Vijay (RID : 474kwbrsbmh)

designation   ML Engineer

location   Location : Ahmedabad, India

experience   Experience : 2 Year

rate   Rate: $11 / Hourly

Availability   Availability : Immediate

Work From   Work From : Offsite

designation   Category : Information Technology & Services

Last Active: 30+ Days ago
Shortlisted : 0
Total Views : 6
Key Skills
Python DeepLearning NLP Statistics ML Algorithms & Libraries DataModeling DataCleansing
  • Motivated software developer having 2 years of experience in software development, data science, and web development technologies. Passionate about building models that fix problems. Relevant skills include machine learning, problem-solving, programming, and creative thinking.


Face Recognition

● Using various techniques to count and detect the number of Faces from the image, and then perform Face Recognition using Deep Learning

Techniques such as Face Net (Google pre-trained model) and Transfer Learning.

● Tools and Technologies: OpenCV, MTCN, and TensorFlow.

Legal document’s classification using ML & DL

● Natural Language Processing (NLP) based project, using OCR tool user can upload legal documents in Image (JPG, JPEG, PNG), Pdf and

Docx format, then text classifiers can automatically analyze text and then assign a set of pre-defined tags or categories based on its content. Text Classification we have proposed Machine Learning and Deep Learning approaches. For the Machine Learning approach KNN, SVC & Naïve Bayes is used while the BERT model is used for Deep

Learning approach.

● Tools and Technologies: Pandas, NumPy, OpenCV, Tensorflow, scikitlearn, Django, Nodejs.

Multiple Emotion Recognition in Gujarati using Natural Language Processing

● Generally in NLP positive, negative, and neutral reactions have various datasets. For this use, a dataset from Kaggle is classified into six different emotions, viz. anger, fear, joy, love, sadness & surprise. The dataset is in the English language & contains 20000 labeled sentences. As our aim was to recognize emotions in the Gujarati language, we translated the same dataset into Gujarati, with the assumption that emotions do not change. The translated dataset was cleaned manually. The dataset created for the Gujarati language has 19600 labeled sentences.

● Tools and Technologies: Translate API of AWS, Tensorflow, scikitlearn, NLTK

Visual Question Answering

● It is a simple project for 2d shapes. Using Computer vision to detect Geometric shapes and using Deep Learning (Bag of words & RNN) we ask some simple Questions to the image and it will predict the correct answer based on which question is asked.

● Tools and Technologies: OpenCV, Tensorflow, NTKL, Nodejs Medical Chatbot

● Created a medical chatbot for medical emergencies which is created using dialog flow and RASA, which is integrated with different social platforms like telegram, messenger, WhatsApp.

Matching Resources
My Project History & Feedbacks
Copyright : 2022 – OnBenchMark All Right Reserved.

stuff goes in here!