Publications (18)
Bayesian Federated Neural Matching that Completes Full Information
Peng Xiao, Samuel Cheng
Federated learning is a contemporary machine learning paradigm where locally trained models are distilled into a global model. Due to the intrinsic permutation invariance of neural…
How likely is a random graph shift-enabled?
Liyan Chen, Samuel Cheng, Vladimir Stankovic +1
The shift-enabled property of an underlying graph is essential in designing distributed filters. This article discusses when a random graph is shift-enabled. In particular, popular…
Pancreatic Tumor Segmentation as Anomaly Detection in CT Images Using Denoising Diffusion Models
Reza Babaei, Samuel Cheng, Theresa Thai +1
Despite the advances in medicine, cancer has remained a formidable challenge. Particularly in the case of pancreatic tumors, characterized by their diversity and late diagnosis, ea…
Neural Network for NILM Based on Operational State Change Classification
Peng Xiao, Samuel Cheng
Energy disaggregation in a non-intrusive way estimates appliance level electricity consumption from a single meter that measures the whole house electricity demand. Recently, with…
Zero-error Slepian-Wolf Coding of Confined Correlated Sources with Deviation Symmetry
Rick Ma, Samuel Cheng
In this paper, we use linear codes to study zero-error Slepian-Wolf coding of a set of sources with deviation symmetry, where the sources are generalization of the Hamming sources…
Implementing distributed graph filters by elementary matrix decomposition
Samuel Cheng
In this letter, we consider the implementation problem of distributed graph filters, where each node only has access to the signals of the current and its neighboring nodes. By usi…
Water Mapping and Change Detection Using Time Series Derived from the Continuous Monitoring of Land Disturbance Algorithm
Huong Pham, Samuel Cheng, Tao Hu +1
Given the growing environmental challenges, accurate monitoring and prediction of changes in water bodies are essential for sustainable management and conservation. The Continuous…
Shift-enabled graphs: Graphs where shift-invariant filters are representable as polynomials of shift operations
Liyan Chen, Samuel Cheng, Vlandimir Stankovic +1
In digital signal processing, shift-invariant filters can be represented as a polynomial expansion of a shift operation,that is, the Z-transform representation. When extended to gr…
Decomposition Approach for Low-rank Matrix Completion
Rick Ma, Samuel Cheng
In this paper, we describe a low-rank matrix completion method based on matrix decomposition. An incomplete matrix is decomposed into submatrices which are filled with a proposed t…
Probabilistic Federated Learning of Neural Networks Incorporated with Global Posterior Information
Peng Xiao, Samuel Cheng
In federated learning, models trained on local clients are distilled into a global model. Due to the permutation invariance arises in neural networks, it is necessary to match the…
The Star-Planet Activity Research CubeSat (SPARCS): Determining Inputs to Planetary Habitability
David R. Ardila, Evgenya Shkolnik, Paul Scowen +19
Seventy-five billion low-mass stars in our galaxy host at least one small planet in their habitable zone (HZ). The stellar ultraviolet (UV) radiation received by the planets is str…
Onboard Dynamic Image Exposure Control for the Star-Planet Activity Research CubeSat (SPARCS)
Tahina Ramiaramanantsoa, Judd D. Bowman, Evgenya L. Shkolnik +19
The Star-Planet Activity Research CubeSat (SPARCS) is a 6U CubeSat under development to monitor the flaring and chromospheric activity of M dwarfs at near-ultraviolet (NUV) and far…
Hamming Code for Multiple Sources
Rick Ma, Samuel Cheng
We consider Slepian-Wolf (SW) coding of multiple sources and extend the packing bound and the notion of perfect code from conventional channel coding to SW coding with more than tw…
Binary Rate Distortion With Side Information: The Asymmetric Correlation Channel Case
Andrei Sechelea, Samuel Cheng, Adrian Munteanu +1
Advancing over up-to-date information theoretic results that assume symmetric correlation models, in this work we consider the problem of lossy binary source coding with side infor…
Time-Resolved Photometry of the High-Energy Radiation of M Dwarfs with the Star-Planet Activity Research CubeSat (SPARCS)
Tahina Ramiaramanantsoa, Judd D. Bowman, Evgenya L. Shkolnik +18
Know thy star, know thy planet,... especially in the ultraviolet (UV). Over the past decade, that motto has grown from mere wish to necessity in the M dwarf regime, given that the…
Undirected graphs: is the shift-enabled condition trivial or necessary?
Liyan Chen, Samuel Cheng, Kanghang He +2
It has recently been shown that, contrary to the wide belief that a shift-enabled condition (necessary for any shift-invariant filter to be representable by a graph shift matrix) c…
Delta-doped Electron Multiplying CCDs for FIREBall-2
Gillian Kyne, Erika T. Hamden, Shouleh Nikzad +11
We present the status of on-going detector development efforts for our joint NASA/CNES balloon-borne UV multi-object spectrograph, the Faint Intergalactic Redshifted Emission Ballo…
Capsule networks with non-iterative cluster routing
Zhihao Zhao, Samuel Cheng
Capsule networks use routing algorithms to flow information between consecutive layers. In the existing routing procedures, capsules produce predictions (termed votes) for capsules…