Abnormality Detection in Correlated Gaussian Molecular Nano-Networks: Design and Analysis

Neural Network With Attention Mechanism for Abnormality Detection and Localization in Diffusive Molecular Communication

Diffusive molecular communication (DMC) is an emerging paradigm in nanotechnology, which provides biocompatibility and nanoscale communication for many promising applications, such as targeted drug delivery, environmental monitoring, etc. However, detecting and localizing abnormalities in most of these applications is challenging, such as identifying tumor cells within the body or detecting pollution in air or water. In this paper, we introduce a method for detecting and localizing abnormalities in three dimensional DMC system with multiple sensors, receivers and one fusion center by adopting Transformer-based model with attention mechanism. We make full use of the attention mechanism to capture the inter-symbol interference (ISI) to improve the accuracy of detection and localization. In addition, we simplify the model structure to significantly reduce the complexity of this model. Furthermore, two strategies that different types of molecules (DMT) and same type of molecules (SMT) are released by sensors are considered. The training dataset and testing dataset are generated under these two strategies. Simulation results show that the information about the abnormality detection and localization can be obtained at the same time based on the Transformer-based model under DMT and SMT. Especially, our model outperforms the Informer-based model, deep neural networks (DNN)-based model and log-likelihood ratio (LLR) method.

Performance Analysis and ISI Mitigation With Imperfect Transmitter in Molecular Communication

In molecular communication (MC), molecules are released from the transmitter to convey information. This paper considers a realistic molecule shift keying (MoSK) scenario with two species of molecule in two reservoirs, where the molecules are harvested from the environment and placed into different reservoirs, which are purified by exchanging molecules between the reservoirs. This process consumes energy, and for a reasonable energy cost, the reservoirs cannot be pure; thus, our MoSK transmitter is imperfect, releasing mixtures of both molecules for every symbol, resulting in inter-symbol interference (ISI). To mitigate ISI, the properties of the receiver are analyzed and a detection method based on the ratio of different molecules is proposed. Theoretical and simulation results are provided, showing that with the increase of energy cost, the system achieves better performance. The good performance of the proposed detection scheme is also demonstrated.

dMole: A Novel Transreceiver for Mobile Molecular Communication Using Robust Differential Detection Techniques

This paper proposes two differential detection techniques for signal detection in mobile molecular communication (MMC) for targeted drug delivery (TDD) application. In MMC, a nano-transmitter and a nano-receiver are considered to be in Brownian motion in an extracellular fluid medium. Transmitter uses calcium molecules to communicate with the receiver. Detection is performed using concentration difference based detector (CDD) at the receiver which calculates the maximum absolute concentration difference of the received signal within the same bit interval to detect the bit. This improves the bit error rate (BER) performance in MMC. The performance is further enhanced using manchester coded transmission with differential detection (MCD). In MCD, Bit-1 is coded by the symbol [1 0] and Bit-0 is coded by the symbol [0 1] and the difference between peaks of signals received in consecutive bit duration is taken to detect the bit. Simulation results prove that the MCD technique is 3 dB less sensitive to inter symbol interference (ISI) than the CDD technique. The detection threshold is selected using maximum a posteriori probability (MAP) rule. The performance of these detectors is compared with other existing detection techniques. Results reveal that BER performance of the CDD and MCD better by at least 3 dB and 6 dB, respectively. The proposed CDD and MCD techniques perform better in different bit-sequence length, various initial distance and different bit duration than other existing techniques.

On Gradient Descent Optimization in Diffusion-Advection Based 3-D Molecular Cooperative Communication

This work considers a cooperative communication system in 3-D fluid medium in which the flow of molecules is supported by the drift and the diffusion phenomena. To enhance the system performance, the equal gain combining is used at the destination nanomachine (DN) where the molecular signals arriving from the direct and the cooperative paths are combined together by employing equal weights. Using the gradient descent algorithm, the optimum threshold at DN, and the optimal number of molecules transmitted from source and cooperative nanomachines are obtained. For this purpose, the convex constraints are determined using the closed-form expression for the average probability of error at DN. Finally, the accuracy of the analytical results is validated through the particle/ Monte Carlo-based simulations.

Cooperative Abnormality Detection via Diffusive Molecular Communications

In this paper, we consider abnormality detection via diffusive molecular communications (MCs) for a network consisting of several sensors and a fusion center (FC). If a sensor detects an abnormality, it injects a number of molecules into the medium which is proportional to its sensing output. Two transmission schemes for releasing molecules into the medium are considered. In the first scheme, each sensor releases a different type of molecule (DTM), whereas in the second scheme, all sensors release the same type of molecule (STM). The molecules released by the sensors propagate through the MC channel and some may reach the FC where the final decision regarding whether or not an abnormality has occurred is made. We derive the optimal decision rules for both DTM and STM. However, the optimal detectors entail high computational complexity as log-likelihood ratios (LLRs) have to be computed. To overcome this issue, we show that the optimal decision rule for STM can be transformed into an equivalent low-complexity decision rule. Since a similar transformation is not possible for DTM, we propose simple low-complexity sub-optimal detectors based on different approximations of the LLR. The proposed low-complexity detectors are more suitable for practical MC systems than the original complex optimal decision rule, particularly when the FC is a nano-machine with limited computational capabilities. Furthermore, we analyze the performance of the proposed detectors in terms of their false alarm and missed detection probabilities. Simulation results verify our analytical derivations and reveal interesting insights regarding the tradeoff between complexity and performance of the proposed detectors and the considered DTM and STM schemes.

Early Cancer Detection in Blood Vessels Using Mobile Nanosensors

In this paper, we propose using mobile nanosensors (MNSs) for early stage anomaly detection. For concreteness, we focus on the detection of cancer cells located in a particular region of a blood vessel. These cancer cells produce and emit special molecules, so-called biomarkers, which are symptomatic for the presence of anomaly, into the cardiovascular system. Detection of cancer biomarkers with conventional blood tests is difficult in the early stages of a cancer due to the very low concentration of the biomarkers in the samples taken. However, close to the cancer cells, the concentration of the cancer biomarkers is high. Hence, detection is possible if a sensor with the ability to detect these biomarkers is placed in the vicinity of the cancer cells. Therefore, in this paper, we study the use of MNSs that are injected at a suitable injection site and can move through the blood vessels of the cardiovascular system, which potentially contain cancer cells. These MNSs can be activated by the biomarkers close to the cancer cells, where the biomarker concentration is sufficiently high. Eventually, the MNSs are collected by a fusion center (FC), where their activation levels are read and exploited to declare the presence of anomaly. We analytically derive the biomarker concentration in a network of interconnected blood vessels as well as the probability mass function of the MNSs' activation levels and validate the obtained results via particle-based simulations. Then, we derive the optimal decision rule for the FC regarding the presence of anomaly assuming that the entire network is known at the FC. Finally, for the FC, we propose a simple sum detector that does not require knowledge of the network topology. Our simulations reveal that while the optimal detector achieves a higher performance than the sum detector, both proposed detectors significantly outperform a benchmark scheme that uses fixed nanosensors at the FC.