Artificial neural network visualization methods reveal diagnostically relevant brain regions to detect Alzheimer’s disease: The first step towards comprehensive artificial intelligence

Objective: To develop and implement an online Artificial Neural Network (ANN) that provides the probability of a subject having mild cognitive impairment (MCI) or Alzheimer’s disease (AD). Method: Different ANNs were trained using a sample of 350 controls (CONT), 75 MCI and 93 AD subjects. The ANN structure chosen was the following: (1) an input layer of 33 cognitive variables from the Neuronorma battery plus two sociodemographic variables, age and education. This layer was reduced to a 15 features input vector using Multiple Discriminant Analysis method, (2) one hidden layer with 8 neurons, and (3) three output neurons corresponding to the 3 expected cognitive states. This ANN was defined in a previous study [28]. The ANN was implemented on the web site www.test-barcelona.com (Test Barcelona Workstation) [9]. Results: When comparing CONT, MCI and AD participants, the best ANN correctly classifies up to 94,87% of the study participants. Conclusions: The online implemented ANN, delivers the probabilities (%) of belonging to the CONT, MCI and AD groups of a subject assessed using the 35 characteristics (variables) of the Neuronorma profile. This tool is a good complement for the interpretation of cognitive profiles. This technology improves clinical decision making. Keywords: Artificial Neural Network, Probability, Alzheimer disease, Test Barcelona Workstation.

Download Full-text

Tower of London Test: A Comparison between Conventional Statistic Approach and Modelling Based on Artificial Neural Network in Differentiating Fronto-Temporal Dementia from Alzheimer’s Disease

Behavioural Neurology ◽

10.1155/2011/754659 ◽

2011 ◽

Vol 24 (2) ◽

pp. 149-158 ◽

Cited By ~ 10

Author(s):

Massimo Franceschi ◽

Paolo Caffarra ◽

Rita Savarè ◽

Renata Cerutti ◽

Enzo Grossi ◽

...

Keyword(s):

Neural Network ◽

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Artificial Neural Network ◽

Tower Of London ◽

Artificial Neural ◽

Statistic Approach

Download Full-text

Development of New Permeability Formulation From Well Log Data Using Artificial Intelligence Approaches

Journal of Energy Resources Technology ◽

10.1115/1.4039270 ◽

2018 ◽

Vol 140 (7) ◽

Cited By ~ 24

Author(s):

Tamer Moussa ◽

Salaheldin Elkatatny ◽

Mohamed Mahmoud ◽

Abdulazeez Abdulraheem

Keyword(s):

Neural Network ◽

Artificial Intelligence ◽

Artificial Neural Network ◽

Well Log ◽

Well Test ◽

Log Data ◽

Hydrocarbon Reservoir ◽

Reservoir Permeability ◽

Artificial Neural ◽

Core Permeability

Permeability is a key parameter related to any hydrocarbon reservoir characterization. Moreover, many petroleum engineering problems cannot be precisely answered without having accurate permeability value. Core analysis and well test techniques are the conventional methods to determine permeability. These methods are time-consuming and very expensive. Therefore, many researches have been introduced to identify the relationship between core permeability and well log data using artificial neural network (ANN). The objective of this research is to develop a new empirical correlation that can be used to determine the reservoir permeability of oil wells from well log data, namely, deep resistivity (RT), bulk density (RHOB), microspherical focused resistivity (RSFL), neutron porosity (NPHI), and gamma ray (GR). A self-adaptive differential evolution integrated with artificial neural network (SaDE-ANN) approach and evolutionary algorithm-based symbolic regression (EASR) techniques were used to develop the correlations based on 743 actual core permeability measurements and well log data. The obtained results showed that the developed correlations using SaDE-ANN models can be used to predict the reservoir permeability from well log data with a high accuracy (the mean square error (MSE) was 0.0638 and the correlation coefficient (CC) was 0.98). SaDE-ANN approach is more accurate than the EASR. The introduced technique and empirical correlations will assist the petroleum engineers to calculate the reservoir permeability as a function of the well log data. This is the first time to implement and apply SaDE-ANN approaches to estimate reservoir permeability from well log data (RSFL, RT, NPHI, RHOB, and GR). Therefore, it is a step forward to eliminate the required lab measurements for core permeability and discover the capabilities of optimization and artificial intelligence models as well as their application in permeability determination. Outcomes of this study could help petroleum engineers to have better understanding of reservoir performance when lab data are not available.

Download Full-text