Honglin Wang¹, Yangyang Zhang^2,*, Cheng Zhu³

CMC-Computers, Materials & Continua, Vol.82, No.2, pp. 3399-3417, 2025, DOI:10.32604/cmc.2024.058932 - 17 February 2025

Abstract Forest fires pose a serious threat to ecological balance, air quality, and the safety of both humans and wildlife. This paper presents an improved model based on You Only Look Once version 5 (YOLOv5), named YOLO Lightweight Fire Detector (YOLO-LFD), to address the limitations of traditional sensor-based fire detection methods in terms of real-time performance and accuracy. The proposed model is designed to enhance inference speed while maintaining high detection accuracy on resource-constrained devices such as drones and embedded systems. Firstly, we introduce Depthwise Separable Convolutions (DSConv) to reduce the complexity of the feature extraction… More >

Feifei Yu¹, Yongxian Huang^2,*, Guoyan Chen¹, Xiaoqing Yang², Canyi Du^2,*, Yongkang Gong²

CMC-Computers, Materials & Continua, Vol.82, No.1, pp. 843-862, 2025, DOI:10.32604/cmc.2024.058051 - 03 January 2025

Abstract To accurately diagnose misfire faults in automotive engines, we propose a Channel Attention Convolutional Model, specifically the Squeeze-and-Excitation Networks (SENET), for classifying engine vibration signals and precisely pinpointing misfire faults. In the experiment, we established a total of 11 distinct states, encompassing the engine’s normal state, single-cylinder misfire faults, and dual-cylinder misfire faults for different cylinders. Data collection was facilitated by a highly sensitive acceleration signal collector with a high sampling rate of 20,840 Hz. The collected data were methodically divided into training and testing sets based on different experimental groups to ensure generalization and… More >

Diana Abi-Nader¹, Hassan Harb², Ali Jaber¹, Ali Mansour³, Christophe Osswald³, Nour Mostafa^2,*, Chamseddine Zaki²

CMES-Computer Modeling in Engineering & Sciences, Vol.142, No.1, pp. 279-298, 2025, DOI:10.32604/cmes.2024.056816 - 17 December 2024

Abstract Security and safety remain paramount concerns for both governments and individuals worldwide. In today’s context, the frequency of crimes and terrorist attacks is alarmingly increasing, becoming increasingly intolerable to society. Consequently, there is a pressing need for swift identification of potential threats to preemptively alert law enforcement and security forces, thereby preventing potential attacks or violent incidents. Recent advancements in big data analytics and deep learning have significantly enhanced the capabilities of computer vision in object detection, particularly in identifying firearms. This paper introduces a novel automatic firearm detection surveillance system, utilizing a one-stage detection… More >

Arkan Kh Shakr Sabonchi^*

Journal of Information Hiding and Privacy Protection, Vol.6, pp. 21-45, 2024, DOI:10.32604/jihpp.2024.058954 - 31 December 2024

Abstract Substitution boxes (S-boxes) are key components of symmetrical cryptosystems, acting as nonlinear substitution functions that hide the relationship between the encrypted text and input key. This confusion mechanism is vital for cryptographic security because it prevents attackers from intercepting the secret key by analyzing the encrypted text. Therefore, the S-box design is essential for the robustness of cryptographic systems, especially for the data encryption standard (DES) and advanced encryption standard (AES). This study focuses on the application of the firefly algorithm (FA) and metaheuristic lion optimization algorithm (LOA), thereby proposing a hybrid approach called the… More >

Hebat-Allah S. Tohamy^*

Journal of Renewable Materials, Vol.12, No.12, pp. 1963-1983, 2024, DOI:10.32604/jrm.2024.054977 - 20 December 2024

Abstract Fire retardant CNTs/WPP/Gel composite papers were fabricated by incorporating bio-based carbon nanotubes (CNTs) recycled from mature beech pinewood sawdust (MB) and cellulosic waste printed paper (WPP) into a gelatin solution (Gel) and allowing the mixture to dry at room temperature. The CNTs within the WPP matrix formed a network, enhancing the mechanical and thermal properties of the resulting CNTs paper sheet. In comparison to pure WPP/Gel, CNTs/WPP/Gel exhibited superior flexibility, mechanical toughness, and notable flame retardancy characteristics. This study provides a unique and practical method for producing flame-retardant CNTs/WPP/Gel sheets, suitable for diverse industrial applications,… More > Graphic Abstract

Trong Thua Huynh^*, Hoang Thanh Nguyen, Du Thang Phu

CMC-Computers, Materials & Continua, Vol.81, No.2, pp. 2281-2298, 2024, DOI:10.32604/cmc.2024.057954 - 18 November 2024

Abstract In recent years, early detection and warning of fires have posed a significant challenge to environmental protection and human safety. Deep learning models such as Faster R-CNN (Faster Region based Convolutional Neural Network), YOLO (You Only Look Once), and their variants have demonstrated superiority in quickly detecting objects from images and videos, creating new opportunities to enhance automatic and efficient fire detection. The YOLO model, especially newer versions like YOLOv10, stands out for its fast processing capability, making it suitable for low-latency applications. However, when applied to real-world datasets, the accuracy of fire prediction is… More >

Yeye Liu¹, Leilei Zhang^1,*, Ruonan Zhang¹, Siqi Shao¹, Lina Sun¹, Xinyi Wan¹, Tiantian Wang¹

The International Conference on Computational & Experimental Engineering and Sciences, Vol.30, No.2, pp. 1-1, 2024, DOI:10.32604/icces.2024.012576

Abstract Superior thermal insulating and fire-retardant ceramic membranes are urgently demanded in the aerospace, construction and chemical engineering industries. However, the generic characteristics of ceramic membranes, such as brittleness, structural collapse and crystallization-induced pulverization behavior, present a great plague to their practical applications. Herein, we report a highly flexible, mechanically stable, fire retardant and high-temperature-resistant ceramic membrane based on the interlocked Si₃N₄ nanowires formed by the precursor pyrolysis method. The Si₃N₄ nanowires membrane (SNM) has excellent high temperature resistance under alcohol lamp and butane spray lance. The thermal insulation with a thermal conductivity as low as 0.056… More >

Lilik Astari^1,2,*, Benoit Belleville¹, Kenji Umemura³, Alex Filkov⁴, Barbara Ozarska¹, Robert H. Crawford⁵

Journal of Renewable Materials, Vol.12, No.10, pp. 1729-1756, 2024, DOI:10.32604/jrm.2024.054786 - 23 October 2024

Abstract The demand for particleboard is increasing along with economic and population growth. However, two major barriers to the manufacture of particleboard are a shortage of raw materials (woodchips) and the emission of formaldehyde from conventional adhesives. Agricultural by-products such as corn stalks contain an abundance of renewable lignocellulosic fiber. This study evaluates the effect of citric acid as a natural adhesive and fire retardant addition on the physical, mechanical, and fire retardancy properties of particleboards fabricated from corn stalks. A cost-effective and inorganic salt, calcium carbonate, was tested to enhance the fire retardancy. Ammonium dihydrogen… More > Graphic Abstract

Arkan Kh Shakr Sabonchi^*

Journal on Artificial Intelligence, Vol.6, pp. 261-282, 2024, DOI:10.32604/jai.2024.056552 - 18 October 2024

Abstract The phenomenal increase in device connectivity is making the signaling and resource-based operational integrity of networks at the node level increasingly prone to distributed denial of service (DDoS) attacks. The current growth rate in the number of Internet of Things (IoT) attacks executed at the time of exchanging data over the Internet represents massive security hazards to IoT devices. In this regard, the present study proposes a new hybrid optimization technique that combines the firefly optimization algorithm with global searches for use in attack detection on IoT devices. We preprocessed two datasets, CICIDS and UNSW-NB15,… More >

Abdelwahed Motwakel^1,*, Badriyya B. Al-onazi², Jaber S. Alzahrani³, Ayman Yafoz⁴, Mahmoud Othman⁵, Abu Sarwar Zamani¹, Ishfaq Yaseen¹, Amgad Atta Abdelmageed¹

Computer Systems Science and Engineering, Vol.48, No.5, pp. 1387-1403, 2024, DOI:10.32604/csse.2023.033902 - 13 September 2024

Abstract Handwritten character recognition becomes one of the challenging research matters. More studies were presented for recognizing letters of various languages. The availability of Arabic handwritten characters databases was confined. Almost a quarter of a billion people worldwide write and speak Arabic. More historical books and files indicate a vital data set for many Arab nations written in Arabic. Recently, Arabic handwritten character recognition (AHCR) has grabbed the attention and has become a difficult topic for pattern recognition and computer vision (CV). Therefore, this study develops fireworks optimization with the deep learning-based AHCR (FWODL-AHCR) technique. The… More >