Artificial Intelligence

1208 Submissions

[6] viXra:1208.0235 [pdf] submitted on 2012-08-30 09:31:38

The Navigation Mobile Robot Systems Using Bayesian Approach Through the Virtual Projection Method

Authors: Luige Vladareanu, Gabriela Tont, Victor Vladareanu, Florentin Smarandache, Lucian Capitanu
Comments: 6 Pages.

The paper presents the navigation mobile walking robot systems for movement in non-stationary and non-structured environments, using a Bayesian approach of Simultaneous Localization and Mapping (SLAM) for avoiding obstacles and dynamical stability control for motion on rough terrain. By processing inertial information of force, torque, tilting and wireless sensor networks (WSN) an intelligent high level algorithm is implementing using the virtual projection method. The control system architecture for the dynamic robot walking is presented in correlation with a stochastic model of assessing system probability of unidirectional or bidirectional transition states, applying the non-homogeneous/non-stationary Markov chains. The rationality and validity of the proposed model are demonstrated via an example of quantitative assessment of states probabilities of an autonomous robot. The results show that the proposed new navigation strategy of the mobile robot using Bayesian approach walking robot control systems for going around obstacles has increased the robot’s mobility and stability in workspace.
Category: Artificial Intelligence

[5] viXra:1208.0110 [pdf] submitted on 2012-08-19 00:10:25

Fabric Inspection System using Artificial Neural Networks

Authors: P. Banumathi, G. M. Nasira
Comments: 8 Pages.

Fabric inspection system is important to maintain the quality of fabric. Fabric inspection is carried out manually with human visual inspection for a long time. The work of inspectors is very tedious and consumes time and cost.To reduce the wastage of cost and time, automatic fabric inspection is required. This paper proposes an approach to recognize fabric defects in textile industry for minimizing production cost and time. The Fabric inspection system first acquires high quality vibration free images of the fabric. Then the acquired images are subjected to defect segmentation algorithm. The output of the processed image is used as an input to the Artificial Neural Network (ANN) which uses back propagation algorithm to calculate the weighted factors and generates the desired classification of defects as an output.
Category: Artificial Intelligence

[4] viXra:1208.0109 [pdf] submitted on 2012-08-19 00:11:50

Experience on re-Engineering Applying with Software Product Line

Authors: Waraporn Jirapanthong
Comments: 10 Pages.

In this paper, we present our experience based on a reengineering project. The software project is to re-engineer the original system of a company to answer the new requirements and changed business functions. Reengineering is a process that involves not only the software system, but also underlying business model. Particularly, the new business model is designed along with new technologies to support the new system. This paper presents our experience that applies with software product line approach to develop the new system supporting original business functions and new ones.
Category: Artificial Intelligence

[3] viXra:1208.0108 [pdf] submitted on 2012-08-19 00:16:35

Tea Insect Pests Classification Based on Artificial Neural Networks

Authors: R. K. Samanta, Indrajit Ghosh
Comments: 13 Pages.

Tea is one of the major health drinks of our society. It is a perennial crop in India and other countries. One of the production barriers of tea is insect pests. This paper presents an automatic diagnosis system for detecting tea insect pests based on artificial neural networks. We apply correlation-based feature selection (CFS) and incremental back propagation network (IBPLN). This is applied on a new database created by the authors based on the records of tea gardens of North Bengal Districts of India. We compare classification results with reduction of dimension and without reduction of dimension. The correct classification rate of the proposed system is 100% in both the cases.
Category: Artificial Intelligence

[2] viXra:1208.0063 [pdf] submitted on 2012-08-15 10:51:00

On the Travelling Salesman Algorithm: An Application

Authors: David Grace, Alessandro Waldron, Tahir Ahmad
Comments: 7 Pages.

The aim of this paper is to set up a simulation model of the production process of an aircraft company in order to obtain a tool for process analysis and decision support. To achieve this object has been used ProModel as simulation software. The advantages of all tools used in a correct and efficient internal movement, the different layouts and the possible usable materials handling system.
Category: Artificial Intelligence

[1] viXra:1208.0049 [pdf] submitted on 2012-08-12 06:17:32

种飞机图像目标多特征信息融合识别方法

Authors: Xin-De Li, Wei-Dong Yang, Jean Dezert
Comments: 10 Pages.

种基于概率神经网络(Probabilistic neural networks, PNN) 和DSmT 推理(Dezert-Smarandache theory) 的飞机图像目标多特征融合识别算法. 针对提取的多个图像特征量, 利用数据融合的思想对来自图像目标各个特征量提供的 信息进行融合处理. 首先, 对图像进行二值化预处理, 并提取Hu 矩、归一化转动惯量、仿射不变矩、轮廓离散化参数和奇异 值特征5 个特征量; 其次, 针对Dezert-Smarandache Theory 理论中信度赋值构造困难的问题, 利用PNN 网络, 构造目标识别率矩阵, 通过目标识 别率矩阵对证据源进行信度赋值; 然后, 用DSmT 组合规则在决策级层进行融合, 从而完成对飞机目标的识别; 最后, 在目标 图像小畸变情形下, 将本文提出的图像多特征信息融合方法和单一特征方法进行了对比测试实验, 结果表明本文方法在同等 条件下正确识别率得到了很大提高, 同时达到实时性要求, 而且具有有效拒判能力和目标图像尺寸不敏感性. 即使在大畸变情 况下, 识别率也能达到89.3 %.
Category: Artificial Intelligence