The University of Maryland, College Park, founded in 1856, is a distinguished public research university. It is the largest university in Maryland and the Washington metropolitan area, and is located nine miles from downtown Washington, D.C. It is a public research university offering over 200 degree-granting programs across its eleven schools and colleges, attracting top students and renowned faculty from around the world. It is known for its innovative and challenging academic programs, strong research opportunities, and a vibrant multicultural community. NEC Labs America collaborates with the University of Maryland, College Park, on research spanning edge AI, distributed systems, machine learning interpretability, learning with limited labels, domain adaptation, and continual learning. Our research improves model generalization in dynamic conditions. We jointly study robust inference, communication-efficient federated learning, and privacy-aware analytics for large-scale deployments. Please read about our latest news and collaborative publications with the University of Maryland, College Park.

Posts

Efficient Semantic Communication Through Transformer-Aided Compression

Transformers, known for their attention mechanisms, have proven highly effective in focusing on critical elements within complex data. This feature can effectively be used to address the time-varying channels in wireless communication systems. In this work, we introduce a channel-aware adaptive framework for semantic communication, where different regions of the image are encoded and compressed based on their semantic content. By employing vision transformers, we interpret the attention mask as a measure of the semantic contents of the patches and dynamically categorize the patches to be compressed at various rates as a function of the instantaneous channel bandwidth. Our method enhances communication efficiency by adapting the encoding resolution to the content’s relevance, ensuring that even in highly constrained environments, critical information is preserved. We evaluate the proposed adaptive transmission framework using the TinyImageNet dataset, measuring both reconstruction quality and accuracy. The results demonstrate that our approach maintains high semantic fidelity while optimizing bandwidth, providing an effective solution for transmitting multiresolution data in limited bandwidth conditions.

Deep Learning-Based Real-Time Quality Control of Standard Video Compression for Live Streaming

Ensuring high-quality video content for wireless users has become increasingly vital. Nevertheless, maintaining a consistent level of video quality faces challenges due to the fluctuating encoded bitrate, primarily caused by dynamic video content, especially in live streaming scenarios. Video compression is typically employed to eliminate unnecessary redundancies within and between video frames, thereby reducing the required bandwidth for video transmission. The encoded bitrate and the quality of the compressed video depend on encoder parameters, specifically, the quantization parameter (QP). Poor choices of encoder parameters can result in reduced bandwidth efficiency and high likelihood of non-conformance. Non-conformance refers to the violation of the peak signal-to-noise ratio (PSNR) constraint for an encoded video segment. To address these issues, a real-time deep learning-based H.264 controller is proposed. This controller dynamically estimates the optimal encoder parameters based on the content of a video chunk with minimal delay. The objective is to maintain video quality in terms of PSNR above a specified threshold while minimizing the average bitrate of the compressed video. Experimental results, conducted on both QCIF dataset and a diverse range of random videos from public datasets, validate the effectiveness of this approach. Notably, it achieves improvements of up to 2.5 times in average bandwidth usage compared to the state-of-the-art adaptive bitrate video streaming, with a negligible non-conformance probability below 10?2.

Deep Learning-Based Real-Time Rate Control for Live Streaming on Wireless Networks

Providing wireless users with high-quality video content has become increasingly important. However, ensuring consistent video quality poses challenges due to variable encodedbitrate caused by dynamic video content and fluctuating channel bitrate caused by wireless fading effects. Suboptimal selection of encoder parameters can lead to video quality loss due to underutilized bandwidth or the introduction of video artifacts due to packet loss. To address this, a real-time deep learning-based H.264 controller is proposed. This controller leverages instantaneous channel quality data driven from the physical layer, along with the video chunk, to dynamically estimate the optimal encoder parameters with a negligible delay in real-time. The objective is to maintain an encoded video bitrate slightly below the available channel bitrate. Experimental results, conducted on both QCIF dataset and a diverse selection of random videos from public datasets, validate the effectiveness of the approach. Remarkably, improvements of 10-20 dB in PSNR with respect to the state-of-the art adaptive bitrate video streaming is achieved, with an average packet drop rate as low as 0.002.

Blind Cyclic Prefix-based CFO Estimation in MIMO-OFDM Systems

Low-complexity estimation and correction of carrier frequency offset (CFO) are essential in orthogonal frequency division multiplexing (OFDM). In this paper, we propose a low overhead blind CFO estimation technique based on cyclic prefix (CP), in multi-input multi-output (MIMO)-OFDM systems. We propose to use antenna diversity for CFO estimation. Given that the RF chains for all antenna elements at a communication node share the same clock, the carrier frequency offset (CFO) between two points may be estimated by using the combination of the received signal at all antennas. We improve our method by combining the antenna diversity with time diversity by considering the CP for multiple OFDM symbols. We provide a closed-form expression for CFO estimation and present algorithms that can considerably improve the CFO estimation performance at the expense of a linear increase in computational complexity. We validate the effectiveness of our estimation scheme via extensive numerical analysis.

Channel Reciprocity Calibration for Hybrid Beamforming in Distributed MIMO Systems

Time Division Duplex (TDD)-based distributed massive MIMO systems are envisioned as candidate solution for the physical layer of 6G multi-antenna systems supporting cooperative hybrid beamforming that heavily relies on the obtained uplink channel estimates for efficient coherent downlink precoding. However, due to the hardware impairment between the transmitter and the receiver, full channel reciprocity does not hold between the downlink and uplink direction. Such reciprocity mismatch deteriorates the performance of mm-Wave hybrid beamforming and has to be estimated and compensated for, to avoid performance degradation in the co-operative hybrid beamforming. In this paper, we address the channel reciprocity calibration between any two nodes at two levels. We decompose the problem into two sub-problems. In the first sub-problem, we calibrate the digital chain, i.e. obtain the mismatch coefficients of the (DAC/ADC) up to a constant scaling factor. In the second subproblem, we obtain the (PA/LNA) mismatch coefficients. At each step, we formulate the channel reciprocity calibration as a least square optimization problem that can efficiently be solved via conventional methods such as alternative optimization with high accuracy. Finally, we verify the performance of our channel reciprocity calibration approach through extensive numerical experiments.

Codebook Design for Hybrid Beamforming in 5G Systems

Massive MIMO and hybrid beamforming are among the key physical layer technologies for the next generation wireless systems. In the last stage of the hybrid beamforming, the goal is to generate sharp beam with maximal and preferably uniform gain. We highlight the shortcomings of uniform linear arrays (ULAs) in generating such perfect beams, i.e., beams with maximal uniform gain and sharp edges, and propose a solution based on a novel antenna configuration, namely, twin-ULA (TULA). Consequently, we propose two antenna configurations based on TULA: Delta and Star. We pose the problem of finding the beamforming coefficients as a continuous optimization problem for which we find the analytical closed-form solution by a quantization/aggregation method. Thanks to the derived closed-form solution the beamforming coefficients can be easily obtained with low complexity. Through numerical analysis, we illustrate the effectiveness of the proposed antenna structure and beamforming algorithm to reach close-to-perfect beams.

Codebook Design for Composite Beamforming in Next-generation mmWave Systems

In pursuance of the unused spectrum in higher frequencies, millimeter wave (mmWave) bands have a pivotal role. However, the high path-loss and poor scattering associated with mmWave communications highlight the necessity of employing effective beamforming techniques. In order to efficiently search for the beam to serve a user and to jointly serve multiple users it is often required to use a composite beam which consists of multiple disjoint lobes. A composite beam covers multiple desired angular coverage intervals (ACIs) and ideally has maximum and uniform gain (smoothness) within each desired ACI, negligible gain (leakage) outside the desired ACIs, and sharp edges. We propose an algorithm for designing such ideal composite codebook by providing an analytical closed-form solution with low computational complexity. There is a fundamental trade-off between the gain, leakage and smoothness of the beams. Our design allows to achieve different values in such trade-off based on changing the design parameters. We highlight the shortcomings of the uniform linear arrays (ULAs) in building arbitrary composite beams. Consequently, we use a recently introduced twin-ULA (TULA) antenna structure to effectively resolve these inefficiencies. Numerical results are used to validate the theoretical findings.

Codebook Design for Composite Beamforming in Next generation mmWave Systems

In pursuance of the unused spectrum in higher frequencies, millimeter wave (mmWave) bands have a pivotal role. However, the high path loss and poor scattering associated with mmWave communications highlight the necessity of employing effective beamforming techniques. In order to efficiently search for the beam to serve a user and to jointly serve multiple users it is often required to use a composite beam which consists of multiple disjoint lobes. A composite beam covers multiple desired angular coverage intervals (ACIs) and ideally has maximum and uniform gain (smoothness) within each desired ACI, negligible gain (leakage) outside the desired ACIs, and sharp edges. We propose an algorithm for designing such ideal composite codebook by providing an analytical closed form solution with low computational complexity. There is a fundamental trade off between the gain, leakage and smoothness of the beams. Our design allows to achieve different values in such trade off based on changing the design parameters. We highlight the shortcomings of the uniform linear arrays (ULAs) in building arbitrary composite beams. Consequently, we use a recently introduced twin ULA (TULA) antenna structure to effectively resolve these inefficiencies. Numerical results are used to validate the theoretical findings.

Conditional GAN with Discriminative Filter Generation for Text-to-Video Synthesis

Developing conditional generative models for text-to-video synthesis is an extremely challenging yet an important topic of research in machine learning. In this work, we address this problem by introducing Text-Filter conditioning Generative Adversarial Network (TFGAN), a conditional GAN model with a novel multi-scale text-conditioning scheme that improves text-video associations. By combining the proposed conditioning scheme with a deep GAN architecture, TFGAN generates high quality videos from text on challenging real-world video datasets. In addition, we construct a synthetic dataset of text-conditioned moving shapes to systematically evaluate our conditioning scheme. Extensive experiments demonstrate that TFGAN significantly outperforms existing approaches, and can also generate videos of novel categories not seen during training.