A clinical decision support system using multi-layer perceptron neural network to predict quality of life in diabetes

Rao, M. R. Narasinga; Sridhar, GR; Madhu, K; Rao, Allam Appa

doi:10.1016/j.dsx.2009.04.002

Cited by 22 publications

(22 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…14 by considering the psychosocial and builtenvironment factors for the prevention of diabetes. Prevention of Type 2 diabetes will require measures to promote physical activity and stress reduction measures in the built environment they live in, and to reduce obesity in adults and children 13 . Finally, in this research, The authors have tried to find the relationship between built environment and diabetes mellitus using neural network technology.…”

Section: Discussionmentioning

confidence: 99%

“…The test set is fundamentally similar to the training set, but it contains different data 13 . If testing fails network structure or the learning parameters are then modified 12 .…”

mentioning

confidence: 99%

“…The learning takes place by providing data for both inputs and outputs 13 . The calculated output value is compared to the required value that is also given in the training set 13 .…”

mentioning

confidence: 99%

See 2 more Smart Citations

A Study of Psychosocial and Built Environment factors for Diabetes using MLP Neural Network

Narasingarao¹,

Rao²,

Ramakrishna³

2012

IJCA

View full text Add to dashboard Cite

Background: Diabetes Mellitus is a common metabolic disorder and which is prevalent among many people in India. Although there are many factors which influence the onset of diabetes, the relationship between built environment and psycho-social factors is one such factor which play a crucial role for the onset of diabetes. Hence, in this research, the authors try to make a comparative study between built environment and psychosocial factors by using multilayer feed-forward neural networks using back propagation and Modified Feed-Forward Neural Network Constructive (MFNNC)algorithm. Material and MethodsIn this research, we tried to compare the performance of two individual neural networks, one is an MLP with backpropagation algorithm and the other is also an MLP with a constructive algorithm known as multilayer feed forward neural network constructive (MFNNC) algorithm. For using an MLP with back-propagation algorithm prior knowledge of neural network architecture is necessary for proper training and testing the network. Usually, trial and error method is used to predict the exact architecture of the network. Hence, in this connection we have proposed a constructive algorithm called multilayer feed-forward neural network constructive algorithm (MFNNC) with which one can predict the exact architecture of the network along with predictive capability. The MFNNC algorithm starts with one hidden neuron in the hidden layer and gradually increases the hidden neurons in the hidden layer if the error generated by the network is more than the value given in the interactive mode or the error is the same for three consecutive examples. The performances of the MLP with back-propagation algorithm and the other with MFNNC algorithm were compared and tested. ResultsMales who are having lesser primary activity (PMA) have more food intake(FI) and more basic mobility (BMB) than their female counterparts. Males who are having more activity by health(ABH), have more professional activity(PRA), almost the same rest (RES) values, more food intake (FI) and have more basic mobility (BMB) compared to their female counter parts. Males who are having more professional activity (PRA) have lesser leisure (LEI) values, almost the same rest (RES) values, more food intake (FI), more basic mobility (BMB), when compared to their female counterparts.Males who are having similar leisure (LEI) have the same rest (RES), when compared to their female counterparts. ConclusionWe have developed two prototype models using neural networks one is an MLP with back propagation algorithm and other one is a feed forward neural network with MFNNC algorithm. We have observed that both the networks have performed well in assessing the parameters for the onset of diabetes by giving the inputs as biological and biographical variables and by considering error values of both of the networks. It is also observed that, using the MFNNC algorithm is better if one wants to know the architecture of the trained network rather than just using MLP with back propagation a...

show abstract

Section: Discussionmentioning

confidence: 99%

“…The test set is fundamentally similar to the training set, but it contains different data 13 . If testing fails network structure or the learning parameters are then modified 12 .…”

mentioning

confidence: 99%

See 1 more Smart Citation

A Study of Psychosocial and Built Environment factors for Diabetes using MLP Neural Network

Narasingarao¹,

Rao²,

Ramakrishna³

2012

IJCA

View full text Add to dashboard Cite

show abstract

“…This back-propagation algorithm is used to train the network for predicting correct outputs those obtained from experiments and generated ones. The operation of the typical back-propagation network occurs as follows [20].…”

Section: B Neural Network Architecturementioning

confidence: 99%

An intelligent system for predicting Thrips tabaci Linde pest population dynamics allied to cotton crop

Patil

Govardhan

Mytri³

2009

2009 2nd IEEE International Conference on Computer Science and Information Technology

View full text Add to dashboard Cite

The agricultural sector in India is up against a series of problems when it comes to increasing crop productivity. A number of successful researches have been carried out to discover productive agricultural practices to improve crop cultivation but despite their efforts, productivity achieved by most of the farmers has not been in upper-bound level. The prime reason stated globally for crop loss is Insect pests. An efficient pest management technique can be devised if we could predict in advance the occurrences of peak activities of a given pest. Researchers are undertaken to understand the pest population dynamics by employing analytical and other techniques on pest surveillance data sets. In this paper, we present an intelligent system for pest prediction in cotton crop with the aid of the data obtained from College of Agriculture, Raichur, India. We make an effort to understand population dynamics of Thrips tabaci Linde (Thrips) pest on cotton (Gossypium Arboreum) crop using neural networks by analyzing pest surveillance data. The Multi-layer perceptron neural network with back-propagation training algorithm is utilized in the design of the presented intelligent system. The results show that neural network system can be able to give results with a very high degree of accuracy and is best suited to build a prediction system. With the aid of this pest prediction system, the farming communities get more beneficiaries in crop productivity.

show abstract

“…The backpropagation algorithm trains the network for predicting the correct outputs those acquired from experiments and generated ones. The operation of the typical backpropagation network is given as [20]. 1.Transmission of information through the network to the output layer (forward propagation) once the data is presented to the input layer.…”

Section: Neural Network Architecturementioning

confidence: 99%

A Prediction Model for Population Dynamics of Cotton Pest (Thrips tabaci Linde) using Multilayer-Perceptron Neural Network

Patil¹,

Mytri²

2013

IJCA

View full text Add to dashboard Cite

India's agricultural sector faces a series of problems when it comes to increasing crop productivity. Despite the efforts of researchers to discover productive agricultural practices, crop yield has not been the most pleasing, and one global reason stated for this poor crop yield is the insect pests. Predicting in advance the occurrence of peak activities of a given pest could enable the development of a suitable pest control mechanism that would initiate better production. Researchers have attempted to comprehend the pest population dynamics by applying analytical and other techniques on pest surveillance data sets. In this paper, An intelligent system for effectual prediction of pest population dynamics of Thrips Tabaci Linde (Thrips) on cotton (Gossypium Arboreum) crop is presented. The raw data used in the proposed system was obtained from the College of Agriculture, Raichur, India. Initially, the raw (pest surveillance) data is prepared by 1) Data preprocessing 2) Normalization and 3) Data transformation. The feed forward Multi-Layer Perceptron (MLP) Neural Network with backpropagation training algorithm is employed in the design of the intelligent system. The neural network is trained and tested with the data prepared. The experimental results portray the effectiveness of the proposed system in predicting pest population dynamics of Thrips on cotton crop. Moreover, a comparative analysis is performed between the proposed system and two of the existing works. The results showed that the proposed system based on feed forward neural networks was best suited for effective pest prediction.

show abstract

A clinical decision support system using multi-layer perceptron neural network to predict quality of life in diabetes

Cited by 22 publications

References 2 publications

A Study of Psychosocial and Built Environment factors for Diabetes using MLP Neural Network

A Study of Psychosocial and Built Environment factors for Diabetes using MLP Neural Network

An intelligent system for predicting Thrips tabaci Linde pest population dynamics allied to cotton crop

A Prediction Model for Population Dynamics of Cotton Pest (Thrips tabaci Linde) using Multilayer-Perceptron Neural Network

Contact Info

Product

Resources

About