Page 48 - ITU Journal Future and evolving technologies Volume 2 (2021), Issue 3 – Internet of Bio-Nano Things for health applications

ITU Journal on Future and Evolving Technologies, Volume 2 (2021), Issue 3

Classification of
existing works

Static nano-machines Mobile nano-machines

Pure diffusive channels Flow-induced channels Pure diffusive channels Flow-induced channels

• Single transmitter/receiver-based MC systems
• Relay-based MC systems
• MIMO MC systems
• Distributed MC systems
• Machine-learning-based MC systems

Transmitter Receiver

Detection schemes
Modulation schemes
with complexity

Symbol-by-symbol or Coherent or
sequence detectors non-coherent detectors

Fig. 1 – Various aspects of MC systems discussed in this paper.

An example of abnormality detection [15] has been Further, various machine‑learning‑based MC systems
shown in Fig. 8. This is a cooperative MC system for [27], [28], [29], [30] are also proposed in the literature.
detecting the presence of a cancer cell. The cancer cell The advantage of machine‑learning‑based MC systems is
releases biomarkers inside the blood vessel. The that the receiver does not need any channel knowledge
concentration of biomarkers are sensed by multiple since it can directly learn from the data [31]. These ma‑
nano‑sensors and inally the FC placed at a suitable chine learning based algorithms are particularly suitable
location inside the blood vessel collects the reading of for detection in a complex environment e.g., more than
nano‑sensors to decide whether cancer cells are two receivers in 3‑D medium.
present or not. For a global decision at FC, various
decision rules at FC (e.g., AND, OR, and K out of N Furthermore, every MC system discussed above is in‑
rules) have been proposed in the literature. In the AND tended for different applications. An example showing the
rule, the FC makes a positive decision if all the receivers possible applications of the different MC systems in IoBNT
send a positive decision. In the OR rule, if any one of the has been shown in Fig. 9. In this example, if an abnor‑
receivers sends a positive decision then the FC makes a mality detection system detects an abnormality such as
positive decision. In the K out of N rule, the FC makes a cancer cells, it can send molecular signals to the bio‑cyber
positive decision if K out of N receivers send a positive interface. The bio‑cyber interface can be a wearable de‑
decision. Note that each of the decision rules results in vice that can convert molecular signals to electromagnetic
different system performance. (EM) signals [17] and vice versa. The bio‑cyber interface
further sends the signal to an access point.

36 © International Telecommunication Union, 2021