Deep Learning Neural Network (DLNN), is a new branch of machine learning with the ability for complex feature representatio Although it was mainly suited for image feature (since it was inspired by object recognition method of mammalian visual system), if any type of feature can be translate into image, other type of data could be fit for using DLNN. In this paper, we prove that Mel Frequency Cepstrum Coefficient (MFCC) feature generates from audio signal of infant cry could be used as input feature for the Convolution Neural Network (CNN J Fundam Appl Sci. 2017, 9(3S), 768-778 769 The result shows CNN can be used to classify between normal and pathological (asphyxiated) cry with 94.3% accuracy in training set and 92.8% accuracy in testing set.

This paper focuses on the application of Fuzzy Analytic Hierarchy Process (FAHP) approach to solve multi-criteria decision making (MCDM) problems. MCDM is a process which involves a decision maker or a group of decision makers to evaluate and to choose the best alternatives based on the criteria decided by the decision maker(s). A real-life empirical example about supplier selection is used to implement the FAHP method. The objectives of the study are: (1) to implement FAHP approach with different linguistic scales to solve MCDM problems; and (2) to compare the relative weights of each alternative with respect to the criterion that was computed using different linguistic scales. There are three sets of scales denoted as S1, S2 and S3 used in this paper. Four criteria which are delivery, price, service and payment terms and three alternatives which are Supplier A, Supplier B and Supplier C has been considered in this study. The first objective is achieved since FAHP can be used to solve the MCDM problems. Meanwhile, for second objective, the Coefficient of Variations (CV) has been used to do the comparison. The findings revealed that scale S2 is the most preferable linguistic scale for this case study.

No abstract

No abstract