A Comparison Study between Integrated OBFARX-NN and OBF-NN for Modeling of Nonlinear Systems in Extended Regions of Operation

2014 ◽  
Vol 625 ◽  
pp. 382-385
Author(s):  
Haslinda Zabiri ◽  
M. Ariff ◽  
Lemma Dendena Tufa ◽  
Marappagounder Ramasamy
Keyword(s):  
Neural Network ◽  
Nonlinear Models ◽  
Nonlinear System Identification ◽  
Model Performance ◽  
Identification Algorithm ◽  
Comparison Study ◽  
Auto Regressive ◽  
Linear And Nonlinear ◽  
Parallel Integration

In this paper the combination of linear and nonlinear models in parallel for nonlinear system identification is investigated. A residuals-based sequential identification algorithm using parallel integration of linear Orthornormal basis filters-Auto regressive with exogenous input (OBFARX) and a nonlinear neural network (NN) models is developed. The model performance is then compared against previously developed parallel OBF-NN model in a nonlinear CSTR case study in extended regions of operation (i.e. extrapolation capability).

Heuristic Order Reduction of NARX-OBF models Applied to Nonlinear System Identification

2020 ◽  
Vol 1 (2) ◽  
Author(s):  
Elder Oroski ◽  
Beatriz Do Santos Pês ◽  
Adolfo Bauchspiess ◽  
Marco Egito Coelho
Keyword(s):  
System Identification ◽  
Nonlinear System ◽  
Nonlinear System Identification ◽  
Model Performance ◽  
Order Reduction ◽  
Computational Effort ◽  
Model Parameters ◽  
Auto Regressive ◽  
Narx Models

Nonlinear system identification concerns the determination of the model structure and its parameters. Although the designers often seek the best model for each system, it can be tricky to determine, at the same time, the best structure and the parameters which optimize the model performance. This paper proposes the use of a Genetic Algorithm, GA, and the Levenberg-Marquardt, LM, method to obtain the model parameters, as well as perform the order reduction of the model. In order to validate the proposed methodology, the identification of a magnetic levitator, operating in closed loop, was performed. The class NARX-OBF, Nonlinear Auto Regressive with eXogenous input-Orthonormal Basis Function, was used. The use of OBF functions aims to reduce the number of terms in NARX models. Once the model is found, the order reduction is performed using GA and LM, in a hybrid application, capable of determining the model parameters and reducing the original model order, simultaneously. The results show, considering the inherent trade-of between accuracy and computational effort, the proposed methodology provided an implementation with good mean square error, when compared with the full NARX-OBF model.

scholarly journals Design a Different Structures Controller for Controlled Systems Using a Spiking Neural Network

2019 ◽  
pp. 18-29
Keyword(s):  
Neural Network ◽  
Mean Squared Error ◽  
Nonlinear Models ◽  
Spiking Neural Network ◽  
Spike Response ◽  
Controlled Systems ◽  
Minimum Mean Squared Error ◽  
Minimum Number ◽  
Linear And Nonlinear ◽  
Spike Response Model

The design and simulation of the Spiking Neural Network (SNN) are proposed in this paper to control a plant without and with load. The proposed controller is performed using Spike Response Model. SNNs are more powerful than conventional artificial neural networks since they use fewer nodes to solve the same problem. The proposed controller is implemented using SNN to work with different structures as P, PI, PD or PID like to control linear and nonlinear models. This controller is designed in discrete form and has three inputs (error, integral of error and derivative of error) and has one output. The type of controller, number of hidden nodes, and number of synapses are set using external inputs. Sampling time is set according to the controlled model. Social-Spider Optimization algorithm is applied for learning the weights of the SNN layers. The proposed controller is tested with different linear and nonlinear models and different reference signals. Simulation results proved the efficiency of the suggested controller to reach accurate responses with minimum Mean Squared Error, small structure and minimum number of epochs under no load and load conditions.

scholarly journals Optimizing the Environmental and Economic Sustainability of Remote Community Infrastructure

2020 ◽  
Vol 12 (6) ◽  
pp. 2208 ◽  
Author(s):  
Jamie E. Filer ◽  
Justin D. Delorit ◽  
Andrew J. Hoisington ◽  
Steven J. Schuldt
Keyword(s):  
Environmental Impacts ◽  
Sustainability Assessment ◽  
Model Performance ◽  
Assessment Model ◽  
Remote Communities ◽  
Remote Community ◽  
Rural Villages ◽  
Sustainable Technologies ◽  
Study Results

Remote communities such as rural villages, post-disaster housing camps, and military forward operating bases are often located in remote and hostile areas with limited or no access to established infrastructure grids. Operating these communities with conventional assets requires constant resupply, which yields a significant logistical burden, creates negative environmental impacts, and increases costs. For example, a 2000-member isolated village in northern Canada relying on diesel generators required 8.6 million USD of fuel per year and emitted 8500 tons of carbon dioxide. Remote community planners can mitigate these negative impacts by selecting sustainable technologies that minimize resource consumption and emissions. However, the alternatives often come at a higher procurement cost and mobilization requirement. To assist planners with this challenging task, this paper presents the development of a novel infrastructure sustainability assessment model capable of generating optimal tradeoffs between minimizing environmental impacts and minimizing life-cycle costs over the community’s anticipated lifespan. Model performance was evaluated using a case study of a hypothetical 500-person remote military base with 864 feasible infrastructure portfolios and 48 procedural portfolios. The case study results demonstrated the model’s novel capability to assist planners in identifying optimal combinations of infrastructure alternatives that minimize negative sustainability impacts, leading to remote communities that are more self-sufficient with reduced emissions and costs.

scholarly journals Effectiveness of transfer learning for enhancing tumor classification with a convolutional neural network on frozen sections

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Young-Gon Kim ◽  
Sungchul Kim ◽  
Cristina Eunbee Cho ◽  
In Hye Song ◽  
Hee Jin Lee ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Frozen Section ◽  
Medical Center ◽  
External Validation ◽  
Model Performance ◽  
Classification Model ◽  
Training Dataset

AbstractFast and accurate confirmation of metastasis on the frozen tissue section of intraoperative sentinel lymph node biopsy is an essential tool for critical surgical decisions. However, accurate diagnosis by pathologists is difficult within the time limitations. Training a robust and accurate deep learning model is also difficult owing to the limited number of frozen datasets with high quality labels. To overcome these issues, we validated the effectiveness of transfer learning from CAMELYON16 to improve performance of the convolutional neural network (CNN)-based classification model on our frozen dataset (N = 297) from Asan Medical Center (AMC). Among the 297 whole slide images (WSIs), 157 and 40 WSIs were used to train deep learning models with different dataset ratios at 2, 4, 8, 20, 40, and 100%. The remaining, i.e., 100 WSIs, were used to validate model performance in terms of patch- and slide-level classification. An additional 228 WSIs from Seoul National University Bundang Hospital (SNUBH) were used as an external validation. Three initial weights, i.e., scratch-based (random initialization), ImageNet-based, and CAMELYON16-based models were used to validate their effectiveness in external validation. In the patch-level classification results on the AMC dataset, CAMELYON16-based models trained with a small dataset (up to 40%, i.e., 62 WSIs) showed a significantly higher area under the curve (AUC) of 0.929 than those of the scratch- and ImageNet-based models at 0.897 and 0.919, respectively, while CAMELYON16-based and ImageNet-based models trained with 100% of the training dataset showed comparable AUCs at 0.944 and 0.943, respectively. For the external validation, CAMELYON16-based models showed higher AUCs than those of the scratch- and ImageNet-based models. Model performance for slide feasibility of the transfer learning to enhance model performance was validated in the case of frozen section datasets with limited numbers.

Sign in / Sign up

Export Citation Format

Share Document