Article
Health Care Sciences & Services
Hannah Johns, Julie Bernhardt, Leonid Churilov
Summary: Predicting patient outcomes based on patient characteristics and care processes is common in medical research, but simplifying multifaceted features into scalar variables for statistical analysis may result in a loss of important clinical detail. The limited range of distance-based predictive methods poses a challenge for researchers, who must balance between simplifying features for analysis or using methods that may not fully meet the needs of the analysis problem.
STATISTICAL METHODS IN MEDICAL RESEARCH
(2021)
Article
Oncology
Rodolphe Vallee, Jean-Noel Vallee, Carole Guillevin, Athena Lallouette, Clement Thomas, Guillaume Rittano, Michel Wager, Remy Guillevin, Alexandre Vallee
Summary: The study aims to use machine learning decision tree models applied to perfusion and spectroscopy MRI to classify lymphomas, glioblastomas, and metastases, and identify the underlying key pathophysiological processes involved in the decision-making algorithms of the models.
FRONTIERS IN ONCOLOGY
(2023)
Article
Agronomy
Elzbieta Wojcik-Gront, Marcin Studnicki
Summary: The study evaluated the yield variability of spring and winter triticale in 31 locations across Poland from 2009 to 2017, finding that spring triticale is more influenced by soil quality while winter triticale is more dependent on water availability, suggesting early sowing for spring triticale and consideration of fungicides and growth regulators for winter triticale grown in Poland with periodic excess water.
Article
Engineering, Industrial
Jiyong Choi, Daniel P. de Oliveira, Fernanda Leite
Summary: This research proposes a novel approach using Classification and Regression Trees to capture similarity in capital project benchmarking, specifically in healthcare projects. The trees are constructed by selecting critical and flexible features associated with cost and schedule performance of the projects. The effectiveness of the method is validated through statistical methods and comparative analysis. This new approach allows for more targeted performance comparisons.
JOURNAL OF MANAGEMENT IN ENGINEERING
(2022)
Article
Business, Finance
Koresh Galil, Ami Hauptman, Rosit Levy Rosenboim
Summary: This study utilizes machine learning techniques to predict corporate credit ratings, finding that classification and regression trees and support vector regression have their own advantages in accuracy and interpretability. However, unconstrained models may produce non-monotonic relationships, thus recommending the use of restricted models. Additionally, the importance of company size in credit rating prediction is underscored.
FINANCE RESEARCH LETTERS
(2023)
Article
Geochemistry & Geophysics
Jiahui Qu, Qian Du, Yunsong Li, Long Tian, Haoming Xia
Summary: This article proposes a novel Gaussian mixture model-based anomaly detection method for hyperspectral images, with main contributions being a new extraction approach for anomaly pixels and a weighting approach for fusing the results.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Robotics
Daniil Lisus, Charles Champagne Cossette, Mohammed Shalaby, James Richard Forbes
Summary: This letter demonstrates how to estimate robot heading using UWB range and RSS measurements, by learning a data-driven relationship and combining with a gyroscope and an invariant extended Kalman filter.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2021)
Article
Computer Science, Interdisciplinary Applications
Yinlin Fu, Xiaonan Liu, Suryadipto Sarkar, Teresa Wu
Summary: A new algorithm called Expectation Selection Maximization (ESM) is proposed in this paper to address the issue of confusion and increased computational cost in GMM models by adding a feature selection step. The introduction of a relevancy index (RI) assists in feature selection by indicating the probability of assigning data points to specific clustering groups. The theoretical analysis justifies the effectiveness of RI for feature selection.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Environmental Sciences
Jikai Qin, Zheng Liu, Lei Ran, Rong Xie, Junkui Tang, Hongyu Zhu
Summary: This paper proposes an automatic target recognition (ATR) method for synthetic aperture radar (SAR) images based on the scattering parameter Gaussian mixture model (GMM), aiming to improve the robustness of the ATR system under different extended operation conditions (EOCs). Experimental results demonstrate that the method exhibits excellent robustness while maintaining low computation time.
Article
Engineering, Multidisciplinary
Monia Hamdi, Ines Hilali-Jaghdam, Bushra Elamin Elnaim, Azhari A. Elhag
Summary: This paper uses Gaussian Mixture Model and decision tree method to analyze the data of the COVID-19 pandemic, classifying and predicting new infection cases. The results are applicable to any context and provide numerical results based on the Chinese case.
ALEXANDRIA ENGINEERING JOURNAL
(2023)
Article
Geochemistry & Geophysics
Jianwen Wang, Gang Li, Zhichun Zhao, Jian Jiao, Shuai Ding, Kunpeng Wang, Meiya Duan
Summary: An anomaly detection algorithm based on GMM and radar micro-Doppler features is proposed in this article, achieving a higher detection rate for abnormal motion status of space targets by utilizing normal distributed micro-Doppler features and fitting multidimensional feature distribution using the EM algorithm.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Automation & Control Systems
Hiromasa Kaneko
Summary: The study introduces a novel modeling approach that transforms explanatory variables into latent variables and combines them with Gaussian mixture regression for direct inverse analysis. By using dimensionality reduction methods such as PCA or DAE, PCA-GMR and DAE-GMR models are developed, which significantly reduce prediction errors and enhance predictive accuracy.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2021)
Article
Public, Environmental & Occupational Health
Rui Zhu, Yun-Hao Zheng, Zi-Han Zhang, Pei-Di Fan, Jun Wang, Xin Xiong
Summary: This study developed a new category scheme for the profile morphology of temporomandibular disorders (TMDs) based on lateral cephalometric morphology. The study identified three subgroups based on cephalometric morphology and built a decision tree model with high prediction accuracy. This proposed category system may supplement the understanding of TMD and benefit the management of TMD treatment.
FRONTIERS IN PUBLIC HEALTH
(2022)
Article
Acoustics
Ji Wu, Fei Yang, Wenkai Hu
Summary: This study proposes an unsupervised anomalous sound detection method based on ArcFace classifier and Gaussian mixture model (GMM) to address the challenges of classifying similar samples and determining decision boundaries, achieving better performance in comparison with other methods.
Article
Environmental Sciences
Zhen Gao, Kun Fang, Zhipeng Wang, Kai Guo, Yuan Liu
Summary: This paper introduces an ionosphere-free (Ifree) filtering algorithm for ensuring the integrity of a ground-based augmentation system (GBAS). It proposes an overbounding framework based on a Gaussian mixture model (GMM) to handle the errors outputted by the Ifree algorithm. The performance of the algorithm is evaluated through Monte Carlo simulations and real-world road tests.