Random forest learning method to identify different objects using channel estimations from VLC link

Ilter, Mehmet Cagri; Dowhuszko, Alexis A.; Vangapattu, Kiran K.; Kutlu, Kubra; Hämäläinen, Jyri

doi:10.1109/pimrc48278.2020.9217131

Cited by 5 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach was applied e.g. in [4] and [5], where a Random Forest Classifier was trained to identify the object type and position that most likely generated the observed CSI. Similarly, an unsupervised learning algorithm that identifies the clusters in which the collected CSI should be divided, where each cluster is associated to a different event, was proposed in [6].…”

Section: Introductionmentioning

confidence: 99%

Effect of the Color Temperature of LED lighting on the sensing ability of Visible Light Communications

Dowhuszko

Ilter

Pinho

et al. 2021

2021 IEEE International Conference on Communications Workshops (ICC Workshops)

Self Cite

View full text Add to dashboard Cite

This paper studies the effect that the color temperature of an LED lamp has on the ability of a Visible Light Communication (VLC) system to detect different events, which could be the presence, position, and/or color of an object in the sensing area. The proposed VLC-based monitoring system takes advantage of the Channel State Information (CSI) that the VLC receiver estimates regularly for OFDM equalization, and makes use of K-means++ clustering to estimate the number of events that can be identified in the collected CSI data. The color temperature of the LED lighting is varied by changing the fraction of the total radiant flux emitted by Cool-White and Red-Orange LEDs, respectively, enabling to obtain a complete palette of white light that ranges from warm reddish (2600 K) to cool blueish (6200 K). The experimental evaluation is carried out with the aid of a software-defined VLC demonstrator, and shows that the sensing performance when using the reflected VLC signal to estimate the position of the object does not vary notably with the color temperature of the LED lamp. In contrast, the use of white light with high Color Rendering Index provides better results when the objective is to identify the color signature that different objects create when placed in the sensing area.

show abstract

Section: Introductionmentioning

confidence: 99%

Effect of the Color Temperature of LED lighting on the sensing ability of Visible Light Communications

Dowhuszko

Ilter

Pinho

et al. 2021

2021 IEEE International Conference on Communications Workshops (ICC Workshops)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, novel machine learning solutions have been proposed to extract useful patterns from the VLC channel for monitoring purposes. For example, the authors of [7], [8] presented an object identification and object localization algorithm, respectively, using a Random Forest Classifier that was trained using the Channel State Information (CSI) that was collected in presence of different target events. However, the main drawback of such supervised learning algorithms is the data to train the classifier must be properly labeled, which is a requirement that complicates notably the implementation of these algorithms in practice.…”

Section: Introductionmentioning

confidence: 99%

Visible light communication-based monitoring for indoor environments using unsupervised learning

Ilter¹,

Dowhuszko²,

Hämäläinen³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Visible Light Communication (VLC) systems provide not only illumination and data communication, but also indoor monitoring services if the effect that different events create on the received optical signal is properly tracked. For this purpose, the Channel State Information that a VLC receiver computes to equalize the subcarriers of the OFDM signal can be also reused to train an Unsupervised Learning classifier. This way, different clusters can be created on the collected CSI data, which could be then mapped into relevant events to-bemonitored in the indoor environments, such as the presence of a new object in a given position or the change of the position of a given object. When compared to supervised learning algorithms, the proposed approach does not need to add tags in the training data, simplifying notably the implementation of the machine learning classifier. The practical validation the monitoring approach was done with the aid of a software-defined VLC link based on OFDM, in which a copy of the intensity modulated signal coming from a Phosphor-converted LED was captured by a pair of Photodetectors (PDs). The performance evaluation of the experimental VLC-based monitoring demo achieved a positioning accuracy in the few-centimeter-range, without the necessity of deploying a large number of sensors and/or adding a VLC-enabled sensor on the object to-be-tracked.

show abstract

Indoor monitoring system based on ARQ signaling generated by a Visible Light Communication link

Bas

Ortega

Martí

et al. 2021

2021 IEEE Global Communications Conference (GLOBECOM)

View full text Add to dashboard Cite

Visible Light Communications (VLC) is a candidate technology that complements the benefits of radio communication networks, particularly in those situations where a low-cost solution using license-free spectrum is required to enable ultra-dense deployments of indoor small cells. However, the main drawback that VLC has when compared to wireless communications on RF bands is that, in presence of obstacles between the transmitter and the receiver, full-blockage events are likely to happen as the power received on reflections is much weaker than the power of the blocked line-of-sight link. In this paper, we take advantage of this phenomenon and study the effect that different activities performed by people in the service area to-be-monitored have on the Automatic Repeat reQuest (ARQ) signaling of the VLC link. Based on the presented experimental studies, it is possible to conclude that different relevant events are able to be detected correctly according to the statistics of the ARQ signaling that is collected from the ongoing VLC transmission.

show abstract

Random forest learning method to identify different objects using channel estimations from VLC link

Cited by 5 publications

References 21 publications

Effect of the Color Temperature of LED lighting on the sensing ability of Visible Light Communications

Effect of the Color Temperature of LED lighting on the sensing ability of Visible Light Communications

Visible light communication-based monitoring for indoor environments using unsupervised learning

Indoor monitoring system based on ARQ signaling generated by a Visible Light Communication link

Contact Info

Product

Resources

About