Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Feleke Tsegaye Yareshe has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    AI-refined neural-network surrogate optimization for delayed vibration suppression using the smoothed spectral abscissa

    by Feleke Tsegaye Yareshe, Libor Pekař, Meron Tadele Roba, Mihret Kochito Wolde, Abebe Alemu Wendimu

  • Open Access

    Mapping Artificial Intelligence in Model Predictive Control: Evolution, Research Fronts, and Functional Integration

    by Mihret Kochito Wolde, Marek Kubalčík, Abebe Alemu Wendimu, Meron Tadele Roba, Feleke Tsegaye Yareshe

    Artificial intelligence (AI) is increasingly combined with model predictive control (MPC), but its role and implications differ according to where learning enters the control architecture. This study combines bibliometric analysis of 13,765 Scopus and Web of Science records published between 2000 and 2025 with a structured critical synthesis of 86 selected studies. Annual publication output grew by 15.7% and accelerated after 2015/2016, while reinforcement learning increased from 1.7% to 22.5% of records and the relative prominence of fuzzy systems declined. Co-citation, bibliographic coupling, and technique–domain analyses reveal the field’s intellectual foundations, current research fronts, and application-specific specialisation. The critical synthesis classifies AI according to whether it modifies theprediction model, horizon information, objective, safety mechanism, online solution, or controller parameters. The findings show that the benefit and control-theoretic obligation of learning depend primarily on this functional position. Prediction learning requires representative multi-step accuracy, optimisation acceleration requires timely feasible solutions, and safety integration depends on calibrated uncertainty and recursive feasibility. The study thus contributes both a longitudinal map of AI–MPC research and a function–consequence framework linking architectural position to prediction, computation, feasibility, stability, safety, and validation.

  • Open Access

    A novel approach to UAV control: Fuzzy PID-based ANFIS (FPIDANFIS)

    by Nigatu Wanore Madebo, Feleke Tsegaye Yareshe, Lebsework Negash Lemma

    This paper presents a novel hybrid control strategy, the Fuzzy PID based Adaptive Neuro-Fuzzy Inference System (FPIDANFIS), designed to enhance the trajectory tracking performance of Unmanned Aerial Vehicles (UAVs). The distinct contribution of this work lies in its data-driven design approach: historical input–output data from a baseline Fuzzy PID (FPID) controller using tracking error and its derivative as inputs and FPID control signals as outputs are leveraged to train an ANFIS model that autonomously generates the adaptive FPIDANFIS controller. This methodology differs from existing studies by enabling the new controller to inherit the baseline controller’s behavior while introducing adaptive capabilities not present in conventional FPID frameworks. A dataset of 5001 samples is generated using MATLAB’s Neuro-Fuzzy Designer toolbox for offline training with a hybrid learning algorithm and Gaussian membership functions. Once trained, FPIDANFIS dynamically tunes control actions in real time, improving robustness and adaptability under uncertainty. The controller is evaluated across three scenarios: nominal trajectory tracking, tracking with input disturbances, and tracking under parameter variations. Performance is quantified using the Integral of Time-weighted Absolute Error (ITAE). Simulation results show that FPIDANFIS outperforms the baseline FPID controller, achieving a 42% ITAE reduction under disturbances and a 22.12% reduction under parameter variations. The proposed method introduces a data-driven, adaptive extension of the FPID framework and demonstrates significant improvements in UAV trajectory tracking accuracy, making it suitable for applications requiring precise and robust maneuverability.

  • Linear to Nonlinear MPC: Reproducible Design Pipeline on the Cart–Pole Benchmark

    by Mihret Kochito Wolde, Marek Kubalčík, Abebe Alemu Wendimu, Meron Tadele Roba, Feleke Tsegaye Yareshe

  • Open Access

    Fractional-Order Control: Bibliometric Analysis and Performance Evaluation

    by Meron Tadele Roba, Radek Matušů, Feleke Tsegaye Yareshe, Mihret Kochito Wolde, Abebe Alemu Wendimu, Tewodros Asfaw Gebretsadik

    The development of fractional-order control has been derived from the mathematical generalization of classical calculus and has become an important tool in the modeling and control of dynamical systems with memory and hereditary effects. In spite of the rapid development of this area of control theory and applications, the overall scientific development, structure, and engineering relevance of fractional-order control remain insufficiently understood. In this paper, we address this problem by combining large-scale bibliometric analysis with representative controller performance studies. A total of 6482 publications indexed in the Web of Science database during the period 2010–2026 are analyzed. The bibliometric results indicate that fractional-order control is an increasingly connected global research field with strong roots in fractional calculus, advanced control theory, and growing interdisciplinary links with applied mathematics, automation, and computer science. To further illustrate controller level behavior, representative simulations are performed on a fractional-order time-delay process and an uncertain nonlinear system. For the fractional-order time-delay process, a well-tuned PID controller is compared with a realizable FOPID controller implemented through Oustaloup recursive approximation. The results show that the FOPID controller improves several performance measures, including overshoot, settling time, control energy, total variation, and sensitivity peak, while the comparison is interpreted as a performance trade-off rather than universal superiority. For the uncertain nonlinear system, fractional-order sliding mode control produces smoother control action and substantially reduces chattering. By combining bibliometric mapping with representative performance evaluation, this paper provides a comprehensive overview of fractional-order control as a globally active and practically relevant discipline in control engineering.


  • Open Access

    Artificial Intelligence-Driven Control of Time Delay Systems: A Comprehensive Review, Bibliometric Analysis, and Future Research Framework

    by Feleke Tsegaye Yareshe, Libor Pekař, Meron Tadele Roba, Mihret Kochito Wolde, Abebe Alemu Wendimu

    Time-delay systems (TDSs) arise in many engineering applications where sensing, actuation, computation, transport, or communication delays affect closed-loop stability and performance. Classical control methods, including predictor-based control, Lyapunov–Krasovskii functional approaches, robust control, model predictive control, and adaptive control, provide rigorous theoretical foundations for delay compensation and stability analysis. However, their effectiveness may be limited when the system is nonlinear, uncertain, poorly modeled, or subject to unknown and time-varying delays. In recent years, artificial intelligence (AI)-based methods, such as neural networks, fuzzy systems, deep learning, and reinforcement learning, have attracted increasing attention for their capabilities in learning, approximation, prediction, and adaptation. This paper presents a comprehensive review and bibliometric analysis of control strategies for TDSs, with an emphasis on the interactions among classical, AI-based, and hybrid methods. Publications indexed in the Web of Science database from 2010 to 2025 are analyzed using bibliometrix and VOSviewer to identify publication trends, influential contributors, collaboration patterns, citation structures, and thematic evolution. In addition, a unified framework is proposed to classify TDS control strategies into classical, AI-based, and hybrid categories. The results show that classical stability and robustness analysis remain central to the field, while AI-based and hybrid methods are increasingly used to address nonlinearities, uncertainties, communication delays, and real-time implementation challenges. Finally, key research gaps and future directions are discussed, including stability-guaranteed learning, learning-based delay compensation, interpretable AI control, benchmarking, and practical deployment in cyber-physical, robotic, aerospace, and networked systems.


  • Open Access

    A Unified Comparative Framework for Fractional-Order Operator Approximation with Pareto-Based Analysis

    by Abebe Alemu Wendimu, Radek Matušů, Ibrahim Shaikh, Mihret Kochito Wolde, Meron Tadele Roba, Feleke Tsegaye Yareshe

    Fractional-order operators play a fundamental role in the modeling and control of complex dynamical systems; however, their infinite-dimensional nature necessitates rational approximation for practical implementation. This paper presents a unified comparative framework for evaluating widely used approximation methods, including standard and refined Oustaloup filters, continued fraction expansion (CFE), Matsuda, curve-fitting, and modified stability boundary locus (M-SBL) approaches. A systematic evaluation methodology is developed to assess these methods based on frequency-domain accuracy, time-domain performance, and robustness. Furthermore, a Pareto-based multi-objective analysis is introduced to explicitly capture the trade-offs among conflicting performance criteria, enabling the identification of non-dominated solutions without relying on weighted-sum formulations. Extensive simulations are conducted over a wide frequency range to evaluate approximation accuracy and control-oriented performance. The results reveal that different methods exhibit distinct trade-offs between accuracy, robustness, and complexity. In particular, the Oustaloup and M-SBL approaches demonstrate strong overall performance across multiple criteria, while methods such as CFE and curve-fitting show limitations under wideband conditions. The proposed framework provides a systematic and reproducible basis for selecting appropriate approximation techniques in fractional-order control applications, offering valuable insights into their practical implementation and performance trade-offs.


  • Top Cited Papers
    Open Access

    Design and Analysis of Adaptive Fuzzy Super-Twisting Sliding Mode Controller for Uncertain 2-DOF Robotic Manipulator

    by Hayleyesus Girma Dirara, Feleke Tsegaye Yareshe, Chala Merga Abdissa

    This paper proposes a robust Adaptive Fuzzy Super-Twisting Sliding Mode Controller (AF-STSMC) to enhance the trajectory tracking capability of a 2-DOF robotic manipulator. The novel controller compensates system uncertainties by adaptively adjusting control parameters based on the angular position of the target joints. To evaluate the controller’s performance, the dynamic model of a two-link manipulator is derived using the Lagrangian method, and stability analysis of the system is considered according to the Lyapunov direct method. Modeling and simulation are done in MATLAB/Simulink. Performance is assessed by comparing the proposed AF-STSMC with conventional Sliding Mode Controller (SMC), Super- Twisting Sliding Mode Controller (ST-SMC), and Adaptive Fuzzy Sliding Mode Controller (AF-SMC), using the Integral of Absolute Error (IAE) as the performance criterion. Simulation results indicate that the AF-STSMC successfully reduces tracking error. For link 1, the IAE is reduced to 0.01465 rad, a 99.9% reduction over SMC (14.24 rad), an 85% reduction over ST-SMC (0.0977 rad), and a 78.5% reduction over AF-SMC (0.06819 rad). Similarly, in link 2, the AF-STSMC gives an IAE of 0.003862 rad that is equivalent to a 99.93% decrease with respect to SMC (5.723 rad), a 98.7% increase over ST-SMC (0.306 rad), and a 91.2% decrease compared to AF-SMC (0.04391 rad). It is therefore clear that the designed AF-STSMC performs better than the controllers in terms of accuracy and robustness to achieve the required performance specifications of accurate trajectory tracking by robotic manipulators.


  • Top Cited Papers
    Open Access

    Trajectory Tracking of Fixed-Wing UAV Using ANFIS-Based Sliding Mode Controller

    by Feleke Tsegaye Yareshe, Nigatu Wanore Madebo, Chala Merga Abdissa, Lebsework Negash Lemma

    This paper proposes a robust Adaptive Neuro-Fuzzy Inference System-based Sliding Mode Controller (ANFIS-SMC) for trajectory tracking in fixed-wing unmanned aerial vehicles (FWUAVs). FWUAVs are autonomous and versatile, finding applications in many fields such as defense, surveillance, and logistics. However, their dynamic model is highly complex due to nonlinearity and coupling effects. In this paper the decoupling is held based on extracting dominant inputs, and all other inputs are considered uncertainties, for designing controllers. The proposed ANFIS-SMC integrates the adaptability of the ANFIS with the robustness of SMC to overcome issues such as the chattering effect and shortcomings of traditional fuzzy logic controllers. ANFIS is trained with the sliding surface as an input data and SMC’s discontinuous control effort as an output data. Through such training, ANFIS can effectively approximate the discontinuous control action without losing smoothness and adaptability of control while keeping the robustness of the traditional SMC strategy. The Lyapunov theory ensures the finite time convergence of both reaching and sliding phases of sliding mode controller. The proposed ANFIS-SMC controller is stronger and more adaptive compared to FSMC and SMC. During mass variation along the x-axis, ITAE increased from 10.94 to 63.52 using ANFIS-SMC, from 17.39 to 128.3 using FSMC, and from 38.28 to 830.1 using SMC. This is an improvement of 50% over FSMC and 90% over SMC, which demonstrates improved trajectory tracking performance for fixed-wing UAVs in dynamic environments. Simulations on MATLAB®/Simulink® confirm that the proposed ANFIS-SMC ensures stable flight and accurate trajectory tracking, even in challenging flight conditions.