Yin Ni¹, Wu Zeng^2,*, Peng Xia¹, Guang Stanley Yang³, Ruochen Tan⁴

CMC-Computers, Materials & Continua, Vol.79, No.3, pp. 5295-5312, 2024, DOI:10.32604/cmc.2024.049911

Abstract Deepfake-generated fake faces, commonly utilized in identity-related activities such as political propaganda, celebrity impersonations, evidence forgery, and familiar fraud, pose new societal threats. Although current deepfake generators strive for high realism in visual effects, they do not replicate biometric signals indicative of cardiac activity. Addressing this gap, many researchers have developed detection methods focusing on biometric characteristics. These methods utilize classification networks to analyze both temporal and spectral domain features of the remote photoplethysmography (rPPG) signal, resulting in high detection accuracy. However, in the spectral analysis, existing approaches often only consider the power spectral density… More >

Hong Pang¹, Ao Lu¹, Ming Xiong¹, Chen Chen¹, Xian Cao¹, Xiong Xu^2,3,*, Jing Wang¹

FDMP-Fluid Dynamics & Materials Processing, Vol.20, No.5, pp. 1063-1074, 2024, DOI:10.32604/fdmp.2023.044000

Abstract Conventional repairing methods for asphalt pavement have some inconveniences, such as insufficient strength, and are typically time-consuming. To address these issues, this study proposes a new technological method to design and prepare a high-performance assembled asphalt concrete block for fast repair of the potholes. A series of composite modified asphalt binders with 10% crumb rubber (CR) and different dosages (0%, 1%, 3%, 5%) of polyurethane (PU) are examined to determine the optimized binder. Subsequently, the corresponding asphalt mixtures are prepared for further comparison and assessment of engineering properties, such as moisture-induced damage, high-temperature deformation, and More >

Samaneh Kouzegaran^*, Kourosh Shahraki^†, Ali Makateb^‡, Farkhondeh Shahri^§, Negin Hatami^¶, Vahid Behnod^#, Amir Saber Tanha^**

Oncology Research, Vol.25, No.4, pp. 471-478, 2017, DOI:10.3727/096504016X14721217330657

Abstract In this study, expression of FasL and Ki-67 messenger RNA (FasL and Ki-67 mRNA) in human retinoblastoma (HRB) was examined by the immunohistochemistry method and quantitative real-time PCR. Positive expression of Ki-67 in tumor cells was detected in 16 of 30 patients (53.33%), and only 9 (30%) of the tissues from patients with retinoblastoma showed positive staining for FasL. Our results revealed that FasL expression was significantly higher in tumor tissue with invasion compared with the noninvasion form (p = 0.033). Ki-67 expression was markedly increased in tumor tissues with invasion compared with the noninvasion group… More >

Vivian Adamski^*, Anne Dorothée Schmitt^*, Charlotte Flüh^*, Michael Synowitz^*, Kirsten Hattermann^†1, Janka Held-Feindt^*1

Oncology Research, Vol.25, No.3, pp. 341-353, 2017, DOI:10.3727/096504016X14737243054982

Abstract Gliomas are the most common primary brain tumors. The most malignant form, the glioblastoma multiforme (GBM; WHO IV), is characterized by an invasive phenotype, which enables the tumor cells to infiltrate into adjacent brain tissue. When investigating GBM migration and invasion properties in vitro, in most cases GBM cell lines were analyzed. Comprehensive investigations focusing on progression-dependent characteristics of migration processes using fresh human glioma samples of different malignancy grades do not exist. Thus, we isolated fast-migrating tumor cells from fresh human glioma samples of different malignancy grades (astrocytomas WHO grade II, grade III, GBM,… More >

Sanae Haga^*, Akira Kanno^†, Takeaki Ozawa^‡, Naoki Morita^§, Mami Asano^*¶,¶ and Michitaka Ozaki^*¶

Oncology Research, Vol.26, No.3, pp. 503-513, 2018, DOI:10.3727/096504017X15005102445191

Abstract Liver injury is often observed in various pathological conditions including posthepatectomy state and cancer chemotherapy. It occurs mainly as a consequence of the combined necrotic and apoptotic types of cell death. In order to study liver/hepatocyte injury by the necrotic type of cell death, we studied signal-regulated necrosis (necroptosis) by developing a new optic probe for detecting receptor-interacting protein kinase 1 (RIP)/RIP3 binding, an essential process for necroptosis induction. In the mouse hepatocyte cell line, TIB-73 cells, TNF-a/cycloheximide (T/C) induced RIP1/3 binding only when caspase activity was suppressed by the caspase-specific inhibitor z-VAD-fmk (zVAD). T/C/zVAD-induced… More >

Yutong Tian¹, Minghan Gao², Qiang Gao^1,*, Xiao-Hong Peng³

Intelligent Automation & Soft Computing, Vol.39, No.2, pp. 175-188, 2024, DOI:10.32604/iasc.2024.042762

Abstract How to find an effective trading policy is still an open question mainly due to the nonlinear and non-stationary dynamics in a financial market. Deep reinforcement learning, which has recently been used to develop trading strategies by automatically extracting complex features from a large amount of data, is struggling to deal with fast-changing markets due to sample inefficiency. This paper applies the meta-reinforcement learning method to tackle the trading challenges faced by conventional reinforcement learning (RL) approaches in non-stationary markets for the first time. In our work, the history trading data is divided into multiple… More >

Chuandong Qin^1,2, Yu Cao^1,*, Liqun Meng¹

CMC-Computers, Materials & Continua, Vol.79, No.2, pp. 1975-1994, 2024, DOI:10.32604/cmc.2024.049228

Abstract Brain tumors come in various types, each with distinct characteristics and treatment approaches, making manual detection a time-consuming and potentially ambiguous process. Brain tumor detection is a valuable tool for gaining a deeper understanding of tumors and improving treatment outcomes. Machine learning models have become key players in automating brain tumor detection. Gradient descent methods are the mainstream algorithms for solving machine learning models. In this paper, we propose a novel distributed proximal stochastic gradient descent approach to solve the L-Smooth Support Vector Machine (SVM) classifier for brain tumor detection. Firstly, the smooth hinge loss is… More >

J. Sheril Angel¹, A. Diana Andrushia^1,*, T. Mary Neebha¹, Oussama Accouche², Louai Saker², N. Anand³

CMC-Computers, Materials & Continua, Vol.79, No.2, pp. 2427-2448, 2024, DOI:10.32604/cmc.2024.047326

Abstract Facial emotion recognition (FER) has become a focal point of research due to its widespread applications, ranging from human-computer interaction to affective computing. While traditional FER techniques have relied on handcrafted features and classification models trained on image or video datasets, recent strides in artificial intelligence and deep learning (DL) have ushered in more sophisticated approaches. The research aims to develop a FER system using a Faster Region Convolutional Neural Network (FRCNN) and design a specialized FRCNN architecture tailored for facial emotion recognition, leveraging its ability to capture spatial hierarchies within localized regions of facial… More >

Yiwei Liu¹, Yingnan Zhao^1,*, Yi Chen¹, Zheng Hu¹, Min Xia²

CMC-Computers, Materials & Continua, Vol.79, No.1, pp. 909-926, 2024, DOI:10.32604/cmc.2024.047901

Abstract Scene text detection is an important task in computer vision. In this paper, we present YOLOv5 Scene Text (YOLOv5ST), an optimized architecture based on YOLOv5 v6.0 tailored for fast scene text detection. Our primary goal is to enhance inference speed without sacrificing significant detection accuracy, thereby enabling robust performance on resource-constrained devices like drones, closed-circuit television cameras, and other embedded systems. To achieve this, we propose key modifications to the network architecture to lighten the original backbone and improve feature aggregation, including replacing standard convolution with depth-wise convolution, adopting the C2 sequence module in place More >

ZONGQIAN WANG, HAIWEI YANG, JIAN XING, ZHI LIU^*

Journal of Polymer Materials, Vol.36, No.2, pp. 149-159, 2019, DOI:10.32381/JPM.2019.36.02.4

Abstract Colored silk fibroin (SF) film can change the proportion of transmitted light composition and therefore shows potential application in optoelectronics area. However, few methods are reported for the preparation of colored SF film with good color fastness. Herein, colored SF film was prepared by coupling modification dyeing (CM-dyeing) of SF tyrosine residues in solution. SF film shows excellent color fastness due to the formation of the azo covalent bond formed by electrophilic substitution reaction between SF tyrosine residues and aniline diazonium salt. Furthermore, compared with the undyed film, the dyed SF film is effectively preserved More >