ENHANCED EVALUATION OF RSS FINGERPRINTING BASED INDOOR LOCALIZATION S.SANTHOSH *1, M.PRIYA *2, R.PRIYA *3. Technology, Chennai, Tamil Nadu, India.

Transcription

1 ENHANCED EVALUATION OF RSS FINGERPRINTING BASED INDOOR LOCALIZATION S.SANTHOSH *1, M.PRIYA *2, R.PRIYA *3 *1 Assistant Professor, 23 Student, New Prince Shri Bhavani College of Engineering and Technology, Chennai, Tamil Nadu, India. *1 2 3 Abstract: Knowing the Location and determining the current Location are essential for Indoor Localization techniques. GPS is technology which is often used for getting the current location of the user. It can t be used efficiently while performing indoors because the losses occurred during the signal strength propagation. Since Wi-Fi technology which will probably be used in all Smart Buildings, Indoor localization algorithms have been surveyed and requirements which are essential for obtaining Mobile computing technology have been researched, and a contextbased approach for a Smart Building. Using Wi-Fi technology to measure the Wi-Fi signal strength level which has got mobile computing structure is proposed. Keywords: Indoor Localization, GPS, Wi-Fi Signal Strength, RSS, IPS, Access Point 1. INTRODUCTION Mobile Computing is a technology that allows transmission of data, via a computer without being connected to a fixed physical link. It is human computer interaction by which a computer is expected to be transported during normal usage. Mobile computing involves mobile communication, mobile hardware and mobile software.communication issues include ad-hoc and infrastructure networks as well as communication properties, protocols, data formats and concrete technologies.hardware includes mobile devices or device components. Mobile software deals with the characteristics and requirements of mobile applications as shown in the Figure 1 Journal of Innovation in Science and Engineering Research Page 288

2 Figure 1. Mobile Computing Architecture An Indoor Localization System is a system used to locate the Objects or people inside a building using RSS collected by our Handheld Mobile devices[1].the System includes distance measurement to find the accurate position by using the Access Points.It also uses Global Positioning System to locate the buildings and persons inside it. Indoor Localization System can efficiently detect the location of the object. The Received Signal Strength(RSS) is measured using the AccessPoints(AP s).the information collected from the RSS is called as Fingerprinting. Many Fingerprints can be used to create a Fingerprint Database.The current Location of the user can be determined by comparing the fingerprint measurements with the database. Location determination along with fingerprints is collected with the crowdsourcing paradigm[2]. The LNPL model is used to consider the path loss[3]. It can be used in Normal Rooms,Corridors etc.rss based Fingerprinting improves the efficiency and accuracy[4]. The indoor mapping solutions expands, more solutions will become available for various purposes. Visitors can find one location to another location easily.seamlessly visualized, complex indoor or outdoor scenarios customized Location-Based Services (LBS) for a wide range of users. Each accesspoint(ap) and reference point(rp) contains a number of RSS measurements which are raw[5]. Journal of Innovation in Science and Engineering Research Page 289

3 2. EXISTING WORK Indoor maps for malls are not enabled efficiently in the existing system.users cannot get Wi-Fi Signal Strength range inside the Smart buildings.getting the current user location by GPS.Signal Fluctuations may occur which can change the path of the user.accuracy is impacted by the reflection and absorption of walls. Accuracy depends on the size and type of the environment.it produces accurate location when used in small buildings and its accuracy is decreased when used in a large buildings. Indoor Positioning Systems (IPS) have recently received consideration attention, mainly because GPS is unavailable in indoor spaces and consumes considerable energy. On the other hand, predominant smart phones OS localization subsystems currently rely on server-side localization processes, allowing the service provider to know the location of a user at all times. DISADVANTAGES By tracking, the exact place of the particular object only can be known. The option to add the favorite shops and place is not available which makes the user unaware of the changes in that particular place. Coverage calculations are sensitive to signal. It suffered degraded accuracy in the open-industrial environment. Accuracy of Wi-Fi based fingerprinting algorithm depend on type and size of the environment. 3. PROPOSED WORK This subsection briefly summarizes the performance of proposed indoor positioning system based on Received Signal Strength (RSS) and WLANS.The major performance metrics studied by all the system are position accuracy and which is a form of error measurement. The accuracy of the location information is reported and calculates the distance measurement between the current location and the established location of the WLAN access point level with more accuracy by getting the piece of information is termed as fingerprinting which is stored in the database. The collected fingerprint of indoor map is compared with the fingerprint stored in the database as shown in the Figure 2. In our proposed system, there are many highlights like Indoor maps for malls and other smart buildings can be enabled. Journal of Innovation in Science and Engineering Research Page 290

4 User can get the Wi-Fi signal strength range inside the smart buildings. Figure 2. System Architecture MULTI DIMENSIONAL SCALING ALGORITHM (MDS): MDS algorithm is a technique for visualizing the similarity level of case dataset. It is used to display a particular content in distance matrix. MDS algorithm places each object in an N- dimensional space so that the distance between the objects is preserved. Each object will be assigned coordinates in the N-dimensional space. First we must decide the no of dimensions; more the no of dimensions more the statistical fits. We can use it for one dimensional and two dimensional spaces. It is widely used in positioning systems. MDS is used to create a high dimensional sample space from the information collected from the mobile sensors and motion of the user. It is used to visualize the similarities and non-similarities in the data. The user s current location is found by comparing the high dimensional space and the physical space. Journal of Innovation in Science and Engineering Research Page 291

5 4. PERFORMANCE EVALUATION Figure 3.Comparision of the CDF of positioning error between triangulations and fingerprint based localization. Figure 3. shows the comparability of the CDF of positioning error between triangulations and fingerprint based localization.compared to the existing system our proposed system proposes more accuracy in determining the location of the user in the smart buildings.the accuracy is also based on the signal strength of Wi-Fi.If the signal strength of the Wi-Fi is good then we can more accurately find the position of the user.we obtain more efficiency in this system.it also uses GPS and blueprint so that all the floors,rooms and corridors inside the smart buildings can be easily identified. 5. CONCLUSION This indoor based localization can be used in school campus, Museums, Airports, Stores, Malls, Hospitals,etc. It will be very useful for the persons who are new to that place.they can use this Indoor Localization to find the place where they want to go and find the place where they are.it can be useful for Foreign Visitors to track their desired Restaurant or Hotel Inside a Mall. REFERENCES [1] Z. Yang, Z. Zhou, and Y. Liu, From RSSI to CSI: Indoor localizationvia channel response, ACM Comput. Surv., vol. 46, no. 2,pp. 1 32, Journal of Innovation in Science and Engineering Research Page 292

6 [2] K. Chintalapudi, A. P. Iyer, and V. N. Padmanabhan, Indoorlocalization without the pain, in Proc. 16th Annu. Int. Conf. MobileComput. Netw., 2010, pp [3] C. Oestges, N. Czink, B. Bandemer, P. Castiglione, F. Kaltenberger, and J. Paulraj, Experimental characterization and modeling of outdoor-to-indoor and indoor-to-indoor distributed channels, IEEE Trans. Veh. Technol., vol. 59, no. 5, pp ,Nov [4]T. V. Haute, et al., Comparability of RF-based indoor localization solutions in heterogeneous environments: An experimental study, Int. J. Ad Hoc Ubiquitous Comput., vol. 23, no. 1/2, pp , [5] F. Lemic, A. Behboodi, V. Handziski, and V. Wolisz, Experimental decomposition of the performance of fingerprinting-based localization algorithms, in Proc. Int. Conf. Indoor Positioning Indoor Navigation, 2016, pp Journal of Innovation in Science and Engineering Research Page 293