earticle

영어

Location estimation (LE) is important in Ubiquitous Computing Environments (UCE). For positioning application, Global Positioning System (GPS) and Received Signal Strength (RSS) from Access Pointer (AP) using LE is increasingly popular choice especially after pervasive adoption of IEEE 802.11 Wireless Sensor Networks (WSN). Fundamental requirement of such LE is to estimate location from RSS at a particular location. Multi-Path Fading Effects (MPFE) make RSS to fluctuate in unpredictable manner, introducing uncertainty in LE. Moreover, in practical situations, RSS values RF Signal (RFS) from AP are not available at some locations all the time making the problem more difficult. To deal with this problem, machine learning techniques have been applied so that the carried along devices can learn and make decision where they are in the building, especially. Recent machine learning techniques remain many unsolved problem such as high cost of computation, high complexity of model structures and scalability. In this paper, we will introduce a few methods which give high accuracy and overcome other methods’ disadvantages, such as Support Vector Machine (SVM), Push Pull Estimation (PPE), and Modular Multi-Layer Perceptron (MMLP) with Neural Networks (NN) using RFS from AP.