Three-dimensional medical image recognition of cancer of the liver by a revised radial basis function (RBF) neural network algorithm

In this study, we propose a revised radial basis function (RBF) neural network algorithm and apply this algorithm to computer-aided diagnosis (CAD) of the liver. First, the revised RBF neural network algorithm is applied to recognition of the liver regions, and the recognition results are compared with those obtained using the conventional RBF neural network and the conventional multilayered neural network trained using the back-propagation algorithm. It is shown that the revised RBF neural network is accurate, and is a useful method because the parameters are automatically determined. Then, the revised RBF neural network is applied to CAD of the liver cancer called hepatocellular carcinoma (HCC).     

Development of an epileptic seizure prediction algorithm using R–R intervals with self-attentive autoencoder

Epilepsy is a neurological disorder that may affect the autonomic nervous system (ANS) from 15 to 20 min before seizure onset, and disturbances of ANS affect R–R intervals (RRI) on an electrocardiogram (ECG). This study aims to develop a machine learning algorithm for predicting focal epileptic seizures by monitoring R–R interval (RRI) data in real time. The developed algorithm adopts a self-attentive autoencoder (SA-AE), which is a neural network for time-series data. The results of applying the developed seizure prediction algorithm to clinical data demonstrated that it functioned well in most patients; however, false positives (FPs) occurred in specific participants. In a future work, we will investigate the causes of FPs and optimize the developing seizure prediction algorithm to further improve performance using newly added clinical data.

     

Building a speech recognition system with privacy identification information based on Google Voice for social robots

The Journal of Supercomputing - Currently, many smart speakers, even social robots, appear on the market to help people's lives become more convenient. Usually, people use smart speakers to...     

Two-stage subspace identification for softsensor design and disturbance estimation

Softsensors or virtual sensors are key technologies in industry because important variables such as product quality are not always measured on-line. In the present work, two-stage subspace identification (SSID) is proposed to develop highly accurate softsensors that can take into account the influence of unmeasured disturbances on estimated key variables explicitly. The proposed two-stage SSID method can estimate unmeasured disturbances without the assumptions that the conventional Kalman filtering technique must make. Therefore, it can outperform the Kalman filtering technique when innovations are not Gaussian white noises or the characteristics of disturbances do not stay constant with time. The superiority of the proposed method over the conventional methods is demonstrated through numerical examples and application to an industrial ethylene fractionator.     

Fabrication of sub-micron structures for MEMS using deep X-ray lithography

Fabrication techniques of microstructures with high resolution and high aspect ratio are necessary for practical microelectromechanical systems (MEMS) that have high performance and integration. In order to fabricate microstructures with sub-micron resolution and high aspect ratio, deep X-ray lithography has been investigated using the compact synchrotron radiation (SR) light source called “AURORA”. An X-ray mask for sub-micron deep X-ray lithography, which is composed of 1 μm thick Au as absorbers, 2 μm thick SiC as a membrane and 625 μm thick Si as a frame, was designed. In preliminary experiments, the following results were achieved: EB resist microstructures with an aspect ratio of 22 corresponding with 0.07 μm width and 1.3 μm height were formed; a 10 μm thick PMMA resist containing no warp was formed by direct polymerization, enabling more precise gap control.     

Cooperation of categorical and behavioral learning in a practical solution to the abstraction problem

Real robots should be able to adapt autonomously to various environments in order to go on executing their tasks without breaking down. They achieve this by learning how to abstract only useful information from a huge amount of information in the environment while executing their tasks. This paper proposes a new architecture which performs categorical learning and behavioral learning in parallel with task execution. We call the architectureSituation Transition Network System (STNS). In categorical learning, it makes a flexible state representation and modifies it according to the results of behaviors. Behavioral learning is reinforcement learning on the state representation. Simulation results have shown that this architecture is able to learn efficiently and adapt to unexpected changes of the environment autonomously. Atsushi Ueno, Ph.D.: He is a research associate in the Artificial Intelligence Laboratory at the Graduate School of Information Science at the Nara Institute of Science and Technology (NAIST). He received the B.E., the M.E., and the Ph.D. degrees in aeronautics and astronautics from the University of Tokyo in 1991, 1993, and 1997 respectively. His research interest is robot learning and autonomous systems. He is a member of Japan Association for Artificial Intelligence (JSAI). Hideaki Takeda, Ph.D.: He is an associate professor in the Artificial Intelligence Laboratory at the Graduate School of Information Science at the Nara Institute of Science and Technology (NAIST). He received his Ph.D. in precision machinery engineering from the University of Tokyo in 1991. He has conducted research on a theory of intelligent computer-aided design systems, in particular experimental study and logical formalization of engineering design. He is also interested in multiagent architectures and ontologies for knowledge base systems.