arXiv subjects

Swapnil Saha

Publications and source records attributed to Swapnil Saha.

9 recordsLinked to original sources

arXiv2026

An ArcGIS Framework for Mapping Human-Centered Noise Annoyance for AAM Infrastructure Planning

Advanced Air Mobility (AAM) represents a transformative shift in urban transportation; however, successful implementation depends strongly on public acceptance, with noise emerging as a major concern for low-altitude electric vertical takeoff and landing (eVTOL) operations. Existing studies commonly describe eVTOL noise using acoustic metrics such as A-weighted sound level and day-night average sound level. This study develops a Geographic Information System (GIS)-based framework that translates eVTOL acoustic outputs into maps representing the percentage of the population that is highly annoyed (%HA) for a representative medical delivery route in Northwest Arkansas. The results show that noise and annoyance generally decrease with distance from the route, while the highest annoyance occurs during descent, followed by climb and cruise. Census population data are integrated to estimate the number of highly annoyed individuals and identify spatial impact hotspots. Noise-annoyance results are then combined with route distance and airspace factors to evaluate alternative routes and identify balanced routing strategies. The proposed framework connects acoustic assessment with human response and supports the identification of noise-sensitive areas, comparison of route alternatives, and socially sustainable AAM infrastructure planning.

eess.SY↗

arXiv2026

A Systems Engineering Framework for Vision-Language-Enabled UAV Triage and Disaster Response

Recent advances in Vision Language Models (VLMs) have created new opportunities for disaster response, where responders must interpret large volumes of sensor data under time pressure. Current VLM applications include social media monitoring for situational awareness, generation of draft action plans, and translation of technical alerts into public-facing messages. While these efforts can accelerate information flow, they remain largely limited to decision-support roles. Such approaches can increase operator burden because humans must still translate outputs into coordinated actions across teams and robotic assets. This study explores the viability of embedding VLMs as coordination agents within the human-UAV loop. The proposed architecture integrates natural language interaction, mission-level task coordination, software-in-the-loop implementation, and communication aligned with the Incident Command System (ICS). Rather than functioning solely as advisory tools, VLMs facilitate communication between human operators, mission control logic, and UAV task execution. The framework was developed using a Model-Based Systems Engineering (MBSE) approach, with use case and block definition diagrams representing system roles, internal structure, and component interactions. Three key elements, the VLM Coordinator Agent, UAV Mission Control, and Task Allocator, were implemented within an integrated simulation and control environment. A preliminary human-factors evaluation with seven participants showed reduced perceived workload across mental demand, effort, and frustration, along with high ratings for AI trust and communication clarity. By integrating MBSE, software-in-the-loop testing, and human-factors evaluation, this work advances scalable human-autonomy teaming for high-stakes disaster response, with broader implications for aerospace autonomy and civil safety.

cs.RO↗

arXiv2026

Covert Routing with DSSS Signaling Against Cycle Detectors

This paper investigates covert multi-hop communication in wireless networks where an adversary employs a cyclostationary (cycle) detector to reveal hidden transmissions. The covert route employs direct sequence spread spectrum (DSSS) signaling to ensure either maximum end-to-end covertness maximization or minimum latency minimization-under quality-of-service (QoS) and link budget constraints. Optimal bandwidth, transmit power, and spreading gain for each hop jointly satisfy reliability and either rate or covertness requirements. We show the equivalence between the covertness and the detection SNR gain-based widest-path formulations, and, hence, enabling efficient route computation. Numerical simulations in a realistic 3D environment illustrate that (i) end-to-end latency increases exponentially with the covertness requirement, (ii) the end-to-end latency increase is super-linear with the packet size M, and (iii) cycle and energy detectors impose different latency behavior as a function of the message length and the covertness requirement. The proposed framework provides important insights into resource allocation and routing design for covert networks against advanced detection adversaries.

eess.SP↗

arXiv2026

Hybrid Coupling Topology with Dynamic ZZ Suppression for Optimizing Circuit Depth during Runtime in Superconducting Quantum Processor

To reduce circuit depth when executing Quantum algorithms, it is necessary to maximize qubit connectivity on a near-term quantum processor. While addressing this, we also need to ensure high gate fidelity, suppression of unwanted ZZ cross-talk, a compact layout footprint, and minimal control hardware complexity to support scalability. In current superconducting quantum chips, fixed coupling is used as it is easier to scale, but it is limited by unwanted static ZZ interaction during single qubit operations, which degrades system performance. To overcome these challenges, we have introduced a first-of-its-kind hybrid tunable-coupling architecture that connects four fixed-frequency transmon qubits using a single coupler. This hybrid coupler uses off-resonant Stark drives to tune ZZ strength between qubit pairs. Experimentally backed simulation results indicate that our proposed hybrid design maximizes the qubit connectivity while reducing control overhead. This design achieves a near 20% reduction in circuit depth compared to IBM's Heavy-Hexagonal layout, showing its potential for scalability.

quant-ph↗

arXiv2025

On Optimal Batch Size in Coded Computing

We consider computing systems that partition jobs into tasks, add redundancy through coding, and assign the encoded tasks to different computing nodes for parallel execution. The expected execution time depends on the level of redundancy. The computing nodes execute large jobs in batches of tasks. We show that the expected execution time depends on the batch size as well. The optimal batch size that minimizes the execution time depends on the level of redundancy under a fixed number of parallel servers and other system parameters. Furthermore, we show how to (jointly) optimize the redundancy level and batch size to reduce the expected job completion time for two service-time distributions. The simulation presented helps us appreciate the claims.

cs.IT↗

arXiv2025

Deep Mismatch Channel Estimation in IRS based 6G Communication

We propose a channel estimation protocol to determine the uplink channel state information (CSI) at the base station for an intelligent reflecting surface (IRS) based wireless communication. More specifically, we develop a channel estimation scheme in a multi-user system with high estimation accuracy and low computational complexity. One of the state-of-the-art approaches to channel estimation is the deep learning-based approach. However, the data-driven model often experiences high computational complexity and, thus, is slow to channel estimation. Inspired by the success of utilizing domain knowledge to build effective data-driven models, the proposed scheme uses the high channel correlation property to train a shallow deep learning model. More specifically, utilizing the one coherent channel estimation, the model predicts the subsequent channel coherence CSI. We evaluate the performance of the proposed scheme in terms of normalized mean square error (NMSE) and spectral efficiency (SE) via simulation. The proposed scheme can estimate the CSI with reasonable success of lower NMSE, higher SE, and lower estimation time than existing schemes.

eess.SP↗

arXiv2022

Heart Abnormality Detection from Heart Sound Signals using MFCC Feature and Dual Stream Attention Based Network

Cardiovascular diseases are one of the leading cause of death in today's world and early screening of heart condition plays a crucial role in preventing them. The heart sound signal is one of the primary indicator of heart condition and can be used to detect abnormality in the heart. The acquisition of heart sound signal is non-invasive, cost effective and requires minimum equipment. But currently the detection of heart abnormality from heart sound signal depends largely on the expertise and experience of the physician. As such an automatic detection system for heart abnormality detection from heart sound signal can be a great asset for the people living in underdeveloped areas. In this paper we propose a novel deep learning based dual stream network with attention mechanism that uses both the raw heart sound signal and the MFCC features to detect abnormality in heart condition of a patient. The deep neural network has a convolutional stream that uses the raw heart sound signal and a recurrent stream that uses the MFCC features of the signal. The features from these two streams are merged together using a novel attention network and passed through the classification network. The model is trained on the largest publicly available dataset of PCG signal and achieves an accuracy of 87.11, sensitivity of 82.41, specificty of 91.8 and a MACC of 87.12.

cs.SD↗

arXiv2022

A Sequence Agnostic Multimodal Preprocessing for Clogged Blood Vessel Detection in Alzheimer's Diagnosis

Successful identification of blood vessel blockage is a crucial step for Alzheimer's disease diagnosis. These blocks can be identified from the spatial and time-depth variable Two-Photon Excitation Microscopy (TPEF) images of the brain blood vessels using machine learning methods. In this study, we propose several preprocessing schemes to improve the performance of these methods. Our method includes 3D-point cloud data extraction from image modality and their feature-space fusion to leverage complementary information inherent in different modalities. We also enforce the learned representation to be sequence-order invariant by utilizing bi-direction dataflow. Experimental results on The Clog Loss dataset show that our proposed method consistently outperforms the state-of-the-art preprocessing methods in stalled and non-stalled vessel classification.

eess.IV↗

arXiv2022

Privacy-preserving Non-negative Matrix Factorization with Outliers

Non-negative matrix factorization is a popular unsupervised machine learning algorithm for extracting meaningful features from data which are inherently non-negative. However, such data sets may often contain privacy-sensitive user data, and therefore, we may need to take necessary steps to ensure the privacy of the users while analyzing the data. In this work, we focus on developing a Non-negative matrix factorization algorithm in the privacy-preserving framework. More specifically, we propose a novel privacy-preserving algorithm for non-negative matrix factorisation capable of operating on private data, while achieving results comparable to those of the non-private algorithm. We design the framework such that one has the control to select the degree of privacy grantee based on the utility gap. We show our proposed framework's performance in six real data sets. The experimental results show that our proposed method can achieve very close performance with the non-private algorithm under some parameter regime, while ensuring strict privacy.

cs.LG↗