AbstractThere is an increasing need to determine whether inputs are out-of-distribution (OOD) for safely deploying machine learning models in the open world scenario. Typical neural classifiers based on closed assumption, where training data and test drawn i.i.d. from same distribution, as a result, give over-confident predictions even faced with OOD inputs. For tackling this problem, previous ...

Nowadays, one of the main problems encountered in minimally invasive surgery and telesurgery is the detection of arteries in tissue. In this study, for the first time, tactile detection of an artery in tissue and distinguishing it from the tumor has been modeled by finite element method. In this modeling, three 2D models of tissue have been created: tissue, tissue including a tumor, and tissue ...

Conventionally, hand-crafted features are used to train machine learning algorithms, however choosing useful features is not a trivial task as they are very much data-dependent. Given raw image intensities as inputs, supervised neural networks (NNs) essentially learn useful features by adjusting the weights of its nodes using the back-propagation algorithm. In this paper we investigate the perf...

Integration of distributed generations (DGs) in power grids is expected to play an essential role in the infrastructure and market of electrical power systems. Microgrids are small energy systems, capable of balancing captive supply and requesting resources to retain stable service within a specific boundary. Microgrids can operate in grid-connected or islanding modes. Effective islanding detec...