An Improved Adaptive Optimal Regulation Framework with Robust Control Synthesis

The detection of coreferent pairs within a text is one of the basic tasks in the area of natural language processing (NLP). The state‑ of‑ the‑ art methods of coreference resolution are based on machine learning algorithms. The key idea of the methods is to detect certain regularities between the semantic or grammatical features of text entities. In the paper, the comparative analysis of current methods of coreference resolution in English and Ukrainian texts has been performed. The key disadvantage of many methods consists in the interpretation of coreference resolution as a classification problem. The result of coreferent pairs detection is the set of groups in which elements refer to a common entity. Therefore it is advisable to consider the coreference resolution as a clusterization task. The method of coreference resolution using the set of filtering sieves and a convolutional neural network has been suggested. The set of filtering sieves to find candidates for coreferent pairs formation has been implemented. The training process of a multichannel convolutional neural network on a marked Ukrainian corpus has been performed. The usage of a multichannel structure allows analyzing of the different components of text units: semantic, lexical, and grammatical features of words and sentences. Furthermore, it is possible to process input data with unfixed size (words or sentences of a text) using a convolutional layer. The output result of the method is the set of clusters. In order to form clusters, it is necessary to take into account the previous steps of the model’s workflow. Nevertheless, such an approach contradicts the traditional methodology of machine learning. Thus, the training process of the network has been performed using the SEARN algorithm that allows the solving of tasks with unfixed output structures using a classifier model. An experimental examination of the method on the corpus of Ukrainian news has been performed. In order to estimate the accuracy of the method the corresponding common metrics for clusterization tasks have been calculated. The results obtained can indicate that the suggested method can be used to find coreferent pairs within Ukrainian texts. The method can be also easily adapted and applied to other natural languages.

This paper presents a new hybrid metaheuristic model in order to estimate wind speeds accurately. The study was started by the training process of artificial neural networks with some metaheuristic algorithms such as evolutionary strategy, genetic algorithm, ant colony optimization, probability-based incremental learning, particle swarm optimization, and radial movement optimization in the literature. The success of each model is recorded in graphs. In order to make the closest estimation and to increase the system stability, a new hybrid metaheuristic model was developed using particle swarm optimization and radial movement optimization, and the training process of artificial neural networks was performed with this new model. The data were obtained by real-time measurements from a 63-m-high wind measurement station built at the coordinates of UTM E 263254 and N 4173479, altitude 1313 m. Two different scenarios were created using actual data and applied to all models. It was observed that the error values in the designed new hybrid metaheuristic model were lower than those of the other models.

Environmental sound intelligence detection is one of the important means of smart city construction. The performance of the detection is particularly affected by environmental noise. To increase the performance of environmental sound (ES) recognition, different target features and masks are used in denoising, which has large differences in numerical range. However, as the number of targets with large numerical differences increases, the difficulty of network learning data rules will increase, and so will the target estimation error. The multi-objective learning noise suppression algorithm put forth in this paper aims to reduce the influence, based on a convolutional and dual temporal convolutional neural network (CNN-2TCN). The algorithm combines CNN and two parallel TCN modules to learn two types of targets with large differences in numerical range, which can optimize the training process of neural networks. In addition, the secondary targets and the IRM-based adaptive post-processing method are adopted to improve the prediction accuracy of primary targets and the quality of the reconstructed ES. The experimental results show that the proposed algorithm achieves better performance than other algorithms. Moreover, the proposed algorithm can improve the performance of the ES detection system. Especially, the ES detection system, which has used the proposed method, has made an increase of 5.95%, 31.35%, and 36.75% in the recognition accuracy under the three signal-to-noise ratios (SNR) of 5 dB, 0 dB, and -5 dB, respectively.

Neural networks have emerged as a cornerstone in the field of machine learning, driving significant advancements across various domains such as computer vision, natural language processing, and autonomous systems. This paper explores the fundamental principles of neural networks, including their structural design, activation functions, and training algorithms. Key architectures such as feedforward neural networks, convolutional neural networks, recurrent neural networks, and generative adversarial networks are discussed in detail, highlighting their unique capabilities and applications. The training process of neural networks, involving techniques like backpropagation and gradient descent, is examined alongside methods to enhance performance and prevent overfitting, such as regularization and optimization strategies. This paper also reviews major applications of neural networks, showcasing their impact on image and speech recognition, language translation, and autonomous vehicles. Recent advancements in the field, including the rise of deep learning, improved model explainability, and the development of specialized hardware accelerators, are analyzed to provide insights into current trends and future prospects. The ongoing research in areas like unsupervised learning, few-shot learning, and the integration of neural networks with other AI paradigms is highlighted as a promising avenue for further innovation. By providing a comprehensive overview of neural networks and their applications, this paper underscores their transformative role in advancing machine learning technologies and anticipates future developments that will continue to shape the landscape of artificial intelligence.

In recent years, with the great success of dendritic neuron model (DNM) in various fields, the application of intelligent optimization algorithms in dendritic neuron model has attracted increasing attention of researchers. The training process of neural network is regarded as one of the great challenges of machine learning because of its non-linear nature and unknown optimal parameters. The traditional training algorithm of DNM is prone to fall into local optimum and speed of convergence slowly and so on, resulting in the problem of accuracy and low efficiency. In this paper, for solving the classification problem of dendritic neural model, an innovative intelligent optimization algorithm which named whale optimization algorithm (WOA), is applied to the training of DNM for the first time. Compared with six traditional and classic intelligent optimization algorithms in four classic datasets, the results indicate that WOA-DNM has good performance in various aspects, and its advantage is remarkable.

Because it is so difficult to distinguish handwritten digits, digit identification is one of the most critical applications in computer vision. This is one of the reasons why it is so tough. The field of handwritten character recognition is one in which a great deal of application of numerous deep learning models has occurred. The startling parallels that can be drawn between deep learning and the brain are primarily responsible for its meteoric rise in popularity. In this study, the Artificial Neural Network and the Convolutional Neural Network, two of the most used Deep Learning algorithms, were investigated with an eye toward the recognition process's feature extraction and classification phases. With the assistance of the categorical cross-entropy loss and the ADAM optimizer, the models were trained on the MNIST dataset. Backpropagation and gradient descent are the two methods utilized during the training process of neural networks that contain reLU activations and carry out automatic feature extraction. In computer vision, one of the most common and widely used classifiers is the Convolution Neural Network, sometimes referred to as ConvNets or Convolutional neural networks. This network is used for the recognition and categorization of images.

This paper presents a new method to calculate the geometric dilution of precision (GDOP) of GPS by incorporating the concept of model predictive filtering in the training process of neural networks to learn the relationship between GDOP and the azimuth and elevation of satellite. This method overcomes the shortcomings of the traditional back propagation neural networks, such as the slow convergence speed and easily falling into local minimum. A model predictive filtering algorithm is developed by using network weights as system state variables to optimize the network weights based on the neural network’s error correction. During the training process, the neural network model error is corrected by compensating the deviation between the actual and target output via the model predictive filtering. Experimental results and comparison analysis demonstrate that the proposed method can effectively approximate GDOP with improved accuracy and reduced training time.

Semi-supervised learning provides an effective means to address the challenge of insufficient labeled data in medical image segmentation tasks. However, when a semi-supervised segmentation model is overfitted and exhibits cognitive bias, its performance will deteriorate. Errors stemming from cognitive bias can quickly amplify and become difficult to correct during the training process of neural networks, resulting in the continuous accumulation of erroneous knowledge. To address the issue of error accumulation, a novel learning strategy is required to enhance the accuracy of medical image segmentation. This paper proposes a semi-supervised medical image segmentation network based on mutual learning (MLNet) to alleviate the issue of continuous accumulation of erroneous knowledge. The MLNet adopts a teacher-student network as the backbone framework, training student and teacher networks on labeled data and mutually updating network parameter weights, enabling the two models to learn from each other. Additionally, an image partial exchange algorithm (IPE) as an appropriate perturbation addition method is proposed to reduce the introduction of erroneous information and the disruption to the contextual information of the image. In the 10% labeled experiment on the ACDC dataset, our Dice coefficient reached 89.48%, a 9.28% improvement over the baseline model. In the 10% labeled experiment on the BraTS2019 dataset, the proposed method still performs exceptionally well, achieving 84.56%, surpassing other comparative methods. Compared with other methods, experimental results demonstrate that our approach achieves optimal performance across all metrics, proving its effectiveness and reliability.

In this paper, the ${H}_{\infty }$ optimal control problem for a class of continuous-time nonlinear systems is investigated using event-triggered method. First, the ${H}_{\infty }$ optimal control problem is formulated as a two-player zero-sum (ZS) differential game. Then, an adaptive triggering condition is derived for the ZS game with an event-triggered control policy and a time-triggered disturbance policy. The event-triggered controller is updated only when the triggering condition is not satisfied. Therefore, the communication between the plant and the controller is reduced. Furthermore, a positive lower bound on the minimal intersample time is provided to avoid Zeno behavior. For implementation purpose, the event-triggered concurrent learning algorithm is proposed, where only one critic neural network (NN) is used to approximate the value function, the control policy and the disturbance policy. During the learning process, the traditional persistence of excitation condition is relaxed using the recorded data and instantaneous data together. Meanwhile, the stability of closed-loop system and the uniform ultimate boundedness (UUB) of the critic NN’s parameters are proved by using Lyapunov technique. Finally, simulation results verify the feasibility to the ZS game and the corresponding ${H}_{\infty }$ control problem.

This paper is concentrated on aperiodic sampling and adaptive learning in continuous-time nonlinear systems. The objective is to find the optimal control policy by minimizing an infinite-quadratic cost function in an online fashion. An algorithm based on integral reinforcement learning is proposed for problems with unknown model information, and a novel dynamic triggering method is combined for saving communication as much as possible. The identifying neural network is utilized to free the input dynamics and critic neural network is constructed to approximate the cost function. The weight convergence and asymptotic stability are theoretically elaborated, and afterwards, a numerical example is presented for illustrating the effectiveness and superiority of the algorithm by comparison.

In this paper, the H ∞ optimal control for a class of continuous-time nonlinear systems is investigated using event-triggered method. First, the H ∞ optimal control problem is formulated as a two-player zero-sum differential game. Then, an adaptive triggering condition is derived for the closed loop system with an event-triggered control policy and a time-triggered disturbance policy. For implementation purpose, the event-triggered concurrent learning algorithm is proposed, where only one critic neural network is required. Finally, an illustrated example is provided to demonstrate the effectiveness of the proposed scheme.

In this chapter, we aim at improving the critic learning criterion to cope with the event-based nonlinear \(H_{\infty }\) state feedback control design. First of all, the \(H_{\infty }\) control problem is regarded as a two-player zero-sum game and the adaptive critic mechanism is used to achieve the minimax optimization under event-based environment. Then, based on an improved updating rule, the event-based optimal control law and the time-based worst-case disturbance law are obtained approximately by training a single critic neural network. The initial stabilizing control is no longer required during the implementation process of the new algorithm. Next, the closed-loop system is formulated as an impulsive model and its stability issue is handled by incorporating the improved learning criterion. The infamous Zeno behavior of the present event-based design is also avoided through theoretical analysis on the lower bound of the minimal inter-sample time. Finally, the applications to an aircraft dynamics and a robot arm plant are carried out to verify the efficient performance of the present novel design method.

In this paper, an infinite horizon optimal robust guaranteed cost control scheme of a class of continuous-time uncertain nonlinear systems is established based on adaptive dynamic programming. The main idea lies in that the optimal robust guaranteed cost control problem can be transformed into an optimal control problem. Actually, the optimal cost function of the nominal system is nothing but the optimal guaranteed cost of the original uncertain system. A critic neural network is constructed to help solving the modified Hamilton-Jacobi-Bellman equation corresponding to the nominal system. Then, an additional stabilizing term is introduced to reinforce the updating process of the weight vector and reduce the requirement of an initial stabilizing control. An example is provided to illustrate the effectiveness of the present control approach.

An online adaptive optimal control is proposed for continuous-time nonlinear systems with completely unknown dynamics, which is achieved by developing a novel identifier-critic-based approximate dynamic programming algorithm with a dual neural network (NN) approximation structure. First, an adaptive NN identifier is designed to obviate the requirement of complete knowledge of system dynamics, and a critic NN is employed to approximate the optimal value function. Then, the optimal control law is computed based on the information from the identifier NN and the critic NN, so that the actor NN is not needed. In particular, a novel adaptive law design method with the parameter estimation error is proposed to online update the weights of both identifier NN and critic NN simultaneously, which converge to small neighbourhoods around their ideal values. The closed-loop system stability and the convergence to small vicinity around the optimal solution are all proved by means of the Lyapunov theory. The proposed adaptation algorithm is also improved to achieve finite-time convergence of the NN weights. Finally, simulation results are provided to exemplify the efficacy of the proposed methods.

Deep learning-based segmentation methods for optical coherence tomography (OCT) have demonstrated outstanding performance. However, the stochastic distribution of training data and the inherent limitations of deep neural networks introduce uncertainty into the segmentation process. Accurately estimating this uncertainty is essential for generating reliable confidence assessments and improving model predictions. To address these challenges, we propose a novel uncertainty-guided cross-layer fusion network (UGCFNet) for retinal OCT segmentation. UGCFNet integrates uncertainty quantification into the training process of deep neural networks and leverages this uncertainty to enhance segmentation accuracy. Our model employs an encoder-decoder architecture that quantitatively assesses uncertainty at multiple stages, directing the network's focus toward regions with higher uncertainty. By facilitating cross-layer feature fusion, UGCFNet enhances the comprehensive understanding of both semantic information and morphological details. Additionally, we incorporate an improved Bayesian neural network loss function alongside an uncertainty-aware loss function, enabling the network to effectively utilize these mechanisms for better uncertainty modeling. We conducted extensive experiments on the publicly available AI-Challenger and OIMHS OCT segmentation datasets. The training, validation, and testing sets of the AI-Challenger dataset are comprised of 32, 8, and 43 OCT volumes, yielding a total of 4096, 1024, and 5504 B-scans, respectively. The training, validation, and testing sets of the OIMHS dataset consist of 100, 25, and 25 OCT volumes, resulting in 2,310, 798, and 751 B-scans, respectively. The results demonstrate that UGCFNet achieves state-of-the-art performance, with average Dice similarity coefficients of 79.47% and 93.22% on the respective datasets. Our proposed UGCFNet significantly advances retinal OCT segmentation by integrating uncertainty guidance and cross-level feature fusion, offering more reliable and accurate segmentation outcomes.