Search

Many significant research achievements in the past few decades have demonstrated that convolutional neural networks (CNNs) could be capable of steering wheel control which is the basic and essential maneuver of autonomous vehicles. We propose an end-to-end steering controller with CNN-based closed-loop feedback for autonomous vehicles that improves driving performance compared to traditional CNN-based approaches. This paper demonstrates that the proposed neural network, DAVE-2SKY, is able to learn to inference steering wheel angles for the lateral control of self-driving vehicles through initial supervised pre-training and subsequent reinforced closed-loop post-training with images from a camera mounted on the vehicle. We used the PreScan simulator and Caffe deep learning framework for training under diversified circumstances in a software in the loop (SIL) simulation environment. We used DRIVE TM PX2 computer to implement a self-driving car for an experimental validation of the proposed end-to-end controller. The performance of the proposed system has been investigated under simulations and on-road tests as well. This work shows that the CNN-based end-to-end controller performs robust steering control even under partially observable road conditions, which indicates the possibility of fully self-driving vehicles controlled by CNN-based end-to-end steering controllers.

WISDOM is an international initiative to deploy large-scale in-silico docking on a public grid infrastructure in an attempt to find potential drugs against neglected or emerging diseases such as Malaria and Avian Flu. Within the framework of the WISDOM initiative, large-scale deployments of in silico docking have been done on production grid infrastructures, demonstrating the relevance of large scale grids for high throughput virtual screening from scientific and grid deployment perspective. However, from the usability point of view, there still seems to be a lot to be done in order to be able to get the grid-enabled large-scale virtual screening approach handier for non-experts of grid computing. To address this issue, we have developed an intuitive and easy-to-use grid-enabled virtual screening tool called Drugscreener-G (DSG), aiming to help scientists in drug discovery including biologists and biochemists to more easily carryout large-scale deployment of molecular docking on grids without having to know details of grid middleware services and tools. With the help of DSG, scientists can easily have access to the PDB database, download and view the 3D structure of target proteins of their interest, launch and manage millions of in-silico docking simulations on the Grid. To facilitate the analysis of docking results, visualization and molecular modeling tools such as Jmol and Chimera have been integrated into DSG as well. The DSG client tool is now being used and tested by biologists in Chonnam National University, one of long-time partners of the WISDOM collaboration. With the help of tools like DSG, their long-time dream of large-scale virtual screening on their own at any time with any help from grid experts is to be made realized in the near future.

AMI is the totality of systems and networks used to measure, collect, store, analyze, and use energy usage data. The industry and technology surrounding AMI has been evolving at a very fast pace for the past several years. In this paper, we propose new key establishment and security algorithm based on public key cryptography to solve AMI network security problems. We evaluate the performance of the proposed key establishment procedure compared with existing algorithm, and we find that the performance of proposed algorithm.

TETRA (Terrestrial Trunked Radio) is the standard of DTRS(Digital Trunked Radio System) developed by the ETSI(European Telecommunications Standards Institute). Currently, TETRA has been selected as the power IT wireless backbone network in Korea while the traditional distribution automation system has used the wireless network of mobile service provider using CDMA(Code Division Multiple Access) and WCDMA(Wideband CDMA) modems. Therefore, the development of gateway platform is indispensable according to the change to the TETRA network. In this paper, we propose an embedded Linux-based gateway platform for transmitting industrial power IT protocol using TETRA network.

The next generation power IT system will consist of automated transmission and distribution systems that support efficient and reliable supply and delivery of power. The goal is to create a power IT system capable of handling emergency and disaster situations, while also able to accommodate current and future utility business environments, market requirements, and customer needs. In this paper, we propose multi-function TETRA Gateway (MFTG) that can convert various power IT protocols into TETRA protocols to show that the next generation electric power IT system can be constructed in TETRA radio infrastructure. Our MFTG is a TETRA network equipment that converts power IT protocols (for example, transformer load monitoring protocol, RTU (Remote Terminal Unit) protocol for monitoring power transmission steel tower wind direction/wind velocity, DLMS, DNP, and IEC61850 etc...) into TETRA protocols through short data, status messaging and packet data.

The characteristics of pulse compression during the laser pulse amplification using a counter-propagating pump and plasmas have been investigated using a one-dimensional fluid model of stimulated Raman backscattering. The pulse widths of the amplified laser at the front and rear half are examined in terms of the initial amplitudes of the pump and the seed, and the ratio of the electron plasma frequency to the laser frequency. The pulse widths have a common scaling behaviour in time over the considered parameter regime. The scaling exponents of the pulse widths during broadening and compression are all the same as 1.0. The pulse compression scaling shows a reciprocal behaviour to the peak energy growth.