11 February 2021 in IEEE Wireless Communications Letters
The Hybrid Non-Orthogonal Multiple Access (NOMA) is a promising candidate for multiple access techniques of future wireless communication, which integrates orthogonal multiple access and traditional NOMA. The performance of hybrid NOMA systems depends on resource allocation including power and channel. In this letter, we focus on the channel assignment. Since channel assignment needs to be adapted to a real-time changing environment and accomplished in a restricted time slot, we treat the optimization of the dynamic channel assignment problem as a deep reinforcement learning task, to achieve better environmental adaptability with low time complexity. Simulation results show that the proposed method achieves better performance in terms of sum rate and spectral efficiency, compared to conventional methods.
23 January 2013 in IEEE Transactions on Signal Processing
Matrix Joint Diagonalization (MJD) is a powerful approach for solving the Blind Source Separation (BSS) problem. It relies on the construction of matrices which are diagonalized by the unknown demixing matrix. Their joint diagonalizer serves as a correct estimate of this demixing matrix only if it is uniquely determined. Thus, a critical question is under what conditions is a joint diagonalizer unique. In the present work we fully answer this question about the identifiability of MJD based BSS approaches and provide a general result on uniqueness conditions of matrix joint diagonalization. It unifies all existing results which exploit the concepts of non-circularity, non-stationarity, non-whiteness, and non-Gaussianity. As a corollary, we propose a solution for complex BSS, which can be formulated in closed form in terms of an eigen and a singular value decomposition of two matrices.
5 June 2019 in IEEE Transactions on Pattern Analysis and Machine Intelligence
This work studies the problem of learning appropriate low dimensional image representations. We propose a generic algorithmic framework, which leverages two classic representation learning paradigms, i.e., sparse representation and the trace quotient criterion, to disentangle underlying factors of variation in high dimensional images. Specifically, we aim to learn simple representations of low dimensional, discriminant factors by applying the trace quotient criterion to well-engineered sparse representations. We construct a unified cost function, coined as the SPARse LOW dimensional representation (SparLow) function, for jointly learning both a sparsifying dictionary and a dimensionality reduction transformation. The SparLow function is widely applicable for developing various algorithms in three classic machine learning scenarios, namely, unsupervised, supervised, and semi-supervised learning. In order to develop efficient joint learning algorithms for maximizing the SparLow function, we deploy a framework of sparse coding with appropriate convex priors to ensure the sparse representations to be locally differentiable. Moreover, we develop an efficient geometric conjugate gradient algorithm to maximize the SparLow function on its underlying Riemannian manifold. Performance of the proposed SparLow algorithmic framework is investigated on several image processing tasks, such as 3D data visualization, face/digit recognition, and object/scene categorization.
6 September 2012 in Signal Processing