Optimizing artificial neural network-based indoor positioning system using genetic algorithm

Abstract

The Global Positioning System (GPS) is expected to play an integral role in the development of digital earth; however, the GPS cannot provide positioning information in regions where a majority of the population spends their time, that is, in urban and indoor environments. Hence, alternate positioning systems that work in indoor and urban environments should be developed to achieve the vision of digital earth. Wi-Fi-based positioning systems (WPS) stand out because of the near-ubiquitous presence of the associated infrastructure and signals in indoor environments. The WPS-based fingerprinting is the most widely adopted technique for position determination, but its accuracy is lower than that of techniques such as time of arrival and angle of arrival. Improving the accuracy is still a challenging task because of the complex nature of the propagation of Wi-Fi signals. Here, a novel server-based, genetic-algorithm-optimized, cascading artificial neural network-based positioning model is presented. The model is tested in 2D and 3D indoor environments under varying conditions. The model is thoroughly investigated on a real Wi-Fi network, and its accuracy is found to be better than that of other well-known techniques. A mean accuracy of 1.9 m is achieved with 87% of the distance error within the range of 0–3 m.     

A block-based selection method for road network generalization

Abstract

When road symbols are shown in a size proportionate to the reduced scale, several problems of legibility may arise concerning the urban blocks. By the method proposed in this paper, in order to overcome these problems, urban block areas are enlarged through amalgamation and the intervening roads in the amalgams are eliminated. This method includes two new approaches for computation of threshold used in determination of important roads based on the connectivity measure, and for definition of minimum block space and area requirements based on graphic limits. A block life cycle was designed for amalgamation of blocks. For the amalgamation process, a new algorithm was developed. The experimental testing indicates that important roads and the roads surrounding the urban area have been preserved. A simpler and more legible road network has been acquired. This method can be described as a more holistic approach as the buildings are taken into account. The problems arising in the experimental testing indicate that the cartographic selection/elimination process is not sufficient by itself for road network generalization, which can be assumed as one of the integral parts of Digital Earth. As well as the selection/elimination, processes such as displacement and caricaturizing are also needed.     

Enrichment of topographic road database for the purpose of routing and navigation

With growing demand on multi-purpose or multi-modal navigation, the route calculation needs to traverse semantically enriched road networks for different transportation modes. Currently, operational route planning algorithms reveal rather limited performances or their potential for comprehensive applications are constrained by the unavailable or insufficient interoperation among the underlying geo-data that are separately maintained in different spatial databases. To overcome this limitation, a novel approach has been proposed to integrate the routing-relevant information from different data sources, which involves three processes: (1) automatic matching to identify the corresponding road objects between different datasets; (2) interaction to refine the automatic matching result; and (3) transferring the routing-relevant information from one data-set to another. In process (1), the Delimited Stroke Oriented algorithm is employed to achieve the automatic data matching between different datasets, which has revealed a high matching rate and certainty. However uncertain matching problems occur in areas where topological conditions are too complicated or inconsistent. The remaining unmatched or wrongly matched objects are treated in process (2), with the help of a series of interaction tools. On the basis of refined matching results after the interaction, process (3) is dedicated to automatic integration of the routing-relevant information from different data sources.     

Potentiality of feed-forward neural networks for classifying dark formations to oil spills and look-alikes

Radar backscatter values from oil spills are very similar to backscatter values from very calm sea areas and other ocean phenomena. Several studies aiming at oil spill detection have been conducted. Most of these studies rely on the detection of dark areas, which have high Bayesian probability of being oil spills. The drawback of these methods is a complex process, mainly because non-linearly separable datasets are introduced in statistically based decisions. The use of neural networks (NNs) in remote sensing has increased significantly, as NNs can simultaneously handle non-linear data of a multidimensional input space. In this article, we investigate the ability of two commonly used feed-forward NN models: multilayer perceptron (MLP) and radial basis function (RBF) networks, to classify dark formations in oil spills and look-alike phenomena. The appropriate training algorithm, type and architecture of the optimum network are subjects of research. Inputs to the networks are the original synthetic aperture radar image and other images derived from it. MLP networks are recognized as more suitable for oil spill detection.     

A rule-based parameter aided with object-based classification approach for extraction of building and roads from WorldView-2 images

Roads and buildings constitute a significant proportion of urban areas. Considerable amount of research has been done on the road and building extraction from remotely sensed imagery. However, a few of them have been concentrating on using only spectral information. This study presents a comparison between three object-based models for urban features’ classification, specifically roads and buildings, from WorldView-2 satellite imagery. The three applied algorithms are support vector machines (SVMs), nearest neighbour (NN) and proposed rule-based system. The results indicated that the proposed rules in this study, despite the spectral complexity of land cover types, performed a satisfactory output with an overall accuracy of 92.92%. The advantages offered by the proposed rules were not provided by other two applied algorithms and it revealed the highest accuracy compared to SVM and NN. The overall accuracy for SVM was 76.76%, which is almost similar to the result achieved by NN (77.3%).     

Model generalization of two different drainage patterns by self-organizing maps

In this study, we develop a new method using self-organizing maps (SOMs) for the selection of hydrographic model generalization. The most suitable attributes of the stream objects are used as input variables to the SOM. The attributes were weighted using Pearson’s chi-square independence test. We used the Radical Law to determine how many features should be selected, and an incremental approach was developed to determine which clusters should be selected from the SOM. Two drainage patterns (dendritic and modified basic) were obtained from the National Hydrography Datasets of United States Geological Survey at 1:24,000-scale (high resolution) and used in order to derive stream networks at 1:100,000-scale (medium resolution). The 1:100,000-scale stream networks, derived in accordance with the proposed approach, are similar to those in the original maps in both quantity and visual aspects. Stream density and pattern were maintained in each subunit, and continuous and semantically correct networks were obtained.     

东莞市城市现状路网调查与建库

阐述了东莞市城市现状路网调查与建库项目的背景及项目内容,剖析了项目采用的技术路线和工作步骤,最后对项目成果的精度的分析结果表明,成果精度能够满足城乡规划的使用需要。     

Artificial neural networks and nonlinear regression techniques to assess the influence of slake durability cycles on the prediction of uniaxial compressive strength and modulus of elasticity for carbonate rocks

Understanding rock material characterizations and solving relevant problems are quite difficult tasks because of their complex behavior, which sometimes cannot be identified without intelligent, numerical, and analytical approaches. Because of that, some prediction techniques, like artificial neural networks (ANN) and nonlinear regression techniques, can be utilized to solve those problems. The purpose of this study is to examine the effects of the cycling integer of slake durability index test on intact rock behavior and estimate some rock properties, such as uniaxial compressive strength (UCS) and modulus of elasticity (E) from known rock index parameters using ANN and various regression techniques. Further, new performance index (PI) and degree of consistency (Cd) are introduced to examine the accuracy of generated models. For these purposes, intact rock dataset is established by performing rock tests including uniaxial compressive strength, modulus of elasticity, Schmidt hammer, effective porosity, dry unit weight, p‐wave velocity, and slake durability index tests on selected carbonate rocks. Afterward, the models are developed using ANN and nonlinear regression techniques. The concluding remark given is that four‐cycle slake durability index (I_d4) provides more accurate results to evaluate material characterization of carbonate rocks, and it is one of the reliable input variables to estimate UCS and E of carbonate rocks; introduced performance indices, both PI and Cd, may be accepted as good indicators to assess the accuracy of the complex models, and further, the ANN models have more prediction capability than the regression techniques to estimate relevant rock properties. Copyright © 2011 John Wiley & Sons, Ltd.     

Efficient collection of training data for sub-pixel land cover classification using neural networks

Artificial neural networks (ANNs) are a popular class of techniques for performing soft classifications of satellite images. They have successfully been applied for estimating crop areas through sub-pixel classification of medium to low resolution images. Before a network can be used for classification and estimation, however, it has to be trained. The collection of the reference area fractions needed to train an ANN is often both time-consuming and expensive. This study focuses on strategies for decreasing the efforts needed to collect the necessary reference data, without compromising the accuracy of the resulting area estimates. Two aspects were studied: the spatial sampling scheme (i) and the possibility for reusing trained networks in multiple consecutive seasons (ii). Belgium was chosen as the study area because of the vast amount of reference data available. Time series of monthly NDVI composites for both SPOT-VGT and MODIS were used as the network inputs. The results showed that accurate regional crop area estimation (R² > 80%) is possible using only 1% of the entire area for network training, provided that the training samples used are representative for the land use variability present in the study area. Limiting the training samples to a specific subset of the population, either geographically or thematically, significantly decreased the accuracy of the estimates. The results also indicate that the use of ANNs trained with data from one season to estimate area fractions in another season is not to be recommended. The interannual variability observed in the endmembers’ spectral signatures underlines the importance of using up-to-date training samples. It can thus be concluded that the representativeness of the training samples, both regarding the spatial and the temporal aspects, is an important issue in crop area estimation using ANNs that should not easily be ignored.     

膨胀系数可调的Balloon Snake方法在道路轮廓提取中的应用

以条带检测的结果初始化道路轮廓,利用balloon snake方法提取道路轮廓.在初始道路轮廓存在缺失的情况下,balloon snake的膨胀作用可以找回丢失的道路片段,提高道路提取的完整性.基于图像梯度和轮廓曲率调节膨胀系数,降低道路提取效果对膨胀系数的敏感,并加快道路轮廓的扩张,减少迭代次数.通过多幅道路图像的试...