Research Guidance

72021

田中　章司郎

24.00単位

学年指定なし

2022年度前期、2022年度後期

Application of statistics with computer technology exposes patterns and associations of elements in economy and environment. Step-by-step techniques are presented in this course, and the data-driven methodology is to be mastered by students on their specific topics of dissertation respectively.

Students must publish several academic papers prior to finalize their dissertation. The papers of which are expected being reviewed.

Based on the understanding of the course "Special Studies on Environment and Resource Informatics" in parallel, the actual programming skills are to be mastered:
(1) Basic statistics and multivariate correlations,
(2) Least-square fits,
(3) Maximum likelihood estimations and probability functions,
(4) Parameter estimations,
(5) Goodness of fit,
(6) Residual analysis,
(7) Quasi-real time data disposal and computer memory handling.

Optional items of classification depending on the theme of dissertations are:
(8) Bayesian discriminant analysis ,
(9) Back-propagation method of artificial neural networks,
(10) Deep learning,
(11) Supervised vector machine.

We also provide practical instructions on research ethics
(comprehensive research ethics education including the responsibility of the author, the concept of conflict of interest, confidentiality, etc.).

"Special Studies on Environment and Resource Informatics"

Students will be required to look into the themes through internet and/or in library and be prepared for in-class discussion of the scheduled topic.

References will be presented to students occasionally in class.　

G.P. Patil and C.R. Rao (Eds.). Handbook of Statistics XII: Environmental Statistics. Amsterdam: North Holland.

No regular exam.

Grades will be evaluated by: 1) participation in interactive discussions (10%); 2) presentations (20%); 3) submitted papers to academic journals/conferences (70%).

Programming skills such as R, Matlab, SQL, SAS, and/or C are required.