Search for: All records

Multiple visions of 6G networks elicit Artificial Intelligence (AI) as a central, native element. When 6G systems are deployed at a large scale, end-to-end AI-based solutions will necessarily have to encompass both the radio and the fiberoptical domain. This paper introduces the Decentralized Multi- Party, Multi-Network AI (DMMAI) framework for integrating AI into 6G networks deployed at scale. DMMAI harmonizes AI-driven controls across diverse network platforms and thus facilitates networks that autonomously configure, monitor, and repair themselves. This is particularly crucial at the network edge, where advanced applications meet heightened functionality and security demands. The radio/optical integration is vital due to the current compartmentalization of AI research within these domains, which lacks a comprehensive understanding of their interaction. Our approach explores multi-network orchestration and AI control integration, filling a critical gap in standardized frameworks for AI-driven coordination in 6G networks. The DMMAI framework is a step towards a global standard for AI in 6G, aiming to establish reference use cases, data and model management methods, and benchmarking platforms for future AI/ML solutions. 

This paper presents findings from an extensive 28 GHz mmWave measurement campaign conducted in New York City. The study includes over 20 million power measurements collected from two key scenarios: around-corner (non-line-ofsight due to building blockages) and same-street (nominally lineof-sight without obstructions from street furniture or foliage), covering over 1,300 unique links. For urban macro-cell (UMa) rooftop base stations above local clutter, the dominant angle of arrival (AoA) deviates by only 2 to 3.5 degrees from the direct transmitter/receiver direction. This small deviation allows for effective spatial separation between users, facilitating the future development of Multi-User MIMO algorithms for Beyond5G networks. In the urban micro-cell (UMi) dataset, with base stations below local clutter, a path gain drop of over 20 dB was observed in around-corner segments just 20 meters into a corner. Our Street-Clutter-NLOS path loss model achieves an RMSE of 6.4 dB, compared to 11.9 dB from NLOS 3GPP models. Using the best path loss model to estimate coverage for 90% of users traveling around corners, downlink rates could drop by over 10 times after 50 meters, highlighting the challenges in maintaining consistent user experience over mmWave networks in urban street canyons. 

The rapid advancement of deepfake technology presents significant challenges for video authenticity verification, necessitating robust detection mechanisms. This paper introduces a novel framework for deepfake video detection that integrates the Multi-Scale Spectral-Guided Graph Attention Network (MSG-GAT) with the Lightweight Assimilation-Elimination (Lite-ASEL) algorithm. By representing video frames as graphs, the framework effectively captures intricate pixel relationships, enabling the detection of subtle manipulations with enhanced precision. Additionally, the Lite-ASEL algorithm is employed for feature selection, balancing reduced computational complexity with high detection performance. Experimental results demonstrate the superiority of the proposed framework, achieving state-of-theart performance with an AUC of 99.1% and a detection accuracy of 99.3%. Furthermore, hyperparameter tuning confirms the framework’s robustness and efficiency, consistently achieving an optimal objective score of 98.54%, validating its effectiveness for optimal feature selection and deepfake detection. 

The Software-Defined Networking (SDN) paradigm has significantly improved network efficiency by integrating machine learning (ML) capabilities into the control plane (CP). This integration allows adaptive management of network resources in response to dynamic traffic conditions. However, the significant geographical distance between the CP and data plane (DP) causes considerable round-trip latency, measured in milliseconds, which poses a major challenge to time-sensitive traffic. To address this challenge, our research proposes a novel in-network Reinforcement Learning (RL) inference framework. This framework extends programmability from the CP to the DP, enabling timely and precise control of network resources to meet the stringent Quality of Service (QoS) requirements of mission-critical applications. The in-network RL inference is implemented using match-action tables within the Protocol Independent Switch Architecture (PISA) framework in the DP and validated through hardware deployment of protocol-independent packet processors (P4). To allocate bandwidth precisely based on QoS requirements, a P4 meter extern is used to differentiate the unique demands of individual traffic flows. Our enhanced deepdeterministic policy gradient (eDDPG)-based RL inference achieves superior performance with minimal processing overhead, reducing latency by 88.7% and jitter by 89.1% compared to systems without RL inference. 

Accurate modeling of the gain spectrum in erbium-doped fiber amplifiers (EDFAs) is essential for optimizing optical network performance, particularly as networks evolve toward multi-vendor solutions. In this work, we propose a generalized few-shot transfer learning architecture based on a semi-supervised self-normalizing neural network (SS-NN) that leverages internal EDFA features—such as VOA input/output power and attenuation—to improve gain spectrum prediction. Our SS-NN model employs a two-phase training strategy comprising unsupervised pre-training with noise-augmented measurements and supervised fine-tuning with a custom-weighted MSE loss. Furthermore, we extend the framework with transfer learning (TL) techniques that enable both homogeneous (same-feature space) and heterogeneous (different-feature sets) model adaptation across booster, pre-amplifier, and ILA EDFAs. To address feature mismatches in heterogeneous TL, we incorporate a covariance matching loss to align second-order feature statistics between the source and target domains. Extensive experiments conducted across 26 EDFAs in the COSMOS and Open Ireland testbeds demonstrate that the proposed approach significantly reduces the number of measurement requirements on the system while achieving lower mean absolute errors and improved error distributions compared to benchmark methods. 

In order to enable the simultaneous transmission and reception of wireless signals on the same frequency, a fullduplex (FD) radio must be capable of suppressing the powerful self-interference (SI) signal emitted from the transmitter and picked up by the receiver. Critically, a major bottleneck in wideband FD deployments is the need for adaptive SI cancellation (SIC) that would allow the FD wireless system to achieve strong cancellation across different settings with distinct electromagnetic environments. In this work, we evaluate the performance of an adaptive wideband FD radio in three different locations and demonstrate that it achieves strong SIC in every location across different bandwidths. 

Recent advances in Visual Language Models (VLMs) have significantly enhanced video analytics. VLMs capture complex visual and textual connections. While Convolutional Neural Networks (CNNs) excel in spatial pattern recognition, VLMs provide a global context, making them ideal for tasks like complex incidents and anomaly detection. However, VLMs are much more computationally intensive, posing challenges for large-scale and real-time applications. This paper introduces EdgeCloudAI, a scalable system integrating VLMs and CNNs through edge-cloud computing. Edge- CloudAI performs initial video processing (e.g., CNN) on edge devices and offloads deeper analysis (e.g., VLM) to the cloud, optimizing resource use and reducing latency. We have deployed EdgeCloudAI on the NSF COSMOS testbed in NYC. In this demo, we will demonstrate EdgeCloudAI’s performance in detecting user-defined incidents in real-time.