Freelancer logo How It Works Browse Jobs
Log In Sign Up
Post a Project
EXPLORE
Java
JavaScript
Project Management
Python
Website Design
Profile cover photo
You're now following
Error following user.
This user does not allow users to follow them.
You are already following this user.
Your membership plan only allows 0 follows. Upgrade here.
Successfully unfollowed
Error unfollowing user.
You have successfully recommended
Error recommending user.
Something went wrong. Please refresh the page and try again.
Email successfully verified.
User Avatar
$60 USD / hour
Flag of UNITED STATES
san francisco, united states
$60 USD / hour
It's currently 2:36 PM here
Joined January 20, 2015
0 Recommendations

Anurag S.

@anuragsah00

 0.0 (0 reviews)
0.0
0.0
0%
0%
$60 USD / hour
Flag of UNITED STATES
san francisco, united states
$60 USD / hour
N/A
Jobs Completed
N/A
On Budget
N/A
On Time
N/A
Repeat Hire Rate

Full Stack AI Developer & Architect

I find passion in the work I do and see poetry in the code I write. I have managed a team of 10 software developers following Agile Development in a deep learning startup I Co-Founded, AitoeLabs ([login to view URL]). I have knowledge in designing, architecting, and implementing on a wide spectrum of technology for deep technology companies. I have worked with embedded hardware, web development, smartphone app development, Big Data technologies, Artificial Intelligence, Deep Learning & Computer Vision. My Process: 1. Requirements 2. User Stories 3. Design and Architecture (Frontend/Backend/Database) 4. Iterative implementation with milestones and feedback 5. Deployment & Delivery I am open to consult on existing products, ensure development best practices and future-proofness by a thorough understanding of your business goals. (Please see skills and portfolio section)
Freelancer Java Developers United States
See all Java Developers in United States

Contact Anurag S. about your job

Log in to discuss any details over chat.

Portfolio

4329522
This report is about load balancing Java Server which routes requests across heterogeneous servers. That is, giving higher workload to powerful servers and lesser workload to weaker servers. Since these servers have different capacities, a simple Round Robin approach cannot be implemented where all servers get equal load. Since less powerful servers will be saturated while powerful servers will be under-utilized, this is not the best solution. Hence an efficient method is to be made so that each server gets what it can take. This introduces the concept of Weighted Round Robin where there is an extra parameter of weights which allocates the load. This method was tested and tried in the experiments and showed positive results with the response time (Total time taken for a user to get a response after submitting a request) reduced to 51.83% of the response time when Round Robin was used.
Load Balancing: Heterogenuous Servers Request Distribution
4329510
REQUIREMENT: 1. An hardware device with sensors which attaches to a pen to record the strokes digitally 2. Transmits the sensor data to a smartphone app via bluetooth. 3. The smartphone app receives it, stores notes. 4. Collaborative canvas so many users can draw on the same canvas at the same time with different input devices (other Efemel Pens, through the smartphone app, browser webapp etc.) Hardware Skills: C++, I2C Communication, Bluetooth, Circuit Board Design Web Application Skills: Android Programming, iOS Programming, AngularJS, Bootstrap, SocketIO, NodeJS with ExpressJS RESULT: A collaborative drawing product used for P2P tutoring and taking notes and storing them digitally.
Efemel Digital Smart Pen
4329502
REQUIREMENT: Free ride-sharing service for students of HKUST (Hong Kong) matched with faculty with cars and empty seats. Students commute to and from the university face problems with busy public transportation. Faculty usually bring personal cars for their commute. We developed a platform for this matching as well as an Android/iOS app. IMPLEMENTATION: This involved components like student and faculty registration, verification, authentication, request-offer matching, tracking the ride with GPS, etc. Front-End Technologies: HTML5, Jquery, AngularJS, Bootstrap, Phonegap Back-End Technologies: NodeJS, ExpressJS, MySQL, SocketIO, Google Cloud Messaging, Apple Push Notification, Nodemailer RESULT: This application was deployed among 10,000 students and 3,000 faculty members and reduced rush hour traffic exponentially since each ride had approximately 3 empty seats each. This put far lesser load on the public transportation system making rush hour easier to handle.
BeThere: University Ride-Sharing App
REQUIREMENT: Free ride-sharing service for students of HKUST (Hong Kong) matched with faculty with cars and empty seats. Students commute to and from the university face problems with busy public transportation. Faculty usually bring personal cars for their commute. We developed a platform for this matching as well as an Android/iOS app. IMPLEMENTATION: This involved components like student and faculty registration, verification, authentication, request-offer matching, tracking the ride with GPS, etc. Front-End Technologies: HTML5, Jquery, AngularJS, Bootstrap, Phonegap Back-End Technologies: NodeJS, ExpressJS, MySQL, SocketIO, Google Cloud Messaging, Apple Push Notification, Nodemailer RESULT: This application was deployed among 10,000 students and 3,000 faculty members and reduced rush hour traffic exponentially since each ride had approximately 3 empty seats each. This put far lesser load on the public transportation system making rush hour easier to handle.
BeThere: University Ride-Sharing App
REQUIREMENT: Free ride-sharing service for students of HKUST (Hong Kong) matched with faculty with cars and empty seats. Students commute to and from the university face problems with busy public transportation. Faculty usually bring personal cars for their commute. We developed a platform for this matching as well as an Android/iOS app. IMPLEMENTATION: This involved components like student and faculty registration, verification, authentication, request-offer matching, tracking the ride with GPS, etc. Front-End Technologies: HTML5, Jquery, AngularJS, Bootstrap, Phonegap Back-End Technologies: NodeJS, ExpressJS, MySQL, SocketIO, Google Cloud Messaging, Apple Push Notification, Nodemailer RESULT: This application was deployed among 10,000 students and 3,000 faculty members and reduced rush hour traffic exponentially since each ride had approximately 3 empty seats each. This put far lesser load on the public transportation system making rush hour easier to handle.
BeThere: University Ride-Sharing App
REQUIREMENT: Free ride-sharing service for students of HKUST (Hong Kong) matched with faculty with cars and empty seats. Students commute to and from the university face problems with busy public transportation. Faculty usually bring personal cars for their commute. We developed a platform for this matching as well as an Android/iOS app. IMPLEMENTATION: This involved components like student and faculty registration, verification, authentication, request-offer matching, tracking the ride with GPS, etc. Front-End Technologies: HTML5, Jquery, AngularJS, Bootstrap, Phonegap Back-End Technologies: NodeJS, ExpressJS, MySQL, SocketIO, Google Cloud Messaging, Apple Push Notification, Nodemailer RESULT: This application was deployed among 10,000 students and 3,000 faculty members and reduced rush hour traffic exponentially since each ride had approximately 3 empty seats each. This put far lesser load on the public transportation system making rush hour easier to handle.
BeThere: University Ride-Sharing App
REQUIREMENT: Free ride-sharing service for students of HKUST (Hong Kong) matched with faculty with cars and empty seats. Students commute to and from the university face problems with busy public transportation. Faculty usually bring personal cars for their commute. We developed a platform for this matching as well as an Android/iOS app. IMPLEMENTATION: This involved components like student and faculty registration, verification, authentication, request-offer matching, tracking the ride with GPS, etc. Front-End Technologies: HTML5, Jquery, AngularJS, Bootstrap, Phonegap Back-End Technologies: NodeJS, ExpressJS, MySQL, SocketIO, Google Cloud Messaging, Apple Push Notification, Nodemailer RESULT: This application was deployed among 10,000 students and 3,000 faculty members and reduced rush hour traffic exponentially since each ride had approximately 3 empty seats each. This put far lesser load on the public transportation system making rush hour easier to handle.
BeThere: University Ride-Sharing App
4329487
I have managed a team of 10 software developers following Agile Development in a startup I Co-Founded, AitoeLabs (www.aitoelabs.com) where we provide Video Surveillance Analytics leveraging technologies like Deep Learning for large government projects. The final product has a complex architecture, design and was implemented in house leveraging latest web technologies like React, Node and latest AI frameworks like Cafe, Darknet as well as proprietary Data Summarization. It is able to process offline security videos (mp4 files) as well as real time streams from the security cameras. The analytics is able to perform computer vision tasks such as Object Recognition, Face Recognition, Optical Character Recognition etc. The User gets security alerts having set the exceptions, search with natural queries, get statistics and view video summaries. I have spoken on LDV Vision Summit NY (https://vimeo.com/227930) as well as Alchemist Accelerator, San Francisco (https://vimeo.com/271770757).
AitoeLabs: Custom Deep Learning for Security Video Analytics
I have managed a team of 10 software developers following Agile Development in a startup I Co-Founded, AitoeLabs (www.aitoelabs.com) where we provide Video Surveillance Analytics leveraging technologies like Deep Learning for large government projects. The final product has a complex architecture, design and was implemented in house leveraging latest web technologies like React, Node and latest AI frameworks like Cafe, Darknet as well as proprietary Data Summarization. It is able to process offline security videos (mp4 files) as well as real time streams from the security cameras. The analytics is able to perform computer vision tasks such as Object Recognition, Face Recognition, Optical Character Recognition etc. The User gets security alerts having set the exceptions, search with natural queries, get statistics and view video summaries. I have spoken on LDV Vision Summit NY (https://vimeo.com/227930) as well as Alchemist Accelerator, San Francisco (https://vimeo.com/271770757).
AitoeLabs: Custom Deep Learning for Security Video Analytics
I have managed a team of 10 software developers following Agile Development in a startup I Co-Founded, AitoeLabs (www.aitoelabs.com) where we provide Video Surveillance Analytics leveraging technologies like Deep Learning for large government projects. The final product has a complex architecture, design and was implemented in house leveraging latest web technologies like React, Node and latest AI frameworks like Cafe, Darknet as well as proprietary Data Summarization. It is able to process offline security videos (mp4 files) as well as real time streams from the security cameras. The analytics is able to perform computer vision tasks such as Object Recognition, Face Recognition, Optical Character Recognition etc. The User gets security alerts having set the exceptions, search with natural queries, get statistics and view video summaries. I have spoken on LDV Vision Summit NY (https://vimeo.com/227930) as well as Alchemist Accelerator, San Francisco (https://vimeo.com/271770757).
AitoeLabs: Custom Deep Learning for Security Video Analytics
I have managed a team of 10 software developers following Agile Development in a startup I Co-Founded, AitoeLabs (www.aitoelabs.com) where we provide Video Surveillance Analytics leveraging technologies like Deep Learning for large government projects. The final product has a complex architecture, design and was implemented in house leveraging latest web technologies like React, Node and latest AI frameworks like Cafe, Darknet as well as proprietary Data Summarization. It is able to process offline security videos (mp4 files) as well as real time streams from the security cameras. The analytics is able to perform computer vision tasks such as Object Recognition, Face Recognition, Optical Character Recognition etc. The User gets security alerts having set the exceptions, search with natural queries, get statistics and view video summaries. I have spoken on LDV Vision Summit NY (https://vimeo.com/227930) as well as Alchemist Accelerator, San Francisco (https://vimeo.com/271770757).
AitoeLabs: Custom Deep Learning for Security Video Analytics
I have managed a team of 10 software developers following Agile Development in a startup I Co-Founded, AitoeLabs (www.aitoelabs.com) where we provide Video Surveillance Analytics leveraging technologies like Deep Learning for large government projects. The final product has a complex architecture, design and was implemented in house leveraging latest web technologies like React, Node and latest AI frameworks like Cafe, Darknet as well as proprietary Data Summarization. It is able to process offline security videos (mp4 files) as well as real time streams from the security cameras. The analytics is able to perform computer vision tasks such as Object Recognition, Face Recognition, Optical Character Recognition etc. The User gets security alerts having set the exceptions, search with natural queries, get statistics and view video summaries. I have spoken on LDV Vision Summit NY (https://vimeo.com/227930) as well as Alchemist Accelerator, San Francisco (https://vimeo.com/271770757).
AitoeLabs: Custom Deep Learning for Security Video Analytics
I have managed a team of 10 software developers following Agile Development in a startup I Co-Founded, AitoeLabs (www.aitoelabs.com) where we provide Video Surveillance Analytics leveraging technologies like Deep Learning for large government projects. The final product has a complex architecture, design and was implemented in house leveraging latest web technologies like React, Node and latest AI frameworks like Cafe, Darknet as well as proprietary Data Summarization. It is able to process offline security videos (mp4 files) as well as real time streams from the security cameras. The analytics is able to perform computer vision tasks such as Object Recognition, Face Recognition, Optical Character Recognition etc. The User gets security alerts having set the exceptions, search with natural queries, get statistics and view video summaries. I have spoken on LDV Vision Summit NY (https://vimeo.com/227930) as well as Alchemist Accelerator, San Francisco (https://vimeo.com/271770757).
AitoeLabs: Custom Deep Learning for Security Video Analytics
I have managed a team of 10 software developers following Agile Development in a startup I Co-Founded, AitoeLabs (www.aitoelabs.com) where we provide Video Surveillance Analytics leveraging technologies like Deep Learning for large government projects. The final product has a complex architecture, design and was implemented in house leveraging latest web technologies like React, Node and latest AI frameworks like Cafe, Darknet as well as proprietary Data Summarization. It is able to process offline security videos (mp4 files) as well as real time streams from the security cameras. The analytics is able to perform computer vision tasks such as Object Recognition, Face Recognition, Optical Character Recognition etc. The User gets security alerts having set the exceptions, search with natural queries, get statistics and view video summaries. I have spoken on LDV Vision Summit NY (https://vimeo.com/227930) as well as Alchemist Accelerator, San Francisco (https://vimeo.com/271770757).
AitoeLabs: Custom Deep Learning for Security Video Analytics
I have managed a team of 10 software developers following Agile Development in a startup I Co-Founded, AitoeLabs (www.aitoelabs.com) where we provide Video Surveillance Analytics leveraging technologies like Deep Learning for large government projects. The final product has a complex architecture, design and was implemented in house leveraging latest web technologies like React, Node and latest AI frameworks like Cafe, Darknet as well as proprietary Data Summarization. It is able to process offline security videos (mp4 files) as well as real time streams from the security cameras. The analytics is able to perform computer vision tasks such as Object Recognition, Face Recognition, Optical Character Recognition etc. The User gets security alerts having set the exceptions, search with natural queries, get statistics and view video summaries. I have spoken on LDV Vision Summit NY (https://vimeo.com/227930) as well as Alchemist Accelerator, San Francisco (https://vimeo.com/271770757).
AitoeLabs: Custom Deep Learning for Security Video Analytics
4329354
A telecom company with a 100 million users wanted to use customer data to predict key performance indicators like Churn, Customer Segmentation, Social Media Analytics etc. using Machine Learning techniques. These were done to modify marketing campaign in order to retain users increase use of services and grow user base. IMPLEMENTATION: We built a Machine Learning Platform in a Microservice Architecture which pooled data from existing Source Systems like on-boarding forms, company app usage and also the network tower data. We supervised ML models for predicting if a given user will increase or decrease data usage or churn out entirely based on historical data. Having understood this, we segment the customers into categories and determine the churn reason using unsupervised ML and are able to use target marketing to send promotions to the given user before he/she churns so that they will not churn and increase usage.
Telecom Customer Analytics
A telecom company with a 100 million users wanted to use customer data to predict key performance indicators like Churn, Customer Segmentation, Social Media Analytics etc. using Machine Learning techniques. These were done to modify marketing campaign in order to retain users increase use of services and grow user base. IMPLEMENTATION: We built a Machine Learning Platform in a Microservice Architecture which pooled data from existing Source Systems like on-boarding forms, company app usage and also the network tower data. We supervised ML models for predicting if a given user will increase or decrease data usage or churn out entirely based on historical data. Having understood this, we segment the customers into categories and determine the churn reason using unsupervised ML and are able to use target marketing to send promotions to the given user before he/she churns so that they will not churn and increase usage.
Telecom Customer Analytics
A telecom company with a 100 million users wanted to use customer data to predict key performance indicators like Churn, Customer Segmentation, Social Media Analytics etc. using Machine Learning techniques. These were done to modify marketing campaign in order to retain users increase use of services and grow user base. IMPLEMENTATION: We built a Machine Learning Platform in a Microservice Architecture which pooled data from existing Source Systems like on-boarding forms, company app usage and also the network tower data. We supervised ML models for predicting if a given user will increase or decrease data usage or churn out entirely based on historical data. Having understood this, we segment the customers into categories and determine the churn reason using unsupervised ML and are able to use target marketing to send promotions to the given user before he/she churns so that they will not churn and increase usage.
Telecom Customer Analytics
A telecom company with a 100 million users wanted to use customer data to predict key performance indicators like Churn, Customer Segmentation, Social Media Analytics etc. using Machine Learning techniques. These were done to modify marketing campaign in order to retain users increase use of services and grow user base. IMPLEMENTATION: We built a Machine Learning Platform in a Microservice Architecture which pooled data from existing Source Systems like on-boarding forms, company app usage and also the network tower data. We supervised ML models for predicting if a given user will increase or decrease data usage or churn out entirely based on historical data. Having understood this, we segment the customers into categories and determine the churn reason using unsupervised ML and are able to use target marketing to send promotions to the given user before he/she churns so that they will not churn and increase usage.
Telecom Customer Analytics
A telecom company with a 100 million users wanted to use customer data to predict key performance indicators like Churn, Customer Segmentation, Social Media Analytics etc. using Machine Learning techniques. These were done to modify marketing campaign in order to retain users increase use of services and grow user base. IMPLEMENTATION: We built a Machine Learning Platform in a Microservice Architecture which pooled data from existing Source Systems like on-boarding forms, company app usage and also the network tower data. We supervised ML models for predicting if a given user will increase or decrease data usage or churn out entirely based on historical data. Having understood this, we segment the customers into categories and determine the churn reason using unsupervised ML and are able to use target marketing to send promotions to the given user before he/she churns so that they will not churn and increase usage.
Telecom Customer Analytics
4329522
This report is about load balancing Java Server which routes requests across heterogeneous servers. That is, giving higher workload to powerful servers and lesser workload to weaker servers. Since these servers have different capacities, a simple Round Robin approach cannot be implemented where all servers get equal load. Since less powerful servers will be saturated while powerful servers will be under-utilized, this is not the best solution. Hence an efficient method is to be made so that each server gets what it can take. This introduces the concept of Weighted Round Robin where there is an extra parameter of weights which allocates the load. This method was tested and tried in the experiments and showed positive results with the response time (Total time taken for a user to get a response after submitting a request) reduced to 51.83% of the response time when Round Robin was used.
Load Balancing: Heterogenuous Servers Request Distribution
4329510
REQUIREMENT: 1. An hardware device with sensors which attaches to a pen to record the strokes digitally 2. Transmits the sensor data to a smartphone app via bluetooth. 3. The smartphone app receives it, stores notes. 4. Collaborative canvas so many users can draw on the same canvas at the same time with different input devices (other Efemel Pens, through the smartphone app, browser webapp etc.) Hardware Skills: C++, I2C Communication, Bluetooth, Circuit Board Design Web Application Skills: Android Programming, iOS Programming, AngularJS, Bootstrap, SocketIO, NodeJS with ExpressJS RESULT: A collaborative drawing product used for P2P tutoring and taking notes and storing them digitally.
Efemel Digital Smart Pen
4329502
REQUIREMENT: Free ride-sharing service for students of HKUST (Hong Kong) matched with faculty with cars and empty seats. Students commute to and from the university face problems with busy public transportation. Faculty usually bring personal cars for their commute. We developed a platform for this matching as well as an Android/iOS app. IMPLEMENTATION: This involved components like student and faculty registration, verification, authentication, request-offer matching, tracking the ride with GPS, etc. Front-End Technologies: HTML5, Jquery, AngularJS, Bootstrap, Phonegap Back-End Technologies: NodeJS, ExpressJS, MySQL, SocketIO, Google Cloud Messaging, Apple Push Notification, Nodemailer RESULT: This application was deployed among 10,000 students and 3,000 faculty members and reduced rush hour traffic exponentially since each ride had approximately 3 empty seats each. This put far lesser load on the public transportation system making rush hour easier to handle.
BeThere: University Ride-Sharing App
REQUIREMENT: Free ride-sharing service for students of HKUST (Hong Kong) matched with faculty with cars and empty seats. Students commute to and from the university face problems with busy public transportation. Faculty usually bring personal cars for their commute. We developed a platform for this matching as well as an Android/iOS app. IMPLEMENTATION: This involved components like student and faculty registration, verification, authentication, request-offer matching, tracking the ride with GPS, etc. Front-End Technologies: HTML5, Jquery, AngularJS, Bootstrap, Phonegap Back-End Technologies: NodeJS, ExpressJS, MySQL, SocketIO, Google Cloud Messaging, Apple Push Notification, Nodemailer RESULT: This application was deployed among 10,000 students and 3,000 faculty members and reduced rush hour traffic exponentially since each ride had approximately 3 empty seats each. This put far lesser load on the public transportation system making rush hour easier to handle.
BeThere: University Ride-Sharing App
REQUIREMENT: Free ride-sharing service for students of HKUST (Hong Kong) matched with faculty with cars and empty seats. Students commute to and from the university face problems with busy public transportation. Faculty usually bring personal cars for their commute. We developed a platform for this matching as well as an Android/iOS app. IMPLEMENTATION: This involved components like student and faculty registration, verification, authentication, request-offer matching, tracking the ride with GPS, etc. Front-End Technologies: HTML5, Jquery, AngularJS, Bootstrap, Phonegap Back-End Technologies: NodeJS, ExpressJS, MySQL, SocketIO, Google Cloud Messaging, Apple Push Notification, Nodemailer RESULT: This application was deployed among 10,000 students and 3,000 faculty members and reduced rush hour traffic exponentially since each ride had approximately 3 empty seats each. This put far lesser load on the public transportation system making rush hour easier to handle.
BeThere: University Ride-Sharing App
REQUIREMENT: Free ride-sharing service for students of HKUST (Hong Kong) matched with faculty with cars and empty seats. Students commute to and from the university face problems with busy public transportation. Faculty usually bring personal cars for their commute. We developed a platform for this matching as well as an Android/iOS app. IMPLEMENTATION: This involved components like student and faculty registration, verification, authentication, request-offer matching, tracking the ride with GPS, etc. Front-End Technologies: HTML5, Jquery, AngularJS, Bootstrap, Phonegap Back-End Technologies: NodeJS, ExpressJS, MySQL, SocketIO, Google Cloud Messaging, Apple Push Notification, Nodemailer RESULT: This application was deployed among 10,000 students and 3,000 faculty members and reduced rush hour traffic exponentially since each ride had approximately 3 empty seats each. This put far lesser load on the public transportation system making rush hour easier to handle.
BeThere: University Ride-Sharing App
REQUIREMENT: Free ride-sharing service for students of HKUST (Hong Kong) matched with faculty with cars and empty seats. Students commute to and from the university face problems with busy public transportation. Faculty usually bring personal cars for their commute. We developed a platform for this matching as well as an Android/iOS app. IMPLEMENTATION: This involved components like student and faculty registration, verification, authentication, request-offer matching, tracking the ride with GPS, etc. Front-End Technologies: HTML5, Jquery, AngularJS, Bootstrap, Phonegap Back-End Technologies: NodeJS, ExpressJS, MySQL, SocketIO, Google Cloud Messaging, Apple Push Notification, Nodemailer RESULT: This application was deployed among 10,000 students and 3,000 faculty members and reduced rush hour traffic exponentially since each ride had approximately 3 empty seats each. This put far lesser load on the public transportation system making rush hour easier to handle.
BeThere: University Ride-Sharing App
4329487
I have managed a team of 10 software developers following Agile Development in a startup I Co-Founded, AitoeLabs (www.aitoelabs.com) where we provide Video Surveillance Analytics leveraging technologies like Deep Learning for large government projects. The final product has a complex architecture, design and was implemented in house leveraging latest web technologies like React, Node and latest AI frameworks like Cafe, Darknet as well as proprietary Data Summarization. It is able to process offline security videos (mp4 files) as well as real time streams from the security cameras. The analytics is able to perform computer vision tasks such as Object Recognition, Face Recognition, Optical Character Recognition etc. The User gets security alerts having set the exceptions, search with natural queries, get statistics and view video summaries. I have spoken on LDV Vision Summit NY (https://vimeo.com/227930) as well as Alchemist Accelerator, San Francisco (https://vimeo.com/271770757).
AitoeLabs: Custom Deep Learning for Security Video Analytics
I have managed a team of 10 software developers following Agile Development in a startup I Co-Founded, AitoeLabs (www.aitoelabs.com) where we provide Video Surveillance Analytics leveraging technologies like Deep Learning for large government projects. The final product has a complex architecture, design and was implemented in house leveraging latest web technologies like React, Node and latest AI frameworks like Cafe, Darknet as well as proprietary Data Summarization. It is able to process offline security videos (mp4 files) as well as real time streams from the security cameras. The analytics is able to perform computer vision tasks such as Object Recognition, Face Recognition, Optical Character Recognition etc. The User gets security alerts having set the exceptions, search with natural queries, get statistics and view video summaries. I have spoken on LDV Vision Summit NY (https://vimeo.com/227930) as well as Alchemist Accelerator, San Francisco (https://vimeo.com/271770757).
AitoeLabs: Custom Deep Learning for Security Video Analytics
I have managed a team of 10 software developers following Agile Development in a startup I Co-Founded, AitoeLabs (www.aitoelabs.com) where we provide Video Surveillance Analytics leveraging technologies like Deep Learning for large government projects. The final product has a complex architecture, design and was implemented in house leveraging latest web technologies like React, Node and latest AI frameworks like Cafe, Darknet as well as proprietary Data Summarization. It is able to process offline security videos (mp4 files) as well as real time streams from the security cameras. The analytics is able to perform computer vision tasks such as Object Recognition, Face Recognition, Optical Character Recognition etc. The User gets security alerts having set the exceptions, search with natural queries, get statistics and view video summaries. I have spoken on LDV Vision Summit NY (https://vimeo.com/227930) as well as Alchemist Accelerator, San Francisco (https://vimeo.com/271770757).
AitoeLabs: Custom Deep Learning for Security Video Analytics
I have managed a team of 10 software developers following Agile Development in a startup I Co-Founded, AitoeLabs (www.aitoelabs.com) where we provide Video Surveillance Analytics leveraging technologies like Deep Learning for large government projects. The final product has a complex architecture, design and was implemented in house leveraging latest web technologies like React, Node and latest AI frameworks like Cafe, Darknet as well as proprietary Data Summarization. It is able to process offline security videos (mp4 files) as well as real time streams from the security cameras. The analytics is able to perform computer vision tasks such as Object Recognition, Face Recognition, Optical Character Recognition etc. The User gets security alerts having set the exceptions, search with natural queries, get statistics and view video summaries. I have spoken on LDV Vision Summit NY (https://vimeo.com/227930) as well as Alchemist Accelerator, San Francisco (https://vimeo.com/271770757).
AitoeLabs: Custom Deep Learning for Security Video Analytics
I have managed a team of 10 software developers following Agile Development in a startup I Co-Founded, AitoeLabs (www.aitoelabs.com) where we provide Video Surveillance Analytics leveraging technologies like Deep Learning for large government projects. The final product has a complex architecture, design and was implemented in house leveraging latest web technologies like React, Node and latest AI frameworks like Cafe, Darknet as well as proprietary Data Summarization. It is able to process offline security videos (mp4 files) as well as real time streams from the security cameras. The analytics is able to perform computer vision tasks such as Object Recognition, Face Recognition, Optical Character Recognition etc. The User gets security alerts having set the exceptions, search with natural queries, get statistics and view video summaries. I have spoken on LDV Vision Summit NY (https://vimeo.com/227930) as well as Alchemist Accelerator, San Francisco (https://vimeo.com/271770757).
AitoeLabs: Custom Deep Learning for Security Video Analytics
I have managed a team of 10 software developers following Agile Development in a startup I Co-Founded, AitoeLabs (www.aitoelabs.com) where we provide Video Surveillance Analytics leveraging technologies like Deep Learning for large government projects. The final product has a complex architecture, design and was implemented in house leveraging latest web technologies like React, Node and latest AI frameworks like Cafe, Darknet as well as proprietary Data Summarization. It is able to process offline security videos (mp4 files) as well as real time streams from the security cameras. The analytics is able to perform computer vision tasks such as Object Recognition, Face Recognition, Optical Character Recognition etc. The User gets security alerts having set the exceptions, search with natural queries, get statistics and view video summaries. I have spoken on LDV Vision Summit NY (https://vimeo.com/227930) as well as Alchemist Accelerator, San Francisco (https://vimeo.com/271770757).
AitoeLabs: Custom Deep Learning for Security Video Analytics
I have managed a team of 10 software developers following Agile Development in a startup I Co-Founded, AitoeLabs (www.aitoelabs.com) where we provide Video Surveillance Analytics leveraging technologies like Deep Learning for large government projects. The final product has a complex architecture, design and was implemented in house leveraging latest web technologies like React, Node and latest AI frameworks like Cafe, Darknet as well as proprietary Data Summarization. It is able to process offline security videos (mp4 files) as well as real time streams from the security cameras. The analytics is able to perform computer vision tasks such as Object Recognition, Face Recognition, Optical Character Recognition etc. The User gets security alerts having set the exceptions, search with natural queries, get statistics and view video summaries. I have spoken on LDV Vision Summit NY (https://vimeo.com/227930) as well as Alchemist Accelerator, San Francisco (https://vimeo.com/271770757).
AitoeLabs: Custom Deep Learning for Security Video Analytics
I have managed a team of 10 software developers following Agile Development in a startup I Co-Founded, AitoeLabs (www.aitoelabs.com) where we provide Video Surveillance Analytics leveraging technologies like Deep Learning for large government projects. The final product has a complex architecture, design and was implemented in house leveraging latest web technologies like React, Node and latest AI frameworks like Cafe, Darknet as well as proprietary Data Summarization. It is able to process offline security videos (mp4 files) as well as real time streams from the security cameras. The analytics is able to perform computer vision tasks such as Object Recognition, Face Recognition, Optical Character Recognition etc. The User gets security alerts having set the exceptions, search with natural queries, get statistics and view video summaries. I have spoken on LDV Vision Summit NY (https://vimeo.com/227930) as well as Alchemist Accelerator, San Francisco (https://vimeo.com/271770757).
AitoeLabs: Custom Deep Learning for Security Video Analytics
4329354
A telecom company with a 100 million users wanted to use customer data to predict key performance indicators like Churn, Customer Segmentation, Social Media Analytics etc. using Machine Learning techniques. These were done to modify marketing campaign in order to retain users increase use of services and grow user base. IMPLEMENTATION: We built a Machine Learning Platform in a Microservice Architecture which pooled data from existing Source Systems like on-boarding forms, company app usage and also the network tower data. We supervised ML models for predicting if a given user will increase or decrease data usage or churn out entirely based on historical data. Having understood this, we segment the customers into categories and determine the churn reason using unsupervised ML and are able to use target marketing to send promotions to the given user before he/she churns so that they will not churn and increase usage.
Telecom Customer Analytics
A telecom company with a 100 million users wanted to use customer data to predict key performance indicators like Churn, Customer Segmentation, Social Media Analytics etc. using Machine Learning techniques. These were done to modify marketing campaign in order to retain users increase use of services and grow user base. IMPLEMENTATION: We built a Machine Learning Platform in a Microservice Architecture which pooled data from existing Source Systems like on-boarding forms, company app usage and also the network tower data. We supervised ML models for predicting if a given user will increase or decrease data usage or churn out entirely based on historical data. Having understood this, we segment the customers into categories and determine the churn reason using unsupervised ML and are able to use target marketing to send promotions to the given user before he/she churns so that they will not churn and increase usage.
Telecom Customer Analytics
A telecom company with a 100 million users wanted to use customer data to predict key performance indicators like Churn, Customer Segmentation, Social Media Analytics etc. using Machine Learning techniques. These were done to modify marketing campaign in order to retain users increase use of services and grow user base. IMPLEMENTATION: We built a Machine Learning Platform in a Microservice Architecture which pooled data from existing Source Systems like on-boarding forms, company app usage and also the network tower data. We supervised ML models for predicting if a given user will increase or decrease data usage or churn out entirely based on historical data. Having understood this, we segment the customers into categories and determine the churn reason using unsupervised ML and are able to use target marketing to send promotions to the given user before he/she churns so that they will not churn and increase usage.
Telecom Customer Analytics
A telecom company with a 100 million users wanted to use customer data to predict key performance indicators like Churn, Customer Segmentation, Social Media Analytics etc. using Machine Learning techniques. These were done to modify marketing campaign in order to retain users increase use of services and grow user base. IMPLEMENTATION: We built a Machine Learning Platform in a Microservice Architecture which pooled data from existing Source Systems like on-boarding forms, company app usage and also the network tower data. We supervised ML models for predicting if a given user will increase or decrease data usage or churn out entirely based on historical data. Having understood this, we segment the customers into categories and determine the churn reason using unsupervised ML and are able to use target marketing to send promotions to the given user before he/she churns so that they will not churn and increase usage.
Telecom Customer Analytics
A telecom company with a 100 million users wanted to use customer data to predict key performance indicators like Churn, Customer Segmentation, Social Media Analytics etc. using Machine Learning techniques. These were done to modify marketing campaign in order to retain users increase use of services and grow user base. IMPLEMENTATION: We built a Machine Learning Platform in a Microservice Architecture which pooled data from existing Source Systems like on-boarding forms, company app usage and also the network tower data. We supervised ML models for predicting if a given user will increase or decrease data usage or churn out entirely based on historical data. Having understood this, we segment the customers into categories and determine the churn reason using unsupervised ML and are able to use target marketing to send promotions to the given user before he/she churns so that they will not churn and increase usage.
Telecom Customer Analytics

Reviews

Changes saved
No reviews to see here!

Experience

Co-Founder & CEO

AitoeLabs
Apr 2016 - Present
Managing a team of 12 Machine Learning and Full Stack Developers. Complete Product Architecture from Computer Vision Engine in C++ to Web APIs in NodeJS to Frontend in AngularJS and ReactJS.

Software Developer

AccionLabs
Sep 2015 - Apr 2016 (7 months, 1 day)
Worked with MEAN Stack (MongoDB, ExpressJS, AngularJS, NodeJS) and deploying Automated RESTful APIs for easy CRUD operations.

Engineering Intern

Tata Consulting Services
Jan 2013 - Feb 2013 (1 month, 1 day)
Distributing requests across heterogeneous servers. Load balancing system for CodeVita competition (a coding competition in India where computer scientists register and compete with each other in coding challenges). The load balancer was responsible for prioritising and allocating the programs submitted by competitors to different servers based on task, compute, cores of server and various other features.

Education

BTech. in Computer Engineering

The Hong Kong University of Science and Technology, Hong Kong 2012 - 2015
(3 years)

Publications

Learning From Less Data

Anurag Sahoo
A special class of subset selection functions naturally model notions of diversity, coverage and representation and they can be used to eliminate redundancy and thus lend themselves well for training data subset selection. link: https://arxiv.org/abs/1805.11191

A Unified Multi-Faceted Video Summarization System

Anurag Sahoo
Research paper on Video Summarization with Deep Learning. This paper addresses automatic summarization and search in visual data comprising of videos, live streams and image collections in a unified manner. In particular, we propose a framework for multi-faceted summarization which extracts key-frames (image summaries), skims (video summaries) and entity summaries (summarization at the level of entities like objects, scenes, humans and faces in the video). link: https://arxiv.org/abs/1704.01466

20 Most Promising Artificial Intelligence Solution Providers of 2018

CIO Review, India
AitoeLabs: High End And Customized Ai Models With Uncompromising Accuracy link: https://artificial-intelligence.cioreviewindia.com/vendor/2018/aitoe_labs

This startup can detect intrusion & make a video searchable

CNBC MoneyControl
The company's Artificial Intelligence product, Newton, can recognize, track objects and indexes them to make the video searchable. link: https://www.moneycontrol.com/news/business/startup/this-startup-can-detect-intrusion-make-a-video-searchable-2324997.html

Contact Anurag S. about your job

Log in to discuss any details over chat.

Verifications

Preferred Freelancer
Identity Verified
Payment Verified
Phone Verified
Email Verified
Facebook Connected

Top Skills

Java
JavaScript
Python
Website Design
Project Management

Browse Similar Freelancers

Java Developers in United States
Java Developers
Javascript Developers
Python Developers

Browse Similar Showcases

Java
JavaScript
Python
Website Design
Previous User Next User
Invite sent successfully!
Thanks! We’ve emailed you a link to claim your free credit.
Something went wrong while sending your email. Please try again.
Freelancer logo US (International) / English Help & Support Freelancer Categories Projects Contests Freelancers Enterprise Membership Preferred Freelancer Program Project Management Local Jobs Photo Anywhere Showcase API for Developers Get Verified Desktop App About About us How it Works Security Investor Sitemap Stories News Team Awards Press Releases Careers Terms Privacy Policy Terms and Conditions Copyright Policy Code of Conduct Fees and Charges Partners Escrow.com Loadshift Warrior Forum Apps Apple App Store logoGoogle Play logo
Copy to clipboard failed, please try again after adjusting your permissions.
Copied to clipboard.
Registered Users Total Jobs Posted
Freelancer ® is a registered Trademark of Freelancer Technology Pty Limited (ACN 142 189 759)
Copyright © 2024 Freelancer Technology Pty Limited (ACN 142 189 759)
Loading preview
Permission granted for Geolocation.
Your login session has expired and you have been logged out. Please log in again.