This research focused on testing with maize, economical crop grown in Phetchabun province, Thailand, by installing a total of 20 sets of internet of things (IoT) devices which consist of soil moisture sensors and temperature and humidity sensors (DHT11). Data science tools such as rapidminer studio was used for data cleansing, data imputation, clustering, and prediction. Next, these data would undergo data cleansing in order to group them to obtain optimization clustering to identify the optimum condition and amount of water required to grow the maize through k-mean technique. From the analysis, the optimization result showed 3 classes and these data were further analyzed through prediction to identify precision. By comparing several algorithms including artificial neural network (ANN), decision tree, naïve bayes, and deep learning, it was found that deep learning algorithm can provide the most accurate result at 99.6% with root mean square error (RMSE)=0.0039. The algorithm obtained was used to write function to control the automated watering system to make sure that the temperature and humidity for growing maize is at appropriate condition. By using the improved watering system, it improved the efficacy of watering system which saves more water by 13.89%

Big data technology (BDT) is being actively adopted by world-leading organizations due to its expected benefits. However, most of the organizations in Thailand are still in the decision or planning stage to adopt BDT. Many challenges exist in encouraging the BDT diffusion in businesses. Thus, this study develops a research model that investigates the determinants of BDT adoption in the Thai context based on the technology-organization-environment (TOE) framework and diffusion of innovation (DOI) theory. Data were collected through an online questionnaire. Three hundred IT employees in different organizations in Thailand were used as a sample group. Structural equation modeling (SEM) was conducted to test the hypotheses. The result indicated that the research model was fitted with the empirical data with the statistics: Normed Chi-Square=1.651, GFI=0.895, AFGI=0.863, NFI=0.930, TLI=0.964, CFI=0.971, SRMR=0.0392, and RMSEA=0.046. The research model could, at 52%, explain decision to adopt BDT. Relative advantage, top management support, competitive pressure, and trading partner pressure show significant positive relation with BDT adoption, while security negatively influences BDT adoption.

No abstract

The objective of this paper consists of two sections. The first is to evaluate the framework of adaptive e-learning recommendation system based on Multiple Intelligence. The second of this paper was to synthesize on an adaptive e-learning recommendation System based on Multiple Intelligence and learner profile. This paper propose conceptual model of adaptive e-learning guidance system based on Multiple Intelligence. The concept framework divided into five modules. (1) We introduce rule base module. (2) We explain recommendation module for students. (3) We present the LMS module. (4) We present the adaptive module. (5) We describe the content module which is based on Multiple Intelligence. The process of evaluation consists of three steps. The first step define group of experts for evaluate framework. The second step create questionnaire for appropriate evaluation. The last step present the synthetic framework to experts for appropriate evaluation. The result from experts are very appropriate with the average score equal to 4.34/5 (S.D.=0.52). 

No abstract