Self-Organizing Type-2 Fuzzy Double Loop Recurrent Neural Network for Uncertain Nonlinear System Control.

Nonlinear systems, such as robotic systems, play an increasingly important role in our modern daily life and have become more dominant in many industries; however, robotic control still faces various challenges due to diverse and unstructured work environments. This article proposes a double-loop recurrent neural network (DLRNN) with the support of a Type-2 fuzzy system and a self-organizing mechanism for improved performance in nonlinear dynamic robot control. The proposed network has a double-loop recurrent structure, which enables better dynamic mapping. In addition, the network combines a Type-2 fuzzy system with a double-loop recurrent structure to improve the ability to deal with uncertain environments. To achieve an efficient system response, a self-organizing mechanism is proposed to adaptively adjust the number of layers in a DLRNN. This work integrates the proposed network into a conventional sliding mode control (SMC) system to theoretically and empirically prove its stability. The proposed system is applied to a three-joint robot manipulator, leading to a comparative study that considers several existing control approaches. The experimental results confirm the superiority of the proposed system and its effectiveness and robustness in response to various external system disturbances.

Actor-Critic With Synthesis Loss for Solving Approximation Biases.

Approximation biases of value functions are considered a key problem in reinforcement learning (RL). In particular, existing RL algorithms are hindered by overestimation and underestimation biases, i.e., value mismatching between RL's actual returns and action-value approximations limits the performance of RL algorithms. In this article, we first develop a new synthesis loss function for RL's action-value estimation integrating a regularization term and a modified "clipped double Q -learning" structure for solving overestimation and underestimation biases. To minimize the differences between action-value estimations and actual returns in RL, we develop a new discrepancy function to determine the type and magnitude of approximation biases. Then, two coefficients embedded in the synthesis loss are automatically tuned by minimizing the discrepancy function during training to minimize approximation biases. We further design a new actor-critic (AC) algorithm, named AC with synthesis loss (ACSL), by integrating the synthesis loss function and an error-controlled mechanism. Experimental results on continuous control tasks illustrate that the proposed ACSL algorithm outperforms other cutting-edge RL methods in many tasks and that the proposed synthesis loss function is easily implemented into other algorithms and significantly reduces approximation biases while improving performance. The proposed method can successfully handle many complex continuous control tasks and can greatly outperform other state-of-the-art algorithms on most tasks.

Rule-Ranking-Based Approximate Knowledge Interpolation With Directional Monotonicity.

Fuzzy rule interpolation (FRI) empowers fuzzy rule-based systems (FRBSs) with the ability to infer, even when presented with a sparse rule base where no direct rules are applicable to a given observation. The core principle lies in creating an intermediate fuzzy rule-either interpolated or extrapolated-derived from rules neighboring the observation. Conventionally, the selection of these rules hinges upon distance metrics. While this approach is easy to grasp and has been instrumental in the evolution of various FRI methods, it is burdened by the necessity of extensive distance calculations. This becomes particularly cumbersome when swift responses are imperative or when dealing with large datasets. This article introduces a groundbreaking rule-ranking-based FRI method, termed RT-FRI, which overcomes the constraints of the longstanding distance-centric FRI approach. Instead of relying on distances, RT-FRI harnesses ranking scores for rules and unmatched observation. These scores are produced by amalgamating the antecedent attributes using aggregation functions, thus streamlining the rule selection procedure. Recognizing the rigid monotonicity demands of aggregation functions, a variant-DMRT-FRI-has been introduced to ensure directional monotonicity. Experimental results indicate that RT-FRI emerges as a highly efficient technique, with DMRT-FRI exemplifying a notable balance of accuracy and efficiency.

A Multitask Network for Joint Multispectral Pansharpening on Diverse Satellite Data.

Despite the rapid advance in multispectral (MS) pansharpening, existing convolutional neural network (CNN)-based methods require training on separate CNNs for different satellite datasets. However, such a single-task learning (STL) paradigm often leads to overlooking any underlying correlations between datasets. Aiming at this challenging problem, a multitask network (MTNet) is presented to accomplish joint MS pansharpening in a unified framework for images acquired by different satellites. Particularly, the pansharpening process of each satellite is treated as a specific task, while MTNet simultaneously learns from all data obtained from these satellites following the multitask learning (MTL) paradigm. MTNet shares the generic knowledge between datasets via task-agnostic subnetwork (TASNet), utilizing task-specific subnetworks (TSSNets) to facilitate the adaptation of such knowledge to a certain satellite. To tackle the limitation of the local connectivity property of the CNN, TASNet incorporates Transformer modules to derive global information. In addition, band-aware dynamic convolutions (BDConvs) are proposed that can accommodate various ground scenes and bands by adjusting their respective receptive field (RF) size. Systematic experimental results over different datasets demonstrate that the proposed approach outperforms the existing state-of-the-art (SOTA) techniques.

Decoder Choice Network for Metalearning.

Metalearning has been widely applied for implementing few-shot learning and fast model adaptation. Particularly, existing metalearning methods have been exploited to learn the control mechanism for gradient descent processes, in an effort to facilitate gradient-based learning in gaining high speed and generalization ability. This article presents a novel method that controls the gradient descent process of the model parameters in a neural network, by limiting the model parameters within a low-dimensional latent space. The main challenge for implementing this idea is that a decoder with many parameters may be required. To tackle this problem, the article provides an alternative design of the decoder with a structure that shares certain weights, thereby reducing the number of required parameters. In addition, this work combines ensemble learning with the proposed approach to improve the overall learning performance. Systematic experimental studies demonstrate that the proposed approach offers results superior to the state of the art in performing the Omniglot classification and miniImageNet classification tasks.

Solving Robotic Trajectory Sequential Writing Problem via Learning Character's Structural and Sequential Information.

The writing sequence of numerals or letters often affects aesthetic aspects of the writing outcomes. As such, it remains a challenge for robotic calligraphy systems to perform, mimicking human writers' implicit intention. This article presents a new robot calligraphy system that is able to learn writing sequences with limited sequential information, producing writing results compatible to human writers with good diversity. In particular, the system innovatively applies a gated recurrent unit (GRU) network to generate robotic writing actions with the support of a prelabeled trajectory sequence vector. Also, a new evaluation method is proposed that considers the shape, trajectory sequence, and structural information of the writing outcome, thereby helping ensure the writing quality. A swarm optimization algorithm is exploited to create an optimal set of parameters of the proposed system. The proposed approach is evaluated using Arabic numerals, and the experimental results demonstrate the competitive writing performance of the system against state-of-the-art approaches regarding multiple criteria (including FID, MAE, PSNR, SSIM, and PerLoss), as well as diversity performance concerning variance and entropy. Importantly, the proposed GRU-based robotic motion planning system, supported with swarm optimization can learn from a small dataset, while producing calligraphy writing with diverse and aesthetically pleasing outcomes.

Semantic-Aware Real-Time Correlation Tracking Framework for UAV Videos.

Discriminative correlation filter (DCF) has contributed tremendously to address the problem of object tracking benefitting from its high computational efficiency. However, it has suffered from performance degradation in unmanned aerial vehicle (UAV) tracking. This article presents a novel semantic-aware real-time correlation tracking framework (SARCT) for UAV videos to enhance the performance of DCF trackers without incurring excessive computing cost. Specifically, SARCT first constructs an additional detection module to generate ROI proposals and to filter any response regarding the target irrelevant area. Then, a novel semantic segmentation module based on semantic template generation and semantic coefficient prediction is further introduced to capture semantic information, which can provide precise ROI mask, thereby effectively suppressing background interference in the ROI proposals. By sharing features and specific network layers for object detection and semantic segmentation, SARCT reduces parameter redundancy to attain sufficient speed for real-time applications. Systematic experiments are conducted on three typical aerial datasets in order to evaluate the performance of the proposed SARCT. The results demonstrate that SARCT is able to improve the accuracy of conventional DCF-based trackers significantly, outperforming state-of-the-art deep trackers.

Helper and Equivalent Objectives: Efficient Approach for Constrained Optimization.

Numerous multiobjective evolutionary algorithms (EAs) have been designed for constrained optimization over the past two decades. The idea behind these algorithms is to transform constrained optimization problems (COPs) into multiobjective optimization problems without any constraint, and then solve them. In this article, we propose a new multiobjective method for constrained optimization, which works by converting a COP into a problem with helper and equivalent objectives. An equivalent objective means that its optimal solution set is the same as that of the constrained problem but a helper objective does not. Then, this multiobjective optimization problem is decomposed into a group of subproblems using the weighted sum approach. Weights are dynamically adjusted so that each subproblem eventually tends to a problem with an equivalent objective. We theoretically analyze the computational time of the helper and equivalent objective method on a hard problem called "wide gap." In a wide gap problem, an algorithm needs exponential time to cross between two fitness levels (a wide gap). We prove that using helper and equivalent objectives can shorten the time of crossing the wide gap. We conduct a case study for validating our method. An algorithm with helper and equivalent objectives is implemented. The experimental results show that its overall performance is ranked first when compared with other eight state-of-the-art EAs on IEEE CEC2017 benchmarks in constrained optimization.

A Decision Tree-Initialised Neuro-fuzzy Approach for Clinical Decision Support.

Apart from the need for superior accuracy, healthcare applications of intelligent systems also demand the deployment of interpretable machine learning models which allow clinicians to interrogate and validate extracted medical knowledge. Fuzzy rule-based models are generally considered interpretable that are able to reflect the associations between medical conditions and associated symptoms, through the use of linguistic if-then statements. Systems built on top of fuzzy sets are of particular appealing to medical applications since they enable the tolerance of vague and imprecise concepts that are often embedded in medical entities such as symptom description and test results. They facilitate an approximate reasoning framework which mimics human reasoning and supports the linguistic delivery of medical expertise often expressed in statements such as 'weight low' or 'glucose level high' while describing symptoms. This paper proposes an approach by performing data-driven learning of accurate and interpretable fuzzy rule bases for clinical decision support. The approach starts with the generation of a crisp rule base through a decision tree learning mechanism, capable of capturing simple rule structures. The crisp rule base is then transformed into a fuzzy rule base, which forms the input to the framework of adaptive network-based fuzzy inference system (ANFIS), thereby further optimising the parameters of both rule antecedents and consequents. Experimental studies on popular medical data benchmarks demonstrate that the proposed work is able to learn compact rule bases involving simple rule antecedents, with statistically better or comparable performance to those achieved by state-of-the-art fuzzy classifiers.

ANFIS Construction With Sparse Data via Group Rule Interpolation.

A major assumption for constructing an effective adaptive-network-based fuzzy inference system (ANFIS) is that sufficient training data are available. However, in many real-world applications, this assumption may not hold, thereby requiring alternative approaches. In light of this observation, this article focuses on automated construction of ANFISs in an effort to enhance the potential of the Takagi-Sugeno fuzzy regression models for situations where only limited training data are available. In particular, the proposed approach works by interpolating a group of fuzzy rules in a certain given domain with the assistance of existing ANFISs in its neighboring domains. The construction process involves a number of computational mechanisms, including a rule dictionary which is created by extracting the rules from the existing ANFISs; a group of rules which are interpolated by exploiting the local linear embedding algorithm to build an intermediate ANFIS; and a fine-tuning method which refines the resulting intermediate ANFIS. The experimental evaluation on both synthetic and real-world datasets is reported, demonstrating that when facing the data shortage situations, the proposed approach helps significantly improve the performance of the original ANFIS modeling mechanism.

Type-2 Fuzzy Hybrid Controller Network for Robotic Systems.

Dynamic control, including robotic control, faces both the theoretical challenge of obtaining accurate system models and the practical difficulty of defining uncertain system bounds. To facilitate such challenges, this paper proposes a control system consisting of a novel type of fuzzy neural network and a robust compensator controller. The new fuzzy neural network is implemented by integrating a number of key components embedded in a Type-2 fuzzy cerebellar model articulation controller (CMAC) and a brain emotional learning controller (BELC) network, thereby mimicking an ideal sliding mode controller. The system inputs are fed into the neural network through a Type-2 fuzzy inference system (T2FIS), with the results subsequently piped into sensory and emotional channels which jointly produce the final outputs of the network. That is, the proposed network estimates the nonlinear equations representing the ideal sliding mode controllers using a powerful compensator controller with the support of T2FIS and BELC, guaranteeing robust tracking of the dynamics of the controlled systems. The adaptive dynamic tuning laws of the network are developed by exploiting the popular brain emotional learning rule and the Lyapunov function. The proposed system was applied to a robot manipulator and a mobile robot, demonstrating its efficacy and potential; and a comparative study with alternatives indicates a significant improvement by the proposed system in performing the intelligent dynamic control.

Fuzzy Knowledge-Based Prediction Through Weighted Rule Interpolation.

Fuzzy rule interpolation (FRI) facilitates approximate reasoning in fuzzy rule-based systems only with sparse knowledge available, remedying the limitation of conventional compositional rule of inference working with a dense rule base. Most of the existing FRI work assumes equal significance of the conditional attributes in the rules while performing interpolation. Recently, interesting techniques have been reported for achieving weighted interpolative reasoning. However, they are either particularly tailored to perform classification problems only or employ attribute weights that are obtained using additional information (rather than just the given rules), without integrating them with the associated FRI procedure. This paper presents a weighted rule interpolation scheme for performing prediction tasks by the use of fuzzy sparse knowledge only. The weights of rule conditional attributes are learned from a given rule base to discriminate the relative significance of each individual attribute and are integrated throughout the internal mechanism of the FRI process. This scheme is demonstrated using the popular scale and move transformation-based FRI for resolving prediction problems, systematically evaluated on 12 benchmark prediction tasks. The performance is compared with the relevant state-of-the-art FRI techniques, showing the efficacy of the proposed approach.

Multi-criterion mammographic risk analysis supported with multi-label fuzzy-rough feature selection.

CONTEXT AND BACKGROUND: Breast cancer is one of the most common diseases threatening the human lives globally, requiring effective and early risk analysis for which learning classifiers supported with automated feature selection offer a potential robust solution. MOTIVATION: Computer aided risk analysis of breast cancer typically works with a set of extracted mammographic features which may contain significant redundancy and noise, thereby requiring technical developments to improve runtime performance in both computational efficiency and classification accuracy. HYPOTHESIS: Use of advanced feature selection methods based on multiple diagnosis criteria may lead to improved results for mammographic risk analysis. METHODS: An approach for multi-criterion based mammographic risk analysis is proposed, by adapting the recently developed multi-label fuzzy-rough feature selection mechanism. RESULTS: A system for multi-criterion mammographic risk analysis is implemented with the aid of multi-label fuzzy-rough feature selection and its performance is positively verified experimentally, in comparison with representative popular mechanisms. CONCLUSIONS: The novel approach for mammographic risk analysis based on multiple criteria helps improve classification accuracy using selected informative features, without suffering from the redundancy caused by such complex criteria, with the implemented system demonstrating practical efficacy.

An Improved Fuzzy Brain Emotional Learning Model Network Controller for Humanoid Robots.

The brain emotional learning (BEL) system was inspired by the biological amygdala-orbitofrontal model to mimic the high speed of the emotional learning mechanism in the mammalian brain, which has been successfully applied in many real-world applications. Despite of its success, such system often suffers from slow convergence for online humanoid robotic control. This paper presents an improved fuzzy BEL model (iFBEL) neural network by integrating a fuzzy neural network (FNN) to a conventional BEL, in an effort to better support humanoid robots. In particular, the system inputs are passed into a sensory and emotional channels that jointly produce the final outputs of the network. The non-linear approximation ability of the iFBEL is achieved by taking the BEL network as the emotional channel. The proposed iFBEL works with a robust controller in generating the hand and gait motion of a humanoid robot. The updating rules of the iFBEL-based controller are composed of two parts, including a sensory channel followed by the updating rules of the conventional BEL model, and the updating rules of the FNN and the robust controller which are derived from the "Lyapunov" function. The experiments on a three-joint robot manipulator and a six-joint biped robot demonstrated the superiority of the proposed system in reference to a conventional proportional-integral-derivative controller and a fuzzy cerebellar model articulation controller, based on the more accurate and faster control performance of the proposed iFBEL.