ABSTRACT
Abnormality detection is expected to become one of the most crucial tasks of molecular communications (MC) based nanoscale networks. This task involves the sensing, detection, and reporting of abnormal changes taking place in a fluid medium, which may typify a disease and disorder, by employing a network formed by collaborating nanoscale sensors. By assuming that the channel parameters are perfectly known or accurately estimated, currently available methods for the solution of the distributed collaborative detection problems require the entire statistical characterization of the communication channel between sensors and fusion centre (FC). However, apart from some ideal cases, analytical channel models for MC are usually mathematically complex or, in many cases, analytical channel models don't exist at all. Furthermore, the accurate estimation of channel parameters is a difficult problem, even in ideal cases, because of the slow and dispersive signal propagation characteristics encountered in MC channels. Therefore, this fundamental assumption, which existing methodologies are based on, may be unsuitable in practical nanoscale sensor network implementations. For the first time in the literature, this paper proposes to employ a machine learning approach in this detection task. Specifically, we propose a deep learning-based recurrent neural network structure for decision fusion, which learns from data. Our results show that this approach leads to detectors that can perform well without any knowledge of the channel model and its properties, providing robustness and flexibility to the detection task, which is not present in existing approaches.
- Ian F. Akyildiz, Fernando Brunetti, and Cristina Blázquez. 2008. Nanonetworks: A new communication paradigm. Computer Networks 52 (2008), 2260--2279. Google ScholarDigital Library
- Chan-Byoung Chae and H. Birkan Yilmaz. 2014. Arrival modelling for molecular communication via diffusion. Electronics Letters 50 (2014), 1667--1669. Google ScholarCross Ref
- Raghavendra Chalapathy and Sanjay Chawla. 2019. Deep Learning for Anomaly Detection: A Survey. (2019), 1--50. arXiv:1901.03407 http://arxiv.org/abs/1901.03407Google Scholar
- V Chandola, A Banerjee, and V Kumar. 2009. Anomaly detection: A survey. ACM Reference Format 41, 15, Article 15 (2009), 58 pages. Google ScholarDigital Library
- Y. Deng, A. Noel, W. Guo, A. Nallanathan, and M. Elkashlan. 2016. 3D Stochastic Geometry Model for Large-Scale Molecular Communication Systems. In 2016 IEEE Global Communications Conference (GLOBECOM). IEEE, 1--6. Google ScholarCross Ref
- Nariman Farsad and Andrea Goldsmith. 2018. Neural network detection of data sequences in communication systems. IEEE Transactions on Signal Processing 66, 21 (2018), 5663--5678. arXiv:1802.02046 Google ScholarDigital Library
- Nariman Farsad, H. Birkan Yilmaz, Andrew Eckford, Chan Byoung Chae, and Weisi Guo. 2016. A comprehensive survey of recent advancements in molecular communication. IEEE Communications Surveys and Tutorials 18, 3 (2016), 1887--1919. arXiv:1410.4258 Google ScholarDigital Library
- Siavash Ghavami and Farshad Lahouti. 2017. Abnormality Detection in Correlated Gaussian Molecular Nano-Networks: Design and Analysis. IEEE Transactions on Nanobioscience 16 (2017), 189--202. arXiv:1604.08246 Google ScholarCross Ref
- Siavash Ghavami, Farshad Lahouti, and Ali Masoudi-Nejad. 2012. Modeling and analysis of abnormality detection in biomolecular nano-networks. Nano Communication Networks 3, 4 (2012), 229--241. Google ScholarCross Ref
- Reza Mosayebi, Vahid Jamali, Nafiseh Ghoroghchian, Robert Schober, Masoumeh Nasiri-Kenari, and Mahdieh Mehrabi. 2017. Cooperative Abnormality Detection via Diffusive Molecular Communications. IEEE Transactions on Nanobioscience 16 (2017), 828--842. arXiv:1703.10084 Google ScholarCross Ref
- Reza Mosayebi, Wayan Wicke, Vahid Jamali, Arman Ahmadzadeh, Robert Schober, and Masoumeh Nasiri-Kenari. 2018. Advanced Target Detection via Molecular Communication. 2018 IEEE Global Communications Conference, GLOBECOM 2018 - Proceedings (2018), 1--7. arXiv:1805.01514 Google ScholarCross Ref
- Tadashi Nakano, Andrew W. Eckford, and Tokuko Haraguchi. 2013. Molecular Communication. Cambridge University Press. Google ScholarCross Ref
- Adam Noel. 2015. Modeling and analysis of diffusive molecular communication systems. Ph.D. Dissertation. University of British Columbia.Google Scholar
- Adam Noel, Karen C. Cheung, and Robert Schober. 2014. Optimal receiver design for diffusive molecular communication with flow and additive noise. IEEE Transactions on Nanobioscience 13, 3 (2014), 350--362. arXiv:1308.0109 Google ScholarCross Ref
- H. Birkan Yilmaz, Akif Cem Heren, Tuna Tugcu, and Chan Byoung Chae. 2014. Three-dimensional channel characteristics for molecular communications with an absorbing receiver. IEEE Communications Letters 18 (2014), 929--932. arXiv:1404.4496 Google ScholarCross Ref
Index Terms
- RNN based abnormality detection with nanoscale sensor networks using molecular communications
Recommendations
Energy-efficient detection in sensor networks
There is significant interest in battery-powered sensor networks to be used for detection in a wide variety of applications, from surveillance and security to health and environmental monitoring. Severe energy and bandwidth constraints at each sensor ...
A generalized strength-based signal detection model for concentration-encoded molecular communication
BodyNets '13: Proceedings of the 8th International Conference on Body Area NetworksIn this paper, a generalized strength-based signal detection model for Concentration-Encoded Molecular Communication (CEMC) has been presented. The generalized strength-based signal detection problem in diffusion-based CEMC system has been investigated ...
On learning for fusion over fading channels in wireless sensor networks
ISWPC'10: Proceedings of the 5th IEEE international conference on Wireless pervasive computingIn order to derive optimal/suboptimal fusion rules, in general, it is assumed that statistical properties of sensors' decisions are known to a fusion center in distributed detection for wireless sensor networks. However, if sensors are deployed to ...
Comments