Batna 2 University

Elastic optical networks (EON) have emerged as a promising solution for supporting heterogeneous and time-varying bandwidth demands through flexible spectrum allocation. Nevertheless, efficient resource management in EONs remains challenging due to dynamic traffic conditions, spectrum fragmentation, and the need to jointly optimize multiple objectives such as blocking probability, transmission delay, energy consumption, and spectrum utilization. In this paper, we propose VAE-GNN-RL, an integrated framework that combines a Variational Autoencoder (VAE) for stable traffic data augmentation, a Graph Attention Network (GAT) for topology-aware prediction of spectrum requirements and network performance indicators, and a Deep Reinforcement Learning (DRL) stage for adaptive real-time spectrum allocation. The proposed framework is evaluated on the NSFNET topology under dynamic traffic scenarios with Poisson-distributed arrivals and exponentially distributed holding times. Experimental results show that the proposed approach achieves very high predictive performance, reaching 99.93% classification accuracy and an average mean squared error of 0.0037, while consistently outperforming the GAN-ESN baseline and several conventional deep learning models. In addition, the adaptive optimization stage improves allocation efficiency and network performance under dynamic operating conditions. These findings demonstrate that the proposed VAE-GNN-RL framework provides an effective and intelligent solution for topology-aware and adaptive resource allocation in elastic optical networks.

This study evaluated the chemical composition and therapeutic potential of Olea europaea var. Chemlal extracts, focusing on antioxidant, anticancer, and anticoagulant activities. Polyphenols were extracted using maceration with water, 70% ethanol, and 70% methanol. Antioxidant capacity was assessed via multiple in vitro assays, including total antioxidant capacity, 2,2-diphenyl-1-picrylhydrazyl) (DPPH), 2,2 '-azinobis-(3-ethylbenzothiazoline-6-sulfonic acid (ABTS), beta-carotene bleaching, cupric ion reducing antioxidant capacity (CUPRAC), ferrous ion chelating, and phenanthroline assays. Cytotoxic activity against human hepatocellular cancer cell lines (HePG-2) was measured using the (3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide) (MTT). Anticoagulant properties were evaluated by activated partial thromboplastin time (aPTT) and prothrombin time (PT) tests. The hydromethanolic extract exhibited the highest total phenolic and flavonoid contents, identifying 15 polyphenolic compounds. All extracts demonstrated strong antioxidant activities and significant cytotoxicity against HePG-2 cells, with the hydromethanolic extract showing superior efficacy. In coagulation assays, extracts displayed notable anticoagulant effects; PT was prolonged up to 91.1 seconds at 27 mg/mL concentration, while the aqueous extract extended aPTT beyond 150 seconds at 13.5 and 27 mg/mL. These findings suggest that O. europaea var. Chemlal extracts are promising sources of bioactive compounds with potential pharmaceutical applications for managing oxidative stress, cancer, and blood clotting disorders.

The development of a mixed carbonate–siliciclastic ramp system along the southern Tethyan margin can be clarified by examining the Aptian–Albian sequence of the Aurès Basin. An extensive cross-section was analysed to constrain the lithological architecture and microfacies distribution along the southern flank of Djebel El Azereg, the most prominent anticline of the area. Lithostratigraphic analysis allows the subdivision of the Aptian–Albian succession into three well-defined units: the Ich Moul Formation, the Dechera Baida Formation, and the Ackliath Azougar Formation. The studied succession is composed of laterally and vertically heterogeneous siliciclastic–carbonate deposits, reflecting the interplay between carbonate productivity and episodic terrigenous input under varying accommodation conditions. Petrographic analysis reveals a diverse suite of microfacies, characterised by significant variations in texture and in the relative abundance of skeletal and non-skeletal components. Thirteen microfacies are distinguished and organised into five facies associations, (1) siliciclastic microfacies, constituted by fine- to medium-grained sandstones; (2) siliciclastic–carbonate microfacies with packstone texture, composed mainly of quartz grains, ooids, bivalves, and orbitolinids; (3 and 4) carbonate microfacies with packstone and/or grainstone texture, dominated by ooids and peloids; and (4) wackestone to packstone microfacies, dominated by bivalves and echinoderms. These facies associations record depositional environments along a low-gradient homoclinal ramp, ranging from coastal and hybrid backshoal settings to carbonate shoals (inner and mid-ramp) and a proximal outer ramp domain. The spatial and vertical distribution of these facies associations provides insights into the internal organisation of the ramp (inner, middle and outer) and its stratigraphic evolution. These results highlight the complex dynamics of mixed carbonate–siliciclastic systems and contribute to a better understanding of Aptian–Albian platform development along the southern Tethyan margin.

Fault diagnosis in complex industrial systems plays a critical role in ensuring operational reliability, improving predictive maintenance, and enhancing energy efficiency. In cement rotary kilns, continuous thermal monitoring is essential to maintain process stability, reduce energy losses, and prevent unexpected shutdowns caused by abnormal temperature distributions. This work introduces a hybrid CNN–DDQN framework that transforms thermal fault classification in cement rotary kilns from a static prediction task into an adaptive decision-making process, achieving superior accuracy and robustness on real industrial data. The proposed approach integrates a convolutional neural network (CNN) architecture for robust feature extraction, with a double deep Q-network (DDQN) reinforcement learning model to enhance adaptive fault classification and decision-making. The models were trained and validated using labeled thermal data collected from a real cement production environment comprising multiple fault categories. Comparative evaluation was conducted using classification accuracy and performance efficiency metrics, and compared with the CNN and residual neural network (ResNet) models. The results demonstrate that the DDQN-based model outperforms the conventional CNN architecture in terms of fault classification accuracy and adaptability to thermal variations, highlighting the advantage of integrating deep reinforcement learning with convolutional feature extraction. The proposed framework provides an intelligent and scalable solution for kiln condition monitoring, contributing to improved preventive maintenance strategies, reduced fault occurrence, extended equipment lifespan, and enhanced operational and economic performance in rotary kiln-based industrial systems.

In this paper, a robust control approach for the differential drive wheeled mobile robot (DDWMR) motion, subjected to the skid, slip, and violation of the nonholonomic constraints is presented. The proposed kinematic controller “Perfect Velocity Tracking”, laid on the Lyapunov theory, generates the ideal velocity to ensure the asymptotic convergence of the state vector error. Then, based on the previous output, a new adaptive dynamic power rate sliding-mode control approach is introduced to make the overall system asymptotically stable by generating the desired actuator torques. These two controllers are introduced to promote the tracking motion even in the presence of parameter uncertainties and external disturbances. During the simulation work, an accurate kinematic and dynamic modeling of the differential drive Pioneer 3dx, based on the magic formula’s traction forces, is proposed to simulate the real case motion of the DDWMR.