Adaptive Neuro-Fuzzy Interference System

Suparta, Wayan; Alhasa, Kemal Maulana

doi:10.1007/978-3-319-28437-8_2

Cited by 27 publications

(15 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial intelligence and the family of adaptive models (AMs) have been widely used in the field of biomedical science for the modeling of medical prognosis and patient survival time prediction . The Adaptive Neuro‐Fuzzy Inference System (ANFIS), which is a combination of an adaptive neural network (ANN) and a fuzzy inference system (FIS), can discover and model different classes of data trends, as well as catching subtle patterns from experimental data . Conventional statistical methods, such as the Cox proportional hazard model, log‐rank test and Kaplan–Meier curves, have been shown to be the most useful methods for the investigation of the effect of different parameters on patient survival time.…”

Section: Introductionmentioning

confidence: 99%

DCE‐MRI prediction of survival time for patients with glioblastoma multiforme: using an adaptive neuro‐fuzzy‐based model and nested model selection technique

et al. 2017

View full text Add to dashboard Cite

This pilot study investigates the construction of an Adaptive Neuro-Fuzzy Inference System (ANFIS) for the prediction of the survival time of patients with glioblastoma multiforme (GBM). ANFIS is trained by the pharmacokinetic (PK) parameters estimated by the model selection (MS) technique in dynamic contrast enhanced-magnetic resonance imaging (DCE-MRI) data analysis, and patient age. DCE-MRI investigations of 33 treatment-naïve patients with GBM were studied. Using the modified Tofts model and MS technique, the following physiologically nested models were constructed: Model 1, no vascular leakage (normal tissue); Model 2, leakage without efflux; Model 3, leakage with bidirectional exchange (influx and efflux). For each patient, the PK parameters of the three models were estimated as follows: blood plasma volume (v ) for Model 1; v and volume transfer constant (K ) for Model 2; v , K and rate constant (k ) for Model 3. Using Cox regression analysis, the best combination of the estimated PK parameters, together with patient age, was identified for the design and training of ANFIS. A K-fold cross-validation (K = 33) technique was employed for training, testing and optimization of ANFIS. Given the survival time distribution, three classes of survival were determined and a confusion matrix for the correct classification fraction (CCF) of the trained ANFIS was estimated as an accuracy index of ANFIS's performance. Patient age, k and v (K /k ) of Model 3, and K of Model 2, were found to be the most effective parameters for training ANFIS. The CCF of the trained ANFIS was 84.8%. High diagonal elements of the confusion matrix (81.8%, 90.1% and 81.8% for Class 1, Class 2 and Class 3, respectively), with low off-diagonal elements, strongly confirmed the robustness and high performance of the trained ANFIS for predicting the three survival classes. This study confirms that DCE-MRI PK analysis, combined with the MS technique and ANFIS, allows the construction of a DCE-MRI-based fuzzy integrated predictor for the prediction of the survival of patients with GBM.

show abstract

Section: Introductionmentioning

confidence: 99%

DCE‐MRI prediction of survival time for patients with glioblastoma multiforme: using an adaptive neuro‐fuzzy‐based model and nested model selection technique

et al. 2017

View full text Add to dashboard Cite

show abstract

“…This random version can generate any number of trees. Such randomization could help reduce variance and improve performance (2)- (10). Thus, we take the random order for our algorithm development.…”

Section: The Proposed Methodsmentioning

confidence: 99%

Integrated Learning via Randomized Forests and Localized Regression With Application to Medical Diagnosis

2019

View full text Add to dashboard Cite

The tree-based machine learning functions on the divide-and-conquer principle and is known to perform well in certain applications. In this paper, we first give a new data partitioning rule using the mean of the data columns to grow the tree till the child nodes are small in size. Then, the local regression is applied to leave nodes to enhance the resolution of the node outputs. Randomization is introduced at tree growth and forest creation. The local prediction accuracies on the leaves are used to select a subset of the test data for actual predictions. The case study on the diagnosis of autistic spectrum disorder shows that the proposed method achieves the prediction accuracy of the ensemble at above 96% with reduced variance, which is much better than those reported in the literature.INDEX TERMS Classification and regression tree, hybrid expert system, decision tree.

show abstract

“…There are two types of neural network architecture: feedforward, and feedback [39]. In a feedforward network the data moves in one direction only while feedback neural networks have additional feedback from the previous layer.…”

Section: Figure 1 Artificial Neural Network Structure Showing Relationship Between Inputs Andmentioning

confidence: 99%

“…In a feedforward network the data moves in one direction only while feedback neural networks have additional feedback from the previous layer. Feedback models are commonly used for adaptive control applications [39]. An example of a feedback neural network thermal dynamic model is in [30] where the researchers investigated the use of multi-input multi-output (MIMO) network structures instead of the more typically used multi-input single-output (MISO).…”

Section: Figure 1 Artificial Neural Network Structure Showing Relationship Between Inputs Andmentioning

confidence: 99%

Development of a Grey Box Thermal Dynamic Model without Building Construction Knowledge

LeRiche¹

2021

Preprint

View full text Add to dashboard Cite

Model Predictive Controllers (MPC) in building Heating Ventilation and Air Conditioning (HVAC) systems have demonstrated significant energy savings when compared to typical on/off controllers. MPCs require information about the building’s thermal dynamics which is challenging to model, especially for older structures without buildings specifications. This research investigates the ability to develop a grey box thermal dynamic model that can determine the net thermal dynamics, without any building construction information. Sensors were installed within a test cell to monitor the building automation system (BAS) points, and collect building element surface temperature data. The simulation program Simulink was used to develop and test iterations of grey box models. The final model, that relies solely on BAS points, is able to predict the ambient temperature for a 3-hour Prediction Window to within 1.7% accuracy. This model demonstrates the potential for more buildings to implement HVAC MPC systems with grey box thermal dynamic modeling

show abstract

Adaptive Neuro-Fuzzy Interference System

Cited by 27 publications

References 9 publications

DCE‐MRI prediction of survival time for patients with glioblastoma multiforme: using an adaptive neuro‐fuzzy‐based model and nested model selection technique

DCE‐MRI prediction of survival time for patients with glioblastoma multiforme: using an adaptive neuro‐fuzzy‐based model and nested model selection technique

Integrated Learning via Randomized Forests and Localized Regression With Application to Medical Diagnosis

Development of a Grey Box Thermal Dynamic Model without Building Construction Knowledge

Contact Info

Product

Resources

About