Mathematical Models of Supervised Learning and Application to Medical Diagnosis

2012 ◽  
pp. 67-81
Author(s):  
Roberta De Asmundis ◽  
Mario Rosario Guarracino
Keyword(s):  
Mathematical Models ◽  
Supervised Learning ◽  
Medical Diagnosis

COVID-19 Imaging-based AI Research — A Literature Review

2021 ◽  
Vol 17 ◽  
Author(s):  
Cheng Ge ◽  
Lili Zhang ◽  
Liangxu Xie ◽  
Ren Kong ◽  
Hong Zhang ◽  
...  
Keyword(s):  
Supervised Learning ◽  
Medical Diagnosis ◽  
Severity Assessment ◽  
Chest Imaging ◽  
Processing Methods ◽  
The World ◽  
Weakly Supervised ◽  
Assisted Diagnosis ◽  
Public Datasets ◽  
Future Work

Background: The new coronavirus disease 2019 (COVID-19) is spreading rapidly around the world. Artificial intelligence (AI) assisted identification and detection of diseases is an ef-fective method of medical diagnosis. Objectives: To present recent advances in AI-assisted diagnosis of COVID-19, we introduce major aspects of AI in the process of diagnosing COVID-19. Methods: In this paper, we firstly cover the latest collection and processing methods of da-tasets of COVID-19. The processing methods mainly include building public datasets, transfer learning, unsupervised learning and weakly supervised learning, semi-supervised learning methods and so on. Secondly, we introduce the algorithm application and evaluation metrics of AI in medical imaging segmentation and automatic screening. Then, we introduce the quantifi-cation and severity assessment of infection in COVID-19 patients based on image segmenta-tion and automatic screening. Finally, we analyze and point out the current AI-assisted diagno-sis of COVID-19 problems, which may provide useful clues for future work. Conclusion: AI is critical for COVID-19 diagnosis. Combining chest imaging with AI can not only save time and effort, but also provide more accurate and efficient medical diagnosis results.

scholarly journals Compact Graph based Semi-Supervised Learning for Medical Diagnosis in Alzheimer’s Disease

2014 ◽  
Vol 21 (10) ◽  
pp. 1192-1196 ◽  
Author(s):  
Mingbo Zhao ◽  
Rosa H. M. Chan ◽  
Tommy W. S. Chow ◽  
Peng Tang
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Supervised Learning ◽  
Medical Diagnosis ◽  
Compact Graph

Classification Model on Big Data in Medical Diagnosis Based on Semi-Supervised Learning

2020 ◽  
Author(s):  
Lei Wang ◽  
Qing Qian ◽  
Qiang Zhang ◽  
Jishuai Wang ◽  
Wenbo Cheng ◽  
...  
Keyword(s):  
Big Data ◽  
Supervised Learning ◽  
Medical Record ◽  
Medical Diagnosis ◽  
Learning Algorithm ◽  
Classification Model ◽  
Training Algorithm ◽  
Medical Record Data ◽  
Model Based ◽  
Record Data

Abstract Big data in medical diagnosis can provide abundant value for clinical diagnosis, decision support and many other applications, but obtaining a large number of labeled medical data will take a lot of time and manpower. In this paper, a classification model based on semi-supervised learning algorithm using both labeled and unlabeled data is proposed to process big data in medical diagnosis, which includes structured, semi-structured and unstructured data. For the medical laboratory data, this paper proposes a self-training algorithm based on repeated labeling strategy to solve the problem that mislabeled samples weaken the performance of classifiers. Aiming at medical record data, this paper extracts features with high correlation of classification results based on domain expert knowledge base first, and then chooses the unlabeled medical record data with the highest confidence to expand the training set and optimizes the performance of the classifiers of tri-training algorithm, which uses supervised learning algorithm to train three basic classifiers. The experimental results show that the proposed medical diagnosis data classification model based on semi-supervised learning algorithm has good performance.

scholarly journals GFLIB: An Open Source Library for Genetic Folding Solving Optimization Problems

2019 ◽  
Vol 1 (1) ◽  
Author(s):  
Mohammad A. Mezher
Keyword(s):  
Mathematical Models ◽  
Open Source ◽  
Supervised Learning ◽  
Optimization Problems ◽  
Black Box ◽  
Learning Problems ◽  
Matlab Toolbox ◽  
Classification And Regression ◽  
Free Open Source

This paper aims at presenting GFLIB, a Genetic Folding MATLAB toolbox for supervised learning problems. In particular, the goal of GFLIB is to build a concise model of supervised learning, a free, open source MATLAB toolbox for performing classification and regression. The GFLIB specifically designed for most of the features traditionally used to evolve in applications of mathematical models. The toolbox suits all kinds of users, from the users who implemented GFLIB as a “black box”, to the advanced researcher who wants to generate and test new functionalities and parameters of GF algorithm. The toolbox and its documentation are freely available for download at https://github.com/mohabedalgani/gflib.git

ALEDO Algoritmo para la detección de objetos

2019 ◽  
Vol 6 (1) ◽  
pp. 68-73
Author(s):  
Leydi Mercedes Vargas Ordoñez ◽  
Luis Freddy Muñoz Sanabria ◽  
Francisco Javier Álvarez .
Keyword(s):  
Mathematical Models ◽  
Supervised Learning ◽  
Mobile Applications ◽  
Mobile Application ◽  
Traffic Signals ◽  
Detection Of Objects ◽  
Made In

Esta investigación propone un algoritmo para la detección de objetos denominado ALEDO, para ello se hace una revisión en la literatura sobre los algoritmos más usados en estas actividades y se comparan contra ALEDO mediante modelos matemáticos. Se realiza una aplicación móvil usando ALEDO para el reconocimiento de señales de tránsito y basado en el concepto de aprendizaje supervisado. Al verificar la eficacia de ALEDO en la detección de imágenes frente a los algoritmos más usados para el mismo fin, dio como resultado que además de ser eficiente, cumplió con los propósitos para el que fue desarrollado. Es necesario continuar aplicando el algoritmo en otras aplicaciones móviles para la detección de imágenes que permitan solidificar los resultados. This research proposes an algorithm for the detection of objects called ALEDO, for which a review is made in the literature about the algorithms most used in these activities and they are compared against ALEDO through mathematical models. A mobile application is made using ALEDO for the recognition of traffic signals and based on the concept of supervised learning. When verifying the effectiveness of ALEDO in the detection of images in front of the most used algorithms for the same purpose, it resulted in that besides being efficient, it fulfilled the purposes for which it was developed. It is necessary to continue applying the algorithm in other mobile applications for the detection of images that allow to solidify the results.

Sign in / Sign up

Export Citation Format

Share Document