Dataset for Macroscale Molecular Communication Testbed

Citation Author(s):
Pit
Hofmann
Deutsche Telekom Chair of Communication Networks, Technische Universität Dresden, Dresden, Germany
Jorge
Torres Gómez
Telecommunication Networks Group, School for Electrical Engineering and Computer Science, Technische Universität Berlin, Berlin, Germany
Frank H. P.
Fitzek
Deutsche Telekom Chair of Communication Networks, Technische Universität Dresden, Dresden, Germany; Centre for Tactile Internet with Human-in-the-Loop (CeTI), Dresden, Germany
Falko
Dressler
Telecommunication Networks Group, School for Electrical Engineering and Computer Science, Technische Universität Berlin, Berlin, Germany
Submitted by:
Pit Hofmann
Last updated:
Wed, 11/20/2024 - 18:04
DOI:
10.21227/ytkm-xp81
Links:
Testbed-based Receiver Optimization for SISO Molecular Communication Channels
License:
Creative Commons Attribution
298 Views
Categories:
Communications
Keywords:
Explainable AI, Machine Learning, molecular communication, testbed, neural network, local interpretable model-agnostic explanation, individual conditional expectation
0
0 ratings - Please login to submit your rating.
ACCESS DATASET CITE SHARE/EMBED

Abstract 

This data set is from a macroscale molecular communication testbed and provides a set of experimental measurement data.
The molecules used are composed of a diluted alcoholic solution, i.e., ethanol molecules. We mixed four parts of water with one part ethanol, with the mass ratio 1/4. The molecules are released by a mechanism (propulsive release) at the transmitter side, propagate through the free-space channel (assisted by an additional drift), and can be detected at the receiver side with a commercial-off-the-shelf alcohol sensor. Every 0.1 seconds, the current concentration of the ethanol molecules on the receiver side is measured. The information is consequently encoded into temporal sequences (here the temporal concentration of the ethanol molecules). Further information for the testbed setup can also be found in: https://ieeexplore.ieee.org/document/9900720

Furthermore, the dataset contains the Matlab processing code and the Matlab data visualization code .

 

Instructions: 

Package:

- Publication: Explainability of Neural Networks for Symbol Detection in Molecular Communication Channels, IEEE Transactions on Molecular, Biological, and Multiscale Communications (https://ieeexplore.ieee.org/abstract/document/10188873)

- Matlab processing code: processing_dataset.zip

- Matlab visualization code: visualization_data.zip

- Measurement data set: dataset_SISO_testbed.csv (The data set contains the measured concentration on the receiver side for time steps of 0.1 seconds for 40 measurements. The first column contains the time step, columns two to 41 visualize the measurements. )

Funding Agency: 
German Federal Ministry of Education and Research (BMBF) & German Research Foundation (DFG)
Grant Number: 
16KIS0917, 16KISK001K (BMBF) & DR 639/21-2, EXC 2050/1 – Project ID 390696704 – Cluster of Excellence “Centre for Tactile Internet with Human-in-the-Loop” (CeTI)

Dataset Files

LOGIN TO ACCESS DATASET FILES

 

QUESTIONS?