Article
Computer Science, Artificial Intelligence
Kyoungok Kim
Summary: This study introduces an enhanced kNN algorithm NCC-kNN for classification of imbalanced datasets, especially performing well on data with low positive class coherence.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Artificial Intelligence
Niloofar Rastin, Mansoor Zolghadri Jahromi, Mohammad Taheri
Summary: The generalized Prototype Weighting (PW) scheme introduced in this paper supports various objective functions including F-measure, and is designed to significantly improve performance in multi-label classification by using gradient descent to specify parameters.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Information Systems
Lingli Li, Jie Xu, Yu Li, Jingwen Cai
Summary: HCTree+ is a new index that aims to improve query performance based on incoming queries and their results. By dynamically optimizing the index using incoming query results, it strikes a balance between accuracy and efficiency.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Jue Shi, Xiaofang Chen, Yongfang Xie, Hongliang Zhang, Yubo Sun
Summary: With the increasing demands for profit and safety, advanced intelligent analysis for abnormity forecast of the synthetical balance of material and energy (AF-SBME) on aluminum reduction cells (ARCs) becomes more necessary. This article proposes a refined R-KNN classifier called DR-KNN/CE, which improves R-KNN by using expert knowledge as external assistance and enhancing self-ability to mine and synthesize data knowledge. The experiments conducted on AF-SBME have demonstrated that DR-KNN/CE not only effectively improves R-KNN, but also outperforms other existing high-performance data-driven classifiers.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Information Systems
Xiuwen Gong, Jiahui Yang, Dong Yuan, Wei Bao
Summary: In this paper, the authors propose a novel method called Generalized Large Margin kNN for Partial Label Learning (GLMNN-PLL) to address noise in partial label learning (PLL). The method learns a new metric and reorganizes the data structure to make similarly labeled instances closer while separating differently labeled instances. The proposed GLMNN-PLL outperforms existing approaches in comprehensive experiments on various datasets.
IEEE TRANSACTIONS ON MULTIMEDIA
(2022)
Article
Computer Science, Artificial Intelligence
Jie Gui, Yuan Cao, Heng Qi, Keqiu Li, Jieping Ye, Chao Liu, Xiaowei Xu
Summary: Hashing methods are widely used in Approximate Nearest Neighbor search for big data due to their low storage requirements and high search efficiency. However, the calculation of Hamming distance can lead to confusing rankings. Introducing bit-level weights in weighted Hamming space can improve search accuracy, but existing methods are typically based on time-consuming linear scans.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Computer Science, Information Systems
Yuming Wu, Lei Zhang, Ren Lou, Xinghua Li
Summary: The increasing number of vehicles has made traffic safety more complicated. Autonomous vehicles (AVs) have the potential to greatly reduce accidents. This study proposes a lane changing maneuver recognition model based on physical data and machine learning, achieving good results.
Article
Energy & Fuels
Arangarajan Vinayagam, Veerapandiyan Veerasamy, Mohd Tariq, Asma Aziz
Summary: This paper proposes a heterogeneous based ensemble classifiers method for identifying and classifying power system disturbances in wind integrated microgrid network. The method utilizes discrete wavelet transform for feature extraction and involves two levels of classification. Experimental results demonstrate the effectiveness and robustness of the proposed stacking ensemble model.
SUSTAINABLE ENERGY GRIDS & NETWORKS
(2022)
Article
Engineering, Multidisciplinary
S. Naveen Venkatesh, V. Sugumaran
Summary: This study aims to identify visual faults in photovoltaic modules using machine vision and machine learning techniques, specifically through the classification of normal RGB images with the fusion of deep learning and machine learning methods.
Article
Computer Science, Information Systems
Dakang Liu, Zexiao Liang, Wenlang Li, Yuan Liu, Jianzhong Li
Summary: This paper proposes a method to improve conventional KNN methods in face classification by utilizing high-frequency texture components. The experimental results demonstrate that the proposed method outperforms other machine learning methods and provides similar accuracy to deep learning methods that require more computational resources.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Xianyong Zhang, Hongyuan Gou
Summary: This paper develops more general and robust double-quantitative classifiers by constructing two statistical-average double-quantitative distances based on neighborhood granulation and distance measurement. The experimental results demonstrate that these classifiers have better applicability and performance.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Ying Ma, Rui Huang, Ming Yan, Guoqi Li, Tian Wang
Summary: This paper proposes an Attention-based Local Mean K-Nearest Centroid Neighbor Classifier (ALMKNCN) that addresses the issue of KNN-based methods not fully considering the impact of different training samples in classification tasks. By integrating the attention mechanism with nearest centroid neighbor computation, ALMKNCN takes into account the influence of each training query sample and achieves superior performance compared to state-of-art KNN-based methods.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Yibang Ruan, Yanshan Xiao, Zhifeng Hao, Bo Liu
Summary: The paper introduces a nearest-neighbor search model for distance metric learning (NNS-DML), which constructs metric optimization constraints by searching different optimal nearest-neighbor numbers for each training instance. This model reduces the influence of irrelevant features on similar and dissimilar instance pairs and develops a k-free nearest-neighbor model for classification problems. Extensive experiments show that NNS-DML outperforms state-of-the-art distance metric learning methods.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Yazhou Yang, Marco Loog
Summary: Although much effort has been devoted to designing new active learning algorithms, little attention has been paid to the initialization problem. This paper treats the initialization of active learning as a separate research problem and proposes a new active initialization criterion. Experimental results demonstrate that the proposed method often achieves a smaller number of queried samples for initialization compared to other methods.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Artificial Intelligence
Yikun Wang, Zhibin Pan, Jing Dong
Summary: A new neighbor selection method called two-layer nearest neighbor (TLNN) rule is proposed in this study, which considers both the query's neighborhood and the neighborhoods of all selected training instances. Experimental results show that the proposed TLNN rule outperforms not only the kNN classifier, but also seven other state-of-the-art NN-based classifiers.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Robotics
Sheng Gao, Hao Zhang, Zhuping Wang, Chao Huang
Summary: This study explores an optimal strategy for mixed data injection attacks using input derivatives to disrupt system performance and minimize cost. Additionally, a switching mixed data injection attack strategy is proposed to increase complexity, concealment, and energy efficiency. Numerical results and comparative experiments are provided to demonstrate the effectiveness of the proposed method.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2021)
Article
Engineering, Electrical & Electronic
Xiaoyuan Zheng, Hao Zhang, Zhuping Wang, Chao Huang, Huaicheng Yan
Summary: This study investigates the problem of stochastic event-based distributed fusion estimation for a class of Gaussian systems, and proposes a two-step fusion estimation method based on stochastic event-triggered mechanisms. By considering channel fading and designing a fusion algorithm, the goal of eliminating discrepancies among local sensor estimations is achieved.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
(2022)
Article
Automation & Control Systems
Chao Huang, Linlin Zhang, Changzhu Zhang, Hao Zhang
Summary: In this paper, a robust predictor feedback controller design is proposed for enlarging the admissible delay mismatch while maintaining the convergence rate within a prescribed level. The controller synthesis problem is shown to be cast into a generalised eigenvalue problem (GEVP).
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE
(2022)
Article
Automation & Control Systems
Chao Huang, Gang Feng, Hao Zhang, Zhuping Wang
Summary: This article proposes a novel system identification method based on the notion of invariant subspace, with advantages including identifying linear continuous-time models from slowly sampled data, establishing consistency of model parameters, finding global optimum through solving linear least-square problems, and implementing identification algorithms online with explicit convergence rates.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2022)
Article
Automation & Control Systems
Yongxiao Tian, Huaicheng Yan, Hao Zhang, Jun Cheng, Hao Shen
Summary: This article focuses on the output feedback control problem for continuous-time hidden semi-Markov jump systems with time delays. By establishing emission probabilities relationship, the asynchronous information between controller modes and system modes is better described, and new parameter-dependent stabilization conditions are proposed.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2022)
Article
Computer Science, Artificial Intelligence
Yuan Wang, Huaicheng Yan, Hao Zhang, Hao Shen, Hak-Keung Lam
Summary: This article discusses the design problem of interval type-2 Takagi-Sugeno fuzzy asynchronous controller for nonlinear multiagent systems in discrete-time context. It proposes a dynamic event-triggered scheme to mitigate the communication burden. The article utilizes a unique IT2 T-S fuzzy model and a hidden Markov model to handle the asynchronous phenomena and nonlinear characteristics. The effectiveness and practicality of the proposed control scheme are demonstrated through examples.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Zhichen Li, Huaicheng Yan, Hao Zhang, Hak-Keung Lam, Congzhi Huang
Summary: In this article, a sampled-data ESO design approach is proposed for uncertain nonlinear systems. By using fuzzy modeling and Takagi-Sugeno fuzzy formulation, the nonlinear estimating efficiency and linear numerical tractability are integrated in a unified framework. An exponential convergence criterion for TSFESO is presented, and the observer design method is also provided. Numerical examples demonstrate the superiority and effectiveness of the proposed approaches.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Hao Zhang, Yajie Zou, Xiaoxue Yang, Hang Yang
Summary: This study adopts a novel architecture called TFT to predict freeway speed, which can capture short-term and long-term temporal dependence and improve prediction accuracy by incorporating various types of inputs.
Article
Computer Science, Artificial Intelligence
Xindi Yang, Hao Zhang, Zhuping Wang
Summary: This article introduces a data-based distributed control algorithm to address the consensus control problem in multiagent systems, successfully overcoming the challenges of asynchronous learning. By incorporating an actor-critic structure and neural networks, the algorithm achieves convergence and optimality in both synchronous and asynchronous cases.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Engineering, Electrical & Electronic
Zhichen Li, Yu Zhao, Huaicheng Yan, Hao Zhang, Lu Zeng, Xiaolei Wang
Summary: This paper investigates the time-varying formation tracking control problem for multi-agent systems (MASs). The main objective is to achieve asymptotic convergence of formation tracking error despite nonparametric and nonvanishing uncertainties. A fuzzy extended state observer (FESO) based on event-triggered mechanism is proposed to estimate unmodeled dynamics and external disturbances. Furthermore, a distributed control law is developed using neighborhood formation tracking errors, and total disturbance compensation is introduced to attenuate uncertainty influence in real time. The effectiveness of the proposed control protocol is demonstrated using a numerical example on unmanned aerial vehicle swarm system.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
(2023)
Article
Automation & Control Systems
Min Xue, Huaicheng Yan, Hao Zhang, Xisheng Zhan, Kaibo Shi
Summary: This article discusses compensation-based output feedback control for Takagi-Sugeno fuzzy Markov jump systems subject to packet losses. Utilizing single exponential smoothing as a compensation scheme, an asynchronous output feedback controller is designed with stochastic stability and strict dissipativity. Novel sufficient conditions for controller existence based on mode-dependent Lyapunov function are derived, along with an algorithm for determining the optimal smoothing parameter. Simulation results demonstrate the validity and advantages of the design approach.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Automation & Control Systems
Bo Qin, Huaicheng Yan, Hao Zhang, Yueying Wang, Simon X. Yang
Summary: This paper proposes a control method based on an enhanced reduced-order extended state observer for precise motion control in mobile robot systems. The method reduces energy consumption by estimating unknown state error and negative disturbance and uses a simple state-feedback-feedforward controller to track the reference signal and compensate for negative disturbance.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Automation & Control Systems
Xindi Yang, Hao Zhang, Zhuping Wang, Huaicheng Yan, Changzhu Zhang
Summary: This article presents a model-free predictive control algorithm for real-time systems that improves system performance through data-driven multi-step policy gradient reinforcement learning. By learning from offline and real-time data, the algorithm avoids the need for knowledge of system dynamics in its design and application. Cooperative games are used to model predictive control as multi-agent optimization problems and ensure the optimal predictive control policy. Neural networks are employed to approximate the action-state value function and predictive control policy, with weights determined using weighted residual methods. Numerical results demonstrate the effectiveness of the proposed algorithm.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Automation & Control Systems
Zhichen Li, Huaicheng Yan, Hao Zhang, Simon X. Yang, Mengshen Chen
Summary: This article investigates the design problem of an extended state observer (ESO) for uncertain nonlinear systems subject to limited network bandwidth. A dynamic event-triggered communication protocol is proposed for rational information exchange scheduling, achieving a desirable tradeoff between observation performance and communication resource efficiency. A novel paradigm of event-triggered Takagi-Sugeno fuzzy ESO is introduced, and the TSFESO design approach is derived to carry out exponential convergence for estimation error dynamics under the dynamic event-triggered mechanism. The effectiveness of the proposed method is verified through numerical examples, expanding the application scope of ESO with improved event-triggered strategies.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Computer Science, Artificial Intelligence
Yunkai Lv, Hao Zhang, Zhuping Wang, Huaicheng Yan
Summary: This article focuses on the real-time localization problem in dynamic multi-agent systems with measurement and communication noises under directed graphs. It introduces barycentric coordinates to describe the relative position between agents and proposes a novel robust distributed localization estimation algorithm based on iterative learning. The algorithm uses a relative-distance unbiased estimator constructed from historical iterative information to suppress measurement noise, and a designed stochastic approximation method with two iterative-varying gains to inhibit communication noise. The asymptotic convergence of the proposed methods is derived under certain conditions of zero-mean and independent distribution of measurement and communication noises. Numerical simulations and robot experiments are conducted to test and verify the effectiveness and practicability of the proposed methods.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)