Federated Learning aims at training a global model from multiple decentralized devices (i.e. clients) without exchanging their private local data. A key challenge is the handling of non-i.i.d. (independent identically distributed) data across ...

We introduce localization convolutional neural networks (CNNs), a data-driven time series-based angle of arrival (AOA) localization scheme capable of coping with noise and errors in AOA estimates measured at receiver nodes. Our localization CNNs enhance ...

In recent years, convolutional neural networks (CNNs) have been successfully applied for automatic target recognition (ATR) in synthetic aperture radar (SAR) data. However, it is challenging to train a CNN with high classification accuracy when labeled ...

The use of high frequency millimeter wave (mmWave) bands at 28 GHz or higher will be a defining characteristic of next- generation wireless networks, such as 5G and 802.11ad networks. However, communicating over these high frequencies bands often requires ...

We present HF-ICA, a second-order “Hessian-free” algorithm for Infomax-ICA. Our approach achieves asymptotically quadratic convergence while retaining the memory footprint of first-order methods. Without any hyperparameter tuning, we show ...

We study embedded Binarized Neural Networks (eBNNs) with the aim of allowing current binarized neural networks (BNNs) in the literature to perform feedforward inference efficiently on small embedded devices. We focus on minimizing the required memory ...

Abstract-We propose a novel RF signal classification method based on sparse coding, an unsupervised learning method popular in computer vision. In particular, we employ a convolutional sparse coder that can extract high-level features of an unknown ...

We present a chip architecture for a compressive sensing based method that can be used in conjunction with the JTAG standard to detect IC Trojans. The proposed architecture compresses chip output resulting from a large number of test vectors applied to ...

Detecting Trojans in an integrated circuit (IC) is an important but hard problem. A Trojan is malicious hardware--it can be extremely small in size and dormant until triggered by some unknown circuit state. To allow wake-up, a Trojan could draw a ...

Continuous fine-grain status monitoring of a cloud data center enables rapid response to anomalies, but handling the resulting torrent of data poses a significant challenge. As a solution, we propose CloudSense, a new switch design that performs in-...

In a distributed sensor network, the goodness of a sensor may change according to its current device status (e.g. health of hardware) and environment (e.g. wireless reception conditions at the sensor location). As a result, it is often necessary to ...

We present FlowCode, a system that exploits network coding at the granularity of traffic flows to facilitate fault-tolerant data exchange in wireless mesh networks. Applications include multi-site data replication in adhoc environments such as mesh ...

In this paper we introduce a spectral-based method for validating sensor nodes in the field via clustering of sensors based on their measurement data. We formalize the notion of peer consistency in measurement data by introducing a notion called "sensor ...

We consider the problem of localizing wireless nodes in an outdoor, open-space environment, using ad-hoc radio ranging measurements, e.g., 802.11. We cast these ranging measurements as a set of distance constraints, thus forming an over-determined ...

We consider the problem of managing advertisements (or ads for short) for ad-hoc online videos, such as those generated by end users. We propose a novel ad selection approach based on video tags. We first compute intrinsic values of individual videotags ...

The idea that government should steer economic development by strategically picking and managing certain industries is controversial but appealing to many developing countries that are eager to upgrade their industries. I investigate the impact of ...

We consider the task of using one or more unmanned aerial vehicles (UAVs) to relay messages between two distant ground nodes. For delay-tolerant applications like latency-insensitive bulk data transfer, we seek to maximize throughput by having a UAV ...

In this thesis we explore the use of antenna selection as a new avenue of performance improvement in mobile wireless ad hoc networks. We built an Unmanned Aerial Vehicle (UAV) testbed using commodity dual-antenna 802.11 hardware and performed field ...

This thesis investigates two effective system methods for maximizing throughput in practical networks where low-altitude low-speed Unmanned Aerial Vehicles (UAVs) serve as relays for ground nodes. I consider the task of using multiple UAVs to relay ...