An Intelligent Model for Enterprise Resource Planning Selection Based on BP Neural Network

2018 ◽  
pp. 212-222
Author(s):  
Amine Elyacoubi ◽  
Hicham Attariuas ◽  
Noura Aknin
Keyword(s):  
Neural Network ◽  
Enterprise Resource Planning ◽  
Bp Neural Network ◽  
Resource Planning ◽  
Intelligent Model

An Expert System for Predicting ERP Post-Implementation Benefits Using Artificial Neural Network

2018 ◽  
pp. 760-784
Author(s):  
Ahad Zare Ravasan ◽  
Saeed Rouhani
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Expert System ◽  
Enterprise Resource Planning ◽  
Resource Planning ◽  
Good Prediction ◽  
Industry Type ◽  
Artificial Neural ◽  
Expected Benefits ◽  
Artificial Neural Network Ann

Implementing Enterprise Resource Planning systems (ERPs) is a complex and costly project which usually delivers only a few of expected benefits. Obtaining the expected benefits of ERPs is impressed by a variety of factors and variables which is related to an organization or project environment. In this paper, the idea of predicting ERP post-implementation benefits based on the organizational profiles and factors has been discussed. Regarding the need to form the expectations of organizations about ERP, an expert system is developed by using Artificial Neural Network (ANN) method to articulate the relationships between some organizational factors and ERP's achieved benefits. The expert system's role is in the preparation to capture the data from the new enterprises wishes to implement ERP and predict likely benefits might be achieved from the system. For this end, factors of organizational profiles (such as industry type, size, structure, and so on) are recognized and a feed-forward architecture and Levenberg-Marquardt (trainlm) neural network model is designed, trained and validated with 171 surveyed data of Middle-East located enterprises experienced ERP. The trained ANN embedded in developed expert system predicts with the average correlation coefficients of 0.745, which is respectively high and proves the idea of dependency of ERP post-implementation benefits on the organizational profiles. Besides, total correct classification rate of 0.701 shows good prediction power which can help firms in predicting ERP benefits before system implementation.

An Expert System for Predicting ERP Post-Implementation Benefits Using Artificial Neural Network

2014 ◽  
Vol 10 (3) ◽  
pp. 24-45 ◽  
Author(s):  
Ahad Zare Ravasan ◽  
Saeed Rouhani
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Expert System ◽  
Enterprise Resource Planning ◽  
Size Structure ◽  
Organizational Factors ◽  
Resource Planning ◽  
Good Prediction ◽  
Artificial Neural ◽  
Expected Benefits

Implementing Enterprise Resource Planning systems (ERPs) is a complex and costly project which usually delivers only a few of expected benefits. Obtaining the expected benefits of ERPs is impressed by a variety of factors and variables which is related to an organization or project environment. In this paper, the idea of predicting ERP post-implementation benefits based on the organizational profiles and factors has been discussed. Regarding the need to form the expectations of organizations about ERP, an expert system is developed by using Artificial Neural Network (ANN) method to articulate the relationships between some organizational factors and ERP's achieved benefits. The expert system's role is in the preparation to capture the data from the new enterprises wishes to implement ERP and predict likely benefits might be achieved from the system. For this end, factors of organizational profiles (such as industry type, size, structure, and so on) are recognized and a feed-forward architecture and Levenberg-Marquardt (trainlm) neural network model is designed, trained and validated with 171 surveyed data of Middle-East located enterprises experienced ERP. The trained ANN embedded in developed expert system predicts with the average correlation coefficients of 0.745, which is respectively high and proves the idea of dependency of ERP post-implementation benefits on the organizational profiles. Besides, total correct classification rate of 0.701 shows good prediction power which can help firms in predicting ERP benefits before system implementation.

scholarly journals A particle swarm optimization improved BP neural network intelligent model for electrocardiogram classification

2021 ◽  
Vol 21 (S2) ◽  
Author(s):  
Guixiang Li ◽  
Zhongwei Tan ◽  
Weikang Xu ◽  
Fei Xu ◽  
Lei Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Heart Disease ◽  
Bp Neural Network ◽  
Extraction Method ◽  
Adaptive Threshold ◽  
Swarm Optimization ◽  
Feature Extraction Method ◽  
Feature Dimension ◽  
Intelligent Model

Abstract Background As proven to reflect the work state of heart and physiological situation objectively, electrocardiogram (ECG) is widely used in the assessment of human health, especially the diagnosis of heart disease. The accuracy and reliability of abnormal ECG (AECG) decision depend to a large extent on the feature extraction. However, it is often uneasy or even impossible to obtain accurate features, as the detection process of ECG is easily disturbed by the external environment. And AECG got many species and great variation. What’s more, the ECG result obtained after a long time past, which can not reach the purpose of early warning or real-time disease diagnosis. Therefore, developing an intelligent classification model with an accurate feature extraction method to identify AECG is of quite significance. This study aimed to explore an accurate feature extraction method of ECG and establish a suitable model for identifying AECG and the diagnosis of heart disease. Methods In this research, the wavelet combined with four operations and adaptive threshold methods were applied to filter the ECG and extract its feature waves first. Then, a BP neural network (BPNN) intelligent model and a particle swarm optimization (PSO) improved BPNN (PSO-BPNN) intelligent model based on MIT-BIH open database was established to identify ECG. To reduce the complexity of the model, the principal component analysis (PCA) was used to minimize the feature dimension. Results Wavelet transforms combined four operations and adaptive threshold methods were capable of ECG filtering and feature extraction. PCA can significantly deduce the modeling feature dimension to minimize the complexity and save classification time. The PSO-BPNN intelligent model was suitable for identifying five types of ECG and showed better effects while comparing it with the BPNN model. Conclusion In summary, it was further concluded that the PSO-BPNN intelligent model would be a suitable way to identify AECG and provide a tool for the diagnosis of heart disease.

scholarly journals LSTM DSS Automatism and Dataset Optimization for Diabetes Prediction

2019 ◽  
Vol 9 (17) ◽  
pp. 3532 ◽  
Author(s):  
Alessandro Massaro ◽  
Vincenzo Maritati ◽  
Daniele Giannone ◽  
Daniele Convertini ◽  
Angelo Galiano
Keyword(s):  
Neural Network ◽  
Enterprise Resource Planning ◽  
Short Term Memory ◽  
Resource Planning ◽  
Training Dataset ◽  
Test Accuracy ◽  
Type I ◽  
Patient Health ◽  
Diabetes Prediction ◽  
Few Data

The paper is focused on the application of Long Short-Term Memory (LSTM) neural network enabling patient health status prediction focusing the attention on diabetes. The proposed topic is an upgrade of a Multi-Layer Perceptron (MLP) algorithm that can be fully embedded into an Enterprise Resource Planning (ERP) platform. The LSTM approach is applied for multi-attribute data processing and it is integrated into an information system based on patient management. To validate the proposed model, we have adopted a typical dataset used in the literature for data mining model testing. The study is focused on the procedure to follow for a correct LSTM data analysis by using artificial records (LSTM-AR-), improving the training dataset stability and test accuracy if compared with traditional MLP and LSTM approaches. The increase of the artificial data is important for all cases where only a few data of the training dataset are available, as for more practical cases. The paper represents a practical application about the LSTM approach into the decision support systems (DSSs) suitable for homecare assistance and for de-hospitalization processes. The paper goal is mainly to provide guidelines for the application of LSTM neural network in type I and II diabetes prediction adopting automatic procedures. A percentage improvement of test set accuracy of 6.5% has been observed by applying the LSTM-AR- approach, comparing results with up-to-date MLP works. The LSTM-AR- neural network can be applied as an alternative approach for all homecare platforms where not enough training sequential dataset is available.

Sign in / Sign up

Export Citation Format

Share Document