Dinh Phu Cuong Le^1,2, Dong Wang¹, Viet-Tuan Le^3,*

CMC-Computers, Materials & Continua, Vol.80, No.1, pp. 37-60, 2024, DOI:10.32604/cmc.2024.050790

Abstract Transformer models have emerged as dominant networks for various tasks in computer vision compared to Convolutional Neural Networks (CNNs). The transformers demonstrate the ability to model long-range dependencies by utilizing a self-attention mechanism. This study aims to provide a comprehensive survey of recent transformer-based approaches in image and video applications, as well as diffusion models. We begin by discussing existing surveys of vision transformers and comparing them to this work. Then, we review the main components of a vanilla transformer network, including the self-attention mechanism, feed-forward network, position encoding, etc. In the main part of More >

G. Sunil Santhosh Kumar^1,2,*, M. Rudra Kumar³

CMC-Computers, Materials & Continua, Vol.80, No.1, pp. 695-713, 2024, DOI:10.32604/cmc.2024.050143

Abstract This article presents an innovative approach to automatic rule discovery for data transformation tasks leveraging XGBoost, a machine learning algorithm renowned for its efficiency and performance. The framework proposed herein utilizes the fusion of diversified feature formats, specifically, metadata, textual, and pattern features. The goal is to enhance the system’s ability to discern and generalize transformation rules from source to destination formats in varied contexts. Firstly, the article delves into the methodology for extracting these distinct features from raw data and the pre-processing steps undertaken to prepare the data for the model. Subsequent sections expound… More >

Haiyue Li¹, Jing Xie², Jing Ke³, Ye Yuan¹, Xiaoyong Pan¹, Hongyi Xin⁴, Hongbin Shen^1,*

CMC-Computers, Materials & Continua, Vol.80, No.1, pp. 487-506, 2024, DOI:10.32604/cmc.2024.049640

Abstract Multi-modal histological image registration tasks pose significant challenges due to tissue staining operations causing partial loss and folding of tissue. Convolutional neural network (CNN) and generative adversarial network (GAN) are pivotal in medical image registration. However, existing methods often struggle with severe interference and deformation, as seen in histological images of conditions like Cushing’s disease. We argue that the failure of current approaches lies in underutilizing the feature extraction capability of the discriminator in GAN. In this study, we propose a novel multi-modal registration approach GAN-DIRNet based on GAN for deformable histological image registration. To… More >

Huijuan Fu, Linlin Zhu, Chunhui Wang, Xiaoqi Xi, Yu Han, Lei Li, Yanmin Sun, Bin Yan^*

CMC-Computers, Materials & Continua, Vol.80, No.1, pp. 1711-1725, 2024, DOI:10.32604/cmc.2024.049623

Abstract Nano-computed tomography (Nano-CT) is an emerging, high-resolution imaging technique. However, due to their low-light properties, tabletop Nano-CT has to be scanned under long exposure conditions, which the scanning process is time-consuming. For 3D reconstruction data, this paper proposed a lightweight 3D noise reduction method for desktop-level Nano-CT called AAD-ResNet (Axial Attention DeNoise ResNet). The network is framed by the U-net structure. The encoder and decoder are incorporated with the proposed 3D axial attention mechanism and residual dense block. Each layer of the residual dense block can directly access the features of the previous layer, which More >

Bo Yang^1,*, Yucun Qian¹, Jianzhong Xu², Yaxing Ren³, Yixuan Chen⁴

Energy Engineering, Vol.121, No.8, pp. 2085-2091, 2024, DOI:10.32604/ee.2024.050083

Abstract This article has no abstract. More >

Shan Liu¹, Chengbin Chi¹, Fengze Han², Yanan Wu¹, Lin Zhu¹, Tuo Wang^2,*

Energy Engineering, Vol.121, No.8, pp. 2257-2273, 2024, DOI:10.32604/ee.2024.049861

Abstract Voltage source converter based high voltage direct current (VSC-HVDC) can participate in voltage regulation by flexible control to help maintain the voltage stability of the power grid. In order to quantitatively evaluate its influence on the voltage interaction between VSC-HVDC and line commutated converter based high voltage direct current (LCC-HVDC), this paper proposes a hybrid multi-infeed interaction factor (HMIIF) calculation method considering the voltage regulation control characteristics of VSC-HVDC. Firstly, for a hybrid multi-infeed high voltage direct current system, an additional equivalent operating admittance matrix is constructed to characterize HVDC equipment characteristics under small disturbance.… More >

Liqiong Chen¹, Kui Zhao¹, Kai Zhang^1,*, Duo Xv¹, Hongxvan Hu², Guoguang Ma¹, Wenwen Zhan³

Energy Engineering, Vol.121, No.8, pp. 2143-2165, 2024, DOI:10.32604/ee.2024.049362

Abstract The leakage gas from a buried natural gas pipelines has the great potential to cause economic losses and environmental pollution owing to the complexity of the mountainous environment. In this study, computational fluid dynamics (CFD) method was applied to investigate the diffusion law and hazard range of buried natural gas pipeline leakage in mountainous environment. Based on cloud chart, concentration at the monitoring site and hazard range of lower explosion limit (LEL) and upper explosion limit (UEL), the influences of leakage hole direction and shape, soil property, burial depth, obstacle type on the diffusion law… More >

SNJEŽANA KAŠTELAN^1,2, ANA DIDOVIĆ PAVIČIĆ³, DARIA PAŠALIĆ⁴, TAMARA NIKUŠEVA-MARTIĆ⁵, SAMIR ČANOVIĆ^3,7, PETRA KOVAČEVIĆ^1,6,*, SUZANA KONJEVODA^3,7

Oncology Research, Vol.32, No.8, pp. 1265-1285, 2024, DOI:10.32604/or.2024.048437

Abstract Uveal and conjunctival melanomas are relatively rare tumors; nonetheless, they pose a significant risk of mortality for a large number of affected individuals. The pathogenesis of melanoma at different sites is very similar, however, the prognosis for patients with ocular melanoma remains unfavourable, primarily due to its distinctive genetic profile and tumor microenvironment. Regardless of considerable advances in understanding the genetic characteristics and biological behaviour, the treatment of uveal and conjunctival melanoma remains a formidable challenge. To enhance the prospect of success, collaborative efforts involving medical professionals and researchers in the fields of ocular biology… More > Graphic Abstract

HAIQING HU^1,#,*, HAO YANG^2,#, SHUAISHUAI FAN³, XUE JIA³, YING ZHAO³, HONGRUI LI³

Oncology Research, Vol.32, No.8, pp. 1335-1346, 2024, DOI:10.32604/or.2024.044174

Abstract Long non-coding RNAs (lncRNAs) have been implicated in cancer progression and drug resistance development. Moreover, there is evidence that lncRNA HOX transcript antisense intergenic RNA (HOTAIR) is involved in colorectal cancer (CRC) progression. The present study aimed to examine the functional role of lncRNA HOTAIR in conferring radiotherapy resistance in CRC cells, as well as the underlying mechanism. The relative expression levels of HOTAIR were examined in 70 pairs of CRC tumor and para-cancerous tissues, as well as in radiosensitive and radioresistant samples. The correlations between HOTAIR expression levels and clinical features of patients with… More >

Ali Altalbe^1,2,*, Abdul Rehman Javed³

Computer Systems Science and Engineering, Vol.48, No.4, pp. 1075-1081, 2024, DOI:10.32604/csse.2024.054179

Abstract This article has no abstract. More >