Search

With the increasing demand for location based services, indoor positioning technology has become one of the most attractive research fields. Because the large indoor scenarios exist a large number of Wi-Fi signal, the researchers make it possible to use the existing infrastructure for locating in indoor environment and greatly reduce the cost in recent years. However, this positioning scheme also exists serious problem, the change of the indoor environment can affect the results of positioning, it will lead to the instability and low accuracy of positioning system, positioning method based on Wi-Fi has not been widely used at present. This paper proposes an indoor positioning solution based on the deep learning networks with the fusion of multi-source data, we design the deep learning networks model and introduce Restricted Boltzmann Machine to initialize networks and use grid search to optimize the parameters of networks. When data set is built, we consider the problem of whether the APs are moved or closed, this paper also considers the geomagnetic data, iBeacon in indoor environment, thus the dimensions of the input data are increased, and the stability of the indoor positioning system is improved, the method of cross validation fully trained network is utilized in this paper, at the same time, a data smoothing processing based on Kalman Filter (KF) is introduced. The result of the experiment shows that, average positioning error of scheme based on DNN and Kalman filter is 0.29m, the maximum position error is 1.59m, the position error is 96.33% within 1m, position accuracy is 100% within 2m, basically meets the positioning requirement.

Satellite navigation signals are blocked by the buildings and can’t provide the positioning service for the indoor users. In 2016, Chinese government supports the research and development of the BeiDou/GPS pseudolites for indoor and outdoor seamless positioning in the national key research and development program, in order to reduce application costs, the combination technology of pseudolites and PDR is used for indoor positioning. Firstly, the seamless positioning system architecture, the signal format and navigation message, indoor positioning principle of Beidou/GPS pseudolites are introduced in this paper, the positioning results of array pseudolites begin to converge and the horizontal positioning error is about 1 meter, After the positioning results become very stable, the positioning error of 0.5 meters. Secondly, the pseudolites and PDR combination localization algorithm is studied, the average positioning error of PDR is 5.5 m and 10 m, while the average positioning error of PL\_PDR is 2 meters and 2.3 meters. It can be seen that the combined technology of pseudolites and PDR can achieve high-precision indoor positioning under a long time and long-distance conditions.

Due to the influence of indoor signal multipath effect and human disturbance, the indoor positioning technology of WiFi fingerprint based on deep learning is poor stability. The large sample and accurate data in the room is very difficult to collect for weights training of deep learning, so it is difficult to be widely used. Firstly, the innovative algorithm with multi-sensor fingerprint and deep learning for indoor position (DL-IMPS) is puts forward, and used the statistical model and the ray tracing method to construct a large sample data for weights training, the experiment is proved that the model data of WiFi-RSSI is a subset of the actual measurement data. Secondly, 10.9m×7.4m indoor location test environment is set up in the room, through 9700 groups of modeling data and 1300 groups of measurement data to train DBN's weights, it get more optimal weights matrix and speed up the convergence rate. Finally, The performance of WKNN and DL-IMPS is compared under four different paths, The results prove that the average error of DL-IMPS is 0.52 m, the probability of error less than 1 m is 92.3%, but the average error of WKNN is 1.39 m, the probability of error of less than 1m is 45%, Location accuracy and stability of DL-IMPS are superior to WKNN. The other experiment is the comparison between one-sensor indoor location and DL-IMPS, Locating error probability of DL-IMPS is 1%, and the convergence speed is fast, that of WiFi-only is 24%, iBeacon-only is 25%, Geomagnetic-only is 15%, DL-IMPS have better positioning accuracy and robustness.

There is a large amount of energy waste in coking flue gas desulfurization and denitrification integrated device during the revising process of coking, in order to solve this problem, aiming at the unique reversing process of coking, the reasons for the change of NOx concentration in this process are deeply analyzed; the disturbance of inlet and outlet NOx concentration during the reversing process is modeled by a proposed data driven identification method, the verification is carried out based on the actual data of two 55-hole and 6-meter top charging coke ovens, according to the statistical data, the relationship model of inlet and outlet NOx concentration loss is obtained; we designed a feedforward control system and the feed forward control rate of O 3 is calculated based on the outlet disturbance model, the power consumption cost savings is obtained through simulation, which indicates the necessity of the work in this paper.

Financial institutions, esp. retail banking, have given evidence for the existence of a priority pattern of CRM system in our study. It is concluded that how to manage the relationship of customers and corporations is the core in commercial banks. The paper is to explore CRM of banks to find out if general patterns are applicable. As such, the study shows the comparison of CRM performance with different adoption of Internet-bank technology and methodology. The discussion aims at providing data mining approach and process based for bank CRM analysis. Data mining application model given in Internet-bank or ATM system can be the general goal of the CRM project from a business point and a technical point of view and further add benefit to banks' CRM.