Research

Publications

• S. Das, N. NaderiAlizadeh, A. Ribeiro, "State-Augmented Opportunistic Routing in Wireless Communication Systems with Graph Neural Networks”, ICASSP 2025- IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India.  

https://ieeexplore.ieee.org/abstract/document/10888417

• S. Das, N. NaderiAlizadeh, R. Mangharam, A. Ribeiro, "Opportunistic Routing in Wireless Communications via Learnable State-Augmented Policies”, arXiv:2503.03736v1.  

https://arxiv.org/abs/2503.03736

• S. Das, N. NaderiAlizadeh, A. Ribeiro, "Learning State-Augmented Policies for Information Routing in Communication Networks”, IEEE Transactions on Signal Processing.

https://ieeexplore.ieee.org/abstract/document/10795656

• S. Das, N. NaderiAlizadeh, A. Ribeiro, "State-Augmented Information Routing In Communication Systems With Graph Neural Networks”, ICASSP 2024- IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, South Korea.  

https://ieeexplore.ieee.org/document/10447843

• S. Das, U. R. Jena, "Texture classification using combination of LBP and GLRLM features along with KNN and multiclass SVM classification", Proc. IEEE Conf. CCIS, pp. 115-119, India, Nov. 2016.  

https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7878212 

• S. Das, A. Venkatakrishnan, H. Yamamoto, G. P. Watson, "Fabrication of Organic Thin Film Transistors using Inkjet Printing of PEDOT:PSS", Scholarly Commons: Protocols and Reports, Singh Center for Nanotechnology, University of Pennsylvania, USA, Nov. 2019.

https://repository.upenn.edu/scn_protocols/62/ 

State Augmented Routing for Communication Systems

Abstract - In this study, we examine the problem of information routing in a large-scale communication network, which can be formulated as a constrained statistical learning problem having access to only local information. We delineate a novel State Augmentation (SA) strategy to maximize the aggregate information at source nodes using graph neural network (GNN) architectures, by deploying graph convolutions over the topological links of the communication network. The proposed technique leverages only the local information available at each node and efficiently routes desired information to the destination nodes. We leverage an unsupervised learning procedure to convert the output of the GNN architecture to optimal information routing strategies. In the experiments, we perform the evaluation on real-time network topologies to validate our algorithms. Numerical simulations depict the improved performance of the proposed method in training a GNN parameterization as compared to baseline algorithms.

Related papers:

• Learning State-Augmented Policies for Information Routing in Communication Networks

• State-Augmented Information Routing In Communication Systems With Graph Neural Networks

Wireless Autonomous Systems

Sponsored project by Intel Science and Technology Center (ISTC) on Wireless Autonomous Systems (WAS) 

• Setup F1/10 cars using NVIDIA Jetson TX2 development kit and ROS for simulating real time autonomous

• Implement policies for the joint design of communications and control in a fleet of self-driving F1/10 cars.

Organic Thin Film Transistors

• Organic Thin Film Transistors (OTFT): Developing process flow to fabricate OTFTs and electrical characterization.

• Inkjet Printing of Graphene ink: Using aggregation inhibitors to graphene ink to avoid clogging and enable smooth printing.

• Designing layout of mask using CAD tools.