Mariam Ishtiaq^1,2, Jong-Un Won^1,2,*

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 5343-5361, 2025, DOI:10.32604/cmc.2025.061466 - 06 March 2025

Abstract Fire detection has held stringent importance in computer vision for over half a century. The development of early fire detection strategies is pivotal to the realization of safe and smart cities, inhabitable in the future. However, the development of optimal fire and smoke detection models is hindered by limitations like publicly available datasets, lack of diversity, and class imbalance. In this work, we explore the possible ways forward to overcome these challenges posed by available datasets. We study the impact of a class-balanced dataset to improve the fire detection capability of state-of-the-art (SOTA) vision-based models and propose… More >

Tawfeeq Shawly¹, Ahmed A. Alsheikhy^2,*, Yahia Said³, Shaaban M. Shaaban³, Husam Lahza⁴, Aws I. AbuEid⁵, Abdulrahman Alzahrani⁶

CMES-Computer Modeling in Engineering & Sciences, Vol.142, No.3, pp. 3181-3212, 2025, DOI:10.32604/cmes.2025.061608 - 03 March 2025

Abstract Email communication plays a crucial role in both personal and professional contexts; however, it is frequently compromised by the ongoing challenge of spam, which detracts from productivity and introduces considerable security risks. Current spam detection techniques often struggle to keep pace with the evolving tactics employed by spammers, resulting in user dissatisfaction and potential data breaches. To address this issue, we introduce the Divide and Conquer-Generative Adversarial Network Squeeze and Excitation-Based Framework (DaC-GANSAEBF), an innovative deep-learning model designed to identify spam emails. This framework incorporates cutting-edge technologies, such as Generative Adversarial Networks (GAN), Squeeze and… More >

Ziji Xiao¹, Kaibo Yang¹, Mingen Zhong^1,*, Kang Fan², Jiawei Tan², Zhiying Deng¹

CMC-Computers, Materials & Continua, Vol.82, No.2, pp. 2665-2686, 2025, DOI:10.32604/cmc.2024.058345 - 17 February 2025

Abstract The polyp dataset involves the confidentiality of medical records, so it might be difficult to obtain datasets with accurate annotations. This problem can be effectively solved by expanding the polyp data set with algorithms. The traditional polyp dataset expansion scheme usually requires the use of two models or traditional visual methods. These methods are both tedious and difficult to provide new polyp features for training data. Therefore, our research aims to efficiently generate high-quality polyp samples, so as to effectively expand the polyp dataset. In this study, we first added the attention mechanism to the… More >

Sarvenaz Sadat Khatami¹, Mehrdad Shoeibi², Anita Ershadi Oskouei³, Diego Martín^4,*, Maral Keramat Dashliboroun⁵

CMC-Computers, Materials & Continua, Vol.82, No.1, pp. 881-911, 2025, DOI:10.32604/cmc.2024.059999 - 03 January 2025

Abstract The Internet of Things (IoT) is integral to modern infrastructure, enabling connectivity among a wide range of devices from home automation to industrial control systems. With the exponential increase in data generated by these interconnected devices, robust anomaly detection mechanisms are essential. Anomaly detection in this dynamic environment necessitates methods that can accurately distinguish between normal and anomalous behavior by learning intricate patterns. This paper presents a novel approach utilizing generative adversarial networks (GANs) for anomaly detection in IoT systems. However, optimizing GANs involves tuning hyper-parameters such as learning rate, batch size, and optimization algorithms,… More >

Peng Li, Yanrui Wei, Lili Yin^*

CMC-Computers, Materials & Continua, Vol.82, No.1, pp. 609-625, 2025, DOI:10.32604/cmc.2024.056651 - 03 January 2025

Abstract Stock price prediction is a typical complex time series prediction problem characterized by dynamics, nonlinearity, and complexity. This paper introduces a generative adversarial network model that incorporates an attention mechanism (GAN-LSTM-Attention) to improve the accuracy of stock price prediction. Firstly, the generator of this model combines the Long and Short-Term Memory Network (LSTM), the Attention Mechanism and, the Fully-Connected Layer, focusing on generating the predicted stock price. The discriminator combines the Convolutional Neural Network (CNN) and the Fully-Connected Layer to discriminate between real stock prices and generated stock prices. Secondly, to evaluate the practical application… More >

Sabina Rakhmetulayeva^1,*, Zhandos Zhanabekov², Aigerim Bolshibayeva³

CMC-Computers, Materials & Continua, Vol.81, No.3, pp. 4503-4523, 2024, DOI:10.32604/cmc.2024.057974 - 19 December 2024

Abstract The applications of machine learning (ML) in the medical domain are often hindered by the limited availability of high-quality data. To address this challenge, we explore the synthetic generation of echocardiography images (echoCG) using state-of-the-art generative models. We conduct a comprehensive evaluation of three prominent methods: Cycle-consistent generative adversarial network (CycleGAN), Contrastive Unpaired Translation (CUT), and Stable Diffusion 1.5 with Low-Rank Adaptation (LoRA). Our research presents the data generation methodology, image samples, and evaluation strategy, followed by an extensive user study involving licensed cardiologists and surgeons who assess the perceived quality and medical soundness of More > Graphic Abstract

Xirui Yang, Chen Zhang^*

CMC-Computers, Materials & Continua, Vol.81, No.3, pp. 3781-3804, 2024, DOI:10.32604/cmc.2024.057131 - 19 December 2024

Abstract User location trajectory refers to the sequence of geographic location information that records the user’s movement or stay within a period of time and is usually used in mobile crowd sensing networks, in which the user participates in the sensing task, the process of sensing data collection faces the problem of privacy leakage. To address the privacy leakage issue of trajectory data during uploading, publishing, and sharing when users use location services on mobile smart group sensing terminal devices, this paper proposes a privacy protection method based on generative adversarial networks and attention mechanisms (BiLS-A-GAN).… More >

Monirah Al-Ajlan^*, Mourad Ykhlef

CMC-Computers, Materials & Continua, Vol.81, No.2, pp. 2053-2076, 2024, DOI:10.32604/cmc.2024.055891 - 18 November 2024

Abstract The ever-growing network traffic threat landscape necessitates adopting accurate and robust intrusion detection systems (IDSs). IDSs have become a research hotspot and have seen remarkable performance improvements. Generative adversarial networks (GANs) have also garnered increasing research interest recently due to their remarkable ability to generate data. This paper investigates the application of (GANs) in (IDS) and explores their current use within this research field. We delve into the adoption of GANs within signature-based, anomaly-based, and hybrid IDSs, focusing on their objectives, methodologies, and advantages. Overall, GANs have been widely employed, mainly focused on solving the More >

Qingrong Zeng, Xiaochen Liu, Xuefeng Zhu^*, Xiangkui Zhang, Ping Hu

CMES-Computer Modeling in Engineering & Sciences, Vol.141, No.3, pp. 2065-2085, 2024, DOI:10.32604/cmes.2024.052620 - 31 October 2024

Abstract Traditional topology optimization methods often suffer from the “dimension curse” problem, wherein the computation time increases exponentially with the degrees of freedom in the background grid. Overcoming this challenge, we introduce a real-time topology optimization approach leveraging Conditional Generative Adversarial Networks with Gradient Penalty (CGAN-GP). This innovative method allows for nearly instantaneous prediction of optimized structures. Given a specific boundary condition, the network can produce a unique optimized structure in a one-to-one manner. The process begins by establishing a dataset using simulation data generated through the Solid Isotropic Material with Penalization (SIMP) method. Subsequently, we More >

Laviza Falak Naz¹, Rohail Qamar^2,*, Raheela Asif¹, Muhammad Imran², Saad Ahmed³

Intelligent Automation & Soft Computing, Vol.39, No.5, pp. 855-887, 2024, DOI:10.32604/iasc.2024.055074 - 31 October 2024

Abstract Domain shift is when the data used in training does not match the ones it will be applied to later on under similar conditions. Domain shift will reduce accuracy in results. To prevent this, domain adaptation is done, which adapts the pre-trained model to the target domain. In real scenarios, the availability of labels for target data is rare thus resulting in unsupervised domain adaptation. Herein, we propose an innovative approach where source-free domain adaptation models and Generative Adversarial Networks (GANs) are integrated to improve the performance of computer vision or robotic vision-based systems in… More >