Article
Automation & Control Systems
Xiong Yang, Mengmeng Xu, Qinglai Wei
Summary: This article proposes a simultaneous policy iteration (SPI) algorithm to solve the H-infinity control problem of nonlinear systems with unavailable dynamics and asymmetric saturating actuators. The SPI algorithm converts the control problem into a zero-sum game and solves the corresponding Hamilton-Jacobi-Isaacs equation. A critic, an actor, and a perturbation neural network (NN) are constructed to estimate the cost function, control policy, and perturbation, respectively. The SPI algorithm allows arbitrary control policies and perturbations in the learning process and does not require the persistence of the excitation condition.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Jing Zhu, Peng Zhang, Yijing Hou
Summary: The study introduces an optimal regulation strategy based on adaptive dynamic programming for input-constrained nonlinear time-delay systems, utilizing a neural network for real-time weight updates to reduce computational complexity and storage space.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Multidisciplinary Sciences
Zhenghui Li, Julien Le Kernec, Qammer Abbasi, Francesco Fioranelli, Shufan Yang, Olivier Romain
Summary: To address the problem of limited computational resources on embedded platforms, researchers propose an adaptive magnitude thresholding approach to highlight the region of interest in multi-domain micro-Doppler signatures. This approach extracts salient features with simplicity and low computational cost. Experimental results show that the proposed approach achieves an accuracy of up to 93.1% for six activities, outperforming state-of-the-art deep learning methods with significant reductions in training time, memory footprint, and inference time. These results are crucial for enabling embedded platform deployment.
SCIENTIFIC REPORTS
(2023)
Article
Computer Science, Information Systems
Zhonghong Ou, Zhaofengnian Wang, Fenrui Xiao, Baiqiao Xiong, Hongxing Zhang, Meina Song, Yan Zheng, Pan Hui
Summary: With the popularity of 5G networks and IoT applications, real-time environmental awareness becomes crucial. However, small object detection still faces challenges due to limited scales and low detection accuracy. To address these issues, the proposed AD-RCNN employs dynamic region proposal network, visual attention scheme, and adaptive dynamic training module. Experimental results demonstrate that AD-RCNN outperforms existing methods in terms of mAP and FPS.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Energy & Fuels
Senem Sezer, Furkan Kartal, Ugur Ozveren
Summary: With the growing population and industrial developments, the supply of energy from a feasible and widely available source is important. Biomass gasification is a promising technology that produces lower emissions and allows efficient conversion. The gas obtained from the gasification process, especially in steam gasification, consists of a considerable amount of H-2 and is used in solid oxide fuel cells (SOFC) to generate electricity. However, further research is needed to achieve high energy efficiency in integrated gasification-SOFC systems.
Article
Engineering, Aerospace
Qiang Qi, Xiangwei Bu, Baoxu Jiang
Summary: This study presents an intelligent optimization control method for waverider vehicles based on adaptive dynamic programming (ADP). The method achieves stability, robustness, and near optimization of the tracking problem for waverider vehicles by designing baseline controllers, implementing novel auxiliary systems, and developing transient optimal controllers using a single-network adaptive critic method.
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART G-JOURNAL OF AEROSPACE ENGINEERING
(2023)
Article
Thermodynamics
Guoping Xu, Zeting Yu, Lei Xia, Changjiang Wang, Shaobo Ji
Summary: This study presents a framework and methodology for improving the performance of solid oxide fuel cells (SOFC) using computational fluid dynamics (CFD) modeling, artificial neural network (ANN), and genetic algorithm (GA). The results show that the developed ANN surrogate model achieved the best accuracy for predicting SOFC performance. The combination of CFD modeling, ANN, and GA provides a promising solution for accurately and rapidly predicting, improving, and optimizing the performance of SOFC.
ENERGY CONVERSION AND MANAGEMENT
(2022)
Article
Engineering, Marine
Quan Shi, Changjun Hu, Xin Li, Xiaoxian Guo, Jianmin Yang
Summary: This paper proposes a finite-time constrained control method for dynamic positioning (DP) to ensure operational safety and prevent potential marine accidents in harsh environments by preventing violations of system constraints.
Article
Computer Science, Artificial Intelligence
Yanchao Sun, Yutong Du, Hongde Qin
Summary: This paper proposes a containment control algorithm using a neural network for multiple benthic AUVs under time-varying constraints. The algorithm compensates for environmental disturbances and system model uncertainties and ensures control performance with the aid of an exponential boundary constraint.
Article
Computer Science, Artificial Intelligence
Kaixin Lu, Zhi Liu, Haoyong Yu, C. L. Philip Chen, Yun Zhang
Summary: Solving the problem of optimizing performance and satisfying constraints in control operation usually involves a complicated and time-consuming learning process with neural networks, and is only applicable for simple or time-invariant constraints. This paper proposes a newly adaptive neural inverse approach that removes these restrictions. By introducing a new universal barrier function to transform the constrained system into an equivalent one with no constraint, and designing a switched-type auxiliary controller and a modified criterion for inverse optimal stabilization, it is proven that optimal performance can be achieved with a computationally attractive learning mechanism and all the constraints are never violated. Furthermore, improved transient performance is obtained by explicitly designing the bound of the tracking error. An illustrative example verifies the proposed methods.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Materials Science, Ceramics
Yonghyun Lim, Hojae Lee, Junghum Park, Young-Beom Kim
Summary: Solid oxide fuel cells (SOFCs) have the potential to become the next-generation energy conversion systems. However, the high processing temperature required for their multi-layer ceramic components has been a major barrier for commercialization. Researchers have developed a bi-layer sintering method that effectively lowers the sintering temperature of the electrolyte, leading to comparable cell performance with significantly reduced temperature.
CERAMICS INTERNATIONAL
(2022)
Article
Engineering, Mechanical
Jianfeng Wang, Ping Zhang, Yan Wang, Zhicheng Ji
Summary: This paper investigates the problem of adaptive optimal tracking control for full-state constrained strict-feedback nonlinear systems with input delay. A novel control approach is developed by combining the backstepping design technique and adaptive dynamic programming (ADP) theory. The approach utilizes Pade approximation to handle input delay and barrier Lyapunov functions for state constraints. Neural networks are employed to approximate unknown functions. An adaptive backstepping feedforward controller is developed to convert the tracking task into an equivalent regulation problem. A critic network is constructed within the ADP framework to obtain the optimal control. The resulting controller consists of feedforward and feedback parts, while ensuring that all signals are uniformly ultimately bounded in the closed-loop system.
NONLINEAR DYNAMICS
(2023)
Article
Computer Science, Information Systems
Musa Yilmaz, Resat Celikel, Ahmet Gundogdu
Summary: In this study, an Artificial Neural Network (ANN)-based MPPT method, called the ANN-based Adaptive Reference Voltage (ARV) method, is proposed to determine the optimal operating point of the PV panel. The proposed method demonstrates superior efficiency in rapidly changing atmospheric conditions compared to traditional methods.
Article
Energy & Fuels
Bo Yang, Yijun Chen, Zhengxun Guo, Jingbo Wang, Chunyuan Zeng, Danyang Li, Hongchun Shu, Jieshan Shan, Ting Fu, Xiaoshun Zhang
Summary: A parameter identification technique based on the LMBP algorithm is proposed in this study, which is validated through two typical models to show its performance under different operation conditions. Simulation results demonstrate that the LMBP algorithm significantly improves accuracy, speed, and stability compared to other mainstream meta-heuristic algorithms.
INTERNATIONAL JOURNAL OF ENERGY RESEARCH
(2021)
Article
Chemistry, Physical
Mohammad Hossein Golbabaei, Mohammadreza Saeidi Varnoosfaderani, Arsalan Zare, Hirad Salari, Farshid Hemmati, Hamid Abdoli, Bejan Hamawandi
Summary: This study proposes a machine learning approach to predict the performance of anode-supported solid oxide fuel cells (SOFCs) based on architectural and operational variables. The resulting neural network model can accurately predict the effect of cell parameters on the current-voltage dependency, surpassing the accuracy of previous mathematical and artificial neural network models.
Article
Computer Science, Artificial Intelligence
Rui Lv, Dingheng Wang, Jiangbin Zheng, Zhao-Xu Yang
Summary: In this paper, the authors investigate tensor decomposition for neural network compression. They analyze the convergence and precision of tensor mapping theory, validate the rationality of tensor mapping and its superiority over traditional tensor approximation based on the Lottery Ticket Hypothesis. They propose an efficient method called 3D-KCPNet to compress 3D convolutional neural networks using the Kronecker canonical polyadic (KCP) tensor decomposition. Experimental results show that 3D-KCPNet achieves higher accuracy compared to the original baseline model and the corresponding tensor approximation model.
Article
Computer Science, Artificial Intelligence
Xiangkun He, Zhongxu Hu, Haohan Yang, Chen Lv
Summary: In this paper, a novel constrained multi-objective reinforcement learning algorithm is proposed for personalized end-to-end robotic control with continuous actions. The approach trains a single model using constraint design and a comprehensive index to achieve optimal policies based on user-specified preferences.
Article
Computer Science, Artificial Intelligence
Zhijian Zhuo, Bilian Chen, Shenbao Yu, Langcai Cao
Summary: In this paper, a novel method called Expansion with Contraction Method for Overlapping Community Detection (ECOCD) is proposed, which utilizes non-negative matrix factorization to obtain disjoint communities and applies expansion and contraction processes to adjust the degree of overlap. ECOCD is applicable to various networks with different properties and achieves high-quality overlapping community detection.
Article
Computer Science, Artificial Intelligence
Yizhe Zhu, Chunhui Zhang, Jialin Gao, Xin Sun, Zihan Rui, Xi Zhou
Summary: In this work, the authors propose a Contrastive Spatio-Temporal Distilling (CSTD) approach to improve the detection of high-compressed deepfake videos. The approach leverages spatial-frequency cues and temporal-contrastive alignment to fully exploit spatiotemporal inconsistency information.
Review
Computer Science, Artificial Intelligence
Laijin Meng, Xinghao Jiang, Tanfeng Sun
Summary: This paper provides a review of coverless steganographic algorithms, including the development process, known contributions, and general issues in image and video algorithms. It also discusses the security of coverless steganography from theoretical analysis to actual investigation for the first time.
Article
Computer Science, Artificial Intelligence
Yajie Bao, Tianwei Xing, Xun Chen
Summary: Visual question answering requires processing multi-modal information and effective reasoning. Neural-symbolic learning is a promising method, but current approaches lack uncertainty handling and can only provide a single answer. To address this, we propose a confidence based neural-symbolic approach that evaluates NN inferences and conducts reasoning based on confidence.
Article
Computer Science, Artificial Intelligence
Anh H. Vo, Bao T. Nguyen
Summary: Interior style classification is an interesting problem with potential applications in both commercial and academic domains. This project proposes a method named ISC-DeIT, which combines data-efficient image transformer architectures and knowledge distillation, to address the interior style classification problem. Experimental results demonstrate a significant improvement in predictive accuracy compared to other state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Shashank Kotyan, Danilo Vasconcellos Vargas
Summary: This article introduces a novel augmentation technique called Dynamic Scanning Augmentation to improve the accuracy and robustness of Vision Transformer (ViT). The technique leverages dynamic input sequences to adaptively focus on different patches, resulting in significant changes in ViT's attention mechanism. Experimental results demonstrate that Dynamic Scanning Augmentation outperforms ViT in terms of both robustness to adversarial attacks and accuracy against natural images.
Article
Computer Science, Artificial Intelligence
Hiba Alqasir, Damien Muselet, Christophe Ducottet
Summary: The article proposes a solution to improve the learning process of a classification network by providing shape priors, reducing the need for annotated data. The solution is tested on cross-domain digit classification tasks and a video surveillance application.
Article
Computer Science, Artificial Intelligence
Dexiu Ma, Mei Liu, Mingsheng Shang
Summary: This paper proposes a method using neural dynamics solvers to solve infinity-norm optimization problems. Two improved solvers are constructed and their effectiveness and superiority are demonstrated through theoretical analysis and simulation experiments.
Article
Computer Science, Artificial Intelligence
Francesco Gregoretti, Giovanni Pezzulo, Domenico Maisto
Summary: Active Inference is a computational framework that uses probabilistic inference and variational free energy minimization to describe perception, planning, and action. cpp-AIF is a header-only C++ library that provides a powerful tool for implementing Active Inference for Partially Observable Markov Decision Processes through multi-core computing. It is cross-platform and improves performance, memory management, and usability compared to existing software.
Article
Computer Science, Artificial Intelligence
Zelin Ying, Dawei Cheng, Cen Chen, Xiang Li, Peng Zhu, Yifeng Luo, Yuqi Liang
Summary: This paper proposes a novel stock market trends prediction framework called SMART, which includes a self-supervised stock technical data sequence embedding model S3E. By training with multiple self-supervised auxiliary tasks, the model encodes stock technical data sequences into embeddings and uses the learned sequence embeddings for predicting stock market trends. Extensive experiments on China A-Shares market and NASDAQ market prove the high effectiveness of our model in stock market trends prediction, and its effectiveness is further validated in real-world applications in a leading financial service provider in China.
Article
Computer Science, Artificial Intelligence
Hao Li, Hao Jiang, Dongsheng Ye, Qiang Wang, Liang Du, Yuanyuan Zeng, Liu Yuan, Yingxue Wang, C. Chen
Summary: DHGAT1, a dynamic hyperbolic graph attention network, utilizes hyperbolic metric properties to embed dynamic graphs. It employs a spatiotemporal self-attention mechanism and weighted node representations, resulting in excellent performance in link prediction tasks.
Article
Computer Science, Artificial Intelligence
Jiehui Huang, Zhenchao Tang, Xuedong He, Jun Zhou, Defeng Zhou, Calvin Yu-Chian Chen
Summary: This study proposes a progressive learning multi-scale feature blending model for image deraining tasks. The model utilizes detail dilation and texture extraction to improve the restoration of rainy images. Experimental results show that the model achieves near state-of-the-art performance in rain removal tasks and exhibits better rain removal realism.
Article
Computer Science, Artificial Intelligence
Lizhi Liu, Zilin Gao, Yinhe Wang, Yongfu Li
Summary: This paper proposes a novel discrete-time interconnected model for depicting complex dynamical networks. The model consists of nodes and edges subsystems, which consider the dynamic characteristic of both nodes and edges. By designing control strategies and coupling modes, the stabilization and synchronization of the network are achieved. Simulation results demonstrate the effectiveness of the proposed methods.