Article
Engineering, Multidisciplinary
Andrea Franceschini, Massimiliano Ferronato, Matteo Frigo, Carlo Janna
Summary: Frictional contact is a challenging problem in computational mechanics, requiring solutions for both non-linear and linear systems. This paper proposes a constraint preconditioning method called Reverse, specifically designed for contact mechanics. The method provides faster numerical solutions and is suitable for high-performance computing implementations.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2022)
Article
Computer Science, Information Systems
Wei Guo, Jianjiang Yu, Caigen Zhou, Xiaofeng Yuan, Zhanxiu Wang
Summary: A new robust and compact broad learning system (RCBLS) is proposed to address the deficiencies in outlier environments and model structure of BLS. The RCBLS utilizes an M-estimator-based loss function to reduce sensitivity to outliers and introduces sparsity regularization for model reduction.
Article
Computer Science, Artificial Intelligence
Junwei Jin, Yanting Li, C. L. Philip Chen
Summary: In this paper, we propose a novel label noise tolerant method based on the Broad Learning System (BLS) for classifying patterns with corrupted labels. The standard BLS is efficient and accurate but vulnerable to noisy labels. We introduce a maximum likelihood estimation-based objective function and a manifold regularization term to enhance the robustness and flexibility of the model. The experimental results demonstrate the effectiveness of the proposed method, especially for datasets with a large amount of noisy labels.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Matteo Zecchin, Sangwoo Park, Osvaldo Simeone, Marios Kountouris, David Gesbert
Summary: Standard Bayesian learning is suboptimal in generalization under misspecification and outliers. PAC-Bayes theory shows that the free energy criterion of Bayesian learning bounds the generalization error for Gibbs predictors under uncontaminated sampling distributions. This justifies the limitations of Bayesian learning in misspecified models and outliers. Recent work introduces PAC(m) bounds to enhance performance under misspecification, and this work proposes a robust free energy criterion combining the generalized logarithm score function with PAC(m) ensemble bounds, counteracting the effects of misspecification and outliers.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Jintao Huang, Chi-Man Vong, Guangtai Wang, Wenbin Qian, Yimin Zhou, C. L. Philip Chen
Summary: This article proposes a novel unified LE-LDL learning framework called SGP-FBLS, which improves feature mapping ability using a polynomial-based fuzzy system, mines potential LS using a graph regularized-based objective function (GP-FBLS), and transfers LS and weighted parameters using a weight stacked strategy, thus enhancing the accuracy and efficiency of LDL.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Weiwei Qian, Shunming Li, Tong Yao, Kun Xu
Summary: The paper introduces a novel transfer learning method called discriminative feature-based adaptive distribution alignment (DFADA), which can extract discriminative features and conduct a two-stage adaptive distribution alignment. By fusing Maximum Mean Discrepancy (MMD) and graph Laplacian regularization, task-specific features are extracted, achieving comprehensive and adaptive distribution alignments.
APPLIED SOFT COMPUTING
(2021)
Article
Automation & Control Systems
Fan Yang, Meng Han, Fumin Ma, Xiaojian Ding, Qiaoxi Zhang
Summary: With the exponential growth of multimedia data, the need for swift and accurate information retrieval has increased. Supervised hashing, known for its low memory usage and precise accuracy, is a popular retrieval technique. However, previous studies often neglected latent category correlations and faced optimization challenges. To address these issues, a two-step hashing strategy called Label Embedding Asymmetric Discrete Hashing (LEADH) is proposed. LEADH significantly reduces time consumption, explores multi-label semantic information, and designs an efficient discrete optimization module. Experimental and theoretical studies demonstrate the superiority of LEADH compared to sub-optimal methods, achieving improved performance on different datasets.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Engineering, Chemical
Dayong Han, Qiuhua Tang, Zikai Zhang, Liuyang Yuan, Nikolaos Rakovitis, Dan Li, Jie Li
Summary: This paper addresses a new scheduling problem in the crucial steelmaking and continuous casting (SCC) process, and proposes an efficient solution algorithm that can generate optimal or near-optimal solutions with great performance, surpassing commercial solvers and existing algorithms in practice.
CHEMICAL ENGINEERING RESEARCH & DESIGN
(2021)
Article
Computer Science, Artificial Intelligence
Zhihao Cheng, Li Shen, Miaoxi Zhu, Jiaxian Guo, Meng Fang, Liu Liu, Bo Du, Dacheng Tao
Summary: This paper proposes an algorithm that can adaptively learn safe policies from a single expert dataset under diverse safety constraints. It introduces the use of a Lagrange multiplier to balance imitation and safety performance, and employs a two-stage optimization framework to solve the problem. Experimental results demonstrate the effectiveness of the approach.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Dimitris Bertsimas, Kimberly Villalobos Carballo, Leonard Boussioux, Michael Lingzhi Li, Alex Paskov, Ivan Paskov
Summary: This paper presents a novel holistic deep learning framework that addresses the challenges of vulnerability, overparametrization, and performance instability. The proposed framework improves accuracy, robustness, sparsity, and stability over standard deep learning models, as demonstrated by extensive experiments on different data sets. The results are validated by ablation experiments and SHAP value analysis, revealing the interactions and trade-offs between different evaluation metrics. To support practitioners, a prescriptive approach for selecting a training loss function is provided.
Article
Computer Science, Artificial Intelligence
Shiluo Huang, Zheng Liu, Wei Jin, Ying Mu
Summary: Broad learning system (BLS) is an efficient neural network proven effective in various fields. Semi-supervised BLS, a critical branch, is gaining attention for leveraging unlabeled data. However, existing methods face challenges of feature node sparsity and computational complexity with large datasets. Introducing manifold regularized sparse features (BLS-MS) improves efficiency and effectiveness, with experiments showing promising results.
Article
Automation & Control Systems
Honggui Han, Zheng Liu, Hongxu Liu, Junfei Qiao, C. L. Philip Chen
Summary: This article investigates a type-2 fuzzy BLS, which improves system robustness and computational performance through the use of interval type-2 fuzzy neurons and a fuzzy pseudoinverse learning algorithm. The theoretical analysis on convergence of the type-2 FBLS demonstrates computational efficiency, and experimental results show outstanding performance.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Computer Science, Artificial Intelligence
Canh T. Dinh, Tung T. Vu, Nguyen H. Tran, Minh N. Dao, Hongyu Zhang
Summary: This paper investigates the problem of handling non-IID data in federated learning and proposes a new approach to address the relationship issue in multitask learning. Through the proposed algorithms, better performance can be achieved in different FL settings.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Chemistry, Analytical
Desheng Wang, Weidong Jin, Yunpu Wu
Summary: Researchers propose a novel defense algorithm called Between-Class Adversarial Training (BCAT) that combines Between-Class learning with standard adversarial training to improve the balance between robustness generalization and standard generalization performance. The proposed algorithms use mixed between-class adversarial examples and impose effective regularization on the feature distribution, significantly enhancing the robustness generalization and standard generalization performance of adversarially trained models.
Article
Engineering, Electrical & Electronic
Xiaoyun Han, Chaoxu Mu, Jun Yan, Zeyuan Niu
Summary: The integration of large-scale renewable energy poses challenges to energy management in modern power systems. This paper proposes an autonomous control method based on soft actor-critic (SAC), a recently developed deep-reinforcement learning strategy, to achieve optimal active power dispatch without a mathematical model and improve the consumption rate of renewable energy under stable operation.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2023)
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.