Shamshad Ansari

Potential for Using Deep Learning for Digital-Twin System Validation Testing
IEEE
October 31, 2022

Abstract:
One of the challenges in designing and operating systems composed of interacting components is validating that the emergent behavior of the system does not cause one or more components to migrate, over time, into a hazardous operating state. Many modern airline accidents can be characterized as Interaction Accidents – no component failed, but the interaction of components resulted in a hazardous state.Due to the dependence of time, emergent behavior cannot be evaluated by analysis of the design. In theory it can be evaluated by Digital-Twin agent-based simulations. However, the running these simulations to uncover rare event emergent hazardous states is prohibitive due to: (1) the combinatorics of initial states of each of the components, and the (2) combinatorics of the time dimension (i.e. small variations in timing can result in very different outcomes). Deep Learning Neural Networks (DLNN) have shown promise to capture the underlying combinatoric behavior as well as compress the time dimension.This paper demonstrates the application of DLNN to identify emergent behavior from components with hybrid moded/continuous behavior that plays out over time. DLNNs were trained and tested for three systems with increasing behavioral complexity. The DLNNs accurately were able to represent the time dependent behavior for which they were trained/tested. The DLNNs were also able to learn and predict emergent behavior for behaviors that were not included in the training/testing data (up to 63% of the missing cases). The implications of these results are discussed.

Handwritten Signature Extraction and Matching
Import from medium.com
February 20, 2023

Signature extraction and matching is a vital tool in preventing fraud, verifying identity, ensuring legal compliance, and improving efficiency in various industries. For example:Financial Services: Handwritten signature extraction and matching can be used by financial institutions to verify signatu

How to Train YOLO Model to Detect Distracted Drivers
Import from medium.com
August 01, 2022

Distracted driving is any activity that diverts a driver’s attention while driving a motor vehicle. This includes activities such as texting, talking on the phone, drinking, doing makeup and hair, fiddling with the stereo and radio systems and talking to fellow passengers.Distracted driving is one

Impulse Data Warehousing and OLAP Solution Outperforms Google BigQuery by 3x
Import from medium.com
August 19, 2021

A comprehensive benchmarking of Accure’s Impulse data warehousing and OLAP solution was performed and compared against the price-performance of Google BigQuery (GBQ). Impulse outperformed GBQ by 3x on an average in all queries executed on both the platforms against the same dataset (described belo

Accelerate Data Science, AI and Process Automation With Momentum
Import from medium.com
June 20, 2021

Momentum is a suite of software platforms that enables data engineers, scientists and analysts to efficiently solve machine learning problems and automate business processes.Fig 1. Momentum AI home page screen shotDemocratize AI DevelopmentMomentum enables end-to-end enterprise automation without a

Building A Realtime Pothole Detection System Using Machine Learning and Computer Vision
Import from medium.com
March 15, 2021

Figure 1: Screenshot of potholes detected by a camera installed on a moving vehicle. The potholes are marked with rectangular regions with detection confidence (image by author)Potholes are formed due to wear and tear and weathering of roads. They cause not only discomforts to citizens but also dea

Getting Started with Computer Vision with Machine Learning
Import from medium.com
January 02, 2021

This short article is an attempt to provide with a concise information on different tools and libraries you would need to get started with developing computer vision system or applications. This is not an exhaustive list of all libraries available in the market. The exact toolset will depend on your

Building Deep Autoencoders with Keras and TensorFlow
Import from medium.com
August 03, 2020

In this tutorial, we will explore how to build and train deep autoencoders using Keras and Tensorflow.The primary reason I decided to write this tutorial is that most of the tutorials out there, including the official Keras and TensorFlow ones, use the MNIST data for the training. I have been asked

From Concept to Creation: Building Data Science and AI Solutions Without Coding: A Practical Guide for Non-Programmers, Subject Matter Experts, Engineers, Students, and Analysts
Amazon
October 08, 2024

This book is a practical guide for anyone curious about machine learning and AI, regardless of programming experience. Whether you're a professional, a business leader, or a student, it provides hands-on examples and expert guidance to learn the fundamentals of machine learning and AI. Discover how to implement data science solutions using no-code tools, explore the machine learning development lifecycle, and leverage the Momentum platform for effective data engineering and AI applications.

What You Will Learn:

- Key concepts in machine learning and AI
- Practical applications across various industries
- Utilizing Momentum to build end-to-end AI solutions
Unlock the potential of AI without coding, and start shaping the future today!

Building Computer Vision Applications Using Artificial Neural Networks: With Examples in OpenCV and TensorFlow with Python 2nd ed. Edition
Apress
November 18, 2023

Computer vision is constantly evolving, and this book has been updated to reflect new topics that have emerged in the field since the first edition’s publication. All code used in the book has also been fully updated.

This second edition features new material covering image manipulation practices, image segmentation, feature extraction, and object identification using real-life scenarios to help reinforce each concept. These topics are essential for building advanced computer vision applications, and you’ll gain a thorough understanding of them. The book’s source code has been updated from TensorFlow 1.x to 2.x, and includes step-by-step examples using both OpenCV and TensorFlow with Python.

Upon completing this book, you’ll have the knowledge and skills to build your own computer vision applications using neural networks

What You Will Learn

Understand image processing, manipulation techniques, and feature extraction methods
Work with convolutional neural networks (CNN), single-shot detector (SSD), and YOLO
Utilize large scale model development and cloud infrastructure deployment
Gain an overview of FaceNet neural network architecture and develop a facial recognition system
Who This Book Is For

Those who possess a solid understanding of Python programming and wish to gain an understanding of computer vision and machine learning. It will prove beneficial to data scientists, deep learning experts, and students.

Building Computer Vision Applications Using Artificial Neural Networks: With Step-by-Step Examples in OpenCV and TensorFlow with Python 1st ed. Edition
Apress
July 15, 2020

Apply computer vision and machine learning concepts in developing business and industrial applications ​using a practical, step-by-step approach.



The book comprises four main sections starting with setting up your programming environment and configuring your computer with all the prerequisites to run the code examples. Section 1 covers the basics of image and video processing with code examples of how to manipulate and extract useful information from the images. You will mainly use OpenCV with Python to work with examples in this section.



Section 2 describes machine learning and neural network concepts as applied to computer vision. You will learn different algorithms of the neural network, such as convolutional neural network (CNN), region-based convolutional neural network (R-CNN), and YOLO. In this section, you will also learn how to train, tune, and manage neural networks for computer vision. Section 3 provides step-by-step examples of developing business and industrial applications, such as facial recognition in video surveillance and surface defect detection in manufacturing.



The final section is about training neural networks involving a large number of images on cloud infrastructure, such as Amazon AWS, Google Cloud Platform, and Microsoft Azure. It walks you through the process of training distributed neural networks for computer vision on GPU-based cloud infrastructure. By the time you finish reading Building Computer Vision Applications Using Artificial Neural Networks and working through the code examples, you will have developed some real-world use cases of computer vision with deep learning.

Java & RFID tags
Dr Dobb's Journal
November 01, 2005

An RFID system consists of an antenna and transceiver, which read data transmitted by a transponder via radio frequency (RF). The combined transceiver and antenna are called the" RFID reader." The transponder, referred to as the" RFID tag," is an integrated circuit containing RF circuitry. It transmits data when it comes within the electric or magnetic field of the antenna. The antenna transmits data to a processing unit where it is manipulated according to whatever business needs. The reader is connected to the processing unit or a computer's communication port. Commands are sent from the computer to the reader, which then activates the

INTENT-BASED CLUSTERING OF MEDICAL INFORMATION
20230335298
October 19, 2023

Abstract: A medical information navigation engine (“MINE”) includes a medical information interface, a reconciliation engine, and an intent-based presentation engine. The medical information interface receives medical information from a plurality of medical sources, which is subsequently reconciled by the reconciliation engine. The intent-based presentation engine clusters the reconciled medical information by applying at least one clustering rule to the reconciled medication information. The clustered reconciled medical information can be presented to a user.

SYSTEMS AND METHODS FOR PATIENT RETENTION IN NETWORK THROUGH REFERRAL ANALYTICS
USPTO
February 13, 2023

Abstract: A medical information navigation engine (“MINE”) is capable of inferring referral activity not reported into a referral workflow system by utilizing intent-based clustering of medical information. The intent based clustering reconciles received medical data, from a variety of sources, and then clusters the data by applying one or more clustering rules. After the referrals not otherwise reported are inferred, they may be utilized to generate metrics that can be utilized to enhance patient care, and reduce costs. Metrics may be generated for both in-network and out-of-network referrals in order to distinguish differences in reporting activity.

Systems and methods for event stream platforms which enable applications
USPTO
May 11, 2015

Abstract: Systems and methods to generate a final event stream are provided. The system collects information from a wide variety of sources, and then parses, normalizes, and indexes the information. This generates an initial event stream that can be tagged and then iteratively processed to generate a final event stream. The processing includes first order logic querying and knowledge extraction to infer additional events which is added to the event stream. The final event stream is used by a knowledge exchange for consumption by applications. These applications may be internal applications and/or third party applications. This system may be particularly useful in use with medical information, or any other big data enterprise system.

Medical information navigation engine (MINE) system
USPTO
August 31, 2011

Abstract: A method of transacting medical information includes receiving medical information from a medical sources, identifying, mapping, and consolidating the received medical information by a back-end medical processor, providing access to specific relevant data, based on a user's security privileges, within the identified, mapped, and consolidated medical information, based on user-specific functions or roles by a front-end medical processor, and generating user-customized processed medical information to a plurality of users, with at least a portion of the user-customized processed medical information being provided to each of the plurality of users based on its relevancy to each user's specific function or role and each user's associated security privileges.

Is Your Multi-Platform Approach to Data and AI Costing You More Than It's Delivering?
Thinkers360
December 04, 2024

In an era where efficiency and agility are paramount, should CIOs and CTOs reevaluate whether their multi-platform approach to data and AI is a strategic asset or a costly liability?

Strategic Alignment

1. Do you believe your current multi-platform approach aligns with your long-term strategic vision for innovation, agility, and cost-effectiveness? Or is it creating more silos and inefficiencies?

 

Cost and Efficiency

1. How much are you spending annually on maintaining multiple platforms, including licensing, infrastructure, and the talent required to operate them? Are you confident this cost is justifiable compared to the value delivered?
2. Have you quantified the duplication of efforts and redundancies caused by maintaining disparate platforms? How do you plan to address it?

 

Talent and Skills

1. Given the ongoing demand for highly skilled data and AI professionals, do you find it increasingly difficult to attract and retain talent who can manage your diverse toolset? How sustainable is this model?

 

Operational Complexity

1. How often do projects get delayed or fail because of integration issues between your various platforms? Is this complexity preventing you from fully leveraging your data and AI investments?
2. Do you have a unified data governance and security framework, or is each platform a potential vulnerability point? How does this affect compliance and trust?

 

Scalability and Innovation

1. Are your teams spending more time troubleshooting and integrating platforms than innovating and delivering business value? What does this cost you in terms of competitive advantage?
2. How scalable is your current architecture? Will adding more platforms or tools make scaling easier or harder?

 

Consolidation Opportunities

1. Would consolidating your data and AI platforms into a single, unified platform reduce costs, simplify operations, and accelerate your time-to-value? What’s stopping you from making this move?
2. Do you believe a single platform could enable faster innovation and decision-making by eliminating data silos and integration headaches? Why hasn’t this been prioritized yet?

 

Future Readiness

1. As AI continues to evolve rapidly, can your current fragmented platform ecosystem keep pace with new advancements, or will you constantly play catch-up?
2. If your competitors consolidate their platform footprints for efficiency and speed, how will your organization remain competitive while bearing the weight of a complex and costly ecosystem?

CIOs and CTOs have the opportunity to lead their organizations toward a more streamlined, unified, and efficient future by consolidating their platform footprints. The question isn’t just about reducing costs but about unlocking innovation, improving scalability, and staying ahead of the competition. A single, comprehensive platform could be the key to transforming inefficiencies into opportunities and empowering teams to focus on what truly matters—driving business value and staying competitive in the age of AI.