64 citations · 103 across the 13 of their papers we have counts for
15 papers
RAG-HAR+: Towards Cost-Efficient LLM-Based Human Activity Recognition for Edge Deployment
Hansi Karunarathna, Nirhoshan Sivaroopan, Chamara Madarasingha +2
Human Activity Recognition (HAR) from wearable sensors supports applications in healthcare, rehabilitation, fitness tracking, and smart environments. Yet, existing deep learning ap…
RAG-HAR: Retrieval Augmented Generation-based Human Activity Recognition
Nirhoshan Sivaroopan, Hansi Karunarathna, Chamara Madarasingha +2
Human Activity Recognition (HAR) underpins applications in healthcare, rehabilitation, fitness tracking, and smart environments, yet existing deep learning approaches demand datase…
A Comprehensive Survey on Network Traffic Synthesis: From Statistical Models to Deep Learning
Nirhoshan Sivaroopan, Kaushitha Silva, Chamara Madarasingha +4
Synthetic network traffic generation has emerged as a promising alternative for various data-driven applications in the networking domain. It enables the creation of synthetic data…
Lightweight Dataset for Decoy Development to Improve IoT Security
David Weissman, Anura P. Jayasumana
In this paper, the authors introduce a lightweight dataset to interpret IoT (Internet of Things) activity in preparation to create decoys by replicating known data traffic patterns…
Graph Coordinates and Conventional Neural Networks -- An Alternative for Graph Neural Networks
Zheyi Qin, Randy Paffenroth, Anura P. Jayasumana
Graph-based data present unique challenges and opportunities for machine learning. Graph Neural Networks (GNNs), and especially those algorithms that capture graph topology through…
Investigative Pattern Detection Framework for Counterterrorism
Shashika R. Muramudalige, Benjamin W. K. Hung, Rosanne Libretti +2
Law-enforcement investigations aimed at preventing attacks by violent extremists have become increasingly important for public safety. The problem is exacerbated by the massive dat…
NetDiffus: Network Traffic Generation by Diffusion Models through Time-Series Imaging
Nirhoshan Sivaroopan, Dumindu Bandara, Chamara Madarasingha +3
Network data analytics are now at the core of almost every networking solution. Nonetheless, limited access to networking data has been an enduring challenge due to many reasons in…
Reconstruction of Fragmented Trajectories of Collective Motion using Hadamard Deep Autoencoders
Kelum Gajamannage, Yonggi Park, Randy Paffenroth +1
Learning dynamics of collectively moving agents such as fish or humans is an active field in research. Due to natural phenomena such as occlusion and change of illumination, the mu…
A Pre-training Oracle for Predicting Distances in Social Networks
Gunjan Mahindre, Randy Paffenroth, Anura Jayasumana +1
In this paper, we propose a novel method to make distance predictions in real-world social networks. As predicting missing distances is a difficult problem, we take a two-stage app…
Image Denoising Using the Geodesics' Gramian of the Manifold Underlying Patch-Space
Kelum Gajamannage
With the proliferation of sophisticated cameras in modern society, the demand for accurate and visually pleasing images is increasing. However, the quality of an image captured by…
Link Dimension and Exact Construction of a Graph
Gunjan S. Mahindre, Anura P. Jayasumana
Minimum resolution set and associated metric dimension provide the basis for unique and systematic labeling of nodes of a graph using distances to a set of landmarks. Such a distan…
Network Topology Mapping from Partial Virtual Coordinates and Graph Geodesics
Anura P. Jayasumana, Randy Paffenroth, Gunjan Mahindre +2
For many important network types (e.g., sensor networks in complex harsh environments and social networks) physical coordinate systems (e.g., Cartesian), and physical distances (e.…
Network Topology Mapping from Partial Virtual Coordinates and Graph Geodesics
Anura P. Jayasumana, Randy Paffenroth, Sridhar Ramasamy
For many important network types (e.g., sensor networks in complex harsh environments and social networks) physical coordinate systems (e.g., Cartesian), and physical distances (e.…
Investigative Simulation: Towards Utilizing Graph Pattern Matching for Investigative Search
Benjamin W. K. Hung, Anura P. Jayasumana
This paper proposes the use of graph pattern matching for investigative graph search, which is the process of searching for and prioritizing persons of interest who may exhibit par…
Collaborative Applications over Peer-to-Peer Systems - Challenges and Solutions
H. M. N. Dilum Bandara, Anura P. Jayasumana
Emerging collaborative Peer-to-Peer (P2P) systems require discovery and utilization of diverse, multi-attribute, distributed, and dynamic groups of resources to achieve greater tas…