How to minimise location error (to few centrimeter level) for indoor location system?

More B P Patil's questions See All

What type of nano-material coat will help in improving the solar panel efficiency?

01 February 2019 6,472 3 View

What are the chemicals coats which can be used for enhancing the efficiency of solar panel?

It is found that chemical coat will improve efficiency of solar panel. Let me know which is more effective and why? Thanks

05 June 2018 4,156 4 View

How should I analyze the multiple scans in Malvern Zetasizer software?

Hello, I am currently using the Malvern Zetasizer software for the purpose of obtaining the size distribution of nanoparticles produced in the lab. When I perform the runs in the software to get...

15 February 2021 4,251 1 View

What is/are the best ML classifier(s) for Sentinel2 images?

Hi I am trying to segment a sentinel2 image. At this stage, I want to run a binary classifier that assigns each pixel to either farm or non-farm pixel. For this purpose, I have 4 10m bands...

15 February 2021 3,596 9 View

Which optimization algorithm is most efficient for fitting a regression model using training dataset?

The goal of regression model is either to minimize the prediction error or to maximize a classification accuracy depending on the type of the model. Is there any optimization algorithm that is...

10 February 2021 4,128 3 View

How to choose the Hidden Layers Number and RBM Size in a DBN network?

Hello, When using a Deep Belief network (DBN) for images classification, how could we choose the number of hidden layers (number of Restricted Boltzmann Machines) and nodes (RBM size) in a hidden...

09 February 2021 4,618 5 View

Why does the accuracy of NN decreases when two datasets are combined?

I am working on gait analysis using a feed-forward NN. When I use data from the accelerometer (3 columns for each axis if stored in a data frame), I get an accuracy of 95%, and when I used data...

07 February 2021 9,654 6 View

Is there any similarity index between two time series?

Hi We have two time series dataset. For example mean daily temperature from two stations. Each of them have 30 data for a month. T1={ t1 , t2 ,... , t30 } T2={ t1 , t2 ,... , t30 } Now we want to...

06 February 2021 6,434 7 View

Matrix based scientific data analysis: extrapolating to matrices of sets?

Data sets, when structured, can be put in vector form (v(1)...v(n)), adding time dependency it's v(i, t) for i=1...n and t=1...T. Then we have a matrix of terms v(i, j)... Matrices are important,...

30 January 2021 9,295 6 View

Which techniques are used to improve the accuracy of deep learning models by compressing neural networks?

Hi all, I am looking for enhancing the accuracy of a deep learning model using some techniques to compress neural networks. Could someone suggest to me some of the tools/techniques,...

29 January 2021 1,781 4 View

When is the right time to stop training a classification algorithm?

In this example giving 400 samples looks like there is an accuracy of 91.5% while training beyond that point, accuracy is getting decreased. Are 400 samples enough to keep for this example? If...

27 January 2021 5,657 3 View

45% top1 Accuracy on TinyImgeNet?

I trained a model from scratch no transfer learning of any kind I got top1 validation accuracy of 45.79 and top5 validation accuracy of 72.39. I did a lot of hyperparameters tuning I have seen...

19 January 2021 6,883 2 View

Janusz Opiła

It depends on where is location registered.

If moving object has to discover its location I'd use phase shift analysis using 3 or 4 radio low frequency stationary wave sources.

If the system should localize objects, they should have radio source (Bluetooth?) attached, then three or four stationary receivers ought analyse phase shift.

Bert Shaw

There's a commercial product aimed at just your problem, Phase-Net, developed by a company called Venture Ad Astra, which is described at:

http://ventureadastra.com/gov-services/technologies-projects/index.html

briefly: "PhaseNet (also branded as ZuluTime in the commercial/consumer sector) uses any wireless network as the location network PhaseNet uses the communications emanating from these devices within the network to measure the distance between the same devices/nodes. This is quite similar to how GPS works outdoors, but with each node functioning as a pseudo GPS satellite." My understanding is that under normal circumstances it substantailly beats the 30-40 cm location you'd expect.

I believe that Patent No. US 07876266 Issue Date Jan 25, 2011

describes part of the methodology involved.

Francisco Martín

Dr B P Patil,

Your question is very general. I do not know if you are talking of a system that detects objects (using cameras, laser, RGBD...) or you are talking about something similar to a robot that calculates its position in the environment using sensory information.

Could you describe your problem?

B P Patil

By wireless means (radio waves) and not by laser means.

Basically beacons are used to find location.

Fernando Meira da Rocha

In the case of beacons , the best results have been with a particulate filter ( PF ) as this work:

Article Improved particle filter based on WLAN RSSI fingerprinting a...

Cheriet Mohammed El Amine

The best result for the indoor localization is obtained using Ultra Wideband technology (2cm) because it is not affected by the obstacles and the ground effects etc.

I invite you to watch this video:

http://www.timedomain.com/brandon.php

Best regards,

Dr. CHERIET A