profile-img
About
• Experienced in ML, Classifiers, Regression, Clustering, Data Mining, NLP, Recommender Systems • Expert on Deep Learning (CNN, RNN, LSTM) & deep learning frameworks (TensorFlow, Keras) • Currently working as Data Scientist at Wipro R&D • Worked as a Data Scientist at Charmboard • Worked as a Software Developer at Directi on the product Zeta
1:1 Live Courses
Coming Soon!
Experience
Education
education-img
Indian Institute of Engineering Science and Technology (IIEST), ShibpurMaster Of Technology (M.Tech/M.E), Computer Science2016
education-img
Government College of Engineering and Textile Technology, Berhampore (Berhampore)Bachelor of Technology (B.Tech), Computer Science2013
Skills
Python
React.js Framework
Machine Learning
Data Science and AI
Java
Accomplishments
Certifications
Improving Deep Neural Networks  
Issued : Feb 2019
Structuring Machine Learning Projects  
Issued : Feb 2019
Sequence Models  
Issued : Feb 2019
Convolution Neural Networks  
Issued : Feb 2019
Neural Networks and Deep Learning  
Issued : Jan 2019
Projects
MetLife Web Application Development  
Completion Date : Jul 2016
Technology: Java, ReactJS, Loadash – modern JavaScript utility library, Radis Client. Description: Developing Metlife web application. Role & Responsibilities: • Understand the assigned story and code development. • Create new React component. • Develop webpage based on wireframe.
Fuzzy Logic Based Optimized Power Scheduling Scheme for Home Automation  
Completion Date : May 2016
Technology: Fuzzy Logic, Artificial Intelligent, Algorithms Description: The current energy crisis has required significant energy reduction in all areas. The energy consumption in home areas has increased as more home appliances are installed. Energy saving and renewable energy sources are considered as methods of solving home energy problem. A home has two parts concerning energy: consumption and generation. Numerous home appliances and lights are in the energy consumption part. Renewable energies such as solar and wind energies are in the energy generation part. Because a home consumes and generates energy. A control device like a home server needs to monitor and control both energy consumption and energy generation to minimize the energy cost. In this paper, we have developed a system such that it will be capable to keep a track of each and every appliance in the home and the energy consumption parameters of each individual appliance will be sent to gateway where an intelligent fuzzy logic based scheduling algorithm will be running to manage all the appliances as per user requirements.
Dynamic Congestion Analysis for Better Traffic Management Using Social Media(FACEBOOK)  
Completion Date : Feb 2016
Technology: Facebook php sdk, Machine Learning, K-means Clustering, Data Mining. Description: Social media has emerged as an imperative tool for addressing many real-life problems in an innovative way in recent years. Traffic management is a demanding problem for any populous city in the world. In the current paper, we explore how the dynamic data from social media can be employed for continuous traffic monitoring of cities in a better way. To accomplish this, congestion analysis and clustering of congested areas are performed. With the term congestion, we denote co-gatherings in an area for two different occasions within a defined time interval. While doing so, we introduce a novel measure for quantifying the congestion of different areas in a city. Subsequently, association rule mining is applied to find out the association between congested roads. To our surprise, we observe a major impact of various gatherings on the disorder of traffic control in many cities. With additional analyses, we gain some new insights about the overall status of traffic quality in India from the temporal analysis of data.
Development of Bengali Text Synthesis System using Support Vector Machine.  
Completion Date : Jun 2013
descriptionTechnology: Algorithm, Machine Learning, SVM. Description: Objective was to develop a Bengali Text synthesis system which can help visually impaired person to read daily newspapers available in the market as well as ink printed text books. Basically, Visually Impaired person have to rely on books printed by braille characters. We are taking snap of a page, converting the image to corresponding sequence of text. Then covert the text to speech so that a visually impaired person can listen to the text written on ink printed paper.
Publications
Dynamic Congestion Analysis for Better Traffic Management using Social Media (FACEBOOK)  
Publication Date : May 2016
Languages
Bengali
English
Hindi
About
• Experienced in ML, Classifiers, Regression, Clustering, Data Mining, NLP, Recommender Systems • Expert on Deep Learning (CNN, RNN, LSTM) & deep learning frameworks (TensorFlow, Keras) • Currently working as Data Scientist at Wipro R&D • Worked as a Data Scientist at Charmboard • Worked as a Software Developer at Directi on the product Zeta

Reviews