurately predict the solubility of different acids in supercritical carbon dioxide. Four different machine learning algorithms of radial basis function, multi-layer perceptron (MLP), artificial neural networks (ANN), least squares support vector machine (LSSVM) and adaptive neuro-fuzzy inference system (ANFIS) are used to model the solubility of different acids in carbon dioxide based on the temperature, pressure, hydrogen number, carbon number, molecular weight, and the dissociation constant of acid. To evaluate the proposed models, different graphical and statistical analyses, along with novel More >

Ravi Samikannu^{1, *}, Rohini Ravi², Sivaram Murugan³, Bakary Diarra⁴

CMC-Computers, Materials & Continua, Vol.63, No.3, pp. 1133-1142, 2020, DOI:10.32604/cmc.2020.08578 - 30 April 2020

Abstract The identification of brain tumors is multifarious work for the separation of the similar intensity pixels from their surrounding neighbours. The detection of tumors is performed with the help of automatic computing technique as presented in the proposed work. The non-active cells in brain region are known to be benign and they will never cause the death of the patient. These non-active cells follow a uniform pattern in brain and have lower density than the surrounding pixels. The Magnetic Resonance (MR) image contrast is improved by the cost map construction technique. The deep learning algorithm More >

Shiqi Wang¹, Yimin Yang^{1, *}, Ruizhong Wei¹, Qingming Jonathan Wu²

CMC-Computers, Materials & Continua, Vol.63, No.3, pp. 1081-1091, 2020, DOI:10.32604/cmc.2020.09648 - 30 April 2020

Abstract Human motion recognition plays a crucial role in the video analysis framework. However, a given video may contain a variety of noises, such as an unstable background and redundant actions, that are completely different from the key actions. These noises pose a great challenge to human motion recognition. To solve this problem, we propose a new method based on the 3-Dimensional (3D) Bag of Visual Words (BoVW) framework. Our method includes two parts: The first part is the video action feature extractor, which can identify key actions by analyzing action features. In the video action More >

Zhuqing Jiao^{1, *}, Yixin Ji¹, Tingxuan Jiao¹, Shuihua Wang^{2, *}

CMES-Computer Modeling in Engineering & Sciences, Vol.123, No.2, pp. 845-871, 2020, DOI:10.32604/cmes.2020.08999 - 01 May 2020

Abstract Currently, functional connectomes constructed from neuroimaging data have emerged as a powerful tool in identifying brain disorders. If one brain disease just manifests as some cognitive dysfunction, it means that the disease may affect some local connectivity in the brain functional network. That is, there are functional abnormalities in the sub-network. Therefore, it is crucial to accurately identify them in pathological diagnosis. To solve these problems, we proposed a sub-network extraction method based on graph regularization nonnegative matrix factorization (GNMF). The dynamic functional networks of normal subjects and early mild cognitive impairment (eMCI) subjects were… More >

Wei Liu^{1, 2, *}, Qianxiang Wu²

CMES-Computer Modeling in Engineering & Sciences, Vol.123, No.2, pp. 661-690, 2020, DOI:10.32604/cmes.2020.07764 - 01 May 2020

Abstract A utility tunnel system consists of pipes and ancillary facilities. In this paper, a finite element model of a concrete utility tunnel with pipes inside is established. Several tunnel segments were built to simulate a real utility tunnel, while the pipe was fixed by springs on the brackets in the utility tunnel. Using the discrete soil spring element to simulate the soil-structure interaction, actual earthquake records were adopted as excitation to analyze the seismic responses of pipes in a utility tunnel. Moreover, the influences of different parameters, including soil type, earthquake records, and field apparent More >

Caining Zhang¹, Xiaopeng Guo², Xiaoya Guo³, David Molony⁴, Huaguang Li², Habib Samady⁴, Don P. Giddens^4,5, Lambros Athanasiou⁶, Dalin Tang^1*,7, Rencan Nie^2,*, Jinde Cao⁸

CMES-Computer Modeling in Engineering & Sciences, Vol.123, No.2, pp. 631-646, 2020, DOI:10.32604/cmes.2020.09718 - 01 May 2020

Abstract Optical coherence tomography (OCT) is a new intravascular imaging technique with high resolution and could provide accurate morphological infor￾mation for plaques in coronary arteries. However, its segmentation is still com￾monly performed manually by experts which is time-consuming. The aim of this study was to develop automatic techniques to characterize plaque components and quantify plaque cap thickness using 3 machine learning methods including convolutional neural network (CNN) with U-Net architecture, CNN with Fully convolutional DenseNet (FC-DenseNet) architecture and support vector machine (SVM). In vivo OCT and intravascular ultrasound (IVUS) images were acquired from two patients at Emory… More >

Xinglong Wang^1,2, Cheng Wang^1,2, Xin Zhou^1,*, Mingkang Zhang³, Peiyu Zhang¹, Lei Wang²

CMES-Computer Modeling in Engineering & Sciences, Vol.123, No.2, pp. 495-508, 2020, DOI:10.32604/cmes.2020.09778 - 01 May 2020

Abstract The new regenerative cooling thermal protection system exhibits the multifunctional characteristics of load-carrying and heat exchange cooling, which are fundamental for the lightweight design and thermal protection of hypersonic vehicles. Triply periodic minimal surface (TPMS) is especially suitable for the structural design of the internal cavity of regenerative cooling structures owing to its excellent structural characteristics. In this study, test pieces were manufactured using Ti6Al4V lightweight material. We designed three types of porous test pieces, and the interior was filled with a TPMS lattice (Gyroid, Primitive, I-WP) with a porosity of 30%. All porous test… More >

Mounir Kriraa^1,2,*, Khalid Souhar³, Driss Achemlal⁴, Youssef Ait Yassine^5,6, Abdelmajid Farchi¹

FDMP-Fluid Dynamics & Materials Processing, Vol.16, No.2, pp. 199-209, 2020, DOI:10.32604/fdmp.2020.07986 - 21 April 2020

Abstract In this paper, a detailed investigation of water (Pr ¼ 7:0) convection in a chemical condenser is carried out. Two openings are located along one side of the cavity. The Navier-Stokes equations are solved in the frame of a control volume method using the SIMPLEC algorithm to implement adequate coupling of pressure and velocity. Special emphasis is given to the influence of the Reynolds number, the tilt of the channel and the Rayleigh number on the convective heat transfer. Results are presented and discussed allowing the control parameters to span relatively wide intervals: Rayleigh number (10⁴ More >

A. Aissa^{1, *}, M. E. A. Slimani², F. Mebarek-Oudina³, R. Fares¹, A. Zaim¹, L. Kolsi^{4, 5}, M. Sahnoun¹, M. E. Ganaoui⁶

FDMP-Fluid Dynamics & Materials Processing, Vol.16, No.2, pp. 147-159, 2020, DOI:10.32604/fdmp.2020.04073 - 21 April 2020

Abstract In this paper, flow of slightly rarefied compressible nitrogen in microchannels has been investigated numerically for low values of Reynolds and Mach numbers. The 2D governing equations were solved using Finite Element Method with first-order slip boundary conditions (Comsol Multiphysics software). A validation was performed by comparing with similar configuration from the literature. It was found that our model can accurately predict the pressure driven flow in microchannels. Several interesting findings are reported about the Relative pressure, longitudinal velocity, Mach number, effect of gas rarefaction and flow rate. More >

Abierdi¹, Yuzhou Xiang², Haiyi Zhong², Xin Gu², Hanlong Liu^{2, 3}, Wengang Zhang^{2, 3, *}

CMC-Computers, Materials & Continua, Vol.63, No.2, pp. 825-844, 2020, DOI:10.32604/cmc.2020.07946 - 01 May 2020

Abstract Tunnel excavation is a complicated loading-unloading-reloading process characterized by decreased radial stresses and increased axial stresses. An approach that considers only loading, is generally used in tunnel model testing. However, this approach is incapable of characterizing the unloading effects induced by excavation on surrounding rocks and hence presents radial and tangential stress paths during the failure process that are different from the actual stress state of tunnels. This paper carried out a comparative analysis using laboratory model testing and particle flow code (PFC^2D)-based numerical simulation, and shed light upon the crack propagation process and, microscopic stress More >