Article
Neurosciences
Taylor Chomiak, Neilen P. Rasiah, Leonardo A. Molina, Bin Hu, Jaideep S. Bains, Tamas Fuzesi
Summary: LoTRA is a simple computational approach for analyzing time-series data, showing versatility in Parkinsonian gait and in vivo brain dynamics. The algorithm can be used to build a remarkably simple machine-learning model that outperforms deep-learning models in detecting Parkinson's disease from a single digital handwriting test.
NPJ PARKINSONS DISEASE
(2021)
Article
Computer Science, Artificial Intelligence
Wei Chen, Ke Shi
Summary: With the rapid increase of data availability, a novel deep learning model MACNN has been developed to solve the TSC problem, achieving the best performance on 85 UCR standard datasets and outperforming other methods by a large margin.
Article
Computer Science, Information Systems
Omer David Harel, Robert Moskovitch
Summary: In this paper, a novel deep learning-based framework called INSTINCT is proposed for Symbolic Time Intervals (STIs) series classification (STIC). INSTINCT transforms raw STIs series into real matrices while preserving almost all information and uses a ensemble of deep inception based convolutional neural networks for classification. Experimental results show that INSTINCT significantly improves accuracy compared to state-of-the-art methods and deep learning-based baselines on six real-world STIC benchmark datasets. Additionally, a comprehensive architecture study and scalability analysis of INSTINCT are conducted, revealing an overall linear time complexity in each main property of the input STIs series.
INFORMATION SCIENCES
(2023)
Article
Physics, Fluids & Plasmas
Kota Shiozawa, Taisuke Uemura, Isao T. Tokuda
Summary: A method is proposed to detect the dynamical instability of complex time series by studying the evolution of the partitioned entropy of an initially localized region of the attractor. The growth rate of the partitioned entropy is found to correspond to the first Lyapunov exponent. A criterion is introduced to distinguish chaos from limit cycles or tori to avoid spurious detection. Numerical experiments and analysis of experimental data demonstrate the effectiveness and robustness of the method.
Article
Environmental Sciences
Mehmet Ozgur Turkoglu, Stefano D'Aronco, Gregor Perich, Frank Liebisch, Constantin Streit, Konrad Schindler, Jan Dirk Wegner
Summary: This paper introduces a method for agricultural crop classification based on expert knowledge, using a hierarchical neural network model. Validated on a new large dataset, the hierarchical model shows at least 9.9 percentage points superiority in F1-score compared to baseline methods.
REMOTE SENSING OF ENVIRONMENT
(2021)
Article
Physics, Multidisciplinary
Celik Ozdes, Deniz Eroglu
Summary: Irregularly sampled time series analysis is a common problem in various disciplines. We propose a method to obtain a regularly sampled time series spectrum with minimum information loss. The approach is applied to validate a prototypical model and identify critical climate transition periods and their characteristic properties in palaeoclimate proxy data sets around Africa.
EUROPEAN PHYSICAL JOURNAL-SPECIAL TOPICS
(2023)
Article
Physics, Fluids & Plasmas
Tobias Braun, Cinthya N. Fernandez, Deniz Eroglu, Adam Hartland, Sebastian F. M. Breitenbach, Norbert Marwan
Summary: The analysis of irregularly sampled time series is a challenging task. We demonstrate that the edit distance is an effective metric for comparing time series segments of unequal length. We study the impact of sampling rate variations on recurrence quantification analysis and propose a method to correct for biases. The effectiveness of the proposed approach is demonstrated with an example and a real-world dataset.
Article
Automation & Control Systems
Yanrui Li, Chunjie Yang
Summary: This paper proposes a framework using deep learning and time representation techniques to model long temporal industrial data with multiple sampling frequency. By aggregating the data into different time scales and extracting information using a bottleneck layer and one-dimensional filter, the proposed model achieves significant improvement and has been deployed in the factory.
JOURNAL OF PROCESS CONTROL
(2022)
Article
Computer Science, Artificial Intelligence
Di Wu, Fei Peng, Chaozhi Cai, Xinbao Du
Summary: In this study, a new multi-scale AGRes2Net full convolutional network model (IMAGRes2Net-FCN) is proposed to address the issue of unsatisfactory feature extraction capability and feature loss in deep learning for time series classification. The proposed model processes the time series data to add dimensional information and uses a neural network model for feature extraction. Correlations between AGRes2Net residual blocks are learned by an inter-module adaptive feature adjustment mechanism (IAM), and the local features obtained by AGRes2Net multi-scale feature extraction are combined with the global features acquired by IAM. Experimental results demonstrate that the proposed model achieves improved accuracy and reduced PCE compared to other existing models.
NEURAL PROCESSING LETTERS
(2023)
Article
Mathematics, Interdisciplinary Applications
Qianshun Yuan, Jing Zhang, Haiying Wang, Changgui Gu, Huijie Yang
Summary: In traditional statistics-based time series analysis, rich patterns in nonlinear dynamical processes are merged into averages. This study uses the multi-scale transition matrix to display patterns and their evolutions in several typical chaotic systems, such as the Logistic Map, the Tent Map, and the Lorentz System. Compared with Markovian processes, there are rich non-trivial patterns. The unpredictability of transitions matches closely with the Lyapunov exponent. The eigenvalues decay exponentially with respect to the time scale, providing detailed information on the curves of Lyapunov exponent versus dynamical parameters. The evolutionary behaviors differ and do not saturate to those of the corresponding shuffled series.
CHAOS SOLITONS & FRACTALS
(2023)
Article
Multidisciplinary Sciences
Xiangtian Zheng, Nan Xu, Loc Trinh, Dongqi Wu, Tong Huang, S. Sivaranjani, Yan Liu, Le Xie
Summary: This paper presents PSML, a first-of-its-kind open-access multi-scale time-series dataset, to aid in the development of data-driven machine learning (ML)-based approaches towards reliable operation of future electric grids. The dataset captures the interactions and uncertainties of the grid dynamics and provides state-of-the-art ML benchmarks on three challenging use cases.
Article
Telecommunications
Junjie Li, Lin Zhu, Yong Zhang, Da Guo, Xingwen Xia
Summary: This article explores time series data and proposes a multi-scale prediction model based on the attention mechanism for the periodic trend of the data. Experimental results demonstrate its superior performance compared to traditional methods.
CHINA COMMUNICATIONS
(2022)
Article
Computer Science, Information Systems
Liang Zhao, Chunyang Mo, Jiajun Ma, Zhikui Chen, Chenhui Yao
Summary: Deep learning methods, especially CNN and FCN, show competitive performance in time series classification task. Variants of CNN, such as LSTM-FCN and GRU-FCN, achieve state of the art results by learning spatial and temporal features simultaneously, inspiring the proposal of multimodal network LSTM-MFCN.
COMPUTER COMMUNICATIONS
(2022)
Article
Engineering, Civil
Hui Zuo, Gaowei Yan, Ruochen Lu, Rong Li, Shuyi Xiao, Yusong Pang
Summary: In this paper, a multi-taskbased decomposition-integration-prediction (Multi-SDIPC) model is proposed for runoff prediction. The model utilizes parallel and multi-timescale reservoirs to simulate the stochasticity of the runoff system, achieving high accuracy and strong generalization.
WATER RESOURCES MANAGEMENT
(2023)
Article
Computer Science, Information Systems
Xiaohui Wang, Mengchen Xia, Weiwei Deng
Summary: In this paper, a deep learning model called MSRN-Informer is proposed to enhance the precision of time series forecast. The model utilizes a multi-scale structure to extract data features of different scales and applies a residual network to reduce data loss. Compared with other methods, MSRN-Informer shows better prediction ability and reduced error. The research findings of this paper can serve as a reliable reference and basis for effective time series prediction.
Article
Computer Science, Artificial Intelligence
Guang-Hai Liu, Zuo-Yong Li, Jing-Yu Yang, David Zhang
Summary: This article introduces a novel image retrieval method that improves retrieval performance by using sublimated deep features. The method incorporates orientation-selective features and color perceptual features, effectively mimicking these mechanisms to provide a more discriminating representation.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Fengguang Peng, Zihan Ding, Ziming Chen, Gang Wang, Tianrui Hui, Si Liu, Hang Shi
Summary: RGB-Thermal (RGB-T) semantic segmentation is an emerging task that aims to improve the robustness of segmentation methods under extreme imaging conditions by using thermal infrared modality. The challenges of foreground-background distinguishment and complementary information mining are addressed by proposing a cross modulation process with two collaborative components. Experimental results show that the proposed method achieves state-of-the-art performances on current RGB-T segmentation benchmarks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Baihong Han, Xiaoyan Jiang, Zhijun Fang, Hamido Fujita, Yongbin Gao
Summary: This paper proposes a novel automatic prompt generation method called F-SCP, which focuses on generating accurate prompts for low-accuracy classes and similar classes. Experimental results show that our approach outperforms state-of-the-art methods on six multi-domain datasets.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Huikai Liu, Ao Zhang, Wenqian Zhu, Bin Fu, Bingjian Ding, Shengwu Xiong
Summary: Adverse weather conditions present challenges for computer vision tasks, and image de-weathering is an important component of image restoration. This paper proposes a multi-patch skip-forward structure and a Residual Deformable Convolutional module to improve feature extraction and pixel-wise reconstruction.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Oliver M. Crook, Mihai Cucuringu, Tim Hurst, Carola-Bibiane Schonlieb, Matthew Thorpe, Konstantinos C. Zygalakis
Summary: The transportation LP distance (TLP) is a generalization of the Wasserstein WP distance that can be applied directly to color or multi-channelled images, as well as multivariate time-series. TLP interprets signals as functions, while WP interprets signals as measures. Although both distances are powerful tools in modeling data with spatial or temporal perturbations, their computational cost can be prohibitively high for moderate pattern recognition tasks. The linear Wasserstein distance offers a method for projecting signals into a Euclidean space, and in this study, we propose linear versions of the TLP distance (LTLP) that show significant improvement over the linear WP distance in signal processing tasks while being several orders of magnitude faster to compute than the TLP distance.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Haitao Tian, Shiru Qu, Pierre Payeur
Summary: This paper proposes a method of target-dependent classifier, which optimizes the joint hypothesis of domain adaptation into a target-dependent hypothesis that better fits with the target domain clusters through an unsupervised fine-tuning strategy and the concept of meta-learning. Experimental results demonstrate that this method outperforms existing techniques in synthetic-to-real adaptation and cross-city adaptation benchmarks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Qingsen Yan, Axi Niu, Chaoqun Wang, Wei Dong, Marcin Wozniak, Yanning Zhang
Summary: Deep learning-based methods have achieved remarkable results in the field of super-resolution. However, the limitation of paired training image sets has led researchers to explore self-supervised learning. However, the assumption of inaccurate downscaling kernel functions often leads to degraded results. To address this issue, this paper introduces KGSR, a kernel-guided network that trains both upscaling and downscaling networks to generate high-quality high-resolution images even without knowing the actual downscaling process.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Yifan Chen, Xuelong Li
Summary: Gait recognition is a popular technology for identification due to its ability to capture gait features over long distances without cooperation. However, current methods face challenges as they use a single network to extract both temporal and spatial features. To solve this problem, we propose a two-branch network that focuses on spatial and temporal feature extraction separately. By combining these features, we can effectively learn the spatio-temporal information of gait sequences.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Wei Shi, Wentao Zhang, Wei-shi Zheng, Ruixuan Wang
Summary: This article proposes a simple yet effective visualization framework called PAMI, which does not require detailed model structure and parameters to obtain visualization results. It can be applied to various prediction tasks with different model backbones and input formats.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Xiaobo Hu, Jianbo Su, Jun Zhang
Summary: This paper reviews the latest technologies in pattern recognition, highlighting their instabilities and failures in practical applications. From a control perspective, the significance of disturbance rejection in pattern recognition is discussed, and the existing problems are summarized. Finally, potential solutions related to the application of compensation on features are discussed to emphasize future research directions.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Andres Felipe Posada-Moreno, Nikita Surya, Sebastian Trimpe
Summary: Convolutional neural networks are widely used in critical systems, and explainable artificial intelligence has proposed methods for generating high-level explanations. However, these methods lack the ability to determine the location of concepts. To address this, we propose a novel method for automatic concept extraction and localization based on pixel-wise aggregations, and validate it using synthetic datasets.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Peng Bao, Jianian Li, Rong Yan, Zhongyi Liu
Summary: In this paper, a novel Dynamic Graph Contrastive Learning framework, DyGCL, is proposed to capture the temporal consistency in dynamic graphs and achieve good performance in node representation learning.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Kristian Schultz, Saptarshi Bej, Waldemar Hahn, Markus Wolfien, Prashant Srivastava, Olaf Wolkenhauer
Summary: Research indicates that deep generative models perform poorly compared to linear interpolation-based methods for synthetic data generation on small, imbalanced tabular datasets. To address this, a new approach called ConvGeN, combining convex space learning with deep generative models, has been proposed. ConvGeN improves imbalanced classification on small datasets while remaining competitive with existing linear interpolation methods.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Khondaker Tasrif Noor, Antonio Robles-Kelly
Summary: In this paper, the authors propose H-CapsNet, a capsule network designed for hierarchical image classification. The network effectively captures hierarchical relationships using dedicated capsules for each class hierarchy. A modified hinge loss is utilized to enforce consistency among the involved hierarchies. Additionally, a strategy for dynamically adjusting training parameters is presented to achieve better balance between the class hierarchies. Experimental results demonstrate that H-CapsNet outperforms competing hierarchical classification networks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Lei Liu, Guorun Li, Yuefeng Du, Xiaoyu Li, Xiuheng Wu, Zhi Qiao, Tianyi Wang
Summary: This study proposes a new agricultural image segmentation model called CS-Net, which uses Simple-Attention Block and Simpleformer to improve accuracy and inference speed, and addresses the issue of performance collapse of Transformers in agricultural image processing.
PATTERN RECOGNITION
(2024)