Using Deep Learning Approaches to Predict Indoor Thermal Comfort and Outdoor Rainfall Probability by Embedded Weather Box

• Main Authors: YEH, SHING-YU, 葉星虞
• Other Authors: CHANG, KUEI-CHUNG
• Format: Others
• Language: en_US
• Published: 2017
• Online Access: http://ndltd.ncl.edu.tw/handle/zfyezh

碩士 === 逢甲大學 === 資訊工程學系 === 105 === With new technological advancements, the mobile phones and 3C products have been popularized in the life. Internet of Things (IoT) is also equipped in our living space so that the internet can be anywhere and make our society more digitized. Face the pressure of work and the irritable things in life, people hope that they can have a more comfortable living space and so resulting in the applications for smart home appear quickly. For highly developed countries which faced aging societies, the health management of the elderly is one of the most important problems. The body of elderly is not only low resistance but also poor temperature regulation and sensitivity. Slight temperature changes may cause colds, fever and other diseases. Therefore, how to use a simple application to give people a thermal comfortable living space will be an important issue. Raining can not only affect thermal comfort but also cause inconvenience to people, e.g., shopping or hanging the clothes. If we can provide more accurate prediction of raining, people will be able to facilitate their planning schedules. This thesis aims to use the Arduino weather box to collect the weather data from the user’s living space, and then these data can be analyzed via Support Vector Machine (SVM) and Neural Network (NN) to predict thermal comfort and probability of rainfall. We compare the prediction accuracy of temperature and rainfall probability using the two machine learning approaches. We use accuracy and correlation coefficient to determine which one is the best. From the experimental results, we can find using NN can get better results of temperature prediction, and using SVM can get better results to predict rainfall probability.