Effective project risk management (PRM) necessitates accurate prediction and actionable insights. Machine learning (ML) models improve risk assessment by uncovering complex patterns; however, their black-box nature limits interpretability, making it difficult for stakeholders to trust predictions. Traditional explainable artificial intelligence (XAI) methods highlight influential risk factors yet often fail to provide actionable recommendations, focusing on model behavior rather than practical interventions. Counterfactual explanations (CEs) aim to bridge this gap by suggesting modifications to risk factors or project conditions that could alter outcomes. However, existing CE methods in PRM often lack domain specificity, overlook interdependencies, and ignore temporal constraints, producing recommendations that are unrealistic or infeasible. To address these limitations, we propose Counterfactual Reasoning with Risk Temporal Knowledge Graph (CR-RTKG), a framework that integrates counterfactual reasoning with a Risk Temporal Knowledge Graph (RTKG) to improve interpretability and actionability of risk mitigation. The RTKG encodes domain knowledge, models causal dependencies and cascading effects, and classifies risks by temporal horizon, supporting prioritization based on urgency and systemic influence. By embedding stakeholder-defined constraints into a multi-objective optimization process, CR-RTKG generates context-sensitive and feasible counterfactuals. Unlike conventional methods, it aligns recommendations with real-world project constraints. Experimental results show that CR-RTKG achieves higher plausibility (96%) and feasibility (93%), outperforming baselines including Diverse Counterfactual Explanations (DiCE) and Flow-based Counterfactual Explanation (CeFlow).

Accurate wind power forecasting (WPF) is crucial for integrating renewable energy into power grids and optimizing energy management systems. However, existing forecasting methods often struggle to capture the complex temporal dynamics and nonlinear relationships inherent in wind power data. This paper introduces ASPEN-WIND (Adaptive Spectral and Self-supervised Predictive Network - Wind Integrated Neural Dynamics), a novel deep learning (DL) model for enhanced WPF. ASPEN-WIND combines an adaptive spectral block (ASB), an interactive convolution block (ICB), long short-term memory (LSTM) networks, and self-supervised learning. The ASB employs Fourier analysis to capture multi-scale temporal patterns and adaptively filter noise, while the ICB extracts complex spatial-temporal features. LSTM networks model long-term dependencies, and self-supervised pre-training improves the model’s ability to learn from limited labeled data. We evaluated ASPEN-WIND on multiple real-world wind farm datasets, demonstrating its superior performance compared to traditional and recent DL-based forecasting methods across various time horizons. The results, averaged over multiple runs (e.g., 10 runs with different random seeds), show significant improvements in forecasting accuracy, with average reductions in mean absolute error (MAE) and root mean square error (RMSE) of 5–8% and 8–12%, respectively.

This paper addresses the challenge of real-time control of multirotors subjected to partially known and unmodeled dynamics. A physics-informed Koopman operator framework is proposed, where the known physical dynamics and unknown residual effects are separated using a Strang splitting approach. The continuous-time Koopman operator is trained on physics-derived trajectories, while the discrete-time Koopman operator is learned from real-world trajectory data, enabling a data-efficient and globally linearizable model of the multirotor dynamics. The learned linear model is subsequently used to design a discrete-time Sequential Action Control (SAC) policy for real-time trajectory tracking. Experimental validation on a quadrotor platform tracking a lemniscate trajectory demonstrates that the proposed PI-EDMD-based SAC controller achieves superior tracking accuracy and up to 67% lower control energy consumption compared to baseline nonlinear SAC and LQR controllers. These results highlight the effectiveness of the proposed framework in enhancing both trajectory fidelity and actuation efficiency for multirotors.

In high-stakes project risk assessment, balancing predictive accuracy with interpretability is critical to fostering stakeholder trust and supporting well-informed decision-making. This study presents the Interpretable Risk Assessment Framework with Belief Rule-Based Systems (IRAF-BRB), an Explainable AI (XAI) framework specifically designed to improve transparency, accountability, and accuracy in risk assessment. IRAF-BRB combines Interpretive Structural Modeling (ISM) to map and analyze interdependencies among risk factors with an optimized Belief Rule-Based (BRB) model. A modified Differential Evolution Covariance Matrix Self-Adaptation (DECMSA) algorithm is employed to enhance the predictive power of the BRB model while preserving interpretability, ensuring that stakeholders can both trust and understand the model’s outputs. By transforming complex risk data into intuitive visualizations, the IRAF-BRB framework enables project managers to identify key risk drivers and anticipate cascading effects, leading to proactive risk mitigation. Experimental results demonstrate that IRAF-BRB reduces Mean Squared Error (MSE) to 4.09 e − 4 in predicting risk levels for high-rise construction projects, outperforming traditional BRB models such as Differential Evolution-based BRB (DE-BRB) ( 8.29 e − 4 ) and Particle Swarm Optimization-based BRB (PSO-BRB) ( 2.53 e − 3 ) . The statistical significance of these results was confirmed via a two-sample t-test ( p < 0.05 ) , establishing IRAF-BRB as a reliable and effective tool for accurate and interpretable risk assessment.

With the arrival of deep learning and advanced sensor technologies, the autonomous vehicle domain has gained increased research interest. In particular, deep learning networks developed based on 3D LiDAR sensing data for perception and planning in autonomous vehicles demonstrate remarkable performance. However, recent research reveals vulnerabilities in LiDAR-based perception tasks, such as 3D object detection and segmentation, to intentionally crafted adversarial perturbations. Yet, the adversarial robustness of LiDAR-based regression tasks like scene flow estimation, remains largely unexplored. Therefore, this study introduces a novel point perturbation attack named FlowCraft, based on two loss functions, along with a critical analysis of selecting the adversarial objective against scene flow estimation. In particular, evaluations are conducted on trainable, runtime optimization, supervised, and self-supervised, scene flow estimation methods using the Argoverse 2 and Waymo datasets in both black-box and white-box settings. Experimental results on the Argoverse 2 benchmark dataset and the DeFlow network show that FlowCraft achieves a relative endpoint error increment of 2.9, while demonstrating a higher endpoint error increase of 5.5 per unit change in Chamfer Distance compared to PGD and CosPGD attacks. Furthermore, our results demonstrate that the performance of point perturbation attacks against runtime optimization methods involves a trade-off between their success rate and overall imperceptibility. • Explain why adding perturbations to the point cloud at t=t+1 is more effective for evaluations. • Introduce the FlowCraft attack against scene flow estimation, which is based on dual loss functions. • The white-box version of the FlowCraft attack against the DeFlow network on the Argoverse 2 dataset achieves a relative endpoint error increment of 2.9, and a relative endpoint error increment of 1.7 on the Waymo dataset. • Evaluate the black-box transferability of FlowCraft against supervised, self-supervised methods, trainable and run-time optimization-based methods, using the Argoverse 2 and Waymo datasets. • FlowCraft outperforms PGD and CosPGD attacks in terms of attack effectiveness and imperceptibility under trainable approaches.

This study introduces a dynamics-driven visual servoing methodology tailored for an over-actuated quadrotor equipped with tilting rotors. The mathematical framework encompasses both translational and rotational dynamics, incorporating the tilting rotor angles to facilitate autonomous control over attitude and position. The stereo camera model is derived utilizing stacked Jacobians. The proposed dynamics-driven methodology establishes a direct correspondence between the dynamics of image pixel accelerations captured by the stereo cameras and the thrust and torque commands of the over-actuated tilting quadrotor. This obviates the necessity for computationally intensive inverse Jacobian computations typically required in traditional visual servoing methods. By employing an over-actuated tilting rotor configuration instead of a conventional quadrotor setup, the dynamics-driven approach surmounts limitations in independently controlling the pose and attitude. It enables the tracking of not only the 3D position but also the orientation of points of interest using the onboard stereo cameras. Simulation outcomes affirm the efficacy of the approach in achieving precise visual tracking.

LiDAR-based 3D perception is a focal point in autonomous vehicle research due to its efficacy in real-world environments and falling costs. However, recent research reveals challenges with LiDAR sensing under corruptions that occur due to adverse weather conditions and sensor-level errors, known as common corruptions. In particular, the majority of these corruptions lead to sparsity or noise in LiDAR point clouds, degrading the performance of downstream perception tasks. To address this, we propose a blind inpainting method named 3DR-DIFF, utilizing diffusion networks to reconstruct and segment corrupted point clouds. 3DR-DIFF comprises two key components: a corrupted region prediction network, acting as a binary mask predictor, and a conditional diffusion network. The evaluation results demonstrate that the 3DR-DIFF is able to reconstruct the LiDAR samples with a depth error of less than 0.56 mean absolute error (MAE) and an intensity error of 0.02 MAE, along with an average segmentation performance of 0.43 mean intersection over union. Furthermore, benchmarking results highlight that 3DR-DIFF outperforms state-of-the-art methods in reconstructing LiDAR beam-missing scenarios, exhibiting an approximately 9.2% lower error for a degradation of 1 MAE.

Deep learning methods, specifically convolutional neural networks (CNNs), have achieved state-of-the-art in various tasks including image classification. However, the computational and memory requirements of advanced CNNs like ResNet-50 pose deployment challenges, particularly in resource-constrained environments. Our study introduces a new lightweight approach, namely ResNet-Lite, for image classification. It combines knowledge distillation and network tuning along with hyperparameter tuning techniques to overcome deployment barriers. ResNet-Lite involves the extracting of knowledge from a pre-trained ResNet-50 network and transferring it to a smaller network, creating a more compact and effective approach. After that, hyperparameter and network tuning have been applied to determine the optimal combination of parameters that maximizes the generalization and performance of the model. Our experimental results demonstrate that ResNet-Lite achieves a significantly reduced model size while maintaining competitive classification performance. Specifically, it outperforms the original ResNet-50 model by 5.40% and by 7.13% in accuracy on the CIFAR-10 and Fashion-MNIST datasets, respectively. In summary, our study provides a practical solution for developing high-performance image classification models, even in resource-constrained environments, contributing to the field of advanced deep learning.

This paper presents a robust decentralised control approach for modular aerial parcel delivery using persistently excited physics-informed neural networks (PE-PINNs). The proposed method enables each propeller module to independently generate control efforts based solely on its local state information and that of its 1-hop neighbors, without requiring global system knowledge. The PE-PINN is trained to approximate the optimal centralized control policy by incorporating the nominal system dynamics and accounting for modeling uncertainties. Key innovations include estimating the Lipschitz constant to ensure persistent excitation during training, and a decentralised control formulation that minimizes the difference between the learned and optimal control efforts. Experimental results on a modular aerial testbed demonstrate the PE-PINN's ability to achieve high-accuracy fixed-point hover and trajectory tracking performance, outperforming a prior decentralised control approach by 8.57% and 24.17% respectively. The proposed framework enables scalable and robust control of modular aerial systems for parcel delivery applications.

Mission Planning for Multi-Uncrewed Ground Vehicle (multi-UGV) missions is a key functional module for achieving effective autonomy and coordination within a fleet of vehicles. However, the complexity of mission planning is compounded by the interconnected sub-problems involved and the challenging environments encountered by UGVs. Aiming to devise efficient and effective techniques to tackle the intricacies of mission planning in complex and cluttered environments, this paper presents an algorithmic architecture tailored for hierarchical multi-UGV mission planning systems. Specifically, this paper designs a Modified Cost Approximation Method integrated with two-layer environmental modelling for fast estimation of the travelling cost graphs of target points. A Hybrid Clustering Method that merges k-means clustering with a marginal cost-based assignment is proposed to streamline task decomposition and task assignment. Furthermore, a three-layer path planner is developed by integrating A*, post-processing steps, and Multi-operator Continuous Ant Colony optimisation, aiming to find paths with reduced cost for UGVs in challenging terrains. To evaluate the proposed techniques, a benchmark set for multi-UGV mission planning problems is designed using the robotic simulation platform CoppeliaSim. Simulation results demonstrate the superior performance of the proposed planning techniques.

This article presents a visual servoing strategy that integrates the capabilities of a physics-informed neural network (PINN) to estimate system uncertainties and inaccuracies with a dynamics-centered visual servoing technique for multirotors. The proposed method effectively combines these approaches, eliminating the need for inverse Jacobian calculations to determine multirotor motion by directly relating pixel variations to the multirotor's torque and thrust inputs, while also strengthening the method's robustness through the utilization of the PINN to model and address uncertainties in camera and multirotor parameters, as well as the modeling inaccuracies inherent in the dynamics-centered visual servoing technique. In contrast to existing state-of-the-art data-driven approaches, the proposed PINN approach requires, on average, 65% less labeled data to characterize uncertainties and inaccuracies. To ensure real-time implementation of the visual servoing model, the PINN-learned model is combined with an adaptive horizon monotonically weighted nonlinear model predictive controller (NMPC), capable of processing control efforts at rates 10 times faster than existing Tube MPC and Adaptive MPC strategies. These findings are validated through real-time trajectory tracking experiments, which not only highlight the effectiveness of the proposed approach in approximating modeling inaccuracies but also its capability in handling uncertainties upto 70% in camera parameters.

Ensuring robust and precise tracking control in the presence of uncertain multi-input-multi-output (MIMO) system dynamics and environmental variations is a significant challenge in the field of robust and adaptive control theory. While fuzzy control strategies have demonstrated good tracking performance in normal conditions, designing and tuning fuzzy controllers can be a challenging task in highly uncertain environments. In this study, we investigate a novel approach that combines robust nonlinear negative-imaginary (NI) systems theory with a self-adaptive fuzzy control scheme and the Lyapunov synthesis to develop a robust adaptive negative-imaginary-fuzzy (RANIF) control scheme. We optimize the critical parameters of the proposed fuzzy system using a self-tuning technique with a proportional-derivative sliding manifold. Furthermore, unlike the existing adaptive fuzzy control methods, we propose a small number of membership functions and systematically derive the fuzzy rules by employing Lyapunov, nonlinear NI, and dissipativity theories, which simplify the tuning process, work out the matter of "explosion of complexity," and reduce computational complexity. We demonstrate the global stability of the closed-loop system using nonlinear NI theory. To evaluate the effectiveness of our proposed approach, we present simulation results for two examples involving uncertain MIMO second-order Euler-Lagrange systems. These systems, known for their capacity to represent a diverse range of practical physical systems, serve as suitable testbeds for our methodology. Our results show that RANIF outperforms other control methods, such as nonlinear strictly NI-Fuzzy, fuzzy-logic control, model predictive control, and conventional PID control, in terms of robustness to disturbances and inestimable faults, trajectory tracking performance, and computational complexity.

At present the perception system of autonomous vehicles is grounded on 3D vision technologies along with deep learning to process depth information. Although deep learning models for 3D perception give promising results, recent research demonstrates that they are also vulnerable to adversarial attacks similar to deep learning models trained on 2D images. As a result, it is essential to further explore the vulnerabilities of 3D perception models in autonomous vehicles and find methods to cope with the risks associated with these adversarial vulnerabilities, in order to improve the social acceptance of commercial autonomous vehicles. This study aims to provide an in-depth overview of the recent adversarial attacks and countermeasures against 3D perception models on autonomous vehicles. Further, challenges associated with the research domain and future research directions are highlighted to make autonomous vehicles robust against adversarial attacks.

The main objective of this study is to propose an enhanced wind power forecasting (EWPF) transformer model for handling power grid operations and boosting power market competition. It helps reliable large-scale integration of wind power relies in large part on accurate wind power forecasting (WPF). The proposed model is evaluated for single-step and multi-step WPF, and compared with gated recurrent unit (GRU) and long short-term memory (LSTM) models on a wind power dataset. The results of the study indicate that the proposed EWPF transformer model outperforms conventional recurrent neural network (RNN) models in terms of time-series forecasting accuracy. In particular, the results reveal a minimum performance improvement of 5% and a maximum of 20% compared to LSTM and GRU. These results indicate that the EWPF transformer model provides a promising alternative for wind power forecasting and has the potential to significantly improve the precision of WPF. The findings of this study have implications for energy producers and researchers in the field of WPF.

In this article, a novel version of the general regression neural network (Imp_GRNN) is developed to control a class of multiinput and multioutput (MIMO) nonlinear discrete-time (DT) systems. The improvements retain the features of the original GRNN along with a significant improvement of the control accuracy. The enhancements include developing a method to set the input-hidden weights of GRNN using the inputs recursive statistical means, introducing a new output layer and adaptable forward weighted connections from the inputs to the new layer, and suggesting an interval-type smoothing parameter to eradicate the need for selecting the parameter beforehand or adapting it online. Also, controller stability is studied using Lyapunov's method for DT systems. The controller performance is tested with different simulation examples and compared with the original GRNN to verify its superiority over it. Also, Imp_GRNN performance is compared with an adaptive radial basis function network controller, an adaptive feedforward neural-network (NN) controller, and a proportional-integral-derivative (PID) controller, where it demonstrated higher accuracy in comparison with them. In comparison with the formerly proposed control methods for MIMO DT systems, our controller is capable of producing high control accuracy while it is model free, does not require complex mathematics, has low computational complexity, and can be utilized for a wide range of DT dynamic systems. Also, it is one of the few methods that aims to improve the control system accuracy by improving the NN structure.

Quadrotors are one of the popular unmanned aerial vehicles (UAVs) due to their versatility and simple design. However, the tuning of gains for quadrotor flight controllers can be laborious, and accurately stable control of trajectories can be difficult to maintain under exogenous disturbances and uncertain system parameters. This article introduces a novel robust adaptive control synthesis methodology for a quadrotor robot's attitude and altitude stabilization. The proposed method is based on the fuzzy reinforcement learning and strictly negative imaginary (SNI) property. The first stage of our control approach is to transform a nonlinear quadrotor system into an equivalent negative-imaginary (NI) linear model by means of the feedback linearization (FL) technique. The second phase is to design a control scheme that adapts online the SNI controller gains via fuzzy Q -learning. The performance of the designed controller is compared with that of a fixed-gain SNI controller, a fuzzy-SNI controller, and a conventional PID controller in a series of numerical simulations. Furthermore, the proofs for the stability of the proposed controller and the adaptive laws are provided using the NI theorem.

This paper proposes an innovative approach to coverage path planning and obstacle avoidance for multiple Unmanned Ground Vehicles (UGVs) in a changing environment, taking into account constraints on the time, path length, number of UGVs and obstacles. Our approach leverages deformable virtual leader-follower formations to enable UGVs to adapt their formation based on both planned and real-time sensor data. A hierarchical block algorithm is employed to identify areas in the environment where UGV formations can spread out to meet time and budget constraints. Additionally, we introduce a novel control scheme that allows each UGV to generate a local steering force to dodge any static and mobile obstacles based on the closest safe angle. Results from simulations and real UGV experiments demonstrate that our approach achieves a higher coverage percentage than rule-based and reactive swarming approaches without planning. Our approach offers a promising solution for efficient coverage path planning and obstacle avoidance in complex environments with multiple UGVs.

Monocular depth estimation is an important task that can be applied to many robotic applications. Existing methods focus on improving depth estimation accuracy via training increasingly deeper and wider networks, however these suffer from large computational complexity. Recent studies found that edge information are important cues for convolutional neural networks (CNNs) to estimate depth. Inspired by the above observations, we present a novel lightweight Edge Guided Depth Estimation Network (EGD-Net) in this study. In particular, we start out with a lightweight encoder-decoder architecture and embed an edge guidance branch which takes as input image gradients and multi-scale feature maps from the backbone to learn the edge attention features. In order to aggregate the context information and edge attention features, we design a transformer-based feature aggregation module (TRFA). TRFA captures the long-range dependencies between the context information and edge attention features through cross-attention mechanism. We perform extensive experiments on the NYU depth v2 dataset. Experimental results show that the proposed method runs about 96 fps on a Nvidia GTX 1080 GPU whilst achieving the state-of-the-art performance in terms of accuracy.

In real world scenarios, out-of-distribution (OOD) datasets may have a large distributional shift from training datasets. This phenomena generally occurs when a trained classifier is deployed on varying dynamic environments, which causes a significant drop in performance. To tackle this issue, we are proposing an end-to-end deep multi-task network in this work. Observing a strong relationship between rotation prediction (self-supervised) accuracy and semantic classification accuracy on OOD tasks, we introduce an additional auxiliary classification head in our multi-task network along with semantic classification and rotation prediction head. To observe the influence of this addition classifier in improving the rotation prediction head, our proposed learning method is framed into bi-level optimisation problem where the upper-level is trained to update the parameters for semantic classification and rotation prediction head. In the lower-level optimisation, only the auxiliary classification head is updated through semantic classification head by fixing the parameters of the semantic classification head. The proposed method has been validated through three unseen OOD datasets where it exhibits a clear improvement in semantic classification accuracy than other two baseline methods. Our code is available on GitHub https://github.com/harshita-555/OSSL

Many real-world classification problems have imbalanced frequency of class labels; a well-known issue known as the "class imbalance" problem. Classic classification algorithms tend to be biased towards the majority class, leaving the classifier vulnerable to misclassification of the minority class. While the literature is rich with methods to fix this problem, as the dimensionality of the problem increases, many of these methods do not scale-up and the cost of running them become prohibitive. In this paper, we present an end-to-end deep generative classifier. We propose a domain-constraint autoencoder to preserve the latent-space as prior for a generator, which is then used to play an adversarial game with two other deep networks, a discriminator and a classifier. Extensive experiments are carried out on three different multi-class imbalanced problems and a comparison with state-of-the-art methods. Experimental results confirmed the superiority of our method over popular algorithms in handling high-dimensional imbalanced classification problems. Our code is available on https://github.com/TanmDL/SLPPL-GAN

We propose a three-player spectral generative adversarial network (GAN) architecture to afford GAN the ability to manage minority classes under imbalanced conditions. A class-dependent mixture generator spectral GAN (MGSGAN) was developed to force generated samples to remain within the actual distribution of the data. MGSGAN was able to generate minority classes, even when the imbalanced ratio of majority to minority classes was high. A classifier based on lower features was adopted along with a sequential discriminator to develop a three-player GAN game. The generative networks performed data augmentation to improve the classifier ’ s performance. The proposed method was validated using two hyperspectral image data sets and compared with state-of-the-art methods in two class-imbalanced settings corresponding with real data distributions.

As an essential component for many autonomous driving and robotic activities such as ego-motion estimation, obstacle avoidance and scene understanding, monocular depth estimation (MDE) has attracted great attention from the computer vision and robotics communities. Over the past decades, a large number of methods have been developed. To the best of our knowledge, however, there is not a comprehensive survey of MDE. This paper aims to bridge this gap by reviewing 197 relevant articles published between 1970 and 2021. In particular, we provide a comprehensive survey of MDE covering various methods, introduce the popular performance evaluation metrics and summarize publically available datasets. We also summarize available open-source implementations of some representative methods and compare their performances. Furthermore, we review the application of MDE in some important robotic tasks. Finally, we conclude this paper by presenting some promising directions for future research. This survey is expected to assist readers to navigate this research field.

Depth estimation from a single RGB image has attracted great interest in autonomous driving and robotics. State-of-the-art methods are usually designed on top of complex and extremely deep network architectures, which require more computational resources. Moreover, the inherent characteristic of the backbone used by the existing approaches results in severe spatial information loss in the produced feature maps, which impairs the accuracy of depth estimation on small sized images. In this study, we aimed to design a novel and efficient Convolutional Neural Network (CNN) to address these problems. Specifically, we stacked two shallow encoder-decoder style subnetworks successively in a unified network. Extensive experiments have been conducted on the NYU depth v2, KITTI, Make3D and Unreal data sets. Experimental results show that the proposed network achieves comparable accuracy to state-of-the-art methods that have extremely deep architectures but runs at a much faster speed on a single, less powerful GPU.

Recently, Type-2 fuzzy systems have become increasingly prominent as they have been applied to various nonlinear control applications. This article presents an adaptive fuzzy controller based on the sliding-mode control theory. The proposed self-adaptive interval Type-2 fuzzy controller (SAF2C) is based on the Takagi–Sugeno (TS) fuzzy model and it accommodates the “enhanced iterative algorithm with stop condition” type-reducer, which is more computationally efficient than the “Kernel–Mendel” type-reduction algorithm. We developed an integrated multi-input–multi-output (MIMO) SAF2C-controller to reduce the computation time so that we can expedite the learning process of our control algorithm by 80% compared to separate single-input–single-output (SISO) controllers. The stability of our controller is proven using the Lyapunov technique. To ensure the applicability of the presented control scheme, we implemented our controller on various nonlinear systems, including a hexacopter unmanned aerial vehicle (UAV). We also compare the accuracy of our controller with a conventional proportional–integral–derivative autopilot system. Our research indicates around 20% improvement in its transient response, in addition to achieving a better noise rejection capability with respect to a Type-1 fuzzy counterpart.

Traditional oversampling methods are generally employed to handle class imbalance in datasets. This oversampling approach is independent of the classifier; thus, it does not offer an end-to-end solution. To overcome this, we propose a three-player adversarial game-based end-to-end method, where a domain-constraints mixture of generators, a discriminator, and a multi-class classifier are used. Rather than adversarial minority oversampling, we propose an adversarial oversampling (AO) and a data-space oversampling (DO) approach. In AO, the generator updates by fooling both the classifier and discriminator, however, in DO, it updates by favoring the classifier and fooling the discriminator. While updating the classifier, it considers both the real and synthetically generated samples in AO. But, in DO, it favors the real samples and fools the subset class-specific generated samples. To mitigate the biases of a classifier towards the majority class, minority samples are over-sampled at a fractional rate. Such implementation is shown to provide more robust classification boundaries. The effectiveness of our proposed method has been validated with high-dimensional, highly imbalanced and large-scale multi-class tabular datasets. The results as measured by average class specific accuracy (ACSA) clearly indicate that the proposed method provides better classification accuracy (improvement in the range of 0.7% to 49.27%) as compared to the baseline classifier

Considerable progress has been made in improving the estimation accuracy of cognitive workload using various sensor technologies. However, the overall performance of different algorithms and methods remain suboptimal in real-world applications. Some studies in the literature demonstrate that a single modality is sufficient to estimate cognitive workload. These studies are limited to controlled settings, a scenario that is significantly different from the real world where data gets corrupted, interrupted, and delayed. In such situations, the use of multiple modalities is needed. Multimodal fusion approaches have been successful in other domains, such as wireless-sensor networks, in addressing single-sensor weaknesses and improving information quality/accuracy. These approaches are inherently more reliable when a data source is lost. In the cognitive workload literature, sensors, such as electroencephalography (EEG), electrocardiography (ECG), and eye tracking, have shown success in estimating the aspects of cognitive workload. Multimodal approaches that combine data from several sensors together can be more robust for real-time measurement of cognitive workload. In this article, we review the published studies related to multimodal data fusion to estimate the cognitive workload and synthesize their main findings. We identify the opportunities for designing better multimodal fusion systems for cognitive workload modeling.

Formation control techniques have been widely implemented in networked multirobot systems. In this article, we present a novel framework for swarm multiagent systems based on the relative-position output feedback consensus supported with the new concept of adaptive strictly negative imaginary consensus controllers, leveraging the learning capability of artificial neural networks. For experimental validation, we consider the case of two quadcopters moving together while carrying a dynamic load. We employ Kharitonov's theorem to study the stability of the proposed adaptive control systems. Finally, a rigorous real-time experimental study is conducted to highlight the merits of the proposed formation control algorithms.

This paper presents a three-layered approach for the mission route planning problems involving a team of autonomous vehicles where they have to collectively navigate to a number of target locations in an environment with both static and dynamic obstacles. The first layer computes the maximum distance that need to be traveled to complete a mission by a team of vehicles. We have developed a nearest-neighbor-search based approach to assign closely located tasks to each vehicle in the team. We developed a stochastic optimization based path planning algorithm that can compute the collision-free (with both static and dynamic obstacles) trajectory for a vehicle to navigate from start to the target location. By combining task assignment with path planning algorithm, we can estimate the maximum traveled distance for a mission with a team of vehicles. The second layer determines the optimal number of vehicles required for a mission based on any user defined constraint by casting it as a multiobjective optimization problem with two competing objectives, i.e. time vs cost. The methods derived in layer one are utilized to evaluate the objective functions in layer two. Finally, we have proposed a data driven neural network-based prediction model that will forecast the mission completion time with a reasonable accuracy which will utilize the historical information of the previous missions. The forecasting model is intended to facilitate the effective planning of parallel and subsequent missions. We have demonstrated the effectiveness of our approach with numerical simulation results for every layer mentioned above.

Finding synergy between a variety of control and estimation approaches can lead to effective solutions for controlling nonlinear dynamic systems in an efficient and systematic manner. In this paper, a novel controller design consisting of generalized regression neural networks (GRNNs) and sliding mode control (SMC) is proposed to control nonlinear multi-input and multi-output (MIMO) dynamic systems. The proposed design transforms GRNN from an offline regression model to an online adaptive controller. The suggested controller does not require any pretraining and it learns quickly from scratch. It uses a low computational complexity algorithm to provide accurate and stable performance. The proposed controller (GRNNSMC) performance is verified with a generic MIMO nonlinear dynamic system and a hexacopter model with a variable center of gravity. The results are compared with the standard PID controller. In addition, the stability of the GRNNSMC controller is verified using the Lyapunov stability method.

This paper presents a hybrid nonlinear control system, comprising of a conventional proportional-differential (PD) controller and a PD-type fuzzy logic autopilot for the trajectory tracking of a quadcopter drone. Given the inherent nature of traditional control, which is model-based, and the essence of fuzzy logic control, which is knowledge-based, the proposed hybrid controllers can provide a more robust solution in the face of uncertainties. Both controllers operate in a parallel incremental form to improve the transient performance and the robustness of the closed-loop control system. Through extensive computer simulations supported by real-time flight tests, this paper highlights the efficacy of the proposed hybrid control system in the presence of some parameter variations, nonlinear aerodynamic models, and some external disturbances (e.g., wind gusts). The Dryden and 1-cos turbulence models are employed to represent the effects of wind gusts under realistic flight environments. The stability analysis of the closed-loop control system is conducted using Lyapunov's indirect method.

We introduce a new configuration of a robust and adaptive autopilot system for a model-scale flapping-wing aircraft. The system is specifically designed to achieve high performance flapping angle tracking in the face of large uncertainties. To describe the dynamics of the system, we leverage the benefits of both first principle modeling and data-driven approach (system identification technique). We introduce a high-performance robust and adaptive nonlinear control system by means of a feedback linearization (FL) technique, supported with an interval Type-2 fuzzy system due to its ability to accommodate the footprint-of-uncertainties (FoUs). While the first stage of our nonlinear control system is to cancel some predictable nonlinearities using an FL technique, the second phase of control is to accommodate the existing uncertainties in the system by way of an interval Type-2 fuzzy control technique, e.g., due to imperfect cancelation and modeling errors. This way, the stability and the robustness of the closed-loop control system can be guaranteed. We quantify the relative merit of our hybrid control system with respect to an FL technique, supported with a fixed gain state feedback controller and a Type-1 fuzzy system. Lastly, we also conduct stability analysis of the overall closed-loop control system.

A critical issue in evolutionary robotics is the transfer of controllers learned in simulation to reality. This is especially the case for small Unmanned Aerial Vehicles (UAVs), as the platforms are highly dynamic and susceptible to breakage. Previous approaches often require simulation models with a high level of accuracy, otherwise significant errors may arise when the well-designed controller is being deployed onto the targeted platform. Here we try to overcome the transfer problem from a different perspective, by designing a spiking neurocontroller which uses synaptic plasticity to cross the reality gap via online adaptation. Through a set of experiments we show that the evolved plastic spiking controller can maintain its functionality by self-adapting to model changes that take place after evolutionary training, and consequently exhibit better performance than its non-plastic counterpart.

Swarm guidance, such as the case of guiding a group of sheep away from a field, is a challenging task. As the swarm size increases, it becomes necessary that multiple control points, or sheepdogs, are needed to guide the swarm. In this paper, a swarm of unmanned aerial vehicles (UAVs) acts as a moving safety network (aka a formation) that not only guides the sheep swarm, but also prevents them from dispersing or reversing to the other side of the field. We investigate two types of formations. The first type acts as a baseline, maintains fixed distances from the sheep swarm, and relies on fixed predefined angular structure relative to the sheep's global centre of mass (GCM). The second type is dynamic, where the force vector to control the UAV and the individual distance of each UAV from the sheep's GCM are controlled by a Perceptron, with the weights optimized by a particle swarm optimization algorithm. We evolve five Perceptrons to specialize in relative positions in the formation, which fixes the space cost for the optimization algorithm, while allowing the size of the swarm of UAVs to scale up. We demonstrate that the use of Perceptron-networks for dynamic control scheme reduces the total distance travelled by the UAVs, is transparent when interpreted with Hinton diagrams, and transferable to a larger number of UAVs.

In recent times, with the incremental demand for fully autonomous systems, research interests are observed in learning machine-based intelligent, self-organizing, and evolving controllers. In this paper, a new evolving and self-organizing controller, namely generic-controller (G-controller), is proposed. The G-controller works in a fully online mode with minor expert domain knowledge. It is developed by incorporating the sliding mode control (SMC) theory with an advanced incremental learning machine, namely generic evolving neuro-fuzzy inference system. The controller starts operating from scratch with an empty set of fuzzy rule, and therefore, no offline training is required. To cope with the changing dynamic characteristics of the plant, the controller can add or prune the rules on demand. Control law and adaptation laws for the consequent parameters are derived from the SMC algorithm to establish a stable closed-loop system, where the stability of the G-controller is guaranteed by using the Lyapunov function. The uniform asymptotic convergence of tracking error to zero is witnessed through the implication of an auxiliary robustifying control term. In addition, the implementation of the multivariate Gaussian function helps the controller to handle the nonaxis parallel data from the plant and consequently, enhances the robustness against uncertainties and environmental perturbations. Finally, the controller's performance has been evaluated by observing the tracking performance in controlling simulated plants of unmanned aerial vehicle, namely bio-inspired flapping wing micro air vehicle and hexacopter for a variety of trajectories.

We introduce a new nonlinear system identification technique, leveraging the benefits of the Type-2 Evolutionary Takagi-Sugeno (T2-ETS) fuzzy system. The major advantage of our proposed system identification technique is mainly due to its ability to learn-from-scratch while accommodating the footprint-of-uncertainties (FoUs). To support its mission to achieve a reasonably high prediction accuracy for uncertain nonlinear dynamic systems, we also introduce a new type reduction method to convert Type-2 fuzzy systems into their Type-1 counterparts. As a part of its efficient pruning strategy, the proposed system incorporates the concept of information entropy to avoid over fitting, which is a highly undesirable issue in modeling. We demonstrate the effectiveness of our system identification technique in achieving a delicate balance between minimizing the complexity of the acquired fuzzy model and maximizing the prediction accuracy. To highlight the efficacy of our algorithm, we employ a set of challenging pH neutralization data, known for its substantial nonlinearity, in addition to the dynamics of a nonlinear mechanical system. We conclude our research by conducting a rigorous comparative study to quantify the relative merits of our proposed technique with respect to the previous ETS algorithm (as its predecessor), the well-known KM-type reduction technique, and the higher-order discrete transfer functions, widely implemented in most conventional mathematical modeling techniques.

In this article, a novel self-evolving general regression neural network (SEGRNN) is designed for tracking control of a class of discrete-time dynamic systems with unknown dynamics and unknown external disturbances. The proposed controller starts from scratch and automatically adjusts its structure and parameters online to solve the tracking control problem. The proposed controller can add, prune, and replace nodes online according to the control task, external disturbance, and the design specifications. A robustifying control term is also added to SEGRNN's output to mitigate the effects of the external disturbance. The concept of a data reservoir is proposed where a record of the deleted nodes is stored for any future recall, if they are seen to be significant again. Unlike most of the previously proposed self-evolving systems, our controller offers user-friendly design parameters to suit a variety of real-world systems. Lyapunov stability analysis is utilized to study the stability of the suggested controller and to determine an appropriate learning rate for the SEGRNN weights. A continuous stirred-tank reactor simulation example is employed to verify the performance of the proposed controller. The performance of the proposed controller is also compared with a variety of controllers, including adaptive radial basis functional networks, adaptive feed-forward neural networks, adaptive fuzzy logic system, proportional integral derivative controller, sliding-mode controller, and iterative learning controller. Finally, a dc motor platform is used to experimentally validate the controller performance.

Robustness in the face of uncertainties is an important aspect in designing high performance control systems. This paper addresses the problem of accurate trajectory tracking of a small quadcopter unmanned aerial vehicle in the face of uncertainties. Accommodating the worst-case scenario, we propose a hybrid feedback and feedforward autopilot that has the capability to eliminate the cross-coupling disturbance between the lateral and the longitudinal loops with respect to the vertical loop as well as external disturbances (e.g., wind gusts). The proposed control system leverages on the technical benefits of both the nonlinear model predictive control and the fuzzy feedforward compensator. We highlight the efficacy of our hybrid autopilot system with respect to the performance of the conventional PD control systems through rigorous comparative studies. We also present stability analysis of our hybrid control system.

Interval Type-2 fuzzy controllers have become increasingly popular, and have been applied in many engineering applications over the past few decades. In this paper, a knowledge-based interval Type-2 fuzzy controller is proposed to control an inverted pendulum on a cart system in the presence of disturbance, random noise and parameter variations. The proposed controller utilizes the Takagi-Sugeno fuzzy inference system, supported by the Nie-Tan (NT) type-reduction method for the input-output mapping. The adaptation laws for the Type-2 fuzzy consequent parameters are derived based on the sliding mode control (SMC) theory. A comparison study of the proposed interval Type-2 fuzzy controller with a conventional PID controller is investigated in the presence of disturbance, external noise and parameter variations. Simulation results show the efficacy of the proposed controller with respect to a conventional PID controller as indicated by lower RMSE values.

In this work, a simple evolving neuro-fuzzy system with less learning parameters is utilized to develop an intelligent controller namely Reduced Parsimonious Controller (RedPAC). The proposed RedPAC is a simplified version of one of the recently developed intelligent controller called Parsimonious Controller (PAC). In RedPAC, the network parameters are reduced into two steps. Firstly, unlike the conventional fuzzy logic or neuro-fuzzy-based intelligent controller, it has no premise parameters. Secondly, in contrast with PAC, the number of consequent parameters have further reduced to one parameter per rule in RedPAC. The sliding mode control (SMC) technique is utilized to adapt consequent parameters of RedPAC, where the SMC-based auxiliary robustifying control term has guaranteed the uniform asymptotic convergence of tracking error to zero. The proposed controller's performance has been evaluated by implementing it to control a quadcopter unmanned aerial vehicle (UAV) simulator namely Dronekit. In addition, trajectory tracking performance of the quadcopter is compared with three different benchmark controllers namely a linear PID, a nonlinear SMC, and an intelligent controller called PAC. RedPAC outperforms PID and SMC techniques. The results of tracking trajectories are also comparable to PAC; however, RedPAC needs comparatively less learning parameters to obtain a similar or better tracking accuracy.

Data stream has been the underlying challenge in the age of big data because it calls for real-time data processing with the absence of a retraining process and/or an iterative learning approach. In the realm of the fuzzy system community, data stream is handled by algorithmic development of self-adaptive neuro-fuzzy systems (SANFS) characterized by the single-pass learning mode and the open structure property that enables effective handling of fast and rapidly changing natures of data streams. The underlying bottleneck of SANFSs lies in its design principle, which involves a high number of free parameters (rule premise and rule consequent) to be adapted in the training process. This figure can even double in the case of the type-2 fuzzy system. In this paper, a novel SANFS, namely parsimonious learning machine (PALM), is proposed. PALM features utilization of a new type of fuzzy rule based on the concept of hyperplane clustering, which significantly reduces the number of network parameters because it has no rule premise parameters. PALM is proposed in both type-1 and type-2 fuzzy systems where all of which characterize a fully dynamic rule-based system. That is, it is capable of automatically generating, merging, and tuning the hyperplane-based fuzzy rule in the single-pass manner. Moreover, an extension of PALM, namely recurrent PALM, is proposed and adopts the concept of teacher-forcing mechanism in the deep learning literature. The efficacy of PALM has been evaluated through numerical study with six real-world and synthetic data streams from public database and our own real-world project of autonomous vehicles. The proposed model showcases significant improvements in terms of computational complexity and number of required parameters against several renowned SANFSs, while attaining comparable and often better predictive accuracy.

In this work we present non-linear system identification for a class of the dragonfly-like flapping wing aircraft. We model the system in its vertical and all attitude loops (roll, pitch, and yaw) as well as its actuator dynamics. Based on a set of input-output data, obtained from first principle modelling; we perform the entropy fuzzy system identification to derive the open loop dynamics of the aircraft using the Mamdani Fuzzy inference method, which is more intuitive, despite being non-linear. This will make the proposed models well-suited to non-expert users (e.g. average drone operators). Our research indicates that the information entropy is very effective to maximize the system accuracy while avoiding overfitting problems. Through numerical simulation, we demonstrate the efficacy of the proposed fuzzy models as we can achieve reasonably good average modelling accuracy of around 90 % for all attitude loops.

Nowadays, the application of fully autonomous system like rotary wing unamnned air vehicles (UAVs) are increasing sharply. Due to the complex nonlinear dynamics a huge research interest is witnessed in developing learning machine based intelligent, self-organizing evolving controller for these vehicles notably to address the system's dynamic characteristics. In this work, such an evolving controller namely Generic-controller (Gcontroller) is proposed to control the altitude of a rotary wing UAV namely hexacopter. This controller can work with very minor expert domain knowledge. The evolving architecture of this controller is based on an advanced incremental learning algorithm namely Generic Evolving Neuro-Fuzzy Inference System (GENEFIS). The controller does not require any offline training, since it starts operating from scratch with an empty set of fuzzy rules, and then add or delete rules on demand. The adaptation laws for the consequent paramters are derived from the sliding model control (SMC) theory. The Lyapunov theory is used to guarantee the stability of the proposed controller. In addition, an auxiliary robustifying control term is implemented to obtain an uniform asymptotic convergence of tracking error to zero. Finally, the G-controller's performance evaluation is observed through the altitude tracking of an UAV namely hexacopter for various trajectories.

We discuss state-of-the-art intelligent robotic aircraft with the special focus on evolutionary autopilots for small unmanned aerial vehicles (UAVs). Under the umbrella of adaptive autopilots, we highlight the pros and cons of the most widely implemented intelligent algorithms against the navigational and maneuvering capabilities of small UAVs. We present several cutting-edge applications of bioinspired flight control systems that have the capability of self-learning. We also highlight several research opportunities and challenges associated with each technique.

In this paper, we comprehensively discuss the current progress of visual-inertial (VI) navigation systems and sensor fusion research with a particular focus on small unmanned aerial vehicles, known as microaerial vehicles (MAVs). Such fusion has become very topical due to the complementary characteristics of the two sensing modalities. We discuss the pros and cons of the most widely implemented VI systems against the navigational and maneuvering capabilities of MAVs. Considering the issue of optimum data fusion from multiple heterogeneous sensors, we examine the potential of the most widely used advanced state estimation techniques (both linear and nonlinear as well as Bayesian and non-Bayesian) against various MAV design considerations. Finally, we highlight several research opportunities and potential challenges associated with each technique.

Existing extreme learning algorithm have not taken into account four issues: 1) complexity; 2) uncertainty; 3) concept drift; and 4) high dimensionality. A novel incremental type-2 meta-cognitive extreme learning machine (ELM) called evolving type-2 ELM (eT2ELM) is proposed to cope with the four issues in this paper. The eT2ELM presents three main pillars of human meta-cognition: 1) what-to-learn; 2) how-to-learn; and 3) when-to-learn. The what-to-learn component selects important training samples for model updates by virtue of the online certainty-based active learning method, which renders eT2ELM as a semi-supervised classifier. The how-to-learn element develops a synergy between extreme learning theory and the evolving concept, whereby the hidden nodes can be generated and pruned automatically from data streams with no tuning of hidden nodes. The when-to-learn constituent makes use of the standard sample reserved strategy. A generalized interval type-2 fuzzy neural network is also put forward as a cognitive component, in which a hidden node is built upon the interval type-2 multivariate Gaussian function while exploiting a subset of Chebyshev series in the output node. The efficacy of the proposed eT2ELM is numerically validated in 12 data streams containing various concept drifts. The numerical results are confirmed by thorough statistical tests, where the eT2ELM demonstrates the most encouraging numerical results in delivering reliable prediction, while sustaining low complexity.

Design optimization of an unmanned underwater vehicle (UUV) is a complex and a computationally expensive exercise that requires the identification of optimal vehicle dimensions offering the best tradeoffs between the objectives, while satisfying the set of design constraints. Although hull form optimization of marine vessels has long been an active area of research, limited attempts in the past have focused on the design optimization of UUVs and there are even fewer reports on the use of high-fidelity analysis methods within the course of optimization. While it is understood that the high-fidelity analysis is more accurate, they also tend to be far more computationally expensive. Thus, it is important to identify when a high-fidelity analysis is required as opposed to a low-fidelity estimate. The work reported in this paper is an extension of the authors previous work of a design optimization framework, where the design problem was solved using a low-fidelity model based on empirical estimates of drag. In this paper, the framework is extended to deal with high-fidelity estimates derived through seamless integration of computer-aided design, meshing and computational fluid dynamics analysis tools i.e., computer aided 3-D interactive application, ICEM, and FLUENT. The effects of using low-fidelity and high-fidelity analyses are studied in depth using a small-scale (length nominally less than 400 mm) and light-weight (less than 450 g) toy submarine. Useful insights on possible means to identify appropriateness of fidelity models via correlation measures are proposed. The term optimality used in this paper refers to optimal hull form shapes that satisfy placement of a set of prescribed internal components.

This paper discusses an overview on different path planning algorithms and analyzes their performance. Based on this, an efficient hybrid algorithm is proposed for path planning in both static and dynamic environments. The numerical results are presented to validate the proposed design. The method is compared to other heuristic algorithms in different scenarios. The proposed algorithm is shown to be more efficient computationally than the other comparable algorithms.

This paper describes path replanning techniques and obstacles avoidance for autonomous vehicles, in complex environments. The Vectorized Particle Swarm optimization (VPSO) method is used for searching for an optimal path. A simultaneous replanning concept is incorporated with path planning to avoid static and dynamic obstacles. This proposed simultaneous replanning vectorized particle swarm optimization (SRVPSO) algorithm reduces the computational time of the path planning. Numerical results show that the SRVPSO algorithm provides better replanning time in a dynamic environment.

In this paper, a novel evolving fuzzy-rule-based classifier, termed parsimonious classifier (pClass), is proposed. pClass can drive its learning engine from scratch with an empty rule base or initially trained fuzzy models. It adopts an open structure and plug and play concept where automatic knowledge building, rule-based simplification, knowledge recall mechanism, and soft feature reduction can be carried out on the fly with limited expert knowledge and without prior assumptions to underlying data distribution. In this paper, three state-of-the-art classifier architectures engaging multi-input-multi-output, multimodel, and round robin architectures are also critically analyzed. The efficacy of the pClass has been numerically validated by means of real-world and synthetic streaming data, possessing various concept drifts, noisy learning environments, and dynamic class attributes. In addition, comparative studies with prominent algorithms using comprehensive statistical tests have confirmed that the pClass delivers more superior performance in terms of classification rate, number of fuzzy rules, and number of rule-base parameters.

This paper outlines our proposal for a novel metacognitive-based scaffolding classifier, namely recurrent classifier (rClass). rClass is capable of emulating three fundamental pillars of human learning in terms of what-to-learn, how-to-learn, and when-to-learn. The cognitive constituent of rClass is underpinned by a recurrent network based on a generalized version of the Takagi-Sugeno-Kang fuzzy system possessing a local feedback of the rule layer. The main basis of the what-to-learn component relies on the new active learning-based conflict measure. Meanwhile, the when-to-learn learning scenario makes use of the standard sample reserved strategy. The how-to-learn module actualizes the Schema and Scaffolding concepts of cognitive psychology. All learning principles are committed in the single-pass local learning modes and create a plug-and-play learning foundation minimizing additional pre- or post-training phases. The efficacy of rClass has been scrutinized by means of rigorous empirical studies, statistical tests, and benchmarks with state-of-the-art classifiers, which demonstrate the rClass potency in producing reliable classification rates, while retaining low complexity in terms of the rule base burden, computational load, and annotation effort.

Unmanned underwater vehicles (UUVs) are becoming an attractive option for maritime search and survey operations as they are cheap and efficient compared to conventional use of divers or manned submersibles. Consequently, there has been a growing interest in UUV research among scientific and engineering communities. Although UUVs have received significant research interest in recent years, limited attention has been paid towards design and development of mini/micro UUVs (usually less than 1 foot in length). Micro unmanned underwater vehicles (μUUVs) are particularly attractive for deployment in extraordinarily confined spaces such as inspection of intricate underwater structures, ship wrecks, oil pipe lines or extreme hazardous areas. This paper considers previous work done in the field of miniature UUVs and presents an optimization framework for preliminary design of that class of UUVs. A state-of-the-art optimization algorithm namely infeasibility driven evolutionary algorithm (IDEA) is used to carry out optimization of the μUUV designs. The framework is subsequently used to identify optimal design of a torpedo-shaped μUUV with an overall length of six inches (152.4 mm). The preliminary design identified through the process of optimization is further analyzed with the help of a computer-aided design tool to come up with a detailed design. The final design has since then been built and is currently undergoing trials.

A novel meta-cognitive-based scaffolding classifier, namely Generic-Classifier (gClass), is proposed in this paper to handle non-stationary classification problems in the single-pass learning mode. Meta-cognitive learning is a breakthrough in the machine learning where the learning process is not only directed to craft learning strategies to exacerbate the classification rates, i.e., how-to-leam aspect, but also is focused to accommodate the emotional reasoning and commonsense of human being in terms of what-to-leam and when-to-learn facets. The crux of gClass is to synergize the scaffolding learning concept, which constitutes a well-known tutoring theory in the psychological literatures, in the how-to-learn context of meta-cognitive learning, in order to boost the learner's performance in dealing with complex data. A comprehensive empirical studies in time-varying datasets is carried out, where gClass numerical results are benchmarked with other state-of-the-art classifiers. gClass is, generally speaking, capable of delivering the most encouraging numerical results where a trade-off between predictive accuracy and classifier's complexity can be achieved.

Nowadays, there is increasing demand for an integrated system usable to real-time environments under limited computational resources and minimum operator supervision. In contrast, the model is also supposed to actualize high predictive quality in order to confirm the process safety and attractive working framework allowing the user to grasp how the particular task is settled. A holistic concept of a fully data-driven modeling tool namely Generic Evolving Neuro-Fuzzy Inference System (GENEFIS) is proposed in this paper. The major spotlight of GENEFIS is in delivering a sensible tradeoff between high predictive accuracy and parsimonious rule base while reckoning tractable rule semantics. The viability of GENEFIS is numerically validated via a series of experimentations using real world and artificial datasets and is compared against state of the art of the evolving neuro-fuzzy systems (ENFSs), where GENEFIS not only showcases higher predictive accuracies but also lands on more frugal structures than other algorithms.

This paper focuses on an optimum route search function in the in-vehicle routing guidance system. For a dynamic route guidance system (DRGS), it should provide dynamic routing advice based on real-time traffic information and traffic conditions, such as congestion and roadwork. However, considering all these situations in traditional methods makes it very difficult to identify a valid mathematical model. To realize the DRGS, this paper proposes the analytical hierarchy process (AHP) using a fuzzy inference technique based on the real-time traffic information. This AHP-FUZZY approach is a multicriterion combination system. The nature of the AHP-FUZZY approach is a pairwise comparison, which is expressed by the fuzzy inference techniques, to achieve the weights of the attributes. The hierarchy structure of the AHP-FUZZY approach can greatly simplify the definition of a decision strategy and explicitly represent the multiple criteria, and the fuzzy inference technique can handle the vagueness and uncertainty of the attributes and adaptively generate the weights for the system. Based on the AHP-FUZZY approach, a simulation system is implemented in the route guidance system, and the process is analyzed.

Most of the dynamics in real-world systems are compiled by shifts and drifts, which are uneasy to be overcome by omnipresent neuro-fuzzy systems. Nonetheless, learning in nonstationary environment entails a system owning high degree of flexibility capable of assembling its rule base autonomously according to the degree of nonlinearity contained in the system. In practice, the rule growing and pruning are carried out merely benefiting from a small snapshot of the complete training data to truncate the computational load and memory demand to the low level. An exposure of a novel algorithm, namely parsimonious network based on fuzzy inference system (PANFIS), is to this end presented herein. PANFIS can commence its learning process from scratch with an empty rule base. The fuzzy rules can be stitched up and expelled by virtue of statistical contributions of the fuzzy rules and injected datum afterward. Identical fuzzy sets may be alluded and blended to be one fuzzy set as a pursuit of a transparent rule base escalating human's interpretability. The learning and modeling performances of the proposed PANFIS are numerically validated using several benchmark problems from real-world or synthetic datasets. The validation includes comparisons with state-of-the-art evolving neuro-fuzzy methods and showcases that our new method can compete and in some cases even outperform these approaches in terms of predictive fidelity and model complexity.

This paper presents a novel evolving fuzzy rule-based classifier stemming from our recently developed algorithm for regression problem termed generic evolving neuro-fuzzy system (GENEFIS). On the one hand, the novel classifier namely GENEFIS-class is composed of two different architectures specifically zero and first orders which are dependent on the type of consequent used. On the other hand, GENEFIS-class refurbishes GENEFIS algorithm as the main learning engine to conform classification requirement. The interesting property of GENEFIS is its fully flexible rule base and its computationally efficient algorithm. GENEFIS can initiate its learning process from scratch with an empty rule base and highly narrow expert knowledge. The fuzzy rules are then flourished based on the novelty of streaming data via their statistical contribution. Conversely, the fuzzy rules, which contribute little during their lifespan, can be pruned by virtue of their contributions up to the end of training process. Meanwhile, the fuzzy rules and fuzzy sets, which are redundant, can be merged to purpose a transparent rule base. Online feature selection process coupled during the training process can be undertaken to cope with possible combinatorial rule explosion drawback. All of these are fruitful to grant significant reduction of rule base load while retaining the classification accuracy which is in line with online real-time necessity. The efficacy of GENEFIS-class was numerically validated exploiting real world and synthetic problems and compared with state-of-the-art algorithms where it generally speaking outperforms other algorithms in terms of classification performance and rule-base complexity.

This paper introduces a novel identifier scheme for identification of nonlinear systems with disturbances. The identification process is carried out in two steps: an offline procedure and an online procedure. The method comprises of an automatic structure generating phase using entropybased technique. The accuracy of the model is suitably controlled using the entropy measure. The parameter learning phase uses the backpropagation technique. To improve the accuracy and also for generalization of the model to handle different data sets, Differential Evolution technique is employed whereby the parameters of the model are suitably tuned using evolutionary technique. A semi serial-parallel model is introduced to improve the online identification process in the presence of noisy data. The proposed mechanism is utilized and compared against the classical Sugeno, adaptive network-based fuzzy inference system (ANFIS) modeling and Laguerre Network-Based Fuzzy System for the identification of a nonlinear benchmark problem. In addition, the proposed technique is also used to model a rotary wing unmanned aerial vehicle (UAV) from real test input–output data. The modeling performance and generalization capability are seen to be superior with our method.

Dynamic multi-objective optimization (DMO) is one of the most challenging class of optimization problems where the objective functions change over time and the optimization algorithm is required to identify the corresponding Pareto optimal solutions with minimal time lag. DMO has received very little attention in the past and none of the existing multi-objective algorithms perform satisfactorily on test problems and a handful of such applications have been reported. In this paper, we introduce a memetic algorithm (MA) and illustrate its performance for online neural network (NN) identification of the multi-input multi-output unmanned aerial vehicle (UAV) system. As a typical case, the longitudinal model of the UAV is considered and the performance of a NN trained with the memetic algorithm is compared to another trained with Levenberg-Marquardt training algorithm using mini-batches. The memetic algorithm employs an orthogonal epsilon-constrained formulation to deal with multiple objectives and a sequential quadratic programming (SQP) solver is embedded as its local search mechanism to improve the rate of convergence. The performance of the memetic algorithm is presented for two benchmarks Fisherpsilas Discriminant Analysis (FDA), FDA1 and modified FDA2 before highlighting its benefits for online NN model identification for UAVs. Observations from our recent work indicated that Mean Square Error (MSE) alone may not always be a good measure for training the networks. Hence the MSE and maximum absolute value of the instantaneous error is considered as objectives to be minimized which requires a Dynamic MO algorithm. The proposed memetic algorithm is aimed to solve such identification problems and the same can be extended to control problems.

In this paper a comparison of an offline and online neural network architecture for the identification of an unmanned aerial vehicle (UAV) is presented. The identification algorithm is based on autoregressive model aided by neural networks for the six degree of freedom, non-linear dynamics of a fixed wing UAV. One of the architectures involved the use of a single network to model the complete UAV system and the other involved the use of two decoupled networks for the lateral and longitudinal dynamics taking coupling into account. Numerical simulation results are presented for each of these architectures. The results have been validated using the real-time hardware in the loop (HIL) simulation technique for different sets of flight data.

This paper describes a system identification technique based on dynamic selection of multiple neural networks for the Unmanned Aerial Vehicle (UAV). The UAV is a multi- input multi-output (MIMO) nonlinear system. The neural network models are based on the autoregressive technique. The multi-network dynamic selection method allows a combination of online and offline neural network models to be used in the architecture where the most suitable output is selected based on the given criteria. The online network uses a novel training scheme with memory retention. Flight test validation results for online and offline models are presented. Real-time hardware in the loop (HIL) simulation results show that the multi-net dynamic selection technique performs better than the individual models.