Collaborating Authors


Manufacturers bet on bright future for rehab robot market

The Japan Times

OSAKA – Manufacturers are stepping up the development of health care rehabilitation robots because the global market for such equipment is expected to grow rapidly. Companies of all kinds are trying to tap into a medical robot market that is forecast to grow 24.51 percent through 2020, according to market researcher Infiniti Research. Demand for rehabilitation robots could be particularly strong in Japan, given the rapidly graying and shrinking population. The robots are expected to help elderly people regain the use of limbs and avoid becoming bedridden. They also allow patients to train without assistance, a major attraction in a nation with a dwindling working-age population and a mushrooming number of retirees.

A Probabilistic Classification System for Predicting the Cellular Localization Sites of Proteins

AAAI Conferences

Kenta Nakai Institute of Molecular and Cellular Biology Osaka University, 1-3 Yamada-oka, Suita 565, Japan p Abstract We have defined a simple model of classification which combines human provided expert knowledge with probabilistic reasoning. We have developed software to implement this model and have applied it to the problem of classifying proteins into their various cellular localization sites based on their amino acid sequences. Since our system requires no hand tuning to learn training data, we can now evaluate the prediction accuracy of protein localization sites by a more objective cross-validation method than earlier studies using production rule type expert systems. Keywords: Protein Localization, Probabilistic Reasoning, Classification, Yeast, E.coli Introduction The field of computational biology has mainly been characterized by successes in the efficient organization of biological data into databases and the development of algorithms, e.g. This research has been of great utility but it stops short of modeling aspects of biology at the cellular or higher levels.