Current Issue : October - December Volume : 2016 Issue Number : 4 Articles : 5 Articles
Fingerprint recognition is a mature biometric technique for identification or authentication application.\nIn this work, we describe a method based on the use of neural network to authenticate\npeople who want to accede to an automated fingerprint system for E-learning. The idea is to apply\nback propagation algorithm on a multilayer perceptron during the training stage. One of the advantages\nof this technique is the use of a hidden layer which allows the network to make comparison\nby calculating probabilities on template which are invariant to translation and rotation. Results\ncome both from the NIST special database 4 and a local database, and show that a proposed\nmethod gives good results in some cases....
A typical modern optimization technique is usually either heuristic or meta heuristic. This technique has managed to solve\nsome optimization problems in the research area of science, engineering, and industry. However, implementation strategy of\nmeta heuristic for accuracy improvement on convolution neural networks (CNN), a famous deep learning method, is still rarely\ninvestigated. Deep learning relates to a type of machine learning technique, where its aim is to move closer to the goal of artificial\nintelligence of creating a machine that could successfully perform any intellectual tasks that can be carried out by a human. In this\npaper, we propose the implementation strategy of three popular metaheuristic approaches, that is, simulated annealing, differential\nevolution, and harmony search, to optimize CNN. The performances of these meta heuristic methods in optimizing CNN on\nclassifying MNIST and CIFAR data set were evaluated and compared. Furthermore, the proposed methods are also compared\nwith the original CNN. Although the proposed methods show an increase in the computation time, their accuracy has also been\nimproved (up to 7.14 percent)....
The shunting schedule of electric multiple units depot (SSED) is one of the essential plans for high-speed train maintenance\nactivities. This paper presents a 0-1 programmingmodel to address the problem of determining an optimal SSED through automatic\ncomputing. The objective of the model is to minimize the number of shunting movements and the constraints include track\noccupation conflicts, shunting routes conflicts, time durations ofmaintenance processes, and shunting running time. An enhanced\nparticle swarm optimization (EPSO) algorithm is proposed to solve the optimization problem. Finally, an empirical study from\nShanghai South EMU Depot is carried out to illustrate the model and EPSO algorithm. The optimization results indicate that the\nproposed method is valid for the SSED problem and that the EPSO algorithm outperforms the traditional PSO algorithm on the\naspect of optimality....
A bioinspired locomotion system for a quadruped robot is presented. Locomotion is achieved by a spiking neural network (SNN)\nthat acts as a Central Pattern Generator (CPG) producing different locomotion patterns represented by their raster plots. To\ngenerate these patterns, the SNN is configured with specific parameters (synaptic weights and topologies), which were estimated by\nametaheuristic method based on ChristiansenGrammar Evolution (CGE).Thesystem has been implemented and validated on two\nrobot platforms; firstly, we tested our system on a quadruped robot and, secondly, on a hexapod one. In this last one, we simulated\nthe case where two legs of the hexapod were amputated and its locomotion mechanism has been changed. For the quadruped\nrobot, the control is performed by the spiking neural network implemented on an Arduino board with 35% of resource usage. In\nthe hexapod robot, we used Spartan 6 FPGA board with only 3% of resource usage. Numerical results show the effectiveness of the\nproposed system in both cases....
As themanufacturing tasks becomemore individualized andmore flexible, the machines in smart factory are required to do variable\ntasks collaboratively without reprogramming. This paper for the first time discusses the similarity between smart manufacturing\nsystems and the ubiquitous robotic systems and makes an effort on deploying ubiquitous robotic technology to the smart factory.\nSpecifically, a component based framework is proposed in order to enable the communication and cooperation of the heterogeneous\nrobotic devices. Further, compared to the service robotic domain, the smart manufacturing systems are often in larger size. So a\nhierarchical planning method was implemented to improve the planning efficiency. A test bed of smart factory is developed. It\ndemonstrates that the proposed framework is suitable for industrial domain, and the hierarchical planning method is able to solve\nlarge problems intractable with flat methods....
Loading....