Browse
You are looking at 1 - 10 of 81,578 items for
Yun Wei, Ying Yu, Lifeng Xu, Wei Huang, Jianhua Guo, Ying Wan and Jinde Cao
Abstract
Vehicle emission calculation is critical for evaluating motor vehicle related environmental protection policies. Currently, many studies calculate vehicle emissions from integrating the microscopic traffic simulation model and the vehicle emission model. However, conventionally vehicle emission models are presented as a stand-alone software, requiring a laborious processing of the simulated second-by-second vehicle activity data. This is inefficient, in particular, when multiple runs of vehicle emission calculations are needed. Therefore, an integrated vehicle emission computation system is proposed around a microscopic traffic simulation model. In doing so, the relational database technique is used to store the simulated traffic activity data, and these data are used in emission computation through a built-in emission computation module developed based on the IVE model. In order to ensure the validity of the simulated vehicle activity data, the simulation model is calibrated using the genetic algorithm. The proposed system was implemented for a central urban region of Nanjing city. Hourly vehicle emissions of three types of vehicles were computed using the proposed system for the afternoon peak period, and the results were compared with those computed directly from the IVE software with a trivial difference in the results from the proposed system and the IVE software, indicating the validity of the proposed system. In addition, it was found for the study region that passenger cars are critical for controlling CO, buses are critical for controlling CO and VOC, and trucks are critical for controlling NOx and CO2. Future work is to test the proposed system in more traffic management and control strategies, and more vehicle emission models are to be incorporated in the system.
Yuchen Hou and Lawrence B. Holder
Abstract
Deep learning has been successful in various domains including image recognition, speech recognition and natural language processing. However, the research on its application in graph mining is still in an early stage. Here we present Model R, a neural network model created to provide a deep learning approach to the link weight prediction problem. This model uses a node embedding technique that extracts node embeddings (knowledge of nodes) from the known links’ weights (relations between nodes) and uses this knowledge to predict the unknown links’ weights. We demonstrate the power of Model R through experiments and compare it with the stochastic block model and its derivatives. Model R shows that deep learning can be successfully applied to link weight prediction and it outperforms stochastic block model and its derivatives by up to 73% in terms of prediction accuracy. We analyze the node embeddings to confirm that closeness in embedding space correlates with stronger relationships as measured by the link weight. We anticipate this new approach will provide effective solutions to more graph mining tasks.
Igor Aizenberg, Antonio Luchetta, Stefano Manetti and Maria Cristina Piccirilli
Abstract
A procedure for the identification of lumped models of distributed parameter electromagnetic systems is presented in this paper. A Frequency Response Analysis (FRA) of the device to be modeled is performed, executing repeated measurements or intensive simulations. The method can be used to extract the values of the components. The fundamental brick of this architecture is a multi-valued neuron (MVN), used in a multilayer neural network (MLMVN); the neuron is modified in order to use arbitrary complex-valued inputs, which represent the frequency response of the device. It is shown that this modification requires just a slight change in the MLMVN learning algorithm. The method is tested over three completely different examples to clearly explain its generality.
Keiko Ono, Yoshiko Hanada, Masahito Kumano and Masahiro Kimura
Abstract
In evolutionary computation approaches such as genetic programming (GP), preventing premature convergence to local minima is known to improve performance. As with other evolutionary computation methods, it can be difficult to construct an effective search bias in GP that avoids local minima. In particular, it is difficult to determine which features are the most suitable for the search bias, because GP solutions are expressed in terms of trees and have multiple features. A common approach intended to local minima is known as the Island Model. This model generates multiple populations to encourage a global search and enhance genetic diversity. To improve the Island Model in the framework of GP, we propose a novel technique using a migration strategy based on textit f requent trees and a local search, where the frequent trees refer to subtrees that appear multiple times among the individuals in the island. The proposed method evaluates each island by measuring its activation level in terms of the fitness value and how many types of frequent trees have been created. Several individuals are then migrated from an island with a high activation level to an island with a low activation level, and vice versa. The proposed method also combines strong partial solutions given by a local search. Using six kinds of benchmark problems widely adopted in the literature, we demonstrate that the incorporation of frequent tree information into a migration strategy and local search effectively improves performance. The proposed method is shown to significantly outperform both a typical Island Model GP and the aged layered population structure method.
Gustavo Botelho de Souza, Daniel Felipe da Silva Santos, Rafael Gonçalves Pires, Aparecido Nilceu Marana and João Paulo Papa
Abstract
Biometric systems have been widely considered as a synonym of security. However, in recent years, malicious people are violating them by presenting forged traits, such as gelatin fingers, to fool their capture sensors (spoofing attacks). To detect such frauds, methods based on traditional image descriptors have been developed, aiming liveness detection from the input data. However, due to their handcrafted approaches, most of them present low accuracy rates in challenging scenarios. In this work, we propose a novel method for fingerprint spoofing detection using the Deep Boltzmann Machines (DBM) for extraction of high-level features from the images. Such deep features are very discriminative, thus making complicated the task of forgery by attackers. Experiments show that the proposed method outperforms other state-of-the-art techniques, presenting high accuracy regarding attack detection.
