Article
Chemistry, Analytical
Peter D. Wentzell, Thays R. Goncalves, Makoto Matsushita, Patricia Valderrama
Summary: Kurtosis-based projection pursuit analysis (kPPA) is a useful tool for visualizing multivariate data and partitioning binary datasets effectively. The introduction of Combinatorial Projection Pursuit Analysis (CombPPA) allows researchers to explore interesting projections more fully by mapping local minima and visualizing different projections. This approach enhances the orthogonality of solutions obtained and provides insights into various combinations of projections.
ANALYTICA CHIMICA ACTA
(2021)
Article
Computer Science, Software Engineering
Tacito Trindade de Araujo Tiburtino Neves, Rafael Messias Martins, Danilo Barbosa Coimbra, Kostiantyn Kucher, Andreas Kerren, Fernando Paulovich
Summary: Streaming data applications are becoming more common, but existing visualization methods have limitations. This paper presents a novel incremental dimensionality reduction technique called Xtreaming, which can continuously update visual representations without revisiting the data.
COMPUTERS & GRAPHICS-UK
(2022)
Article
Computer Science, Information Systems
Yuqin Yao, Hua Meng, Yang Gao, Zhiguo Long, Tianrui Li
Summary: Dimensionality reduction is a significant data preprocessing technique. This article analyzes the drawbacks of the traditional linear unsupervised dimensionality reduction method LPP and proposes an improved model to resolve them. Furthermore, the article enhances LPP to maintain topological connectivity of data. Experimental results demonstrate that the new model outperforms the original LPP model and other classic linear or non-linear dimensionality reduction methods.
INFORMATION SCIENCES
(2023)
Article
Chemistry, Multidisciplinary
Oktay Erten, Fabio P. L. Pereira, Clayton Deutsch
Summary: The paper "Efficiency of Sampling in Monte Carlo Analysis: A Study on Projection Pursuit Multivariate Transform" proposes a technique called projection pursuit multivariate transform to improve the efficiency and quality of sampling in Monte Carlo analysis. Synthetic case studies show the superiority of this technique in sampling uncorrelated and correlated random variables in low and high dimensional spaces. It is found that the projection pursuit multivariate transform yields the fewest sampling errors and the best sampling space coverage, which can save a significant amount of computational effort.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Hardware & Architecture
Ruisheng Ran, Qianghui Zeng, Xiaopeng Jiang, Bin Fang
Summary: Isometric Projection (IsoP) is a linear dimensionality reduction method that only considers one-way mapping from high-dimensional to low-dimensional space. This paper proposes a new method called IsoP-R, which utilizes an encoding-decoding mechanism to reconstruct the original high-dimensional data from the projected low-dimensional data, resulting in more accurate and effective representation of the data.
JOURNAL OF SUPERCOMPUTING
(2023)
Article
Agronomy
Yong Zhao, Yuebin Zhang, Jun Zhao, Fenggang Zan, Peifang Zhao, Jun Deng, Caiwen Wu, Jiayong Liu
Summary: In breeding new sugarcane varieties, the traditional statistical methods may not be suitable due to the non-normal or non-linear distribution of the survey data. The projection pursuit clustering (PPC) model provides a promising approach as it can analyze high-dimensional, non-linear, and non-normal data without making assumptions. In this study, the PPC model was successfully used to evaluate sugarcane varieties and identify excellent resources for further breeding.
Article
Engineering, Multidisciplinary
Xiaoshu Zeng, Roger Ghanem
Summary: This work addresses the accurate stochastic approximations in high-dimensional parametric space using uncertainty quantification tools. A novel approach combining basis adaptation and projection pursuit regression is proposed to simultaneously learn the optimal low-dimensional spaces and polynomial chaos expansions from given data. The method demonstrates the ability to discover low-dimensional manifolds and learn surrogate models with high accuracy with limited data.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2023)
Article
Multidisciplinary Sciences
Tyler Grear, Chris Avery, John Patterson, Donald J. Jacobs
Summary: The article introduces a novel neural network for identifying molecular functional mechanisms and generating working hypotheses through experiments and simulations to optimize design. Feature extraction and selection require attention to signal-to-noise, statistical significance, and clustering quality to create data-driven working hypotheses. By demonstrating utility and generality in multiple benchmarks, this approach can be applied to the analysis of massive data streams in computational biology and material science.
SCIENTIFIC REPORTS
(2021)
Article
Computer Science, Artificial Intelligence
Jingyu Wang, Lin Wang, Feiping Nie, Xuelong Li
Summary: The study introduces a fast unsupervised projection method, which constructs a simplified graph of samples and representative points to reduce projection time for large-scale data and ensure the orthogonality of the projection matrix. Experimental results demonstrate the effectiveness of retaining information using this method.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Hongchun Qu, Lin Li, Zhaoni Li, Jian Zheng, Xiaoming Tang
Summary: This article introduces a new feature extraction method called Robust Discriminative Projection with Dynamic Graph Regularization (RDPDG). RDPDG learns reliable projection by integrating discriminant analysis, reconstituted data, and manifold learning in a unified framework, and effectively utilizes local intrinsic structure through dynamic graph regularization. Experiments demonstrate that RDPDG outperforms other related methods in classification tasks.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Ruixu Zhou, Wensheng Gao, Dengwei Ding, Weidong Liu
Summary: Supervised subspace projection technology, specifically generalized discriminant component analysis (GDCA), and its kernelization forms are proposed in this paper, with rigorous mathematical proofs provided. The theoretical validity, technical advantages, and effectiveness of GDCA are verified using validation data sets and compared against 36 state-of-the-art dimensionality reduction algorithms.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Information Systems
Shuai Yin, Yanfeng Sun, Junbin Gao, Yongli Hu, Boyue Wang, Baocai Yin
Summary: LR-LPP and LR-FLPP are low-rank locality preserving projection algorithms that are more robust to outliers. LR-LPP decomposes the data, learns the projective matrix based on the clean intrinsic component, while LR-FLPP measures low-dimensional features using the F-norm.
ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA
(2021)
Article
Computer Science, Artificial Intelligence
Chao Zhang, Huaxiong Li, Chunlin Chen, Xianzhong Zhou
Summary: This paper proposes a novel unsupervised dimensionality reduction method NRDP, which focuses on the local and nonlocal structure of data by simultaneously maximizing nonlocal scatter and minimizing local scatter to learn discriminant projection. NRDP utilizes a nonnegative representation model and l(1)-norm as metric for robustness against noises, and solves the optimization model through an iterative algorithm, significantly improving the representation power and discrimination of features.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2021)
Article
Engineering, Electrical & Electronic
Lin Jiang, Xiaozhao Fang, Weijun Sun, Na Han, Shaohua Teng
Summary: Subspace learning is a fundamental method for feature extraction, but existing methods often face difficulties in handling multiple tasks. To solve this problem, this paper proposes a dual representation locality preserving projection method that introduces two different projection matrices, uses a flexible form to select features, and incorporates structural similarity and linear subspace reconstruction to capture relationships and reduce noise interference.
Article
Engineering, Electrical & Electronic
Paul M. Baggenstoss, Steven Kay
Summary: A new information criterion for nonlinear dimension reduction based on PDF estimation is proposed, which maximizes information transfer and can generate desired output distribution. The method is general, efficient, and superior to traditional dimension reduction methods in experiments with high-dimensional non-Gaussian input data.
IEEE TRANSACTIONS ON SIGNAL PROCESSING
(2022)
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)