Jianxin Feng^1,2,*, Xiaoyao Liu^1,2

CMC-Computers, Materials & Continua, Vol.83, No.2, pp. 2087-2107, 2025, DOI:10.32604/cmc.2025.060252 - 16 April 2025

Abstract As a form of discrete representation learning, Vector Quantized Variational Autoencoders (VQ-VAE) have increasingly been applied to generative and multimodal tasks due to their ease of embedding and representative capacity. However, existing VQ-VAEs often perform quantization in the spatial domain, ignoring global structural information and potentially suffering from codebook collapse and information coupling issues. This paper proposes a frequency quantized variational autoencoder (FQ-VAE) to address these issues. The proposed method transforms image features into linear combinations in the frequency domain using a 2D fast Fourier transform (2D-FFT) and performs adaptive quantization on these frequency components… More >

Stellar Choi¹, HeeAe Ko², KyungRok Bae³, HyunSook Lee², HaeJong Joo⁴, Woong Choi^5,*

CMC-Computers, Materials & Continua, Vol.83, No.1, pp. 335-355, 2025, DOI:10.32604/cmc.2025.061243 - 26 March 2025

Abstract Previous research utilizing Cartoon Generative Adversarial Network (CartoonGAN) has encountered limitations in managing intricate outlines and accurately representing lighting effects, particularly in complex scenes requiring detailed shading and contrast. This paper presents a novel Enhanced Pixel Integration (EPI) technique designed to improve the visual quality of images generated by CartoonGAN. Rather than modifying the core model, the EPI approach employs post-processing adjustments that enhance images without significant computational overhead. In this method, images produced by CartoonGAN are converted from Red-Green-Blue (RGB) to Hue-Saturation-Value (HSV) format, allowing for precise adjustments in hue, saturation, and brightness, thereby… More >

TINGTING LIU^#, XIANGRUI KONG^#, JIANSHE WEI^*

BIOCELL, Vol.48, No.12, pp. 1735-1749, 2024, DOI:10.32604/biocell.2024.056272 - 30 December 2024

Abstract Type 2 diabetes mellitus (T2DM) is a chronic metabolic disorder characterized by persistent hyperglycemia. In recent times, an elevated risk of Parkinson’s disease (PD) development among individuals with T2DM has become evident. However, the molecular mechanisms that underpin the interplay between T2DM and the pathogenesis of PD remain to be elucidated. Nevertheless, recent epidemiological studies have underscored several shared molecular pathways that are crucial for normal cellular function and are also associated with the progression and etiology of both T2DM and PD. This review encapsulates some of the shared pathophysiological mechanisms, including genetic risk factors, More >

Wenshu Zhuang^1,#, Guangyang Jin^1,#, Yiting Zou¹, Zhong Bian¹, Dong Xie¹, Shuwei Zhang¹, Hadi Yeilaghi¹, Liangliang Yu³, Muiyun Wong⁴, Xiaolei Fan^1,2, Dongsheng Zhao^1,2, Qiaoquan Liu^1,2, Lin Zhang^1,2,*

Phyton-International Journal of Experimental Botany, Vol.93, No.11, pp. 2737-2754, 2024, DOI:10.32604/phyton.2024.054649 - 30 November 2024

Abstract Panicle size is one of the important factors in shaping yield potential in rice, but it shows plasticity in different environments, which leads to yield fluctuation. Variations in panicle size among varieties are largely determined by quantitative trait loci (QTLs). QTL analysis could elaborate on the environmental impact on trait plasticity using nearly isogenic lines (NILs) of different QTLs. Two QTLs, ipa1-2D and qPL6 are identified to have pleiotropic contributions to panicle size and plant architecture, but their responses to different growth conditions are still unclear. In this study, we developed NILs harboring a single locus… More >

Xi Li^1,2, Yuxin Li², Zhenhua Xiao^3,*, Zhenghua Huang¹, Lianying Zou¹

CMC-Computers, Materials & Continua, Vol.81, No.2, pp. 3325-3349, 2024, DOI:10.32604/cmc.2024.056464 - 18 November 2024

Abstract Human pose estimation is a critical research area in the field of computer vision, playing a significant role in applications such as human-computer interaction, behavior analysis, and action recognition. In this paper, we propose a U-shaped keypoint detection network (DAUNet) based on an improved ResNet subsampling structure and spatial grouping mechanism. This network addresses key challenges in traditional methods, such as information loss, large network redundancy, and insufficient sensitivity to low-resolution features. DAUNet is composed of three main components. First, we introduce an improved BottleNeck block that employs partial convolution and strip pooling to reduce… More >

WEITAO ZHENG¹, DONG JIANG², SONGEN CHEN¹, MEILING WU¹, BAOQI YAN², JIAHUI ZHAI², YUNQIANG SHI², BIN XIE¹, XINGWANG XIE², KANGHONG HU^1,*, WENXUE MA^3,*

Oncology Research, Vol.32, No.12, pp. 1837-1850, 2024, DOI:10.32604/or.2024.056565 - 13 November 2024

Abstract Objectives: The Kirsten rat sarcoma virus (KRAS) G12D oncogenic mutation poses a significant challenge in treating solid tumors due to the lack of specific and effective therapeutic interventions. This study aims to explore innovative approaches in T cell receptor (TCR) engineering and characterization to target the KRAS G12D_7-16 mutation, providing potential strategies for overcoming this therapeutic challenge. Methods: In this innovative study, we engineered and characterized two T cell receptors (TCRs), KDA11-01 and KDA11-02 with high affinity for the KRAS G12D_7-16 mutation. These TCRs were isolated from tumor-infiltrating lymphocytes (TILs) derived from tumor tissues of patients More >

Mohammed A. Mahdi¹, Shahanawaj Ahamad², Sawsan A. Saad³, Alaa Dafhalla³, Alawi Alqushaibi⁴, Rizwan Qureshi^5,*

CMES-Computer Modeling in Engineering & Sciences, Vol.141, No.3, pp. 2351-2373, 2024, DOI:10.32604/cmes.2024.055723 - 31 October 2024

Abstract The segmentation of head and neck (H&N) tumors in dual Positron Emission Tomography/Computed Tomography (PET/CT) imaging is a critical task in medical imaging, providing essential information for diagnosis, treatment planning, and outcome prediction. Motivated by the need for more accurate and robust segmentation methods, this study addresses key research gaps in the application of deep learning techniques to multimodal medical images. Specifically, it investigates the limitations of existing 2D and 3D models in capturing complex tumor structures and proposes an innovative 2.5D UNet Transformer model as a solution. The primary research questions guiding this study… More >

Oncology Research Editorial Office

Oncology Research, Vol.32, No.11, pp. 1815-1815, 2024, DOI:10.32604/or.2024.056890 - 16 October 2024

Abstract This article has no abstract. More >

Zhaojie Sun¹, Linlin Xing^1,*, Longbo Zhang¹, Hongzhen Cai², Maozu Guo³

CMC-Computers, Materials & Continua, Vol.80, No.3, pp. 4325-4340, 2024, DOI:10.32604/cmc.2024.053588 - 12 September 2024

Abstract Extracting valuable information from biomedical texts is one of the current research hotspots of concern to a wide range of scholars. The biomedical corpus contains numerous complex long sentences and overlapping relational triples, making most generalized domain joint modeling methods difficult to apply effectively in this field. For a complex semantic environment in biomedical texts, in this paper, we propose a novel perspective to perform joint entity and relation extraction; existing studies divide the relation triples into several steps or modules. However, the three elements in the relation triples are interdependent and inseparable, so we… More >

Bingrui Ju^1,2, Wenxiang Sun², Wenzhen Qu^1,2,*, Yan Gu²

CMES-Computer Modeling in Engineering & Sciences, Vol.141, No.1, pp. 267-280, 2024, DOI:10.32604/cmes.2024.052159 - 20 August 2024

Abstract In this study, we propose an efficient numerical framework to attain the solution of the extended Fisher-Kolmogorov (EFK) problem. The temporal derivative in the EFK equation is approximated by utilizing the Crank-Nicolson scheme. Following temporal discretization, the generalized finite difference method (GFDM) with supplementary nodes is utilized to address the nonlinear boundary value problems at each time node. These supplementary nodes are distributed along the boundary to match the number of boundary nodes. By incorporating supplementary nodes, the resulting nonlinear algebraic equations can effectively satisfy the governing equation and boundary conditions of the EFK equation. More >