Learn More
This paper proposes the integrated motion control method to make a bipedal humanoid walk, jump and run. This method generates dynamically consistent motion patterns in real-time based on the concept of the dynamics filter, which assures that the force and the moment generated by the robot can equilibrate with that caused by the environment. The validity of(More)
PURPOSE To develop a deep convolutional neural network (DCNN)-based computer-aided diagnosis (CAD) system for detecting the masses in digital mammographic images. METHODS A DCNN architecture, which consists of 5 convolutional layers and 3 fully connected layers, is constructed in this study. The DCNN parameters are then trained by the following two(More)
  • 1