Semi-supervised Gaussian process classification algorithm addressing the class imbalance by Zhan-guo XIA, Shi-xiong XIA, Shi-yu CAI, Ling WAN

“…The traditional supervised learning is difficult to deal with real-world datasets with less labeled information when the training sets class is imbalanced.Therefore,a new semi-supervised Gaussian process classification of address-ing was proposed.The semi-supervised Gaussian process was realized by calculating the posterior probability to obtain more accurate and credible labeled data,and embarking from self-training semi-supervised methods to add class label into the unlabeled data.The algorithm makes the distribution of training samples relatively balance,so the classifier can adaptively optimized to obtain better effect of classification.According to the experimental results,when the circum-stances of training set are class imbalance and much lack of label information,The algorithm improves the accuracy by obtaining effective labeled in comparison with other related works and provides a new idea for addressing the class im-balance is demonstrated.…”
Get full text

New Paraquat Requirements by Frederick M. Fishel

“…This document will present an overview of the new label revisions. …”
Get full text

New Paraquat Requirements by Frederick M. Fishel

“…This document will present an overview of the new label revisions. …”
Get full text

Frequency Assignment Model of Zero Divisor Graph by R. Radha, N. Mohamed Rilwan

“…Given a frequency assignment network model is a zero divisor graph Γ=V,E of commutative ring Rη, in this model, each node is considered to be a channel and their labelings are said to be the frequencies, which are assigned by the L2,1 and L3,2,1 labeling constraints. …”
Get full text

New Results on the (Super) Edge-Magic Deficiency of Chain Graphs by Ngurah Anak Agung Gede, Adiwijaya

“…An edge-magic labeling f of G with f(V(G))={1,2,3,…,v} is called a super edge-magic labeling. …”
Get full text

Application of improved self-training model in the identification of users with poor service quality by Li YU, Zhe LI, Fei GAO, Xiangyang YUAN, Yong YANG

“…Poor quality user identification is an important method to reduce the complaint rate and increase satisfaction.It is difficult to effectively label a large amount of structured and unstructured data related to business perception in current telecommunications network systems, poor quality user labels are not complete, and the existing supervised learning model training samples are unbalanced, resulting in a low quality recognition rate.An improved self-training semi-supervised learning model was adopted, a small number of low-satisfaction and complaint users as poor quality user labels was used to label network data, and label migration was used to train a large amount of unlabeled data to identify poor quality users.Experiments show that compared to fully supervised learning with high recognition model accuracy but high training cost and unsupervised learning with low recognition model accuracy, semi-supervised learning can make full use of unlabeled sample data for effective training, ensuring lower training costs and the recognition accuracy of poor-quality users is significantly improved.…”
Get full text

Quantum Dots Do Not Alter the Differentiation Potential of Pancreatic Stem Cells and Are Distributed Randomly among Daughter Cells by S. Danner, H. Benzin, T. Vollbrandt, J. Oder, A. Richter, C. Kruse

“…With the increasing relevance of cell-based therapies, there is a demand for cell-labeling techniques for in vitro and in vivo studies. …”
Get full text

Basic Studies on Radioimmunotargeting of CD133-Positive HCT116 Cancer Stem Cells by Zhao-Hui Jin, Chizuru Sogawa, Takako Furukawa, Yuriko Saito, Winn Aung, Yasuhisa Fujibayashi, Tsuneo Saga

“…Antibodies against CD133 were labeled with 125 I, and their in vitro cell binding properties were tested. …”
Get full text

Resonant Frequency Modeling of Microwave Antennas Using Gaussian Process Based on Semisupervised Learning by Jing Gao, Yubo Tian, Xie Zheng, Xuezhi Chen

“…Traditional machine learning methods usually use only labeled samples or unlabeled samples, but in practical problems, labeled samples and unlabeled samples coexist, and the acquisition cost of labeled samples is relatively high. …”
Get full text

Unsupervised and Semisupervised Machine Learning Frameworks for Multiclass Tool Wear Recognition by Maryam Assafo, Peter Langendoerfer

“…Single sensor and multisensor data under different percentages of labeled training data were considered in the evaluation. …”
Get full text

Systematic literature review on Calcium Pyrophosphate Deposition (CPPD) nomenclature: condition elements and clinical states— A Gout, Hyperuricaemia and Crystal-Associated Disease... by Georgios Filippou, Antonella Adinolfi, Emilio Filippucci, Nicola Dalbeth, Robert Terkeltaub, Tristan Pascart, Edoardo Cipolletta, Silvia Sirotti, Charlotte Jauffret, Sara Tedeschi, Daniele Cirillo, Luca Ingrao, Alessandro Lucia

“…CPPD clinical phenotypes were often described as ‘pseudo-form’ labels.Conclusion Those results demonstrate the heterogeneity of labels used to describe CPPD condition concepts, with wide variation in condition labels in the medical literature. …”
Get full text

BSG-WSL: BackScatter-guided weakly supervised learning for water mapping in SAR images by Kai Wang, Zhongle Ren, Biao Hou, Weibin Li, Licheng Jiao

“…Then, a morphological pseudo-label optimization algorithm is designed to employ CAMs to generate high-quality pseudo-labels. …”
Get full text

Dual-Contrast Cellular Magnetic Resonance Imaging by Rohan Dharmakumar, Zhouli Zhang, Ioannis Koktzoglou, Sotirios A. Tsaftaris, Debiao Li

“…However, visualizing and tracking labeled cells on the basis of negative contrast is often met with limited specificity and sensitivity. …”
Get full text

A Semi-supervised Deep Learning Method for Cervical Cell Classification by Siqi Zhao, Yongjun He, Jian Qin, Zixuan Wang

“…However, cervical cell labeling requires specialized physicians and the cost of labeling is high, resulting in a lack of sufficient labeling data in this field. …”
Get full text

HPM-Match: A Generic Deep Learning Framework for Historical Landslide Identification Based on Hybrid Perturbation Mean Match by Shuhao Ran, Gang Ma, Fudong Chi, Wei Zhou, Yonghong Weng

“…The scarcity of high-quality labeled data poses a challenge to the application of deep learning (DL) in landslide identification from remote sensing (RS) images. …”
Get full text

FSErasing: Improving Face Recognition with Data Augmentation Using Face Parsing by Hiroya Kawai, Koichi Ito, Hwann-Tzong Chen, Takafumi Aoki

“…The part labels used in conventional face parsing are defined based on biological features, and thus, one label is given to a large region, such as skin. …”
Get full text

Ex Vivo and in Vivo Administration of Fluorescent CNA35 Specifically Marks Cardiac Fibrosis by Sanne de Jong, Lars B. van Middendorp, Robin H.A. Hermans, Jacques M.T. de Bakker, Marti F.A. Bierhuizen, Frits W. Prinzen, Harold V.M. van Rijen, Mario Losen, Marc A. Vos, Marc A.M.J. van Zandvoort

“…Furthermore, fluorescently labeled CNA35 was administered in vivo in mice. Hearts were isolated, and CNA35 labeling was examined in tissue sections. …”
Get full text

Knowledge triple extraction in cybersecurity with adversarial active learning by Tao LI, Yuanbo GUO, Ankang JU

“…Aiming at the problem that using pipeline methods for extracting cybersecurity knowledge triples may cause the errors propagation of entity recognition and did not consider the correlation between entity recognition and relation extraction,and training triple extraction model lacked labeled corpora,an end-to-end cybersecurity knowledge triple extraction method with adversarial active learning was proposed.For knowledge triple extraction,the conventional entity recognition and relation extraction were modelled as sequence labeling task through joint labeling strategy firstly.And then,a BiLSTM-LSTM-based model with dynamic attention mechanism was designed to jointly extract entities and relations,forming triples.Finally,with adversarial learning framework,a discriminator was trained to incrementally select high-quality samples for labeling,and the performance of the joint extraction model was continuously enhanced by iterative retraining.Experiments show that the proposed joint extraction model outperforms the existing cybersecurity knowledge triple extraction methods,and demonstrate the effectiveness of proposed adversarial active learning scheme.…”
Get full text

Changing our Diagnostic Paradigm Part II: Movement System Diagnostic Classification by Paula M Ludewig, Gaura Saini, Aaron Hellem, Emily K Kahnert, S Cyrus Rezvanifar, Jonathan P Braman, Justin L Staker

“…Replacement of pathoanatomic labels with non-specific regional pain labels has been proposed, and occurs frequently in clinical practice. …”
Get full text

Dynamic-budget superpixel active learning for semantic segmentation by Yuemin Wang, Ian Stavness

“…IntroductionActive learning can significantly decrease the labeling cost of deep learning workflows by prioritizing the limited labeling budget to high-impact data points that have the highest positive impact on model accuracy. …”
Get full text