Neural Computing and Applications

In this paper, an online optimization approach of a fractional-order PID controller based on a fractional-order actor-critic algorithm (FOPID-FOAC) is proposed. The proposed FOPID-FOAC scheme exploits the advantages of the FOPID controller and FOAC approaches to improve the performance of nonlinear systems. The proposed FOAC is built by developing a FO-based learning approach for the actor-critic neural network with adaptive learning rates. Moreover, a FO rectified linear unit (RLU) is introduced to enable the AC neural network to define and optimize its own activation function. By the means of the Lyapunov theorem, the convergence and the stability analysis of the proposed algorithm are investigated. The FO operators for the FOAC learning algorithm are obtained using the gray wolf optimization (GWO) algorithm. The effectiveness of the proposed approach is proven by extensive simulations based on the tracking problem of the two degrees of freedom (2-DOF) helicopter system and the stabilization issue of the inverted pendulum (IP) system. Moreover, the performance of the proposed algorithm is compared against optimized FOPID control approaches in different system conditions, namely when the system is subjected to parameter uncertainties and external disturbances. The performance comparison is conducted in terms of two types of performance indices, the error performance indices, and the time response performance indices. The first one includes the integral absolute error (IAE), and the integral squared error (ISE), whereas the second type involves the rising time, the maximum overshoot (Max. OS), and the settling time. The simulation results explicitly indicate the high effectiveness of the proposed FOPID-FOAC controller in terms of the two types of performance measurements under different scenarios compared with the other control algorithms.

Drones, also known as unmanned aerial vehicles, can be used to aid various aerial cinematography tasks. However, using drones for aerial cinematography requires the coordination of several people, increasing the cost and reducing the shooting flexibility, while also increasing the cognitive load of the drone operators. To overcome these limitations, we propose a deep reinforcement learning (RL) method for continuous fine-grained drone control, that allows for acquiring high-quality frontal view person shots. To this end, a head pose image dataset is combined with 3D models and face alignment/warping techniques to develop an RL environment that realistically simulates the effects of the drone control commands. An appropriate reward-shaping approach is also proposed to improve the stability of the employed continuous RL method. Apart from performing continuous control, it was demonstrated that the proposed method can be also effectively combined with simulation environments that support only discrete control commands, improving the control accuracy, even in this case. The effectiveness of the proposed technique is experimentally demonstrated using several quantitative and qualitative experiments.

Parameter optimization and feature selection influence the classification accuracy of support vector machine (SVM) significantly. In order to improve classification accuracy of SVM, this paper hybridizes chaotic search and gravitational search algorithm (GSA) with SVM and presents a new chaos embedded GSA-SVM (CGSA-SVM) hybrid system. In this system, input feature subsets and the SVM parameters are optimized simultaneously, while GSA is used to optimize the parameters of SVM and chaotic search is embedded in the searching iterations of GSA to optimize the feature subsets. Fourteen UCI datasets are employed to calculate the classification accuracy rate in order to evaluate the developed CGSA-SVM approach. The developed approach is compared with grid search and some other hybrid systems such as GA-SVM, PSO-SVM and GSA-SVM. The results show that the proposed approach achieves high classification accuracy and efficiency compared with well-known similar classifier systems.

The major key attributes of decision-making during emergency to de-escalate disaster, reduce fatality and prevent asset loss are time and the efficiency of the process. Decision-makers faced the challenge of accessing adequate and precise information during emergency cases due to the time limitation, inadequate data on and about the disasters and thus decision-making process becomes complex and complicated. A well-advanced and developed mathematical tool is required to respond adequately in the presence of these challenges. The current study investigates the effects of post-flood management plans in Iran through sustainable development features in the possible early time. A new hybrid emergency decision-making approach integrating the best–worst method (BWM), Z numbers and zero‐sum game is proposed to ensure much more effective responses in realistic cases. The importance weights of criteria are computed using the BWM, the payoff assessments of decision-makers are collected employing the Z numbers, and finally, the zero‐sum game method is utilized to rank the alternative of emergency solutions. The proposed hybrid approach assists the decision-makers to deal decisively with the ambiguity associated with the data for assessing and evaluating the emergency circumstances. To show the efficiency of the proposed approach, a real-life example of the Golestan flood of 2019 is presented. More so, a comparison analysis is performed to assess the practicability and feasibility of the proposed hybrid approach. The result indicates that the proposed methodology has considerable merits compared with the existing tools and can adequately deal with these shortages. In this case, the aircraft emergency delivery system of the relief supplies is obtained as the best solution to the problem.

The turning operation using a self-propelled rotary tool (SPRT) is efficient manufacturing for hard machining. However, optimization-based energy saving of the rotary turning has not presented because of expensive implementation. This study addresses a parameter optimization to enhance the machining rate (MR) and decrease the energy consumption (ET) as well as the machined roughness (R) for a hard turning using SPRT. The process inputs are the inclined angle (α), depth of cut (a), feed rate (f), and cutting speed (V). The hard turning runs were performed using the experimental plan generated by the Taguchi approach. The adaptive neuro-fuzzy inference system (ANFIS) was used to construct the correlations between the process inputs and responses. The analytic hierarchy process technique was adopted to explore the weight values of the outputs, and the optimum solution was obtained utilizing the adaptive simulated annealing. Moreover, an integrative approach using the response surface method and utilizing the desirability approach was employed to select the optimal outcomes and compare with the proposed technique. The findings revealed that the proposed ANFIS models minimize the predictive error in comparison with the traditional one. The accurate weights may help to select reliable optimal results. The optimal values of the α, a, f, and V are 18°, 0.15 mm, 0.40 mm/rev, and 200 mm/min, respectively. Moreover, ET and roughness are decreased by 50.29% and 19.77%, while the MR is enhanced by 33.16%, respectively, as compared to the general process.

The automatic and precise perceptual parsing of Chinese landscape paintings (CLP) significantly aids in the digitization and recreation of artworks. Manual extraction and analysis of objects in CLPs is challenging, even for expert painters with professional knowledge and sharp discernment. Two main key reasons restricted the development of CLP parsing: (1) a lack of pixel-level labeled data used to supervise model training, and (2) the inherent complexity of CLP images compared to real scenes, characterized by varied scales, diverse textures, and intricate empty spaces. To address these challenges, we first construct a pixel-level annotated CLP segmentation datasets to advance perceptual parsing. Then, a novel CLP Perceptual Parsing (CLPPP) model is designed to fully utilize the intrinsic features of CLP images. To dynamically and adaptively capture context information, we introduced a set of learnable kernels into the CLPPP model based on the multiscale features of objects within CLPs. This enabled the model to learn an appropriate receptive field for context information extraction. Additionally, a positional attention head is devised to effectively eliminate noise from the intergroup and help the kernel gain inter-object position information. This iterative optimization process is helpful to learn powerful feature representations for different textures in CLPs. The experiment results demonstrate that the proposed CLPPP model outperforms state-of-the-art methods with mIoU, aAcc, and mAcc scores of 55.45, 75.08, and 71.15, respectively, achieving a large margin on the CLP dataset under consistent conditions.

Diffusion tensor imaging (DTI) is a non-invasive technique for analyzing the movement of water in the brain. However, the precision of measurements required for tracking white matter pathways can lead to long scan times, which can be challenging for some patient populations such as pediatric patients. To address this issue, researchers have been experimenting with deep learning techniques for faster estimation of DTI parameters, which are helpful in neurological diagnosis, of diffusion-weighted images. Our proposed solution is a transformer neural network-based approach for fast estimation of diffusion tensor parameters using sparse measurements. While there have been attempts to address this problem, our proposed model handles both scalable and generalized estimation of DTI parameters using multiple sparse measurements. Through experimentation on the Human Connectome Project (HCP) Young Adult benchmark dataset, our proposed model demonstrated state-of-the-art results in terms of fractional anisotropy (FA), axial diffusivity (AD), and mean diffusivity (MD) when compared to traditional linear least square (LLS) fitting and 3D U-Net model with $$16 \times 16 \times 16$$ input size (3D U-Net16).

Due to the miscellaneous ambiguity of semantics in open-domain conversation, current deep dialogue models disregard to detect potential emotional and action response features in the latent space, which leads to the general tendency to produce inaccurate and irrelevant sentences. To address this problem, we propose a semantic-aware conditional variational autoencoder that discriminates the sentiment and action responses features in the latent space for one-to-many open-domain dialogue generation. Specifically, explicit controllable variables are leveraged from the proposed module to create diverse conversational texts. This controllable variable can constrain the distribution of the latent space, disentangling the latent space features during training. Furthermore, the feature disentanglement improves the dialogue generation in terms of deep learning interpretability and text quality, which also reveals the latent features of different emotions on the logic of text generation.

Early detection of unnatural control chart patterns (CCP) is desirable for any industrial process. Most of recent CCP recognition works are on statistical feature extraction and artificial neural network (ANN)-based recognizers. In this paper, a two-stage hybrid detection system has been proposed using support vector machine (SVM) with self-organized maps. Direct Cosine transform of the CCP data is taken as input. Simulation results show significant improvement over conventional recognizers, with reduced detection window length. An analogous recognition system consisting of statistical feature vector input to the SVM classifier is further developed for comparison.