Juryon Paik^*

Intelligent Automation & Soft Computing, Vol.26, No.1, pp. 193-204, 2020, DOI:10.31209/2019.100000140

Abstract It seems to be sure that the IoT is one of promising potential topics today. Sensors are the one that lead the current IoT revolution. The advances of sensor-rich environments produce the massive volume of raw data that is enlarging faster than the rate at which it is being handled. JSON is a lightweight data-interchange format and preferred for IoT applications. Before JSON, XML was de factor standard format for interchanging data. The common point is that their structure scheme is the tree. Tree structure provides data exchangeability and heterogeneity, which encourages user-flexibilities. Therefore, JSON sensor format is an easy… More >

Juan Li

Intelligent Automation & Soft Computing, Vol.25, No.1, pp. 35-48, 2019, DOI:10.31209/2018.100000003

Abstract K-Nearest Neighbor algorithm (KNN) is a simple and mature classification method. However there are susceptible factors influencing the classification performance, such as k value determination, the overlarge search space, unbalanced and multi-class patterns, etc. To deal with the above problems, a new classification algorithm that absorbs tree structure, tree pruning and adaptive k value method was proposed. The proposed algorithm can overcome the shortcoming of KNN, improve the performance of multi-class and unbalanced classification, reduce the scale of dataset maintaining the comparable classification accuracy. The simulations are conducted and the proposed algorithm is compared with several existing algorithms. The results… More >

Kemal Akyol^{1, *}

CMES-Computer Modeling in Engineering & Sciences, Vol.122, No.2, pp. 619-632, 2020, DOI:10.32604/cmes.2020.07632

Abstract Parkinson’s disease is a serious disease that causes death. Recently, a new dataset has been introduced on this disease. The aim of this study is to improve the predictive performance of the model designed for Parkinson’s disease diagnosis. By and large, original DNN models were designed by using specific or random number of neurons and layers. This study analyzed the effects of parameters, i.e., neuron number and activation function on the model performance based on growing and pruning approach. In other words, this study addressed the optimum hidden layer and neuron numbers and ideal activation and optimization functions in order… More >