| Budget Amount *help |
¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2014: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2013: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2012: ¥2,730,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥630,000)
|
|---|
| Outline of Final Research Achievements |
In this research we first evaluated the relation between each radio feature and state and/or position, where radio features are eigenvalue and eigenvector expanding signal subspace by experiments. Based on the evaluation, we proposed state classification techniques using machine learning such as support vector machine. We also proposed a localization technique based on radio features obtained by array sensor. Our localization technique is a kind of fingerprinting technique so that we need training in advance. It is not so practical to test in many positions in advance. Thus, we want a localization technique that can localize positions where test is not done in advance. Our proposed localization technique can localize even positions without training and achieve higher localization accuracy, compared with the conventional radio signal strength (RSS) based localization technique, such as Nuzzer.
|
