Vol.2 No.1 2009

15/88

Research paper : Predictive modeling of everyday behavior from large-scale data (Y. Motomura)−12−Synthesiology - English edition Vol.2 No.1 (2009) (i) Description of “non-deterministic approach”.(ii) Description of the concrete examples.(iii) Description of the need of a meaningful large scale data for realization of the examples.(iv) Description of the proposal of “Research as a service” as the methodology of the study to obtain a large scale data.(v) Description of the essentiality of cooperation of some stakeholders for the “Research as a service”.Answer (Yoichi Motomura)Thank you for your suggestions. I have revised the composition based on proposal 1.3 Additional description of specific examplesQuestion and comment (Hideyuki Nakashima)“As this information service spreads and multiple users utilize the system, the history of selection content accumulates ever-larger amounts of statistical data. Improvements in the Bayesian network model resulting from that data will increase the appropriateness and inference precision of the model, create a self-supporting feedback loop, and allow horizontal development of other services to be realized”, this part is the most important in the presented paper. Please describe more concretely about the spiral - what happened actually. I appreciate that you carried out the verified test of the proposed system to over 1000 people, however, you cannot say that the system is practical just by this. For example, it is usual to use the questioner dataset which is over 1000 samples in social science. In IT field, construction and evaluation of pre-production system is not enough to say that you actually used the system - To provide the actual service in the real world” is the significant step.Answer (Yoichi Motomura)I have added the description with respect to the examples.4 Description of the reusable model Question and comment (Masaaki Mochimaru)The figure which shows the concrete image of “reusable model” corresponds to “general knowledge model” shown in comment 1. The interest as Synthesiology is in that the model can be horizontally developed into other applications (services). On the other hand, “the study is done through the service circulation in the real world. Additionally, the reusable model is generated”. This concept’s description maybe excess information for readers, and readability is not good. So, I suggest that the author describes the concept in chapter 8 with a figure.Answer (Yoichi Motomura)I have revised chapter 2 and chapter 8.

※このページを正しく表示するにはFlashPlayer9以上が必要です