Learn More
In conventional setpoint control problem of robots, the desired position is specified as a point. However, it is interesting to observe from most human reaching movements that the desired targets are regions rather than points. In fact, when the desired region is specified arbitrarily small, it reduces to a point. In this paper, we propose a new control(More)
In conventional setpoint control problems of robot, the desired position is specified as a point. However, in some applications, the desired target is a region instead of a point. In this paper, we propose a new control concept called region reaching control for robot manipulators. In this new control concept, the desired objective can be specified as a(More)
In the past, many compensation-based solutions have been proposed to solve the maintenance query anomalies due to concurrent updates of data sources in data warehouse environments. Generally, they are required to send the extra queries to the data sources for compensating concurrency updates, which apparently increases the round-trip between the data(More)
Recently researchers have proposed using deep learning-based systems for malware detection. Unfortunately, all deep learning classification systems are vulnerable to adversarial attacks where miscreants can avoid detection by the classification algorithm with very few perturbations of the input data. Previous work has studied adversarial attacks against(More)
  • 1