Learning algorithm for reconfigurable antenna state selection

Gulati, Nikhil; González, David R.; Dandekar, Kapil R.

doi:10.1109/rws.2012.6175375

Cited by 6 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Future work will involve further analysis to quantify the training overhead required to find the optimal antenna state. Integrating and extending existing state selection techniques [14], [10] in future is essential for real-time operation.…”

Section: Discussionmentioning

confidence: 99%

Impact of pattern reconfigurable antennas on Interference Alignment over measured channels

Bahl

Gulati

Dandekar

et al. 2012

2012 IEEE Globecom Workshops

Self Cite

View full text Add to dashboard Cite

In recent years, it has been shown that concentrating interference and desired signal into separate spaces using Interference Alignment (IA), can achieve the outer bound of the degrees of freedom for the interference channel. However, the non-orthogonality of signal and interference space limits sum capacity performance. In this paper, we present the notion that by using reconfigurable antenna based pattern diversity, the optimal channel can be realized in order to maximize the distance between the two subspaces, thereby increasing sum capacity. We experimentally validate our claim and show the benefits of pattern reconfigurability using real world channels, measured in a MIMO-OFDM interference network. We quantify the results with two different reconfigurable antenna architectures. We show that an additional 47% gain in chordal distance and 45% gain in sum capacity were achieved by exploiting pattern diversity with IA. We further show that due to optimal channel selection, the performance of IA can also be improved in a low SNR regime.

show abstract

Section: Discussionmentioning

confidence: 99%

Impact of pattern reconfigurable antennas on Interference Alignment over measured channels

Bahl

Gulati

Dandekar

et al. 2012

2012 IEEE Globecom Workshops

Self Cite

View full text Add to dashboard Cite

show abstract

“…Any state selection scheme must account for these changes in order to maximize performance of the reconfigurable antenna system by reducing the time spent in suboptimal states. Additionally, the state selection scheme must rely on simple metrics so as to reduce the impact of increased overhead and feedback requirements [8].…”

Section: A Machine Learningmentioning

confidence: 99%

“…A state selection technique developed by the authors in [8] employs an online learning framework which seeks to learn the optimal state for a given environment without prior information about each antenna state and without the need for periodic exhaustive training or eliminating states available to the system. The selection process is formulated as a multi-armed bandit problem [?,?…”

Section: A Machine Learningmentioning

confidence: 99%

See 1 more Smart Citation

A Software Defined Testbed for Reconfigurable Antenna Cognitive Radio

Wanuga¹,

Pfeil²,

González³

et al. 2012

Proceedings of the 7th International Conference on Cognitive Radio Oriented Wireless Networks

Self Cite

View full text Add to dashboard Cite

A cognitive radio is capable of sensing local radio conditions and adapting its transmission and reception parameters to optimize performance in the evolving network environment. The use of software defined radio (SDR) to make communications more flexible has greatly facilitated the design of cognitive radios, by making communications reconfigurable at lower layers of the networking stack. The Cognitive Antenna Testbed described in this paper augments the flexibility of physical layer design through the use of reconfigurable antennas, which are capable of adapting frequency, pattern and polarization electrically, thereby expanding the design space of cognitive radio and networking algorithms. This testbed offers a platform for developing and field-testing reconfigurable antenna algorithms. Representative results of experiments performed with this testbed for antenna state selection, are provided to illustrate its relevance to cognitive networking research. Current research adapting this technology for use in dynamic spectrum access (DSA) applications is also discussed.

show abstract

“…We note that other diversity techniques such as antenna diversity, frequency diversity and MIMO technique can also be used to create feature set for our proposed learning method and it is not a requirement to have reconfigurable antennas to implement the learning technique. We explain how we utilize pattern diversity in Sec II-C and for more information on reconfigurable antennas and their applications, we direct the reader to these references [12], [13].…”

Section: Introductionmentioning

confidence: 99%

GMM Based Semi-Supervised Learning for Channel-Based Authentication Scheme

Gulati

Greenstadt

Dandekar

et al. 2013

2013 IEEE 78th Vehicular Technology Conference (VTC Fall)

Self Cite

View full text Add to dashboard Cite

Abstract-Authentication schemes based on wireless physical layer channel information have gained significant attention in recent years. It has been shown in recent studies, that the channel based authentication can either cooperate with existing higher layer security protocols or provide some degree of security to networks without central authority such as sensor networks. We propose a Gaussian Mixture Model based semi-supervised learning technique to identify intruders in the network by building a probabilistic model of the wireless channel of the network users. We show that even without having a complete apriori knowledge of the statistics of intruders and users in the network, our technique can learn and update the model in an online fashion while maintaining high detection rate. We experimentally demonstrate our proposed technique leveraging pattern diversity and show using measured channels that miss detection rates as low as 0.1% for false alarm rate of 0.4% can be achieved.

show abstract

Learning algorithm for reconfigurable antenna state selection

Cited by 6 publications

References 14 publications

Impact of pattern reconfigurable antennas on Interference Alignment over measured channels

Impact of pattern reconfigurable antennas on Interference Alignment over measured channels

A Software Defined Testbed for Reconfigurable Antenna Cognitive Radio

GMM Based Semi-Supervised Learning for Channel-Based Authentication Scheme

Contact Info

Product

Resources

About