SUMMARY

An enthusiastic & highly motivated individual having Master degree in Computer Science.Seeking a beginner role to enhance and explore my knowledge in Python and Machine Learning, gained during the Post Graduate Diploma program in last one year.Passionate about learning new technologies and methodologies and possess ability to work under pressure.

KEY SKILLS

TECHNICAL SKILLS

ACADEMIC PROJECT EXPERIENCE

Micro-controller Based Electrical Control System for Smart Home Application using GSM Mobile

WORD SPOTTING USING DTW TECHNIQUE

Sayan Paul

Data Science Enthusiast

+91-912*******

adpfrq@r.postjobfree.com

https://www.linkedin.com/in/saya

paul-092804124/

Kolkata

Machine Learning using Python

NLP Using Python

Deep Learning using Python

Object Oriented Programming using JAVA,C,C++

Hands on experience in Ms-SQL

Languages: Python,JAVA,C++, C, MS-SQL,

Packages: Scikit-Learn, Numpy, Scipy, Pandas, NLTK, BeautifulSoup, Matplotlib,,Tensorflow,Keras,TextBlob, Seaborn,Jupyter Notebook

Machine Learning: Linear/Logistic Regression, SVM, Random Forests, Clustering In this project we have developed a simple and reliable GSM based communication system to control household appliances that are far away from the user by making a call. The mobile which is connected to the system is kept in

"Auto Answering" mode. Using DTMF technology any devices an be switched and controlled by pressing the correspondence buttons during the course of a call. These tones are then decoded by using a DTMF decoder and corresponding devices are chosen .

The objective of this project is to enable the users to remotely control their home appliances and systems using a cell phone based interfaces.The cell phone based interface at home (control unit) would relay the commands to a micro- controller that would perform the required action/function. For the transition from traditional to digital libraries, the large number of handwritten manuscripts that exist pose a great challenge.Easy Access to such collection requires an index,which is currently created manually at great cost. Because automatic handwriting recognizer fail on historical manuscripts,the word spotting technique has been developed. the words in a collection are matched as images and grouped into the clusters which contain all instances of the same word. By annotating " interesting" clusters, an index that links words to the locations where they occur can be built automatically.

Due to the noise in historical documents,selecting the right features for matching word is crucial.We analysed a range of features suitable for matching words using Dynamic Type Warping(DTW), which aligns and compares sets of features extracted from two images.Each feature's individual performances waas measured on a test set.With an average precision of 72%,a combination of features outperforms competing techniques in speed and precision. ADDITIONAL PROJECT

CONSUMER COMPLAINT RESOLUTION

Data Collection

Data Wrangling

Data Visualization

Python Machine Learning - Clustering & Classification EDUCATION

Aug '16- Jun '18

Ratulia Teahers' Training Institute Panskura, WB,IN B.Ed

Aug '14- Jun '16

Vidyasagar University Medinipur, WB,IN

MSc with First Class (73.75%)

Computer Science

Jul '11- May '14

Mahishadal Raj College Mahishadal, WB,IN

BSc with First Class(62.9%)

Computer Science

ADDITIONAL INFORMATION

CERTIFICATIONS

Conducted extensive research on kaggle

Cleaned, merged and manipulated data-sets and conducted feature engineering using Pandas Created various charts in Jupyter Notebook using Matplotlib to perform a preliminary analysis on the collected data Applied various machine learning techniques. We used some Classification algorithm for predicting and comparing the accuracy (viz. - Random Forest, Decision Tree,Logistic Regression etc.) Languages: English, Bengali, Hindi

PGP in Data Science IIT Guwahati in collaboration with Edureka nov'19 - Nov '20

Contact this candidate