Article
Environmental Sciences
Lujun Lin, Yongchun Liang, Lei Liu, Yang Zhang, Danni Xie, Fang Yin, Tariq Ashraf
Summary: This study accurately estimated the ground-level PM2.5 pollution in Guanzhong Urban Agglomeration (GUA) using the RF-XGBoost model, and analyzed its variations. The results showed that GUA had the highest PM2.5 pollution in 2018 and 2019, but there was a decrease in 2019 compared to the previous year. However, more than 65% of the study area still had mean PM2.5 concentrations higher than the standard value in the winter of 2019, indicating a grim air pollution situation.
Article
Biochemistry & Molecular Biology
Leqi Tian, Wenbin Wu, Tianwei Yu
Summary: Random Forest (RF) is a popular machine learning method for classification and regression tasks, and it performs well under low sample size situations. However, there are issues with gene selection using RF as the important genes are usually scattered on the gene network, which conflicts with the biological assumption of functional consistency. To address this issue, we propose the Graph Random Forest (GRF) method, which incorporates external topological information to identify highly connected important features. The algorithm achieves equivalent classification accuracy to RF while selecting interpretable feature sub-graphs.
Article
Chemistry, Analytical
Iram Noreen, Muhammad Hamid, Uzma Akram, Saadia Malik, Muhammad Saleem
Summary: Recent advancements in computer applications have led to the use of hand gestures for operating various devices, presenting new challenges in the field. A multiple parallel stream 2D CNN model, utilizing depth data, has been proposed for accurate hand posture recognition, outperforming previous methods in terms of accuracy.
Article
Environmental Sciences
Hao Fei, Zehua Fan, Chengkun Wang, Nannan Zhang, Tao Wang, Rengu Chen, Tiecheng Bai
Summary: This study proposes a county-scale cotton mapping method based on multiple features and random forest. By selecting spectral features, vegetation indices, and texture features, and exploring the contribution of texture features to cotton classification accuracy, the study improves the accuracy and efficiency of cotton classification.
Article
Biochemistry & Molecular Biology
Hasan Zulfiqar, Shi-Shi Yuan, Qin-Lai Huang, Zi-Jie Sun, Fu-Ying Dao, Xiao-Long Yu, Hao Lin
Summary: This study developed a computational model to discriminate cyclin proteins from non-cyclin proteins with high accuracy. By encoding and optimizing protein sequences with seven features, and training a gradient boost decision tree classifier, the model achieved better results than previous studies on the same data.
COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL
(2021)
Article
Biochemical Research Methods
Yatao Zhang, Zhenguo Ma, Jiarui Song, Xiaoming Kong, Ziyu Guo, Bin Jiang
Summary: The study evaluated the performance of classic machine learning algorithms on classifying ECG recordings based on six different feature schemes. The results showed that time domain, frequency domain, and PCA features provided reliable combinations for RF and SVM, with RF achieving higher F1-scores in both binary and tri-classification tasks compared to SVM, LS-SVM, and NB.
Article
Water Resources
Julien Meloche, Alexandre Langlois, Nick Rutter, Donald McLennan, Alain Royer, Paul Billecocq, Serguei Ponomarenko
Summary: Increasing surface temperatures in the Arctic have reduced the extent and duration of annual snow cover, affecting polar ecosystems. Accurate monitoring of these ecosystems requires detailed information on snow cover properties at resolutions below 100 meters. In this study, a machine learning method using topographic parameters and the Random Forest algorithm was applied to an arctic landscape, providing predictions of snow depth distributions with good accuracy.
HYDROLOGICAL PROCESSES
(2022)
Article
Environmental Sciences
Gongbo Chen, Yingxin Li, Yun Zhou, Chunxiang Shi, Yuming Guo, Yuewei Liu
Summary: A non-AOD random forest model was developed in this study to estimate daily PM2.5 concentrations in Guangdong Province, China, where over 80% of AOD data were missing. The predictive performance of the non-AOD model was found to be similar to that of an AOD-based model, making it suitable for epidemiological studies at a high resolution.
ENVIRONMENTAL RESEARCH
(2021)
Article
Biochemical Research Methods
Chunyan Ao, Quan Zou, Liang Yu
Summary: A novel predictor, RFhy-m2G, was developed in this study to identify m2G modification sites using hybrid features and random forest. The predictor achieved high accuracies through feature fusion and optimal feature selection.
Article
Environmental Sciences
Fan Wu, Yufen Ren, Xiaoke Wang
Summary: Using multi-source data and the random forest algorithm, this study successfully extracted and mapped plantation forest in Yanqing, north China, achieving promising results.
Article
Mathematics
Jiameng Yan, Qiang Meng, Lan Tian, Xiaoyu Wang, Junhui Liu, Meng Li, Ming Zeng, Huifang Xu
Summary: A brand-new tone recognition method based on random forest (RF) and feature fusion is proposed for Mandarin learning in HCI systems. Three fusion feature sets (FFSs) were created using different fusion methods on sound source features linked to Mandarin syllable tone. The method achieved high tone recognition accuracy and has good generalization capability and classification ability with unbalanced data, making it suitable for mobile HCI learning systems.
Article
Agricultural Engineering
Chao Chen, Zhi Wang, Yadong Ge, Rui Liang, Donghao Hou, Junyu Tao, Beibei Yan, Wandong Zheng, Rositsa Velichkova, Guanyi Chen
Summary: This study established a series of data-enhanced machine learning models and conducted sensitivity analysis to achieve accurate prediction of hydrothermal biochar properties. Compared with traditional models, the accuracy was significantly improved, reaching an average of 94.89% for the optimal random forest model. The key factors influencing the prediction results were reaction temperature, reaction pressure, and specific element of biomass feedstock.
BIORESOURCE TECHNOLOGY
(2023)
Article
Biochemical Research Methods
Yunpei Xu, Hong-Dong Li, Cui-Xiang Lin, Ruiqing Zheng, Yaohang Li, Jinhui Xu, Jianxin Wang
Summary: Single-cell RNA sequencing (scRNA-seq) is a powerful tool for dissecting biological tissues. This study presents CellBRF, a feature selection method that considers the relevance of genes to cell types, improving single-cell clustering accuracy. CellBRF outperforms existing methods in terms of clustering accuracy and consistency, and has been successfully applied to cell differentiation stage identification, non-malignant cell subtype identification, and rare cell identification.
Article
Environmental Sciences
Xiaoguang Yuan, Shiruo Liu, Wei Feng, Gabriel Dauphin
Summary: This article investigates the classification of farmland using satellite monitoring data and deep learning. By expanding features and selecting important features, the classification accuracy can be improved and predictions can be made without using all the input data. This approach supports intelligent monitoring of farm crops and facilitates the implementation of various agricultural policies.
Article
Environmental Sciences
Fangwen Bao, Kai Huang, Shengbiao Wu
Summary: This study proposes a random forest (RF) model driven by a differential operator for aerosol retrieval from geostationary satellite Himawari-8. The model establishes a linear relationship between aerosol optical depth (AOD) and top-of-atmosphere (TOA) reflectance enhancement. It achieves simultaneous retrievals over different surfaces and maintains mathematical correlation between spectral AODs and Angstrom Exponents (AE). The proposed method improves the performance of RF in retrieving aerosol properties and offers a new prospect for aerosol remote sensing.
REMOTE SENSING OF ENVIRONMENT
(2023)
Article
Optics
Zhichao Dong, Weizhi Nai
Article
Engineering, Biomedical
Weizhi Nai, Junyan Feng, Ling Shan, Feiyong Jia, Minghui Sun, Xiaoying Sun
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2019)
Article
Computer Science, Cybernetics
Weizhi Nai, Jianyu Liu, Chongyang Sun, Qinglong Wang, Guohong Liu, Xiaoying Sun
Summary: This study proposes a method for rendering periodic vibrotactile feedback for textured patterns, which involves selecting representative signal segments and constructing waveform segment tables. Results show the importance of preserving patterns in haptic feedback rendering for textured patterns.
IEEE TRANSACTIONS ON HAPTICS
(2021)
Article
Engineering, Electrical & Electronic
Weizhi Nai, Yue Liu, Qinglong Wang, Xiaoying Sun
Summary: This paper proposes a method for allowing users to use self-defined mid-air hand gestures as commands for Human-Computer Interaction (HCI). The gesture detection and recognition algorithm is based on pattern matching using 3 separate sets of features. An experiment is conducted to test the recognition rate and false positive ratio of the method.
IEEE SENSORS JOURNAL
(2022)
Article
Engineering, Electrical & Electronic
Guohong Liu, Shuai Lv, Cong Wang, Xiaomeng Li, Weizhi Nai
Summary: This article focuses on surface material classification with unbalanced visual and haptic data, which is important in teleoperation and robotic recognition. To overcome the performance degradation of existing classification methods, the double deep Q-learning network (DDQN) method is proposed. It offers strong representation ability and avoids overestimation.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Engineering, Electrical & Electronic
Chongyang Sun, Xuezhi Yan, Weizhi Nai, Xiaoying Sun
Summary: This article introduces a method of using the scale index of vibration signals as an objective measure for the perceived regularity of textures, and provides feasibility verification and application examples.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Weizhi Nai, David Rempel, Yue Liu, Alan Barr, Carisa Harris-Adamson, Yongtian Wang
VIRTUAL, AUGMENTED AND MIXED REALITY
(2017)
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)