Filters








8,214 Hits in 3.0 sec

Aligning Bayesian Network Classifiers with Medical Contexts [chapter]

Linda C. van der Gaag, Silja Renooij, Ad Feelders, Arend de Groote, Marinus J. C. Eijkemans, Frank J. Broekmans, Bart C. J. M. Fauser
2009 Lecture Notes in Computer Science  
For Bayesian network classifiers to become more widely accepted within the medical community then, we feel that they should be better aligned with their context of application.  ...  We describe how to incorporate well-known concepts of clinical relevance in the process of constructing and evaluating Bayesian network classifiers to achieve such an alignment.  ...  The medical context In this section we describe the medical concepts relevant for our case study of aligning Bayesian network classifiers with a medical context.  ... 
doi:10.1007/978-3-642-03070-3_59 fatcat:k3zy6k3oyrhxdplfokrjrnxpca

Blockmodels for connectome analysis

Daniel Moyer, Boris Gutman, Gautam Prasad, Joshua Faskowitz, Greg Ver Steeg, Paul Thompson, Eduardo Romero, Natasha Lepore, Juan D. García-Arteaga, Jorge Brieva
2015 11th International Symposium on Medical Information Processing and Analysis  
We further provide a simple generative classifier that, alongside more discriminating methods, provides evidence that blockmodels accurately summarize tractography count networks with respect to a disease  ...  In the present work we study a family of generative network model and its applications for modeling the human connectome.  ...  goodness-of-fit for each blockmodel, in tandem with the aforementioned simple Bayesian classifier.  ... 
doi:10.1117/12.2211519 fatcat:tpttoovxuzcnrhmfbirztsp7qi

Heart murmurs identification using random forests in assistive environments

Euripides Loukis, Manolis Maragoudakis
2010 Proceedings of the 3rd International Conference on PErvasive Technologies Related to Assistive Environments - PETRA '10  
Also, some alternative classifiers have been applied to the same data for comparison purposes.  ...  The aging population in many countries, in combination with high government deficits and financial resources limitations, necessitates new methods for the home care of the elderly at reasonable costs based  ...  More specifically, a Naïve Bayesian classifier, which incorporated a Gaussian distribution for tackling with numerical features, along with Radial Basis Functions Neural Networks (using a Gaussian kernel  ... 
doi:10.1145/1839294.1839304 dblp:conf/petra/LoukisM10 fatcat:aasfkkzenzftnhzuzyu72kfhee

Enhancing Health Risk Prediction with Deep Learning on Big Data and Revised Fusion Node Paradigm

Hongye Zhong, Jitian Xiao
2017 Scientific Programming  
Deep learning involves the complex application of machine-learning algorithms, such as Bayesian fusions and neural network, for data extraction and logical inference.  ...  With recent advances in health systems, the amount of health data is expanding rapidly in various formats.  ...  The aim of the process of CNN is to map the n input aligned data to m output health risks in a vast sampling context with high performance ( Figure 11 ).  ... 
doi:10.1155/2017/1901876 fatcat:b3yrbejvbzh3bi7etsoeykzivu

Lung nodule detection in CT using 3D convolutional neural networks

Xiaojie Huang, Junjie Shan, Vivek Vaidya
2017 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)  
The results also showed the advantages of 3D CNN over 2D CNN in volumetric medical image analysis.  ...  The system leverages both a priori knowledge about lung nodules and confounding anatomical structures and data-driven machine-learned features and classifier.  ...  Our system is different in the following aspects: 1) candidate generation with curvature-based filter and bayesian models, 2) principal direction alignment of candidate cubes, 3) data augmentation, 4)  ... 
doi:10.1109/isbi.2017.7950542 dblp:conf/isbi/HuangSV17 fatcat:on4ufzvmmvddhkq6rpb6vupt7a

Application on Pervasive Computing in Healthcare – A Review

Paramita Sarkar, Ditipriya Sinha
2017 Indian Journal of Science and Technology  
Along with this it has presented comparative analysis of the surveyed algorithms based on their important features.  ...  Background/Objectives: Application of pervasive computation in healthcare is an interdisciplinary research domain for both the medical and computer domains.  ...  In context aware system 5.46 proposes a quality assured and context aware data fusion and an ontological rule based semantic network for context delivery by Dynamic Bayesian network and mediated by ontological  ... 
doi:10.17485/ijst/2017/v10i3/110619 fatcat:cciamdk3hvebdlvb7ir6xqcy6m

Group Emotion Recognition Using Machine Learning [article]

Samanyou Garg
2019 arXiv   pre-print
In this report, we describe our solution which is a hybrid machine learning system that incorporates deep neural networks and Bayesian classifiers.  ...  The Bayesian network works from top to bottom, inferring the global emotion for the image, by integrating the visual features of the contents of the image obtained through a scene descriptor.  ...  Fails to work on non-aligned images and those with occlusions.  ... 
arXiv:1905.01118v1 fatcat:62anlz7mxvhwvfaeqxifz3qpmu

Word2Vec inversion and traditional text classifiers for phenotyping lupus

Clayton A. Turner, Alexander D. Jacobs, Cassios K. Marques, James C. Oates, Diane L. Kamen, Paul E. Anderson, Jihad S. Obeid
2017 BMC Medical Informatics and Decision Making  
These matrices were subjected to several different NLP classifiers: neural networks, random forests, naïve Bayes, support vector machines, and Word2Vec inversion, a Bayesian inversion method.  ...  The aim of this research is to evaluate the performance of traditional classifiers for identifying patients with Systemic Lupus Erythematosus (SLE) in comparison with a newer Bayesian word vector method  ...  Funding This work is funded by the National Institutes of Health (NIH) Grant #s P60AR062755 and UL1TR000062, the Medical University of South Carolina, the College of Charleston and the SmartState Program  ... 
doi:10.1186/s12911-017-0518-1 pmid:28830409 pmcid:PMC5568290 fatcat:ptcp4xs37bbydnpjcyodltb7s4

Large Scale Indexing of Generic Medical Image Data using Unbiased Shallow Keypoints and Deep CNN Features [article]

L. Chauvin, M. Ben Lazreg, J.B. Carluer, W. Wells, M. Toews
2020 arXiv   pre-print
A novel Bayesian model combines shallow and deep features based on an assumption of conditional independence and validated by experiments indexing specific family members and general group categories in  ...  How do deep network activations and shallow keypoint descriptors compare in the context of medical image data indexing and classification?  ...  Discussion We propose a novel Bayesian formulation in order to combine generic keypoint and CNN information into a single, highly efficient memory-based model for indexing and classifying generic 3D medical  ... 
arXiv:2010.04283v2 fatcat:yszvwiockvh7lihmdixaoavkli

Generalizations of Rough Sets: From Crisp to Fuzzy Cases [chapter]

Masahiro Inuiguchi
2004 Lecture Notes in Computer Science  
Classifier Networks -Towards Hierarchical Concept Construction p. 554 Associative Historical Knowledge Extraction from the Structured Memory p. 561 Clustering Utilizing Rough Sets and Multi-objective  ...  Used with permission.  ... 
doi:10.1007/978-3-540-25929-9_3 fatcat:saiacsrpovgphlh5zzhoq4tcrq

Health Recommender System Using Big Data Analytics

J.Archenaa, E.A.Mary Anita
2017 Zenodo  
Bayesian methods is becoming popular in medical research due its effectiveness in making better predictions.For example on training the model with the age of women and diabetes condition helps to predict  ...  In this world filled with the latest technology, healthcare professionals feel more comfortable to utilize the social network to treat their patients effectively.  ...  Bayesian classifier is used to predict diabetes accurately even with less amounts of training data.  ... 
doi:10.5281/zenodo.833884 fatcat:f536knjc3fb3fexzjrcgca47oe

Health Recommender System Using Big Data Analytics

J.Archenaa, E.A.Mary Anita
2017 Zenodo  
Bayesian methods is becoming popular in medical research due its effectiveness in making better predictions.For example on training the model with the age of women and diabetes condition helps to predict  ...  In this world filled with the latest technology, healthcare professionals feel more comfortable to utilize the social network to treat their patients effectively.  ...  Bayesian classifier is used to predict diabetes accurately even with less amounts of training data.  ... 
doi:10.5281/zenodo.834918 fatcat:gua3hpksmbckzogurxscykxwue

Health Recommender System Using Big Data Analytics

J.Archenaa, E.A.Mary Anita
2017 Zenodo  
Bayesian methods is becoming popular in medical research due its effectiveness in making better predictions.For example on training the model with the age of women and diabetes condition helps to predict  ...  In this world filled with the latest technology, healthcare professionals feel more comfortable to utilize the social network to treat their patients effectively.  ...  Bayesian classifier is used to predict diabetes accurately even with less amounts of training data.  ... 
doi:10.5281/zenodo.833885 fatcat:olmkxvgv4nedpjp5t7j5owuybu

PROBABILISTIC GLYCEMIC CONTROL DECISION SUPPORT IN ICU: PROOF OF CONCEPT USING BAYESIAN NETWORK

Asma Abu-Samah, Normy Norfiza Abdul Razak, Fatanah Mohamad Suhaimi, Ummu Kulthum Jamaludin, Azrina Md. Ralib
2019 Jurnal Teknologi  
With more data, improved Bayesian Network is believed to be reproduced.  ...  These results, nevertheless, points at the feasibility of the network to act as an effective classifier using intensive care units data, and glycemic control performance to be the basis of a probabilistic  ...  Bayesian Network Probabilistic Bayesian Network (BN) is a method that has various advantages over the stochastic method.  ... 
doi:10.11113/jt.v81.12721 fatcat:4sm3nn3qj5acfplvd65czordb4

Spatial component analysis of MRI data for Alzheimer's disease diagnosis: a Bayesian network approach

Ignacio A. Illan, Juan M. Górriz, Javier Ramírez, Anke Meyer-Base
2014 Frontiers in Computational Neuroscience  
In this approach, the whole brain image is subdivided in regions or spatial components, and a Bayesian network is used to model the dependencies between affected regions of AD.  ...  The structure of relations between affected regions allows to detect neurodegeneration with an estimated performance of 88% on more than 400 subjects and predict neurodegeneration with 80% accuracy, supporting  ...  Bayesian networks Formally, a Bayesian network for a set of labeled random variables {Z,Y} is a pair G and θ.  ... 
doi:10.3389/fncom.2014.00156 pmid:25505408 pmcid:PMC4244642 fatcat:nenlk7s35bf5biqgkyh4jtv5gu
« Previous Showing results 1 — 15 out of 8,214 results