Article
Mathematics
Shengfeng Gan, Mohammed Alshahrani, Shichao Liu
Summary: This article discusses the important problem of network link prediction and proposes a positive-unlabeled learning framework to address the issue of insufficient labeled training samples. The article learns representation vectors of nodes using a network representation method and utilizes different classifiers and learning strategies to improve prediction performance. Experimental results demonstrate the positive impact of positive-unlabeled learning on predictive performances.
Article
Chemistry, Analytical
Jing Li, Haowen Zhang, Yabo Dong, Tongbin Zuo, Duanqing Xu
Summary: This paper focuses on the application of self-training methods in the positive unlabeled time series classification problem, and proposes a new approach called ST-average, which utilizes an average sequence for data labeling that is more representative and reliable compared to traditional methods.
Article
Engineering, Environmental
Shaodong Zheng, Jinsong Zhao
Summary: With the rapid development of the modern chemical process industry, process monitoring techniques have been investigated to enhance loss prevention capability. In this study, a three-step high-fidelity PU approach based on deep learning is proposed for semi-supervised fault detection of chemical processes. Experimental results demonstrate the effectiveness and superiority of the proposed approach compared to other competing PU learning approaches and supervised fault detection models.
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2022)
Article
Computer Science, Artificial Intelligence
Ales Papic, Igor Kononenko, Zoran Bosnic
Summary: The quantity of data generated daily makes processing difficult. Positive and unlabeled (PU) learning aims to train a binary classifier from partially labeled data, combining supervised and semi-supervised learning. A novel Conditional Generative PU framework (CGenPU) with a built-in auxiliary classifier is proposed in this paper. Evaluation shows CGenPU achieves the state-of-the-art performance on standard positive and unlabeled learning benchmark datasets with higher accuracy compared to the current state-of-the-art D-GAN framework.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Automation & Control Systems
Liang Xi, Zichao Yun, Han Liu, Ruidong Wang, Xunhua Huang, Haoyi Fan
Summary: Semi-supervised learning is a powerful method for model training with partially labeled data. The proposed SSTSC model utilizes self-supervised learning as an auxiliary task to optimize the main TSC task, effectively utilizing temporal relations in time series data and unlabeled data.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Computer Science, Information Systems
Cephas A. S. Barreto, Arthur Costa Gorgonio, Joao C. Xavier-Junior, Anne Magaly De Paula Canuto
Summary: Semi-supervised learning (SSL) is a machine learning approach that integrates supervised and unsupervised learning mechanisms. This paper focuses on the use of a wrapper-based strategy in SSL and proposes three selection methods for efficient selection of unlabelled instances. The feasibility of these methods is evaluated through empirical analysis on two well-known SSL methods: Self-training and Co-training.
Article
Computer Science, Artificial Intelligence
Jing Li, Yuangang Pan, Ivor W. Tsang
Summary: This article proposes a dual mechanism called adaptive sharpening (ADS) to minimize prediction uncertainty in semi-supervised learning. ADS applies a soft-threshold to mask out uncertain and negligible predictions, and sharpens the informed ones to distill certain predictions.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Xi Wang, Hao Chen, Huiling Xiang, Huangjing Lin, Xi Lin, Pheng-Ann Heng
Summary: A novel semi-supervised deep learning method incorporating self-training and consistency regularization is proposed in this study to improve the discrimination capability of training models by effectively utilizing useful information from unlabeled data.
MEDICAL IMAGE ANALYSIS
(2021)
Article
Computer Science, Artificial Intelligence
Weichao Yi, Liquan Dong, Ming Liu, Mei Hui, Lingqin Kong, Yuejin Zhao
Summary: In this study, a novel Semi-supervised Progressive Dehazing Network (Semi-PDNet) is proposed, which leverages both synthetic and real-world images in the training process. The network follows a progressive architecture with three core stages: image encode stage (IES), feature enhance stage (FES), and hierarchical reconstruction stage (HRS). The stage-by-stage paradigm allows for better haze removal by utilizing informative features from shallow to deep. Additionally, an unlabeled contrastive guidance (UCG) is utilized to bridge the domain gap between synthetic and real-world images.
Article
Computer Science, Artificial Intelligence
Samia Boukir
Summary: This study investigates the use of margin and diversity, two key concepts in ensemble learning, to develop a versatile uncertainty-driven ensemble classifier under the scarcity of labeled data. New semi-supervised definitions are proposed for both margin and diversity, and new robust ensemble metrics are introduced to strengthen the semi-supervised classification scheme. The relevance of these new criteria is examined in change detection experiments, and the underlying fusion rule significantly improves the change detection performance.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Yiming Li, Baoyuan Wu, Yan Feng, Yanbo Fan, Yong Jiang, Zhifeng Li, Shu-Tao Xia
Summary: This paper introduces a novel defense method, robust training (RT), which enhances accuracy and adversarial robustness by jointly minimizing separated risks of benign examples and their neighborhoods. Extensive experiments show the effectiveness of the proposed SRT method in defending against pixel-wise or spatial perturbations separately, as well as its robustness to both perturbations simultaneously.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Information Systems
Bing Li, Jikui Wang, Zhengguo Yang, Jihai Yi, Feiping Nie
Summary: Self-training is a widely used semi-supervised learning algorithm framework. To improve the quality of high-confidence samples, researchers have proposed data editing methods. However, these methods have high time complexity. In this study, a fast semi-supervised self-training algorithm based on data editing (EBSA) is proposed, which achieves both fast training speed and high-quality sample selection. Experimental results on benchmark datasets demonstrate the superiority of the proposed algorithm in terms of speed and classification performance.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Information Systems
Roohallah Alizadehsani, Danial Sharifrazi, Navid Hoseini Izadi, Javad Hassannataj Joloudari, Afshin Shoeibi, Juan M. Gorriz, Sadiq Hussain, Juan E. Arco, Zahra Alizadeh Sani, Fahime Khozeimeh, Abbas Khosravi, Saeid Nahavandi, Sheikh Mohammed Shariful Islam, U. Rajendra Acharya
Summary: This article introduces a semi-supervised classification method using limited labeled data, relying on Sobel edge detection and Generative Adversarial Networks (GANs) to automate COVID-19 diagnosis. Experimental results demonstrate that the proposed method significantly outperforms supervised learning methods in cases where labeled data is scarce.
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Jose L. Salazar Gonzalez, Juan A. Alvarez-Garcia, Fernando J. Rendon-Segador, Fabio Carrara
Summary: This study presents a semi-supervised learning approach based on conditioned cooperative student-teacher training, which utilizes Closed Circuit Television (CCTV) and weapon detection models to reduce violent assaults and homicides. The effectiveness of the approach is demonstrated by collecting a new firearms image dataset and comparing it with various learning techniques.
Review
Biochemical Research Methods
Fuyi Li, Shuangyu Dong, Andre Leier, Meiya Han, Xudong Guo, Jing Xu, Xiaoyu Wang, Shirui Pan, Cangzhi Jia, Yang Zhang, Geoffrey Webb, Lachlan J. M. Coin, Chen Li, Jiangning Song
Summary: Conventional supervised binary classification algorithms have been widely used in biological and biomedical data analysis. However, labeling data can be laborious, leading to the proposal of the positive unlabeled (PU) learning scheme. This approach allows for learning from limited positive samples and a large number of unlabeled samples, contributing to the development of various PU learning algorithms for addressing biological questions.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Computer Science, Artificial Intelligence
Lucas de Carvalho Pagliosa, Rodrigo Fernandes de Mello
EXPERT SYSTEMS WITH APPLICATIONS
(2017)
Article
Computer Science, Artificial Intelligence
Fausto G. da Costa, Felipe S. L. G. Duarte, Rosane M. M. Vallim, Rodrigo F. de Mello
EXPERT SYSTEMS WITH APPLICATIONS
(2017)
Article
Computer Science, Artificial Intelligence
Martha Dais Ferreira, Debora Cristina Correa, Luis Gustavo Nonato, Rodrigo Fernandes de Mello
EXPERT SYSTEMS WITH APPLICATIONS
(2018)
Article
Mathematics, Applied
Rodrigo F. de Mello, Ricardo A. Rios, Paulo A. Pagliosa, Caio S. Lopes
Article
Geosciences, Multidisciplinary
Millaray Curilem, Rodrigo Fernandes de Mello, Fernando Huenupan, Cesar San Martin, Luis Franco, Erasmo Hernandez, Ricardo Araujo Rios
JOURNAL OF VOLCANOLOGY AND GEOTHERMAL RESEARCH
(2018)
Article
Computer Science, Artificial Intelligence
Rodrigo F. de Mello, Yule Vaz, Carlos H. Grossi, Albert Bifet
EXPERT SYSTEMS WITH APPLICATIONS
(2019)
Article
Engineering, Electrical & Electronic
Felipe S. L. G. Duarte, Ricardo A. Rios, Eduardo R. Hruschka, Rodrigo F. de Mello
DIGITAL SIGNAL PROCESSING
(2019)
Article
Computer Science, Artificial Intelligence
Rodrigo E. de Mello, Chaitanya Manapragada, Albert Bifet
EXPERT SYSTEMS WITH APPLICATIONS
(2019)
Article
Agriculture, Multidisciplinary
Adriele Giaretta Biase, Tiago Zanett Albertini, Rodrigo Fernandes de Mello
Summary: Livestock production efficiency is crucial for improving the global food chain, providing more meat to people and reducing costs, while promoting environmental sustainability. This study proposes two adaptable approaches to predict cattle body weights based on various variables, surpassing traditional models.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Tiago S. Nazare, Gabriel B. Paranhos da Costa, Rodrigo F. de Mello, Moacir A. Ponti
PROCEEDINGS 2018 31ST SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Felipe S. L. G. Duarte, Ricardo A. Rios, Eduardo R. Hruschka, Rodrigo F. de Mello
2018 7TH BRAZILIAN CONFERENCE ON INTELLIGENT SYSTEMS (BRACIS)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Ricardo A. Rios, Caio S. Lopes, Fabio H. G. Sikansi, Paulo A. Pagliosa, Rodrigo F. de Mello
2017 6TH BRAZILIAN CONFERENCE ON INTELLIGENT SYSTEMS (BRACIS)
(2017)
Article
Computer Science, Theory & Methods
Rodrigo F. de Mello, Ricardo A. Rios, Paulo A. Pagliosa, Renato P. Ishii
INTERNATIONAL JOURNAL OF UNCONVENTIONAL COMPUTING
(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)