Deep Hybrid System of Computational Intelligence with Architecture Adaptation for Medical Fuzzy Diagnostics

@article{Perova2017DeepHS,
  title={Deep Hybrid System of Computational Intelligence with Architecture Adaptation for Medical Fuzzy Diagnostics},
  author={Iryna Perova and Iryna Pliss},
  journal={International Journal of Intelligent Systems and Applications},
  year={2017},
  volume={9},
  pages={12-21}
}
  • I. Perova, I. Pliss
  • Published 8 July 2017
  • Computer Science
  • International Journal of Intelligent Systems and Applications
In the paper the deep hybrid system of computational intelligence with architecture adaptation for medical fuzzy diagnostics is proposed. This system allows to increase a quality of medical information processing under the condition of overlapping classes due to special adaptive architecture and training algorithms. The deep hybrid system under consideration can tune its architecture in situation when number of features and diagnoses can be variable. The special algorithms for its training are… 

Tables from this paper

A Two-Step Data Normalization Approach for Improving Classification Accuracy in the Medical Diagnosis Domain
TLDR
A new two-step method for data normalization of numerical medical datasets based on the possibility of considering both the interdependencies between the features of each observation from the dataset and their absolute values to improve the accuracy when performing medical data mining tasks is developed.
Fuzzy Clustering of Biomedical Datasets Using BSB-Neuro-Fuzzy-Model
TLDR
A special neural networks that contain autoassociative memory (AM) BSBand GBSB-models are investigated and a training algorithm enables to enrich the BSB-neuro-fuzzy model by adaptive properties.
ADAPTIVE HUMAN MACHINE INTERACTION APPROACH FOR FEATURE SELECTION-EXTRACTION TASK IN MEDICAL DATA MINING
TLDR
New approach to evaluation of medical features information quantity, based on optimized combination of feature selection and feature extraction methods is proposed, which allows physicians to have the most informative features without losing their linguistic interpreting.
Piecewise-linear Approach for Medical Insurance Costs Prediction using SGTM Neural-Like Structure
TLDR
The article proposes a new insurance medical cost prediction method based on the piecewise-linear approach using the SGTM neural-like structure, which shows the possibility of using the proposed approach for the processing of a large amount of data, in particular in the fields of medicine, economics, materials science, service sciences.
Multidimensional Wavelet Neuron for Pattern Recognition Tasks in the Internet of Things Applications
TLDR
The proposed multidimensional wavelet neuron can be used to solve a very large class of information processing problems for the Internet of Things applications when signals are fed in online mode from many sensors.
Non-iterative Neural-like Predictor for Solar Energy in Libya
TLDR
The proposed method showed the best prediction results (MAPE, RMSE) compared to SVM, Linear Regression, the linear Neural-like structure of the Successive Geometric Transformation Model (SGTM), and the RBF based on the NLS SGTM.
Data Stream Clustering in Conditions of an Unknown Amount of Classes
An on-line modified X-means method is proposed for solving data stream clustering tasks in conditions when an amount of clusters is apriori unknown. This approach is based on an ensemble of
On-line Robust Fuzzy Clustering for Anomalies Detection
TLDR
New robust fuzzy clustering algorithm (RFC) for exploring of signals of different nature taking into account the presence of noise with unknown density distributions and anomalous outliers in the data being analyzed is presented in this paper.
The Ontology as the Core of Integrated Information Environment of Chinese Image Medicine
TLDR
The architecture of the components integrated onto-oriented information and analytical environment for scientific research, professional healing activities and e-learning of the Chinese Image Medicine is presented and the axiomatic-deductive strategy of organizing the knowledge space of the CIM is proposed.
Technologies for Making Reliable Decisions on a Variety of Effective Factors using Fuzzy Logic
TLDR
Problem of choosing methods has been presented for increasing the reliability of solutions while reducing the time resource for researching the state space of a particular object using the fuzzy inference procedure and the Zade-Mamdani’s approach.
...
...

References

SHOWING 1-10 OF 29 REFERENCES
Design of a hybrid system for the diabetes and heart diseases
Automated Differential Diagnosis in Medical Systems Using Neural Networks, kNN and SOM
TLDR
This system aids medical diagnosis in the whole dataset by computing the probability of occurrence of a particular ailment from the medical data using a unique algorithm which increases accuracy of such diagnosis by combining Neural Networks and Differential Diagnosis all integrated into one single approach.
Evolving fuzzy medical diagnosis of Pima Indians diabetes and of dermatological diseases
MEDICAL DIAGNOSIS ON PIMA INDIAN DIABETES USING GENERAL REGRESSION NEURAL NETWORKS
TLDR
Close classification accuracy to the reference work using ARTMAP-IC structured model, which is the best result obtained since now, is achieved by using GRNN, which has a simpler structure.
A novel method for medical disease diagnosis using artificial neural networks based on backpropagation algorithm
TLDR
Two different artificial neural networks are proposed for disease diagnosis, which uses Scaled Conjugate gradient backpropagation and Levenberg-Marquardt back Propagation algorithm for training the neural networks.
Multi-objective evolutionary algorithms for fuzzy classification in survival prediction
An evolving radial basis neural network with adaptive learning of its parameters and architecture
The paper proposes a learning method for an evolving Radial Basis Neural Network that makes it possible in an online mode to adjust not only synaptic weights but also parameters of the radial basis
Study of Type 2 diabetes risk factors using neural network for Thai people and tuning neural network parameters
TLDR
New factors that are smoking and alcohol consumption to improve accuracy in diabetes prediction are presented and tuning neural network parameter introduces a high accuracy compared with the baseline up to 1.2%.
...
...