Tengda Li, Gang Wang, Qiang Fu^*

CMES-Computer Modeling in Engineering & Sciences, Vol.140, No.3, pp. 2559-2586, 2024, DOI:10.32604/cmes.2024.052039

Abstract Aiming at the problems of low solution accuracy and high decision pressure when facing large-scale dynamic task allocation (DTA) and high-dimensional decision space with single agent, this paper combines the deep reinforcement learning (DRL) theory and an improved Multi-Agent Deep Deterministic Policy Gradient (MADDPG-D2) algorithm with a dual experience replay pool and a dual noise based on multi-agent architecture is proposed to improve the efficiency of DTA. The algorithm is based on the traditional Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm, and considers the introduction of a double noise mechanism to increase the action exploration… More >

Xuejie Wang¹, Jianxun Zhang^1,*, Ye Tao², Xiaoli Yuan¹, Yifan Guo¹

CMC-Computers, Materials & Continua, Vol.79, No.3, pp. 4621-4639, 2024, DOI:10.32604/cmc.2024.051556

Abstract While single-modal visible light images or infrared images provide limited information, infrared light captures significant thermal radiation data, whereas visible light excels in presenting detailed texture information. Combining images obtained from both modalities allows for leveraging their respective strengths and mitigating individual limitations, resulting in high-quality images with enhanced contrast and rich texture details. Such capabilities hold promising applications in advanced visual tasks including target detection, instance segmentation, military surveillance, pedestrian detection, among others. This paper introduces a novel approach, a dual-branch decomposition fusion network based on AutoEncoder (AE), which decomposes multi-modal features into intensity… More >

Sandeep Dasari, Rajesh Kaluri^*

CMES-Computer Modeling in Engineering & Sciences, Vol.140, No.2, pp. 2035-2051, 2024, DOI:10.32604/cmes.2024.049152

Abstract The increasing data pool in finance sectors forces machine learning (ML) to step into new complications. Banking data has significant financial implications and is confidential. Combining users data from several organizations for various banking services may result in various intrusions and privacy leakages. As a result, this study employs federated learning (FL) using a flower paradigm to preserve each organization’s privacy while collaborating to build a robust shared global model. However, diverse data distributions in the collaborative training process might result in inadequate model learning and a lack of privacy. To address this issue, the… More > Graphic Abstract

HULYA SEMA KOKER¹, HÜLYA YAVUZ ERSAN¹, AYSE AYTAC^2,3,*

Journal of Polymer Materials, Vol.37, No.3-4, pp. 165-177, 2020, DOI:10.32381/JPM.2020.37.3-4.4

Abstract Chitosan (CH) and low-density polyethylene (PE) blend films were produced by a twin-screw extruder and heat press with different plasticizers glycerol (GLY), sorbitol (SOR) and polyethylene glycol (PEG). The tensile strength decreased and elongation at break increased with the incorporation of plasticizer for blends with 10 wt% of CH. The thermal stability of the films was slightly higher for films containing GLY and PEG as compared to SOR. Contact angles reduced from CH-PE film to the films containing PEG, SOR and GLY in decreasing order, respectively. Fourier transform infrared spectroscopy revealed no interactions between CH More >

İBRAHIM KARTERI^a,b,*, MUSTAFA ÖZYEŞILDAĞ^b

Journal of Polymer Materials, Vol.38, No.1-2, pp. 167-177, 2021, DOI:10.32381/JPM.2021.38.1-2.13

Abstract This study aims to provide a comprehensive account of chemically reduced graphene oxide (RGO) and decabromodiphenyl ethane (DBDPE) filled acrylonitrile-butadiene-styrene (ABS) multifunctional filaments for fused deposition modeling (FDM) applications. ABS/RGO with DBDPE nanocomposites (ABS-GDM) were fabricated by single-screw extrusion at a diameter of 1.75 mm. The proportion of RGO and DBDPE for the ABS-GDM filaments was set to 0.75 wt%. The properties of the ABS-GDM were determined using optical, mechanical, thermal, and morphological characteristics (using scanning electron microscopy). A three-dimensional (3D) model was successfully printed using the developed ABS-GDM filaments for FDM 3D printing. These More >

RAID BANAT^1,*, MANAL AL-RAWASHDEH¹, HEBA ALKHLAIFAT¹

Journal of Polymer Materials, Vol.38, No.1-2, pp. 137-151, 2021, DOI:10.32381/JPM.2021.38.1-2.11

Abstract Composite of oil Shale ash (OSA) filler and high density polyethylene (HDPE) matrix was formulated and studied. OSA mainly composed of Ca, Si, and Fe most of which in oxide forms. OSA-HDPE composite with 0, 5, 10, 15, 20, and 25 wt. % OSA were produced using extrusion and hot press. Mechanical, morphological, and water uptake properties of the composite are discussed herein. While the tensile stress at yield, 47 MPa, restored its value close to the neat HDPE, an increase in the mean values of the tensile stress at rapture from 19 to 33… More >

ALOK K. SAHU^a, RAJSHREE VIJAYVARGIYA^a, R. M. SARVIYA^b

Journal of Polymer Materials, Vol.39, No.3-4, pp. 183-193, 2022, DOI:10.32381/JPM.2022.39.3-4.1

Abstract HDPE material is found to be best suited material for the manufacturing of floating bed structure for the solar photovoltaic (PV) system due to its light weight and excellent mechanical & chemical resistant properties. However, the major restriction in this regard is the limited engineering design and also the effect of UV radiations present in the natural environment that leads to the degradation of the plastic materials. Hence, in order to improve its UV stability carbon black is incorporated into it as UV resistant additive and hollow cubical floats of such HDPE/carbon black composite material… More >

Jean-Pierre Chery¹, Marie Gradeler¹, Vincent Bonnal^2,3,4

Revue Internationale de Géomatique, Vol.31, No.2, pp. 355-376, 2022, DOI:10.3166/RIG.31.355-376©2022

Abstract Les besoins de valoriser et de partager des informations génériques et originales de différents projets de recherche, ont conduit à concevoir une plateforme géoweb dédiée, dénommée NAMO. Sa conception utilise des fonctionnalités ouvertes, libres et gratuites qui montrent leur souplesse dans une démarche agile et itérative. C’est en particulier le développement de deux dimensions de valorisation et de positionnement en géoweb 2.0 qui est souligné : la cartographie narrative et la modélisation systémique. Les dispositifs d’usage de l’information géographique, en particulier dans les démarches de co-construction et de science ouverte, peuvent ainsi être mieux outillés. More >

Sherly Alphonse^*, Harshit Verma

CMC-Computers, Materials & Continua, Vol.78, No.2, pp. 2067-2086, 2024, DOI:10.32604/cmc.2024.046070

Abstract Although lots of research has been done in recognizing facial expressions, there is still a need to increase the accuracy of facial expression recognition, particularly under uncontrolled situations. The use of Local Directional Patterns (LDP), which has good characteristics for emotion detection has yielded encouraging results. An innovative end-to-end learnable High Response-based Local Directional Pattern (HR-LDP) network for facial emotion recognition is implemented by employing fixed convolutional filters in the proposed work. By combining learnable convolutional layers with fixed-parameter HR-LDP layers made up of eight Kirsch filters and derivable simulated gate functions, this network considerably More >

Sanxiu Jiao¹, Lecai Cai^2,*, Jintao Meng³, Yue Zhao³, Kui Cheng²

Computer Systems Science and Engineering, Vol.48, No.1, pp. 247-265, 2024, DOI:10.32604/csse.2023.040194

Abstract Federated learning is a distributed machine learning framework that solves data security and data island problems faced by artificial intelligence. However, federated learning frameworks are not always secure, and attackers can attack customer privacy information by analyzing parameters in the training process of federated learning models. To solve the problems of data security and availability during federated learning training, this paper proposes an Efficient Differential Privacy Federated Learning Algorithm based on early stopping mechanism (Efficient DP-FL). This method inherits the advantages of differential privacy and federated learning and improves the performance of model training while More >