- UAV Applications and Optimization
- Distributed Control Multi-Agent Systems
- Opportunistic and Delay-Tolerant Networks
- Cooperative Communication and Network Coding
- Wireless Signal Modulation Classification
- Advanced MIMO Systems Optimization
- Mobile Ad Hoc Networks
- Underwater Vehicles and Communication Systems
- Cognitive Radio Networks and Spectrum Sensing
- Radar Systems and Signal Processing
- Reinforcement Learning in Robotics
- Speech and Audio Processing
- Privacy-Preserving Technologies in Data
- Advanced Sensor and Control Systems
- Stochastic Gradient Optimization Techniques
- Machine Learning and ELM
- Indoor and Outdoor Localization Technologies
- Caching and Content Delivery
- Image Processing Techniques and Applications
- Adversarial Robustness in Machine Learning
- Advanced Wireless Network Optimization
- Anomaly Detection Techniques and Applications
- Modular Robots and Swarm Intelligence
- Advanced SAR Imaging Techniques
- IoT Networks and Protocols
United States Air Force Research Laboratory
2013-2025
U.S. Air Force Research Laboratory Information Directorate
2021
Applied Research Laboratory at the University of Hawai‘i
2020
Science Research Laboratory
2020
Channel Autoencoders (CAEs) have shown significant potential in optimizing the physical layer of a wireless communication system for specific channel through joint end-to-end training. However, practical implementation CAEs faces several challenges, particularly realistic and dynamic scenarios. Channels systems are change with time. Still, most proposed CAE designs assume stationary scenarios, meaning they trained tested only one realization without regard nature systems. Moreover,...
In this paper, we study the problem of spectrum scarcity in a network unmanned aerial vehicles (UAVs) during mission-critical applications such as disaster monitoring and public safety missions, where pre-allocated is not sufficient to offer high data transmission rate for real-time video-streaming. scenarios, UAV can lease part terrestrial licensed exchange providing relaying service. order optimize performance prolong its lifetime, some UAVs will function relay primary while rest carry out...
The problem of decentralized multiple Point Interests (Pols) detection and associated task completion in an unknown environment with resource-constrained self-interested Unmanned Aerial Vehicles (UAVs) is studied. UAVs form several coalitions to efficiently complete the compound tasks which are impossible be performed individually. objectives such coalition formation firstly minimize resource consumption completing encountered on time, secondly enhance reliability coalitions, lastly...
Indoor localization has gained significant attention in recent years due to its various applications smart homes, industrial automation, and healthcare, especially since more people rely on their wireless devices for location-based services. Deep learning-based solutions have shown promising results accurately estimating the position of indoor environments using parameters such as Channel State Information (CSI) Received Signal Strength Indicator (RSSI). However, despite success deep...
Modulation recognition is a fundamental task in communication systems as the accurate identification of modulation schemes essential for reliable signal processing, interference mitigation coexistent technologies, and network optimization. Incorporating deep learning (DL) models into has demonstrated promising results various scenarios. However, conventional DL often fall short online dynamic contexts, particularly class incremental scenarios where new are encountered during deployment....
Barrage relay networks (BRNs) are a class of mobile ad hoc based on an autonomous cooperative communications scheme that affords distributed, rapid, and robust broadcast mechanism. BRN-based radios currently being used operationally; understanding scaling laws for BRNs can thus shed light how future systems ought be designed to address wider range military missions. It has previously been shown scale optimally traffic (in terms sum throughput latency). Furthermore, experimental evidence...
Device-to-device (D2D) communications provide efficient ways to increase spectrum utilization ratio with reduced power consumption for proximity wireless applications. In this paper, we investigate resource allocation strategies D2D underlaying cellular networks. To be specific, study the centralized algorithm controlling transmit powers of underlying pairs in order maximize weighted sum-rate while guaranteeing quality service (QoS) requirements both and users (CUs). A novel DC (difference...
In this paper we introduce XLayer, a cross-layer communications substrate for tactical Information Management Systems which enable nodes on radio network to seamlessly communicate with different heterogeneous networks. While conventional strategies environments tend focus the localized optimization between neighbor layers of stack, our approach focuses interface middleware and underlying infrastructure. The XLayer leverages native information services available at infrastructure improve...
Maintaining constant communication between mobile entities distributed across a large geographical area is crucial task for many commercial and military applications. For example when troops are deployed in hostile or sensor deprived environments, maintaining radio contact with base station would increase the efficiency of coordinating deployment, yet communications should not interfere primary tasks these entities. The BioAIR system was developed to coordinate airborne nodes such as...
Power control plays an important role in improving the system throughput communication since co-channel interference is a major limitation to throughput. The power problem of maximizing multiuser and multichannel highly complicated nonconvex user are interfered with one another if operating same wireless channel. We reformulate objective function this as difference two convex functions, which called DC (difference function) programming. To reduce computation complexity high dimensional...
Indoor localization has gained significant attention in recent years due to its various applications smart homes, industrial automation, and healthcare, especially since more people rely on their wireless devices for location-based services. Deep learning-based solutions have shown promising results accurately estimating the position of indoor environments using parameters such as Channel State Information (CSI) Received Signal Strength Indicator (RSSI). However, despite success deep...
Deep neural networks (DNNs) are being increasingly used to achieve signal awareness. Usually, DNNs have been entirely executed at the mobile device. However, as become more complex, edge computing techniques will necessary for DNN deployment. Notably, it has shown that original architectures can be modified by introducing a "bottleneck" producing compressed representation of input. The split computation is then orchestrated between device and edge, which respectively execute layers before...
Mobile edge caching (MEC) has been introduced to support ever-growing end-users' needs. To reduce the backhaul traffic demand and content delivery latency, cache-enabled servers at base stations (BSs) are employed provision popular contents network edge. In this paper, multiple-input-multiple-output (MIMO) operation user association policy linked underlying cache placement strategy ensure a good trade-off between load balancing taking into account wireless channel finite capacity servers....
The Bio-inspired Autonomous Infrastructure Monitoring (BioAIM) system detects anomalous behavior during the deployment and maintenance of a wireless communication network formed autonomously by unmanned airborne nodes. A node may experience or unexpected in presence hardware/software faults/failures, external influence (e.g. natural weather phenomena, enemy threats). This detects, reasons with differentiates an anomaly from interference), alerts human operator anomalies at runtime via...
In this work, we demonstrate the interference mitigation capabilities of auxiliary vector (AV) receiver for scalable video transmission over direct-sequence code division multiple access (DS-CDMA) systems using a hardware testbed. The proposed design is also compared to conventional RAKE matched-filter (RAKE-MF) and minimum variance distortionless response (MVDR) receivers. DS-CDMA data stream transmitted an RF channel under ''real world'' Rayleigh-faded multipath conditions, emulating open...
This position paper introduces a Dynamic Data Driven Open Radio Access Network System (3D-O-RAN). The key objective of 3D-O-RAN is to support congested, contested and contaminated tactical settings where multimedia sensors, application constraints operating wireless conditions may frequently change over space, time frequency. compliant with the O-RAN specification for beyond 5G cellular systems reduce costs guarantee interoperability among vendors. Moreover, integrates computational,...
Communications systems are increasingly demanding, in terms of throughput, latency, and security requirements. To combat this, a complex system radio access networks, each with unique dynamic performance characteristics has evolved to support modern communications. These advancements, however, bring new interesting challenges when tuning the network meet specific requirements for supported application data flow. Here, we propose two developments this challenge. First, analytical models that...