The introduction of massive MIMO (Multiple Input Multiple Output) communication systems enables base stations (BS) to perform beamforming for enhancing communication reliability. A typical key assumption, however, is the availability of accurate downlink channel state information (CSI). In practice, CSI estimation and reporting delays coupled with the process of channel aging result in the BS receiving outdated CSI information, which in turn impacts the system's spectral efficiency. To combat this latency, this paper develops efficient methods of CSI prediction that preemptively predict future downlink CSI based on historical data. We leverage the spatial and temporal correlation properties of the channel and use explicit feature extraction frameworks for both dimensions to accurately predict future CSI. We analyze combinations of spatial and temporal feature extractors in terms of a tradeoff between performance and latency. We evaluate the performance of the proposed prediction model in terms of proximity to the ground truth, prediction latency, and model footprint. Our experiments show that our method outperforms classical statistical methods as well as existing CSI prediction baselines.

In recent years, machine learning (ML) methods have become increasingly popular in wireless communication systems for several applications. A critical bottleneck for designing ML systems for wireless communications is the availability of realistic wireless channel datasets, which are extremely resource-intensive to produce. To this end, the generation of realistic wireless channels plays a key role in the subsequent design of effective ML algorithms for wireless communication systems. Generative models have been proposed to synthesize channel matrices, but outputs produced by such methods may not correspond to geometrically viable channels and do not provide any insight into the scenario being generated. In this work, we aim to address both these issues by integrating established parametric, physics-based geometric channel (PPGC) modeling frameworks with generative methods to produce realistic channel matrices with interpretable representations in the parameter domain. We show that the generative model converges to prohibitively suboptimal stationary points when learning the underlying prior directly over the parameters due to the non-convex PPGC model. To address this limitation, we propose a linearized reformulation of the problem to ensure smooth gradient flow during generative model training, while also providing insights into the underlying physical environment. We evaluate our model against prior baselines by comparing the generated, scenario-specific samples in terms of the 2-Wasserstein distance and through its utility when used for downstream compression tasks.

The ubiquitous deployment of 4G/5G technology has made it a critical infrastructure for society that will facilitate the delivery and adoption of emerging applications and use cases (extended reality, automation, robotics, to name but a few). These new applications require high throughput and low latency in both uplink and downlink for optimal performance, while coexisting with traditional downlink-heavy consumer applications. Successfully supporting these new use cases hinges on the network being able to allocate resources as efficiently as possible. In this paper, we utilize a 3GPP-compliant 5G testbed to analyze the limitations of legacy network resource allocation methods, which are based on instantaneous channel measurements, and examine the effect on throughput – a key performance indicator. We then propose a framework that allows resource allocation decisions to leverage predictions of network quality (computed at the connected devices), and study two different prediction methods that provide different degrees of reliability. We further validate our framework with real-world cellular data and demonstrate that with accurate channel metric forecast knowledge, the mean network throughput can improve by a factor of $\sim 1.8$ over the baseline reactive approach based on best CQI policy, for the considered scenario.

The new applications enabled by the 5G new radio (NR) use cases require novel solutions capable of supporting high end-user data rates at low latency. To meet these needs, it is critical to have accurate channel state information at the receiver. This requires sending a large number of reference signals which scales up with the number of users and layers, thereby introducing significant overhead that eventually impacts the system's spectral efficiency. This paper introduces a new downlink data structure that is free from demodulation reference signals, and does not require channel estimation at the receiver. The proposed structure involves a repetition step of part of the user data across the time-frequency grid. Exploiting the repetition structure at the receiver, it is shown that reliable recovery is possible via canonical correlation analysis (CCA). This paper also proposes two effective mechanisms for optimizing the CCA performance in OFDM systems, one for repetition pattern selection and another to deal with the severe frequency selectivity issues. The proposed approach provides rigorous recovery guarantees, exhibits favorable complexity-performance tradeoff, and is shown to be robust to high interference scenarios, thus rendering it appealing for practical implementation. The paper provides simulation results, using a 3GPP link-level testbench, that demonstrate the feasibility of the proposed approach.

In this work, we propose a deep learning approach for jointly compressing and denoising the CSI feedback in massive MIMO systems. We consider a practical scenario where only noisy CSI is available for training and inference. To jointly denoise and compress the CSI feedback for improved reconstruction quality without having access to true CSI, we propose a novel generic loss function based on the Stein's unbiased risk estimator (SURE) for unsupervised denoising, and the evidence lower bound (ELBO) for CSI compression. This is in contrast to most existing supervised denoising methods that either require knowledge of the true CSI or are limited to high SNR regimes. Empirically, we show that the proposed approach improves the reconstruction quality of the state-of-the-art method. Moreover, the proposed approach is independent of the choice of the encoder-decoder architecture and can be easily extended to the existing volume of work on this topic.

To compensate for the path losses in millimeter wave (mmWave) communication, multiple-input-multiple-output (MIMO) systems leverage beamforming-based solutions to boost the received SNR. Since beamforming requires knowledge of the wireless channel, its performance is also closely tied with the channel estimation accuracy. In mmWave communication, wireless channels are known to have only a few dominant paths. Several channel estimation methods leverage this characteristic by either using low-rank methods or by modeling element-wise sparsity of channels in angular domain. In this work we propose that the channel in angular domain is better characterized as group sparse rather than element-wise sparse. We further leverage the recent advancements in implicit regularization with gradient descent to develop a non-convex formulation that implicitly enforces group sparsity without additional regularization terms. We further compare the performance of the proposed approach against existing low rank or sparsity based matrix completion methods for channel estimation.

Hybrid beamforming has evolved as a promising technology that offers the balance between system performance and design complexity in mmWave MIMO systems. Existing hybrid beamforming methods either impose unit-modulus constraints or a codebook constraint on the analog precoders/combiners, which in turn results in a performance-overhead tradeoff. This paper puts forth a tensor framework to handle the wideband hybrid beamforming problem, with Vandermonde constraints on the analog precoders/combiners. The proposed method strikes the balance between performance, overhead and complexity. Numerical results on a 3GPP link-level test bench reveal the efficacy of the proposed approach relative to the codebook-based method while attaining the same feedback overhead. Moreover, the proposed method is shown to achieve comparable performance to the unit-modulus approaches, with substantial reductions in overhead.

This paper proposes a method to compute camera 6 DoF poses to achieve a user defined coverage. The camera placement problem is modeled as a combinatorial optimization where given the maximum number of cameras, a camera set is selected from a larger pool of possible camera poses. We propose to minimize the squared error between the desired and the achieved coverage, and formulate the non-linear cost function as a mixed integer linear programming problem. A camera lens model is utilized to project the camera's view on a 3D voxel map to compute a coverage score which makes the optimization problem in real environments tractable. Experimental results in two real retail store environments demonstrate the better performance of the proposed formulation in terms of coverage and overlap for triangulation compared to existing methods.

Generating a video from a textual input is a challenging research topic that would have a variety of applications in industries such as retail, e-commerce, online entertainment, education etc. In this paper, we discuss the application of generating videos of a human subject in a desired outfit using an input video of the subject. We present a two stage solution, wherein at the first stage a generative model is learned such that, given the subject's image and a textual description of the outfit, a corresponding image of the subject in the described outfit is synthesized. At the second stage, all the frames of the subject's video are individually processed by the stage 1 model to generate corresponding frames and an optical flow based post processing step is performed to maintain visual coherence across the generated frames. Towards the stage-1 objective, multiple supervised and unsupervised convolutional neural network (CNN) based generative models have been proposed. A novel approach to inject an external masking layer that maintains the structural integrity of the generated images is also presented. We train and test the different methods on the publicly available multi-view clothing image data-set and the performance in videos is showcased on a set of real-world commercial videos. The experiments show the efficacy of our approach in generating images/videos in both low (64 × 64) and high (256 × 256) resolutions.

In this letter, we discuss the problem of unsupervised clustering of sensor signals based on their information content. In the past, the problem has been formulated as a matrix factorization problem and has been solved with different variants of gradient descent. We reformulate the nonconvex cost function as a mixed integer linear programing problem with explicit clustering constraints and solve it with branch and bound, while introducing a scalable variant to reduce the computational time. The proposed method is applied to clustering problems in hyperspectral imaging and multiview image clustering and extensive results have been presented demonstrating the superiority of the novel framework over existing alternatives.

In this work we derive a novel clustering scheme for hyperspectral pixels according to the material they sense. We utilize statistical correlations that pixels sensing the same material exhibit. Specifically, kernel learning is combined with a norm-one regularized canonical correlations framework that can perform data clustering on nonlinearly dependent data. To tackle the derived minimization formulation we employ gradient descent iterations that enable a computationally efficient determination of proper sparse clustering matrices. Extensive numerical tests on real hyperspectral images reveal that the proposed approach, in spite of being unsupervised, can outperform existing supervised and unsupervised techniques especially in the presence of missing pixels that may be caused by malfunctioning in the data acquisition system.