Rahul Sengupta
YOU?
Author Swipe
View article: An Investigation to Enhance the Flexural Modulus of the Natural Fibre Composite Using Hemp Fibre Polymer Matrix
An Investigation to Enhance the Flexural Modulus of the Natural Fibre Composite Using Hemp Fibre Polymer Matrix Open
Natural fibre composites are gaining importance in engineering and automotive sectors due to their sustainability, lightweight nature, and cost-effectiveness. However, their flexural modulus and other mechanical properties require enhancem…
View article: CAESAR: A Unified Framework for Foundation and Generative Models for Efficient Compression of Scientific Data
CAESAR: A Unified Framework for Foundation and Generative Models for Efficient Compression of Scientific Data Open
We introduce CAESAR, a new framework for scientific data reduction that stands for Conditional AutoEncoder with Super-resolution for Augmented Reduction. The baseline model, CAESAR-V, is built on a standard variational autoencoder with sca…
View article: IntTrajSim: Trajectory Prediction for Simulating Multi-Vehicle driving at Signalized Intersections
IntTrajSim: Trajectory Prediction for Simulating Multi-Vehicle driving at Signalized Intersections Open
Traffic simulators are widely used to study the operational efficiency of road infrastructure, but their rule-based approach limits their ability to mimic real-world driving behavior. Traffic intersections are critical components of the ro…
View article: Evaluating Generative Vehicle Trajectory Models for Traffic Intersection Dynamics
Evaluating Generative Vehicle Trajectory Models for Traffic Intersection Dynamics Open
Traffic Intersections are vital to urban road networks as they regulate the movement of people and goods. However, they are regions of conflicting trajectories and are prone to accidents. Deep Generative models of traffic dynamics at signa…
View article: TGDT: A Temporal Graph-based Digital Twin for Urban Traffic Corridors
TGDT: A Temporal Graph-based Digital Twin for Urban Traffic Corridors Open
Urban congestion at signalized intersections leads to significant delays, economic losses, and increased emissions. Existing deep learning models often lack spatial generalizability, rely on complex architectures, and struggle with real-ti…
View article: Dynamic Graph Attention Networks for Travel Time Distribution Prediction in Urban Arterial Roads
Dynamic Graph Attention Networks for Travel Time Distribution Prediction in Urban Arterial Roads Open
Effective congestion management along signalized corridors is essential for improving productivity and reducing costs, with arterial travel time serving as a key performance metric. Traditional approaches, such as Coordinated Signal Timing…
View article: Evaluating the consistency of lenition measures: Neural networks' posterior probability, intensity velocity, and duration
Evaluating the consistency of lenition measures: Neural networks' posterior probability, intensity velocity, and duration Open
Predictions of gradient degree of lenition of voiceless and voiced stops in a corpus of Argentine Spanish are evaluated using three acoustic measures (minimum and maximum intensity velocity and duration) and two recurrent neural network (P…
View article: Comparative Analysis of Dentin Replacement Materials and Enamel Layer Thickness on Color and Translucency of Single-shade Composite Restorations
Comparative Analysis of Dentin Replacement Materials and Enamel Layer Thickness on Color and Translucency of Single-shade Composite Restorations Open
Objective: To evaluate the color and translucency of the single-shade composite, Omnichroma (Tokuyama), when used as an enamel layer over aesthetically unfavorable dentin replacement materials, such as Biodentine (Septodont) and TheraCal L…
View article: MTDT: A Multi-Task Deep Learning Digital Twin
MTDT: A Multi-Task Deep Learning Digital Twin Open
Traffic congestion has significant impacts on both the economy and the environment. Measures of Effectiveness (MOEs) have long been the standard for evaluating traffic intersections' level of service and operational efficiency. However, th…
View article: Graph Attention Network for Lane-Wise and Topology-Invariant Intersection Traffic Simulation
Graph Attention Network for Lane-Wise and Topology-Invariant Intersection Traffic Simulation Open
Traffic congestion has significant economic, environmental, and social ramifications. Intersection traffic flow dynamics are influenced by numerous factors. While microscopic traffic simulators are valuable tools, they are computationally …
View article: Acquisition of Similar versus Different Speech Rhythmic Class
Acquisition of Similar versus Different Speech Rhythmic Class Open
Does shared rhythmic class in L1 (English and German, vs French) facilitate L2 speech learning? The rhythmic patterns of native and German-accented English and French, and native, English- and French-accented German utterances from the Bon…
View article: Measuring Gradient Effects of Alcohol on Speech with Neural Networks’ Posterior Probability of Phonological Features
Measuring Gradient Effects of Alcohol on Speech with Neural Networks’ Posterior Probability of Phonological Features Open
Alcohol is known to impair fine articulatory control and movements. In drunken speech, incomplete closure of the vocal tract can result in deaffrication of the English affricate sounds /tʃ/ and /ʤ/, spirantization (fricative-like productio…
View article: Quantitative Acoustic versus Deep Learning Metrics of Lenition
Quantitative Acoustic versus Deep Learning Metrics of Lenition Open
Spanish voiced stops /b, d, ɡ/ surfaced as fricatives [β, ð, ɣ] in intervocalic position due to a phonological process known as spirantization or, more broadly, lenition. However, conditioned by various factors such as stress, place of art…
View article: From sonority hierarchy to posterior probability as a measure of lenition: The case of Spanish stops
From sonority hierarchy to posterior probability as a measure of lenition: The case of Spanish stops Open
A deep learning Phonet model was evaluated as a method to measure lenition. Unlike quantitative acoustic methods, recurrent networks were trained to recognize the posterior probabilities of sonorant and continuant phonological features in …
View article: Using DSRC Road-Side Unit Data to Derive Braking Behavior
Using DSRC Road-Side Unit Data to Derive Braking Behavior Open
View article: Towards Effective Traffic Signal Safety and Optimization Using Fisheye Video
Towards Effective Traffic Signal Safety and Optimization Using Fisheye Video Open
View article: Design And Analysis Of Cardiac Stent
Design And Analysis Of Cardiac Stent Open
This project presents the modification and analysis of two stent designs based on an existing design. The modifications were made using SolidWorks, followed by ANSYS analysis to evaluate von Mises stress and strain, stress intensity, maxim…
View article: An investigation of interference between electromagnetic articulography and electroglottography
An investigation of interference between electromagnetic articulography and electroglottography Open
The present study tested whether there is cross-interference between electromagnetic articulography (EMA) and electroglottography (EGG) during the acquisition of kinematic speech data. In experiments 1A and 1B, EMA sensors were calibrated …
View article: Lenition measures: Neural networks’ posterior probability vs. acoustic cues
Lenition measures: Neural networks’ posterior probability vs. acoustic cues Open
A phonologically informed neural network approach, Phonet, was compared to acoustic measurements of intensity, duration and harmonicity in estimating lenition degree of voiced and voiceless stops in a corpus of Argentine Spanish. Recurrent…
View article: InterTwin: Deep Learning Approaches for Computing Measures of Effectiveness for Traffic Intersections
InterTwin: Deep Learning Approaches for Computing Measures of Effectiveness for Traffic Intersections Open
Microscopic simulation-based approaches are extensively used for determining good signal timing plans on traffic intersections. Measures of Effectiveness (MOEs) such as wait time, throughput, fuel consumption, emission, and delays can be d…
View article: Subcycle-based Neural Network Algorithms for Turning Movement Count Prediction
Subcycle-based Neural Network Algorithms for Turning Movement Count Prediction Open
View article: Design And Implementation Of Gps Based Medical Services Using Drone
Design And Implementation Of Gps Based Medical Services Using Drone Open
This paper is aimed to provide medical assistance to people through the delivery of medical supplies by unmanned drones. The use of unmanned drones’ benefits people in distant areas around the world. The paper gives attentionto the design …
View article: Analysis and presenting the educational techniques in Machine and Deep Learning Short communication
Analysis and presenting the educational techniques in Machine and Deep Learning Short communication Open
This paper gives a present of general learning of deep methodology and its applications to a variety of signal and data processing schedules. It is discussed about Machine learning vs. Deep Learning a brief and which is best suited in the …