Sarfaraz Natha^1,2,*, Fareed A. Jokhio¹, Mehwish Laghari¹, Mohammad Siraj^3,*, Saif A. Alsaif³, Usman Ashraf⁴, Asghar Ali⁵

CMC-Computers, Materials & Continua, Vol.81, No.3, pp. 3707-3729, 2024, DOI:10.32604/cmc.2024.057684 - 19 December 2024

Abstract Surveillance cameras have been widely used for monitoring in both private and public sectors as a security measure. Close Circuits Television (CCTV) Cameras are used to surveillance and monitor the normal and anomalous incidents. Real-world anomaly detection is a significant challenge due to its complex and diverse nature. It is difficult to manually analyze because vast amounts of video data have been generated through surveillance systems, and the need for automated techniques has been raised to enhance detection accuracy. This paper proposes a novel deep-stacked ensemble model integrated with a data augmentation approach called Stack… More >

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 >

Guojun Chen^*, Tao Cui, Yongjie Hou, Huihui Li

CMC-Computers, Materials & Continua, Vol.81, No.3, pp. 3969-3987, 2024, DOI:10.32604/cmc.2024.056093 - 19 December 2024

Abstract Existing glass segmentation networks have high computational complexity and large memory occupation, leading to high hardware requirements and time overheads for model inference, which is not conducive to efficiency-seeking real-time tasks such as autonomous driving. The inefficiency of the models is mainly due to employing homogeneous modules to process features of different layers. These modules require computationally intensive convolutions and weight calculation branches with numerous parameters to accommodate the differences in information across layers. We propose an efficient glass segmentation network (EGSNet) based on multi-level heterogeneous architecture and boundary awareness to balance the model performance… More >

Umapathi Krishnamoorthy^1,*, Shanmugam Jagan², Mohammed Zakariah³, Abdulaziz S. Almazyad^4,*, K. Gurunathan⁵

CMC-Computers, Materials & Continua, Vol.81, No.3, pp. 3903-3926, 2024, DOI:10.32604/cmc.2024.055910 - 19 December 2024

Abstract Brain signal analysis from electroencephalogram (EEG) recordings is the gold standard for diagnosing various neural disorders especially epileptic seizure. Seizure signals are highly chaotic compared to normal brain signals and thus can be identified from EEG recordings. In the current seizure detection and classification landscape, most models primarily focus on binary classification—distinguishing between seizure and non-seizure states. While effective for basic detection, these models fail to address the nuanced stages of seizures and the intervals between them. Accurate identification of per-seizure or interictal stages and the timing between seizures is crucial for an effective seizure… More >

Haizhen Wang^1,2,*, Na Jia^1,2, Yang He¹, Pan Tan^1,2

CMC-Computers, Materials & Continua, Vol.81, No.3, pp. 3825-3851, 2024, DOI:10.32604/cmc.2024.055497 - 19 December 2024

Abstract As the popularity and dependence on the Internet increase, DDoS (distributed denial of service) attacks seriously threaten network security. By accurately distinguishing between different types of DDoS attacks, targeted defense strategies can be formulated, significantly improving network protection efficiency. DDoS attacks usually manifest as an abnormal increase in network traffic, and their diverse types of attacks, along with a severe data imbalance, make it difficult for traditional classification methods to effectively identify a small number of attack types. To solve this problem, this paper proposes a DDoS recognition method CVWGG (Conditional Variational Autoencoder-Wasserstein Generative Adversarial… More >

J. L. Rodríguez-Muñoz^1,*, J. S. Pacheco-Cedeño^1,*, J. F. Ituna-Yudonago², J. J. Ramírez-Minguela³, I. J. González-Hernández⁴

Frontiers in Heat and Mass Transfer, Vol.22, No.6, pp. 1719-1741, 2024, DOI:10.32604/fhmt.2024.057924 - 19 December 2024

Abstract In conventional absorption refrigeration systems (ARS), the heat from the condenser is usually rejected by the environment in place to be used in the system, so recuperating this is a good alternative to enhance the system’s performance. For instance, in this paper, an alternative ARS in which LiBr/Water is used as a refrigerant mixture, where part of condensing heat is recovered via the solution heat recovery generator absorption cycle (HR-ARS) was energy and exergy evaluated. The influence of generator, condenser and evaporator temperatures, as well as the efficiency of the solution heat exchanger on the coefficient of… More > Graphic Abstract

Tsung-Han Li^1,*, Chia-Ming Fan¹, Po-Wei Li²

The International Conference on Computational & Experimental Engineering and Sciences, Vol.32, No.1, pp. 1-1, 2024, DOI:10.32604/icces.2024.012120

Abstract The generalized finite difference method (GFDM), which cooperated with the fictitious-nodes technique, is proposed in this study to accurately analyze three-dimensional boundary value problems, governed by high-order partial differential equations. Some physical applications can be mathematically described by boundary value problems governed by high-order partial differential equations, but it is non-trivial to analyze the high-order partial differential equations by adopting conventional mesh-based numerical schemes, such as finite difference method, the finite element method, etc. In this study, the GFDM, a localized meshless method, is proposed to accurately and efficiently solve boundary value problems governed by… More >

Fengchao Wang^1,*

The International Conference on Computational & Experimental Engineering and Sciences, Vol.32, No.1, pp. 1-1, 2024, DOI:10.32604/icces.2024.011068

Abstract Gas permeation through nanopores is a long-standing research interest because of its importance in fundamental science and many technologies. The free molecular flow is conventionally described by Knudsen theory, under the diffuse reflection assumption. Recent experiments reported ballistic molecular transport of gases, which urges for the development of theoretical tools to address the predominant specular reflections on atomically smooth surfaces. Here we develop a generalized Knudsen theory, which is applicable to various boundary conditions covering from the extreme specular reflection to the complete diffuse reflection [1]. Our model overcomes the limitation of Smoluchowski model, which More >

Taku Itoh^1,*

The International Conference on Computational & Experimental Engineering and Sciences, Vol.31, No.4, pp. 1-1, 2024, DOI:10.32604/icces.2024.012260

Abstract In meshless methods, although elements constructing an analysis domain are not required, the domain should be represented in some way, instead. A scalar field g(x), that contains the analysis domain, is sometimes employed, and the boundary of analysis domain is represented as an implicit surface, g(x) = 0. In this study, we consider generating an implicit surface from scattered points on the surface of an object. The scattered points are obtained by a three-dimensional scanning device. To generate g(x), field values f_ijk on N3 uniform grid points x_ijk are required. Although the field values f_ijk have been… More >

Chenze Li¹, Manish Jain^1,2, Qian Liu¹, Zhuohan Cao¹, Michael Ferry³, Jamie J. Kruzic¹, Bernd Gludovatz¹, Xiaopeng Li^1,*

The International Conference on Computational & Experimental Engineering and Sciences, Vol.31, No.4, pp. 1-2, 2024, DOI:10.32604/icces.2024.011290

Abstract Laser powder bed fusion (LPBF) additive manufacturing (AM) technology has become a versatile tool for producing new microstructures in metal components, offering novel mechanical properties for different applications. In this work, enhanced ductility (~55% elongation) and tunable mechanical anisotropy (ratio of ductility along vertical to horizontal orientation from ~0.2 to ~1) were achieved for a CoCrNi medium entropy alloy (MEA) by multi-scale synergistic microstructure manipulation (i.e., melt pool boundary, grain morphology and crystallographic texture) through adjusting key LPBF processing parameters (e.g., laser power and scan speed). By increasing the volumetric energy density (VED) from 68.3… More >