Article
Mathematics, Applied
Allen G. Hart, James L. Hook, Jonathan H. P. Dawes
Summary: Echo State Networks (ESNs) are single-layer recurrent neural networks trained by regularised linear least squares regression, which can approximate target functions effectively. The numerical experiments on the Lorenz system demonstrate the validity and feasibility of ESN.
PHYSICA D-NONLINEAR PHENOMENA
(2021)
Article
Environmental Sciences
Nur Fariha Syaqina Zulkepli, Mohd Salmi Md Noorani, Fatimah Abdul Razak, Munira Ismail, Mohd Almie Alias
Summary: This study proposes a hybridization framework of HACA technique that evaluates the spatial patterns of areas affected by haze episodes by considering the topological similarity between stations. Results show that the inclusion of topological features improves the accuracy of air pollution behavior similarity assessment.
JOURNAL OF ENVIRONMENTAL MANAGEMENT
(2022)
Article
Mathematics, Applied
Cheng Fang, Yubin Lu, Ting Gao, Jinqiao Duan
Summary: In this article, a data-driven framework combining Reservoir Computing and Normalizing Flow is proposed to predict the evolution and replicate the dynamical behaviors of stochastic dynamical systems. The effectiveness of the framework is verified in several experiments, and different types of stochastic processes and phenomena are explored.
PHYSICA D-NONLINEAR PHENOMENA
(2023)
Article
Mathematics, Interdisciplinary Applications
Gonzalo Uribarri, Gabriel B. Mindlin
Summary: Time series forecasting is a significant research problem in the fields of science and engineering, and machine learning algorithms have been proven successful in this area. This paper focuses on training Long Short Term Memory networks (LSTM), a type of Recurrent Neural Networks (RNNs), to predict time series data from a chaotic system. The study shows that LSTM networks can learn to generate a data embedding in their inner state that is topologically equivalent to the original strange attractor.
CHAOS SOLITONS & FRACTALS
(2022)
Article
Computer Science, Artificial Intelligence
Alperen Karan, Atabey Kaygun
Summary: This paper introduces topological data analysis methods for classification tasks on univariate time series, enhancing accuracy and reducing noise through stable topological features and subwindow processing.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Multidisciplinary Sciences
Jifan Shi, Luonan Chen, Kazuyuki Aihara
Summary: Research on causality has a long history and different concepts and computational methods have been developed. This study presents a unified mathematical framework for dynamical causality (DC) and proposes causality criteria called embedding entropy (EE) and conditional embedding entropy (cEE). EE and cEE have significant advantages in nonlinear causal inference and reducing scale bias in numerical calculations, and their effectiveness has been demonstrated through simulations and real-world datasets.
JOURNAL OF THE ROYAL SOCIETY INTERFACE
(2022)
Article
Engineering, Mechanical
Zheyu Shi, Kaiwen Zhou, Chen Qin, Xin Wen
Summary: In this experimental study, dynamic stall was measured using high-frequency surface pressure tapes and pressure-sensitive paint (PSP). The influence of oscillation frequency was examined. Dynamic mode decomposition (DMD) with time-delay embedding was proposed to predict the pressure distribution of the oscillating airfoil. The results showed that DMD with time-delay embedding can accurately reconstruct and predict dynamic stall with higher accuracy than standard DMD.
Article
Multidisciplinary Sciences
Xijuan Zhong, Shuai Wang
Summary: In this paper, we reconstruct the dynamic behavior of the ring-coupled Lorenz oscillators system using reservoir computing and find that it can effectively restore the rotational symmetric structure of the original system.
Article
Physics, Fluids & Plasmas
Miki U. Kobayashi, Kengo Nakai, Yoshitaka Saiki, Natsuki Tsutsumi
Summary: This study evaluates data-driven models from a dynamical system perspective, and finds that these models can more accurately reconstruct dynamical characteristics than directly computing from training data. Using this approach, the study successfully predicts the laminar lasting time distribution of a specific macroscopic variable in chaotic fluid flow.
Article
Multidisciplinary Sciences
Syed Mohamad Sadiq Syed Musa, Mohd Salmi Md Noorani, Fatimah Abdul Razak, Munira Ismail, Mohd Almie Alias
Summary: This paper presents a new approach for flood detection by using persistent homology (PH) in streamflow data analysis. The analysis conducted at Sungai Kelantan, Malaysia shows different patterns of topological features between wet and dry periods. The time series of the distance measure corresponding to the evolution of the components can be used for flood detection at Sungai Kelantan, Malaysia.
Article
Environmental Sciences
Shunya Okuno, Koji Ikeuchi, Kazuyuki Aihara
Summary: The study focuses on data-driven flood forecasting methods, particularly for rivers lacking information for physical models. By utilizing phase-space reconstruction approaches based on dynamical systems theory, the proposed method can accurately predict unprecedented water levels with limited data, outperforming existing methods in forecast performance. Additionally, it allows for early evacuation warnings for small and steep rivers, showcasing both its effectiveness and applicability for various gauged rivers.
WATER RESOURCES RESEARCH
(2021)
Article
Mathematics, Applied
Varad Deshmukh, Elizabeth Bradley, Joshua Garland, James D. Meiss
Summary: This paper introduces an automated technique for extracting and characterizing scaling regions on a graph, which can estimate the slope and extent of the scaling region by considering all possible combinations of end points and generating a distribution of slopes. The method is demonstrated for computations of dimension and Lyapunov exponent in dynamical systems, showing its usefulness in parameter selection for time-delay reconstructions.
Article
Computer Science, Artificial Intelligence
Xinyu Han, Yi Zhao
Summary: This paper proposes an interpretable reservoir computing model based on a directed acyclic network (DAN), which identifies memory properties of reservoir nodes in time series prediction and analyzes the impact of reservoir network structure on prediction performance from the perspective of memory community. Two novel hyperparameters with deterministic meaning are introduced to quantify the influence of model initialization on reservoir input, which significantly contributes to achieving superior prediction performance.
Article
Mathematics, Interdisciplinary Applications
Dongrui Shao, Junyu Chu, Luonan Chen, Huanfei Ma
Summary: Data assimilation is crucial for both data driven and model driven research. The Kalman filter, a widely used data assimilation framework, has traditionally relied on theoretical models. However, recent efforts have aimed to develop model-free Kalman filters that solely rely on data. In this study, we propose a hybrid model framework that combines delay embedding theory and machine learning to bridge the gap between exact model-based and totally model-free methods. This hybrid approach is more flexible in application and has been validated using benchmark systems and real-world problems.
CHAOS SOLITONS & FRACTALS
(2023)
Article
Environmental Sciences
Yslam D. Mammedov, Ezutah Udoncy Olugu, Guleid A. Farah
Summary: Wind power has become a significant research area in renewable energy as a response to increasing demand for global energy supply chain. The study introduces a weather prediction method which includes two models for wind speed and atmospheric system forecasting. The physics-informed model was found to outperform other methods in accuracy and reliability, demonstrating potential for application in wind energy analysis.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2022)
Article
Computer Science, Artificial Intelligence
Hamdan Abdellatef, Lina J. Karam
Summary: This paper proposes performing the learning and inference processes in the compressed domain to reduce computational complexity and improve speed of neural networks. Experimental results show that modified ResNet-50 in the compressed domain is 70% faster than traditional spatial-based ResNet-50 while maintaining similar accuracy. Additionally, a preprocessing step with partial encoding is suggested to improve resilience to distortions caused by low-quality encoded images. Training a network with highly compressed data can achieve good classification accuracy with significantly reduced storage requirements.
Article
Computer Science, Artificial Intelligence
Victor R. Barradas, Yasuharu Koike, Nicolas Schweighofer
Summary: Inverse models are essential for human motor learning as they map desired actions to motor commands. The shape of the error surface and the distribution of targets in a task play a crucial role in determining the speed of learning.
Article
Computer Science, Artificial Intelligence
Ting Zhou, Hanshu Yan, Jingfeng Zhang, Lei Liu, Bo Han
Summary: We propose a defense strategy that reduces the success rate of data poisoning attacks in downstream tasks by pre-training a robust foundation model.
Article
Computer Science, Artificial Intelligence
Hao Sun, Li Shen, Qihuang Zhong, Liang Ding, Shixiang Chen, Jingwei Sun, Jing Li, Guangzhong Sun, Dacheng Tao
Summary: In this paper, the convergence rate of AdaSAM in the stochastic non-convex setting is analyzed. Theoretical proof shows that AdaSAM has a linear speedup property and decouples the stochastic gradient steps with the adaptive learning rate and perturbed gradient. Experimental results demonstrate that AdaSAM outperforms other optimizers in terms of performance.
Article
Computer Science, Artificial Intelligence
Juntong Yun, Du Jiang, Li Huang, Bo Tao, Shangchun Liao, Ying Liu, Xin Liu, Gongfa Li, Disi Chen, Baojia Chen
Summary: In this study, a dual manipulator grasping detection model based on the Markov decision process is proposed. By parameterizing the grasping detection model of dual manipulators using a cross entropy convolutional neural network and a full convolutional neural network, stable grasping of complex multiple objects is achieved. Robot grasping experiments were conducted to verify the feasibility and superiority of this method.
Article
Computer Science, Artificial Intelligence
Miaohui Zhang, Kaifang Li, Jianxin Ma, Xile Wang
Summary: This paper proposes an unsupervised person re-identification (Re-ID) method that uses two asymmetric networks to generate pseudo-labels for each other by clustering and updates and optimizes the pseudo-labels through alternate training. It also designs similarity compensation and similarity suppression based on the camera ID of pedestrian images to optimize the similarity measure. Extensive experiments show that the proposed method achieves superior performance compared to state-of-the-art unsupervised person re-identification methods.
Article
Computer Science, Artificial Intelligence
Florian Bacho, Dominique Chu
Summary: This paper proposes a new approach called the Forward Direct Feedback Alignment algorithm for supervised learning in deep neural networks. By combining activity-perturbed forward gradients, direct feedback alignment, and momentum, this method achieves better performance and convergence speed compared to other local alternatives to backpropagation.
Article
Computer Science, Artificial Intelligence
Xiaojian Ding, Yi Li, Shilin Chen
Summary: This research paper addresses the limitations of recursive feature elimination (RFE) and its variants in high-dimensional feature selection tasks. The proposed algorithms, which introduce a novel feature ranking criterion and an optimal feature subset evaluation algorithm, outperform current state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Naoko Koide-Majima, Shinji Nishimoto, Kei Majima
Summary: Visual images observed by humans can be reconstructed from brain activity, and the visualization of arbitrary natural images from mental imagery has been achieved through an improved method. This study provides a unique tool for directly investigating the subjective contents of the brain.
Article
Computer Science, Artificial Intelligence
Huanjie Tao, Qianyue Duan
Summary: In this paper, a hierarchical attention network with progressive feature fusion is proposed for facial expression recognition (FER), addressing the challenges posed by pose variation, occlusions, and illumination variation. The model achieves enhanced performance by aggregating diverse features and progressively enhancing discriminative features.
Article
Computer Science, Artificial Intelligence
Zhenyi Wang, Pengfei Yang, Linwei Hu, Bowen Zhang, Chengmin Lin, Wenkai Lv, Quan Wang
Summary: In the face of the complex landscape of deep learning, we propose a novel subgraph-level performance prediction method called SLAPP, which combines graph and operator features through an innovative graph neural network called EAGAT, providing accurate performance predictions. In addition, we introduce a mixed loss design with dynamic weight adjustment to improve predictive accuracy.
Article
Computer Science, Artificial Intelligence
Yiyang Yin, Shuangling Luo, Jun Zhou, Liang Kang, Calvin Yu-Chian Chen
Summary: Medical image segmentation is crucial for modern healthcare systems, especially in reducing surgical risks and planning treatments. Transanal total mesorectal excision (TaTME) has become an important method for treating colon and rectum cancers. Real-time instance segmentation during TaTME surgeries can assist surgeons in minimizing risks. However, the dynamic variations in TaTME images pose challenges for accurate instance segmentation.
Article
Computer Science, Artificial Intelligence
Teng Cheng, Lei Sun, Junning Zhang, Jinling Wang, Zhanyang Wei
Summary: This study proposes a scheme that combines the start-stop point signal features for wideband multi-signal detection, called Fast Spectrum-Size Self-Training network (FSSNet). By utilizing start-stop points to build the signal model, this method successfully solves the difficulty of existing deep learning methods in detecting discontinuous signals and achieves satisfactory detection speed.
Article
Computer Science, Artificial Intelligence
Wenming Wu, Xiaoke Ma, Quan Wang, Maoguo Gong, Quanxue Gao
Summary: The layer-specific modules in multi-layer networks are critical for understanding the structure and function of the system. However, existing methods fail to accurately characterize and balance the connectivity and specificity of these modules. To address this issue, a joint learning graph clustering algorithm (DRDF) is proposed, which learns the deep representation and discriminative features of the multi-layer network, and balances the connectivity and specificity of the layer-specific modules through joint learning.
Article
Computer Science, Artificial Intelligence
Guanghui Yue, Guibin Zhuo, Weiqing Yan, Tianwei Zhou, Chang Tang, Peng Yang, Tianfu Wang
Summary: This paper proposes a novel boundary uncertainty aware network (BUNet) for precise and robust colorectal polyp segmentation. BUNet utilizes a pyramid vision transformer encoder to learn multi-scale features and incorporates a boundary exploration module (BEM) and a boundary uncertainty aware module (BUM) to handle boundary areas. Experimental results demonstrate that BUNet outperforms other methods in terms of performance and generalization ability.