We present a new representation and recognition method for human activities. An activity is considered to be composed of action threads, each thread being executed by a single act...
The composition of the example set has a major impact on the quality of neural learning. The popular approach is focused on extensive preprocessing to bridge the representation ga...
We present a structured output prediction approach for classifying potential anti-cancer drugs. Our QSAR model takes as input a description of a molecule and predicts the activity...
Abstract--Sensor network ubiquitous environments may generate a lot of data including heterogeneous `raw' sensor data, low-level feature and/or trend data and higher-level con...
Brian J. d'Auriol, Le Xuan Hung, Sungyoung Lee, Yo...
Labeling nodes in a network is an important problem that has seen a growing interest. A number of methods that exploit both local and relational information have been developed fo...