peptide

Machine Learning-Guided Design of Antimicrobial Peptides

Antimicrobial peptides (AMPs) show promise in treating resistant infections. However, applications of known AMPs have encountered issues in development, production, and shelf-life. To drive the development of AMP-based treatments, it is necessary to create design approaches with higher precision and selectivity toward resistant targets. In this project, we developed AMPGAN a generative adversarial-based model, and obtained proof-of-concept evidence for the generative approach to design AMPs with experimental validation. We proposed a bidirectional conditional generative adversarial network (BiCGAN)-based approach for rational AMP design. AMPGAN uses generator-discriminator dynamics to learn data-driven priors and controls generation using conditioning variables. The bidirectional component, implemented using a learned encoder to map data samples into the latent space of the generator, aids iterative manipulation of candidate peptides. These elements allow the AMPGAN to generate candidates that are novel, diverse, and tailored for specific applications, making it an efficient AMP design tool.

ML_Core

Creating Adaptive Agents With Meta-RL and Intrinsic Motivation

Agents created with traditional reinforcement learning (RL) techniques have achieved some remarkable successes recently. However, they tend to perform poorly on environments with partially observable information and feature poor generalization when faced with new phenomena. We are working on combining advances from Meta-RL, which creates agents that are able to learn how to solve new tasks, and Intrinsic Motivation, which induces agents to intelligently explore their environment.

cyber-security

False Data Injection Attack Detection using Deep learning

State estimation is critical to the operation and control of modern power systems. However, many cyber-attacks, such as false data injection attacks, can be undetectable using conventional detection methods and interfere with the normal operation of grids. In this project, we aim to use deep neural networks for detection of false data injection attacks and localizing where this false data was injected.

endoleak

Deep Learning for Endoleak Recognition

An Abdominal Aortic Aneurysm (AAA) is an enlarged area in the lower part of the aorta and in the case of larger or rapidly growing aneurysms represents a major surgical risk. Surgical treatment can involve open repair to replace the aneurysmal aorta with a graft or more commonly endovascular repair (EVAR) to seal an aneurysm with a stent-graft. This paper is primarily concerned with the automated binary classification of Endoleaks, defined as perigraft flow into the residual aneurysm sac, within computerized tomography angiography (CTA) volumes of patients post-EVAR. We propose a set of cascaded deep convolutional neural network architectures to localize an aneurysm region and subsequently predict the presence of an Endoleak within this region. The proposed method has further shown promising results on our dataset of over 700 labeled CTA volumes, with an optimized accuracy of 89 ± 3% on the task of Endoleak recognition.

PVER

Model Parameter Verification in Power Systems

In power systems, accurate device modeling is the key factor to grid reliability, availability, and resiliency. In the US, all generators of 10 MVA or larger are required to validate their models every five years. This project aims to use advanced deep learning and reinforcement learning models to verify power systems devices from PMU data.

Classification & Geolocalization of the US. Traffic Signs

In collaboration with the Vermont Agency of Transportation, we are working on a research project on classification and geolocalization of the US. traffic signs using deep learning. We introduce Automotive Repository of Traffic Signs (ARTS); a new large-scale dataset oriented for TSR. Our dataset is open-sourced and available on our website.

HOV

Vehicle Passenger Detection System

Implemented scalable Deep Neural Networks algorithms for counting passengers in vehicles. Xerox Vehicle Passenger Detection System identifies the number of occupants in a vehicle with more than 95% accuracy, at speeds ranging from stop and go to 100 mph. I created scalable deep learning convolutional neural network algorithms to count the number of passengers inside the car.

1. S. Wshah, B.i Xu, O. Bulan, SYSTEM AND METHOD FOR EXPANDING AND TRAINING CONVOLUTIONAL NEURAL NETWORKS FOR LARGE SIZE INPUT IMAGES, 20160110US01, Filed on 28 Jun 2016

2. S. Wshah, B. Xu, O. Bulan, MULTI-LAYER FUSION IN A CONVOLUTIONAL NEURAL NETWORK FOR IMAGE CLASSIFICATION, 20151361US02 , Filed on 10 Jun 2016

3. S. Wshah, B. Xu, O. Bulan, J. Kumar, P. Paul, Deep learning architectures for domain adaptation in HOV/HOT lane enforcement, 2016 IEEE Winter Conference on Applications of Computer Vision (WACV 2016).

DA

Digital Alternatives

Led a digital alternatives project focused on filling out forms electronically from different sources such as mobile camera, electronic and scanners. I contributed technically to the project by Implementing high advanced image processing algorithms to analyze documents captured from different sources in order to fill them electronically on fly. The Xerox Digital Alternatives Tool maintain productivity and reduce document workflow complexity in an always-connected world. It is a workflow solution supporting today’s increasingly mobile knowledge worker population, providing the ability to complete multiple workflows within a single application and without the need for paper.

1. M. Maltz, S. Wshah, RELATIONAL DATA BASE FOR FORM UNDERSTANDING WITH ORPHAN REMOVAL, 20150436, 24 Jul 2015

2. M. Maltz, S. Wshah, BUILDING TABLES WITH ROW AND COLUMN HEADING FROM A SCANNED FORM, 20150435, 09 Jul 2015

3. S. Wshah, M. Maltz, D. Venable, METHOD AND SYSTEM OF IDENTIFYING FILLABLE FIELDS OF AN ELECTRONIC FORM, 20151112US01, 10 Dec 2015

MPTextSep

Handwriting and Machine Printed Text Separation

Implementing deep learning algorithms that separate handwritten from machine printed text in structured documents using auto-encoders.

1. S. Wshah ,M. Campanelli , Y. Zhou , METHOD AND APPARATUS FOR CLASSIFYING MACHINE PRINTED TEXT AND HANDWRITTEN TEXT, US Patent App. 14/284,592, 2014.

keywordspotting

Keyword spotting in offline Handwritten Documents

Proposed filler and background models for keyword spotting that combines local scores and global word hypotheses scores to learn a classifier for keywords and non-keywords based on statistical Markov models.

1. G. Kumar , S. Wshah ., G.Venu , Segmentation-free keyword spotting framework using dynamic background model, In proceeding of: Document Recognition and Retrieval XX, (DRR 2013).

2. G. Kumar , S. Wshah ., G.Venu , Variational dynamic background model for keyword spotting in handwritten documents, Electronic Imaging. International Society for Optics and Photonics, (IS\&T/SPIE 2013).

3. S. Wshah ., Kumar G., Venu G., Script IndependentWord Spotting in Offline Handwritten Documents Based on Hidden Markov Models, International Conference on Frontiers in Handwriting Recognition, (ICFHR 2012).

4. S. Wshah., G. Kumar G., G. Venu , Multilingual Word Spotting in Offline Handwritten Documents , 21st International Conference on Pattern Recognition, (ICPR 2012).

5. S. Wshah, G. Kumar , V. Govindaraju, Statistical script independent word spotting in offline handwritten documents, Pattern Recognition Journal, 2014.

Ignite

Xerox Ignite Educator Support System

Implemented image processing and deep learning approaches using auto-encoders and convolutional neural networks to recognize students handwriting from elementary schools. Ignite is a workflow and software solution that is using the power of data to transform K-12 education. Teachers would first scan students homework and/or exams into the Ignite system via a range of multifunctional input devices. Xerox Ignite reads, interprets, and analyzes the students work in minutes.

1. S. Wshah , M. Campanelli , CHARACTER RECOGNITION METHOD AND SYSTEM USING DIGIT SEGMENTATION AND RECOMBINATION, US Patent App. 15/149,483,2013.

2. E. Gross, S. Wshah, I. Simmons, G. Skinnerl, A handwriting recognition system for the classroom, Fifth International Conference on Learning Analytics And Knowledge, (LAK 2015)