Mobile Station Positioning Using GSM Cellular Phone and Artificial Neural Networks

In this paper, we describe a novelapproach to mobile station positioning using a GSMmobile phone. The approach is based on the use of aninherent feature of the GSM cellular system (themobile phone continuously measures radio signalstrengths from a number of the nearest base stations(antennas)) and on the use of this information to estimatethe phone's location. The current values of the signalstrengths are processed by a trained artificial neuralnetwork executed at the computer attached to themobile phone to estimate the position of the mobilestation in real time. The neural network configurationis obtained by using a genetic algorithm that searchesthe space of specific neural network types anddetermines which one provides the best locationestimation results. Two general methods are explored:the first is based on using a neural network forclassification and the second uses functionapproximation. The experimental results are reportedand discussed.     

Geolocation in mines with an impulse response fingerprinting technique and neural networks

The location of people, mobile terminals and equipment is highly desirable for operational enhancements in the mining industry. In an indoor environment such as a mine, the multipath caused by reflection, diffraction and diffusion on the rough sidewall surfaces, and the non-line of sight (NLOS) due to the blockage of the shortest direct path between transmitter and receiver are the main sources of range measurement errors. Unreliable measurements of location metrics such as received signal strengths (RSS), angles of arrival (AOA) and times of arrival (TOA) or time differences of arrival (TDOA), result in the deterioration of the positioning performance. Hence, alternatives to the traditional parametric geolocation techniques have to be considered. In this paper, we present a novel method for mobile station location using wideband channel measurement results applied to an artificial neural network (ANN). The proposed system, the wide band neural network-locate (WBNN-locate), learns off-line the location 'signatures' from the extracted location-dependent features of the measured channel impulse responses for line of sight (LOS) and non-line of sight (NLOS) situations. It then matches on-line the observation received from a mobile station against the learned set of 'signatures' to accurately locate its position. The location accuracy of the proposed system, applied in an underground mine, has been found to be 2 meters for 90% and 80% of trained and untrained data, respectively. Moreover, the proposed system may also be applicable to any other indoor situation and particularly in confined environments with characteristics similar to those of a mine (e.g. rough sidewalls surface).     

Understanding and predicting the motivators of mobile music acceptance – A multi-stage MRA-artificial neural network approach

The adoption level of digital music is still at its formative stage although the adoption renders advantageous to consumers. Therefore, the study develops a model to predict on the motivation leading to consumer’s intention to adopt mobile music services by extending Perceived Cost (PC), Perceived Credibility (PCr), Social Influence (SI), and Personal Innovativeness (INNO) with Technology Acceptance Model (TAM). 160 Respondents were tested using a multi-stage Multiple Regression Analysis (MRA) and Artificial Neural Network (ANN) approach. A non-linear non-compensatory Multi Layer Perceptron (MLP) ANN with feed-forward back-propagation algorithm and ten cross-validation neural networks was deployed in order to capture the motivators of mobile music adoption. All predictor variables were found to have relevance to the output neuron based on the non-zero synaptic weights connected to the hidden neurons. The RMSE values indicated that the ANN models were able to predict the motivators with very high accuracy. The ANN models have out-performed the MRA models as they are able to capture the non-linear relationships between the predictor and criterion variables. While the study found that TAM is a significant predictor, the insignificance linear relationships of PCr and INNO requires further investigation. The music industry can use the findings from this study beneficially to the development of mobile music adoption.     

基于GPS的红外成像测向交叉定位方法

开展基于GPS的红外成像测向交叉定位研究,引入GPS技术进行测站定位、确定目标测向基准,以地理投影坐标系为定位坐标系,建立双站交叉定位、测站定位、目标测向数学模型;分析定位误差与布站情况、GPS定位精度、测角精度的关系;提出基于SolidWorks的仿真试验方法,验证了本文双站交叉定位数学模型的正确性;设计两组外场验证试验,全面验证了本文定位方法的有效性。试验表明,本文方法对近1km远处目标的定位误差<0.5m,不要求测站相互可见,且便于描述目标偏离测站、其他任意GPS已知点的地理方位角,具有重要应用价值。     

GNSS positioning accuracy improvement based on surface meteorological parameters using artificial neural networks

With the ongoing development of global navigation satellite system (GNSS) technologies, user's dependence on these technologies has drastically risen. Ranging anywhere from industrial applications to agriculture or geodetic applications, the growing demand has stimulated the need for more sophisticated equipment with seamless accuracy. However, the signal received by a GNSS receiver has always faced the risk of contamination by many different sources of error, and this issue decreases the GNSS positioning accuracy. One of the most notable errors is the delay that occurs mainly in the troposphere layer, which mostly relies on the meteorological condition parameters. In this work, an artificial neural network (ANN)‐based mitigation technique in order to eliminate troposphere delay is presented. Our ANN model trained using the surface meteorological parameters, namely, temperature, humidity, wind speed, maximum wind direction, and pressure with the number of satellites achieved by a GNSS receiver. The result showed that ANN model successfully improved the position accuracy level of the GNSS receiver in both horizontal (2D) and three dimensions (3D) at 43.77% and 19.19%, respectively.     

电离层虚高对超视距雷达多站联合定位精度的影响

在天波超视距雷达系统的短基线多站联合定位中，一般假设多站点电离层反射虚高保持一致，为确定这一假设对定位结果的影响，本文进行电离层探测试验，以研究电离层虚高对多站联合定位精度的影响。试验时分别架设两个接收站模拟短基线超视距雷达系统的接收站点，再在较远距离架设目标站点，利用来自目标站点的发射信号模拟目标的返回信号。本文假设参考站点到目标站点链路的电离层反射虚高和大圆距离是已知的，对于同一工作频率，利用参考站点-目标站点链路上的电离层虚高，去解算定位站点-目标站点之间的大圆距离。参考站点和定位站点相距约90 km情况下，结果显示:目标和定位站(道孚-武汉)大圆距离约为1 260 km时，两条链路的虚高均方根误差约为5.82 km，相应的大圆距离的定位均方根误差约为5.02 km，相对误差约为0.34%；当目标和定位站(乐山-武汉)大圆距离约为1 000 km时，误差分别约为5.5 km, 5.69 km和0.46%。试验结果和理论分析表明，可以从缩短接收站点的布局和降低电离层反射虚高两个方面进一步提高目标定位的精度。本文试验结果可为短基线天波超视距雷达的建设提供较为重要的参考价值。     

A Train-Once Approach for Location Estimation Using the Directional Propagation Model

Location estimation that is based on the mobile phone network has drawn considerable attention in the field of wireless communications. Among the different mobile location estimation methods, the one that estimates a mobile station location with reference to a wave propagation model is shown to be effective and is applicable to different kinds of cellular networks, including Global System for Mobile Communications (GSM), cdmaOne, CDMA2000, and the Universal Mobile Telecommunications System. We have designed a train-once approach for location estimations using the directional propagation model (DPM). The DPM is an improved model that is based on the traditional free-space wave propagation model with the directional gain and environmental factors integrated in the estimation. The train-once approach works because we observe that different types of antennas are designed for different types of environments. Thus, a parameter estimation is related to the antenna type and, in turn, related to the environment. In this paper, we report our study of the train-once approach with the DPM for location estimations. We have tested our model with 192 177 sets of real-life data that have been collected from a major mobile phone operator in Hong Kong. Experimental results show that the train-once approach with the DPM is practical and outperforms the existing location estimation algorithms in terms of accuracy, stability among different types of terrains, and success rates.     

接收站位形对甚低频源定位精度的影响

考虑到地球曲率的影响,文中使用基于球面模型的远距离多站时差定位算法来具体研究VLF源定位的精度.针对四接收站下的方型布站和星型布站两类典型布站几何,使用蒙特卡洛随机试验的仿真方法计算了探测区域内接收系统对VLF源定位结果的均方根误差,分析了布站几何、基线长度和主站选择三类因素对定位精度的影响.结果表明:提高基线长度可以...     

小波分析法解决无线定位跟踪问题

无线定位中,信号的非视距传播（NLoS）很大程度上决定了移动台的定位精度,而小波分析理论在信号处理中有较为明显的优点,提出了一种在蜂窝网络中非视距环境下对移动台（MS）的定位及跟踪算法。利用小波变换对信号的分解和重构,实现了对TDOA测量值误差的修正,再利用经典Chan算法对移动台位置进行估计,配合相应的距离门限值对移动台的位置进行跟踪定位。仿真结果表明,该算法能够有效地实现对移动台位置的静态定位和动态跟踪,并明显优于同等环境下经典算法的仿真结果,有效提高了定位精度。     

无源测距定位系统设计中的GDOP分析

几何精度因子(GDOP)是衡量一个定位系统精度的重要标准之一.为分析三维空间中GDOP随几何位置关系的变化,构建了GDOP分析模型.对GDOP的解算算法和典型四基站三维无源定位系统的分析表明,测距精度最终导致的定位精度会随着用户处于不同的相对几何位置而产生明显波动和规律变化.在以球体作为几何参考体的情况下,GDOP在不同“经线”或“纬线”上会出现不同程度的波动或近似为常数；延径向向外GDOP不断增大；基站点处出现GDOP的间断点.这些分析结果可以作为用户选择基站或操作区域的基本判据,并可为无源测距定位系统基准站点的布设提供参考.基站周边应当设定适当的保护距离以保持用户的定位精度；用户应当尽可能在参考几何体内部运动；在系统设计中,应当充分考虑用户的活动区域等限制因素.     

一种基于SO-CNN模型的可见光室内定位优化方法

针对基于机器学习的可见光室内定位方法存在的手工调参、定位精度低等问题,结合蛇优化(Snake Optimization, SO)算法的寻优能力与卷积神经网络(Convolutional Neural Network, CNN)处理复杂非线性问题的能力,提出了一种基于SO-CNN模型的可见光室内定位优化方法。在考虑多径效应影响的情况下,采集每个位置点处的信噪比和对应位置坐标构建指纹数据库,对SO-CNN模型进行训练和测试,以得到最佳定位模型。实验结果表明,在5 m×5 m×3 m的房间中,与未经优化的CNN相比,该方法的平均定位误差降低了35.13%;与反向传播神经网络(Back Propagation Neural Network, BPNN)、多层感知器(Multilayer Perceptron, MLP)、SO-MLP相比,该方法的平均定位误差分别降低了54.75%,48.08%,37.01%。     

Neural network-based path loss model for cellular mobile networks at 800 and 1800 MHz bands

Cellular radio communication systems have become essential for data/voice/video/multimedia applications. The performance of cellular communication radio systems is assessed by considering the design specifications of frequency planning, channel assignment and interference mitigation strategies among others. Frequency planning is the most important component to improve capacity or quality of cellular radio systems. Large-scale path loss values between the base station and mobile stations are the key regulating factors that limit the performance of cellular systems, especially in urban/vegetation region. There is a necessity to develop a suitable path loss prediction model for predicting path loss values based on received signal strength measurements. In this paper, an ANN-based path loss model was used for macro cell measurement data obtained in the Vijayawada urban region, India. The Multi-Layer Perceptron (MLP) neural network model was considered. The prediction results indicate that the ANN model outperformed the Auto Regressive Moving Average (ARMA) and COST-231-WImodels. The outcome of this research work will be immensely useful for improving coverage and ensuring better frequency planning of cellular radio systems.     

Improved TOA‐Based Localization Method with BS Selection Scheme for Wireless Sensor Networks

The purpose of a localization system is to estimate the coordinates of the geographic location of a mobile device. The accuracy of wireless localization is influenced by non‐line‐of‐sight (NLOS) errors in wireless sensor networks. In this paper, we present an improved time of arrival (TOA)–based localization method for wireless sensor networks. TOA‐based localization estimates the geographic location of a mobile device using the distances between a mobile station (MS) and three or more base stations (BSs). However, each of the NLOS errors along a distance measured from an MS (device) to a BS (device) is different because of dissimilar obstacles in the direct signal path between the two devices. To accurately estimate the geographic location of a mobile device in TOA‐based localization, we propose an optimized localization method with a BS selection scheme that selects three measured distances that contain a relatively small number of NLOS errors, in this paper. Performance evaluations are presented, and the experimental results are validated through comparisons of various localization methods with the proposed method.     

A Real-Time Intelligent Wireless Mobile Station Location Estimator with Application to TETRA Network

Mobile location estimation has received considerable interest over the past few years due to its great potential in different applications such as logistics, patrol, and fleet management. Many mobile location estimation techniques had been proposed to improve the accuracy of location estimation. Location estimation based on artificial intelligence techniques is a recent alternative approach. In this paper, adaptive neuro-fuzzy inference system (ANFIS) is used as a robust location estimator to locate the mobile station (MS) using the MS geo-fencing area data within 9 km from a serving base station. Extensive evaluations and comparisons have been performed, and a set of statistical parameters has been obtained. From the comparison of the proposed ANFIS estimator with the neural-network-based estimators, it is found that ANFIS estimator is faster and more robust. Its average computation time (ACT) is 0.076 sec. While the ACT for multilayer perceptron (MLP) and radial-based function (RBF) neural networks is 0.88 and 1.7, respectively. Whereas on comparing ANFIS with other techniques, it is found that in ANFIS estimator, 67 percent of the estimated location errors do not exceed 149 m, while these for the statistical, multiple linear regression, and geometric are 170, 280, and 2,346 m, respectively. Thus, the results clearly reveal that the proposed ANFIS estimator outperforms all other techniques.     

Design of broadband array elements based on neural network and genetic algorithm

Coupled artificial neural network (ANN) and genetic algorithm (GA) models are developed for the design of broadband tapered slot antenna array elements. The ANN is employed to establish the complicated relationships between the key array performance indicator, i.e. active reflection coefficient, and its element parameters. The trained ANN models are combined with the GA to optimise the element parameters for a given operating frequency band without using time-consuming EM simulators. Optimisation results show the developed ANN-GA model can retain the accuracy obtainable from EM simulators and exhibit high computational efficiency.     

多站无源时差定位精度分析

针对在多站无源时差定位系统中影响目标定位精度的因素,分析了时差测量误差和站址误差对目标定位精度的影响。影响时差测量精度的因素有接收机热噪声、多普勒效应、站间同步误差、本地时钟误差和大气等因素。通过分析各个因素对目标定位精度的影响程度,在特定布站方式下,仿真计算得到在固定时差测量误差和站址误差下可能达到的目标定位精度,并根据主要误差来源提出相应的提高定位精度的措施。     

Software‐only TDOA/RTT positioning for 3G WCDMA wireless network

A hybrid location finding technique based on time difference of arrival (TDOA) with round‐trip time (RTT) measurements is proposed for a wideband code division multiple access (WCDMA) network. In this technique, a mobile station measures timing from at least three base stations using user equipment receive—transmit (UE Rx—Tx) time difference and at least three base stations measure timing from the mobile station using RTT. The timing measurements of mobile and base stations are then combined to solve for both the location of the mobile and the synchronization offset between base stations. A software‐only geolocation system based on the above mobile/base stations timing measurements is implemented in Matlab platform and the performance of the system is investigated using large‐scale propagation models. Copyright © 2007 John Wiley & Sons, Ltd.     

高精度定位系统中传输系统研究

高精度定位系统将满足厘米级的行业应用,未来市场规模巨大.高精度定位系统由卫星系统、基准站、高精定位平台及用户端等组成,而用于传送基准站和高精度定位平台间的传输网络是系统运行的基础,构建安全、灵活、低成本、易实现的传输网络是保证高精度定位系统的关键.本文简单介绍了高精度定位系统的架构,测算了带宽需求,并建议以分组传送网+IP承载网方式构建高精度定位系统传输网络.     

Improving the fault tolerance of GSM networks

A PCS network constantly tracks the locations of the mobile stations so that incoming calls can be delivered to the target mobile stations. In general, a two-level database system is used to store location information of the mobile stations. When the location databases fail, incoming calls may be lost. This article describes the standard GSM database failure restoration procedure which reduces the number of lost calls. Then we propose an efficient visitor location register (VLR) identification algorithm for the home location register (HLR) failure recovery procedure, which utilizes mobile station movement information to speed up the recovery procedure     

多发多收探测雷达定位精度分析

多发多收是提高雷达系统定位精度的重要手段之一, 为分析不同形式多发多收定位精度, 采用二维定位几何精度稀释分析方法, 分别针对两发两收、两发四收和三发三收三种探测方式进行了仿真分析.结果表明:两发四收探测系统定位精度比两发两收系统整体上提高, 在基线近区提高比较明显; 三发三收探测系统克服了两发两收探测系统在基线上定位盲区的缺点, 但与两发四收探测系统相比, 除基线附近外,在三站围成的定位区域内定位性能并没有明显提高.仿真结果为多发多收探测系统选取、布站提供了理论参考, 具有一定的工程应用价值.