SlideShare a Scribd company logo
1 of 8
Download to read offline
http://www.ierek.com/press
Print ISSN: 2357-0849
International Journal on: Proceedings of Science and Technolgy
pg. 1
Performance Analysis of Enhanced Delta Sampling Algorithm for
BLE Indoor Localization
Mohd Faiz Bin Mat Daud1
, Idawaty Ahmad 1
1
Faculty of Computer Science and Information Technology,
University Putra Malaysia,
Selangor, Malaysia
David Chieng2
, Alvin Ting2
, SehChun Ng2
2
Wireless Innovation,
Mimos Berhad,Technology Park Malaysia,
Kuala Lumpur, Malaysia
Keywords
RSSI; BLE; Smoothing
Algorithm; Delta Sampling;
Indoor Localization
Abstract
Localization technologies are becoming increasingly important in support of Smart
Building applications such as in-building navigation, asset and visitor or staff
tracking applications. These Smart Building applications in turn improve user
experience, operation efficiency, security and safety of building occupants. In case
of active localization or position tracking technologies, Bluetooth Low Energy (BLE)
has gained popularity due to its accuracy and lower entry cost. BLE indoor
localization technology typically utilizes the Receive Signal Strength Indicator
(RSSI) as a basis for wireless positioning algorithms such as fingerprinting or
trilateration to compute its location. However, the accuracy of location computation
is often impacted by unstable RSSI reading especially inside the buildings. To
investigate this problem, we first evaluate the Delta Sampling algorithm proposed by
Huh et. al. (2016) on its capability to stabilize the RSSI reading using an actual
testbed. We then analyze its strength and weaknesses and propose an enhanced
algorithm. The results show that the original Delta Sampling Algorithm is capable of
stabilizing the RSSI readings but it posses some drawbacks. Further results show that
our proposed enhanced algorithm is able to mitigate some of these problems.
1. Introduction
Localization technologies are becoming increasingly important in support of Smart Building applications such as in-
building navigation, asset and visitor or staff tracking applications. These applications in turn improve user experience,
operation efficiency, security and safety of building occupants. In case of active localization or position tracking,
Bluetooth 4.0 or Bluetooth Low Energy (BLE) technology has gained popularity due to its accuracy and lower entry
cost. BLE indoor localization technology typically uses Receive Signal Strength Indicator (RSSI) as a basis for
wireless positioning algorithms such as fingerprinting or trilateration to compute its location. However, the accuracy
of this system is often impacted by unstable RSSI values at the receiver’s end due to well-known challenges such as
RF interference, multipath fading, shadowing, etc, which impact the accuracy of location estimation. As shown by
many studies, the further the receiver is away from the transmitter, the more unstable it becomes. Hence, some forms
of preprocessing is required such as applying time-series filters or smoothing algorithms to stabilize the signal before
it is can be used by localization algorithm.
The work by Huh et al. (2016) introduces a Delta Sampling algorithm which removes some of the flier points or
“noises” in the raw RSSI reading. It is believed that the algorithm can be further improved by addressing the undecided
Mohd Faiz et al. / Proceedings of Science and Technolgy
pg. 2
range of sample size and also identifying the number of invalid or false data. This algorithm can be combined with
other smoothing algorithms to further improve the result. Figure 1 shows the application of the algorithm used in
indoor localization which includes its usage in Wi-Fi and Cellular systems.
Figure 1 Flow chart for problem area
This paper proposes several improvements over the original Delta Sampling algorithm (Huh et al., 2016). A number
of additional features are proposed to counter the weakness of the Delta Sampling. Since highly fluctuating RSSI will
result in inaccurate location estimation, this study therefore only focuses on solving this problem.
2. Related work
The underlying technologies for indoor localization ranges from Wi-Fi, BLE, visible light, sound/audio, magnetic,
cellular system to mobile cameras (Dmitry, 2015). These technologies can either be implemented independently or in
combination of two or more technologies. For example, a smart phone can fuse the info from WI-FI, BLE and its
built-in sensors (Accelerometer, Magnetometer, Stepmeter) in order to achieve a better localization experience.
However in practice, Wi-Fi and BLE-based systems are more popular due to their lower entry cost and widely
accessibility. In the case of Wi-Fi, there is almost no need to build the infrastructure as Wi-Fi is available virtually
everywhere. The common techniques used to compute the position are triangulation, trilateration and fingerprinting.
Except for triangulation, most of these localization algorithms use RSSI as the base parameter for positioning
computation, thus an error in RSSI measurement will severely impact the accuracy. Unfortunately in practise, RSSI
reading of BLE is very unstable as proven in Neburka et al.(2016), Faragher et al. (2014) and Georgia et al. (2014).
As shown in Georgia (2014) and Zhou et al. (2017), to get a stable RSSI value, smoothing and/or Kalman filters are
often applied to the raw RSSI readings before the data can be used for localization.
In this paper, with aim to further stabilize the received RSSI values, the Delta Sampling algorithm proposed in Huh
et al. (2016) is implemented using an actual testbed and its strength and weaknesses are analyzed. The original is later
enhanced to address some of the weaknesses found.
3. Methodology
This experimental study consists of data collection and data analysis phases as shown in Figure 2 by adopting the
methodology similar to Huh et al. (2016). During data collection phase, the raw data was gathered and stored while
data analysis phase, the proposed Delta Sampling algorithm was executed and analyzed. The data collected phase was
done using an android application. In the data analysis phase, the proposed algorithm was implemented and analyzed
using a Python script.
Mohd Faiz et al. / Proceedings of Science and Technolgy
pg. 3
Figure 2 Experiment design
3.1. Data collection phase
In order to perform this task, we developed an Android application with BLE receiver which offered the wireless
scanner functionality. An integrated database within the app was also developed so that the scanned BLE data could
be stored. The report generator functionality was also implemented in order to convert the data into the simple form
which is easier to be analyzed. The filter algorithms were also implemented for this experiment.
A BLE beaconing hardware was used as the transmitter according to iBeacon configuration. During the experiment,
RSSI samples were collected every 100ms while moving the distance of the receiver (smartphone) from the transmitter
(beacon) from 1m to 3m. The RSSI samples were collected at each distance for 70 seconds. The data obtained from
the experiment (using the Android app) were raw RSSI which is subsequently exported to CSV format so that it can
be easily processed.
3.2. Data analysis phase
The data (RSSI samples) collected in CSV format needs to be imported into a computer so that data processing and
analysis could be performed via a Python script. The script needs to use the raw RSSI data as input. After executing
the script, the results were output in CSV form to enable graph plotting as well as computation of statistical data such
as minimum, maximum and standard deviation. The results gather were than compared with the results obtained from
Huh et al. (2016).
3.3. Experiment environment and setup
Figure 3 shows on how the data collection phase was setup. The beacon was preconfigured configured with iBeacon
standard. The configuration of this experiment is shown in Table 1 which is similar to those used in Huh et al. (2016).
Figure 3 Experiment setup for data collection phase
Mohd Faiz et al. / Proceedings of Science and Technolgy
pg. 4
Table 1. Experiment configuration.
3.4. Delta sampling algorithm
Figure 4 shows the detail mechanism in Delta Sampling Algorithm implemented in this experiment. As stated in Huh
et al. (2016), this algorithm is good on its own or can be used in combination with other algorithms. They have also
presented the result of combination with average filter. However, they the recommended values for Range and
Threshold in the said algorithm are not addressed. The subsequent experiments aim to look into this.
Mohd Faiz et al. / Proceedings of Science and Technolgy
pg. 5
Figure 4 Delta Sampling algorithm. Huh et al. (2016)
From the result shown in Figure 5, it can be seen that the overall trends are comparable to the benchmark paper (Huh
et al., 2016). However, the raw RSSI in Huh et al. (2016) is found to be much more unstable as compared to this
experiment as shown by its high standard deviation. The differences are likely owed to device and environment
heterogeneity.
Figure 5 Delta sampling algorithm. Huh et al. (2016)
From Figure 6, it is clearly shown that the Delta sampling result is much more stable than the raw data. In this
experiment, Delta sampling algorithm proven itself to be effective to solve the problem of RSSI fluctuation by
detecting the flier points and remove them from the result.
Figure 6 Raw vs delta sample
This paper further analyzes the effect of Threshold and Range parameters in Delta Sampling algorithm. As shown in
in Figure 4, the Threshold parameter is the main deciding factor in the detection of flier points while Range controls
the data sets that are to be included in the calculation. In order to further understand the impacts of Threshold and
Range parameters, further experiments were performed as shown in Figure 7 and Figure 8.
The result in Figure 7 is obtained by using different Threshold values. When a low Threshold value is used, almost all
of the Raw Data values are being considered as flier points or invalid data. As the Threshold value increases on the
other hand, the graph will become closer to its original raw data which mean it is become less sensitive in outlier
detection.
Figure 7 Comparing threshold value
Mohd Faiz et al. / Proceedings of Science and Technolgy
pg. 6
Meanwhile, further analysis on Range value as in Figure 8 reveals that smaller range means only a few past data is
taken into consideration in order to find the trend which means it only considers very recent data trend. This is quite
useful option to we only want to consider the latest data.
Figure 8 Comparing range value
3.5. Enhanced delta sampling algorithm
The original Delta Sampling algorithm is not only good in detecting sudden change in data but can also be easily
combined with other algorithms without much difficulty as stated in Huh et al. (2016). However, the weaknesses of
Delta Sampling algorithm, especially in terms of identification of suitable Range and Threshold values in real-time
must be addressed in order for it to be useful for BLE localization.
This section proposes that the Range value must be in real-time application in order to be useful. Since the beacons
are normally set at the beaconing rate or interval between 500ms to 1s only, therefore the data is much lesser compared
to this experiment where the beaconing rate is at 100ms. Moreover, data that are older than 3s are normally unwanted
as in real-time application as the user might have already moved more than 5m after 3s. The proposed solution uses
aging or decay method in finding the right Range value. In short, tagging for time is added when the Raw data is
collected by receiver. Figure 9 depicts the Enhanced Delta Sampling algorithm.
For the Threshold, the best value is equal to 1.0 or below. This is because the lower the value of mean, the more
sensitive it is to the outlier. In order to enable this, the Delta Sampling algorithm needs to be modified so that it is able
to reset itself. This is provided if it detects more than or equal to 3 flier points continuously. Figure 10 shows the result
of the enhanced algorithm with lower Threshold value and self-resetting function. The result shows that further
improvement can be attained with the enhancements. In order to get a smoother result, this algorithm can be combined
with other filtering or smoothing algorithms such as Kalman or Gaussian filter. Figure 11 shows the result of combined
enhanced Delta Sampling with Moving Average (MA) filter. It is shown that the RSSI values can be stabilized
significantly.
4. Conclusion and future work
Through this experiment, it can be concluded that the Delta Sampling algorithm can stabilize the raw RSSI by
removing the flier points in the samples. However, the results are very much depending on the choice of Threshold
and Range values. To address this uncertainty, an enhancement in the algorithm is proposed. The results show that
some further improvements can be achieved especially when combined with additional filter algorithm such as
Moving Average.
Mohd Faiz et al. / Proceedings of Science and Technolgy
pg. 7
Figure 9 Enhanced Delta Sampling algorithm
Figure 10 Raw vs Enhanced Delta Sampling algorithm
Mohd Faiz et al. / Proceedings of Science and Technolgy
pg. 8
Figure 11 Raw vs enhanced delta sampling + moving average
5. Acknowledgement
The author would like to acknowledge the support from MIMOS Wireless Innovation Lab and University Putra
Malaysia. This paper is also sponsored by Fundamental Research Grant Scheme (FRGS), University Putra Malaysia
(UPM). Project code: 08-01-15-1722FR.
6. References
Chai S, An R, Du Z. An indoor positioning algorithm using bluetooth low energy RSSI. International Conference on
Advanced Material Science and Environmental Engineering (AMSEE 2016).
Cho K, Park W, Hong M, Park G, Cho W, Seo J, Han K. Analysis of latency performance of Bluetooth Low Energy
(BLE) networks. Sensors 2015;15(1):59-78.
Dmitry N. On indoor positioning. Int J Open Information Tech ISSN: 2307-8162 2015;3(3).
Dong Q, Dargie W. Evaluation of the reliability of RSSI for indoor localization. International Conference on Wireless
Communications in Underground and Confined Areas 2012:1-6.
Faragher, Ramsey, Harle, Robert. An analysis of the accuracy of bluetooth low energy for indoor positioning
applications. Proceedings of the 27th International Technical Meeting of the Satellite Division of the Institute of
Navigation (ION GNSS+’14) 2014; 201-210.
Georgia I, Carlos M, Michel D. Improving distance estimation in object localisation with bluetooth low energy.
SENSORCOMM 2014, 8th International Conference on Sensor Technologies and Applications 2014;45-49.
Grzechca DE, Pelczar P, Chruszczyk L. Analysis of object location accuracy for iBeacon technology based on the
RSSI path loss model and fingerprint map. Int J Electronics Telecommunications 2016;62(4):371-378.
Huh JH, Bu YH, Seo KR. Bluetooth-tracing RSSI sampling method as basic technology of indoor localization for
smart homes. Int J Smart Home 2016;10(10):9-22.
Kim DY, Kim SH, Choi DS, Jin SH, Accurate indoor proximity zone detection based on time window and frequency
with bluetooth low energy. Procedia Computer Science 2015;56(1):88-95.
Kriz P, Maly F, Kozel T. Improving indoor localization using bluetooth low energy beacons. Mobile Information
Systems 2016:1-11.
Lee JG, Kim BK, Jang SB, Yeon SH, Ko YW. Accuracy enhancement of RSSI-based distance estimation by applying
gaussian filter. Indian J Science Technology 2016;9(20):1-5.
Ma Z, Poslad S, Bigham J, Zhang X, Men L. A BLE RSSI ranking based indoor positioning system for generic
smartphones. Wireless Telecommunications Symposium 2017.
Neburka J, Tlamsa Z, Benes V, Polak L, Kaller O, Bolecek L. Sebesta J, Kratochvil T. Study of the performance of
RSSI based bluetooth smart indoor positioning. 26th
International Conference Radioelektronika
(RADIOELEKTRONIKA) 2016.
Sung Y. RSSI-based distance estimation framework using a Kalman filter for sustainable indoor computing
environments. Sustainability 2016:8(11):1136.
Zhou C, Yuan JZ, Liu HZ, Qiu J. Bluetooth indoor positioning based on RSSI and Kalman filter. Wireless Personal
Communications 2017;96(3):4115-4130.

More Related Content

What's hot

IEEE Final Year Projects 2011-2012 :: Elysium Technologies Pvt Ltd::Paralleld...
IEEE Final Year Projects 2011-2012 :: Elysium Technologies Pvt Ltd::Paralleld...IEEE Final Year Projects 2011-2012 :: Elysium Technologies Pvt Ltd::Paralleld...
IEEE Final Year Projects 2011-2012 :: Elysium Technologies Pvt Ltd::Paralleld...sunda2011
 
A generic log analyzer for auto recovery of container orchestration system
A generic log analyzer for auto recovery of container orchestration systemA generic log analyzer for auto recovery of container orchestration system
A generic log analyzer for auto recovery of container orchestration systemConference Papers
 
ITA: The Improved Throttled Algorithm of Load Balancing on Cloud Computing
ITA: The Improved Throttled Algorithm of Load Balancing on Cloud ComputingITA: The Improved Throttled Algorithm of Load Balancing on Cloud Computing
ITA: The Improved Throttled Algorithm of Load Balancing on Cloud ComputingIJCNCJournal
 
IEEE Projects 2013 For ME Cse Seabirds ( Trichy, Thanjavur, Karur, Perambalur )
IEEE Projects 2013 For ME Cse Seabirds ( Trichy, Thanjavur, Karur, Perambalur )IEEE Projects 2013 For ME Cse Seabirds ( Trichy, Thanjavur, Karur, Perambalur )
IEEE Projects 2013 For ME Cse Seabirds ( Trichy, Thanjavur, Karur, Perambalur )SBGC
 
Algorithm Solved IEEE Projects 2012 2013 Java @ Seabirdssolutions
Algorithm Solved IEEE Projects 2012 2013 Java @ SeabirdssolutionsAlgorithm Solved IEEE Projects 2012 2013 Java @ Seabirdssolutions
Algorithm Solved IEEE Projects 2012 2013 Java @ SeabirdssolutionsSBGC
 
Ieee projects 2012 for cse
Ieee projects 2012 for cseIeee projects 2012 for cse
Ieee projects 2012 for cseSBGC
 
Dynamic Framework Design for Offloading Mobile Applications to Cloud
Dynamic Framework Design for Offloading Mobile Applications to CloudDynamic Framework Design for Offloading Mobile Applications to Cloud
Dynamic Framework Design for Offloading Mobile Applications to Cloudiosrjce
 
IRJET- Cipher Text-Policy Attribute-Based Encryption and with Delegation ...
IRJET-  	  Cipher Text-Policy Attribute-Based Encryption and with Delegation ...IRJET-  	  Cipher Text-Policy Attribute-Based Encryption and with Delegation ...
IRJET- Cipher Text-Policy Attribute-Based Encryption and with Delegation ...IRJET Journal
 
Ieee projects-2014-bulk-ieee-projects-2015-title-list-for-me-be-mphil-final-y...
Ieee projects-2014-bulk-ieee-projects-2015-title-list-for-me-be-mphil-final-y...Ieee projects-2014-bulk-ieee-projects-2015-title-list-for-me-be-mphil-final-y...
Ieee projects-2014-bulk-ieee-projects-2015-title-list-for-me-be-mphil-final-y...birdsking
 
Just in-time code offloading for wearable computing
Just in-time code offloading for wearable computingJust in-time code offloading for wearable computing
Just in-time code offloading for wearable computingredpel dot com
 
Automated LiveMigration of VMs
Automated LiveMigration of VMs Automated LiveMigration of VMs
Automated LiveMigration of VMs Akhila Chatlapalle
 
Iaetsd pinpointing performance deviations of subsystems in distributed
Iaetsd pinpointing performance deviations of subsystems in distributedIaetsd pinpointing performance deviations of subsystems in distributed
Iaetsd pinpointing performance deviations of subsystems in distributedIaetsd Iaetsd
 
A survey-report-on-cloud-computing-testing-environment
A survey-report-on-cloud-computing-testing-environmentA survey-report-on-cloud-computing-testing-environment
A survey-report-on-cloud-computing-testing-environmentshritosh kumar
 

What's hot (14)

IEEE Final Year Projects 2011-2012 :: Elysium Technologies Pvt Ltd::Paralleld...
IEEE Final Year Projects 2011-2012 :: Elysium Technologies Pvt Ltd::Paralleld...IEEE Final Year Projects 2011-2012 :: Elysium Technologies Pvt Ltd::Paralleld...
IEEE Final Year Projects 2011-2012 :: Elysium Technologies Pvt Ltd::Paralleld...
 
A generic log analyzer for auto recovery of container orchestration system
A generic log analyzer for auto recovery of container orchestration systemA generic log analyzer for auto recovery of container orchestration system
A generic log analyzer for auto recovery of container orchestration system
 
ITA: The Improved Throttled Algorithm of Load Balancing on Cloud Computing
ITA: The Improved Throttled Algorithm of Load Balancing on Cloud ComputingITA: The Improved Throttled Algorithm of Load Balancing on Cloud Computing
ITA: The Improved Throttled Algorithm of Load Balancing on Cloud Computing
 
IEEE Projects 2013 For ME Cse Seabirds ( Trichy, Thanjavur, Karur, Perambalur )
IEEE Projects 2013 For ME Cse Seabirds ( Trichy, Thanjavur, Karur, Perambalur )IEEE Projects 2013 For ME Cse Seabirds ( Trichy, Thanjavur, Karur, Perambalur )
IEEE Projects 2013 For ME Cse Seabirds ( Trichy, Thanjavur, Karur, Perambalur )
 
Algorithm Solved IEEE Projects 2012 2013 Java @ Seabirdssolutions
Algorithm Solved IEEE Projects 2012 2013 Java @ SeabirdssolutionsAlgorithm Solved IEEE Projects 2012 2013 Java @ Seabirdssolutions
Algorithm Solved IEEE Projects 2012 2013 Java @ Seabirdssolutions
 
Ieee projects 2012 for cse
Ieee projects 2012 for cseIeee projects 2012 for cse
Ieee projects 2012 for cse
 
Dynamic Framework Design for Offloading Mobile Applications to Cloud
Dynamic Framework Design for Offloading Mobile Applications to CloudDynamic Framework Design for Offloading Mobile Applications to Cloud
Dynamic Framework Design for Offloading Mobile Applications to Cloud
 
IRJET- Cipher Text-Policy Attribute-Based Encryption and with Delegation ...
IRJET-  	  Cipher Text-Policy Attribute-Based Encryption and with Delegation ...IRJET-  	  Cipher Text-Policy Attribute-Based Encryption and with Delegation ...
IRJET- Cipher Text-Policy Attribute-Based Encryption and with Delegation ...
 
Ieee projects-2014-bulk-ieee-projects-2015-title-list-for-me-be-mphil-final-y...
Ieee projects-2014-bulk-ieee-projects-2015-title-list-for-me-be-mphil-final-y...Ieee projects-2014-bulk-ieee-projects-2015-title-list-for-me-be-mphil-final-y...
Ieee projects-2014-bulk-ieee-projects-2015-title-list-for-me-be-mphil-final-y...
 
Just in-time code offloading for wearable computing
Just in-time code offloading for wearable computingJust in-time code offloading for wearable computing
Just in-time code offloading for wearable computing
 
Automated LiveMigration of VMs
Automated LiveMigration of VMs Automated LiveMigration of VMs
Automated LiveMigration of VMs
 
IBM Think Milano
IBM Think MilanoIBM Think Milano
IBM Think Milano
 
Iaetsd pinpointing performance deviations of subsystems in distributed
Iaetsd pinpointing performance deviations of subsystems in distributedIaetsd pinpointing performance deviations of subsystems in distributed
Iaetsd pinpointing performance deviations of subsystems in distributed
 
A survey-report-on-cloud-computing-testing-environment
A survey-report-on-cloud-computing-testing-environmentA survey-report-on-cloud-computing-testing-environment
A survey-report-on-cloud-computing-testing-environment
 

Similar to Performance analysis of enhanced delta sampling algorithm for ble indoor localization

Indoor tracking with bluetooth low energy devices using k nearest neighbour a...
Indoor tracking with bluetooth low energy devices using k nearest neighbour a...Indoor tracking with bluetooth low energy devices using k nearest neighbour a...
Indoor tracking with bluetooth low energy devices using k nearest neighbour a...Conference Papers
 
Nuzzer algorithm based Human Tracking and Security System for Device-Free Pas...
Nuzzer algorithm based Human Tracking and Security System for Device-Free Pas...Nuzzer algorithm based Human Tracking and Security System for Device-Free Pas...
Nuzzer algorithm based Human Tracking and Security System for Device-Free Pas...Eswar Publications
 
FUZZY CLUSTERING FOR IMPROVED POSITIONING
FUZZY CLUSTERING FOR IMPROVED POSITIONINGFUZZY CLUSTERING FOR IMPROVED POSITIONING
FUZZY CLUSTERING FOR IMPROVED POSITIONINGijitjournal
 
A genetic based indoor positioning algorithm using Wi-Fi received signal stre...
A genetic based indoor positioning algorithm using Wi-Fi received signal stre...A genetic based indoor positioning algorithm using Wi-Fi received signal stre...
A genetic based indoor positioning algorithm using Wi-Fi received signal stre...IAESIJAI
 
Traffic Outlier Detection by Density-Based Bounded Local Outlier Factors
Traffic Outlier Detection by Density-Based Bounded Local Outlier FactorsTraffic Outlier Detection by Density-Based Bounded Local Outlier Factors
Traffic Outlier Detection by Density-Based Bounded Local Outlier FactorsITIIIndustries
 
The proposed System for Indoor Location Tracking
The proposed System for Indoor Location TrackingThe proposed System for Indoor Location Tracking
The proposed System for Indoor Location TrackingEditor IJCATR
 
REAL-TIME PEDESTRIAN DETECTION USING APACHE STORM IN A DISTRIBUTED ENVIRONMENT
REAL-TIME PEDESTRIAN DETECTION USING APACHE STORM IN A DISTRIBUTED ENVIRONMENTREAL-TIME PEDESTRIAN DETECTION USING APACHE STORM IN A DISTRIBUTED ENVIRONMENT
REAL-TIME PEDESTRIAN DETECTION USING APACHE STORM IN A DISTRIBUTED ENVIRONMENTcscpconf
 
Real-Time Pedestrian Detection Using Apache Storm in a Distributed Environment
Real-Time Pedestrian Detection Using Apache Storm in a Distributed Environment Real-Time Pedestrian Detection Using Apache Storm in a Distributed Environment
Real-Time Pedestrian Detection Using Apache Storm in a Distributed Environment csandit
 
Unsupervised region of interest
Unsupervised region of interestUnsupervised region of interest
Unsupervised region of interestcsandit
 
Data mining projects topics for java and dot net
Data mining projects topics for java and dot netData mining projects topics for java and dot net
Data mining projects topics for java and dot netredpel dot com
 
SECURE & EFFICIENT AUDIT SERVICE OUTSOURCING FOR DATA INTEGRITY IN CLOUDS
SECURE & EFFICIENT AUDIT SERVICE OUTSOURCING FOR DATA INTEGRITY IN CLOUDSSECURE & EFFICIENT AUDIT SERVICE OUTSOURCING FOR DATA INTEGRITY IN CLOUDS
SECURE & EFFICIENT AUDIT SERVICE OUTSOURCING FOR DATA INTEGRITY IN CLOUDSGyan Prakash
 
Location estimation in zig bee network based on fingerprinting
Location estimation in zig bee network based on fingerprintingLocation estimation in zig bee network based on fingerprinting
Location estimation in zig bee network based on fingerprintingHanumesh Palla
 
Automated traffic sign board
Automated traffic sign boardAutomated traffic sign board
Automated traffic sign boardijcsa
 
Ijsartv6 i336124
Ijsartv6 i336124Ijsartv6 i336124
Ijsartv6 i336124aissmsblogs
 
IRJET - Object Detection using Hausdorff Distance
IRJET -  	  Object Detection using Hausdorff DistanceIRJET -  	  Object Detection using Hausdorff Distance
IRJET - Object Detection using Hausdorff DistanceIRJET Journal
 
IRJET- Object Detection using Hausdorff Distance
IRJET-  	  Object Detection using Hausdorff DistanceIRJET-  	  Object Detection using Hausdorff Distance
IRJET- Object Detection using Hausdorff DistanceIRJET Journal
 
IRJET- Profile Management System
IRJET- Profile Management SystemIRJET- Profile Management System
IRJET- Profile Management SystemIRJET Journal
 

Similar to Performance analysis of enhanced delta sampling algorithm for ble indoor localization (20)

Indoor tracking with bluetooth low energy devices using k nearest neighbour a...
Indoor tracking with bluetooth low energy devices using k nearest neighbour a...Indoor tracking with bluetooth low energy devices using k nearest neighbour a...
Indoor tracking with bluetooth low energy devices using k nearest neighbour a...
 
Nuzzer algorithm based Human Tracking and Security System for Device-Free Pas...
Nuzzer algorithm based Human Tracking and Security System for Device-Free Pas...Nuzzer algorithm based Human Tracking and Security System for Device-Free Pas...
Nuzzer algorithm based Human Tracking and Security System for Device-Free Pas...
 
FUZZY CLUSTERING FOR IMPROVED POSITIONING
FUZZY CLUSTERING FOR IMPROVED POSITIONINGFUZZY CLUSTERING FOR IMPROVED POSITIONING
FUZZY CLUSTERING FOR IMPROVED POSITIONING
 
A genetic based indoor positioning algorithm using Wi-Fi received signal stre...
A genetic based indoor positioning algorithm using Wi-Fi received signal stre...A genetic based indoor positioning algorithm using Wi-Fi received signal stre...
A genetic based indoor positioning algorithm using Wi-Fi received signal stre...
 
Traffic Outlier Detection by Density-Based Bounded Local Outlier Factors
Traffic Outlier Detection by Density-Based Bounded Local Outlier FactorsTraffic Outlier Detection by Density-Based Bounded Local Outlier Factors
Traffic Outlier Detection by Density-Based Bounded Local Outlier Factors
 
The proposed System for Indoor Location Tracking
The proposed System for Indoor Location TrackingThe proposed System for Indoor Location Tracking
The proposed System for Indoor Location Tracking
 
ActivFi
ActivFiActivFi
ActivFi
 
REAL-TIME PEDESTRIAN DETECTION USING APACHE STORM IN A DISTRIBUTED ENVIRONMENT
REAL-TIME PEDESTRIAN DETECTION USING APACHE STORM IN A DISTRIBUTED ENVIRONMENTREAL-TIME PEDESTRIAN DETECTION USING APACHE STORM IN A DISTRIBUTED ENVIRONMENT
REAL-TIME PEDESTRIAN DETECTION USING APACHE STORM IN A DISTRIBUTED ENVIRONMENT
 
Real-Time Pedestrian Detection Using Apache Storm in a Distributed Environment
Real-Time Pedestrian Detection Using Apache Storm in a Distributed Environment Real-Time Pedestrian Detection Using Apache Storm in a Distributed Environment
Real-Time Pedestrian Detection Using Apache Storm in a Distributed Environment
 
Unsupervised region of interest
Unsupervised region of interestUnsupervised region of interest
Unsupervised region of interest
 
Data mining projects topics for java and dot net
Data mining projects topics for java and dot netData mining projects topics for java and dot net
Data mining projects topics for java and dot net
 
SECURE & EFFICIENT AUDIT SERVICE OUTSOURCING FOR DATA INTEGRITY IN CLOUDS
SECURE & EFFICIENT AUDIT SERVICE OUTSOURCING FOR DATA INTEGRITY IN CLOUDSSECURE & EFFICIENT AUDIT SERVICE OUTSOURCING FOR DATA INTEGRITY IN CLOUDS
SECURE & EFFICIENT AUDIT SERVICE OUTSOURCING FOR DATA INTEGRITY IN CLOUDS
 
adcom2013_submission_59
adcom2013_submission_59adcom2013_submission_59
adcom2013_submission_59
 
Location estimation in zig bee network based on fingerprinting
Location estimation in zig bee network based on fingerprintingLocation estimation in zig bee network based on fingerprinting
Location estimation in zig bee network based on fingerprinting
 
Automated traffic sign board
Automated traffic sign boardAutomated traffic sign board
Automated traffic sign board
 
Video
VideoVideo
Video
 
Ijsartv6 i336124
Ijsartv6 i336124Ijsartv6 i336124
Ijsartv6 i336124
 
IRJET - Object Detection using Hausdorff Distance
IRJET -  	  Object Detection using Hausdorff DistanceIRJET -  	  Object Detection using Hausdorff Distance
IRJET - Object Detection using Hausdorff Distance
 
IRJET- Object Detection using Hausdorff Distance
IRJET-  	  Object Detection using Hausdorff DistanceIRJET-  	  Object Detection using Hausdorff Distance
IRJET- Object Detection using Hausdorff Distance
 
IRJET- Profile Management System
IRJET- Profile Management SystemIRJET- Profile Management System
IRJET- Profile Management System
 

More from Conference Papers

Ai driven occupational skills generator
Ai driven occupational skills generatorAi driven occupational skills generator
Ai driven occupational skills generatorConference Papers
 
Advanced resource allocation and service level monitoring for container orche...
Advanced resource allocation and service level monitoring for container orche...Advanced resource allocation and service level monitoring for container orche...
Advanced resource allocation and service level monitoring for container orche...Conference Papers
 
Adaptive authentication to determine login attempt penalty from multiple inpu...
Adaptive authentication to determine login attempt penalty from multiple inpu...Adaptive authentication to determine login attempt penalty from multiple inpu...
Adaptive authentication to determine login attempt penalty from multiple inpu...Conference Papers
 
Absorption spectrum analysis of dentine sialophosphoprotein (dspp) in orthodo...
Absorption spectrum analysis of dentine sialophosphoprotein (dspp) in orthodo...Absorption spectrum analysis of dentine sialophosphoprotein (dspp) in orthodo...
Absorption spectrum analysis of dentine sialophosphoprotein (dspp) in orthodo...Conference Papers
 
A deployment scenario a taxonomy mapping and keyword searching for the appl...
A deployment scenario   a taxonomy mapping and keyword searching for the appl...A deployment scenario   a taxonomy mapping and keyword searching for the appl...
A deployment scenario a taxonomy mapping and keyword searching for the appl...Conference Papers
 
Automated snomed ct mapping of clinical discharge summary data for cardiology...
Automated snomed ct mapping of clinical discharge summary data for cardiology...Automated snomed ct mapping of clinical discharge summary data for cardiology...
Automated snomed ct mapping of clinical discharge summary data for cardiology...Conference Papers
 
Automated login method selection in a multi modal authentication - login meth...
Automated login method selection in a multi modal authentication - login meth...Automated login method selection in a multi modal authentication - login meth...
Automated login method selection in a multi modal authentication - login meth...Conference Papers
 
Atomization of reduced graphene oxide ultra thin film for transparent electro...
Atomization of reduced graphene oxide ultra thin film for transparent electro...Atomization of reduced graphene oxide ultra thin film for transparent electro...
Atomization of reduced graphene oxide ultra thin film for transparent electro...Conference Papers
 
An enhanced wireless presentation system for large scale content distribution
An enhanced wireless presentation system for large scale content distribution An enhanced wireless presentation system for large scale content distribution
An enhanced wireless presentation system for large scale content distribution Conference Papers
 
An analysis of a large scale wireless image distribution system deployment
An analysis of a large scale wireless image distribution system deploymentAn analysis of a large scale wireless image distribution system deployment
An analysis of a large scale wireless image distribution system deploymentConference Papers
 
Validation of early testing method for e government projects by requirement ...
Validation of early testing method for e  government projects by requirement ...Validation of early testing method for e  government projects by requirement ...
Validation of early testing method for e government projects by requirement ...Conference Papers
 
The design and implementation of trade finance application based on hyperledg...
The design and implementation of trade finance application based on hyperledg...The design and implementation of trade finance application based on hyperledg...
The design and implementation of trade finance application based on hyperledg...Conference Papers
 
Unified theory of acceptance and use of technology of e government services i...
Unified theory of acceptance and use of technology of e government services i...Unified theory of acceptance and use of technology of e government services i...
Unified theory of acceptance and use of technology of e government services i...Conference Papers
 
Towards predictive maintenance for marine sector in malaysia
Towards predictive maintenance for marine sector in malaysiaTowards predictive maintenance for marine sector in malaysia
Towards predictive maintenance for marine sector in malaysiaConference Papers
 
The new leaed (ii) ion selective electrode on free plasticizer film of pthfa ...
The new leaed (ii) ion selective electrode on free plasticizer film of pthfa ...The new leaed (ii) ion selective electrode on free plasticizer film of pthfa ...
The new leaed (ii) ion selective electrode on free plasticizer film of pthfa ...Conference Papers
 
Searchable symmetric encryption security definitions
Searchable symmetric encryption security definitionsSearchable symmetric encryption security definitions
Searchable symmetric encryption security definitionsConference Papers
 
Super convergence of autonomous things
Super convergence of autonomous thingsSuper convergence of autonomous things
Super convergence of autonomous thingsConference Papers
 
Study on performance of capacitor less ldo with different types of resistor
Study on performance of capacitor less ldo with different types of resistorStudy on performance of capacitor less ldo with different types of resistor
Study on performance of capacitor less ldo with different types of resistorConference Papers
 
Stil test pattern generation enhancement in mixed signal design
Stil test pattern generation enhancement in mixed signal designStil test pattern generation enhancement in mixed signal design
Stil test pattern generation enhancement in mixed signal designConference Papers
 
On premise ai platform - from dc to edge
On premise ai platform - from dc to edgeOn premise ai platform - from dc to edge
On premise ai platform - from dc to edgeConference Papers
 

More from Conference Papers (20)

Ai driven occupational skills generator
Ai driven occupational skills generatorAi driven occupational skills generator
Ai driven occupational skills generator
 
Advanced resource allocation and service level monitoring for container orche...
Advanced resource allocation and service level monitoring for container orche...Advanced resource allocation and service level monitoring for container orche...
Advanced resource allocation and service level monitoring for container orche...
 
Adaptive authentication to determine login attempt penalty from multiple inpu...
Adaptive authentication to determine login attempt penalty from multiple inpu...Adaptive authentication to determine login attempt penalty from multiple inpu...
Adaptive authentication to determine login attempt penalty from multiple inpu...
 
Absorption spectrum analysis of dentine sialophosphoprotein (dspp) in orthodo...
Absorption spectrum analysis of dentine sialophosphoprotein (dspp) in orthodo...Absorption spectrum analysis of dentine sialophosphoprotein (dspp) in orthodo...
Absorption spectrum analysis of dentine sialophosphoprotein (dspp) in orthodo...
 
A deployment scenario a taxonomy mapping and keyword searching for the appl...
A deployment scenario   a taxonomy mapping and keyword searching for the appl...A deployment scenario   a taxonomy mapping and keyword searching for the appl...
A deployment scenario a taxonomy mapping and keyword searching for the appl...
 
Automated snomed ct mapping of clinical discharge summary data for cardiology...
Automated snomed ct mapping of clinical discharge summary data for cardiology...Automated snomed ct mapping of clinical discharge summary data for cardiology...
Automated snomed ct mapping of clinical discharge summary data for cardiology...
 
Automated login method selection in a multi modal authentication - login meth...
Automated login method selection in a multi modal authentication - login meth...Automated login method selection in a multi modal authentication - login meth...
Automated login method selection in a multi modal authentication - login meth...
 
Atomization of reduced graphene oxide ultra thin film for transparent electro...
Atomization of reduced graphene oxide ultra thin film for transparent electro...Atomization of reduced graphene oxide ultra thin film for transparent electro...
Atomization of reduced graphene oxide ultra thin film for transparent electro...
 
An enhanced wireless presentation system for large scale content distribution
An enhanced wireless presentation system for large scale content distribution An enhanced wireless presentation system for large scale content distribution
An enhanced wireless presentation system for large scale content distribution
 
An analysis of a large scale wireless image distribution system deployment
An analysis of a large scale wireless image distribution system deploymentAn analysis of a large scale wireless image distribution system deployment
An analysis of a large scale wireless image distribution system deployment
 
Validation of early testing method for e government projects by requirement ...
Validation of early testing method for e  government projects by requirement ...Validation of early testing method for e  government projects by requirement ...
Validation of early testing method for e government projects by requirement ...
 
The design and implementation of trade finance application based on hyperledg...
The design and implementation of trade finance application based on hyperledg...The design and implementation of trade finance application based on hyperledg...
The design and implementation of trade finance application based on hyperledg...
 
Unified theory of acceptance and use of technology of e government services i...
Unified theory of acceptance and use of technology of e government services i...Unified theory of acceptance and use of technology of e government services i...
Unified theory of acceptance and use of technology of e government services i...
 
Towards predictive maintenance for marine sector in malaysia
Towards predictive maintenance for marine sector in malaysiaTowards predictive maintenance for marine sector in malaysia
Towards predictive maintenance for marine sector in malaysia
 
The new leaed (ii) ion selective electrode on free plasticizer film of pthfa ...
The new leaed (ii) ion selective electrode on free plasticizer film of pthfa ...The new leaed (ii) ion selective electrode on free plasticizer film of pthfa ...
The new leaed (ii) ion selective electrode on free plasticizer film of pthfa ...
 
Searchable symmetric encryption security definitions
Searchable symmetric encryption security definitionsSearchable symmetric encryption security definitions
Searchable symmetric encryption security definitions
 
Super convergence of autonomous things
Super convergence of autonomous thingsSuper convergence of autonomous things
Super convergence of autonomous things
 
Study on performance of capacitor less ldo with different types of resistor
Study on performance of capacitor less ldo with different types of resistorStudy on performance of capacitor less ldo with different types of resistor
Study on performance of capacitor less ldo with different types of resistor
 
Stil test pattern generation enhancement in mixed signal design
Stil test pattern generation enhancement in mixed signal designStil test pattern generation enhancement in mixed signal design
Stil test pattern generation enhancement in mixed signal design
 
On premise ai platform - from dc to edge
On premise ai platform - from dc to edgeOn premise ai platform - from dc to edge
On premise ai platform - from dc to edge
 

Recently uploaded

WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brandgvaughan
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsMiki Katsuragi
 
Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptxLBM Solutions
 
Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024Neo4j
 
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024BookNet Canada
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...shyamraj55
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfAlex Barbosa Coqueiro
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationRidwan Fadjar
 
costume and set research powerpoint presentation
costume and set research powerpoint presentationcostume and set research powerpoint presentation
costume and set research powerpoint presentationphoebematthew05
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesSinan KOZAK
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitecturePixlogix Infotech
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr LapshynFwdays
 
Artificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraArtificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraDeakin University
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machinePadma Pradeep
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Commit University
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024Scott Keck-Warren
 

Recently uploaded (20)

WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brand
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering Tips
 
Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptx
 
Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024
 
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food Manufacturing
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping Elbows
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdf
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 Presentation
 
costume and set research powerpoint presentation
costume and set research powerpoint presentationcostume and set research powerpoint presentation
costume and set research powerpoint presentation
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen Frames
 
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptxE-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC Architecture
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
 
Artificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraArtificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning era
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machine
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024
 

Performance analysis of enhanced delta sampling algorithm for ble indoor localization

  • 1. http://www.ierek.com/press Print ISSN: 2357-0849 International Journal on: Proceedings of Science and Technolgy pg. 1 Performance Analysis of Enhanced Delta Sampling Algorithm for BLE Indoor Localization Mohd Faiz Bin Mat Daud1 , Idawaty Ahmad 1 1 Faculty of Computer Science and Information Technology, University Putra Malaysia, Selangor, Malaysia David Chieng2 , Alvin Ting2 , SehChun Ng2 2 Wireless Innovation, Mimos Berhad,Technology Park Malaysia, Kuala Lumpur, Malaysia Keywords RSSI; BLE; Smoothing Algorithm; Delta Sampling; Indoor Localization Abstract Localization technologies are becoming increasingly important in support of Smart Building applications such as in-building navigation, asset and visitor or staff tracking applications. These Smart Building applications in turn improve user experience, operation efficiency, security and safety of building occupants. In case of active localization or position tracking technologies, Bluetooth Low Energy (BLE) has gained popularity due to its accuracy and lower entry cost. BLE indoor localization technology typically utilizes the Receive Signal Strength Indicator (RSSI) as a basis for wireless positioning algorithms such as fingerprinting or trilateration to compute its location. However, the accuracy of location computation is often impacted by unstable RSSI reading especially inside the buildings. To investigate this problem, we first evaluate the Delta Sampling algorithm proposed by Huh et. al. (2016) on its capability to stabilize the RSSI reading using an actual testbed. We then analyze its strength and weaknesses and propose an enhanced algorithm. The results show that the original Delta Sampling Algorithm is capable of stabilizing the RSSI readings but it posses some drawbacks. Further results show that our proposed enhanced algorithm is able to mitigate some of these problems. 1. Introduction Localization technologies are becoming increasingly important in support of Smart Building applications such as in- building navigation, asset and visitor or staff tracking applications. These applications in turn improve user experience, operation efficiency, security and safety of building occupants. In case of active localization or position tracking, Bluetooth 4.0 or Bluetooth Low Energy (BLE) technology has gained popularity due to its accuracy and lower entry cost. BLE indoor localization technology typically uses Receive Signal Strength Indicator (RSSI) as a basis for wireless positioning algorithms such as fingerprinting or trilateration to compute its location. However, the accuracy of this system is often impacted by unstable RSSI values at the receiver’s end due to well-known challenges such as RF interference, multipath fading, shadowing, etc, which impact the accuracy of location estimation. As shown by many studies, the further the receiver is away from the transmitter, the more unstable it becomes. Hence, some forms of preprocessing is required such as applying time-series filters or smoothing algorithms to stabilize the signal before it is can be used by localization algorithm. The work by Huh et al. (2016) introduces a Delta Sampling algorithm which removes some of the flier points or “noises” in the raw RSSI reading. It is believed that the algorithm can be further improved by addressing the undecided
  • 2. Mohd Faiz et al. / Proceedings of Science and Technolgy pg. 2 range of sample size and also identifying the number of invalid or false data. This algorithm can be combined with other smoothing algorithms to further improve the result. Figure 1 shows the application of the algorithm used in indoor localization which includes its usage in Wi-Fi and Cellular systems. Figure 1 Flow chart for problem area This paper proposes several improvements over the original Delta Sampling algorithm (Huh et al., 2016). A number of additional features are proposed to counter the weakness of the Delta Sampling. Since highly fluctuating RSSI will result in inaccurate location estimation, this study therefore only focuses on solving this problem. 2. Related work The underlying technologies for indoor localization ranges from Wi-Fi, BLE, visible light, sound/audio, magnetic, cellular system to mobile cameras (Dmitry, 2015). These technologies can either be implemented independently or in combination of two or more technologies. For example, a smart phone can fuse the info from WI-FI, BLE and its built-in sensors (Accelerometer, Magnetometer, Stepmeter) in order to achieve a better localization experience. However in practice, Wi-Fi and BLE-based systems are more popular due to their lower entry cost and widely accessibility. In the case of Wi-Fi, there is almost no need to build the infrastructure as Wi-Fi is available virtually everywhere. The common techniques used to compute the position are triangulation, trilateration and fingerprinting. Except for triangulation, most of these localization algorithms use RSSI as the base parameter for positioning computation, thus an error in RSSI measurement will severely impact the accuracy. Unfortunately in practise, RSSI reading of BLE is very unstable as proven in Neburka et al.(2016), Faragher et al. (2014) and Georgia et al. (2014). As shown in Georgia (2014) and Zhou et al. (2017), to get a stable RSSI value, smoothing and/or Kalman filters are often applied to the raw RSSI readings before the data can be used for localization. In this paper, with aim to further stabilize the received RSSI values, the Delta Sampling algorithm proposed in Huh et al. (2016) is implemented using an actual testbed and its strength and weaknesses are analyzed. The original is later enhanced to address some of the weaknesses found. 3. Methodology This experimental study consists of data collection and data analysis phases as shown in Figure 2 by adopting the methodology similar to Huh et al. (2016). During data collection phase, the raw data was gathered and stored while data analysis phase, the proposed Delta Sampling algorithm was executed and analyzed. The data collected phase was done using an android application. In the data analysis phase, the proposed algorithm was implemented and analyzed using a Python script.
  • 3. Mohd Faiz et al. / Proceedings of Science and Technolgy pg. 3 Figure 2 Experiment design 3.1. Data collection phase In order to perform this task, we developed an Android application with BLE receiver which offered the wireless scanner functionality. An integrated database within the app was also developed so that the scanned BLE data could be stored. The report generator functionality was also implemented in order to convert the data into the simple form which is easier to be analyzed. The filter algorithms were also implemented for this experiment. A BLE beaconing hardware was used as the transmitter according to iBeacon configuration. During the experiment, RSSI samples were collected every 100ms while moving the distance of the receiver (smartphone) from the transmitter (beacon) from 1m to 3m. The RSSI samples were collected at each distance for 70 seconds. The data obtained from the experiment (using the Android app) were raw RSSI which is subsequently exported to CSV format so that it can be easily processed. 3.2. Data analysis phase The data (RSSI samples) collected in CSV format needs to be imported into a computer so that data processing and analysis could be performed via a Python script. The script needs to use the raw RSSI data as input. After executing the script, the results were output in CSV form to enable graph plotting as well as computation of statistical data such as minimum, maximum and standard deviation. The results gather were than compared with the results obtained from Huh et al. (2016). 3.3. Experiment environment and setup Figure 3 shows on how the data collection phase was setup. The beacon was preconfigured configured with iBeacon standard. The configuration of this experiment is shown in Table 1 which is similar to those used in Huh et al. (2016). Figure 3 Experiment setup for data collection phase
  • 4. Mohd Faiz et al. / Proceedings of Science and Technolgy pg. 4 Table 1. Experiment configuration. 3.4. Delta sampling algorithm Figure 4 shows the detail mechanism in Delta Sampling Algorithm implemented in this experiment. As stated in Huh et al. (2016), this algorithm is good on its own or can be used in combination with other algorithms. They have also presented the result of combination with average filter. However, they the recommended values for Range and Threshold in the said algorithm are not addressed. The subsequent experiments aim to look into this.
  • 5. Mohd Faiz et al. / Proceedings of Science and Technolgy pg. 5 Figure 4 Delta Sampling algorithm. Huh et al. (2016) From the result shown in Figure 5, it can be seen that the overall trends are comparable to the benchmark paper (Huh et al., 2016). However, the raw RSSI in Huh et al. (2016) is found to be much more unstable as compared to this experiment as shown by its high standard deviation. The differences are likely owed to device and environment heterogeneity. Figure 5 Delta sampling algorithm. Huh et al. (2016) From Figure 6, it is clearly shown that the Delta sampling result is much more stable than the raw data. In this experiment, Delta sampling algorithm proven itself to be effective to solve the problem of RSSI fluctuation by detecting the flier points and remove them from the result. Figure 6 Raw vs delta sample This paper further analyzes the effect of Threshold and Range parameters in Delta Sampling algorithm. As shown in in Figure 4, the Threshold parameter is the main deciding factor in the detection of flier points while Range controls the data sets that are to be included in the calculation. In order to further understand the impacts of Threshold and Range parameters, further experiments were performed as shown in Figure 7 and Figure 8. The result in Figure 7 is obtained by using different Threshold values. When a low Threshold value is used, almost all of the Raw Data values are being considered as flier points or invalid data. As the Threshold value increases on the other hand, the graph will become closer to its original raw data which mean it is become less sensitive in outlier detection. Figure 7 Comparing threshold value
  • 6. Mohd Faiz et al. / Proceedings of Science and Technolgy pg. 6 Meanwhile, further analysis on Range value as in Figure 8 reveals that smaller range means only a few past data is taken into consideration in order to find the trend which means it only considers very recent data trend. This is quite useful option to we only want to consider the latest data. Figure 8 Comparing range value 3.5. Enhanced delta sampling algorithm The original Delta Sampling algorithm is not only good in detecting sudden change in data but can also be easily combined with other algorithms without much difficulty as stated in Huh et al. (2016). However, the weaknesses of Delta Sampling algorithm, especially in terms of identification of suitable Range and Threshold values in real-time must be addressed in order for it to be useful for BLE localization. This section proposes that the Range value must be in real-time application in order to be useful. Since the beacons are normally set at the beaconing rate or interval between 500ms to 1s only, therefore the data is much lesser compared to this experiment where the beaconing rate is at 100ms. Moreover, data that are older than 3s are normally unwanted as in real-time application as the user might have already moved more than 5m after 3s. The proposed solution uses aging or decay method in finding the right Range value. In short, tagging for time is added when the Raw data is collected by receiver. Figure 9 depicts the Enhanced Delta Sampling algorithm. For the Threshold, the best value is equal to 1.0 or below. This is because the lower the value of mean, the more sensitive it is to the outlier. In order to enable this, the Delta Sampling algorithm needs to be modified so that it is able to reset itself. This is provided if it detects more than or equal to 3 flier points continuously. Figure 10 shows the result of the enhanced algorithm with lower Threshold value and self-resetting function. The result shows that further improvement can be attained with the enhancements. In order to get a smoother result, this algorithm can be combined with other filtering or smoothing algorithms such as Kalman or Gaussian filter. Figure 11 shows the result of combined enhanced Delta Sampling with Moving Average (MA) filter. It is shown that the RSSI values can be stabilized significantly. 4. Conclusion and future work Through this experiment, it can be concluded that the Delta Sampling algorithm can stabilize the raw RSSI by removing the flier points in the samples. However, the results are very much depending on the choice of Threshold and Range values. To address this uncertainty, an enhancement in the algorithm is proposed. The results show that some further improvements can be achieved especially when combined with additional filter algorithm such as Moving Average.
  • 7. Mohd Faiz et al. / Proceedings of Science and Technolgy pg. 7 Figure 9 Enhanced Delta Sampling algorithm Figure 10 Raw vs Enhanced Delta Sampling algorithm
  • 8. Mohd Faiz et al. / Proceedings of Science and Technolgy pg. 8 Figure 11 Raw vs enhanced delta sampling + moving average 5. Acknowledgement The author would like to acknowledge the support from MIMOS Wireless Innovation Lab and University Putra Malaysia. This paper is also sponsored by Fundamental Research Grant Scheme (FRGS), University Putra Malaysia (UPM). Project code: 08-01-15-1722FR. 6. References Chai S, An R, Du Z. An indoor positioning algorithm using bluetooth low energy RSSI. International Conference on Advanced Material Science and Environmental Engineering (AMSEE 2016). Cho K, Park W, Hong M, Park G, Cho W, Seo J, Han K. Analysis of latency performance of Bluetooth Low Energy (BLE) networks. Sensors 2015;15(1):59-78. Dmitry N. On indoor positioning. Int J Open Information Tech ISSN: 2307-8162 2015;3(3). Dong Q, Dargie W. Evaluation of the reliability of RSSI for indoor localization. International Conference on Wireless Communications in Underground and Confined Areas 2012:1-6. Faragher, Ramsey, Harle, Robert. An analysis of the accuracy of bluetooth low energy for indoor positioning applications. Proceedings of the 27th International Technical Meeting of the Satellite Division of the Institute of Navigation (ION GNSS+’14) 2014; 201-210. Georgia I, Carlos M, Michel D. Improving distance estimation in object localisation with bluetooth low energy. SENSORCOMM 2014, 8th International Conference on Sensor Technologies and Applications 2014;45-49. Grzechca DE, Pelczar P, Chruszczyk L. Analysis of object location accuracy for iBeacon technology based on the RSSI path loss model and fingerprint map. Int J Electronics Telecommunications 2016;62(4):371-378. Huh JH, Bu YH, Seo KR. Bluetooth-tracing RSSI sampling method as basic technology of indoor localization for smart homes. Int J Smart Home 2016;10(10):9-22. Kim DY, Kim SH, Choi DS, Jin SH, Accurate indoor proximity zone detection based on time window and frequency with bluetooth low energy. Procedia Computer Science 2015;56(1):88-95. Kriz P, Maly F, Kozel T. Improving indoor localization using bluetooth low energy beacons. Mobile Information Systems 2016:1-11. Lee JG, Kim BK, Jang SB, Yeon SH, Ko YW. Accuracy enhancement of RSSI-based distance estimation by applying gaussian filter. Indian J Science Technology 2016;9(20):1-5. Ma Z, Poslad S, Bigham J, Zhang X, Men L. A BLE RSSI ranking based indoor positioning system for generic smartphones. Wireless Telecommunications Symposium 2017. Neburka J, Tlamsa Z, Benes V, Polak L, Kaller O, Bolecek L. Sebesta J, Kratochvil T. Study of the performance of RSSI based bluetooth smart indoor positioning. 26th International Conference Radioelektronika (RADIOELEKTRONIKA) 2016. Sung Y. RSSI-based distance estimation framework using a Kalman filter for sustainable indoor computing environments. Sustainability 2016:8(11):1136. Zhou C, Yuan JZ, Liu HZ, Qiu J. Bluetooth indoor positioning based on RSSI and Kalman filter. Wireless Personal Communications 2017;96(3):4115-4130.