Nazri Mohd Nawi
UNIVERSITI TUN HUSSEIN ONN MALAYSIA (UTHM)

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

Enhancing Knowledge Hyper Surface Method for Casting Diagnosing Nazri Mohd Nawi
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 2, No 1: March 2013
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (832.727 KB)

Abstract

The diagnosis of defective castings has always been a centre of attention in the manufacturing industry. This is mainly because the cause and effect relationship in a casting process is complex and non-linear. Furthermore, a large number of parameters are needed to be coordinated with each other in an optimal way to minimise the occurrence of defective castings. An intelligent diagnosis system is needed to diagnose effectively the causal representation and also justify its diagnosis. A previous method, known as the Knowledge Hyper-surface method which used Lagrange Interpolation polynomials has gained more popularity in learning cause and effect analysis in casting processes. The current method show that the belief value of the occurrence of cause with respect to the change in the belief value in the occurrence of effect can be modeled by linear, quadratic or cubic relationships and the method retained the advantages of neural networks and overcomes their limitations in learning the input-output mapping function in the presence of noisy, limited and sparse data. However, the methodology was unable to model exponential increase/decrease in belief values in cause and effect relationships. This paper proposed an enhancement to the current Knowledge Hyper-surface method by introducing midpoints in the existing shape formulation which further constrains the shape of the Knowledge hyper-surfaces to model an exponential rise in belief values but without exposing the dataset to the limitations of ‘over fitting’. The ability of the proposed method to capture the exponential change in the belief variation of the cause when the belief in the effect is at its minimum is compared to the current method on real casting data.DOI: http://dx.doi.org/10.11591/ij-ai.v2i1.584
A comparative analysis of classification techniques on predicting flood risk Nazri Mohd Nawi; Mokhairi Makhtar; Mohd Zaki Salikon; Zehan Afizah Afip
Indonesian Journal of Electrical Engineering and Computer Science Vol 18, No 3: June 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v18.i3.pp1342-1350

Abstract

Flood is a temporary overflow of a dry area due to overflow of excess water, runoff surface waters or undermining of shoreline. In Malaysia itself in 2014, the country grieved with the catastrophic flood event in Kuala Krai, Kelantan, which caused of human lives, public assets and money lost. Due to uncertainties in flooding event, it is vital for Malaysia to have pre-warning system that assist related agencies in to categorize land areas that face high risk of flood so preventive actions can be planned in place. This paper conducts a comparative analysis of three classifications in classifying the risk of flood, whether high or low. The classification experiment conducts using three variants of Bayesian approaches, which are Bayesian Networks (BN), Naive Bayes (NB), and Tree Augmented Naive Bayes (TAN). The outcome of this research shows that Tree Augmented Naive Bayes (TAN) has the best algorithms as compared to others algorithms in classifying the risk of flood.
Parkinson disease classification: a comparative analysis on classification techniques Nazri Mohd Nawi; Mokhairi Makhtar; Zehan Afizah Afip; Mohd Zaki Salikon
Indonesian Journal of Electrical Engineering and Computer Science Vol 18, No 3: June 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v18.i3.pp1351-1358

Abstract

Parkinson’s disease (PD) among Alzheimer’s and epilepsy are one of the most common neurological disorders which appreciably affect not only live of patients but also their households. According to the current trend of aging social behaviour, it is expected to see a rise of Parkinson’s disease. Even though there is no cure for PD, a proper medication at the early stage can help significantly in alleviating the symptoms. Since, the traditional method for identifying PD is rather invasive, expansive and complicated for self-use, there is a high demand for using classification method on PD detection. This paper compares the performance of Neural Network and decision tree for classifying and discriminating healthy people for people with Parkinson’s disease (PD) by distinguishing dysphonia. The simulation results demonstrate that Neural Network outperformed decision tree by giving accurate results with 87% accuracy as compared to decision tree with only 84% accuracy in determining the classification of healthy and people with Parkinson’s.