Nada Mohammed Murad¹, Adnan Yousif Dawod², Saadaldeen Rashid Ahmed^3,4,*, Ravi Sekhar⁵, Pritesh Shah⁵

Intelligent Automation & Soft Computing, Vol.40, pp. 1-27, 2025, DOI:10.32604/iasc.2024.058624 - 10 January 2025

Abstract This study introduces an innovative hybrid approach that integrates deep learning with blockchain technology to improve cybersecurity, focusing on network intrusion detection systems (NIDS). The main goal is to overcome the shortcomings of conventional intrusion detection techniques by developing a more flexible and robust security architecture. We use seven unique machine learning models to improve detection skills, emphasizing data quality, traceability, and transparency, facilitated by a blockchain layer that safeguards against data modification and ensures auditability. Our technique employs the Synthetic Minority Oversampling Technique (SMOTE) to equilibrate the dataset, therefore mitigating prevalent class imbalance difficulties… More >

Syed Tasnimul Karim Ayon^1,#, Farhan Md. Siraj^1,#, Jia Uddin^2,*

CMC-Computers, Materials & Continua, Vol.82, No.1, pp. 499-520, 2025, DOI:10.32604/cmc.2025.058361 - 03 January 2025

Abstract This study investigates the application of Learnable Memory Vision Transformers (LMViT) for detecting metal surface flaws, comparing their performance with traditional CNNs, specifically ResNet18 and ResNet50, as well as other transformer-based models including Token to Token ViT, ViT without memory, and Parallel ViT. Leveraging a widely-used steel surface defect dataset, the research applies data augmentation and t-distributed stochastic neighbor embedding (t-SNE) to enhance feature extraction and understanding. These techniques mitigated overfitting, stabilized training, and improved generalization capabilities. The LMViT model achieved a test accuracy of 97.22%, significantly outperforming ResNet18 (88.89%) and ResNet50 (88.90%), as well… More >

Sourabh Mhaski^*, G. V. Ramana

CMES-Computer Modeling in Engineering & Sciences, Vol.142, No.1, pp. 251-277, 2025, DOI:10.32604/cmes.2024.055963 - 17 December 2024

Abstract Earthquake-induced soil liquefaction poses significant risks to the stability of geotechnical structures worldwide. An understanding of the liquefaction triggering, and the post-failure large deformation behaviour is essential for designing resilient infrastructure. The present study develops a Smoothed Particle Hydrodynamics (SPH) framework for earthquake-induced liquefaction hazard assessment of geotechnical structures. The coupled flow-deformation behaviour of soils subjected to cyclic loading is described using the PM4Sand model implemented in a three-phase, single-layer SPH framework. A staggered discretisation scheme based on the stress particle SPH approach is adopted to minimise numerical inaccuracies caused by zero-energy modes and tensile… More >

Chen Hao, Chunfeng Mu, Xinyan Yu, Xiaoran Chen, Mengmeng Zhu, Jianrui Wang^*, Yu Liu^*

Phyton-International Journal of Experimental Botany, Vol.93, No.12, pp. 3549-3572, 2024, DOI:10.32604/phyton.2024.056114 - 31 December 2024

Abstract Entoloma clypeatum, a kind of edible ectomycorrhizal fungus, can be usually symbiotic with Rosaceae fruit trees. Fruit trees have become an important part of China’s agriculture. The present work focused on exploring how E. clypeatum affected symbiotic Rosaceae plants and establishing a symbiotic culture with Malus robusta, Pyrus betulifolia and Prunus armeniaca rootstocks. The results showed that E. clypeatum and three Rosaceae plants can generate cylindrical or clavate mycorrhizae. The inoculation treatment had different degrees of positive effects on the three plants. Relative to the non-inoculated group, biomass in symbiotic plants increased (32.8%–191.1%), and photosynthesis enhanced. In the level of… More >

Dazhi E¹, Jiale Liu², Ming Zhang^1,*, Huiyuan Jiang², Keming Mao²

CMC-Computers, Materials & Continua, Vol.81, No.3, pp. 3853-3880, 2024, DOI:10.32604/cmc.2024.057538 - 19 December 2024

Abstract Imbalance is a distinctive feature of many datasets, and how to make the dataset balanced become a hot topic in the machine learning field. The Synthetic Minority Oversampling Technique (SMOTE) is the classical method to solve this problem. Although much research has been conducted on SMOTE, there is still the problem of synthetic sample singularity. To solve the issues of class imbalance and diversity of generated samples, this paper proposes a hybrid resampling method for binary imbalanced data sets, RE-SMOTE, which is designed based on the improvements of two oversampling methods parameter-free SMOTE (PF-SMOTE) and… More >

Ruike Shi¹, Haitian Yang¹, Yue Mei¹, Yiqian He^1,2,*

The International Conference on Computational & Experimental Engineering and Sciences, Vol.31, No.3, pp. 1-1, 2024, DOI:10.32604/icces.2024.012458

Abstract Soft biological tissues, like cartilage or arteries, are often modeled as biphasic, considering both solid matrix and interstitial fluid [1]. This biphasic behavior involves chemo-mechanical couplings that control interstitial fluid osmotic pressure [2]. Therefore, the research on the inverse problems of osmotic pressure in soft tissues is important. In this paper, the authors propose a virtual fields method (VFM) for identifying the constitutive model of solid-liquid biphasic hyperelasticity. This method constructs virtual fields based on finite elements (FE) to solve linearly independent virtual fields that can automatically satisfy constraint conditions of the solution of VFM.… More >

Yuxiang Peng^1,*, Pengnan Sun¹, Niannian Liu¹

The International Conference on Computational & Experimental Engineering and Sciences, Vol.31, No.3, pp. 1-1, 2024, DOI:10.32604/icces.2024.011902

Abstract Immersed boundary method (IBM) has been widely applied in the simulation of fluid-structure interaction problems. The traditional direct force model is less accurate, and the sharp-interface approaches involve complex topological operations which are not conducive to dealing with complex structures. The boundary data immersion method (BDIM) is a new fluid-structure coupling scheme that does not need to cut the mesh and can be extended to reach second-order accuracy. However, the traditional boundary data immersion method needs special treatment to deal with the sharp corners of the structure. In the present work, the volume fraction of More >

Yue Jiang^1,2,#, Lingyu Liu^1,#, Kangyu Wang^1,2, Mingzhu Zhao^1,2, Ping Chen^1,2, Jun Lei^1,2, Yanfang Wang³, Meiping Zhang^1,2, Yi Wang^1,2,*, Guang Chen^1,*

Phyton-International Journal of Experimental Botany, Vol.93, No.11, pp. 3055-3071, 2024, DOI:10.32604/phyton.2024.056384 - 30 November 2024

Abstract The main active components of ginseng are ginsenosides, which play significant roles in treating cardiovascular diseases, cancer, and providing antioxidant effects. Ginsenosides are primarily synthesized through the mevalonate pathway and the methylerythritol phosphate pathway. Many key enzyme genes involved in this biosynthetic process have been cloned and validated, yet the regulatory functions of transcription factors remain unclear. The C₂H₂-type zinc finger protein family, one of the largest families of transcription factors, is crucial in plant growth and development, response to biotic and abiotic stresses, and regulation of secondary metabolism. This study, based on the ginseng transcriptome More >

Yuanhang Yang¹, Changjin Huang^2,*

The International Conference on Computational & Experimental Engineering and Sciences, Vol.31, No.2, pp. 1-1, 2024, DOI:10.32604/icces.2024.010991

Abstract Achieving programmable and reversible deformations of soft materials is a long-standing goal for various applications in soft robotics, flexible electronics and many other fields. Swelling-induced shape-morphing has been intensively studied as one of the potential mechanisms. However, achieving an extremely large swelling ratio (>1000% in volume) remains challenging with existing swellable soft materials (e.g., hydrogels and water-swellable rubbers). Inspired by the shape change enabled by the osmosis-driven swelling in living organisms, herein, we report a polymer composite system composed of fine sodium chloride (NaCl) particles embedded in Ecoflex00-10 polymer. This Ecoflex00-10/NaCl polymer composite can achieve… More >

Qiuxia Fan^1,*, Jianyu Li¹, Xinqi Zhang¹

The International Conference on Computational & Experimental Engineering and Sciences, Vol.31, No.1, pp. 1-1, 2024, DOI:10.32604/icces.2024.012048

Abstract In this paper, a series of smoothed finite element methods for the electromagnetic field distribution of non-contact LVDT are proposed. Firstly, the problem domain is discretized into a set of four-node tetrahedral elements, and the linear shape function is used to interpolate the domain variables. Then, the smooth region is further constructed by combining the nodes, edges and surfaces of the unit. Gradient smoothing technique is used to smooth the magnetic vector potential and scalar potential on each smooth domain. Based on the generalized smooth Galerkin weak form, the discretization system expression is derived and More >