Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Safanah Mudheher Raafat has a total of 51 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Adaptive PID-Fuzzy Control for Trajectory Tracking of Par-4 Delta Parallel Robot

    by Shaymaa M. Mahdi, Ahmed I. Abdulkareem, Amjad J. Humaidi, Safanah M. Raafat

    The Par-4 Delta parallel robot is widely utilized in industrial applications requiring high operational speed and acceleration. However, its control design is severely challenged by strong nonlinearities, cross-coupling dynamics, and structural uncertainty. To overcome these limitations, this study proposes an adaptive trajectory-tracking control framework for the Par-4 Delta parallel robot by integrating Type-1 and Interval Type-2 Fuzzy Logic Controllers (T2FLC) with a Proportional–Integral–Derivative (PID) architecture. The proposed scheme is designed to simultaneously enhance position tracking precision, minimize control energy consumption, and ensure robust disturbance rejection. The proposed controllers are evaluated on a spiral trajectory-tracking benchmark using Root Mean Square Error (RMSE) and Root Mean Square Control Effort (RMSCE) as performance metrics. The adaptive Type-2 fuzzy-PID hybrid (APID-T2FLC) achieves the lowest tracking error and reduces control effort compared with standard PID and Type-1 fuzzy-hybrid baselines, demonstrating its suitability for high-precision control of the Par-4 Delta parallel robot. Robustness is further validated under the effects of disturbance and noise, where stable performance has been maintained under implementation of the APID-T2FLC controller rather than other implemented controller types.

  • Open Access

    Hybrid ISMC–FTC Design with PSO Tuning for Finite-Time Stabilization of a 2-DOF Robotic Manipulator

    by Samara H. Al-Dahlaki, Safanah M. Raafat, Shibly A. Ai-Samarraie, Amjad J. Humaidi

    This paper proposes a hybrid integral sliding mode and finite-time control (ISMC–FTC) strategy for a two-degree-of-freedom (2DOF) robotic manipulator, targeting finite-time stability and high-precision elliptical trajectory tracking. To ensure practical deployment, the controller explicitly enforces actuator saturation limits, joint kinematic bounds, workspace constraints, and prescribed stabilization time requirements. Particle swarm optimization (PSO) is employed to tune the FTC parameters, minimizing convergence time while guaranteeing constraint satisfaction. By integrating ISMC’s inherent robustness against matched disturbances with a PSO-optimized FTC, the scheme eliminates the reaching phase and ensures rapid, finite-time convergence. The simulation results demonstrate that the proposed approach significantly reduces stabilization time for both joints, maintains exceptionally low tracking errors, and enforces all physical constraints under bounded disturbances and model uncertainties through explicit saturation limits and sliding manifold invariance. These results validate the framework’s effectiveness and highlight its potential for safety-critical, high-precision robotic applications requiring guaranteed finite-time performance. Robustness is further validated under simultaneous disturbances and uncertainties, where the controller maintains stable performance and consistently satisfies the required robust stability condition.


  • Open Access

    Adaptive K-Fold Siamese Neural Network Classifier for Automatic Seatbelt Monitoring

    by Ahmed M. Hasan, Farah F. Alkhalid, Safanah M. Rafaat, Amjad J. Humaidi

    A seatbelt is an essential aspect of safety in road traffic accidents. Although most traffic regulations enforce drivers and passengers to wear and fasten the seatbelt manually, AI-based techniques have been introduced for monitoring to improve safety standards. In this study, a new approach is proposed to address the monitoring problem of seatbelts. Deep learning (DL) classification based on adaptive Siamese Neural Network (SNN) has been developed utilizing the K-fold method for feature verification. The proposed adaptive K-Fold-based SNN approach utilizes a binary seatbelt dataset, with positive and negative classes, to verify the status of the seatbelt. The network involves sharing a convolutional feature extractor, followed by a distinct-based similarity function. To enhance model reliability, 5-fold cross validation is applied (k = 5), splitting the dataset into 5 subsets, where the model is trained on four sets and validated on the fifth one. The model was trained using binary cross entropy loss, Adam optimization, and performance metrics such as accuracy, precision, recall, and F1 score. The seatbelt dataset is basically designed for object detection models. In this work, we used a dataset in the verification model and achieved high-performance metrics. The model is implemented using a Python-based Jupyter Notebook 7.5.1. It achieved a high performance in seatbelt verification with an average Accuracy = 0.9989, average Precision = 0.9988, average Recall = 0.9990, and average F1 Score = 0.9989. The proposed adaptive K-Fold SNN model can ensure reliability and reduce the risk of over fitting.

  • Open Access

    Hybrid LLM-Assisted Fault Diagnosis Framework for 5G/6G Networks Using Real-World Logs

    by Aymen D. Salman, Akram T. Zeyad, Shereen S. Jumaa, Safanah M. Raafat, Fanan Hikmat Jasim, Amjad J. Humaidi

    This paper presents Hy-LIFT (Hybrid LLM-Integrated Fault Diagnosis Toolkit), a multi-stage framework for interpretable and data-efficient fault diagnosis in 5G/6G networks that integrates a high-precision interpretable rule-based engine (IRBE) for known patterns, a semi-supervised classifier (SSC) that leverages scarce labels and abundant unlabeled logs via consistency regularization and pseudo-labeling, and an LLM Augmentation Engine (LAE) that generates operator-ready, context-aware explanations and zero-shot hypotheses for novel faults. Evaluations on a five-class, imbalanced Dataset-A and a simulated production setting with noise and label scarcity show that Hy-LIFT consistently attains higher macro-F1 than rule-only and standalone ML baselines while maintaining strong per-class precision/recall (≈0.85–0.93), including minority classes, indicating robust generalization under class imbalance. IRBE supplies auditable, high-confidence seeds; SSC expands coverage beyond explicit rules without sacrificing precision; and LAE improves operational interpretability and surfaces potential “unknown/novel” faults without altering classifier labels. The paper’s contributions are as follows: (i) a reproducible, interpretable baseline that doubles as a high-quality pseudo-label source; (ii) a principled semi-supervised learning objective tailored to network logs; (iii) an LLM-driven explanation layer with zero-shot capability; and (iv) an open, end-to-end toolkit with scripts to regenerate all figures and tables. Overall, Hy-LIFT narrows the gap between brittle rules and opaque black-box models by combining accuracy, data efficiency, and auditability, offering a practical path toward trustworthy AIOps in next-generation mobile networks.


  • Open Access

    Hybrid CDN Architecture Integrating Edge Caching, MEC Offloading, and Q-Learning-Based Adaptive Routing

    by Aymen D. Salman, Akram T. Zeyad, Asia Ali Salman Al-Karkhi, Safanah M. Raafat, Amjad J. Humaidi

    Content Delivery Networks (CDNs) have evolved to meet surging data demands and stringent low-latency requirements driven by emerging applications like high-definition video streaming, virtual reality, and IoT. This paper proposes a hybrid CDN architecture that synergistically combines edge caching, Multi-access Edge Computing (MEC) offloading, and reinforcement learning (Q-learning) for adaptive routing. In the proposed system, popular content is cached at radio access network edges (e.g., base stations) and computation-intensive tasks are offloaded to MEC servers, while a Q-learning agent dynamically routes user requests to the optimal service node (cache, MEC server, or origin) based on the network state. The study presented detailed system design and provided comprehensive simulation-based evaluation. The results demonstrate that the proposed hybrid approach significantly improves cache hit ratios and reduces end-to-end latency compared to traditional CDNs and simpler edge architectures. The Q-learning-enabled routing adapts to changing load and content popularity, converging to efficient policies that outperform static baselines. The proposed hybrid model has been tested against variants lacking MEC, edge caching, or the RL-based controller to isolate each component’s contributions. The paper concludes with a discussion on practical considerations, limitations, and future directions for intelligent CDN networking at the edge.


  • Open Access

    Review of: "Enhancing Lifelong Multi-Agent Path Finding with Cache Mechanism"

    by Safanah Raafat

    Review Comments: In general, the contribution of this manuscript is clear and good. The mechanism of Life long MAPF with Cache Mechanism (L-MAPF-CM) has been clearly described. It integrates high-level cache storage with low-level path planning. A p...

  • Open Access

    Design of A Backstepping Control and Synergetic Control for An Interconnected Twin-Tanks System: A Comparative Study

    by Rawaa Al-Majeez, Kareem Al-Badri, Huthaifa Al-Khazraji, Safanah M. Ra'AFat

    This paper presents a comparative performance examination between designing backstepping control (BSC) and synergetic control (SC) for an interconnected twin-tanks system. The controller is used to maintain the liquid level in the tank at the desired value by manipulating the input flow rate. The nonlinear dynamics of the twin-tanks system is established first. Then, based on the nonlinear dynamics of the system, the control law of the BSC and the SC are developed. The two controllers cooperate with the grasshopper optimization algorithm (GOA) for further improvement of the control design performance by tuning the design parameters of each controller. GOA has strong searchability for optimal solution and it has been successfully used to solve several optimization problems in numerous fields. Finally, the performance and the significance of each controlled system for two case studies (normal operation and under external disturbance) are examined based on MATLAB software. The simulation data shows that the BSC gives better performance than the SC.


  • Event triggered based sliding mode control for magnetic levitation system

    by Mohammed K. Hamzah, Safanah M. Raafat, Shibly A. Al-Samarraie

    In this article, an integral sliding mode controller based on an event-triggered technique is developed for a magnetic levitation system (MLS). The proposed con In this article, an integral sliding mode controller based on an event-triggered technique is developed for a magnetic levitation system (MLS). The proposed con


  • Extremum Seeking Based PID Control of Quadrotor System

    by Safanah M. Raafat, Abdullah N. Muhsen, Ahmed A. A. Alawsai