Article
Automation & Control Systems
Patricia Ochoa, Oscar Castillo, Patricia Melin, Juan R. Castro
Summary: This article presents the usage of interval type-3 fuzzy sets in the differential evolution algorithm for the first time. A study is conducted to explore the influence of the LowerScale (lambda) parameter on the convergence of differential evolution. The results from experiments on benchmark functions and motor control optimization demonstrate that the combination of interval type-3 fuzzy sets and differential evolution outperforms type-1 and interval type-2 variants.
INTERNATIONAL JOURNAL OF FUZZY SYSTEMS
(2023)
Article
Computer Science, Information Systems
Gabriel Antonio Fanelli de Souza, Rodrigo Bispo dos Santos, Lester de Abreu Faria
Summary: A novel Type-Reduction/Defuzzification circuit architecture is proposed for an analog interval type-2 fuzzy inference system. The circuit operates with current-mode inputs and generates a PWM output, making it simple and suitable for various control applications. Additionally, it achieves very low power consumption, allowing its use in power-restrained environments.
Article
Engineering, Mechanical
Reza Hadjiaghaie Vafaie, Ardashir Mohammadzadeh, Md. Jalil Piran
Summary: This study proposes a new nonlinear model-based predictive control scheme using fractional-order calculus and interval type-3 fuzzy logic systems for controlling MEMS-Gs. The controller demonstrates effectiveness in handling dynamic perturbations, actuator nonlinearities, and tracking of chaotic systems.
NONLINEAR DYNAMICS
(2021)
Article
Computer Science, Artificial Intelligence
Cagri Guzay, Tufan Kumbasar
Summary: This paper presents a new differential flatness-based Single Input Fuzzy Logic Controller (SFLC) structure for aggressive maneuvering control on nano quadcopters. The design parameters of SFLCs shape the characteristics of the fuzzy mapping, and simple tuning guidelines are provided. Comparative experimental results show the performance improvements of SFLCs in real-time aggressive maneuvering.
APPLIED SOFT COMPUTING
(2022)
Article
Automation & Control Systems
Leticia Amador-Angulo, Oscar Castillo, Juan R. Castro, Patricia Melin
Summary: This article focuses on the implementation of Interval Type-3 Fuzzy Logic Systems (IT3FLSs) for control problems and analyzes their performance and efficiency in stabilizing nonlinear plants with perturbations. Simulation results show that IT3FLSs outperform type-2 and type-1 in control. The study highlights the potential of interval type-3 in the control area.
INTERNATIONAL JOURNAL OF FUZZY SYSTEMS
(2023)
Article
Chemistry, Analytical
Yongzhi Chu, Hasiaoqier Han, Tianjiao Ma, Mingchao Zhu, Zhongcan Li, Zhenbang Xu, Qingwen Wu
Summary: This paper presents an IT2F-PID controller designed using a new D-GO method. The optimization and fuzzification of the PID controller and fuzzy logic system results in a superior control performance compared to general and concurrent optimization methods.
Article
Automation & Control Systems
Omid Elhaki, Khoshnam Shojaei, Ardashir Mohammadzadeh
Summary: This paper presents a novel adaptive reinforcement learning control method with interval type-3 fuzzy neural networks to improve the trajectory tracking control performance of quadrotor unmanned aerial vehicles in challenging flight conditions. The proposed controller is independent of system dynamics and only relies on measurable signals. An adaptive robust controller in collaboration with reinforcement learning significantly improves system robustness. Prescribed performance control methodology ensures predefined overshoot/undershoot, convergence rate, and final tracking accuracy. High-gain observer is employed to estimate quadrotor velocity and acceleration. Lyapunov-based stability analysis achieves uniform ultimate boundedness stability. The simulation section demonstrates better performance of the proposed intelligent controller with the learning algorithm compared to conventional techniques.
IET CONTROL THEORY AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Omid Elhaki, Khoshnam Shojaei, Ardashir Mohammadzadeh, Sakthivel Rathinasamy
Summary: This paper proposes a new observer-based bounded adaptive fuzzy controller for robotic manipulators with a prescribed performance subjected to uncertainties. Interval type-3 fuzzy logic systems are introduced, and the system uncertainties are modeled by an interval type-3 fuzzy neural network. The controller is designed based on a robust adaptive command-filtered backstepping control scheme, with projection-type adaptive laws and saturation functions utilized to ensure actuator limitations are not violated.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Multidisciplinary Sciences
Oscar Castillo, Patricia Melin
Summary: This paper presents an initial proposal for the utilization of mediative fuzzy logic in control problems. It extends the concept of fuzzy control to mediative fuzzy logic for situations involving two or more control experts, aiming to improve control results by combining their knowledge. The study demonstrates the effectiveness of type-3 mediative fuzzy control in handling uncertainty from noise in the control process.
Article
Automation & Control Systems
Haozhen Dong, Xinyu Li, Pi Shen, Liang Gao, Haorang Zhong
Summary: In this work, an optimization method based on differential evolution is proposed to improve the performance of IT2FL-PID controller in controlling the position of hydraulic actuator. The simplified structure with fewer parameters and the objective function with weighted error terms are used to achieve a balanced control performance. The experiments conducted show the superiority of the proposed method in optimizing the controller and controlling the actuator position.
INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS
(2021)
Article
Engineering, Mechanical
Amin Taghieh, Ardashir Mohammadzadeh, Chunwei Zhang, Sakthivel Rathinasamy, Stelios Bekiros
Summary: A novel observer-based control policy using an interval type-3 fuzzy logic system is developed to overcome the limitations of fuzzy-based controllers in approximating uncertainties and analyzing complex nonlinear systems without detailed dynamics model information. The proposed approach includes online optimized tuning rules, a simple type reduction method, and adaptive mechanisms. It also utilizes an adaptive compensator to improve the robust performance of the closed-loop system and mitigate the effects of approximation errors. Stability analysis is conducted using appropriate Lyapunov functions and Barbalat's lemma. Simulations and experimental implementations demonstrate that the suggested approach achieves more accurate approximation of unknown models and complex nonlinearities, and exhibits good resistance against uncertainties and parameter variations.
NONLINEAR DYNAMICS
(2023)
Article
Mathematics, Applied
Patricia Ochoa, Cinthia Peraza, Oscar Castillo, Patricia Melin
Summary: This paper proposes a generalized type 2 fuzzy system to enhance the performance and convergence of differential evolution. It implemented a generalized type 2 Sugeno controller to optimize the trajectory of a robot and conducted an analysis of execution time and errors. Furthermore, a comparison with different levels of disturbance demonstrated the efficiency of the type 2 fuzzy system.
Article
Computer Science, Artificial Intelligence
Dhan Jeet Singh, Nishchal K. Verma, Ajoy Kanti Ghosh, Appasaheb Malagaudanavar
Summary: This article presents a systematic approach for designing IT3 T-S fuzzy logic systems using alpha-plane representation. The proposed system has better modeling capability than GT2 FLS and is more appealing when dealing with uncertain information or data. The computational cost is bearable and the method performs well in benchmark examples.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2022)
Article
Automation & Control Systems
Oscar Castillo, Juan R. Castro, Patricia Melin
Summary: This article proposes a mathematical definition for interval type-3 fuzzy sets, aiming to construct the theory needed for building interval type-3 fuzzy systems. The authors argue that type-2 fuzzy logic outperforms type-1 in situations with uncertainty, dynamics, or nonlinearity, and advocate exploring the new field of type-3 fuzzy logic. They also demonstrate the potential of interval type-3 in quality control and validate its effectiveness in handling uncertainty through comparison with human expert results.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Xiao Feng, Yongbin Yu, Xiangxiang Wang, Jingye Cai, Shouming Zhong, Hao Wang, Xinyi Han, Jingya Wang, Kaibo Shi
Summary: This article proposes a hybrid search mode-based differential evolution (HSM-DE) algorithm for the complex design of an interval type-2 fuzzy logic system (IT2FLS). The algorithm transforms the design processes of the IT2FLS into optimization problems and applies a memetic algorithm structure. The results show that the HSM-DE algorithm achieves high-performance control and outperforms comparative methods in the auto design of optimal IT2FLS.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Automation & Control Systems
Oscar Castillo, Juan R. Castro, Patricia Melin
Summary: This article proposes a method for predicting COVID-19 based on a combination of fractal theory and interval type-3 fuzzy logic. Fractal dimension is used to estimate the complexity level of time series, specifically in relation to the COVID-19 problem. Interval type-3 fuzzy logic is used to handle uncertainty in decision-making during the forecasting process. The hybrid approach incorporates an interval type-3 fuzzy model with fuzzy if-then rules using linear and non-linear values of dimension as inputs and COVID-19 case forecasts as outputs. The proposed method shows superior performance compared to previous methods in prediction.
INTERNATIONAL JOURNAL OF FUZZY SYSTEMS
(2023)
Article
Chemistry, Analytical
Hector Carreon-Ortiz, Fevrier Valdez, Patricia Melin, Oscar Castillo
Summary: Recurrent Neural Networks (RNN) are commonly used for time series and sequential data applications and are currently used in embedded devices. However, RNNs have the drawbacks of high computational cost and memory requirements. This article explores the use of Nonlinear Autoregressive Neural Networks (NARNN), a type of RNN, and applies the Discrete Mycorrhizal Optimization Algorithm (DMOA) to optimize the NARNN architecture. The proposed approach achieves good results when tested with the Mackey-Glass chaotic time series (MG), and comparisons with other methods like Backpropagation and ANFIS also yield positive outcomes. This algorithm has potential applications in various fields including robotics, microsystems, sensors, and 3D printing.
Article
Mathematics
Leticia Cervantes, Camilo Caraveo, Oscar Castillo
Summary: The aim of this study is to manage the health of people with type 1 diabetes by controlling the insulin dose in real time and under stressful situations. The results showed that the type-2 fuzzy controller was more stable and efficient in controlling insulin levels for patients with type 1 diabetes, especially in situations with increased levels of noise/stress.
Article
Mathematics, Applied
Patricia Ochoa, Cinthia Peraza, Oscar Castillo, Patricia Melin
Summary: This paper proposes a generalized type 2 fuzzy system to enhance the performance and convergence of differential evolution. It implemented a generalized type 2 Sugeno controller to optimize the trajectory of a robot and conducted an analysis of execution time and errors. Furthermore, a comparison with different levels of disturbance demonstrated the efficiency of the type 2 fuzzy system.
Article
Engineering, Aerospace
Fernando Serrano, Oscar Castillo, Madini Alassafi, Fawaz Alsaadi, Adil Ahmad
Summary: This paper presents the development of a quadrotor UAV control based on terminal sliding mode attitude-position quaternion. The dynamics of the UAV is divided into attitude and position loops, and hybrid terminal sliding mode and quaternion controller are implemented for each loop. The advantages of this control strategy include a relatively simple approach due to the use of quaternion based control and a reliable and fast attitude-position tracking. The control loops also incorporate feedforward neural networks as compensators to reduce tracking error.
ADVANCES IN SPACE RESEARCH
(2023)
Editorial Material
Engineering, Aerospace
Hadi Jahanshahi, Oscar Castillo
ADVANCES IN SPACE RESEARCH
(2023)
Article
Green & Sustainable Science & Technology
Gebrail Bekdas, Yaren Aydin, Umit Isikdag, Aidin Nobahar Sadeghifam, Sanghun Kim, Zong Woo Geem
Summary: The study aimed to develop models to predict the cooling load of low-rise tropical buildings based on their basic characteristics. Different machine learning algorithms were tested and the results showed that Histogram Gradient Boosting and Stacking models were the most accurate for predicting the cooling load.
Article
Green & Sustainable Science & Technology
Gebrail Bekdas, Celal Cakiroglu, Sanghun Kim, Zong Woo Geem
Summary: The optimal design of prestressed concrete cylindrical walls has significant economic and environmental benefits. The lack of sufficient training datasets for robust machine learning models has hindered the widespread use of machine learning techniques in structural design. This study demonstrates the application of the harmony search methodology to create a large database of optimal design configurations, and trains ensemble learning models to accurately predict the optimum wall thickness in prestressed concrete cylindrical wall design.
Editorial Material
Chemistry, Multidisciplinary
Zong Woo Geem, Seokwon Yeom, Euntai Kim, Myung-Geun Chun, Young-Jae Ryoo
APPLIED SCIENCES-BASEL
(2023)
Article
Chemistry, Multidisciplinary
Yaren Aydin, Gebrail Bekdas, Sinan Melih Nigdeli, Umit Isikdag, Sanghun Kim, Zong Woo Geem
Summary: CO2 emissions are a major environmental problem contributing to global warming. In order to prevent a potential climate crisis, this research proposes an engineering design solution to reduce CO2 emissions. The proposed solution includes an optimization-machine learning pipeline and a set of models trained to predict the design variables of an eco-friendly concrete column. The results indicate that the random forest algorithm outperforms other machine learning algorithms in terms of accuracy.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Artificial Intelligence
Patricia Ochoa, Cinthia Peraza, Oscar Castillo, Zong Woo Geem
Summary: The study aims to utilize shadowed type-2 fuzzy systems (ST2-FS) to dynamically adapt the crossing parameter of differential evolution (DE). The performance of the dynamic crossing parameter is evaluated through testing it on the motor position control problem, which involves an interval type-2 fuzzy system (IT2-FS) for motor control. A comparison is made between the original DE and the algorithm using shadowed type-2 fuzzy systems (DE-ST2-FS), as well as other state-of-the-art metaheuristics.
Article
Computer Science, Information Systems
Ilgin Gokasar, Dragan Pamucar, Muhammet Deveci, Brij B. Gupta, Luis Martinez, Oscar Castillo
Summary: Continuous, efficient, and sustainable collection of traffic data can be achieved through the use of self-powered sensors once connected autonomous vehicles (CAVs) are integrated into metaverse technology. The integration of metaverse self-powered sensors allows for uninterrupted data capture, enabling activities such as traffic network management, transportation facility optimization, and urban and intercity journey management. Additionally, the study of transportation systems in conjunction with the metaverse can enhance transportation efficiency and sustainability. This study prioritizes four alternatives of CAVs in the metaverse using a novel decision-making model that incorporates self-powered sensors.
INFORMATION SCIENCES
(2023)
Article
Mathematics, Applied
Ivette Miramontes, Patricia Melin
Summary: In this study, the adaptability of the Bird Swarm Algorithm was enhanced using General Type-2 Fuzzy Systems, resulting in significant improvements in two complex case studies. The findings demonstrate the promising potential of this integrated approach in addressing intricate optimization challenges in diverse domains.
Article
Mathematics, Applied
Martha Ramirez, Patricia Melin, Oscar Castillo
Summary: This study proposes a new hybrid-hierarchical model using unsupervised neural networks and type-3 fuzzy systems for the classification and prediction of country indicators. The method achieves separation and integration of multiple indicators by representing the hierarchy with neural networks and combining the results with a set of fuzzy systems.
Article
Mathematics, Applied
Patricia Melin, Oscar Castillo
Summary: This article presents a plant monitoring approach based on a hybrid mixture of type-3 fuzzy logic (T3FL) and the fractal dimension (FD). The combination of T3FL and FD is utilized to take advantage of their respective capabilities in solving the problem of monitoring a plant. The proposed approach outperforms previous methods in terms of performance, making it a significant contribution to the literature.