Machine learning based channel modeling for molecular MIMO communications

Lee, Changmin; Yilmaz, H. Birkan; Chae, Chan-Byoung; Farsad, Nariman; Goldsmith, Andrea

doi:10.1109/spawc.2017.8227765

Cited by 53 publications

(41 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The analysis and simulation results have shown that the performance of ligand-receptor reversible binding based DF relay MC can be significantly improved by increasing the ratio of association to dissociation, optimizing the number of molecules distribution scheme, or assigning an optimal location of relay node. In the future, the machine learning can be used for the channel [9], and some new performance metrics can be researched in the DF relay MC systems.…”

Section: Numerical Resultsmentioning

confidence: 99%

Performance Analysis of Reversible Binding Receptor Based Decode-and-Forward Relay in Molecular Communication Systems

Yuan

Wang

Peng

2018

IEEE Wireless Commun. Lett.

View full text Add to dashboard Cite

Molecular communication (MC) allows nanomachines to communicate and cooperate with each other in a fluid environment. The diffusion-based MC is popular but is easily constrained by the transmit distance due to the severe attenuation of molecule concentrations. In this letter, we present a decode-and-forward (DF) relay strategy for the reversible binding receptor in the diffusion-based MC system. The timevarying spatial distribution of the information molecules based on the reversible association and dissociation between ligand and receptor at the surface of receiver is characterized. An analytical expression for the evaluation of expected error probability is derived, and the key factors impacting on the performance are exploited. Results show that with a constant molecular budget, the proposal can improve the performance significantly, and the performance gain can be enhanced by optimizing the position of the relay node and the number of molecules assigned to the source node. Index Terms-Molecular communication (MC), decode-andforward (DF) relay, reversible binding, ligand-receptor I. INTRODUCTION D IFFUSION-BASED molecular communication (DbMC)is considered as a particularly effective and energyefficient approach of exchanging information among nanomachines [1]. Unlike the active transport and bacterium-based communication, DbMC is a short-to-medium range molecular communication (MC) without external energy and infrastructure. Information molecules are encoded by transmitter propagation to the receiver based on free diffusion in DbMC [2]. During the propagation, however, the attenuation of molecular concentration worsens with the increasing distance. Thus, the reliable communication is challenging for the scenario of long transmit distance.To solve this challenge, one potential solution inherited from the traditional wireless communication is to deploy relay between the transmitter and receiver. There have been several research efforts toward relay-assisted MC [3]-[6]. The design and analysis of repeaters using bacterial has been investigated in [3], an information delivery energy model for MC via bacteria relays is established. In [4] and [5], the authors propose a fixed-gain and variable-gain amplify-and-forward (AF) relay strategies. In [6], a decode-and-forward (DF) relay

show abstract

Section: Numerical Resultsmentioning

confidence: 99%

Performance Analysis of Reversible Binding Receptor Based Decode-and-Forward Relay in Molecular Communication Systems

Yuan

Wang

Peng

2018

IEEE Wireless Commun. Lett.

View full text Add to dashboard Cite

show abstract

“…represents the probability of a single molecule that was emitted from the ith transmit antenna arriving at the j th receiver antenna at the kth time slot. Due to the presence absorbing receivers, p i j [fc] need to be found by random walkbased Monte Carlo simulations or with the help of artificial neural networks [14]. In this paper, random walk-based Monte Carlo simulations are utilized to generate Pi,j[k].…”

Section: Pi J [K]mentioning

confidence: 99%

An ILI Mitigating Modulation Scheme for Molecular MIMO Communications

Gursoy

Başar

Pusane

et al. 2019

2019 42nd International Conference on Telecommunications and Signal Processing (TSP)

View full text Add to dashboard Cite

M ultiple-input-m ultiple-output (MIMO) approach is recently proposed to the diffusion-based m olecular communication realm in order to enhance communication performance. One of the m ost promising approaches of m olecular MIMO, spatial m ultiplexing (SMUX), transm its parallel streams of data to achieve an increased throughput. Unfortunately, the performance of SMUX is lim ited by a high error floor due to severe interlink interference (ILI). Inspired by the relatively more sparse transm ission strategy of the pulse-position m odulation (PPM) scheme, this study proposes a PPM-based novel SMUX approach to the m olecular MIMO literature. In the study, it is shown that the proposed approach combats ILI more effectively than the existing concentration-based SMUX approach and yields promising error performances.

show abstract

“…For modeling a molecular MIMO channel, we utilized the trained ANN of our previous work [22]. A trained ANN is able to estimate the channel coefficients h ji [ ] for a given MIMO scenario without running simulations.…”

Section: Ann For Channel Modelingmentioning

confidence: 99%

Spatial coding techniques for molecular MIMO

Damrath

Yilmaz

Chae

et al. 2017

2017 IEEE Information Theory Workshop (ITW)

Self Cite

View full text Add to dashboard Cite

This paper studies spatial diversity techniques applied to multiple-input multiple-output (MIMO) diffusion-based molecular communications (DBMC). Two types of spatial coding techniques, namely Alamouti-type coding and repetition MIMO coding are suggested and analyzed. In addition, we consider receiver-side equal-gain combining, which is equivalent to maximum-ratio combining in symmetrical scenarios. For numerical analysis, the channel impulse responses of a symmetrical 2×2 MIMO-DBMC system are acquired by a trained artificial neural network. It is demonstrated that spatial diversity has the potential to improve the system performance and that repetition MIMO coding outperforms Alamouti-type coding.

show abstract

Machine learning based channel modeling for molecular MIMO communications

Cited by 53 publications

References 16 publications

Performance Analysis of Reversible Binding Receptor Based Decode-and-Forward Relay in Molecular Communication Systems

Performance Analysis of Reversible Binding Receptor Based Decode-and-Forward Relay in Molecular Communication Systems

An ILI Mitigating Modulation Scheme for Molecular MIMO Communications

Spatial coding techniques for molecular MIMO

Contact Info

Product

Resources

About