arXiv subjects

Supratik Mukhopadhyay

Publications and source records attributed to Supratik Mukhopadhyay.

At least 55 records · Page 3Linked to original sources

arXiv2020

Numerical study of track distortion in the Large Prototype TPC with end-plate based on bulk Micromegas

The present $\mathrm{R}\&\mathrm{D}$ activities for the International Large Detector Time Projection Chamber (ILD-TPC) concern the adoption of the micro pattern devices for the gaseous amplification stage. Seven Micromegas modules which are commissioned on the end-plate of a Large Prototype TPC (LPTPC) at DESY, were tested with a 5 GeV electron beam, under a 1 T magnetic field. During experiments, reduced signal sensitivity as well as distortion in the reconstructed track was observed at the boundaries of these modules. Electrostatic field inhomogeneity near the module boundaries was considered to be the possible major reason behind these observations. In the present work, this hypothesis has been explored using the Garfield simulation framework. It has been possible to contain the computational complexity of the problem with suitable simplifications. Qualitative and quantitative agreements with experimental results have been achieved. Possibility of mitigating the problems has been proposed using the same simulation framework.

physics.ins-det↗

arXiv2020

Charge sharing in single and double GEMs

The Gas Electron Multiplier (GEM) has become a widely used technology for high-rate particle physics experiments like COMPASS, LHCb and are being used as the readout system for the upcoming upgrade version of other experiments such as ALICE TPC. Radiation hardness, ageing resistance and stability against discharges are main criteria for long-term operation of such detectors in high-rate experiments. In particular, discharge is a serious issue as it may cause irreversible damages to the detector as well as the readout electronics. The charge density inside the amplification region is the limiting factor for detector stability against discharges. By using multiple devices and thus, sharing the electron multiplication in different stages, maximum sustainable gain can be increased by several orders of magnitude. A common explanation for this is connected to the transverse electron diffusion, widening of the electron cloud and reducing the charge density in the last multiplier. However, this has not been verified yet. In our work, we are using Garfield simulation framework as a tool to extract the information related to the transverse size of the propagating electron cloud and thus, to estimate the charge density in the GEM holes for multiple stages. For a given gas mixture, we will present the initial results of charge sharing using single and double GEM detectors under different electric field configurations and its effect on other measurable detector parameters such as single point position resolution.

physics.ins-det↗

arXiv2020

Material Discrimination in Cosmic Muon Imaging using Pattern Recognition Method

This work reports numerical simulations and statistical tests carried out to study the performance of a prototype imaging setup to be developed for material discrimination using Muon Scattering Tomography (MST). The reconstructed images have been processed with a Pattern Recognition Method (PRM) to discriminate the low-Z and high-Z materials. The same method has been applied to examine the performance of the setup in recognizing the shape of the test objects. Design parameters of the setup, such as area of the muon detectors, their physical placement, along with their spatial resolution, etc. have been discussed. To evaluate the efficacy of the newly proposed PRM, the results have been compared to another technique based on cluster finding.

physics.ins-det↗

arXiv2020

A One-Shot Learning Framework for Assessment of Fibrillar Collagen from Second Harmonic Generation Images of an Infarcted Myocardium

Myocardial infarction (MI) is a scientific term that refers to heart attack. In this study, we infer highly relevant second harmonic generation (SHG) cues from collagen fibers exhibiting highly non-centrosymmetric assembly together with two-photon excited cellular autofluorescence in infarcted mouse heart to quantitatively probe fibrosis, especially targeted at an early stage after MI. We present a robust one-shot machine learning algorithm that enables determination of 2D assembly of collagen with high spatial resolution along with its structural arrangement in heart tissues post-MI with spectral specificity and sensitivity. Detection, evaluation, and precise quantification of fibrosis extent at early stage would guide one to develop treatment therapies that may prevent further progression and determine heart transplant needs for patient survival.

eess.IV↗

arXiv2020

Context-Aware Design of Cyber-Physical Human Systems (CPHS)

Recently, it has been widely accepted by the research community that interactions between humans and cyber-physical infrastructures have played a significant role in determining the performance of the latter. The existing paradigm for designing cyber-physical systems for optimal performance focuses on developing models based on historical data. The impacts of context factors driving human system interaction are challenging and are difficult to capture and replicate in existing design models. As a result, many existing models do not or only partially address those context factors of a new design owing to the lack of capabilities to capture the context factors. This limitation in many existing models often causes performance gaps between predicted and measured results. We envision a new design environment, a cyber-physical human system (CPHS) where decision-making processes for physical infrastructures under design are intelligently connected to distributed resources over cyberinfrastructure such as experiments on design features and empirical evidence from operations of existing instances. The framework combines existing design models with context-aware design-specific data involving human-infrastructure interactions in new designs, using a machine learning approach to create augmented design models with improved predictive powers.

cs.AI↗

arXiv2019

DeepSat V2: Feature Augmented Convolutional Neural Nets for Satellite Image Classification

Satellite image classification is a challenging problem that lies at the crossroads of remote sensing, computer vision, and machine learning. Due to the high variability inherent in satellite data, most of the current object classification approaches are not suitable for handling satellite datasets. The progress of satellite image analytics has also been inhibited by the lack of a single labeled high-resolution dataset with multiple class labels. In a preliminary version of this work, we introduced two new high resolution satellite imagery datasets (SAT-4 and SAT-6) and proposed DeepSat framework for classification based on "handcrafted" features and a deep belief network (DBN). The present paper is an extended version, we present an end-to-end framework leveraging an improved architecture that augments a convolutional neural network (CNN) with handcrafted features (instead of using DBN-based architecture) for classification. Our framework, having access to fused spatial information obtained from handcrafted features as well as CNN feature maps, have achieved accuracies of 99.90% and 99.84% respectively, on SAT-4 and SAT-6, surpassing all the other state-of-the-art results. A statistical analysis based on Distribution Separability Criterion substantiates the robustness of our approach in learning better representations for satellite imagery.

cs.CV↗

arXiv2019

PCGAN-CHAR: Progressively Trained Classifier Generative Adversarial Networks for Classification of Noisy Handwritten Bangla Characters

Due to the sparsity of features, noise has proven to be a great inhibitor in the classification of handwritten characters. To combat this, most techniques perform denoising of the data before classification. In this paper, we consolidate the approach by training an all-in-one model that is able to classify even noisy characters. For classification, we progressively train a classifier generative adversarial network on the characters from low to high resolution. We show that by learning the features at each resolution independently a trained model is able to accurately classify characters even in the presence of noise. We experimentally demonstrate the effectiveness of our approach by classifying noisy versions of MNIST, handwritten Bangla Numeral, and Basic Character datasets.

cs.CV↗

arXiv2019

Improving Prediction Accuracy in Building Performance Models Using Generative Adversarial Networks (GANs)

Building performance discrepancies between building design and operation are one of the causes that lead many new designs fail to achieve their goals and objectives. One of main factors contributing to the discrepancy is occupant behaviors. Occupants responding to a new design are influenced by several factors. Existing building performance models (BPMs) ignore or partially address those factors (called contextual factors) while developing BPMs. To potentially reduce the discrepancies and improve the prediction accuracy of BPMs, this paper proposes a computational framework for learning mixture models by using Generative Adversarial Networks (GANs) that appropriately combining existing BPMs with knowledge on occupant behaviors to contextual factors in new designs. Immersive virtual environments (IVEs) experiments are used to acquire data on such behaviors. Performance targets are used to guide appropriate combination of existing BPMs with knowledge on occupant behaviors. The resulting model obtained is called an augmented BPM. Two different experiments related to occupant lighting behaviors are shown as case study. The results reveal that augmented BPMs significantly outperformed existing BPMs with respect to achieving specified performance targets. The case study confirms the potential of the computational framework for improving prediction accuracy of BPMs during design.

cs.LG↗

arXiv2019

Numerical studies on effect of operating conditions and geometrical components on the timing response and efficiency of RPC

A detailed numerical simulation has been performed to investigate the timing properties of a standard RPC geometry in order to optimize its application in INO-ICAL experiment designed for studying atmospheric neutrinos. The timing information provided by the RPC is an important observable in the experiment to determine the direction of the neutrinos. Effects of various operating conditions and design components on the RPC timing response, mainly the average signal arrival time and the time resolution have been studied in this context. The dependence of the detector efficiency on the same parameters has also been presented.

physics.ins-det↗

arXiv2019

Why do you take that route?

The purpose of this paper is to determine whether a particular context factor among the variables that a researcher is interested in causally affects the route choice behavior of drivers. To our knowledge, there is limited literature that consider the effects of various factors on route choice based on causal inference.Yet, collecting data sets that are sensitive to the aforementioned factors are challenging and the existing approaches usually take into account only the general factors motivating drivers route choice behavior. To fill these gaps, we carried out a study using Immersive Virtual Environment (IVE) tools to elicit drivers' route choice behavioral data, covering drivers' network familiarity, educationlevel, financial concern, etc, apart from conventional measurement variables. Having context-aware, high-fidelity properties, IVE data affords the opportunity to incorporate the impacts of human related factors into the route choice causal analysis and advance a more customizable research tool for investigating causal factors on path selection in network routing. This causal analysis provides quantitative evidence to support drivers' diversion decision.

cs.CY↗

arXiv2019

Improving Route Choice Models by Incorporating Contextual Factors via Knowledge Distillation

Route Choice Models predict the route choices of travelers traversing an urban area. Most of the route choice models link route characteristics of alternative routes to those chosen by the drivers. The models play an important role in prediction of traffic levels on different routes and thus assist in development of efficient traffic management strategies that result in minimizing traffic delay and maximizing effective utilization of transport system. High fidelity route choice models are required to predict traffic levels with higher accuracy. Existing route choice models do not take into account dynamic contextual conditions such as the occurrence of an accident, the socio-cultural and economic background of drivers, other human behaviors, the dynamic personal risk level, etc. As a result, they can only make predictions at an aggregate level and for a fixed set of contextual factors. For higher fidelity, it is highly desirable to use a model that captures significance of subjective or contextual factors in route choice. This paper presents a novel approach for developing high-fidelity route choice models with increased predictive power by augmenting existing aggregate level baseline models with information on drivers' responses to contextual factors obtained from Stated Choice Experiments carried out in an Immersive Virtual Environment through the use of knowledge distillation.

cs.LG↗

arXiv2019

Progressively Growing Generative Adversarial Networks for High Resolution Semantic Segmentation of Satellite Images

Machine learning has proven to be useful in classification and segmentation of images. In this paper, we evaluate a training methodology for pixel-wise segmentation on high resolution satellite images using progressive growing of generative adversarial networks. We apply our model to segmenting building rooftops and compare these results to conventional methods for rooftop segmentation. We present our findings using the SpaceNet version 2 dataset. Progressive GAN training achieved a test accuracy of 93% compared to 89% for traditional GAN training.

cs.CV↗

arXiv2018

Pixel-level Reconstruction and Classification for Noisy Handwritten Bangla Characters

Classification techniques for images of handwritten characters are susceptible to noise. Quadtrees can be an efficient representation for learning from sparse features. In this paper, we improve the effectiveness of probabilistic quadtrees by using a pixel level classifier to extract the character pixels and remove noise from handwritten character images. The pixel level denoiser (a deep belief network) uses the map responses obtained from a pretrained CNN as features for reconstructing the characters eliminating noise. We experimentally demonstrate the effectiveness of our approach by reconstructing and classifying a noisy version of handwritten Bangla Numeral and Basic Character datasets.

cs.CV↗

arXiv2018

Material Identification with Cosmic Ray Muons using RPCs

We plan to build an imaging setup for material identification utilizing the Coulomb scattering of cosmic ray muons due to their interaction with the materials and tracking their trajectories with RPCs. To begin with, we consider a setup of six RPCs stacked in a parallel manner to read the position and timing information of the muons before and after their interaction with a phantom of a given material using a set of three RPCs for each phase. Here we present a simulation work carried out to study the image formation of the phantom of several materials using the present setup. A detailed modeling of the imaging system consisting of six RPCs was done using GEANT4. Cosmic Ray Library (CRY) was used for generation of particles with the appropriate distribution of energies and momenta. Three reconstruction algorithms were followed for material identification and image reconstruction, viz. Point of Closest Approach (POCA), Iterative POCA and the Binned Clustering Algorithm. A weighted metric discriminator was calculated for target object identification. Using the algorithms, the imaging of the area of interest lying between the two layers of RPCs was done. The time required to discriminate target objects and do the image reconstruction has been studied.

physics.ins-det↗

arXiv2018

Unsupervised Learning using Pretrained CNN and Associative Memory Bank

Deep Convolutional features extracted from a comprehensive labeled dataset, contain substantial representations which could be effectively used in a new domain. Despite the fact that generic features achieved good results in many visual tasks, fine-tuning is required for pretrained deep CNN models to be more effective and provide state-of-the-art performance. Fine tuning using the backpropagation algorithm in a supervised setting, is a time and resource consuming process. In this paper, we present a new architecture and an approach for unsupervised object recognition that addresses the above mentioned problem with fine tuning associated with pretrained CNN-based supervised deep learning approaches while allowing automated feature extraction. Unlike existing works, our approach is applicable to general object recognition tasks. It uses a pretrained (on a related domain) CNN model for automated feature extraction pipelined with a Hopfield network based associative memory bank for storing patterns for classification purposes. The use of associative memory bank in our framework allows eliminating backpropagation while providing competitive performance on an unseen dataset.

cs.CV↗

arXiv2018

CactusNets: Layer Applicability as a Metric for Transfer Learning

Deep neural networks trained over large datasets learn features that are both generic to the whole dataset, and specific to individual classes in the dataset. Learned features tend towards generic in the lower layers and specific in the higher layers of a network. Methods like fine-tuning are made possible because of the ability for one filter to apply to multiple target classes. Much like the human brain this behavior, can also be used to cluster and separate classes. However, to the best of our knowledge there is no metric for how applicable learned features are to specific classes. In this paper we propose a definition and metric for measuring the applicability of learned features to individual classes, and use this applicability metric to estimate input applicability and produce a new method of unsupervised learning we call the CactusNet.

cs.LG↗

arXiv2017

Measurement and simulation of two-phase CO$_2$ cooling for the AFTER electronics of the Micromegas modules for a Large Prototype of a Time Projection Chamber

The readout electronics of a Micromegas (MM) module consume nearly 26 W of electric power, which causes the temperature of electronic board to increase upto $70\,^{\circ}{\rm C}$. Increase in temperature results in damage of electronics. Development of temperature gradient in the Time Projection Chamber (TPC) may affect precise measurement as well. Two-phase CO$_2$ cooling has been applied to remove heat from the MM modules during two test beam experiments at DESY, Hamburg. Following the experimental procedure, a comprehensive study of the cooling technique has been accomplished for a single MM module by means of numerical simulation. This paper is focused to discuss the application of two-phase CO$_2$ cooling to keep the temperature below $30\,^{\circ}{\rm C}$ and stabilized within $0.2\,^{\circ}{\rm C}$.

physics.ins-det↗

arXiv2017

Experimental and numerical simulation of a TPC like set up for the measurement of ion backflow

Ion backflow is one of the effects limiting the operation of a gaseous detector at high flux, by giving rise to space charge which perturbs the electric field. The natural ability of bulk Micromegas to suppress ion feedback is very effective and can help the TPC drift volume to remain relatively free of space charge build-up. An efficient and precise measurement of the backflow fraction is necessary to cope up with the track distortion due to the space charge effect. In a subtle but significant modification of the usual approach, we have made use of two drift meshes in order to measure the ion backflow fraction for bulk Micromegas detector. This helps to truly represent the backflow fraction for a TPC. Moreover, attempt is taken to optimize the field configuration between the drift meshes. In conjunction with the experimental measurement, Garfield simulation framework has been used to simulate the related physics processes numerically.

physics.ins-det↗