Sambit Pritam

admcqm@r.postjobfree.com

+91-891*******

Looking for Data Science/Artificial intelligence/Deep learning/Computer vision/Machine learning jobs/projects only

Education

Qualification Board/University Year Percentage/CGPA B.Tech(ME) Gandhi Institute of Engineering and

Technology, Gunupur

2012-2016 7.85

C.H.S.E. (12th) Pratik Science College, Bhubaneswar 2012 78% B.S.E. (10th) Dharmasala Baneepeetha 2010 83%

Work Experience

System Engineer at Tata Consultancy Services Jan 2017 -Present o Project Title: Original Equipment Manufacturer October 2017 – June 2021 o Role: Testing Engineer and Testing Analyst (Microsoft Contract employee) o Tools & Frameworks: Windows Testing Technology, Microsoft Internal Test Automation tool, Digital Operation Center, SAP MST, SAP OER, Postman o Key Contributions

Manual testing in Digital Operating Center(DOC).

Have handled complete E2E functionality for long time as Testing Analyst and received client appreciation for the work.

Documented the complete E2E functionality and flow and have received client appreciation for the documentation as well.

Have prepared transition plans and documents for several internal tools and frameworks

Have worked on various reports generated during the E2E flow and have documented the complete process of verification. Professional Summary

Experience in Machine Learning algorithms like Linear Regression, Logistic Regression, KNN algorithm, Support Vector Machine (SVM), Decision Tree, Random Forest, AdaBoost, XGBoost, K-Means Clustering.

Skilled in Minimizing the cost function-based algorithms like: Gradient Descent, Stochastic Gradient Descent, Mini-Batch Gradient descent.

Skilled in libraries like Numpy, Pandas, Matplotlib, Seaborn, Scikit Learn, Keras.

Data Visualization techniques with help of Matplotlib, Seaborn.

Skilled in Feature Engineering using Python: Feature Selection, Missing Value handling, Outlier’s handling, Data transformation, Describing the data using Python libraries like Numpy, Pandas and Matplotlib

Good knowledge of Deep Learning (DL) and hands-on with Neural Network Architecture, Loss Function, Cost Function, Optimizers, Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), LSTM, and BERT.

Basic Understanding of Natural Language Processing (NLP) techniques like tokenization, stemming, lemmatization, Text Analysis, Matrix TFIDF and word2vec.

Basic understanding of Computer Vision Techniques like Image pre-processing, Image Segmentation, Object Detection, Object Recognition

Good Knowledge of linear algebra and dimensionality reduction algorithms like PCA

Hands on Experience in working with Dockers, Containers, GPU, and multiple GPU environment.

Experience of using Django and Flask Framework.

Skills

Programming languages – Python, C

Python libraries – Jupyter Notebook, Numpy, Pandas, Matplotlib, Scikit-Learn, Seaborn, OpenCV, TensorFlow, Keras.

Computational skills- Machine learning, Deep learning, OpenCV, NLP.

Machine Learning Algorithms: Linear Regression, logistic Regression, KNN, Decision Tree, Random Forest, SVM, PCA, Grid SearchCV,K Means Clustering, Pipelines.

Deep Learning: ANN, CNN, Autoencoders, Architectures (AlexNet, VGG16, InceptionNet, MobileNet), Object detection and Localiation algorithms like Sliding Window Detection, Yolo Algorithm, GAN, Mixed Precision training.

Visualization Tools and Libraries: Basic understanding of Matplotlib and Seaborn

Others: Dockers, Kubernetes

Professional Certification and Courses

Advance Data science course with hands-on Google-Colab from Netzwerk Data Science Academy as ISO certified institute- year 2021

Certificate for attending the Online Workshop on Accelerated Data Science - February 2021 Data Science Projects

Project 1: Seoul Bike Demand (end -to-end)

Description • Currently Rental bikes are introduced in many urban cities for the enhancement of mobility comfort. It is important to make the rental bike available and accessible to the public at the right time as it lessens the waiting time. Eventually, providing the city with a stable supply of rental bikes becomes a major concern. The crucial part is the prediction of bike count required at each hour for the stable supply of rental bikes. Data used include weather information (Temperature, Humidity, Windspeed, Visibility, Dewpoint, Solar radiation, Snowfall, Rainfall), the number of bikes rented per hour and date information.

• The objective is to calculate the number of bikes required each hour to provide a smooth and stable supply of rental bikes.

• You can find the link here

Tools and

Technologies

used

Python, Numpy, Pandas, Seaborn, Matplotlib, Tensorflow, Pickle, Machine Learning Algorithms, Jupyter Notebook (Anaconda 3) GitHub link https://github.com/sambit-0007/Seoul-Bike-Demand Project 2: CREDIT CARD FRAUD DETECTION USING ANN

Description • Detecting fraud transactions is of great importance for any credit card company.

• It is important to detect potential frauds so that customers are not charged for items that they did not purchase.

• The objective is to use a Deep Learning (Artificial Neural Network) algorithm to detect whether the transaction is fraud or not Tools and

Technologies

used

Python, Numpy, Pandas, Seaborn, Matplotlib, sklearn, Tensorflow, Deep Learning algorithm (ANN), Jupyter Notebook (Anaconda 3)

GitHub link https://github.com/sambit-0007/Credit-Card-Fraud-Detection-using-ANN Project 3: Horse-Breed-Classification-deployed-in-Android Studio Description • The objective is to find a Deep Learning Classifier algorithm

(Convolutional Neural Network) to detect breed of the horse presented in the image.

• I have built a CNN model to train which then classifies the images in 7 categories.

• Once the model is ready to predict, I have deployed it in Android Studio.

Tools and

Technologies

used

Python, Numpy, Pandas, Seaborn, Matplotlib, sklearn, Tensorflow, Deep Learning algorithm (ANN), Jupyter Notebook (Anaconda 3), Android Studio, TFlite GitHub link https://github.com/sambit-0007/Horse-Breed-Classification-deployed-in-Android Project 4: Fake News Detection using NLP

Description • The objective is to detect whether the news is fake or not by using Recurrent Neural Networks and NLP.

• Perform NLP to convert the news title to machine understandable language and build a Neural Network to train the data and predict the accuracy using test data.

Tools and

Technologies

used

Python, Numpy, Pandas, sklearn, Tensorflow, Deep Learning algorithm (RNN), Natural Language Processing (NLP), Jupyter Notebook (Anaconda 3) GitHub link https://github.com/sambit-0007/Fake-News-Detection-end-to-end Project 5: Face Mask Detection using CNN and OpenCV Description • The objective is to detect whether a person is wearing a face mask or not by using CNN and OpenCV.

• The dataset used for training the model contains 7553 RGB images in 2 folders as with mask and without mask.

• Once the model is trained using CNN, I have used OpenCV to detect whether the person is wearing a mask or not.

Tools and

Technologies

used

Python, Numpy, Pandas, Matplotlib, sklearn, Tensorflow, Deep Learning algorithm (CNN), OpenCV, Jupyter Notebook (Anaconda 3) GitHub link https://github.com/sambit-0007/Face-Mask-Detection Project 6: Sentiment Analysis using NLP

Description • The objective is to find a Deep Learning Classifier algorithm (Recurrent Neural Network and NLP) to detect the sentiments of the sentences.

• This repository contains dataset for 40000 IMDB statements and each sentence contain more than 200 words and the model for recognizing the label as positive or negative.

Tools and

Technologies

used

Python, Numpy, Pandas, sklearn, Tensorflow, Deep Learning algorithm (RNN), Natural Language Processing (NLP), Jupyter Notebook (Anaconda 3) GitHub link https://github.com/sambit-0007/Sentiment-Analysis Project 7: BANK NOTE AUTHENTICATION

Description • To detect if the Bank note is original or fake.

• Banknotes are one of the most important assets of a country. Some miscreants introduce fake notes which bear a resemblance to original note to create discrepancies of the money in the financial market. It is difficult for humans to tell true and fake banknotes apart especially because they have a lot of similar features.

• Fake notes are created with precision, hence there is need for an efficient algorithm which accurately predicts whether a banknote is genuine or not.

• In this Supervised machine learning algorithms such as Decision Tree Classifier algorithms is used for differentiating genuine banknotes from fake ones.

Tools and

Technologies

used

Python, Numpy, Pandas, sklearn, Tensorflow, Deep Learning algorithm (RNN), Natural Language Processing (NLP), Jupyter Notebook (Anaconda 3) GitHub link https://github.com/sambit-0007/Bank-Note-Authentication Project 8: Covid_Disease_Detection

Description • Covid Detection is of great importance for current situation where we are fighting with COVID on a larger scale.

• It is important to detect potential Covid patience so that those COVID patients can be kept separately and can provided proper attention.

• The objective is to use a Deep Learning (Concurrent Neural Network) algorithm on X-ray images to detect whether the person is a COVID Patient or not.

• Pros: More time saving; less expensive; easy to operate Tools and

Technologies

used

Python, Numpy, Pandas, Seaborn, Matplotlib, sklearn, Tensorflow, Deep Learning algorithm (CNN), Jupyter Notebook (Anaconda 3)

GitHub link https://github.com/sambit-0007/Covid_Disease_Detection Project 9: Skin Cancer Detection Using CNN

Description • The objective is to find a Deep Learning Classifier algorithm

(Convolutional Neural Network) to detect whether the image is of class benign or malignant.

• Build a CNN model to train which then classifies the images in 2 categories.

Tools and

Technologies

used

Python, Numpy, Pandas, Seaborn, Matplotlib, sklearn, Tensorflow, Deep Learning algorithm (CNN), Jupyter Notebook (Anaconda 3)

GitHub link https://github.com/sambit-0007/Skin-Cancer-Detection-using-CNN Achievements & Extra-Curricular

Attended workshops on “Microsoft Azure Virtual Training Day: AI Fundamentals”.

Attended workshop on “Power BI Training Program”.

Received many client appreciations (Microsoft)

Achieved award for cricket, football, badminton and carrom competition at school, college, and corporate level

Has got lots of appreciation for participation in Hyderabad corporate leagues

Interpersonal Abilities: Problem Solving, Decision Making, Excellent Communication, Strong interpersonal skills

Leisure Interest

Playing football

Reading blogs

Contact this candidate