|Wednesday, December 7|
|16:10 - 16:50|
|Keynote: CCR-K1: Maria Sabrina Greco - Cognitive Radars: Some Applications|
|16:10 - 17:30|
|CCR-1: Machine Learning for Characterization of Cognitive Communications and Radar I|
|Friday, December 9|
|10:00 - 10:40|
|Keynote: CCR-K2: Sejong Yoon - Decentralized Probabilistic Learning for Sensor Network|
|11:00 - 12:20|
|CCR-2: Machine Learning for Characterization of Cognitive Communications and Radar II|
|14:00 - 15:40|
|CCR-3: Machine Learning for Characterization of Cognitive Communications and Radar III|
This paper focuses on some applications of cognitive radars. Cognitive radars are systems based on a perception-action cycle that sense the environment and learn from it important information on the target and its background, then adapt the transmitted waveform to optimally satisfy the needs of their mission according to a desired goal. Both active and passive radars are considered, highlighting the limits and the path forward. In particular, we here consider cognitive active radars that work in spectrally dense environments and change the transmitted waveform on-the-fly to avoid interference with the primary user of the channel, such as broadcast or communication systems.
We also describe cognitive passive radars, which contrary to the active ones cannot directly change the transmitted waveforms on-the-fly but can instead select the best source of opportunity to improve the detection and tracking performance.
Distributed machine learning and large scale optimization methods are starting to play an increasing central role in wireless sensors networks and particularly in data-adaptive and data-driven contexts such as the cognitive radio. In this work we present a review of state-of-the-art machine learning techniques used in sensor network. In particular, we focus on distributed and decentralized machine learning and optimization methods for wireless sensor network and cognitive radio devices. We also introduce a series of recent developments and applications of the alternating direction method of multipliers (ADMM) approaches on the decentralized machine learning problems that can potentially be used for related cognitive radio problems.
Over the next 3-5 years demand for radio spectrum is projected to grow dramatically due to explosive growth in communication and sensing applications, while resources in terms of power and bandwidth will remain limited. The widening gap between demand and available resources is emerging as one of the major challenges for all entities sharing the electromagnetic spectrum. Cognitive Radio (CR), with its capability to sense its environment and flexibly adjust its transceiver parameters, has established itself as an enabling methodology for dynamic time-frequency-space resource allocation and management, offering significant improvement of spectral utilization. However, existing cognitive radio models will no longer be adequate, given the massive demands of emerging communications and sensing applications, including capacity, connectivity, high reliability and low latency, so novel models and algorithms are needed to help improve spectrum utilization.
A natural approach to handling these challenges is the development of a broad range of efficient machine learning algorithms, as well as new frameworks for cooperative learning and sharing, based on complex signal patterns in space, frequency and time. Proliferation of software defined radio technology, as well as applications in Self-organized Networks, Machine-to-Machine Communications, Internet of Things etc, will necessarily create even more complex environments in which CR networks of secondary users will compete for spectrum access not only with primary users, but also with other CR networks. Many of these dense multi-user cognitive radio systems would be difficult to capture using conventional machine learning models.
We recognize that characterization of cognitive communication and radar is emerging as a topic area with rich potential, high relevance and broad applicability for machine learning research and development. For instance, DARPA recently announced its Spectrum Collaboration Challenge (SC2) program, which aims at developing novel algorithms and technologies for collaborative and adaptive spectrum sharing both for military and civilian applications. This high profile initiative envisions leveraging recent advances in artificial intelligence, machine learning and cognitive communications, and is expected to spur a significant burst of interdisciplinary research in these areas over the next 3-5 years. The goal of this Symposium is to bring together researchers from the cognitive communications and machine learning communities, to raise awareness of the current trends and developments, to showcase state-of-the-art machine learning approaches to CR network problems, and to provide a forum for sharing ideas and initiating synergistic activities.
Submissions are welcome on topics including:
Prospective authors are invited to submit 6-page papers. Manuscripts should be original (not submitted/published anywhere else) and written in accordance with the standard IEEE double-column paper template. Submission is through the GlobalSIP website at http://2016.ieeeglobalsip.org/Papers.asp.
|Paper Submission Deadline|
|Review Results Announced|
|Camera-Ready Papers Due||September 30, 2016|