Forecasting of PM_2.5 concentration is a global concern. Evidence has shown that the ambient PM_2.5 concentrations are harmful to human health, climate change, plant species mortality, etc. PM_2.5 concentrations are caused by natural and anthropogenic activities, and it is challenging to predict them due to many uncertain factors. Current research has focused on developing a new model while overlooking the fact that every single model for PM_2.5 prediction has its own strengths and weaknesses. This paper proposes an ensemble framework which combines four diverse learning models for PM_2.5 forecasting in Puli, Taiwan. It explores the synergy between parametric and non-parametric learning, and short-term and long-term learning. The feature set covers periodic, meteorological, and autoregression variables which are selected by a spiral validation process. The experimental dataset, spanning from 1 January 2008 to 31 December 2019, from Puli Township in central Taiwan, is used in this study. The experimental results show the proposed multi-model framework can synergize the advantages of the embedded models and obtain an improved forecasting result. Further, the benefit obtained by blending short-term learning with long-term learning is validated, in surpassing the performance obtained by using just single type of learning. Our multi-model framework compares favorably with deep-learning models on Puli dataset. It also shows high adaptivity, such that our multi-model framework is comparable to the leading methods for PM_2.5 forecasting in Delhi, India.

The aim of this study is to propose an application framework of HBIM for historic buildings in Taiwan with a focus on defining the components of historic buildings, component attributes, and the relationship between the components and restoration data. The information is then imported into a database and presented in a visualized model. Issues explored include definition of components and the process of generating component library for historic buildings with an emphasis on traditional woodwork. The case study is on Huangxi Academy. To generate the component library, regulations must be established to define structural components of historic buildings and the component types must be categorized. The structure of Huangxi Academy is divided into 5 areas with individual elements and the components are classified into one of the three categories, family component with parameters, family component without parameters, and custom component. In addition, for create basic visual effects for each component with data pertaining to renovation, the LOD 300 model is suggested for this project.

Using digital technology for cultural heritage documentation is a global trend in the 21 st century. Many important techniques are currently under development, including 3D digital imaging, reverse engineering, GIS (Geographic Information Systems) etc. However, no system for overall management or data integration is yet available. Therefore, we urgently need such a system to efficiently manage and interpret data for the preservation of cultural heritages. This paper presents a digitizing process developed in Taiwan by the authors. To govern and manage cultural property, three phases of property conservation, registration, restoration and management, has been set up along a timeline. In accordance with the laws of cultural property, a structural system has been built for project management, including data classification and data interpretation with self-documenting characteristics. Through repository information and metadata, a system catalogue (also called data dictionary) (Figure 1) was created. The primary objective of the study is to create an integrated technology for an efficient management of databases. Several benefits could be obtained from this structural standard: (1) cultural heritage management documentation can be centralized to minimize the possibility of data re-entry resulting inconsistency, and also to facilitate simultaneous updating of data; (2) since multiple data can be simultaneously retrieved and saved in real time, the incidence of errors can be reduced; (3) this system could be easily tailored to meet the administrative requirements for the standardization of documentation exchanged between cultural properties institutions and various county and city governments.