Sharaf J. Malebary^*

CMC-Computers, Materials & Continua, Vol.79, No.1, pp. 1301-1317, 2024, DOI:10.32604/cmc.2024.047917

Abstract Brain tumors are a pressing public health concern, characterized by their high mortality and morbidity rates. Nevertheless, the manual segmentation of brain tumors remains a laborious and error-prone task, necessitating the development of more precise and efficient methodologies. To address this formidable challenge, we propose an advanced approach for segmenting brain tumor Magnetic Resonance Imaging (MRI) images that harnesses the formidable capabilities of deep learning and convolutional neural networks (CNNs). While CNN-based methods have displayed promise in the realm of brain tumor segmentation, the intricate nature of these tumors, marked by irregular shapes, varying sizes, uneven distribution, and limited available… More >

Hasan J. Alyamani^*

CMES-Computer Modeling in Engineering & Sciences, Vol.140, No.1, pp. 1129-1142, 2024, DOI:10.32604/cmes.2024.047756

Abstract The evaluation of disease severity through endoscopy is pivotal in managing patients with ulcerative colitis, a condition with significant clinical implications. However, endoscopic assessment is susceptible to inherent variations, both within and between observers, compromising the reliability of individual evaluations. This study addresses this challenge by harnessing deep learning to develop a robust model capable of discerning discrete levels of endoscopic disease severity. To initiate this endeavor, a multi-faceted approach is embarked upon. The dataset is meticulously preprocessed, enhancing the quality and discriminative features of the images through contrast limited adaptive histogram equalization (CLAHE). A diverse array of data augmentation… More > Graphic Abstract

Xianwei Jiang¹, Yanqiong Zhang^1,*, Juan Lei¹, Yudong Zhang^2,3,*

CMES-Computer Modeling in Engineering & Sciences, Vol.140, No.1, pp. 1-40, 2024, DOI:10.32604/cmes.2024.047649

Abstract Research on Chinese Sign Language (CSL) provides convenience and support for individuals with hearing impairments to communicate and integrate into society. This article reviews the relevant literature on Chinese Sign Language Recognition (CSLR) in the past 20 years. Hidden Markov Models (HMM), Support Vector Machines (SVM), and Dynamic Time Warping (DTW) were found to be the most commonly employed technologies among traditional identification methods. Benefiting from the rapid development of computer vision and artificial intelligence technology, Convolutional Neural Networks (CNN), 3D-CNN, YOLO, Capsule Network (CapsNet) and various deep neural networks have sprung up. Deep Neural Networks (DNNs) and their derived… More >

Qazi Mazhar ul Haq¹, Fahim Arif^2,3, Khursheed Aurangzeb⁴, Noor ul Ain³, Javed Ali Khan⁵, Saddaf Rubab⁶, Muhammad Shahid Anwar^7,*

CMC-Computers, Materials & Continua, Vol.78, No.3, pp. 4379-4397, 2024, DOI:10.32604/cmc.2024.047172

Abstract Software project outcomes heavily depend on natural language requirements, often causing diverse interpretations and issues like ambiguities and incomplete or faulty requirements. Researchers are exploring machine learning to predict software bugs, but a more precise and general approach is needed. Accurate bug prediction is crucial for software evolution and user training, prompting an investigation into deep and ensemble learning methods. However, these studies are not generalized and efficient when extended to other datasets. Therefore, this paper proposed a hybrid approach combining multiple techniques to explore their effectiveness on bug identification problems. The methods involved feature selection, which is used to… More >

Lifang Fu¹, Huanxin Peng^2,*, Changjin Ma², Yuhan Liu²

CMC-Computers, Materials & Continua, Vol.78, No.3, pp. 4399-4416, 2024, DOI:10.32604/cmc.2024.047053

Abstract In recent years, how to efficiently and accurately identify multi-model fake news has become more challenging. First, multi-model data provides more evidence but not all are equally important. Secondly, social structure information has proven to be effective in fake news detection and how to combine it while reducing the noise information is critical. Unfortunately, existing approaches fail to handle these problems. This paper proposes a multi-model fake news detection framework based on Tex-modal Dominance and fusing Multiple Multi-model Cues (TD-MMC), which utilizes three valuable multi-model clues: text-model importance, text-image complementary, and text-image inconsistency. TD-MMC is dominated by textural content and… More >

Ritesh Singh¹, Abhishek Gupta¹, Akshoy Ranjan Paul¹, Bireswar Paul¹, Suvash C. Saha^2,*

Energy Engineering, Vol.121, No.4, pp. 835-848, 2024, DOI:10.32604/ee.2024.046849

Abstract A parabolic trough solar collector (PTSC) converts solar radiation into thermal energy. However, low thermal efficiency of PTSC poses a hindrance to the deployment of solar thermal power plants. Thermal performance of PTSC is enhanced in this study by incorporating magnetic nanoparticles into the working fluid. The circular receiver pipe, with dimensions of 66 mm diameter, 2 mm thickness, and 24 m length, is exposed to uniform temperature and velocity conditions. The working fluid, Therminol-66, is supplemented with Fe₃O₄ magnetic nanoparticles at concentrations ranging from 1% to 4%. The findings demonstrate that the inclusion of nanoparticles increases the convective heat… More >

Haomiao Wang¹, Jinxi Wang², Qingmei Sui^2,*, Faye Zhang², Yibin Li¹, Mingshun Jiang², Phanasindh Paitekul³

Structural Durability & Health Monitoring, Vol.18, No.2, pp. 91-110, 2024, DOI:10.32604/sdhm.2023.041522

Abstract Due to their robust learning and expression ability for complex features, the deep learning (DL) model plays a vital role in bearing fault diagnosis. However, since there are fewer labeled samples in fault diagnosis, the depth of DL models in fault diagnosis is generally shallower than that of DL models in other fields, which limits the diagnostic performance. To solve this problem, a novel transfer residual Swin Transformer (RST) is proposed for rolling bearings in this paper. RST has 24 residual self-attention layers, which use the hierarchical design and the shifted window-based residual self-attention. Combined with transfer learning techniques, the… More >

Alexander A. Fedorets¹, Eduard E. Kolmakov¹, Leonid A. Dombrovsky^1,2,3,*

Frontiers in Heat and Mass Transfer, Vol.22, No.1, pp. 1-14, 2024, DOI:10.32604/fhmt.2024.049335

Abstract New experimental results, which are important for the potential use of small levitating droplets as biochemical microreactors, are reported. It is shown that the combination of infrared heating and reduced evaporation of saline water under the droplet cluster is sufficient to produce equilibrium saltwater droplets over a wide temperature range. The resulting universal dependence of droplet size on temperature simplifies the choice of optimal conditions for generating stable droplet clusters with droplets of the desired size. A physical analysis of the experimental results on the equilibrium size of saltwater droplets makes it possible to separate the effects related to the… More > Graphic Abstract

Noureddine Abouricha^1,*, Ayoub Gounni², Mustapha El Alami²

Frontiers in Heat and Mass Transfer, Vol.22, No.1, pp. 359-375, 2024, DOI:10.32604/fhmt.2024.047632

Abstract In this paper, experimental and numerical studies of heat transfer in a test local of side heated from below are presented and compared. All the walls, the rest of the floor and the ceiling are made from plywood and polystyrene in sandwich form ( plywood- polystyrene- plywood) just on one of the vertical walls contained a glazed door (). This local is heated during two heating cycles by a square plate of iron the width , which represents the heat source, its temperature is controlled. The plate is heated for two cycles by an adjustable set-point heat source placed just… More >

Nobuhito Nagasato¹, Zhengyuan Pei¹, Yasushi Koito^2,*

Frontiers in Heat and Mass Transfer, Vol.22, No.1, pp. 49-63, 2024, DOI:10.32604/fhmt.2024.047502

Abstract Visualization experiments were conducted to clarify the operational characteristics of a polymer pulsating heat pipe (PHP). Hydrofluoroether (HFE)-7100 was used as a working fluid, and its filling ratio was 50% of the entire PHP channel. A semi-transparent PHP was fabricated using a transparent polycarbonate sheet and a plastic 3D printer, and the movements of liquid slugs and vapor plugs of the working fluid were captured with a high-speed camera. The video images were then analyzed to obtain the flow patterns in the PHP. The heat transfer characteristics of the PHP were discussed based on the flow patterns and temperature distributions… More >