Kuntal Kumar Pal

Kuntal Kumar Pal

Machine Learning Enthusiast

Download CV

About Me

"Never give in. Never give in. Never, never, never, never - in nothing, great or small, large or petty - never give in, except to convictions of honour and good sense" - Winston Churchill

Hi, I am an undergraduate from Jadavpur University, Kolkata and have a masters degree from National Institute of Technology, Calicut. I am a machine learning enthusiast. I constantly look to gain knowledge and apply my industrial experience and expertise to solve problems, improving and optimizing the conventional process.

My interests include machine learning, pattern recognition, computer vision, natural language processing and data analytics. Currently, I am interested to pursue Ph.D. in machine learning.

Latest Projects

project name

Object Classification

Worked with Dr. Sudeep K.S. Assistant Professor, Department of Computer Science & Engineering, NIT Calicut.

Here object classification have been done using a number of techniques on various datasets like CIFAR10, CIFAR100 and PASCAL VOC 2012 The classification techniques include classifiers like Nearest Neighbor, k-Nearest Neighbor, simple Neural Networks and Convolutional Neural Networks. The impact of multiple activation functions on classification have been studied along with a number of image preprocessing techniques like PCA, mean-normalization, standardization.

project name

Component Based Image Approximation Search

Worked with Dr. Sudeep K.S. Assistant Professor, Department of Computer Science & Engineering, NIT Calicut.

Most of the reverse image searching is based on the image search as a whole. But it does not always catch the information regarding how inter-related two images are, based on their contents. A picture having a number of birds is far more related to a picture having a few birds and an animal than a third picture with all cars. So here a different approach has been used to capture this relation by matching the component of the images. A given composite image (with multiple objects) is searched among a set of other composite images and ordered based on how closely related it is with the images of the set. The top-most image in the ordering indicates the closest image to the given image. For component detection, selective search with fast non-maximal suppression has been used with ZCA normalization. The Convolutional neural network (CNN) have been used for the identification of the components. This can be used to find similarity among images which is difficult to find in conventional methods.

project name

Head Pose Detection Using Histogram of Gradient

This project uses Histogram of Gradient(HOG) features to detect and classify faces in Images and Video. The motivation for this project is the driver safety program. Here HOG features have been used along with SVM to classify images of Pointing04 dataset into different head position classes. The classifier has been evaluated using error-rate, precision, recall, specificity, prevalence and F1-scores. This is a useful part of driver head position identification. For the second part of the project the head position of an individual have been tracked throughout videos using the hog features.

Other Projects

Detection and Decision of Fusion in Wireless Sensor Networks

The project focussed on the creation of a simulation interface for cluster-based detection of an event with virtual sensors, deployed randomly over a specified area. It also shows the fusion nodes which detects the event and which takes the responsibility for the transmission of the decision to a base station. A few features have been added to the interface which includes, controlling mobility of the sensors with options of speed variance, transmission range and area selection and number of virtual sensors being deployed.

Auto Deployment, Delivery and Version Tracker Tool

As an internal project for Tata Consultancy Service(TCS), developed a platform that has the ability to keep track of all the Data Definition Language(DDL) changes and auto-generation and delivery of deployment scripts in any database schema. This has reduced the Database Administrator's responsibilities and thereby has removed tedious work and manual errors. It has also significantly cut down the delivery time to a few minutes from a number of hours.

  • Auto-backup and delivery of all objects of any given oracle database schema.
  • Can track version of each DDL changes and can provide change log for any given version.
  • Helps in deployment and schema preperation for any given version.

Work Experience

Engineer I - Cavium Networks, Bangalore (2016 - Present)

Created a shell based platform to help configure the Software Abstraction Interface(SAI) layer of the Open Compute Project and its integration with Xpliants' software development kit layer. This platform is extensively used by QA team for chip configuration and issue validation. Working on the management of each block of the Software Defined Engine of flexible and fully programmable Xpliant network switches. Parallel with the block manager, working on changes required for various versions of Xpliant chips in Xpliant proprietary compiler. Also worked on generation of meaningful highlights of a delivery by extracting information about bugs fixed and new features incorporated from the git comments.

Skills and Tools Used : Python, Unix, C, C++, Java, Git, Jira.

Teaching Assistant : Database Laboratory - National Institute of Technology, Calicut (2015 - 2016)

I was in charge of developing laboratory practice questions for B.Tech 3rd year students. Other responsibilities included evalutaion of bi-weekly assignments, plagiarism checks and conduction of monthly examinations. I also provided guidance and assistance to the students in understanding basic concepts. As a part of final evaluation panel, I have taken the viva voce examination of the students.

Teaching Assistant : Data-Structure Laboratory - National Institute of Technology, Calicut (2015 - 2016)

In this laboratory, I was in charge of developing practice questions and model answers for B.Tech 2nd year students. I evaluated bi-weekly assignments and provided guidance and assistance to the students. I have taken the viva voce examination of the students as a part of final evaluation panel.

IT Analyst - Tata Consultancy Services, Kolkata (2009 - 2014)

Worked on data migration Project in Diligenta Transformation Programme for UK Insurance Domain. It aimed at data migration of insurance policies of very old legacy systems to a much advanced insurance platform, TCS BaNCs, providing customers with enhanced online features keeping there underlying data intact. The responsibilities of work involved data analysis and migration strategy formulation, cleansing data, developing and unit testing data migration codes, performance tuning, post migration data reconcillation, handling post-production issues and conducting initiation program for new-joiness. Successfully completed the migration of 4 insurance system of UK to BaNCs during the tenure with minimal bugs. Developed an automated process which can take schema backups, keep metadata changes corresponding to all version, can revert to metadata of any particular version and deliver the script for deployment team.

Skills and Tools Used : Oracle 11g, Oracle Warehouse Builder, Unix, PL/SQL, Bugzilla.